cancel(name, body=None, x__xgafv=None)

Starts asynchronous cancellation on a long-running DlpJob. The server makes a best effort to cancel the DlpJob, but success is not guaranteed. See https://cloud.google.com/sensitive-data-protection/docs/inspecting-storage and https://cloud.google.com/sensitive-data-protection/docs/compute-risk-analysis to learn more.

Args:
  name: string, Required. The name of the DlpJob resource to be cancelled. (required)
  body: object, The request body.
    The object takes the form of:

{ # The request message for canceling a DLP job.
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); }
}

close()

Close httplib2 connections.

create(parent, body=None, x__xgafv=None)

Creates a new job to inspect storage or calculate risk metrics. See https://cloud.google.com/sensitive-data-protection/docs/inspecting-storage and https://cloud.google.com/sensitive-data-protection/docs/compute-risk-analysis to learn more. When no InfoTypes or CustomInfoTypes are specified in inspect jobs, the system will automatically choose what detectors to run. By default this may be all types, but may change over time as detectors are updated.

Args:
parent: string, Required. Parent resource name. The format of this value varies depending on whether you have [specified a processing location](https://cloud.google.com/sensitive-data-protection/docs/specifying-location): + Projects scope, location specified: `projects/{project_id}/locations/{location_id}` + Projects scope, no location specified (defaults to global): `projects/{project_id}` The following example `parent` string specifies a parent project with the identifier `example-project`, and specifies the `europe-west3` location for processing data: parent=projects/example-project/locations/europe-west3 (required)
body: object, The request body.
The object takes the form of:

{ # Request message for CreateDlpJobRequest. Used to initiate long running jobs such as calculating risk metrics or inspecting Google Cloud Storage.
"inspectJob": { # Controls what and how to inspect for findings. # An inspection job scans a storage repository for InfoTypes.
"actions": [ # Actions to execute at the completion of the job.
{ # A task to execute on the completion of a job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-actions to learn more.
"deidentify": { # Create a de-identified copy of the requested table or files. A TransformationDetail will be created for each transformation. If any rows in BigQuery are skipped during de-identification (transformation errors or row size exceeds BigQuery insert API limits) they are placed in the failure output table. If the original row exceeds the BigQuery insert API limit it will be truncated when written to the failure output table. The failure output table can be set in the action.deidentify.output.big_query_output.deidentified_failure_output_table field, if no table is set, a table will be automatically created in the same project and dataset as the original table. Compatible with: Inspect # Create a de-identified copy of the input data.
"cloudStorageOutput": "A String", # Required. User settable Cloud Storage bucket and folders to store de-identified files. This field must be set for Cloud Storage deidentification. The output Cloud Storage bucket must be different from the input bucket. De-identified files will overwrite files in the output path. Form of: gs://bucket/folder/ or gs://bucket
"fileTypesToTransform": [ # List of user-specified file type groups to transform. If specified, only the files with these file types will be transformed. If empty, all supported files will be transformed. Supported types may be automatically added over time. If a file type is set in this field that isn't supported by the Deidentify action then the job will fail and will not be successfully created/started. Currently the only file types supported are: IMAGES, TEXT_FILES, CSV, TSV.
"A String",
],
"transformationConfig": { # User specified templates and configs for how to deidentify structured, unstructures, and image files. User must provide either a unstructured deidentify template or at least one redact image config. # User specified deidentify templates and configs for structured, unstructured, and image files.
"deidentifyTemplate": "A String", # De-identify template. If this template is specified, it will serve as the default de-identify template. This template cannot contain `record_transformations` since it can be used for unstructured content such as free-form text files. If this template is not set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify unstructured content.
"imageRedactTemplate": "A String", # Image redact template. If this template is specified, it will serve as the de-identify template for images. If this template is not set, all findings in the image will be redacted with a black box.
"structuredDeidentifyTemplate": "A String", # Structured de-identify template. If this template is specified, it will serve as the de-identify template for structured content such as delimited files and tables. If this template is not set but the `deidentify_template` is set, then `deidentify_template` will also apply to the structured content. If neither template is set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify structured content.
},
"transformationDetailsStorageConfig": { # Config for storing transformation details. # Config for storing transformation details. This is separate from the de-identified content, and contains metadata about the successful transformations and/or failures that occurred while de-identifying. This needs to be set in order for users to access information about the status of each transformation (see TransformationDetails message for more information about what is noted).
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # The BigQuery table in which to store the output. This may be an existing table or in a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_transformation_details_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"jobNotificationEmails": { # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts). # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts).
},
"pubSub": { # Publish a message into a given Pub/Sub topic when DlpJob has completed. The message contains a single field, `DlpJobName`, which is equal to the finished job's [`DlpJob.name`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/projects.dlpJobs#DlpJob). Compatible with: Inspect, Risk # Publish a notification to a Pub/Sub topic.
"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given publishing access rights to the DLP API service account executing the long running DlpJob sending the notifications. Format is projects/{project}/topics/{topic}.
},
"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Data Catalog. In Data Catalog, tag templates are applied to the resource that Cloud DLP scanned. Data Catalog tag templates are stored in the same project and region where the BigQuery table exists. For Cloud DLP to create and apply the tag template, the Cloud DLP service agent must have the `roles/datacatalog.tagTemplateOwner` permission on the project. The tag template contains fields summarizing the results of the DlpJob. Any field values previously written by another DlpJob are deleted. InfoType naming patterns are strictly enforced when using this feature. Findings are persisted in Data Catalog storage and are governed by service-specific policies for Data Catalog. For more information, see [Service Specific Terms](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. This action is allowed only if all resources being scanned are BigQuery tables. Compatible with: Inspect # Publish findings to Cloud Datahub.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to [Security Command Center](https://cloud.google.com/security-command-center). This action is available for only projects that belong to an organization. This action publishes the count of finding instances and their infoTypes. The summary of findings are persisted in Security Command Center and are governed by [service-specific policies for Security Command Center](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. Compatible with: Inspect # Publish summary to Cloud Security Command Center (Alpha).
},
"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This will publish a metric to stack driver on each infotype requested and how many findings were found for it. CustomDetectors will be bucketed as 'Custom' under the Stackdriver label 'info_type'. # Enable Stackdriver metric dlp.googleapis.com/finding_count.
},
"saveFindings": { # If set, the detailed findings will be persisted to the specified OutputStorageConfig. Only a single instance of this action can be specified. Compatible with: Inspect, Risk # Save resulting findings in a provided location.
"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only used for Inspect and must be unspecified for Risk jobs. Columns are derived from the `Finding` object. If appending to an existing table, any columns from the predefined schema that are missing will be added. No columns in the existing table will be deleted. If unspecified, then all available columns will be used for a new table or an (existing) table with no schema, and no changes will be made to an existing table that has a schema. Only for use with external storage.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Store findings in an existing table or a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details. For Inspect, each column in an existing output table must have the same name, type, and mode of a field in the `Finding` object. For Risk, an existing output table should be the output of a previous Risk analysis job run on the same source table, with the same privacy metric and quasi-identifiers. Risk jobs that analyze the same table but compute a different privacy metric, or use different sets of quasi-identifiers, cannot store their results in the same table.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
},
],
"inspectConfig": { # Configuration description of the scanning process. When used with redactContent only info_types and min_likelihood are currently used. # How and what to scan for.
"contentOptions": [ # Deprecated and unused.
"A String",
],
"customInfoTypes": [ # CustomInfoTypes provided by the user. See https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes to learn more.
{ # Custom information type provided by the user. Used to find domain-specific sensitive information configurable to the data in question.
"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. Rules are applied in order that they are specified. Not supported for the `surrogate_type` CustomInfoType.
{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a `CustomInfoType` to alter behavior under certain circumstances, depending on the specific details of the rule. Not supported for the `surrogate_type` custom infoType.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "$\d{3}$ \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "$xxx$", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # A list of phrases to detect as a CustomInfoType.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding to be returned. It still can be used for rules matching.
"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in infoType, when the name matches one of existing infoTypes and that infoType is specified in `InspectContent.info_types` field. Specifying the latter adds findings to the one detected by the system. If built-in info type is not specified in `InspectContent.info_types` list then the name is treated as a custom info type.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be altered by a detection rule if the finding meets the criteria specified by the rule. Defaults to `VERY_LIKELY` if not specified.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Sensitivity for this CustomInfoType. If this CustomInfoType extends an existing InfoType, the sensitivity here will take precedence over that of the original InfoType. If unset for a CustomInfoType, it will default to HIGH. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in `InspectDataSource`. Not currently supported in `InspectContent`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for inspection was created. Output-only field, populated by the system.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example `organizations/433245324/storedInfoTypes/432452342` or `projects/project-id/storedInfoTypes/432452342`.
},
"surrogateType": { # Message for detecting output from deidentification transformations such as [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). These types of transformations are those that perform pseudonymization, thereby producing a "surrogate" as output. This should be used in conjunction with a field on the transformation such as `surrogate_info_type`. This CustomInfoType does not support the use of `detection_rules`. # Message for detecting output from deidentification transformations that support reversing.
},
},
],
"excludeInfoTypes": True or False, # When true, excludes type information of the findings. This is not used for data profiling.
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is included in the response; see Finding.quote. This is not used for data profiling.
"infoTypes": [ # Restricts what info_types to look for. The values must correspond to InfoType values returned by ListInfoTypes or listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference. When no InfoTypes or CustomInfoTypes are specified in a request, the system may automatically choose a default list of detectors to run, which may change over time. If you need precise control and predictability as to what detectors are run you should specify specific InfoTypes listed in the reference, otherwise a default list will be used, which may change over time.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"limits": { # Configuration to control the number of findings returned for inspection. This is not used for de-identification or data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. # Configuration to control the number of findings returned. This is not used for data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. When set within an InspectJobConfig, the specified maximum values aren't hard limits. If an inspection job reaches these limits, the job ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than these maximum values.
"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
{ # Max findings configuration per infoType, per content item or long running DlpJob.
"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per info_type should be provided. If InfoTypeLimit does not have an info_type, the DLP API applies the limit against all info_types that are found but not specified in another InfoTypeLimit.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that are returned for each item scanned. When set within an InspectContentRequest, this field is ignored. This value isn't a hard limit. If the number of findings for an item reaches this limit, the inspection of that item ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns for the item can be multiple times higher than this value.
"maxFindingsPerRequest": 42, # Max number of findings that are returned per request or job. If you set this field in an InspectContentRequest, the resulting maximum value is the value that you set or 3,000, whichever is lower. This value isn't a hard limit. If an inspection reaches this limit, the inspection ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than this value.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. The default is POSSIBLE. In general, the highest likelihood setting yields the fewest findings in results and the lowest chance of a false positive. For more information, see [Match likelihood](https://cloud.google.com/sensitive-data-protection/docs/likelihood).
"minLikelihoodPerInfoType": [ # Minimum likelihood per infotype. For each infotype, a user can specify a minimum likelihood. The system only returns a finding if its likelihood is above this threshold. If this field is not set, the system uses the InspectConfig min_likelihood.
{ # Configuration for setting a minimum likelihood per infotype. Used to customize the minimum likelihood level for specific infotypes in the request. For example, use this if you want to lower the precision for PERSON_NAME without lowering the precision for the other infotypes in the request.
"infoType": { # Type of information detected by the API. # Type of information the likelihood threshold applies to. Only one likelihood per info_type should be provided. If InfoTypeLikelihood does not have an info_type, the configuration fails.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. This field is required or else the configuration fails.
},
],
"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. Exclusion rules, contained in the set are executed in the end, other rules are executed in the order they are specified for each info type.
{ # Rule set for modifying a set of infoTypes to alter behavior under certain circumstances, depending on the specific details of the rules within the set.
"infoTypes": [ # List of infoTypes this rule set is applied to.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
{ # A single inspection rule to be applied to infoTypes, specified in `InspectionRuleSet`.
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in `InspectionRuleSet` are removed from results. # Exclusion rule.
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # Dictionary which defines the rule.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"excludeByHotword": { # The rule to exclude findings based on a hotword. For record inspection of tables, column names are considered hotwords. An example of this is to exclude a finding if it belongs to a BigQuery column that matches a specific pattern. # Drop if the hotword rule is contained in the proximate context. For tabular data, the context includes the column name.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The windowBefore property in proximity should be set to 1 if the hotword needs to be included in a column header.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
"excludeInfoTypes": { # List of excluded infoTypes. # Set of infoTypes for which findings would affect this rule.
"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or contained within with a finding of an infoType from this list. For example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and `exclusion_rule` containing `exclude_info_types.info_types` with "EMAIL_ADDRESS" the phone number findings are dropped if they overlap with EMAIL_ADDRESS finding. That leads to "555-222-2222@example.org" to generate only a single finding, namely email address.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
},
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "$\d{3}$ \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "$xxx$", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
},
],
},
"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig. `inspect_config` will be merged into the values persisted as part of the template.
"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
"excludedFields": [ # References to fields excluded from scanning. This allows you to skip inspection of entire columns which you know have no findings. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When `actions.saveFindings.outputConfig.table` is specified, the values of columns specified here are available in the output table under `location.content_locations.record_location.record_key.id_values`. Nested fields such as `person.birthdate.year` are allowed.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"includedFields": [ # Limit scanning only to these fields. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the rest of the rows are omitted. If not set, or if set to 0, all rows will be scanned. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig.
"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig. Caution: A [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-sampling) is causing the `rowsLimitPercent` field to behave unexpectedly. We recommend using `rowsLimit` instead.
"sampleMethod": "A String", # How to sample the data.
"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Complete BigQuery table reference.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
"cloudStorageOptions": { # Options defining a file or a set of files within a Cloud Storage bucket. # Cloud Storage options.
"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger than this value then the rest of the bytes are omitted. Only one of `bytes_limit_per_file` and `bytes_limit_per_file_percent` can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The number of bytes scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"fileSet": { # Set of files to scan. # The set of one or more files to scan.
"regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular expressions are used to allow fine-grained control over which files in the bucket to include. Included files are those that match at least one item in `include_regex` and do not match any items in `exclude_regex`. Note that a file that matches items from both lists will _not_ be included. For a match to occur, the entire file path (i.e., everything in the url after the bucket name) must match the regular expression. For example, given the input `{bucket_name: "mybucket", include_regex: ["directory1/.*"], exclude_regex: ["directory1/excluded.*"]}`: * `gs://mybucket/directory1/myfile` will be included * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches across `/`) * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the full path doesn't match any items in `include_regex`) * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path matches an item in `exclude_regex`) If `include_regex` is left empty, it will match all files by default (this is equivalent to setting `include_regex: [".*"]`). Some other common use cases: * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all files in `mybucket` except for .pdf files * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will include all files directly under `gs://mybucket/directory/`, without matching across `/` # The regex-filtered set of files to scan. Exactly one of `url` or `regex_file_set` must be set.
"bucketName": "A String", # The name of a Cloud Storage bucket. Required.
"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in the bucket that match at least one of these regular expressions will be excluded from the scan. Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
"includeRegex": [ # A list of regular expressions matching file paths to include. All files in the bucket that match at least one of these regular expressions will be included in the set of files, except for those that also match an item in `exclude_regex`. Leaving this field empty will match all files by default (this is equivalent to including `.*` in the list). Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
},
"url": "A String", # The Cloud Storage url of the file(s) to scan, in the format `gs:///`. Trailing wildcard in the path is allowed. If the url ends in a trailing slash, the bucket or directory represented by the url will be scanned non-recursively (content in sub-directories will not be scanned). This means that `gs://mybucket/` is equivalent to `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to `gs://mybucket/directory/*`. Exactly one of `url` or `regex_file_set` must be set.
},
"fileTypes": [ # List of file type groups to include in the scan. If empty, all files are scanned and available data format processors are applied. In addition, the binary content of the selected files is always scanned as well. Images are scanned only as binary if the specified region does not support image inspection and no file_types were specified. Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
"A String",
],
"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet. Number of files scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0.
"sampleMethod": "A String", # How to sample the data.
},
"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
"kind": { # A representation of a Datastore kind. # The kind to process.
"name": "A String", # The name of the kind.
},
"partitionId": { # Datastore partition ID. A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty. A partition ID contains several dimensions: project ID and namespace ID. # A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty.
"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
"projectId": "A String", # The ID of the project to which the entities belong.
},
},
"hybridOptions": { # Configuration to control jobs where the content being inspected is outside of Google Cloud Platform. # Hybrid inspection options.
"description": "A String", # A short description of where the data is coming from. Will be stored once in the job. 256 max length.
"labels": { # To organize findings, these labels will be added to each finding. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. Label values must be between 0 and 63 characters long and must conform to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`. No more than 10 labels can be associated with a given finding. Examples: * `"environment" : "production"` * `"pipeline" : "etl"`
"a_key": "A String",
},
"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their 'finding_labels' map. Request may contain others, but any missing one of these will be rejected. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. No more than 10 keys can be required.
"A String",
],
"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings meaningful such as the columns that are primary keys.
"identifyingFields": [ # The columns that are the primary keys for table objects included in ContentItem. A copy of this cell's value will stored alongside alongside each finding so that the finding can be traced to the specific row it came from. No more than 3 may be provided.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
},
"timespanConfig": { # Configuration of the timespan of the items to include in scanning. Currently only supported when inspecting Cloud Storage and BigQuery. # Configuration of the timespan of the items to include in scanning.
"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out a valid start_time to avoid scanning files that have not been modified since the last time the JobTrigger executed. This will be based on the time of the execution of the last run of the JobTrigger or the timespan end_time used in the last run of the JobTrigger. **For BigQuery** Inspect jobs triggered by automatic population will scan data that is at least three hours old when the job starts. This is because streaming buffer rows are not read during inspection and reading up to the current timestamp will result in skipped rows. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#recently-streamed-data) related to this operation.
"endTime": "A String", # Exclude files, tables, or rows newer than this value. If not set, no upper time limit is applied.
"startTime": "A String", # Exclude files, tables, or rows older than this value. If not set, no lower time limit is applied.
"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items. Used for data sources like Datastore and BigQuery. **For BigQuery** If this value is not specified and the table was modified between the given start and end times, the entire table will be scanned. If this value is specified, then rows are filtered based on the given start and end times. Rows with a `NULL` value in the provided BigQuery column are skipped. Valid data types of the provided BigQuery column are: `INTEGER`, `DATE`, `TIMESTAMP`, and `DATETIME`. If your BigQuery table is [partitioned at ingestion time](https://cloud.google.com/bigquery/docs/partitioned-tables#ingestion_time), you can use any of the following pseudo-columns as your timestamp field. When used with Cloud DLP, these pseudo-column names are case sensitive. - `_PARTITIONTIME` - `_PARTITIONDATE` - `_PARTITION_LOAD_TIME` **For Datastore** If this value is specified, then entities are filtered based on the given start and end times. If an entity does not contain the provided timestamp property or contains empty or invalid values, then it is included. Valid data types of the provided timestamp property are: `TIMESTAMP`. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-timespan) related to this operation.
"name": "A String", # Name describing the field.
},
},
},
},
"jobId": "A String", # The job id can contain uppercase and lowercase letters, numbers, and hyphens; that is, it must match the regular expression: `[a-zA-Z\d-_]+`. The maximum length is 100 characters. Can be empty to allow the system to generate one.
"locationId": "A String", # Deprecated. This field has no effect.
"riskJob": { # Configuration for a risk analysis job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-risk-analysis to learn more. # A risk analysis job calculates re-identification risk metrics for a BigQuery table.
"actions": [ # Actions to execute at the completion of the job. Are executed in the order provided.
{ # A task to execute on the completion of a job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-actions to learn more.
"deidentify": { # Create a de-identified copy of the requested table or files. A TransformationDetail will be created for each transformation. If any rows in BigQuery are skipped during de-identification (transformation errors or row size exceeds BigQuery insert API limits) they are placed in the failure output table. If the original row exceeds the BigQuery insert API limit it will be truncated when written to the failure output table. The failure output table can be set in the action.deidentify.output.big_query_output.deidentified_failure_output_table field, if no table is set, a table will be automatically created in the same project and dataset as the original table. Compatible with: Inspect # Create a de-identified copy of the input data.
"cloudStorageOutput": "A String", # Required. User settable Cloud Storage bucket and folders to store de-identified files. This field must be set for Cloud Storage deidentification. The output Cloud Storage bucket must be different from the input bucket. De-identified files will overwrite files in the output path. Form of: gs://bucket/folder/ or gs://bucket
"fileTypesToTransform": [ # List of user-specified file type groups to transform. If specified, only the files with these file types will be transformed. If empty, all supported files will be transformed. Supported types may be automatically added over time. If a file type is set in this field that isn't supported by the Deidentify action then the job will fail and will not be successfully created/started. Currently the only file types supported are: IMAGES, TEXT_FILES, CSV, TSV.
"A String",
],
"transformationConfig": { # User specified templates and configs for how to deidentify structured, unstructures, and image files. User must provide either a unstructured deidentify template or at least one redact image config. # User specified deidentify templates and configs for structured, unstructured, and image files.
"deidentifyTemplate": "A String", # De-identify template. If this template is specified, it will serve as the default de-identify template. This template cannot contain `record_transformations` since it can be used for unstructured content such as free-form text files. If this template is not set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify unstructured content.
"imageRedactTemplate": "A String", # Image redact template. If this template is specified, it will serve as the de-identify template for images. If this template is not set, all findings in the image will be redacted with a black box.
"structuredDeidentifyTemplate": "A String", # Structured de-identify template. If this template is specified, it will serve as the de-identify template for structured content such as delimited files and tables. If this template is not set but the `deidentify_template` is set, then `deidentify_template` will also apply to the structured content. If neither template is set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify structured content.
},
"transformationDetailsStorageConfig": { # Config for storing transformation details. # Config for storing transformation details. This is separate from the de-identified content, and contains metadata about the successful transformations and/or failures that occurred while de-identifying. This needs to be set in order for users to access information about the status of each transformation (see TransformationDetails message for more information about what is noted).
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # The BigQuery table in which to store the output. This may be an existing table or in a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_transformation_details_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"jobNotificationEmails": { # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts). # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts).
},
"pubSub": { # Publish a message into a given Pub/Sub topic when DlpJob has completed. The message contains a single field, `DlpJobName`, which is equal to the finished job's [`DlpJob.name`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/projects.dlpJobs#DlpJob). Compatible with: Inspect, Risk # Publish a notification to a Pub/Sub topic.
"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given publishing access rights to the DLP API service account executing the long running DlpJob sending the notifications. Format is projects/{project}/topics/{topic}.
},
"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Data Catalog. In Data Catalog, tag templates are applied to the resource that Cloud DLP scanned. Data Catalog tag templates are stored in the same project and region where the BigQuery table exists. For Cloud DLP to create and apply the tag template, the Cloud DLP service agent must have the `roles/datacatalog.tagTemplateOwner` permission on the project. The tag template contains fields summarizing the results of the DlpJob. Any field values previously written by another DlpJob are deleted. InfoType naming patterns are strictly enforced when using this feature. Findings are persisted in Data Catalog storage and are governed by service-specific policies for Data Catalog. For more information, see [Service Specific Terms](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. This action is allowed only if all resources being scanned are BigQuery tables. Compatible with: Inspect # Publish findings to Cloud Datahub.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to [Security Command Center](https://cloud.google.com/security-command-center). This action is available for only projects that belong to an organization. This action publishes the count of finding instances and their infoTypes. The summary of findings are persisted in Security Command Center and are governed by [service-specific policies for Security Command Center](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. Compatible with: Inspect # Publish summary to Cloud Security Command Center (Alpha).
},
"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This will publish a metric to stack driver on each infotype requested and how many findings were found for it. CustomDetectors will be bucketed as 'Custom' under the Stackdriver label 'info_type'. # Enable Stackdriver metric dlp.googleapis.com/finding_count.
},
"saveFindings": { # If set, the detailed findings will be persisted to the specified OutputStorageConfig. Only a single instance of this action can be specified. Compatible with: Inspect, Risk # Save resulting findings in a provided location.
"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only used for Inspect and must be unspecified for Risk jobs. Columns are derived from the `Finding` object. If appending to an existing table, any columns from the predefined schema that are missing will be added. No columns in the existing table will be deleted. If unspecified, then all available columns will be used for a new table or an (existing) table with no schema, and no changes will be made to an existing table that has a schema. Only for use with external storage.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Store findings in an existing table or a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details. For Inspect, each column in an existing output table must have the same name, type, and mode of a field in the `Finding` object. For Risk, an existing output table should be the output of a previous Risk analysis job run on the same source table, with the same privacy metric and quasi-identifiers. Risk jobs that analyze the same table but compute a different privacy metric, or use different sets of quasi-identifiers, cannot store their results in the same table.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
},
],
"privacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.
"categoricalStatsConfig": { # Compute numerical stats over an individual column, including number of distinct values and value count distribution. # Categorical stats
"field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are supported except for arrays and structs. However, it may be more informative to use NumericalStats when the field type is supported, depending on the data.
"name": "A String", # Name describing the field.
},
},
"deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to figure out that one given individual appears in a de-identified dataset. Similarly to the k-map metric, we cannot compute δ-presence exactly without knowing the attack dataset, so we use a statistical model instead. # delta-presence
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers field must appear in exactly one field of one auxiliary table.
{ # An auxiliary table containing statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity
"entityId": { # An entity in a dataset is a field or set of fields that correspond to a single person. For example, in medical records the `EntityId` might be a patient identifier, or for financial records it might be an account identifier. This message is used when generalizations or analysis must take into account that multiple rows correspond to the same entity. # Message indicating that multiple rows might be associated to a single individual. If the same entity_id is associated to multiple quasi-identifier tuples over distinct rows, we consider the entire collection of tuples as the composite quasi-identifier. This collection is a multiset: the order in which the different tuples appear in the dataset is ignored, but their frequency is taken into account. Important note: a maximum of 1000 rows can be associated to a single entity ID. If more rows are associated with the same entity ID, some might be ignored.
"field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier.
"name": "A String", # Name describing the field.
},
},
"quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are specified, they are considered a single composite key. Structs and repeated data types are not supported; however, nested fields are supported so long as they are not structs themselves or nested within a repeated field.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
"kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what is called "journalist risk" in the literature, except the attack dataset is statistically modeled instead of being perfectly known. This can be done using publicly available data (like the US Census), or using a custom statistical model (indicated as one or several BigQuery tables), or by extrapolating from the distribution of values in the input dataset. # k-map
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers column must appear in exactly one column of one auxiliary table.
{ # An auxiliary table contains statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A auxiliary field.
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity
"quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are defined for the l-diversity computation. When multiple fields are specified, they are considered a single composite key.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value.
"name": "A String", # Name describing the field.
},
},
"numericalStatsConfig": { # Compute numerical stats over an individual column, including min, max, and quantiles. # Numerical stats
"field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are integer, float, date, datetime, timestamp, time.
"name": "A String", # Name describing the field.
},
},
},
"sourceTable": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Input dataset to compute metrics over.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
}

x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format

Returns:
An object of the form:

{ # Combines all of the information about a DLP job.
"actionDetails": [ # Events that should occur after the job has completed.
{ # The results of an Action.
"deidentifyDetails": { # The results of a Deidentify action from an inspect job. # Outcome of a de-identification action.
"deidentifyStats": { # Summary of what was modified during a transformation. # Stats about the de-identification operation.
"transformationCount": "A String", # Number of successfully applied transformations.
"transformationErrorCount": "A String", # Number of errors encountered while trying to apply transformations.
"transformedBytes": "A String", # Total size in bytes that were transformed in some way.
},
"requestedOptions": { # De-identification options. # De-identification config used for the request.
"snapshotDeidentifyTemplate": { # DeidentifyTemplates contains instructions on how to de-identify content. See https://cloud.google.com/sensitive-data-protection/docs/concepts-templates to learn more. # Snapshot of the state of the `DeidentifyTemplate` from the Deidentify action at the time this job was run.
"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.
"deidentifyConfig": { # The configuration that controls how the data will change. # The core content of the template.
"imageTransformations": { # A type of transformation that is applied over images. # Treat the dataset as an image and redact.
"transforms": [ # List of transforms to make.
{ # Configuration for determining how redaction of images should occur.
"allInfoTypes": { # Apply transformation to all findings. # Apply transformation to all findings not specified in other ImageTransformation's selected_info_types. Only one instance is allowed within the ImageTransformations message.
},
"allText": { # Apply to all text. # Apply transformation to all text that doesn't match an infoType. Only one instance is allowed within the ImageTransformations message.
},
"redactionColor": { # Represents a color in the RGB color space. # The color to use when redacting content from an image. If not specified, the default is black.
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"selectedInfoTypes": { # Apply transformation to the selected info_types. # Apply transformation to the selected info_types.
"infoTypes": [ # Required. InfoTypes to apply the transformation to. Required. Provided InfoType must be unique within the ImageTransformations message.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
},
],
},
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the dataset as free-form text and apply the same free text transformation everywhere.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"recordTransformations": { # A type of transformation that is applied over structured data such as a table. # Treat the dataset as structured. Transformations can be applied to specific locations within structured datasets, such as transforming a column within a table.
"fieldTransformations": [ # Transform the record by applying various field transformations.
{ # The transformation to apply to the field.
"condition": { # A condition for determining whether a transformation should be applied to a field. # Only apply the transformation if the condition evaluates to true for the given `RecordCondition`. The conditions are allowed to reference fields that are not used in the actual transformation. Example Use Cases: - Apply a different bucket transformation to an age column if the zip code column for the same record is within a specific range. - Redact a field if the date of birth field is greater than 85.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
"fields": [ # Required. Input field(s) to apply the transformation to. When you have columns that reference their position within a list, omit the index from the FieldId. FieldId name matching ignores the index. For example, instead of "contact.nums[0].type", use "contact.nums.type".
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the contents of the field as free text, and selectively transform content that matches an `InfoType`.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"primitiveTransformation": { # A rule for transforming a value. # Apply the transformation to the entire field.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
"recordSuppressions": [ # Configuration defining which records get suppressed entirely. Records that match any suppression rule are omitted from the output.
{ # Configuration to suppress records whose suppression conditions evaluate to true.
"condition": { # A condition for determining whether a transformation should be applied to a field. # A condition that when it evaluates to true will result in the record being evaluated to be suppressed from the transformed content.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
},
],
},
"transformationErrorHandling": { # How to handle transformation errors during de-identification. A transformation error occurs when the requested transformation is incompatible with the data. For example, trying to de-identify an IP address using a `DateShift` transformation would result in a transformation error, since date info cannot be extracted from an IP address. Information about any incompatible transformations, and how they were handled, is returned in the response as part of the `TransformationOverviews`. # Mode for handling transformation errors. If left unspecified, the default mode is `TransformationErrorHandling.ThrowError`.
"leaveUntransformed": { # Skips the data without modifying it if the requested transformation would cause an error. For example, if a `DateShift` transformation were applied an an IP address, this mode would leave the IP address unchanged in the response. # Ignore errors
},
"throwError": { # Throw an error and fail the request when a transformation error occurs. # Throw an error
},
},
},
"description": "A String", # Short description (max 256 chars).
"displayName": "A String", # Display name (max 256 chars).
"name": "A String", # Output only. The template name. The template will have one of the following formats: `projects/PROJECT_ID/deidentifyTemplates/TEMPLATE_ID` OR `organizations/ORGANIZATION_ID/deidentifyTemplates/TEMPLATE_ID`
"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.
},
"snapshotImageRedactTemplate": { # DeidentifyTemplates contains instructions on how to de-identify content. See https://cloud.google.com/sensitive-data-protection/docs/concepts-templates to learn more. # Snapshot of the state of the image transformation `DeidentifyTemplate` from the `Deidentify` action at the time this job was run.
"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.
"deidentifyConfig": { # The configuration that controls how the data will change. # The core content of the template.
"imageTransformations": { # A type of transformation that is applied over images. # Treat the dataset as an image and redact.
"transforms": [ # List of transforms to make.
{ # Configuration for determining how redaction of images should occur.
"allInfoTypes": { # Apply transformation to all findings. # Apply transformation to all findings not specified in other ImageTransformation's selected_info_types. Only one instance is allowed within the ImageTransformations message.
},
"allText": { # Apply to all text. # Apply transformation to all text that doesn't match an infoType. Only one instance is allowed within the ImageTransformations message.
},
"redactionColor": { # Represents a color in the RGB color space. # The color to use when redacting content from an image. If not specified, the default is black.
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"selectedInfoTypes": { # Apply transformation to the selected info_types. # Apply transformation to the selected info_types.
"infoTypes": [ # Required. InfoTypes to apply the transformation to. Required. Provided InfoType must be unique within the ImageTransformations message.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
},
],
},
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the dataset as free-form text and apply the same free text transformation everywhere.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"recordTransformations": { # A type of transformation that is applied over structured data such as a table. # Treat the dataset as structured. Transformations can be applied to specific locations within structured datasets, such as transforming a column within a table.
"fieldTransformations": [ # Transform the record by applying various field transformations.
{ # The transformation to apply to the field.
"condition": { # A condition for determining whether a transformation should be applied to a field. # Only apply the transformation if the condition evaluates to true for the given `RecordCondition`. The conditions are allowed to reference fields that are not used in the actual transformation. Example Use Cases: - Apply a different bucket transformation to an age column if the zip code column for the same record is within a specific range. - Redact a field if the date of birth field is greater than 85.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
"fields": [ # Required. Input field(s) to apply the transformation to. When you have columns that reference their position within a list, omit the index from the FieldId. FieldId name matching ignores the index. For example, instead of "contact.nums[0].type", use "contact.nums.type".
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the contents of the field as free text, and selectively transform content that matches an `InfoType`.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"primitiveTransformation": { # A rule for transforming a value. # Apply the transformation to the entire field.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
"recordSuppressions": [ # Configuration defining which records get suppressed entirely. Records that match any suppression rule are omitted from the output.
{ # Configuration to suppress records whose suppression conditions evaluate to true.
"condition": { # A condition for determining whether a transformation should be applied to a field. # A condition that when it evaluates to true will result in the record being evaluated to be suppressed from the transformed content.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
},
],
},
"transformationErrorHandling": { # How to handle transformation errors during de-identification. A transformation error occurs when the requested transformation is incompatible with the data. For example, trying to de-identify an IP address using a `DateShift` transformation would result in a transformation error, since date info cannot be extracted from an IP address. Information about any incompatible transformations, and how they were handled, is returned in the response as part of the `TransformationOverviews`. # Mode for handling transformation errors. If left unspecified, the default mode is `TransformationErrorHandling.ThrowError`.
"leaveUntransformed": { # Skips the data without modifying it if the requested transformation would cause an error. For example, if a `DateShift` transformation were applied an an IP address, this mode would leave the IP address unchanged in the response. # Ignore errors
},
"throwError": { # Throw an error and fail the request when a transformation error occurs. # Throw an error
},
},
},
"description": "A String", # Short description (max 256 chars).
"displayName": "A String", # Display name (max 256 chars).
"name": "A String", # Output only. The template name. The template will have one of the following formats: `projects/PROJECT_ID/deidentifyTemplates/TEMPLATE_ID` OR `organizations/ORGANIZATION_ID/deidentifyTemplates/TEMPLATE_ID`
"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.
},
"snapshotStructuredDeidentifyTemplate": { # DeidentifyTemplates contains instructions on how to de-identify content. See https://cloud.google.com/sensitive-data-protection/docs/concepts-templates to learn more. # Snapshot of the state of the structured `DeidentifyTemplate` from the `Deidentify` action at the time this job was run.
"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.
"deidentifyConfig": { # The configuration that controls how the data will change. # The core content of the template.
"imageTransformations": { # A type of transformation that is applied over images. # Treat the dataset as an image and redact.
"transforms": [ # List of transforms to make.
{ # Configuration for determining how redaction of images should occur.
"allInfoTypes": { # Apply transformation to all findings. # Apply transformation to all findings not specified in other ImageTransformation's selected_info_types. Only one instance is allowed within the ImageTransformations message.
},
"allText": { # Apply to all text. # Apply transformation to all text that doesn't match an infoType. Only one instance is allowed within the ImageTransformations message.
},
"redactionColor": { # Represents a color in the RGB color space. # The color to use when redacting content from an image. If not specified, the default is black.
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"selectedInfoTypes": { # Apply transformation to the selected info_types. # Apply transformation to the selected info_types.
"infoTypes": [ # Required. InfoTypes to apply the transformation to. Required. Provided InfoType must be unique within the ImageTransformations message.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
},
],
},
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the dataset as free-form text and apply the same free text transformation everywhere.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"recordTransformations": { # A type of transformation that is applied over structured data such as a table. # Treat the dataset as structured. Transformations can be applied to specific locations within structured datasets, such as transforming a column within a table.
"fieldTransformations": [ # Transform the record by applying various field transformations.
{ # The transformation to apply to the field.
"condition": { # A condition for determining whether a transformation should be applied to a field. # Only apply the transformation if the condition evaluates to true for the given `RecordCondition`. The conditions are allowed to reference fields that are not used in the actual transformation. Example Use Cases: - Apply a different bucket transformation to an age column if the zip code column for the same record is within a specific range. - Redact a field if the date of birth field is greater than 85.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
"fields": [ # Required. Input field(s) to apply the transformation to. When you have columns that reference their position within a list, omit the index from the FieldId. FieldId name matching ignores the index. For example, instead of "contact.nums[0].type", use "contact.nums.type".
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the contents of the field as free text, and selectively transform content that matches an `InfoType`.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"primitiveTransformation": { # A rule for transforming a value. # Apply the transformation to the entire field.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
"recordSuppressions": [ # Configuration defining which records get suppressed entirely. Records that match any suppression rule are omitted from the output.
{ # Configuration to suppress records whose suppression conditions evaluate to true.
"condition": { # A condition for determining whether a transformation should be applied to a field. # A condition that when it evaluates to true will result in the record being evaluated to be suppressed from the transformed content.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
},
],
},
"transformationErrorHandling": { # How to handle transformation errors during de-identification. A transformation error occurs when the requested transformation is incompatible with the data. For example, trying to de-identify an IP address using a `DateShift` transformation would result in a transformation error, since date info cannot be extracted from an IP address. Information about any incompatible transformations, and how they were handled, is returned in the response as part of the `TransformationOverviews`. # Mode for handling transformation errors. If left unspecified, the default mode is `TransformationErrorHandling.ThrowError`.
"leaveUntransformed": { # Skips the data without modifying it if the requested transformation would cause an error. For example, if a `DateShift` transformation were applied an an IP address, this mode would leave the IP address unchanged in the response. # Ignore errors
},
"throwError": { # Throw an error and fail the request when a transformation error occurs. # Throw an error
},
},
},
"description": "A String", # Short description (max 256 chars).
"displayName": "A String", # Display name (max 256 chars).
"name": "A String", # Output only. The template name. The template will have one of the following formats: `projects/PROJECT_ID/deidentifyTemplates/TEMPLATE_ID` OR `organizations/ORGANIZATION_ID/deidentifyTemplates/TEMPLATE_ID`
"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.
},
},
},
},
],
"createTime": "A String", # Time when the job was created.
"endTime": "A String", # Time when the job finished.
"errors": [ # A stream of errors encountered running the job.
{ # Details information about an error encountered during job execution or the results of an unsuccessful activation of the JobTrigger.
"details": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Detailed error codes and messages.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"extraInfo": "A String", # Additional information about the error.
"timestamps": [ # The times the error occurred. List includes the oldest timestamp and the last 9 timestamps.
"A String",
],
},
],
"inspectDetails": { # The results of an inspect DataSource job. # Results from inspecting a data source.
"requestedOptions": { # Snapshot of the inspection configuration. # The configuration used for this job.
"jobConfig": { # Controls what and how to inspect for findings. # Inspect config.
"actions": [ # Actions to execute at the completion of the job.
{ # A task to execute on the completion of a job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-actions to learn more.
"deidentify": { # Create a de-identified copy of the requested table or files. A TransformationDetail will be created for each transformation. If any rows in BigQuery are skipped during de-identification (transformation errors or row size exceeds BigQuery insert API limits) they are placed in the failure output table. If the original row exceeds the BigQuery insert API limit it will be truncated when written to the failure output table. The failure output table can be set in the action.deidentify.output.big_query_output.deidentified_failure_output_table field, if no table is set, a table will be automatically created in the same project and dataset as the original table. Compatible with: Inspect # Create a de-identified copy of the input data.
"cloudStorageOutput": "A String", # Required. User settable Cloud Storage bucket and folders to store de-identified files. This field must be set for Cloud Storage deidentification. The output Cloud Storage bucket must be different from the input bucket. De-identified files will overwrite files in the output path. Form of: gs://bucket/folder/ or gs://bucket
"fileTypesToTransform": [ # List of user-specified file type groups to transform. If specified, only the files with these file types will be transformed. If empty, all supported files will be transformed. Supported types may be automatically added over time. If a file type is set in this field that isn't supported by the Deidentify action then the job will fail and will not be successfully created/started. Currently the only file types supported are: IMAGES, TEXT_FILES, CSV, TSV.
"A String",
],
"transformationConfig": { # User specified templates and configs for how to deidentify structured, unstructures, and image files. User must provide either a unstructured deidentify template or at least one redact image config. # User specified deidentify templates and configs for structured, unstructured, and image files.
"deidentifyTemplate": "A String", # De-identify template. If this template is specified, it will serve as the default de-identify template. This template cannot contain `record_transformations` since it can be used for unstructured content such as free-form text files. If this template is not set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify unstructured content.
"imageRedactTemplate": "A String", # Image redact template. If this template is specified, it will serve as the de-identify template for images. If this template is not set, all findings in the image will be redacted with a black box.
"structuredDeidentifyTemplate": "A String", # Structured de-identify template. If this template is specified, it will serve as the de-identify template for structured content such as delimited files and tables. If this template is not set but the `deidentify_template` is set, then `deidentify_template` will also apply to the structured content. If neither template is set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify structured content.
},
"transformationDetailsStorageConfig": { # Config for storing transformation details. # Config for storing transformation details. This is separate from the de-identified content, and contains metadata about the successful transformations and/or failures that occurred while de-identifying. This needs to be set in order for users to access information about the status of each transformation (see TransformationDetails message for more information about what is noted).
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # The BigQuery table in which to store the output. This may be an existing table or in a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_transformation_details_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"jobNotificationEmails": { # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts). # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts).
},
"pubSub": { # Publish a message into a given Pub/Sub topic when DlpJob has completed. The message contains a single field, `DlpJobName`, which is equal to the finished job's [`DlpJob.name`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/projects.dlpJobs#DlpJob). Compatible with: Inspect, Risk # Publish a notification to a Pub/Sub topic.
"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given publishing access rights to the DLP API service account executing the long running DlpJob sending the notifications. Format is projects/{project}/topics/{topic}.
},
"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Data Catalog. In Data Catalog, tag templates are applied to the resource that Cloud DLP scanned. Data Catalog tag templates are stored in the same project and region where the BigQuery table exists. For Cloud DLP to create and apply the tag template, the Cloud DLP service agent must have the `roles/datacatalog.tagTemplateOwner` permission on the project. The tag template contains fields summarizing the results of the DlpJob. Any field values previously written by another DlpJob are deleted. InfoType naming patterns are strictly enforced when using this feature. Findings are persisted in Data Catalog storage and are governed by service-specific policies for Data Catalog. For more information, see [Service Specific Terms](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. This action is allowed only if all resources being scanned are BigQuery tables. Compatible with: Inspect # Publish findings to Cloud Datahub.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to [Security Command Center](https://cloud.google.com/security-command-center). This action is available for only projects that belong to an organization. This action publishes the count of finding instances and their infoTypes. The summary of findings are persisted in Security Command Center and are governed by [service-specific policies for Security Command Center](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. Compatible with: Inspect # Publish summary to Cloud Security Command Center (Alpha).
},
"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This will publish a metric to stack driver on each infotype requested and how many findings were found for it. CustomDetectors will be bucketed as 'Custom' under the Stackdriver label 'info_type'. # Enable Stackdriver metric dlp.googleapis.com/finding_count.
},
"saveFindings": { # If set, the detailed findings will be persisted to the specified OutputStorageConfig. Only a single instance of this action can be specified. Compatible with: Inspect, Risk # Save resulting findings in a provided location.
"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only used for Inspect and must be unspecified for Risk jobs. Columns are derived from the `Finding` object. If appending to an existing table, any columns from the predefined schema that are missing will be added. No columns in the existing table will be deleted. If unspecified, then all available columns will be used for a new table or an (existing) table with no schema, and no changes will be made to an existing table that has a schema. Only for use with external storage.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Store findings in an existing table or a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details. For Inspect, each column in an existing output table must have the same name, type, and mode of a field in the `Finding` object. For Risk, an existing output table should be the output of a previous Risk analysis job run on the same source table, with the same privacy metric and quasi-identifiers. Risk jobs that analyze the same table but compute a different privacy metric, or use different sets of quasi-identifiers, cannot store their results in the same table.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
},
],
"inspectConfig": { # Configuration description of the scanning process. When used with redactContent only info_types and min_likelihood are currently used. # How and what to scan for.
"contentOptions": [ # Deprecated and unused.
"A String",
],
"customInfoTypes": [ # CustomInfoTypes provided by the user. See https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes to learn more.
{ # Custom information type provided by the user. Used to find domain-specific sensitive information configurable to the data in question.
"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. Rules are applied in order that they are specified. Not supported for the `surrogate_type` CustomInfoType.
{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a `CustomInfoType` to alter behavior under certain circumstances, depending on the specific details of the rule. Not supported for the `surrogate_type` custom infoType.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "$\d{3}$ \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "$xxx$", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # A list of phrases to detect as a CustomInfoType.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding to be returned. It still can be used for rules matching.
"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in infoType, when the name matches one of existing infoTypes and that infoType is specified in `InspectContent.info_types` field. Specifying the latter adds findings to the one detected by the system. If built-in info type is not specified in `InspectContent.info_types` list then the name is treated as a custom info type.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be altered by a detection rule if the finding meets the criteria specified by the rule. Defaults to `VERY_LIKELY` if not specified.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Sensitivity for this CustomInfoType. If this CustomInfoType extends an existing InfoType, the sensitivity here will take precedence over that of the original InfoType. If unset for a CustomInfoType, it will default to HIGH. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in `InspectDataSource`. Not currently supported in `InspectContent`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for inspection was created. Output-only field, populated by the system.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example `organizations/433245324/storedInfoTypes/432452342` or `projects/project-id/storedInfoTypes/432452342`.
},
"surrogateType": { # Message for detecting output from deidentification transformations such as [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). These types of transformations are those that perform pseudonymization, thereby producing a "surrogate" as output. This should be used in conjunction with a field on the transformation such as `surrogate_info_type`. This CustomInfoType does not support the use of `detection_rules`. # Message for detecting output from deidentification transformations that support reversing.
},
},
],
"excludeInfoTypes": True or False, # When true, excludes type information of the findings. This is not used for data profiling.
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is included in the response; see Finding.quote. This is not used for data profiling.
"infoTypes": [ # Restricts what info_types to look for. The values must correspond to InfoType values returned by ListInfoTypes or listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference. When no InfoTypes or CustomInfoTypes are specified in a request, the system may automatically choose a default list of detectors to run, which may change over time. If you need precise control and predictability as to what detectors are run you should specify specific InfoTypes listed in the reference, otherwise a default list will be used, which may change over time.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"limits": { # Configuration to control the number of findings returned for inspection. This is not used for de-identification or data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. # Configuration to control the number of findings returned. This is not used for data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. When set within an InspectJobConfig, the specified maximum values aren't hard limits. If an inspection job reaches these limits, the job ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than these maximum values.
"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
{ # Max findings configuration per infoType, per content item or long running DlpJob.
"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per info_type should be provided. If InfoTypeLimit does not have an info_type, the DLP API applies the limit against all info_types that are found but not specified in another InfoTypeLimit.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that are returned for each item scanned. When set within an InspectContentRequest, this field is ignored. This value isn't a hard limit. If the number of findings for an item reaches this limit, the inspection of that item ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns for the item can be multiple times higher than this value.
"maxFindingsPerRequest": 42, # Max number of findings that are returned per request or job. If you set this field in an InspectContentRequest, the resulting maximum value is the value that you set or 3,000, whichever is lower. This value isn't a hard limit. If an inspection reaches this limit, the inspection ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than this value.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. The default is POSSIBLE. In general, the highest likelihood setting yields the fewest findings in results and the lowest chance of a false positive. For more information, see [Match likelihood](https://cloud.google.com/sensitive-data-protection/docs/likelihood).
"minLikelihoodPerInfoType": [ # Minimum likelihood per infotype. For each infotype, a user can specify a minimum likelihood. The system only returns a finding if its likelihood is above this threshold. If this field is not set, the system uses the InspectConfig min_likelihood.
{ # Configuration for setting a minimum likelihood per infotype. Used to customize the minimum likelihood level for specific infotypes in the request. For example, use this if you want to lower the precision for PERSON_NAME without lowering the precision for the other infotypes in the request.
"infoType": { # Type of information detected by the API. # Type of information the likelihood threshold applies to. Only one likelihood per info_type should be provided. If InfoTypeLikelihood does not have an info_type, the configuration fails.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. This field is required or else the configuration fails.
},
],
"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. Exclusion rules, contained in the set are executed in the end, other rules are executed in the order they are specified for each info type.
{ # Rule set for modifying a set of infoTypes to alter behavior under certain circumstances, depending on the specific details of the rules within the set.
"infoTypes": [ # List of infoTypes this rule set is applied to.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
{ # A single inspection rule to be applied to infoTypes, specified in `InspectionRuleSet`.
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in `InspectionRuleSet` are removed from results. # Exclusion rule.
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # Dictionary which defines the rule.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"excludeByHotword": { # The rule to exclude findings based on a hotword. For record inspection of tables, column names are considered hotwords. An example of this is to exclude a finding if it belongs to a BigQuery column that matches a specific pattern. # Drop if the hotword rule is contained in the proximate context. For tabular data, the context includes the column name.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The windowBefore property in proximity should be set to 1 if the hotword needs to be included in a column header.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
"excludeInfoTypes": { # List of excluded infoTypes. # Set of infoTypes for which findings would affect this rule.
"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or contained within with a finding of an infoType from this list. For example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and `exclusion_rule` containing `exclude_info_types.info_types` with "EMAIL_ADDRESS" the phone number findings are dropped if they overlap with EMAIL_ADDRESS finding. That leads to "555-222-2222@example.org" to generate only a single finding, namely email address.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
},
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "$\d{3}$ \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "$xxx$", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
},
],
},
"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig. `inspect_config` will be merged into the values persisted as part of the template.
"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
"excludedFields": [ # References to fields excluded from scanning. This allows you to skip inspection of entire columns which you know have no findings. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When `actions.saveFindings.outputConfig.table` is specified, the values of columns specified here are available in the output table under `location.content_locations.record_location.record_key.id_values`. Nested fields such as `person.birthdate.year` are allowed.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"includedFields": [ # Limit scanning only to these fields. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the rest of the rows are omitted. If not set, or if set to 0, all rows will be scanned. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig.
"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig. Caution: A [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-sampling) is causing the `rowsLimitPercent` field to behave unexpectedly. We recommend using `rowsLimit` instead.
"sampleMethod": "A String", # How to sample the data.
"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Complete BigQuery table reference.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
"cloudStorageOptions": { # Options defining a file or a set of files within a Cloud Storage bucket. # Cloud Storage options.
"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger than this value then the rest of the bytes are omitted. Only one of `bytes_limit_per_file` and `bytes_limit_per_file_percent` can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The number of bytes scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"fileSet": { # Set of files to scan. # The set of one or more files to scan.
"regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular expressions are used to allow fine-grained control over which files in the bucket to include. Included files are those that match at least one item in `include_regex` and do not match any items in `exclude_regex`. Note that a file that matches items from both lists will _not_ be included. For a match to occur, the entire file path (i.e., everything in the url after the bucket name) must match the regular expression. For example, given the input `{bucket_name: "mybucket", include_regex: ["directory1/.*"], exclude_regex: ["directory1/excluded.*"]}`: * `gs://mybucket/directory1/myfile` will be included * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches across `/`) * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the full path doesn't match any items in `include_regex`) * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path matches an item in `exclude_regex`) If `include_regex` is left empty, it will match all files by default (this is equivalent to setting `include_regex: [".*"]`). Some other common use cases: * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all files in `mybucket` except for .pdf files * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will include all files directly under `gs://mybucket/directory/`, without matching across `/` # The regex-filtered set of files to scan. Exactly one of `url` or `regex_file_set` must be set.
"bucketName": "A String", # The name of a Cloud Storage bucket. Required.
"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in the bucket that match at least one of these regular expressions will be excluded from the scan. Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
"includeRegex": [ # A list of regular expressions matching file paths to include. All files in the bucket that match at least one of these regular expressions will be included in the set of files, except for those that also match an item in `exclude_regex`. Leaving this field empty will match all files by default (this is equivalent to including `.*` in the list). Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
},
"url": "A String", # The Cloud Storage url of the file(s) to scan, in the format `gs:///`. Trailing wildcard in the path is allowed. If the url ends in a trailing slash, the bucket or directory represented by the url will be scanned non-recursively (content in sub-directories will not be scanned). This means that `gs://mybucket/` is equivalent to `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to `gs://mybucket/directory/*`. Exactly one of `url` or `regex_file_set` must be set.
},
"fileTypes": [ # List of file type groups to include in the scan. If empty, all files are scanned and available data format processors are applied. In addition, the binary content of the selected files is always scanned as well. Images are scanned only as binary if the specified region does not support image inspection and no file_types were specified. Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
"A String",
],
"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet. Number of files scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0.
"sampleMethod": "A String", # How to sample the data.
},
"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
"kind": { # A representation of a Datastore kind. # The kind to process.
"name": "A String", # The name of the kind.
},
"partitionId": { # Datastore partition ID. A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty. A partition ID contains several dimensions: project ID and namespace ID. # A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty.
"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
"projectId": "A String", # The ID of the project to which the entities belong.
},
},
"hybridOptions": { # Configuration to control jobs where the content being inspected is outside of Google Cloud Platform. # Hybrid inspection options.
"description": "A String", # A short description of where the data is coming from. Will be stored once in the job. 256 max length.
"labels": { # To organize findings, these labels will be added to each finding. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. Label values must be between 0 and 63 characters long and must conform to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`. No more than 10 labels can be associated with a given finding. Examples: * `"environment" : "production"` * `"pipeline" : "etl"`
"a_key": "A String",
},
"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their 'finding_labels' map. Request may contain others, but any missing one of these will be rejected. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. No more than 10 keys can be required.
"A String",
],
"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings meaningful such as the columns that are primary keys.
"identifyingFields": [ # The columns that are the primary keys for table objects included in ContentItem. A copy of this cell's value will stored alongside alongside each finding so that the finding can be traced to the specific row it came from. No more than 3 may be provided.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
},
"timespanConfig": { # Configuration of the timespan of the items to include in scanning. Currently only supported when inspecting Cloud Storage and BigQuery. # Configuration of the timespan of the items to include in scanning.
"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out a valid start_time to avoid scanning files that have not been modified since the last time the JobTrigger executed. This will be based on the time of the execution of the last run of the JobTrigger or the timespan end_time used in the last run of the JobTrigger. **For BigQuery** Inspect jobs triggered by automatic population will scan data that is at least three hours old when the job starts. This is because streaming buffer rows are not read during inspection and reading up to the current timestamp will result in skipped rows. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#recently-streamed-data) related to this operation.
"endTime": "A String", # Exclude files, tables, or rows newer than this value. If not set, no upper time limit is applied.
"startTime": "A String", # Exclude files, tables, or rows older than this value. If not set, no lower time limit is applied.
"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items. Used for data sources like Datastore and BigQuery. **For BigQuery** If this value is not specified and the table was modified between the given start and end times, the entire table will be scanned. If this value is specified, then rows are filtered based on the given start and end times. Rows with a `NULL` value in the provided BigQuery column are skipped. Valid data types of the provided BigQuery column are: `INTEGER`, `DATE`, `TIMESTAMP`, and `DATETIME`. If your BigQuery table is [partitioned at ingestion time](https://cloud.google.com/bigquery/docs/partitioned-tables#ingestion_time), you can use any of the following pseudo-columns as your timestamp field. When used with Cloud DLP, these pseudo-column names are case sensitive. - `_PARTITIONTIME` - `_PARTITIONDATE` - `_PARTITION_LOAD_TIME` **For Datastore** If this value is specified, then entities are filtered based on the given start and end times. If an entity does not contain the provided timestamp property or contains empty or invalid values, then it is included. Valid data types of the provided timestamp property are: `TIMESTAMP`. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-timespan) related to this operation.
"name": "A String", # Name describing the field.
},
},
},
},
"snapshotInspectTemplate": { # The inspectTemplate contains a configuration (set of types of sensitive data to be detected) to be used anywhere you otherwise would normally specify InspectConfig. See https://cloud.google.com/sensitive-data-protection/docs/concepts-templates to learn more. # If run with an InspectTemplate, a snapshot of its state at the time of this run.
"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.
"description": "A String", # Short description (max 256 chars).
"displayName": "A String", # Display name (max 256 chars).
"inspectConfig": { # Configuration description of the scanning process. When used with redactContent only info_types and min_likelihood are currently used. # The core content of the template. Configuration of the scanning process.
"contentOptions": [ # Deprecated and unused.
"A String",
],
"customInfoTypes": [ # CustomInfoTypes provided by the user. See https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes to learn more.
{ # Custom information type provided by the user. Used to find domain-specific sensitive information configurable to the data in question.
"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. Rules are applied in order that they are specified. Not supported for the `surrogate_type` CustomInfoType.
{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a `CustomInfoType` to alter behavior under certain circumstances, depending on the specific details of the rule. Not supported for the `surrogate_type` custom infoType.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "$\d{3}$ \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "$xxx$", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # A list of phrases to detect as a CustomInfoType.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding to be returned. It still can be used for rules matching.
"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in infoType, when the name matches one of existing infoTypes and that infoType is specified in `InspectContent.info_types` field. Specifying the latter adds findings to the one detected by the system. If built-in info type is not specified in `InspectContent.info_types` list then the name is treated as a custom info type.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be altered by a detection rule if the finding meets the criteria specified by the rule. Defaults to `VERY_LIKELY` if not specified.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Sensitivity for this CustomInfoType. If this CustomInfoType extends an existing InfoType, the sensitivity here will take precedence over that of the original InfoType. If unset for a CustomInfoType, it will default to HIGH. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in `InspectDataSource`. Not currently supported in `InspectContent`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for inspection was created. Output-only field, populated by the system.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example `organizations/433245324/storedInfoTypes/432452342` or `projects/project-id/storedInfoTypes/432452342`.
},
"surrogateType": { # Message for detecting output from deidentification transformations such as [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). These types of transformations are those that perform pseudonymization, thereby producing a "surrogate" as output. This should be used in conjunction with a field on the transformation such as `surrogate_info_type`. This CustomInfoType does not support the use of `detection_rules`. # Message for detecting output from deidentification transformations that support reversing.
},
},
],
"excludeInfoTypes": True or False, # When true, excludes type information of the findings. This is not used for data profiling.
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is included in the response; see Finding.quote. This is not used for data profiling.
"infoTypes": [ # Restricts what info_types to look for. The values must correspond to InfoType values returned by ListInfoTypes or listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference. When no InfoTypes or CustomInfoTypes are specified in a request, the system may automatically choose a default list of detectors to run, which may change over time. If you need precise control and predictability as to what detectors are run you should specify specific InfoTypes listed in the reference, otherwise a default list will be used, which may change over time.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"limits": { # Configuration to control the number of findings returned for inspection. This is not used for de-identification or data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. # Configuration to control the number of findings returned. This is not used for data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. When set within an InspectJobConfig, the specified maximum values aren't hard limits. If an inspection job reaches these limits, the job ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than these maximum values.
"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
{ # Max findings configuration per infoType, per content item or long running DlpJob.
"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per info_type should be provided. If InfoTypeLimit does not have an info_type, the DLP API applies the limit against all info_types that are found but not specified in another InfoTypeLimit.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that are returned for each item scanned. When set within an InspectContentRequest, this field is ignored. This value isn't a hard limit. If the number of findings for an item reaches this limit, the inspection of that item ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns for the item can be multiple times higher than this value.
"maxFindingsPerRequest": 42, # Max number of findings that are returned per request or job. If you set this field in an InspectContentRequest, the resulting maximum value is the value that you set or 3,000, whichever is lower. This value isn't a hard limit. If an inspection reaches this limit, the inspection ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than this value.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. The default is POSSIBLE. In general, the highest likelihood setting yields the fewest findings in results and the lowest chance of a false positive. For more information, see [Match likelihood](https://cloud.google.com/sensitive-data-protection/docs/likelihood).
"minLikelihoodPerInfoType": [ # Minimum likelihood per infotype. For each infotype, a user can specify a minimum likelihood. The system only returns a finding if its likelihood is above this threshold. If this field is not set, the system uses the InspectConfig min_likelihood.
{ # Configuration for setting a minimum likelihood per infotype. Used to customize the minimum likelihood level for specific infotypes in the request. For example, use this if you want to lower the precision for PERSON_NAME without lowering the precision for the other infotypes in the request.
"infoType": { # Type of information detected by the API. # Type of information the likelihood threshold applies to. Only one likelihood per info_type should be provided. If InfoTypeLikelihood does not have an info_type, the configuration fails.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. This field is required or else the configuration fails.
},
],
"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. Exclusion rules, contained in the set are executed in the end, other rules are executed in the order they are specified for each info type.
{ # Rule set for modifying a set of infoTypes to alter behavior under certain circumstances, depending on the specific details of the rules within the set.
"infoTypes": [ # List of infoTypes this rule set is applied to.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
{ # A single inspection rule to be applied to infoTypes, specified in `InspectionRuleSet`.
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in `InspectionRuleSet` are removed from results. # Exclusion rule.
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # Dictionary which defines the rule.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"excludeByHotword": { # The rule to exclude findings based on a hotword. For record inspection of tables, column names are considered hotwords. An example of this is to exclude a finding if it belongs to a BigQuery column that matches a specific pattern. # Drop if the hotword rule is contained in the proximate context. For tabular data, the context includes the column name.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The windowBefore property in proximity should be set to 1 if the hotword needs to be included in a column header.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
"excludeInfoTypes": { # List of excluded infoTypes. # Set of infoTypes for which findings would affect this rule.
"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or contained within with a finding of an infoType from this list. For example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and `exclusion_rule` containing `exclude_info_types.info_types` with "EMAIL_ADDRESS" the phone number findings are dropped if they overlap with EMAIL_ADDRESS finding. That leads to "555-222-2222@example.org" to generate only a single finding, namely email address.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
},
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "$\d{3}$ \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "$xxx$", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
},
],
},
"name": "A String", # Output only. The template name. The template will have one of the following formats: `projects/PROJECT_ID/inspectTemplates/TEMPLATE_ID` OR `organizations/ORGANIZATION_ID/inspectTemplates/TEMPLATE_ID`;
"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.
},
},
"result": { # All result fields mentioned below are updated while the job is processing. # A summary of the outcome of this inspection job.
"hybridStats": { # Statistics related to processing hybrid inspect requests. # Statistics related to the processing of hybrid inspect.
"abortedCount": "A String", # The number of hybrid inspection requests aborted because the job ran out of quota or was ended before they could be processed.
"pendingCount": "A String", # The number of hybrid requests currently being processed. Only populated when called via method `getDlpJob`. A burst of traffic may cause hybrid inspect requests to be enqueued. Processing will take place as quickly as possible, but resource limitations may impact how long a request is enqueued for.
"processedCount": "A String", # The number of hybrid inspection requests processed within this job.
},
"infoTypeStats": [ # Statistics of how many instances of each info type were found during inspect job.
{ # Statistics regarding a specific InfoType.
"count": "A String", # Number of findings for this infoType.
"infoType": { # Type of information detected by the API. # The type of finding this stat is for.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"numRowsProcessed": "A String", # Number of rows scanned after sampling and time filtering (applicable for row based stores such as BigQuery).
"processedBytes": "A String", # Total size in bytes that were processed.
"totalEstimatedBytes": "A String", # Estimate of the number of bytes to process.
},
},
"jobTriggerName": "A String", # If created by a job trigger, the resource name of the trigger that instantiated the job.
"lastModified": "A String", # Time when the job was last modified by the system.
"name": "A String", # The server-assigned name.
"riskDetails": { # Result of a risk analysis operation request. # Results from analyzing risk of a data source.
"categoricalStatsResult": { # Result of the categorical stats computation. # Categorical stats result
"valueFrequencyHistogramBuckets": [ # Histogram of value frequencies in the column.
{ # Histogram of value frequencies in the column.
"bucketSize": "A String", # Total number of values in this bucket.
"bucketValueCount": "A String", # Total number of distinct values in this bucket.
"bucketValues": [ # Sample of value frequencies in this bucket. The total number of values returned per bucket is capped at 20.
{ # A value of a field, including its frequency.
"count": "A String", # How many times the value is contained in the field.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # A value contained in the field in question.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
"valueFrequencyLowerBound": "A String", # Lower bound on the value frequency of the values in this bucket.
"valueFrequencyUpperBound": "A String", # Upper bound on the value frequency of the values in this bucket.
},
],
},
"deltaPresenceEstimationResult": { # Result of the δ-presence computation. Note that these results are an estimation, not exact values. # Delta-presence result
"deltaPresenceEstimationHistogram": [ # The intervals [min_probability, max_probability) do not overlap. If a value doesn't correspond to any such interval, the associated frequency is zero. For example, the following records: {min_probability: 0, max_probability: 0.1, frequency: 17} {min_probability: 0.2, max_probability: 0.3, frequency: 42} {min_probability: 0.3, max_probability: 0.4, frequency: 99} mean that there are no record with an estimated probability in [0.1, 0.2) nor larger or equal to 0.4.
{ # A DeltaPresenceEstimationHistogramBucket message with the following values: min_probability: 0.1 max_probability: 0.2 frequency: 42 means that there are 42 records for which δ is in [0.1, 0.2). An important particular case is when min_probability = max_probability = 1: then, every individual who shares this quasi-identifier combination is in the dataset.
"bucketSize": "A String", # Number of records within these probability bounds.
"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.
"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total number of classes returned per bucket is capped at 20.
{ # A tuple of values for the quasi-identifier columns.
"estimatedProbability": 3.14, # The estimated probability that a given individual sharing these quasi-identifier values is in the dataset. This value, typically called δ, is the ratio between the number of records in the dataset with these quasi-identifier values, and the total number of individuals (inside *and* outside the dataset) with these quasi-identifier values. For example, if there are 15 individuals in the dataset who share the same quasi-identifier values, and an estimated 100 people in the entire population with these values, then δ is 0.15.
"quasiIdsValues": [ # The quasi-identifier values.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
},
],
"maxProbability": 3.14, # Always greater than or equal to min_probability.
"minProbability": 3.14, # Between 0 and 1.
},
],
},
"kAnonymityResult": { # Result of the k-anonymity computation. # K-anonymity result
"equivalenceClassHistogramBuckets": [ # Histogram of k-anonymity equivalence classes.
{ # Histogram of k-anonymity equivalence classes.
"bucketSize": "A String", # Total number of equivalence classes in this bucket.
"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.
"bucketValues": [ # Sample of equivalence classes in this bucket. The total number of classes returned per bucket is capped at 20.
{ # The set of columns' values that share the same ldiversity value
"equivalenceClassSize": "A String", # Size of the equivalence class, for example number of rows with the above set of values.
"quasiIdsValues": [ # Set of values defining the equivalence class. One value per quasi-identifier column in the original KAnonymity metric message. The order is always the same as the original request.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
},
],
"equivalenceClassSizeLowerBound": "A String", # Lower bound on the size of the equivalence classes in this bucket.
"equivalenceClassSizeUpperBound": "A String", # Upper bound on the size of the equivalence classes in this bucket.
},
],
},
"kMapEstimationResult": { # Result of the reidentifiability analysis. Note that these results are an estimation, not exact values. # K-map result
"kMapEstimationHistogram": [ # The intervals [min_anonymity, max_anonymity] do not overlap. If a value doesn't correspond to any such interval, the associated frequency is zero. For example, the following records: {min_anonymity: 1, max_anonymity: 1, frequency: 17} {min_anonymity: 2, max_anonymity: 3, frequency: 42} {min_anonymity: 5, max_anonymity: 10, frequency: 99} mean that there are no record with an estimated anonymity of 4, 5, or larger than 10.
{ # A KMapEstimationHistogramBucket message with the following values: min_anonymity: 3 max_anonymity: 5 frequency: 42 means that there are 42 records whose quasi-identifier values correspond to 3, 4 or 5 people in the overlying population. An important particular case is when min_anonymity = max_anonymity = 1: the frequency field then corresponds to the number of uniquely identifiable records.
"bucketSize": "A String", # Number of records within these anonymity bounds.
"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.
"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total number of classes returned per bucket is capped at 20.
{ # A tuple of values for the quasi-identifier columns.
"estimatedAnonymity": "A String", # The estimated anonymity for these quasi-identifier values.
"quasiIdsValues": [ # The quasi-identifier values.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
},
],
"maxAnonymity": "A String", # Always greater than or equal to min_anonymity.
"minAnonymity": "A String", # Always positive.
},
],
},
"lDiversityResult": { # Result of the l-diversity computation. # L-divesity result
"sensitiveValueFrequencyHistogramBuckets": [ # Histogram of l-diversity equivalence class sensitive value frequencies.
{ # Histogram of l-diversity equivalence class sensitive value frequencies.
"bucketSize": "A String", # Total number of equivalence classes in this bucket.
"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.
"bucketValues": [ # Sample of equivalence classes in this bucket. The total number of classes returned per bucket is capped at 20.
{ # The set of columns' values that share the same ldiversity value.
"equivalenceClassSize": "A String", # Size of the k-anonymity equivalence class.
"numDistinctSensitiveValues": "A String", # Number of distinct sensitive values in this equivalence class.
"quasiIdsValues": [ # Quasi-identifier values defining the k-anonymity equivalence class. The order is always the same as the original request.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
"topSensitiveValues": [ # Estimated frequencies of top sensitive values.
{ # A value of a field, including its frequency.
"count": "A String", # How many times the value is contained in the field.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # A value contained in the field in question.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
],
"sensitiveValueFrequencyLowerBound": "A String", # Lower bound on the sensitive value frequencies of the equivalence classes in this bucket.
"sensitiveValueFrequencyUpperBound": "A String", # Upper bound on the sensitive value frequencies of the equivalence classes in this bucket.
},
],
},
"numericalStatsResult": { # Result of the numerical stats computation. # Numerical stats result
"maxValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Maximum value appearing in the column.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"minValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Minimum value appearing in the column.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"quantileValues": [ # List of 99 values that partition the set of field values into 100 equal sized buckets.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
},
"requestedOptions": { # Risk analysis options. # The configuration used for this job.
"jobConfig": { # Configuration for a risk analysis job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-risk-analysis to learn more. # The job config for the risk job.
"actions": [ # Actions to execute at the completion of the job. Are executed in the order provided.
{ # A task to execute on the completion of a job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-actions to learn more.
"deidentify": { # Create a de-identified copy of the requested table or files. A TransformationDetail will be created for each transformation. If any rows in BigQuery are skipped during de-identification (transformation errors or row size exceeds BigQuery insert API limits) they are placed in the failure output table. If the original row exceeds the BigQuery insert API limit it will be truncated when written to the failure output table. The failure output table can be set in the action.deidentify.output.big_query_output.deidentified_failure_output_table field, if no table is set, a table will be automatically created in the same project and dataset as the original table. Compatible with: Inspect # Create a de-identified copy of the input data.
"cloudStorageOutput": "A String", # Required. User settable Cloud Storage bucket and folders to store de-identified files. This field must be set for Cloud Storage deidentification. The output Cloud Storage bucket must be different from the input bucket. De-identified files will overwrite files in the output path. Form of: gs://bucket/folder/ or gs://bucket
"fileTypesToTransform": [ # List of user-specified file type groups to transform. If specified, only the files with these file types will be transformed. If empty, all supported files will be transformed. Supported types may be automatically added over time. If a file type is set in this field that isn't supported by the Deidentify action then the job will fail and will not be successfully created/started. Currently the only file types supported are: IMAGES, TEXT_FILES, CSV, TSV.
"A String",
],
"transformationConfig": { # User specified templates and configs for how to deidentify structured, unstructures, and image files. User must provide either a unstructured deidentify template or at least one redact image config. # User specified deidentify templates and configs for structured, unstructured, and image files.
"deidentifyTemplate": "A String", # De-identify template. If this template is specified, it will serve as the default de-identify template. This template cannot contain `record_transformations` since it can be used for unstructured content such as free-form text files. If this template is not set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify unstructured content.
"imageRedactTemplate": "A String", # Image redact template. If this template is specified, it will serve as the de-identify template for images. If this template is not set, all findings in the image will be redacted with a black box.
"structuredDeidentifyTemplate": "A String", # Structured de-identify template. If this template is specified, it will serve as the de-identify template for structured content such as delimited files and tables. If this template is not set but the `deidentify_template` is set, then `deidentify_template` will also apply to the structured content. If neither template is set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify structured content.
},
"transformationDetailsStorageConfig": { # Config for storing transformation details. # Config for storing transformation details. This is separate from the de-identified content, and contains metadata about the successful transformations and/or failures that occurred while de-identifying. This needs to be set in order for users to access information about the status of each transformation (see TransformationDetails message for more information about what is noted).
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # The BigQuery table in which to store the output. This may be an existing table or in a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_transformation_details_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"jobNotificationEmails": { # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts). # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts).
},
"pubSub": { # Publish a message into a given Pub/Sub topic when DlpJob has completed. The message contains a single field, `DlpJobName`, which is equal to the finished job's [`DlpJob.name`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/projects.dlpJobs#DlpJob). Compatible with: Inspect, Risk # Publish a notification to a Pub/Sub topic.
"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given publishing access rights to the DLP API service account executing the long running DlpJob sending the notifications. Format is projects/{project}/topics/{topic}.
},
"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Data Catalog. In Data Catalog, tag templates are applied to the resource that Cloud DLP scanned. Data Catalog tag templates are stored in the same project and region where the BigQuery table exists. For Cloud DLP to create and apply the tag template, the Cloud DLP service agent must have the `roles/datacatalog.tagTemplateOwner` permission on the project. The tag template contains fields summarizing the results of the DlpJob. Any field values previously written by another DlpJob are deleted. InfoType naming patterns are strictly enforced when using this feature. Findings are persisted in Data Catalog storage and are governed by service-specific policies for Data Catalog. For more information, see [Service Specific Terms](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. This action is allowed only if all resources being scanned are BigQuery tables. Compatible with: Inspect # Publish findings to Cloud Datahub.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to [Security Command Center](https://cloud.google.com/security-command-center). This action is available for only projects that belong to an organization. This action publishes the count of finding instances and their infoTypes. The summary of findings are persisted in Security Command Center and are governed by [service-specific policies for Security Command Center](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. Compatible with: Inspect # Publish summary to Cloud Security Command Center (Alpha).
},
"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This will publish a metric to stack driver on each infotype requested and how many findings were found for it. CustomDetectors will be bucketed as 'Custom' under the Stackdriver label 'info_type'. # Enable Stackdriver metric dlp.googleapis.com/finding_count.
},
"saveFindings": { # If set, the detailed findings will be persisted to the specified OutputStorageConfig. Only a single instance of this action can be specified. Compatible with: Inspect, Risk # Save resulting findings in a provided location.
"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only used for Inspect and must be unspecified for Risk jobs. Columns are derived from the `Finding` object. If appending to an existing table, any columns from the predefined schema that are missing will be added. No columns in the existing table will be deleted. If unspecified, then all available columns will be used for a new table or an (existing) table with no schema, and no changes will be made to an existing table that has a schema. Only for use with external storage.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Store findings in an existing table or a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details. For Inspect, each column in an existing output table must have the same name, type, and mode of a field in the `Finding` object. For Risk, an existing output table should be the output of a previous Risk analysis job run on the same source table, with the same privacy metric and quasi-identifiers. Risk jobs that analyze the same table but compute a different privacy metric, or use different sets of quasi-identifiers, cannot store their results in the same table.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
},
],
"privacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.
"categoricalStatsConfig": { # Compute numerical stats over an individual column, including number of distinct values and value count distribution. # Categorical stats
"field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are supported except for arrays and structs. However, it may be more informative to use NumericalStats when the field type is supported, depending on the data.
"name": "A String", # Name describing the field.
},
},
"deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to figure out that one given individual appears in a de-identified dataset. Similarly to the k-map metric, we cannot compute δ-presence exactly without knowing the attack dataset, so we use a statistical model instead. # delta-presence
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers field must appear in exactly one field of one auxiliary table.
{ # An auxiliary table containing statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity
"entityId": { # An entity in a dataset is a field or set of fields that correspond to a single person. For example, in medical records the `EntityId` might be a patient identifier, or for financial records it might be an account identifier. This message is used when generalizations or analysis must take into account that multiple rows correspond to the same entity. # Message indicating that multiple rows might be associated to a single individual. If the same entity_id is associated to multiple quasi-identifier tuples over distinct rows, we consider the entire collection of tuples as the composite quasi-identifier. This collection is a multiset: the order in which the different tuples appear in the dataset is ignored, but their frequency is taken into account. Important note: a maximum of 1000 rows can be associated to a single entity ID. If more rows are associated with the same entity ID, some might be ignored.
"field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier.
"name": "A String", # Name describing the field.
},
},
"quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are specified, they are considered a single composite key. Structs and repeated data types are not supported; however, nested fields are supported so long as they are not structs themselves or nested within a repeated field.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
"kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what is called "journalist risk" in the literature, except the attack dataset is statistically modeled instead of being perfectly known. This can be done using publicly available data (like the US Census), or using a custom statistical model (indicated as one or several BigQuery tables), or by extrapolating from the distribution of values in the input dataset. # k-map
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers column must appear in exactly one column of one auxiliary table.
{ # An auxiliary table contains statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A auxiliary field.
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity
"quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are defined for the l-diversity computation. When multiple fields are specified, they are considered a single composite key.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value.
"name": "A String", # Name describing the field.
},
},
"numericalStatsConfig": { # Compute numerical stats over an individual column, including min, max, and quantiles. # Numerical stats
"field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are integer, float, date, datetime, timestamp, time.
"name": "A String", # Name describing the field.
},
},
},
"sourceTable": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Input dataset to compute metrics over.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"requestedPrivacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.
"categoricalStatsConfig": { # Compute numerical stats over an individual column, including number of distinct values and value count distribution. # Categorical stats
"field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are supported except for arrays and structs. However, it may be more informative to use NumericalStats when the field type is supported, depending on the data.
"name": "A String", # Name describing the field.
},
},
"deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to figure out that one given individual appears in a de-identified dataset. Similarly to the k-map metric, we cannot compute δ-presence exactly without knowing the attack dataset, so we use a statistical model instead. # delta-presence
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers field must appear in exactly one field of one auxiliary table.
{ # An auxiliary table containing statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity
"entityId": { # An entity in a dataset is a field or set of fields that correspond to a single person. For example, in medical records the `EntityId` might be a patient identifier, or for financial records it might be an account identifier. This message is used when generalizations or analysis must take into account that multiple rows correspond to the same entity. # Message indicating that multiple rows might be associated to a single individual. If the same entity_id is associated to multiple quasi-identifier tuples over distinct rows, we consider the entire collection of tuples as the composite quasi-identifier. This collection is a multiset: the order in which the different tuples appear in the dataset is ignored, but their frequency is taken into account. Important note: a maximum of 1000 rows can be associated to a single entity ID. If more rows are associated with the same entity ID, some might be ignored.
"field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier.
"name": "A String", # Name describing the field.
},
},
"quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are specified, they are considered a single composite key. Structs and repeated data types are not supported; however, nested fields are supported so long as they are not structs themselves or nested within a repeated field.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
"kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what is called "journalist risk" in the literature, except the attack dataset is statistically modeled instead of being perfectly known. This can be done using publicly available data (like the US Census), or using a custom statistical model (indicated as one or several BigQuery tables), or by extrapolating from the distribution of values in the input dataset. # k-map
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers column must appear in exactly one column of one auxiliary table.
{ # An auxiliary table contains statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A auxiliary field.
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity
"quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are defined for the l-diversity computation. When multiple fields are specified, they are considered a single composite key.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value.
"name": "A String", # Name describing the field.
},
},
"numericalStatsConfig": { # Compute numerical stats over an individual column, including min, max, and quantiles. # Numerical stats
"field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are integer, float, date, datetime, timestamp, time.
"name": "A String", # Name describing the field.
},
},
},
"requestedSourceTable": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Input dataset to compute metrics over.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
"startTime": "A String", # Time when the job started.
"state": "A String", # State of a job.
"type": "A String", # The type of job.
}

delete(name, x__xgafv=None)

Deletes a long-running DlpJob. This method indicates that the client is no longer interested in the DlpJob result. The job will be canceled if possible. See https://cloud.google.com/sensitive-data-protection/docs/inspecting-storage and https://cloud.google.com/sensitive-data-protection/docs/compute-risk-analysis to learn more.

Args:
  name: string, Required. The name of the DlpJob resource to be deleted. (required)
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); }
}

finish(name, body=None, x__xgafv=None)

Finish a running hybrid DlpJob. Triggers the finalization steps and running of any enabled actions that have not yet run.

Args:
  name: string, Required. The name of the DlpJob resource to be finished. (required)
  body: object, The request body.
    The object takes the form of:

{ # The request message for finishing a DLP hybrid job.
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); }
}

get(name, x__xgafv=None)

Gets the latest state of a long-running DlpJob. See https://cloud.google.com/sensitive-data-protection/docs/inspecting-storage and https://cloud.google.com/sensitive-data-protection/docs/compute-risk-analysis to learn more.

Args:
name: string, Required. The name of the DlpJob resource. (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format

Returns:
An object of the form:

{ # Combines all of the information about a DLP job.
"actionDetails": [ # Events that should occur after the job has completed.
{ # The results of an Action.
"deidentifyDetails": { # The results of a Deidentify action from an inspect job. # Outcome of a de-identification action.
"deidentifyStats": { # Summary of what was modified during a transformation. # Stats about the de-identification operation.
"transformationCount": "A String", # Number of successfully applied transformations.
"transformationErrorCount": "A String", # Number of errors encountered while trying to apply transformations.
"transformedBytes": "A String", # Total size in bytes that were transformed in some way.
},
"requestedOptions": { # De-identification options. # De-identification config used for the request.
"snapshotDeidentifyTemplate": { # DeidentifyTemplates contains instructions on how to de-identify content. See https://cloud.google.com/sensitive-data-protection/docs/concepts-templates to learn more. # Snapshot of the state of the `DeidentifyTemplate` from the Deidentify action at the time this job was run.
"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.
"deidentifyConfig": { # The configuration that controls how the data will change. # The core content of the template.
"imageTransformations": { # A type of transformation that is applied over images. # Treat the dataset as an image and redact.
"transforms": [ # List of transforms to make.
{ # Configuration for determining how redaction of images should occur.
"allInfoTypes": { # Apply transformation to all findings. # Apply transformation to all findings not specified in other ImageTransformation's selected_info_types. Only one instance is allowed within the ImageTransformations message.
},
"allText": { # Apply to all text. # Apply transformation to all text that doesn't match an infoType. Only one instance is allowed within the ImageTransformations message.
},
"redactionColor": { # Represents a color in the RGB color space. # The color to use when redacting content from an image. If not specified, the default is black.
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"selectedInfoTypes": { # Apply transformation to the selected info_types. # Apply transformation to the selected info_types.
"infoTypes": [ # Required. InfoTypes to apply the transformation to. Required. Provided InfoType must be unique within the ImageTransformations message.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
},
],
},
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the dataset as free-form text and apply the same free text transformation everywhere.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"recordTransformations": { # A type of transformation that is applied over structured data such as a table. # Treat the dataset as structured. Transformations can be applied to specific locations within structured datasets, such as transforming a column within a table.
"fieldTransformations": [ # Transform the record by applying various field transformations.
{ # The transformation to apply to the field.
"condition": { # A condition for determining whether a transformation should be applied to a field. # Only apply the transformation if the condition evaluates to true for the given `RecordCondition`. The conditions are allowed to reference fields that are not used in the actual transformation. Example Use Cases: - Apply a different bucket transformation to an age column if the zip code column for the same record is within a specific range. - Redact a field if the date of birth field is greater than 85.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
"fields": [ # Required. Input field(s) to apply the transformation to. When you have columns that reference their position within a list, omit the index from the FieldId. FieldId name matching ignores the index. For example, instead of "contact.nums[0].type", use "contact.nums.type".
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the contents of the field as free text, and selectively transform content that matches an `InfoType`.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"primitiveTransformation": { # A rule for transforming a value. # Apply the transformation to the entire field.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
"recordSuppressions": [ # Configuration defining which records get suppressed entirely. Records that match any suppression rule are omitted from the output.
{ # Configuration to suppress records whose suppression conditions evaluate to true.
"condition": { # A condition for determining whether a transformation should be applied to a field. # A condition that when it evaluates to true will result in the record being evaluated to be suppressed from the transformed content.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
},
],
},
"transformationErrorHandling": { # How to handle transformation errors during de-identification. A transformation error occurs when the requested transformation is incompatible with the data. For example, trying to de-identify an IP address using a `DateShift` transformation would result in a transformation error, since date info cannot be extracted from an IP address. Information about any incompatible transformations, and how they were handled, is returned in the response as part of the `TransformationOverviews`. # Mode for handling transformation errors. If left unspecified, the default mode is `TransformationErrorHandling.ThrowError`.
"leaveUntransformed": { # Skips the data without modifying it if the requested transformation would cause an error. For example, if a `DateShift` transformation were applied an an IP address, this mode would leave the IP address unchanged in the response. # Ignore errors
},
"throwError": { # Throw an error and fail the request when a transformation error occurs. # Throw an error
},
},
},
"description": "A String", # Short description (max 256 chars).
"displayName": "A String", # Display name (max 256 chars).
"name": "A String", # Output only. The template name. The template will have one of the following formats: `projects/PROJECT_ID/deidentifyTemplates/TEMPLATE_ID` OR `organizations/ORGANIZATION_ID/deidentifyTemplates/TEMPLATE_ID`
"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.
},
"snapshotImageRedactTemplate": { # DeidentifyTemplates contains instructions on how to de-identify content. See https://cloud.google.com/sensitive-data-protection/docs/concepts-templates to learn more. # Snapshot of the state of the image transformation `DeidentifyTemplate` from the `Deidentify` action at the time this job was run.
"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.
"deidentifyConfig": { # The configuration that controls how the data will change. # The core content of the template.
"imageTransformations": { # A type of transformation that is applied over images. # Treat the dataset as an image and redact.
"transforms": [ # List of transforms to make.
{ # Configuration for determining how redaction of images should occur.
"allInfoTypes": { # Apply transformation to all findings. # Apply transformation to all findings not specified in other ImageTransformation's selected_info_types. Only one instance is allowed within the ImageTransformations message.
},
"allText": { # Apply to all text. # Apply transformation to all text that doesn't match an infoType. Only one instance is allowed within the ImageTransformations message.
},
"redactionColor": { # Represents a color in the RGB color space. # The color to use when redacting content from an image. If not specified, the default is black.
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"selectedInfoTypes": { # Apply transformation to the selected info_types. # Apply transformation to the selected info_types.
"infoTypes": [ # Required. InfoTypes to apply the transformation to. Required. Provided InfoType must be unique within the ImageTransformations message.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
},
],
},
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the dataset as free-form text and apply the same free text transformation everywhere.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"recordTransformations": { # A type of transformation that is applied over structured data such as a table. # Treat the dataset as structured. Transformations can be applied to specific locations within structured datasets, such as transforming a column within a table.
"fieldTransformations": [ # Transform the record by applying various field transformations.
{ # The transformation to apply to the field.
"condition": { # A condition for determining whether a transformation should be applied to a field. # Only apply the transformation if the condition evaluates to true for the given `RecordCondition`. The conditions are allowed to reference fields that are not used in the actual transformation. Example Use Cases: - Apply a different bucket transformation to an age column if the zip code column for the same record is within a specific range. - Redact a field if the date of birth field is greater than 85.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
"fields": [ # Required. Input field(s) to apply the transformation to. When you have columns that reference their position within a list, omit the index from the FieldId. FieldId name matching ignores the index. For example, instead of "contact.nums[0].type", use "contact.nums.type".
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the contents of the field as free text, and selectively transform content that matches an `InfoType`.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"primitiveTransformation": { # A rule for transforming a value. # Apply the transformation to the entire field.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
"recordSuppressions": [ # Configuration defining which records get suppressed entirely. Records that match any suppression rule are omitted from the output.
{ # Configuration to suppress records whose suppression conditions evaluate to true.
"condition": { # A condition for determining whether a transformation should be applied to a field. # A condition that when it evaluates to true will result in the record being evaluated to be suppressed from the transformed content.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
},
],
},
"transformationErrorHandling": { # How to handle transformation errors during de-identification. A transformation error occurs when the requested transformation is incompatible with the data. For example, trying to de-identify an IP address using a `DateShift` transformation would result in a transformation error, since date info cannot be extracted from an IP address. Information about any incompatible transformations, and how they were handled, is returned in the response as part of the `TransformationOverviews`. # Mode for handling transformation errors. If left unspecified, the default mode is `TransformationErrorHandling.ThrowError`.
"leaveUntransformed": { # Skips the data without modifying it if the requested transformation would cause an error. For example, if a `DateShift` transformation were applied an an IP address, this mode would leave the IP address unchanged in the response. # Ignore errors
},
"throwError": { # Throw an error and fail the request when a transformation error occurs. # Throw an error
},
},
},
"description": "A String", # Short description (max 256 chars).
"displayName": "A String", # Display name (max 256 chars).
"name": "A String", # Output only. The template name. The template will have one of the following formats: `projects/PROJECT_ID/deidentifyTemplates/TEMPLATE_ID` OR `organizations/ORGANIZATION_ID/deidentifyTemplates/TEMPLATE_ID`
"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.
},
"snapshotStructuredDeidentifyTemplate": { # DeidentifyTemplates contains instructions on how to de-identify content. See https://cloud.google.com/sensitive-data-protection/docs/concepts-templates to learn more. # Snapshot of the state of the structured `DeidentifyTemplate` from the `Deidentify` action at the time this job was run.
"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.
"deidentifyConfig": { # The configuration that controls how the data will change. # The core content of the template.
"imageTransformations": { # A type of transformation that is applied over images. # Treat the dataset as an image and redact.
"transforms": [ # List of transforms to make.
{ # Configuration for determining how redaction of images should occur.
"allInfoTypes": { # Apply transformation to all findings. # Apply transformation to all findings not specified in other ImageTransformation's selected_info_types. Only one instance is allowed within the ImageTransformations message.
},
"allText": { # Apply to all text. # Apply transformation to all text that doesn't match an infoType. Only one instance is allowed within the ImageTransformations message.
},
"redactionColor": { # Represents a color in the RGB color space. # The color to use when redacting content from an image. If not specified, the default is black.
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"selectedInfoTypes": { # Apply transformation to the selected info_types. # Apply transformation to the selected info_types.
"infoTypes": [ # Required. InfoTypes to apply the transformation to. Required. Provided InfoType must be unique within the ImageTransformations message.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
},
],
},
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the dataset as free-form text and apply the same free text transformation everywhere.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"recordTransformations": { # A type of transformation that is applied over structured data such as a table. # Treat the dataset as structured. Transformations can be applied to specific locations within structured datasets, such as transforming a column within a table.
"fieldTransformations": [ # Transform the record by applying various field transformations.
{ # The transformation to apply to the field.
"condition": { # A condition for determining whether a transformation should be applied to a field. # Only apply the transformation if the condition evaluates to true for the given `RecordCondition`. The conditions are allowed to reference fields that are not used in the actual transformation. Example Use Cases: - Apply a different bucket transformation to an age column if the zip code column for the same record is within a specific range. - Redact a field if the date of birth field is greater than 85.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
"fields": [ # Required. Input field(s) to apply the transformation to. When you have columns that reference their position within a list, omit the index from the FieldId. FieldId name matching ignores the index. For example, instead of "contact.nums[0].type", use "contact.nums.type".
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the contents of the field as free text, and selectively transform content that matches an `InfoType`.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"primitiveTransformation": { # A rule for transforming a value. # Apply the transformation to the entire field.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
"recordSuppressions": [ # Configuration defining which records get suppressed entirely. Records that match any suppression rule are omitted from the output.
{ # Configuration to suppress records whose suppression conditions evaluate to true.
"condition": { # A condition for determining whether a transformation should be applied to a field. # A condition that when it evaluates to true will result in the record being evaluated to be suppressed from the transformed content.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
},
],
},
"transformationErrorHandling": { # How to handle transformation errors during de-identification. A transformation error occurs when the requested transformation is incompatible with the data. For example, trying to de-identify an IP address using a `DateShift` transformation would result in a transformation error, since date info cannot be extracted from an IP address. Information about any incompatible transformations, and how they were handled, is returned in the response as part of the `TransformationOverviews`. # Mode for handling transformation errors. If left unspecified, the default mode is `TransformationErrorHandling.ThrowError`.
"leaveUntransformed": { # Skips the data without modifying it if the requested transformation would cause an error. For example, if a `DateShift` transformation were applied an an IP address, this mode would leave the IP address unchanged in the response. # Ignore errors
},
"throwError": { # Throw an error and fail the request when a transformation error occurs. # Throw an error
},
},
},
"description": "A String", # Short description (max 256 chars).
"displayName": "A String", # Display name (max 256 chars).
"name": "A String", # Output only. The template name. The template will have one of the following formats: `projects/PROJECT_ID/deidentifyTemplates/TEMPLATE_ID` OR `organizations/ORGANIZATION_ID/deidentifyTemplates/TEMPLATE_ID`
"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.
},
},
},
},
],
"createTime": "A String", # Time when the job was created.
"endTime": "A String", # Time when the job finished.
"errors": [ # A stream of errors encountered running the job.
{ # Details information about an error encountered during job execution or the results of an unsuccessful activation of the JobTrigger.
"details": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Detailed error codes and messages.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"extraInfo": "A String", # Additional information about the error.
"timestamps": [ # The times the error occurred. List includes the oldest timestamp and the last 9 timestamps.
"A String",
],
},
],
"inspectDetails": { # The results of an inspect DataSource job. # Results from inspecting a data source.
"requestedOptions": { # Snapshot of the inspection configuration. # The configuration used for this job.
"jobConfig": { # Controls what and how to inspect for findings. # Inspect config.
"actions": [ # Actions to execute at the completion of the job.
{ # A task to execute on the completion of a job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-actions to learn more.
"deidentify": { # Create a de-identified copy of the requested table or files. A TransformationDetail will be created for each transformation. If any rows in BigQuery are skipped during de-identification (transformation errors or row size exceeds BigQuery insert API limits) they are placed in the failure output table. If the original row exceeds the BigQuery insert API limit it will be truncated when written to the failure output table. The failure output table can be set in the action.deidentify.output.big_query_output.deidentified_failure_output_table field, if no table is set, a table will be automatically created in the same project and dataset as the original table. Compatible with: Inspect # Create a de-identified copy of the input data.
"cloudStorageOutput": "A String", # Required. User settable Cloud Storage bucket and folders to store de-identified files. This field must be set for Cloud Storage deidentification. The output Cloud Storage bucket must be different from the input bucket. De-identified files will overwrite files in the output path. Form of: gs://bucket/folder/ or gs://bucket
"fileTypesToTransform": [ # List of user-specified file type groups to transform. If specified, only the files with these file types will be transformed. If empty, all supported files will be transformed. Supported types may be automatically added over time. If a file type is set in this field that isn't supported by the Deidentify action then the job will fail and will not be successfully created/started. Currently the only file types supported are: IMAGES, TEXT_FILES, CSV, TSV.
"A String",
],
"transformationConfig": { # User specified templates and configs for how to deidentify structured, unstructures, and image files. User must provide either a unstructured deidentify template or at least one redact image config. # User specified deidentify templates and configs for structured, unstructured, and image files.
"deidentifyTemplate": "A String", # De-identify template. If this template is specified, it will serve as the default de-identify template. This template cannot contain `record_transformations` since it can be used for unstructured content such as free-form text files. If this template is not set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify unstructured content.
"imageRedactTemplate": "A String", # Image redact template. If this template is specified, it will serve as the de-identify template for images. If this template is not set, all findings in the image will be redacted with a black box.
"structuredDeidentifyTemplate": "A String", # Structured de-identify template. If this template is specified, it will serve as the de-identify template for structured content such as delimited files and tables. If this template is not set but the `deidentify_template` is set, then `deidentify_template` will also apply to the structured content. If neither template is set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify structured content.
},
"transformationDetailsStorageConfig": { # Config for storing transformation details. # Config for storing transformation details. This is separate from the de-identified content, and contains metadata about the successful transformations and/or failures that occurred while de-identifying. This needs to be set in order for users to access information about the status of each transformation (see TransformationDetails message for more information about what is noted).
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # The BigQuery table in which to store the output. This may be an existing table or in a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_transformation_details_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"jobNotificationEmails": { # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts). # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts).
},
"pubSub": { # Publish a message into a given Pub/Sub topic when DlpJob has completed. The message contains a single field, `DlpJobName`, which is equal to the finished job's [`DlpJob.name`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/projects.dlpJobs#DlpJob). Compatible with: Inspect, Risk # Publish a notification to a Pub/Sub topic.
"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given publishing access rights to the DLP API service account executing the long running DlpJob sending the notifications. Format is projects/{project}/topics/{topic}.
},
"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Data Catalog. In Data Catalog, tag templates are applied to the resource that Cloud DLP scanned. Data Catalog tag templates are stored in the same project and region where the BigQuery table exists. For Cloud DLP to create and apply the tag template, the Cloud DLP service agent must have the `roles/datacatalog.tagTemplateOwner` permission on the project. The tag template contains fields summarizing the results of the DlpJob. Any field values previously written by another DlpJob are deleted. InfoType naming patterns are strictly enforced when using this feature. Findings are persisted in Data Catalog storage and are governed by service-specific policies for Data Catalog. For more information, see [Service Specific Terms](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. This action is allowed only if all resources being scanned are BigQuery tables. Compatible with: Inspect # Publish findings to Cloud Datahub.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to [Security Command Center](https://cloud.google.com/security-command-center). This action is available for only projects that belong to an organization. This action publishes the count of finding instances and their infoTypes. The summary of findings are persisted in Security Command Center and are governed by [service-specific policies for Security Command Center](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. Compatible with: Inspect # Publish summary to Cloud Security Command Center (Alpha).
},
"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This will publish a metric to stack driver on each infotype requested and how many findings were found for it. CustomDetectors will be bucketed as 'Custom' under the Stackdriver label 'info_type'. # Enable Stackdriver metric dlp.googleapis.com/finding_count.
},
"saveFindings": { # If set, the detailed findings will be persisted to the specified OutputStorageConfig. Only a single instance of this action can be specified. Compatible with: Inspect, Risk # Save resulting findings in a provided location.
"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only used for Inspect and must be unspecified for Risk jobs. Columns are derived from the `Finding` object. If appending to an existing table, any columns from the predefined schema that are missing will be added. No columns in the existing table will be deleted. If unspecified, then all available columns will be used for a new table or an (existing) table with no schema, and no changes will be made to an existing table that has a schema. Only for use with external storage.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Store findings in an existing table or a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details. For Inspect, each column in an existing output table must have the same name, type, and mode of a field in the `Finding` object. For Risk, an existing output table should be the output of a previous Risk analysis job run on the same source table, with the same privacy metric and quasi-identifiers. Risk jobs that analyze the same table but compute a different privacy metric, or use different sets of quasi-identifiers, cannot store their results in the same table.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
},
],
"inspectConfig": { # Configuration description of the scanning process. When used with redactContent only info_types and min_likelihood are currently used. # How and what to scan for.
"contentOptions": [ # Deprecated and unused.
"A String",
],
"customInfoTypes": [ # CustomInfoTypes provided by the user. See https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes to learn more.
{ # Custom information type provided by the user. Used to find domain-specific sensitive information configurable to the data in question.
"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. Rules are applied in order that they are specified. Not supported for the `surrogate_type` CustomInfoType.
{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a `CustomInfoType` to alter behavior under certain circumstances, depending on the specific details of the rule. Not supported for the `surrogate_type` custom infoType.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "$\d{3}$ \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "$xxx$", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # A list of phrases to detect as a CustomInfoType.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding to be returned. It still can be used for rules matching.
"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in infoType, when the name matches one of existing infoTypes and that infoType is specified in `InspectContent.info_types` field. Specifying the latter adds findings to the one detected by the system. If built-in info type is not specified in `InspectContent.info_types` list then the name is treated as a custom info type.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be altered by a detection rule if the finding meets the criteria specified by the rule. Defaults to `VERY_LIKELY` if not specified.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Sensitivity for this CustomInfoType. If this CustomInfoType extends an existing InfoType, the sensitivity here will take precedence over that of the original InfoType. If unset for a CustomInfoType, it will default to HIGH. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in `InspectDataSource`. Not currently supported in `InspectContent`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for inspection was created. Output-only field, populated by the system.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example `organizations/433245324/storedInfoTypes/432452342` or `projects/project-id/storedInfoTypes/432452342`.
},
"surrogateType": { # Message for detecting output from deidentification transformations such as [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). These types of transformations are those that perform pseudonymization, thereby producing a "surrogate" as output. This should be used in conjunction with a field on the transformation such as `surrogate_info_type`. This CustomInfoType does not support the use of `detection_rules`. # Message for detecting output from deidentification transformations that support reversing.
},
},
],
"excludeInfoTypes": True or False, # When true, excludes type information of the findings. This is not used for data profiling.
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is included in the response; see Finding.quote. This is not used for data profiling.
"infoTypes": [ # Restricts what info_types to look for. The values must correspond to InfoType values returned by ListInfoTypes or listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference. When no InfoTypes or CustomInfoTypes are specified in a request, the system may automatically choose a default list of detectors to run, which may change over time. If you need precise control and predictability as to what detectors are run you should specify specific InfoTypes listed in the reference, otherwise a default list will be used, which may change over time.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"limits": { # Configuration to control the number of findings returned for inspection. This is not used for de-identification or data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. # Configuration to control the number of findings returned. This is not used for data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. When set within an InspectJobConfig, the specified maximum values aren't hard limits. If an inspection job reaches these limits, the job ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than these maximum values.
"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
{ # Max findings configuration per infoType, per content item or long running DlpJob.
"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per info_type should be provided. If InfoTypeLimit does not have an info_type, the DLP API applies the limit against all info_types that are found but not specified in another InfoTypeLimit.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that are returned for each item scanned. When set within an InspectContentRequest, this field is ignored. This value isn't a hard limit. If the number of findings for an item reaches this limit, the inspection of that item ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns for the item can be multiple times higher than this value.
"maxFindingsPerRequest": 42, # Max number of findings that are returned per request or job. If you set this field in an InspectContentRequest, the resulting maximum value is the value that you set or 3,000, whichever is lower. This value isn't a hard limit. If an inspection reaches this limit, the inspection ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than this value.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. The default is POSSIBLE. In general, the highest likelihood setting yields the fewest findings in results and the lowest chance of a false positive. For more information, see [Match likelihood](https://cloud.google.com/sensitive-data-protection/docs/likelihood).
"minLikelihoodPerInfoType": [ # Minimum likelihood per infotype. For each infotype, a user can specify a minimum likelihood. The system only returns a finding if its likelihood is above this threshold. If this field is not set, the system uses the InspectConfig min_likelihood.
{ # Configuration for setting a minimum likelihood per infotype. Used to customize the minimum likelihood level for specific infotypes in the request. For example, use this if you want to lower the precision for PERSON_NAME without lowering the precision for the other infotypes in the request.
"infoType": { # Type of information detected by the API. # Type of information the likelihood threshold applies to. Only one likelihood per info_type should be provided. If InfoTypeLikelihood does not have an info_type, the configuration fails.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. This field is required or else the configuration fails.
},
],
"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. Exclusion rules, contained in the set are executed in the end, other rules are executed in the order they are specified for each info type.
{ # Rule set for modifying a set of infoTypes to alter behavior under certain circumstances, depending on the specific details of the rules within the set.
"infoTypes": [ # List of infoTypes this rule set is applied to.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
{ # A single inspection rule to be applied to infoTypes, specified in `InspectionRuleSet`.
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in `InspectionRuleSet` are removed from results. # Exclusion rule.
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # Dictionary which defines the rule.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"excludeByHotword": { # The rule to exclude findings based on a hotword. For record inspection of tables, column names are considered hotwords. An example of this is to exclude a finding if it belongs to a BigQuery column that matches a specific pattern. # Drop if the hotword rule is contained in the proximate context. For tabular data, the context includes the column name.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The windowBefore property in proximity should be set to 1 if the hotword needs to be included in a column header.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
"excludeInfoTypes": { # List of excluded infoTypes. # Set of infoTypes for which findings would affect this rule.
"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or contained within with a finding of an infoType from this list. For example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and `exclusion_rule` containing `exclude_info_types.info_types` with "EMAIL_ADDRESS" the phone number findings are dropped if they overlap with EMAIL_ADDRESS finding. That leads to "555-222-2222@example.org" to generate only a single finding, namely email address.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
},
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "$\d{3}$ \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "$xxx$", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
},
],
},
"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig. `inspect_config` will be merged into the values persisted as part of the template.
"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
"excludedFields": [ # References to fields excluded from scanning. This allows you to skip inspection of entire columns which you know have no findings. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When `actions.saveFindings.outputConfig.table` is specified, the values of columns specified here are available in the output table under `location.content_locations.record_location.record_key.id_values`. Nested fields such as `person.birthdate.year` are allowed.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"includedFields": [ # Limit scanning only to these fields. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the rest of the rows are omitted. If not set, or if set to 0, all rows will be scanned. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig.
"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig. Caution: A [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-sampling) is causing the `rowsLimitPercent` field to behave unexpectedly. We recommend using `rowsLimit` instead.
"sampleMethod": "A String", # How to sample the data.
"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Complete BigQuery table reference.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
"cloudStorageOptions": { # Options defining a file or a set of files within a Cloud Storage bucket. # Cloud Storage options.
"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger than this value then the rest of the bytes are omitted. Only one of `bytes_limit_per_file` and `bytes_limit_per_file_percent` can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The number of bytes scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"fileSet": { # Set of files to scan. # The set of one or more files to scan.
"regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular expressions are used to allow fine-grained control over which files in the bucket to include. Included files are those that match at least one item in `include_regex` and do not match any items in `exclude_regex`. Note that a file that matches items from both lists will _not_ be included. For a match to occur, the entire file path (i.e., everything in the url after the bucket name) must match the regular expression. For example, given the input `{bucket_name: "mybucket", include_regex: ["directory1/.*"], exclude_regex: ["directory1/excluded.*"]}`: * `gs://mybucket/directory1/myfile` will be included * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches across `/`) * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the full path doesn't match any items in `include_regex`) * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path matches an item in `exclude_regex`) If `include_regex` is left empty, it will match all files by default (this is equivalent to setting `include_regex: [".*"]`). Some other common use cases: * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all files in `mybucket` except for .pdf files * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will include all files directly under `gs://mybucket/directory/`, without matching across `/` # The regex-filtered set of files to scan. Exactly one of `url` or `regex_file_set` must be set.
"bucketName": "A String", # The name of a Cloud Storage bucket. Required.
"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in the bucket that match at least one of these regular expressions will be excluded from the scan. Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
"includeRegex": [ # A list of regular expressions matching file paths to include. All files in the bucket that match at least one of these regular expressions will be included in the set of files, except for those that also match an item in `exclude_regex`. Leaving this field empty will match all files by default (this is equivalent to including `.*` in the list). Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
},
"url": "A String", # The Cloud Storage url of the file(s) to scan, in the format `gs:///`. Trailing wildcard in the path is allowed. If the url ends in a trailing slash, the bucket or directory represented by the url will be scanned non-recursively (content in sub-directories will not be scanned). This means that `gs://mybucket/` is equivalent to `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to `gs://mybucket/directory/*`. Exactly one of `url` or `regex_file_set` must be set.
},
"fileTypes": [ # List of file type groups to include in the scan. If empty, all files are scanned and available data format processors are applied. In addition, the binary content of the selected files is always scanned as well. Images are scanned only as binary if the specified region does not support image inspection and no file_types were specified. Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
"A String",
],
"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet. Number of files scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0.
"sampleMethod": "A String", # How to sample the data.
},
"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
"kind": { # A representation of a Datastore kind. # The kind to process.
"name": "A String", # The name of the kind.
},
"partitionId": { # Datastore partition ID. A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty. A partition ID contains several dimensions: project ID and namespace ID. # A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty.
"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
"projectId": "A String", # The ID of the project to which the entities belong.
},
},
"hybridOptions": { # Configuration to control jobs where the content being inspected is outside of Google Cloud Platform. # Hybrid inspection options.
"description": "A String", # A short description of where the data is coming from. Will be stored once in the job. 256 max length.
"labels": { # To organize findings, these labels will be added to each finding. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. Label values must be between 0 and 63 characters long and must conform to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`. No more than 10 labels can be associated with a given finding. Examples: * `"environment" : "production"` * `"pipeline" : "etl"`
"a_key": "A String",
},
"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their 'finding_labels' map. Request may contain others, but any missing one of these will be rejected. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. No more than 10 keys can be required.
"A String",
],
"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings meaningful such as the columns that are primary keys.
"identifyingFields": [ # The columns that are the primary keys for table objects included in ContentItem. A copy of this cell's value will stored alongside alongside each finding so that the finding can be traced to the specific row it came from. No more than 3 may be provided.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
},
"timespanConfig": { # Configuration of the timespan of the items to include in scanning. Currently only supported when inspecting Cloud Storage and BigQuery. # Configuration of the timespan of the items to include in scanning.
"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out a valid start_time to avoid scanning files that have not been modified since the last time the JobTrigger executed. This will be based on the time of the execution of the last run of the JobTrigger or the timespan end_time used in the last run of the JobTrigger. **For BigQuery** Inspect jobs triggered by automatic population will scan data that is at least three hours old when the job starts. This is because streaming buffer rows are not read during inspection and reading up to the current timestamp will result in skipped rows. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#recently-streamed-data) related to this operation.
"endTime": "A String", # Exclude files, tables, or rows newer than this value. If not set, no upper time limit is applied.
"startTime": "A String", # Exclude files, tables, or rows older than this value. If not set, no lower time limit is applied.
"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items. Used for data sources like Datastore and BigQuery. **For BigQuery** If this value is not specified and the table was modified between the given start and end times, the entire table will be scanned. If this value is specified, then rows are filtered based on the given start and end times. Rows with a `NULL` value in the provided BigQuery column are skipped. Valid data types of the provided BigQuery column are: `INTEGER`, `DATE`, `TIMESTAMP`, and `DATETIME`. If your BigQuery table is [partitioned at ingestion time](https://cloud.google.com/bigquery/docs/partitioned-tables#ingestion_time), you can use any of the following pseudo-columns as your timestamp field. When used with Cloud DLP, these pseudo-column names are case sensitive. - `_PARTITIONTIME` - `_PARTITIONDATE` - `_PARTITION_LOAD_TIME` **For Datastore** If this value is specified, then entities are filtered based on the given start and end times. If an entity does not contain the provided timestamp property or contains empty or invalid values, then it is included. Valid data types of the provided timestamp property are: `TIMESTAMP`. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-timespan) related to this operation.
"name": "A String", # Name describing the field.
},
},
},
},
"snapshotInspectTemplate": { # The inspectTemplate contains a configuration (set of types of sensitive data to be detected) to be used anywhere you otherwise would normally specify InspectConfig. See https://cloud.google.com/sensitive-data-protection/docs/concepts-templates to learn more. # If run with an InspectTemplate, a snapshot of its state at the time of this run.
"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.
"description": "A String", # Short description (max 256 chars).
"displayName": "A String", # Display name (max 256 chars).
"inspectConfig": { # Configuration description of the scanning process. When used with redactContent only info_types and min_likelihood are currently used. # The core content of the template. Configuration of the scanning process.
"contentOptions": [ # Deprecated and unused.
"A String",
],
"customInfoTypes": [ # CustomInfoTypes provided by the user. See https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes to learn more.
{ # Custom information type provided by the user. Used to find domain-specific sensitive information configurable to the data in question.
"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. Rules are applied in order that they are specified. Not supported for the `surrogate_type` CustomInfoType.
{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a `CustomInfoType` to alter behavior under certain circumstances, depending on the specific details of the rule. Not supported for the `surrogate_type` custom infoType.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "$\d{3}$ \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "$xxx$", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # A list of phrases to detect as a CustomInfoType.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding to be returned. It still can be used for rules matching.
"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in infoType, when the name matches one of existing infoTypes and that infoType is specified in `InspectContent.info_types` field. Specifying the latter adds findings to the one detected by the system. If built-in info type is not specified in `InspectContent.info_types` list then the name is treated as a custom info type.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be altered by a detection rule if the finding meets the criteria specified by the rule. Defaults to `VERY_LIKELY` if not specified.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Sensitivity for this CustomInfoType. If this CustomInfoType extends an existing InfoType, the sensitivity here will take precedence over that of the original InfoType. If unset for a CustomInfoType, it will default to HIGH. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in `InspectDataSource`. Not currently supported in `InspectContent`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for inspection was created. Output-only field, populated by the system.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example `organizations/433245324/storedInfoTypes/432452342` or `projects/project-id/storedInfoTypes/432452342`.
},
"surrogateType": { # Message for detecting output from deidentification transformations such as [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). These types of transformations are those that perform pseudonymization, thereby producing a "surrogate" as output. This should be used in conjunction with a field on the transformation such as `surrogate_info_type`. This CustomInfoType does not support the use of `detection_rules`. # Message for detecting output from deidentification transformations that support reversing.
},
},
],
"excludeInfoTypes": True or False, # When true, excludes type information of the findings. This is not used for data profiling.
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is included in the response; see Finding.quote. This is not used for data profiling.
"infoTypes": [ # Restricts what info_types to look for. The values must correspond to InfoType values returned by ListInfoTypes or listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference. When no InfoTypes or CustomInfoTypes are specified in a request, the system may automatically choose a default list of detectors to run, which may change over time. If you need precise control and predictability as to what detectors are run you should specify specific InfoTypes listed in the reference, otherwise a default list will be used, which may change over time.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"limits": { # Configuration to control the number of findings returned for inspection. This is not used for de-identification or data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. # Configuration to control the number of findings returned. This is not used for data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. When set within an InspectJobConfig, the specified maximum values aren't hard limits. If an inspection job reaches these limits, the job ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than these maximum values.
"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
{ # Max findings configuration per infoType, per content item or long running DlpJob.
"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per info_type should be provided. If InfoTypeLimit does not have an info_type, the DLP API applies the limit against all info_types that are found but not specified in another InfoTypeLimit.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that are returned for each item scanned. When set within an InspectContentRequest, this field is ignored. This value isn't a hard limit. If the number of findings for an item reaches this limit, the inspection of that item ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns for the item can be multiple times higher than this value.
"maxFindingsPerRequest": 42, # Max number of findings that are returned per request or job. If you set this field in an InspectContentRequest, the resulting maximum value is the value that you set or 3,000, whichever is lower. This value isn't a hard limit. If an inspection reaches this limit, the inspection ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than this value.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. The default is POSSIBLE. In general, the highest likelihood setting yields the fewest findings in results and the lowest chance of a false positive. For more information, see [Match likelihood](https://cloud.google.com/sensitive-data-protection/docs/likelihood).
"minLikelihoodPerInfoType": [ # Minimum likelihood per infotype. For each infotype, a user can specify a minimum likelihood. The system only returns a finding if its likelihood is above this threshold. If this field is not set, the system uses the InspectConfig min_likelihood.
{ # Configuration for setting a minimum likelihood per infotype. Used to customize the minimum likelihood level for specific infotypes in the request. For example, use this if you want to lower the precision for PERSON_NAME without lowering the precision for the other infotypes in the request.
"infoType": { # Type of information detected by the API. # Type of information the likelihood threshold applies to. Only one likelihood per info_type should be provided. If InfoTypeLikelihood does not have an info_type, the configuration fails.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. This field is required or else the configuration fails.
},
],
"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. Exclusion rules, contained in the set are executed in the end, other rules are executed in the order they are specified for each info type.
{ # Rule set for modifying a set of infoTypes to alter behavior under certain circumstances, depending on the specific details of the rules within the set.
"infoTypes": [ # List of infoTypes this rule set is applied to.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
{ # A single inspection rule to be applied to infoTypes, specified in `InspectionRuleSet`.
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in `InspectionRuleSet` are removed from results. # Exclusion rule.
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # Dictionary which defines the rule.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"excludeByHotword": { # The rule to exclude findings based on a hotword. For record inspection of tables, column names are considered hotwords. An example of this is to exclude a finding if it belongs to a BigQuery column that matches a specific pattern. # Drop if the hotword rule is contained in the proximate context. For tabular data, the context includes the column name.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The windowBefore property in proximity should be set to 1 if the hotword needs to be included in a column header.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
"excludeInfoTypes": { # List of excluded infoTypes. # Set of infoTypes for which findings would affect this rule.
"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or contained within with a finding of an infoType from this list. For example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and `exclusion_rule` containing `exclude_info_types.info_types` with "EMAIL_ADDRESS" the phone number findings are dropped if they overlap with EMAIL_ADDRESS finding. That leads to "555-222-2222@example.org" to generate only a single finding, namely email address.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
},
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "$\d{3}$ \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "$xxx$", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
},
],
},
"name": "A String", # Output only. The template name. The template will have one of the following formats: `projects/PROJECT_ID/inspectTemplates/TEMPLATE_ID` OR `organizations/ORGANIZATION_ID/inspectTemplates/TEMPLATE_ID`;
"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.
},
},
"result": { # All result fields mentioned below are updated while the job is processing. # A summary of the outcome of this inspection job.
"hybridStats": { # Statistics related to processing hybrid inspect requests. # Statistics related to the processing of hybrid inspect.
"abortedCount": "A String", # The number of hybrid inspection requests aborted because the job ran out of quota or was ended before they could be processed.
"pendingCount": "A String", # The number of hybrid requests currently being processed. Only populated when called via method `getDlpJob`. A burst of traffic may cause hybrid inspect requests to be enqueued. Processing will take place as quickly as possible, but resource limitations may impact how long a request is enqueued for.
"processedCount": "A String", # The number of hybrid inspection requests processed within this job.
},
"infoTypeStats": [ # Statistics of how many instances of each info type were found during inspect job.
{ # Statistics regarding a specific InfoType.
"count": "A String", # Number of findings for this infoType.
"infoType": { # Type of information detected by the API. # The type of finding this stat is for.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"numRowsProcessed": "A String", # Number of rows scanned after sampling and time filtering (applicable for row based stores such as BigQuery).
"processedBytes": "A String", # Total size in bytes that were processed.
"totalEstimatedBytes": "A String", # Estimate of the number of bytes to process.
},
},
"jobTriggerName": "A String", # If created by a job trigger, the resource name of the trigger that instantiated the job.
"lastModified": "A String", # Time when the job was last modified by the system.
"name": "A String", # The server-assigned name.
"riskDetails": { # Result of a risk analysis operation request. # Results from analyzing risk of a data source.
"categoricalStatsResult": { # Result of the categorical stats computation. # Categorical stats result
"valueFrequencyHistogramBuckets": [ # Histogram of value frequencies in the column.
{ # Histogram of value frequencies in the column.
"bucketSize": "A String", # Total number of values in this bucket.
"bucketValueCount": "A String", # Total number of distinct values in this bucket.
"bucketValues": [ # Sample of value frequencies in this bucket. The total number of values returned per bucket is capped at 20.
{ # A value of a field, including its frequency.
"count": "A String", # How many times the value is contained in the field.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # A value contained in the field in question.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
"valueFrequencyLowerBound": "A String", # Lower bound on the value frequency of the values in this bucket.
"valueFrequencyUpperBound": "A String", # Upper bound on the value frequency of the values in this bucket.
},
],
},
"deltaPresenceEstimationResult": { # Result of the δ-presence computation. Note that these results are an estimation, not exact values. # Delta-presence result
"deltaPresenceEstimationHistogram": [ # The intervals [min_probability, max_probability) do not overlap. If a value doesn't correspond to any such interval, the associated frequency is zero. For example, the following records: {min_probability: 0, max_probability: 0.1, frequency: 17} {min_probability: 0.2, max_probability: 0.3, frequency: 42} {min_probability: 0.3, max_probability: 0.4, frequency: 99} mean that there are no record with an estimated probability in [0.1, 0.2) nor larger or equal to 0.4.
{ # A DeltaPresenceEstimationHistogramBucket message with the following values: min_probability: 0.1 max_probability: 0.2 frequency: 42 means that there are 42 records for which δ is in [0.1, 0.2). An important particular case is when min_probability = max_probability = 1: then, every individual who shares this quasi-identifier combination is in the dataset.
"bucketSize": "A String", # Number of records within these probability bounds.
"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.
"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total number of classes returned per bucket is capped at 20.
{ # A tuple of values for the quasi-identifier columns.
"estimatedProbability": 3.14, # The estimated probability that a given individual sharing these quasi-identifier values is in the dataset. This value, typically called δ, is the ratio between the number of records in the dataset with these quasi-identifier values, and the total number of individuals (inside *and* outside the dataset) with these quasi-identifier values. For example, if there are 15 individuals in the dataset who share the same quasi-identifier values, and an estimated 100 people in the entire population with these values, then δ is 0.15.
"quasiIdsValues": [ # The quasi-identifier values.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
},
],
"maxProbability": 3.14, # Always greater than or equal to min_probability.
"minProbability": 3.14, # Between 0 and 1.
},
],
},
"kAnonymityResult": { # Result of the k-anonymity computation. # K-anonymity result
"equivalenceClassHistogramBuckets": [ # Histogram of k-anonymity equivalence classes.
{ # Histogram of k-anonymity equivalence classes.
"bucketSize": "A String", # Total number of equivalence classes in this bucket.
"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.
"bucketValues": [ # Sample of equivalence classes in this bucket. The total number of classes returned per bucket is capped at 20.
{ # The set of columns' values that share the same ldiversity value
"equivalenceClassSize": "A String", # Size of the equivalence class, for example number of rows with the above set of values.
"quasiIdsValues": [ # Set of values defining the equivalence class. One value per quasi-identifier column in the original KAnonymity metric message. The order is always the same as the original request.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
},
],
"equivalenceClassSizeLowerBound": "A String", # Lower bound on the size of the equivalence classes in this bucket.
"equivalenceClassSizeUpperBound": "A String", # Upper bound on the size of the equivalence classes in this bucket.
},
],
},
"kMapEstimationResult": { # Result of the reidentifiability analysis. Note that these results are an estimation, not exact values. # K-map result
"kMapEstimationHistogram": [ # The intervals [min_anonymity, max_anonymity] do not overlap. If a value doesn't correspond to any such interval, the associated frequency is zero. For example, the following records: {min_anonymity: 1, max_anonymity: 1, frequency: 17} {min_anonymity: 2, max_anonymity: 3, frequency: 42} {min_anonymity: 5, max_anonymity: 10, frequency: 99} mean that there are no record with an estimated anonymity of 4, 5, or larger than 10.
{ # A KMapEstimationHistogramBucket message with the following values: min_anonymity: 3 max_anonymity: 5 frequency: 42 means that there are 42 records whose quasi-identifier values correspond to 3, 4 or 5 people in the overlying population. An important particular case is when min_anonymity = max_anonymity = 1: the frequency field then corresponds to the number of uniquely identifiable records.
"bucketSize": "A String", # Number of records within these anonymity bounds.
"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.
"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total number of classes returned per bucket is capped at 20.
{ # A tuple of values for the quasi-identifier columns.
"estimatedAnonymity": "A String", # The estimated anonymity for these quasi-identifier values.
"quasiIdsValues": [ # The quasi-identifier values.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
},
],
"maxAnonymity": "A String", # Always greater than or equal to min_anonymity.
"minAnonymity": "A String", # Always positive.
},
],
},
"lDiversityResult": { # Result of the l-diversity computation. # L-divesity result
"sensitiveValueFrequencyHistogramBuckets": [ # Histogram of l-diversity equivalence class sensitive value frequencies.
{ # Histogram of l-diversity equivalence class sensitive value frequencies.
"bucketSize": "A String", # Total number of equivalence classes in this bucket.
"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.
"bucketValues": [ # Sample of equivalence classes in this bucket. The total number of classes returned per bucket is capped at 20.
{ # The set of columns' values that share the same ldiversity value.
"equivalenceClassSize": "A String", # Size of the k-anonymity equivalence class.
"numDistinctSensitiveValues": "A String", # Number of distinct sensitive values in this equivalence class.
"quasiIdsValues": [ # Quasi-identifier values defining the k-anonymity equivalence class. The order is always the same as the original request.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
"topSensitiveValues": [ # Estimated frequencies of top sensitive values.
{ # A value of a field, including its frequency.
"count": "A String", # How many times the value is contained in the field.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # A value contained in the field in question.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
],
"sensitiveValueFrequencyLowerBound": "A String", # Lower bound on the sensitive value frequencies of the equivalence classes in this bucket.
"sensitiveValueFrequencyUpperBound": "A String", # Upper bound on the sensitive value frequencies of the equivalence classes in this bucket.
},
],
},
"numericalStatsResult": { # Result of the numerical stats computation. # Numerical stats result
"maxValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Maximum value appearing in the column.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"minValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Minimum value appearing in the column.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"quantileValues": [ # List of 99 values that partition the set of field values into 100 equal sized buckets.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
},
"requestedOptions": { # Risk analysis options. # The configuration used for this job.
"jobConfig": { # Configuration for a risk analysis job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-risk-analysis to learn more. # The job config for the risk job.
"actions": [ # Actions to execute at the completion of the job. Are executed in the order provided.
{ # A task to execute on the completion of a job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-actions to learn more.
"deidentify": { # Create a de-identified copy of the requested table or files. A TransformationDetail will be created for each transformation. If any rows in BigQuery are skipped during de-identification (transformation errors or row size exceeds BigQuery insert API limits) they are placed in the failure output table. If the original row exceeds the BigQuery insert API limit it will be truncated when written to the failure output table. The failure output table can be set in the action.deidentify.output.big_query_output.deidentified_failure_output_table field, if no table is set, a table will be automatically created in the same project and dataset as the original table. Compatible with: Inspect # Create a de-identified copy of the input data.
"cloudStorageOutput": "A String", # Required. User settable Cloud Storage bucket and folders to store de-identified files. This field must be set for Cloud Storage deidentification. The output Cloud Storage bucket must be different from the input bucket. De-identified files will overwrite files in the output path. Form of: gs://bucket/folder/ or gs://bucket
"fileTypesToTransform": [ # List of user-specified file type groups to transform. If specified, only the files with these file types will be transformed. If empty, all supported files will be transformed. Supported types may be automatically added over time. If a file type is set in this field that isn't supported by the Deidentify action then the job will fail and will not be successfully created/started. Currently the only file types supported are: IMAGES, TEXT_FILES, CSV, TSV.
"A String",
],
"transformationConfig": { # User specified templates and configs for how to deidentify structured, unstructures, and image files. User must provide either a unstructured deidentify template or at least one redact image config. # User specified deidentify templates and configs for structured, unstructured, and image files.
"deidentifyTemplate": "A String", # De-identify template. If this template is specified, it will serve as the default de-identify template. This template cannot contain `record_transformations` since it can be used for unstructured content such as free-form text files. If this template is not set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify unstructured content.
"imageRedactTemplate": "A String", # Image redact template. If this template is specified, it will serve as the de-identify template for images. If this template is not set, all findings in the image will be redacted with a black box.
"structuredDeidentifyTemplate": "A String", # Structured de-identify template. If this template is specified, it will serve as the de-identify template for structured content such as delimited files and tables. If this template is not set but the `deidentify_template` is set, then `deidentify_template` will also apply to the structured content. If neither template is set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify structured content.
},
"transformationDetailsStorageConfig": { # Config for storing transformation details. # Config for storing transformation details. This is separate from the de-identified content, and contains metadata about the successful transformations and/or failures that occurred while de-identifying. This needs to be set in order for users to access information about the status of each transformation (see TransformationDetails message for more information about what is noted).
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # The BigQuery table in which to store the output. This may be an existing table or in a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_transformation_details_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"jobNotificationEmails": { # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts). # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts).
},
"pubSub": { # Publish a message into a given Pub/Sub topic when DlpJob has completed. The message contains a single field, `DlpJobName`, which is equal to the finished job's [`DlpJob.name`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/projects.dlpJobs#DlpJob). Compatible with: Inspect, Risk # Publish a notification to a Pub/Sub topic.
"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given publishing access rights to the DLP API service account executing the long running DlpJob sending the notifications. Format is projects/{project}/topics/{topic}.
},
"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Data Catalog. In Data Catalog, tag templates are applied to the resource that Cloud DLP scanned. Data Catalog tag templates are stored in the same project and region where the BigQuery table exists. For Cloud DLP to create and apply the tag template, the Cloud DLP service agent must have the `roles/datacatalog.tagTemplateOwner` permission on the project. The tag template contains fields summarizing the results of the DlpJob. Any field values previously written by another DlpJob are deleted. InfoType naming patterns are strictly enforced when using this feature. Findings are persisted in Data Catalog storage and are governed by service-specific policies for Data Catalog. For more information, see [Service Specific Terms](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. This action is allowed only if all resources being scanned are BigQuery tables. Compatible with: Inspect # Publish findings to Cloud Datahub.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to [Security Command Center](https://cloud.google.com/security-command-center). This action is available for only projects that belong to an organization. This action publishes the count of finding instances and their infoTypes. The summary of findings are persisted in Security Command Center and are governed by [service-specific policies for Security Command Center](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. Compatible with: Inspect # Publish summary to Cloud Security Command Center (Alpha).
},
"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This will publish a metric to stack driver on each infotype requested and how many findings were found for it. CustomDetectors will be bucketed as 'Custom' under the Stackdriver label 'info_type'. # Enable Stackdriver metric dlp.googleapis.com/finding_count.
},
"saveFindings": { # If set, the detailed findings will be persisted to the specified OutputStorageConfig. Only a single instance of this action can be specified. Compatible with: Inspect, Risk # Save resulting findings in a provided location.
"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only used for Inspect and must be unspecified for Risk jobs. Columns are derived from the `Finding` object. If appending to an existing table, any columns from the predefined schema that are missing will be added. No columns in the existing table will be deleted. If unspecified, then all available columns will be used for a new table or an (existing) table with no schema, and no changes will be made to an existing table that has a schema. Only for use with external storage.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Store findings in an existing table or a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details. For Inspect, each column in an existing output table must have the same name, type, and mode of a field in the `Finding` object. For Risk, an existing output table should be the output of a previous Risk analysis job run on the same source table, with the same privacy metric and quasi-identifiers. Risk jobs that analyze the same table but compute a different privacy metric, or use different sets of quasi-identifiers, cannot store their results in the same table.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
},
],
"privacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.
"categoricalStatsConfig": { # Compute numerical stats over an individual column, including number of distinct values and value count distribution. # Categorical stats
"field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are supported except for arrays and structs. However, it may be more informative to use NumericalStats when the field type is supported, depending on the data.
"name": "A String", # Name describing the field.
},
},
"deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to figure out that one given individual appears in a de-identified dataset. Similarly to the k-map metric, we cannot compute δ-presence exactly without knowing the attack dataset, so we use a statistical model instead. # delta-presence
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers field must appear in exactly one field of one auxiliary table.
{ # An auxiliary table containing statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity
"entityId": { # An entity in a dataset is a field or set of fields that correspond to a single person. For example, in medical records the `EntityId` might be a patient identifier, or for financial records it might be an account identifier. This message is used when generalizations or analysis must take into account that multiple rows correspond to the same entity. # Message indicating that multiple rows might be associated to a single individual. If the same entity_id is associated to multiple quasi-identifier tuples over distinct rows, we consider the entire collection of tuples as the composite quasi-identifier. This collection is a multiset: the order in which the different tuples appear in the dataset is ignored, but their frequency is taken into account. Important note: a maximum of 1000 rows can be associated to a single entity ID. If more rows are associated with the same entity ID, some might be ignored.
"field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier.
"name": "A String", # Name describing the field.
},
},
"quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are specified, they are considered a single composite key. Structs and repeated data types are not supported; however, nested fields are supported so long as they are not structs themselves or nested within a repeated field.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
"kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what is called "journalist risk" in the literature, except the attack dataset is statistically modeled instead of being perfectly known. This can be done using publicly available data (like the US Census), or using a custom statistical model (indicated as one or several BigQuery tables), or by extrapolating from the distribution of values in the input dataset. # k-map
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers column must appear in exactly one column of one auxiliary table.
{ # An auxiliary table contains statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A auxiliary field.
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity
"quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are defined for the l-diversity computation. When multiple fields are specified, they are considered a single composite key.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value.
"name": "A String", # Name describing the field.
},
},
"numericalStatsConfig": { # Compute numerical stats over an individual column, including min, max, and quantiles. # Numerical stats
"field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are integer, float, date, datetime, timestamp, time.
"name": "A String", # Name describing the field.
},
},
},
"sourceTable": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Input dataset to compute metrics over.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"requestedPrivacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.
"categoricalStatsConfig": { # Compute numerical stats over an individual column, including number of distinct values and value count distribution. # Categorical stats
"field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are supported except for arrays and structs. However, it may be more informative to use NumericalStats when the field type is supported, depending on the data.
"name": "A String", # Name describing the field.
},
},
"deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to figure out that one given individual appears in a de-identified dataset. Similarly to the k-map metric, we cannot compute δ-presence exactly without knowing the attack dataset, so we use a statistical model instead. # delta-presence
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers field must appear in exactly one field of one auxiliary table.
{ # An auxiliary table containing statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity
"entityId": { # An entity in a dataset is a field or set of fields that correspond to a single person. For example, in medical records the `EntityId` might be a patient identifier, or for financial records it might be an account identifier. This message is used when generalizations or analysis must take into account that multiple rows correspond to the same entity. # Message indicating that multiple rows might be associated to a single individual. If the same entity_id is associated to multiple quasi-identifier tuples over distinct rows, we consider the entire collection of tuples as the composite quasi-identifier. This collection is a multiset: the order in which the different tuples appear in the dataset is ignored, but their frequency is taken into account. Important note: a maximum of 1000 rows can be associated to a single entity ID. If more rows are associated with the same entity ID, some might be ignored.
"field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier.
"name": "A String", # Name describing the field.
},
},
"quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are specified, they are considered a single composite key. Structs and repeated data types are not supported; however, nested fields are supported so long as they are not structs themselves or nested within a repeated field.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
"kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what is called "journalist risk" in the literature, except the attack dataset is statistically modeled instead of being perfectly known. This can be done using publicly available data (like the US Census), or using a custom statistical model (indicated as one or several BigQuery tables), or by extrapolating from the distribution of values in the input dataset. # k-map
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers column must appear in exactly one column of one auxiliary table.
{ # An auxiliary table contains statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A auxiliary field.
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity
"quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are defined for the l-diversity computation. When multiple fields are specified, they are considered a single composite key.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value.
"name": "A String", # Name describing the field.
},
},
"numericalStatsConfig": { # Compute numerical stats over an individual column, including min, max, and quantiles. # Numerical stats
"field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are integer, float, date, datetime, timestamp, time.
"name": "A String", # Name describing the field.
},
},
},
"requestedSourceTable": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Input dataset to compute metrics over.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
"startTime": "A String", # Time when the job started.
"state": "A String", # State of a job.
"type": "A String", # The type of job.
}

hybridInspect(name, body=None, x__xgafv=None)

Inspect hybrid content and store findings to a job. To review the findings, inspect the job. Inspection will occur asynchronously.

Args:
  name: string, Required. Resource name of the job to execute a hybrid inspect on, for example `projects/dlp-test-project/dlpJob/53234423`. (required)
  body: object, The request body.
    The object takes the form of:

{ # Request to search for potentially sensitive info in a custom location.
  "hybridItem": { # An individual hybrid item to inspect. Will be stored temporarily during processing. # The item to inspect.
    "findingDetails": { # Populate to associate additional data with each finding. # Supplementary information that will be added to each finding.
      "containerDetails": { # Represents a container that may contain DLP findings. Examples of a container include a file, table, or database record. # Details about the container where the content being inspected is from.
        "fullPath": "A String", # A string representation of the full container name. Examples: - BigQuery: 'Project:DataSetId.TableId' - Cloud Storage: 'gs://Bucket/folders/filename.txt'
        "projectId": "A String", # Project where the finding was found. Can be different from the project that owns the finding.
        "relativePath": "A String", # The rest of the path after the root. Examples: - For BigQuery table `project_id:dataset_id.table_id`, the relative path is `table_id` - For Cloud Storage file `gs://bucket/folder/filename.txt`, the relative path is `folder/filename.txt`
        "rootPath": "A String", # The root of the container. Examples: - For BigQuery table `project_id:dataset_id.table_id`, the root is `dataset_id` - For Cloud Storage file `gs://bucket/folder/filename.txt`, the root is `gs://bucket`
        "type": "A String", # Container type, for example BigQuery or Cloud Storage.
        "updateTime": "A String", # Findings container modification timestamp, if applicable. For Cloud Storage, this field contains the last file modification timestamp. For a BigQuery table, this field contains the last_modified_time property. For Datastore, this field isn't populated.
        "version": "A String", # Findings container version, if available ("generation" for Cloud Storage).
      },
      "fileOffset": "A String", # Offset in bytes of the line, from the beginning of the file, where the finding is located. Populate if the item being scanned is only part of a bigger item, such as a shard of a file and you want to track the absolute position of the finding.
      "labels": { # Labels to represent user provided metadata about the data being inspected. If configured by the job, some key values may be required. The labels associated with `Finding`'s produced by hybrid inspection. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. Label values must be between 0 and 63 characters long and must conform to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`. No more than 10 labels can be associated with a given finding. Examples: * `"environment" : "production"` * `"pipeline" : "etl"`
        "a_key": "A String",
      },
      "rowOffset": "A String", # Offset of the row for tables. Populate if the row(s) being scanned are part of a bigger dataset and you want to keep track of their absolute position.
      "tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings meaningful such as the columns that are primary keys. If not known ahead of time, can also be set within each inspect hybrid call and the two will be merged. Note that identifying_fields will only be stored to BigQuery, and only if the BigQuery action has been included.
        "identifyingFields": [ # The columns that are the primary keys for table objects included in ContentItem. A copy of this cell's value will stored alongside alongside each finding so that the finding can be traced to the specific row it came from. No more than 3 may be provided.
          { # General identifier of a data field in a storage service.
            "name": "A String", # Name describing the field.
          },
        ],
      },
    },
    "item": { # Type of content to inspect. # The item to inspect.
      "byteItem": { # Container for bytes to inspect or redact. # Content data to inspect or redact. Replaces `type` and `data`.
        "data": "A String", # Content data to inspect or redact.
        "type": "A String", # The type of data stored in the bytes string. Default will be TEXT_UTF8.
      },
      "table": { # Structured content to inspect. Up to 50,000 `Value`s per request allowed. See https://cloud.google.com/sensitive-data-protection/docs/inspecting-structured-text#inspecting_a_table to learn more. # Structured content for inspection. See https://cloud.google.com/sensitive-data-protection/docs/inspecting-text#inspecting_a_table to learn more.
        "headers": [ # Headers of the table.
          { # General identifier of a data field in a storage service.
            "name": "A String", # Name describing the field.
          },
        ],
        "rows": [ # Rows of the table.
          { # Values of the row.
            "values": [ # Individual cells.
              { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
                "booleanValue": True or False, # boolean
                "dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
                  "day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
                  "month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
                  "year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
                },
                "dayOfWeekValue": "A String", # day of week
                "floatValue": 3.14, # float
                "integerValue": "A String", # integer
                "stringValue": "A String", # string
                "timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
                  "hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
                  "minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
                  "nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
                  "seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
                },
                "timestampValue": "A String", # timestamp
              },
            ],
          },
        ],
      },
      "value": "A String", # String data to inspect or redact.
    },
  },
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Quota exceeded errors will be thrown once quota has been met.
}

list(parent, filter=None, locationId=None, orderBy=None, pageSize=None, pageToken=None, type=None, x__xgafv=None)

Lists DlpJobs that match the specified filter in the request. See https://cloud.google.com/sensitive-data-protection/docs/inspecting-storage and https://cloud.google.com/sensitive-data-protection/docs/compute-risk-analysis to learn more.

Args:
parent: string, Required. Parent resource name. The format of this value varies depending on whether you have [specified a processing location](https://cloud.google.com/sensitive-data-protection/docs/specifying-location): + Projects scope, location specified: `projects/{project_id}/locations/{location_id}` + Projects scope, no location specified (defaults to global): `projects/{project_id}` The following example `parent` string specifies a parent project with the identifier `example-project`, and specifies the `europe-west3` location for processing data: parent=projects/example-project/locations/europe-west3 (required)
filter: string, Allows filtering. Supported syntax: * Filter expressions are made up of one or more restrictions. * Restrictions can be combined by `AND` or `OR` logical operators. A sequence of restrictions implicitly uses `AND`. * A restriction has the form of `{field} {operator} {value}`. * Supported fields/values for inspect jobs: - `state` - PENDING|RUNNING|CANCELED|FINISHED|FAILED - `inspected_storage` - DATASTORE|CLOUD_STORAGE|BIGQUERY - `trigger_name` - The name of the trigger that created the job. - 'end_time` - Corresponds to the time the job finished. - 'start_time` - Corresponds to the time the job finished. * Supported fields for risk analysis jobs: - `state` - RUNNING|CANCELED|FINISHED|FAILED - 'end_time` - Corresponds to the time the job finished. - 'start_time` - Corresponds to the time the job finished. * The operator must be `=` or `!=`. Examples: * inspected_storage = cloud_storage AND state = done * inspected_storage = cloud_storage OR inspected_storage = bigquery * inspected_storage = cloud_storage AND (state = done OR state = canceled) * end_time > \"2017-12-12T00:00:00+00:00\" The length of this field should be no more than 500 characters.
locationId: string, Deprecated. This field has no effect.
orderBy: string, Comma-separated list of fields to order by, followed by `asc` or `desc` postfix. This list is case insensitive. The default sorting order is ascending. Redundant space characters are insignificant. Example: `name asc, end_time asc, create_time desc` Supported fields are: - `create_time`: corresponds to the time the job was created. - `end_time`: corresponds to the time the job ended. - `name`: corresponds to the job's name. - `state`: corresponds to `state`
pageSize: integer, The standard list page size.
pageToken: string, The standard list page token.
type: string, The type of job. Defaults to `DlpJobType.INSPECT`
Allowed values
DLP_JOB_TYPE_UNSPECIFIED - Defaults to INSPECT_JOB.
INSPECT_JOB - The job inspected Google Cloud for sensitive data.
RISK_ANALYSIS_JOB - The job executed a Risk Analysis computation.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format

Returns:
An object of the form:

{ # The response message for listing DLP jobs.
"jobs": [ # A list of DlpJobs that matches the specified filter in the request.
{ # Combines all of the information about a DLP job.
"actionDetails": [ # Events that should occur after the job has completed.
{ # The results of an Action.
"deidentifyDetails": { # The results of a Deidentify action from an inspect job. # Outcome of a de-identification action.
"deidentifyStats": { # Summary of what was modified during a transformation. # Stats about the de-identification operation.
"transformationCount": "A String", # Number of successfully applied transformations.
"transformationErrorCount": "A String", # Number of errors encountered while trying to apply transformations.
"transformedBytes": "A String", # Total size in bytes that were transformed in some way.
},
"requestedOptions": { # De-identification options. # De-identification config used for the request.
"snapshotDeidentifyTemplate": { # DeidentifyTemplates contains instructions on how to de-identify content. See https://cloud.google.com/sensitive-data-protection/docs/concepts-templates to learn more. # Snapshot of the state of the `DeidentifyTemplate` from the Deidentify action at the time this job was run.
"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.
"deidentifyConfig": { # The configuration that controls how the data will change. # The core content of the template.
"imageTransformations": { # A type of transformation that is applied over images. # Treat the dataset as an image and redact.
"transforms": [ # List of transforms to make.
{ # Configuration for determining how redaction of images should occur.
"allInfoTypes": { # Apply transformation to all findings. # Apply transformation to all findings not specified in other ImageTransformation's selected_info_types. Only one instance is allowed within the ImageTransformations message.
},
"allText": { # Apply to all text. # Apply transformation to all text that doesn't match an infoType. Only one instance is allowed within the ImageTransformations message.
},
"redactionColor": { # Represents a color in the RGB color space. # The color to use when redacting content from an image. If not specified, the default is black.
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"selectedInfoTypes": { # Apply transformation to the selected info_types. # Apply transformation to the selected info_types.
"infoTypes": [ # Required. InfoTypes to apply the transformation to. Required. Provided InfoType must be unique within the ImageTransformations message.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
},
],
},
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the dataset as free-form text and apply the same free text transformation everywhere.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"recordTransformations": { # A type of transformation that is applied over structured data such as a table. # Treat the dataset as structured. Transformations can be applied to specific locations within structured datasets, such as transforming a column within a table.
"fieldTransformations": [ # Transform the record by applying various field transformations.
{ # The transformation to apply to the field.
"condition": { # A condition for determining whether a transformation should be applied to a field. # Only apply the transformation if the condition evaluates to true for the given `RecordCondition`. The conditions are allowed to reference fields that are not used in the actual transformation. Example Use Cases: - Apply a different bucket transformation to an age column if the zip code column for the same record is within a specific range. - Redact a field if the date of birth field is greater than 85.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
"fields": [ # Required. Input field(s) to apply the transformation to. When you have columns that reference their position within a list, omit the index from the FieldId. FieldId name matching ignores the index. For example, instead of "contact.nums[0].type", use "contact.nums.type".
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the contents of the field as free text, and selectively transform content that matches an `InfoType`.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"primitiveTransformation": { # A rule for transforming a value. # Apply the transformation to the entire field.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
"recordSuppressions": [ # Configuration defining which records get suppressed entirely. Records that match any suppression rule are omitted from the output.
{ # Configuration to suppress records whose suppression conditions evaluate to true.
"condition": { # A condition for determining whether a transformation should be applied to a field. # A condition that when it evaluates to true will result in the record being evaluated to be suppressed from the transformed content.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
},
],
},
"transformationErrorHandling": { # How to handle transformation errors during de-identification. A transformation error occurs when the requested transformation is incompatible with the data. For example, trying to de-identify an IP address using a `DateShift` transformation would result in a transformation error, since date info cannot be extracted from an IP address. Information about any incompatible transformations, and how they were handled, is returned in the response as part of the `TransformationOverviews`. # Mode for handling transformation errors. If left unspecified, the default mode is `TransformationErrorHandling.ThrowError`.
"leaveUntransformed": { # Skips the data without modifying it if the requested transformation would cause an error. For example, if a `DateShift` transformation were applied an an IP address, this mode would leave the IP address unchanged in the response. # Ignore errors
},
"throwError": { # Throw an error and fail the request when a transformation error occurs. # Throw an error
},
},
},
"description": "A String", # Short description (max 256 chars).
"displayName": "A String", # Display name (max 256 chars).
"name": "A String", # Output only. The template name. The template will have one of the following formats: `projects/PROJECT_ID/deidentifyTemplates/TEMPLATE_ID` OR `organizations/ORGANIZATION_ID/deidentifyTemplates/TEMPLATE_ID`
"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.
},
"snapshotImageRedactTemplate": { # DeidentifyTemplates contains instructions on how to de-identify content. See https://cloud.google.com/sensitive-data-protection/docs/concepts-templates to learn more. # Snapshot of the state of the image transformation `DeidentifyTemplate` from the `Deidentify` action at the time this job was run.
"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.
"deidentifyConfig": { # The configuration that controls how the data will change. # The core content of the template.
"imageTransformations": { # A type of transformation that is applied over images. # Treat the dataset as an image and redact.
"transforms": [ # List of transforms to make.
{ # Configuration for determining how redaction of images should occur.
"allInfoTypes": { # Apply transformation to all findings. # Apply transformation to all findings not specified in other ImageTransformation's selected_info_types. Only one instance is allowed within the ImageTransformations message.
},
"allText": { # Apply to all text. # Apply transformation to all text that doesn't match an infoType. Only one instance is allowed within the ImageTransformations message.
},
"redactionColor": { # Represents a color in the RGB color space. # The color to use when redacting content from an image. If not specified, the default is black.
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"selectedInfoTypes": { # Apply transformation to the selected info_types. # Apply transformation to the selected info_types.
"infoTypes": [ # Required. InfoTypes to apply the transformation to. Required. Provided InfoType must be unique within the ImageTransformations message.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
},
],
},
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the dataset as free-form text and apply the same free text transformation everywhere.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"recordTransformations": { # A type of transformation that is applied over structured data such as a table. # Treat the dataset as structured. Transformations can be applied to specific locations within structured datasets, such as transforming a column within a table.
"fieldTransformations": [ # Transform the record by applying various field transformations.
{ # The transformation to apply to the field.
"condition": { # A condition for determining whether a transformation should be applied to a field. # Only apply the transformation if the condition evaluates to true for the given `RecordCondition`. The conditions are allowed to reference fields that are not used in the actual transformation. Example Use Cases: - Apply a different bucket transformation to an age column if the zip code column for the same record is within a specific range. - Redact a field if the date of birth field is greater than 85.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
"fields": [ # Required. Input field(s) to apply the transformation to. When you have columns that reference their position within a list, omit the index from the FieldId. FieldId name matching ignores the index. For example, instead of "contact.nums[0].type", use "contact.nums.type".
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the contents of the field as free text, and selectively transform content that matches an `InfoType`.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"primitiveTransformation": { # A rule for transforming a value. # Apply the transformation to the entire field.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
"recordSuppressions": [ # Configuration defining which records get suppressed entirely. Records that match any suppression rule are omitted from the output.
{ # Configuration to suppress records whose suppression conditions evaluate to true.
"condition": { # A condition for determining whether a transformation should be applied to a field. # A condition that when it evaluates to true will result in the record being evaluated to be suppressed from the transformed content.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
},
],
},
"transformationErrorHandling": { # How to handle transformation errors during de-identification. A transformation error occurs when the requested transformation is incompatible with the data. For example, trying to de-identify an IP address using a `DateShift` transformation would result in a transformation error, since date info cannot be extracted from an IP address. Information about any incompatible transformations, and how they were handled, is returned in the response as part of the `TransformationOverviews`. # Mode for handling transformation errors. If left unspecified, the default mode is `TransformationErrorHandling.ThrowError`.
"leaveUntransformed": { # Skips the data without modifying it if the requested transformation would cause an error. For example, if a `DateShift` transformation were applied an an IP address, this mode would leave the IP address unchanged in the response. # Ignore errors
},
"throwError": { # Throw an error and fail the request when a transformation error occurs. # Throw an error
},
},
},
"description": "A String", # Short description (max 256 chars).
"displayName": "A String", # Display name (max 256 chars).
"name": "A String", # Output only. The template name. The template will have one of the following formats: `projects/PROJECT_ID/deidentifyTemplates/TEMPLATE_ID` OR `organizations/ORGANIZATION_ID/deidentifyTemplates/TEMPLATE_ID`
"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.
},
"snapshotStructuredDeidentifyTemplate": { # DeidentifyTemplates contains instructions on how to de-identify content. See https://cloud.google.com/sensitive-data-protection/docs/concepts-templates to learn more. # Snapshot of the state of the structured `DeidentifyTemplate` from the `Deidentify` action at the time this job was run.
"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.
"deidentifyConfig": { # The configuration that controls how the data will change. # The core content of the template.
"imageTransformations": { # A type of transformation that is applied over images. # Treat the dataset as an image and redact.
"transforms": [ # List of transforms to make.
{ # Configuration for determining how redaction of images should occur.
"allInfoTypes": { # Apply transformation to all findings. # Apply transformation to all findings not specified in other ImageTransformation's selected_info_types. Only one instance is allowed within the ImageTransformations message.
},
"allText": { # Apply to all text. # Apply transformation to all text that doesn't match an infoType. Only one instance is allowed within the ImageTransformations message.
},
"redactionColor": { # Represents a color in the RGB color space. # The color to use when redacting content from an image. If not specified, the default is black.
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"selectedInfoTypes": { # Apply transformation to the selected info_types. # Apply transformation to the selected info_types.
"infoTypes": [ # Required. InfoTypes to apply the transformation to. Required. Provided InfoType must be unique within the ImageTransformations message.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
},
],
},
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the dataset as free-form text and apply the same free text transformation everywhere.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"recordTransformations": { # A type of transformation that is applied over structured data such as a table. # Treat the dataset as structured. Transformations can be applied to specific locations within structured datasets, such as transforming a column within a table.
"fieldTransformations": [ # Transform the record by applying various field transformations.
{ # The transformation to apply to the field.
"condition": { # A condition for determining whether a transformation should be applied to a field. # Only apply the transformation if the condition evaluates to true for the given `RecordCondition`. The conditions are allowed to reference fields that are not used in the actual transformation. Example Use Cases: - Apply a different bucket transformation to an age column if the zip code column for the same record is within a specific range. - Redact a field if the date of birth field is greater than 85.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
"fields": [ # Required. Input field(s) to apply the transformation to. When you have columns that reference their position within a list, omit the index from the FieldId. FieldId name matching ignores the index. For example, instead of "contact.nums[0].type", use "contact.nums.type".
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"infoTypeTransformations": { # A type of transformation that will scan unstructured text and apply various `PrimitiveTransformation`s to each finding, where the transformation is applied to only values that were identified as a specific info_type. # Treat the contents of the field as free text, and selectively transform content that matches an `InfoType`.
"transformations": [ # Required. Transformation for each infoType. Cannot specify more than one for a given infoType.
{ # A transformation to apply to text that is identified as a specific info_type.
"infoTypes": [ # InfoTypes to apply the transformation to. An empty list will cause this transformation to apply to all findings that correspond to infoTypes that were requested in `InspectConfig`.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"primitiveTransformation": { # A rule for transforming a value. # Required. Primitive transformation to apply to the infoType.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
},
"primitiveTransformation": { # A rule for transforming a value. # Apply the transformation to the entire field.
"bucketingConfig": { # Generalization function that buckets values based on ranges. The ranges and replacement values are dynamically provided by the user for custom behavior, such as 1-30 -> LOW, 31-65 -> MEDIUM, 66-100 -> HIGH. This can be used on data of type: number, long, string, timestamp. If the bound `Value` type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Bucketing
"buckets": [ # Set of buckets. Ranges must be non-overlapping.
{ # Bucket is represented as a range, along with replacement values.
"max": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Upper bound of the range, exclusive; type must match min.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"min": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Lower bound of the range, inclusive. Type should be the same as max if used.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"replacementValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Replacement value for this bucket.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"characterMaskConfig": { # Partially mask a string by replacing a given number of characters with a fixed character. Masking can start from the beginning or end of the string. This can be used on data of any type (numbers, longs, and so on) and when de-identifying structured data we'll attempt to preserve the original data's type. (This allows you to take a long like 123 and modify it to a string like **3. # Mask
"charactersToIgnore": [ # When masking a string, items in this list will be skipped when replacing characters. For example, if the input string is `555-555-5555` and you instruct Cloud DLP to skip `-` and mask 5 characters with `*`, Cloud DLP returns `***-**5-5555`.
{ # Characters to skip when doing deidentification of a value. These will be left alone and skipped.
"charactersToSkip": "A String", # Characters to not transform when masking.
"commonCharactersToIgnore": "A String", # Common characters to not transform when masking. Useful to avoid removing punctuation.
},
],
"maskingCharacter": "A String", # Character to use to mask the sensitive values—for example, `*` for an alphabetic string such as a name, or `0` for a numeric string such as ZIP code or credit card number. This string must have a length of 1. If not supplied, this value defaults to `*` for strings, and `0` for digits.
"numberToMask": 42, # Number of characters to mask. If not set, all matching chars will be masked. Skipped characters do not count towards this tally. If `number_to_mask` is negative, this denotes inverse masking. Cloud DLP masks all but a number of characters. For example, suppose you have the following values: - `masking_character` is `*` - `number_to_mask` is `-4` - `reverse_order` is `false` - `CharsToIgnore` includes `-` - Input string is `1234-5678-9012-3456` The resulting de-identified string is `****-****-****-3456`. Cloud DLP masks all but the last four characters. If `reverse_order` is `true`, all but the first four characters are masked as `1234-****-****-****`.
"reverseOrder": True or False, # Mask characters in reverse order. For example, if `masking_character` is `0`, `number_to_mask` is `14`, and `reverse_order` is `false`, then the input string `1234-5678-9012-3456` is masked as `00000000000000-3456`. If `masking_character` is `*`, `number_to_mask` is `3`, and `reverse_order` is `true`, then the string `12345` is masked as `12***`.
},
"cryptoDeterministicConfig": { # Pseudonymization method that generates deterministic encryption for the given input. Outputs a base64 encoded representation of the encrypted output. Uses AES-SIV based on the RFC https://tools.ietf.org/html/rfc5297. # Deterministic Crypto
"context": { # General identifier of a data field in a storage service. # A context may be used for higher security and maintaining referential integrity such that the same identifier in two different contexts will be given a distinct surrogate. The context is appended to plaintext value being encrypted. On decryption the provided context is validated against the value used during encryption. If a context was provided during encryption, same context must be provided during decryption as well. If the context is not set, plaintext would be used as is for encryption. If the context is set but: 1. there is no record present when transforming a given value or 2. the field is not present when transforming a given value, plaintext would be used as is for encryption. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the encryption function. For deterministic encryption using AES-SIV, the provided key is internally expanded to 64 bytes prior to use.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"surrogateInfoType": { # Type of information detected by the API. # The custom info type to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom info type followed by the number of characters comprising the surrogate. The following scheme defines the format: {info type name}({surrogate character count}):{surrogate} For example, if the name of custom info type is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom info type 'Surrogate'. This facilitates reversal of the surrogate when it occurs in free text. Note: For record transformations where the entire cell in a table is being transformed, surrogates are not mandatory. Surrogates are used to denote the location of the token and are necessary for re-identification in free form text. In order for inspection to work properly, the name of this info type must not occur naturally anywhere in your data; otherwise, inspection may either - reverse a surrogate that does not correspond to an actual identifier - be unable to parse the surrogate and result in an error Therefore, choose your custom info type name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"cryptoHashConfig": { # Pseudonymization method that generates surrogates via cryptographic hashing. Uses SHA-256. The key size must be either 32 or 64 bytes. Outputs a base64 encoded representation of the hashed output (for example, L7k0BHmF1ha5U3NfGykjro4xWi1MPVQPjhMAZbSV9mM=). Currently, only string and integer values can be hashed. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. # Crypto
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # The key used by the hash function.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
},
"cryptoReplaceFfxFpeConfig": { # Replaces an identifier with a surrogate using Format Preserving Encryption (FPE) with the FFX mode of operation; however when used in the `ReidentifyContent` API method, it serves the opposite function by reversing the surrogate back into the original identifier. The identifier must be encoded as ASCII. For a given crypto key and context, the same identifier will be replaced with the same surrogate. Identifiers must be at least two characters long. In the case that the identifier is the empty string, it will be skipped. See https://cloud.google.com/sensitive-data-protection/docs/pseudonymization to learn more. Note: We recommend using CryptoDeterministicConfig for all use cases which do not require preserving the input alphabet space and size, plus warrant referential integrity. # Ffx-Fpe
"commonAlphabet": "A String", # Common alphabets.
"context": { # General identifier of a data field in a storage service. # The 'tweak', a context may be used for higher security since the same identifier in two different contexts won't be given the same surrogate. If the context is not set, a default tweak will be used. If the context is set but: 1. there is no record present when transforming a given value or 1. the field is not present when transforming a given value, a default tweak will be used. Note that case (1) is expected when an `InfoTypeTransformation` is applied to both structured and unstructured `ContentItem`s. Currently, the referenced field may be of value type integer or string. The tweak is constructed as a sequence of bytes in big endian byte order such that: - a 64 bit integer is encoded followed by a single byte of value 1 - a string is encoded in UTF-8 format followed by a single byte of value 2
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Required. The key used by the encryption algorithm.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"customAlphabet": "A String", # This is supported by mapping these to the alphanumeric characters that the FFX mode natively supports. This happens before/after encryption/decryption. Each character listed must appear only once. Number of characters must be in the range [2, 95]. This must be encoded as ASCII. The order of characters does not matter. The full list of allowed characters is: ``0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz~`!@#$%^&*()_-+={[}]|\:;"'<,>.?/``
"radix": 42, # The native way to select the alphabet. Must be in the range [2, 95].
"surrogateInfoType": { # Type of information detected by the API. # The custom infoType to annotate the surrogate with. This annotation will be applied to the surrogate by prefixing it with the name of the custom infoType followed by the number of characters comprising the surrogate. The following scheme defines the format: info_type_name(surrogate_character_count):surrogate For example, if the name of custom infoType is 'MY_TOKEN_INFO_TYPE' and the surrogate is 'abc', the full replacement value will be: 'MY_TOKEN_INFO_TYPE(3):abc' This annotation identifies the surrogate when inspecting content using the custom infoType [`SurrogateType`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/InspectConfig#surrogatetype). This facilitates reversal of the surrogate when it occurs in free text. In order for inspection to work properly, the name of this infoType must not occur naturally anywhere in your data; otherwise, inspection may find a surrogate that does not correspond to an actual identifier. Therefore, choose your custom infoType name carefully after considering what your data looks like. One way to select a name that has a high chance of yielding reliable detection is to include one or more unicode characters that are highly improbable to exist in your data. For example, assuming your data is entered from a regular ASCII keyboard, the symbol with the hex code point 29DD might be used like so: ⧝MY_TOKEN_TYPE
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
"dateShiftConfig": { # Shifts dates by random number of days, with option to be consistent for the same context. See https://cloud.google.com/sensitive-data-protection/docs/concepts-date-shifting to learn more. # Date Shift
"context": { # General identifier of a data field in a storage service. # Points to the field that contains the context, for example, an entity id. If set, must also set cryptoKey. If set, shift will be consistent for the given context.
"name": "A String", # Name describing the field.
},
"cryptoKey": { # This is a data encryption key (DEK) (as opposed to a key encryption key (KEK) stored by Cloud Key Management Service (Cloud KMS). When using Cloud KMS to wrap or unwrap a DEK, be sure to set an appropriate IAM policy on the KEK to ensure an attacker cannot unwrap the DEK. # Causes the shift to be computed based on this key and the context. This results in the same shift for the same context and crypto_key. If set, must also set context. Can only be applied to table items.
"kmsWrapped": { # Include to use an existing data crypto key wrapped by KMS. The wrapped key must be a 128-, 192-, or 256-bit key. Authorization requires the following IAM permissions when sending a request to perform a crypto transformation using a KMS-wrapped crypto key: dlp.kms.encrypt For more information, see [Creating a wrapped key] (https://cloud.google.com/sensitive-data-protection/docs/create-wrapped-key). Note: When you use Cloud KMS for cryptographic operations, [charges apply](https://cloud.google.com/kms/pricing). # Key wrapped using Cloud KMS
"cryptoKeyName": "A String", # Required. The resource name of the KMS CryptoKey to use for unwrapping.
"wrappedKey": "A String", # Required. The wrapped data crypto key.
},
"transient": { # Use this to have a random data crypto key generated. It will be discarded after the request finishes. # Transient crypto key
"name": "A String", # Required. Name of the key. This is an arbitrary string used to differentiate different keys. A unique key is generated per name: two separate `TransientCryptoKey` protos share the same generated key if their names are the same. When the data crypto key is generated, this name is not used in any way (repeating the api call will result in a different key being generated).
},
"unwrapped": { # Using raw keys is prone to security risks due to accidentally leaking the key. Choose another type of key if possible. # Unwrapped crypto key
"key": "A String", # Required. A 128/192/256 bit key.
},
},
"lowerBoundDays": 42, # Required. For example, -5 means shift date to at most 5 days back in the past.
"upperBoundDays": 42, # Required. Range of shift in days. Actual shift will be selected at random within this range (inclusive ends). Negative means shift to earlier in time. Must not be more than 365250 days (1000 years) each direction. For example, 3 means shift date to at most 3 days into the future.
},
"fixedSizeBucketingConfig": { # Buckets values based on fixed size ranges. The Bucketing transformation can provide all of this functionality, but requires more configuration. This message is provided as a convenience to the user for simple bucketing strategies. The transformed value will be a hyphenated string of {lower_bound}-{upper_bound}. For example, if lower_bound = 10 and upper_bound = 20, all values that are within this bucket will be replaced with "10-20". This can be used on data of type: double, long. If the bound Value type differs from the type of data being transformed, we will first attempt converting the type of the data to be transformed to match the type of the bound before comparing. See https://cloud.google.com/sensitive-data-protection/docs/concepts-bucketing to learn more. # Fixed size bucketing
"bucketSize": 3.14, # Required. Size of each bucket (except for minimum and maximum buckets). So if `lower_bound` = 10, `upper_bound` = 89, and `bucket_size` = 10, then the following buckets would be used: -10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70-80, 80-89, 89+. Precision up to 2 decimals works.
"lowerBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Lower bound value of buckets. All values less than `lower_bound` are grouped together into a single bucket; for example if `lower_bound` = 10, then all values less than 10 are replaced with the value "-10".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"upperBound": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Required. Upper bound value of buckets. All values greater than upper_bound are grouped together into a single bucket; for example if `upper_bound` = 89, then all values greater than 89 are replaced with the value "89+".
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"redactConfig": { # Redact a given value. For example, if used with an `InfoTypeTransformation` transforming PHONE_NUMBER, and input 'My phone number is 206-555-0123', the output would be 'My phone number is '. # Redact
},
"replaceConfig": { # Replace each input value with a given `Value`. # Replace with a specified value.
"newValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to replace it with.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
"replaceDictionaryConfig": { # Replace each input value with a value randomly selected from the dictionary. # Replace with a value randomly drawn (with replacement) from a dictionary.
"wordList": { # Message defining a list of words or phrases to search for in the data. # A list of words to select from for random replacement. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"replaceWithInfoTypeConfig": { # Replace each matching finding with the name of the info_type. # Replace with infotype
},
"timePartConfig": { # For use with `Date`, `Timestamp`, and `TimeOfDay`, extract or preserve a portion of the value. # Time extraction
"partToExtract": "A String", # The part of the time to keep.
},
},
},
],
"recordSuppressions": [ # Configuration defining which records get suppressed entirely. Records that match any suppression rule are omitted from the output.
{ # Configuration to suppress records whose suppression conditions evaluate to true.
"condition": { # A condition for determining whether a transformation should be applied to a field. # A condition that when it evaluates to true will result in the record being evaluated to be suppressed from the transformed content.
"expressions": { # An expression, consisting of an operator and conditions. # An expression.
"conditions": { # A collection of conditions. # Conditions to apply to the expression.
"conditions": [ # A collection of conditions.
{ # The field type of `value` and `field` do not need to match to be considered equal, but not all comparisons are possible. EQUAL_TO and NOT_EQUAL_TO attempt to compare even with incompatible types, but all other comparisons are invalid with incompatible types. A `value` of type: - `string` can be compared against all other types - `boolean` can only be compared against other booleans - `integer` can be compared against doubles or a string if the string value can be parsed as an integer. - `double` can be compared against integers or a string if the string can be parsed as a double. - `Timestamp` can be compared against strings in RFC 3339 date string format. - `TimeOfDay` can be compared against timestamps and strings in the format of 'HH:mm:ss'. If we fail to compare do to type mismatch, a warning will be given and the condition will evaluate to false.
"field": { # General identifier of a data field in a storage service. # Required. Field within the record this condition is evaluated against.
"name": "A String", # Name describing the field.
},
"operator": "A String", # Required. Operator used to compare the field or infoType to the value.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Value to compare against. [Mandatory, except for `EXISTS` tests.]
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
"logicalOperator": "A String", # The operator to apply to the result of conditions. Default and currently only supported value is `AND`.
},
},
},
],
},
"transformationErrorHandling": { # How to handle transformation errors during de-identification. A transformation error occurs when the requested transformation is incompatible with the data. For example, trying to de-identify an IP address using a `DateShift` transformation would result in a transformation error, since date info cannot be extracted from an IP address. Information about any incompatible transformations, and how they were handled, is returned in the response as part of the `TransformationOverviews`. # Mode for handling transformation errors. If left unspecified, the default mode is `TransformationErrorHandling.ThrowError`.
"leaveUntransformed": { # Skips the data without modifying it if the requested transformation would cause an error. For example, if a `DateShift` transformation were applied an an IP address, this mode would leave the IP address unchanged in the response. # Ignore errors
},
"throwError": { # Throw an error and fail the request when a transformation error occurs. # Throw an error
},
},
},
"description": "A String", # Short description (max 256 chars).
"displayName": "A String", # Display name (max 256 chars).
"name": "A String", # Output only. The template name. The template will have one of the following formats: `projects/PROJECT_ID/deidentifyTemplates/TEMPLATE_ID` OR `organizations/ORGANIZATION_ID/deidentifyTemplates/TEMPLATE_ID`
"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.
},
},
},
},
],
"createTime": "A String", # Time when the job was created.
"endTime": "A String", # Time when the job finished.
"errors": [ # A stream of errors encountered running the job.
{ # Details information about an error encountered during job execution or the results of an unsuccessful activation of the JobTrigger.
"details": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Detailed error codes and messages.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"extraInfo": "A String", # Additional information about the error.
"timestamps": [ # The times the error occurred. List includes the oldest timestamp and the last 9 timestamps.
"A String",
],
},
],
"inspectDetails": { # The results of an inspect DataSource job. # Results from inspecting a data source.
"requestedOptions": { # Snapshot of the inspection configuration. # The configuration used for this job.
"jobConfig": { # Controls what and how to inspect for findings. # Inspect config.
"actions": [ # Actions to execute at the completion of the job.
{ # A task to execute on the completion of a job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-actions to learn more.
"deidentify": { # Create a de-identified copy of the requested table or files. A TransformationDetail will be created for each transformation. If any rows in BigQuery are skipped during de-identification (transformation errors or row size exceeds BigQuery insert API limits) they are placed in the failure output table. If the original row exceeds the BigQuery insert API limit it will be truncated when written to the failure output table. The failure output table can be set in the action.deidentify.output.big_query_output.deidentified_failure_output_table field, if no table is set, a table will be automatically created in the same project and dataset as the original table. Compatible with: Inspect # Create a de-identified copy of the input data.
"cloudStorageOutput": "A String", # Required. User settable Cloud Storage bucket and folders to store de-identified files. This field must be set for Cloud Storage deidentification. The output Cloud Storage bucket must be different from the input bucket. De-identified files will overwrite files in the output path. Form of: gs://bucket/folder/ or gs://bucket
"fileTypesToTransform": [ # List of user-specified file type groups to transform. If specified, only the files with these file types will be transformed. If empty, all supported files will be transformed. Supported types may be automatically added over time. If a file type is set in this field that isn't supported by the Deidentify action then the job will fail and will not be successfully created/started. Currently the only file types supported are: IMAGES, TEXT_FILES, CSV, TSV.
"A String",
],
"transformationConfig": { # User specified templates and configs for how to deidentify structured, unstructures, and image files. User must provide either a unstructured deidentify template or at least one redact image config. # User specified deidentify templates and configs for structured, unstructured, and image files.
"deidentifyTemplate": "A String", # De-identify template. If this template is specified, it will serve as the default de-identify template. This template cannot contain `record_transformations` since it can be used for unstructured content such as free-form text files. If this template is not set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify unstructured content.
"imageRedactTemplate": "A String", # Image redact template. If this template is specified, it will serve as the de-identify template for images. If this template is not set, all findings in the image will be redacted with a black box.
"structuredDeidentifyTemplate": "A String", # Structured de-identify template. If this template is specified, it will serve as the de-identify template for structured content such as delimited files and tables. If this template is not set but the `deidentify_template` is set, then `deidentify_template` will also apply to the structured content. If neither template is set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify structured content.
},
"transformationDetailsStorageConfig": { # Config for storing transformation details. # Config for storing transformation details. This is separate from the de-identified content, and contains metadata about the successful transformations and/or failures that occurred while de-identifying. This needs to be set in order for users to access information about the status of each transformation (see TransformationDetails message for more information about what is noted).
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # The BigQuery table in which to store the output. This may be an existing table or in a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_transformation_details_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"jobNotificationEmails": { # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts). # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts).
},
"pubSub": { # Publish a message into a given Pub/Sub topic when DlpJob has completed. The message contains a single field, `DlpJobName`, which is equal to the finished job's [`DlpJob.name`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/projects.dlpJobs#DlpJob). Compatible with: Inspect, Risk # Publish a notification to a Pub/Sub topic.
"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given publishing access rights to the DLP API service account executing the long running DlpJob sending the notifications. Format is projects/{project}/topics/{topic}.
},
"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Data Catalog. In Data Catalog, tag templates are applied to the resource that Cloud DLP scanned. Data Catalog tag templates are stored in the same project and region where the BigQuery table exists. For Cloud DLP to create and apply the tag template, the Cloud DLP service agent must have the `roles/datacatalog.tagTemplateOwner` permission on the project. The tag template contains fields summarizing the results of the DlpJob. Any field values previously written by another DlpJob are deleted. InfoType naming patterns are strictly enforced when using this feature. Findings are persisted in Data Catalog storage and are governed by service-specific policies for Data Catalog. For more information, see [Service Specific Terms](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. This action is allowed only if all resources being scanned are BigQuery tables. Compatible with: Inspect # Publish findings to Cloud Datahub.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to [Security Command Center](https://cloud.google.com/security-command-center). This action is available for only projects that belong to an organization. This action publishes the count of finding instances and their infoTypes. The summary of findings are persisted in Security Command Center and are governed by [service-specific policies for Security Command Center](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. Compatible with: Inspect # Publish summary to Cloud Security Command Center (Alpha).
},
"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This will publish a metric to stack driver on each infotype requested and how many findings were found for it. CustomDetectors will be bucketed as 'Custom' under the Stackdriver label 'info_type'. # Enable Stackdriver metric dlp.googleapis.com/finding_count.
},
"saveFindings": { # If set, the detailed findings will be persisted to the specified OutputStorageConfig. Only a single instance of this action can be specified. Compatible with: Inspect, Risk # Save resulting findings in a provided location.
"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only used for Inspect and must be unspecified for Risk jobs. Columns are derived from the `Finding` object. If appending to an existing table, any columns from the predefined schema that are missing will be added. No columns in the existing table will be deleted. If unspecified, then all available columns will be used for a new table or an (existing) table with no schema, and no changes will be made to an existing table that has a schema. Only for use with external storage.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Store findings in an existing table or a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details. For Inspect, each column in an existing output table must have the same name, type, and mode of a field in the `Finding` object. For Risk, an existing output table should be the output of a previous Risk analysis job run on the same source table, with the same privacy metric and quasi-identifiers. Risk jobs that analyze the same table but compute a different privacy metric, or use different sets of quasi-identifiers, cannot store their results in the same table.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
},
],
"inspectConfig": { # Configuration description of the scanning process. When used with redactContent only info_types and min_likelihood are currently used. # How and what to scan for.
"contentOptions": [ # Deprecated and unused.
"A String",
],
"customInfoTypes": [ # CustomInfoTypes provided by the user. See https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes to learn more.
{ # Custom information type provided by the user. Used to find domain-specific sensitive information configurable to the data in question.
"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. Rules are applied in order that they are specified. Not supported for the `surrogate_type` CustomInfoType.
{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a `CustomInfoType` to alter behavior under certain circumstances, depending on the specific details of the rule. Not supported for the `surrogate_type` custom infoType.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "$\d{3}$ \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "$xxx$", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # A list of phrases to detect as a CustomInfoType.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding to be returned. It still can be used for rules matching.
"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in infoType, when the name matches one of existing infoTypes and that infoType is specified in `InspectContent.info_types` field. Specifying the latter adds findings to the one detected by the system. If built-in info type is not specified in `InspectContent.info_types` list then the name is treated as a custom info type.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be altered by a detection rule if the finding meets the criteria specified by the rule. Defaults to `VERY_LIKELY` if not specified.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Sensitivity for this CustomInfoType. If this CustomInfoType extends an existing InfoType, the sensitivity here will take precedence over that of the original InfoType. If unset for a CustomInfoType, it will default to HIGH. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in `InspectDataSource`. Not currently supported in `InspectContent`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for inspection was created. Output-only field, populated by the system.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example `organizations/433245324/storedInfoTypes/432452342` or `projects/project-id/storedInfoTypes/432452342`.
},
"surrogateType": { # Message for detecting output from deidentification transformations such as [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). These types of transformations are those that perform pseudonymization, thereby producing a "surrogate" as output. This should be used in conjunction with a field on the transformation such as `surrogate_info_type`. This CustomInfoType does not support the use of `detection_rules`. # Message for detecting output from deidentification transformations that support reversing.
},
},
],
"excludeInfoTypes": True or False, # When true, excludes type information of the findings. This is not used for data profiling.
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is included in the response; see Finding.quote. This is not used for data profiling.
"infoTypes": [ # Restricts what info_types to look for. The values must correspond to InfoType values returned by ListInfoTypes or listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference. When no InfoTypes or CustomInfoTypes are specified in a request, the system may automatically choose a default list of detectors to run, which may change over time. If you need precise control and predictability as to what detectors are run you should specify specific InfoTypes listed in the reference, otherwise a default list will be used, which may change over time.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"limits": { # Configuration to control the number of findings returned for inspection. This is not used for de-identification or data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. # Configuration to control the number of findings returned. This is not used for data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. When set within an InspectJobConfig, the specified maximum values aren't hard limits. If an inspection job reaches these limits, the job ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than these maximum values.
"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
{ # Max findings configuration per infoType, per content item or long running DlpJob.
"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per info_type should be provided. If InfoTypeLimit does not have an info_type, the DLP API applies the limit against all info_types that are found but not specified in another InfoTypeLimit.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that are returned for each item scanned. When set within an InspectContentRequest, this field is ignored. This value isn't a hard limit. If the number of findings for an item reaches this limit, the inspection of that item ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns for the item can be multiple times higher than this value.
"maxFindingsPerRequest": 42, # Max number of findings that are returned per request or job. If you set this field in an InspectContentRequest, the resulting maximum value is the value that you set or 3,000, whichever is lower. This value isn't a hard limit. If an inspection reaches this limit, the inspection ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than this value.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. The default is POSSIBLE. In general, the highest likelihood setting yields the fewest findings in results and the lowest chance of a false positive. For more information, see [Match likelihood](https://cloud.google.com/sensitive-data-protection/docs/likelihood).
"minLikelihoodPerInfoType": [ # Minimum likelihood per infotype. For each infotype, a user can specify a minimum likelihood. The system only returns a finding if its likelihood is above this threshold. If this field is not set, the system uses the InspectConfig min_likelihood.
{ # Configuration for setting a minimum likelihood per infotype. Used to customize the minimum likelihood level for specific infotypes in the request. For example, use this if you want to lower the precision for PERSON_NAME without lowering the precision for the other infotypes in the request.
"infoType": { # Type of information detected by the API. # Type of information the likelihood threshold applies to. Only one likelihood per info_type should be provided. If InfoTypeLikelihood does not have an info_type, the configuration fails.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. This field is required or else the configuration fails.
},
],
"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. Exclusion rules, contained in the set are executed in the end, other rules are executed in the order they are specified for each info type.
{ # Rule set for modifying a set of infoTypes to alter behavior under certain circumstances, depending on the specific details of the rules within the set.
"infoTypes": [ # List of infoTypes this rule set is applied to.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
{ # A single inspection rule to be applied to infoTypes, specified in `InspectionRuleSet`.
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in `InspectionRuleSet` are removed from results. # Exclusion rule.
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # Dictionary which defines the rule.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"excludeByHotword": { # The rule to exclude findings based on a hotword. For record inspection of tables, column names are considered hotwords. An example of this is to exclude a finding if it belongs to a BigQuery column that matches a specific pattern. # Drop if the hotword rule is contained in the proximate context. For tabular data, the context includes the column name.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The windowBefore property in proximity should be set to 1 if the hotword needs to be included in a column header.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
"excludeInfoTypes": { # List of excluded infoTypes. # Set of infoTypes for which findings would affect this rule.
"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or contained within with a finding of an infoType from this list. For example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and `exclusion_rule` containing `exclude_info_types.info_types` with "EMAIL_ADDRESS" the phone number findings are dropped if they overlap with EMAIL_ADDRESS finding. That leads to "555-222-2222@example.org" to generate only a single finding, namely email address.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
},
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "$\d{3}$ \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "$xxx$", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
},
],
},
"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig. `inspect_config` will be merged into the values persisted as part of the template.
"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
"excludedFields": [ # References to fields excluded from scanning. This allows you to skip inspection of entire columns which you know have no findings. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When `actions.saveFindings.outputConfig.table` is specified, the values of columns specified here are available in the output table under `location.content_locations.record_location.record_key.id_values`. Nested fields such as `person.birthdate.year` are allowed.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"includedFields": [ # Limit scanning only to these fields. When inspecting a table, we recommend that you inspect all columns. Otherwise, findings might be affected because hints from excluded columns will not be used.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the rest of the rows are omitted. If not set, or if set to 0, all rows will be scanned. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig.
"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of rows_limit and rows_limit_percent can be specified. Cannot be used in conjunction with TimespanConfig. Caution: A [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-sampling) is causing the `rowsLimitPercent` field to behave unexpectedly. We recommend using `rowsLimit` instead.
"sampleMethod": "A String", # How to sample the data.
"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Complete BigQuery table reference.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
"cloudStorageOptions": { # Options defining a file or a set of files within a Cloud Storage bucket. # Cloud Storage options.
"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger than this value then the rest of the bytes are omitted. Only one of `bytes_limit_per_file` and `bytes_limit_per_file_percent` can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The number of bytes scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. This field can't be set if de-identification is requested. For certain file types, setting this field has no effect. For more information, see [Limits on bytes scanned per file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
"fileSet": { # Set of files to scan. # The set of one or more files to scan.
"regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular expressions are used to allow fine-grained control over which files in the bucket to include. Included files are those that match at least one item in `include_regex` and do not match any items in `exclude_regex`. Note that a file that matches items from both lists will _not_ be included. For a match to occur, the entire file path (i.e., everything in the url after the bucket name) must match the regular expression. For example, given the input `{bucket_name: "mybucket", include_regex: ["directory1/.*"], exclude_regex: ["directory1/excluded.*"]}`: * `gs://mybucket/directory1/myfile` will be included * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches across `/`) * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the full path doesn't match any items in `include_regex`) * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path matches an item in `exclude_regex`) If `include_regex` is left empty, it will match all files by default (this is equivalent to setting `include_regex: [".*"]`). Some other common use cases: * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all files in `mybucket` except for .pdf files * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will include all files directly under `gs://mybucket/directory/`, without matching across `/` # The regex-filtered set of files to scan. Exactly one of `url` or `regex_file_set` must be set.
"bucketName": "A String", # The name of a Cloud Storage bucket. Required.
"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in the bucket that match at least one of these regular expressions will be excluded from the scan. Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
"includeRegex": [ # A list of regular expressions matching file paths to include. All files in the bucket that match at least one of these regular expressions will be included in the set of files, except for those that also match an item in `exclude_regex`. Leaving this field empty will match all files by default (this is equivalent to including `.*` in the list). Regular expressions use RE2 [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found under the google/re2 repository on GitHub.
"A String",
],
},
"url": "A String", # The Cloud Storage url of the file(s) to scan, in the format `gs:///`. Trailing wildcard in the path is allowed. If the url ends in a trailing slash, the bucket or directory represented by the url will be scanned non-recursively (content in sub-directories will not be scanned). This means that `gs://mybucket/` is equivalent to `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to `gs://mybucket/directory/*`. Exactly one of `url` or `regex_file_set` must be set.
},
"fileTypes": [ # List of file type groups to include in the scan. If empty, all files are scanned and available data format processors are applied. In addition, the binary content of the selected files is always scanned as well. Images are scanned only as binary if the specified region does not support image inspection and no file_types were specified. Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
"A String",
],
"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet. Number of files scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0.
"sampleMethod": "A String", # How to sample the data.
},
"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
"kind": { # A representation of a Datastore kind. # The kind to process.
"name": "A String", # The name of the kind.
},
"partitionId": { # Datastore partition ID. A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty. A partition ID contains several dimensions: project ID and namespace ID. # A partition ID identifies a grouping of entities. The grouping is always by project and namespace, however the namespace ID may be empty.
"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
"projectId": "A String", # The ID of the project to which the entities belong.
},
},
"hybridOptions": { # Configuration to control jobs where the content being inspected is outside of Google Cloud Platform. # Hybrid inspection options.
"description": "A String", # A short description of where the data is coming from. Will be stored once in the job. 256 max length.
"labels": { # To organize findings, these labels will be added to each finding. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. Label values must be between 0 and 63 characters long and must conform to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`. No more than 10 labels can be associated with a given finding. Examples: * `"environment" : "production"` * `"pipeline" : "etl"`
"a_key": "A String",
},
"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their 'finding_labels' map. Request may contain others, but any missing one of these will be rejected. Label keys must be between 1 and 63 characters long and must conform to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. No more than 10 keys can be required.
"A String",
],
"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings meaningful such as the columns that are primary keys.
"identifyingFields": [ # The columns that are the primary keys for table objects included in ContentItem. A copy of this cell's value will stored alongside alongside each finding so that the finding can be traced to the specific row it came from. No more than 3 may be provided.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
},
"timespanConfig": { # Configuration of the timespan of the items to include in scanning. Currently only supported when inspecting Cloud Storage and BigQuery. # Configuration of the timespan of the items to include in scanning.
"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out a valid start_time to avoid scanning files that have not been modified since the last time the JobTrigger executed. This will be based on the time of the execution of the last run of the JobTrigger or the timespan end_time used in the last run of the JobTrigger. **For BigQuery** Inspect jobs triggered by automatic population will scan data that is at least three hours old when the job starts. This is because streaming buffer rows are not read during inspection and reading up to the current timestamp will result in skipped rows. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#recently-streamed-data) related to this operation.
"endTime": "A String", # Exclude files, tables, or rows newer than this value. If not set, no upper time limit is applied.
"startTime": "A String", # Exclude files, tables, or rows older than this value. If not set, no lower time limit is applied.
"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items. Used for data sources like Datastore and BigQuery. **For BigQuery** If this value is not specified and the table was modified between the given start and end times, the entire table will be scanned. If this value is specified, then rows are filtered based on the given start and end times. Rows with a `NULL` value in the provided BigQuery column are skipped. Valid data types of the provided BigQuery column are: `INTEGER`, `DATE`, `TIMESTAMP`, and `DATETIME`. If your BigQuery table is [partitioned at ingestion time](https://cloud.google.com/bigquery/docs/partitioned-tables#ingestion_time), you can use any of the following pseudo-columns as your timestamp field. When used with Cloud DLP, these pseudo-column names are case sensitive. - `_PARTITIONTIME` - `_PARTITIONDATE` - `_PARTITION_LOAD_TIME` **For Datastore** If this value is specified, then entities are filtered based on the given start and end times. If an entity does not contain the provided timestamp property or contains empty or invalid values, then it is included. Valid data types of the provided timestamp property are: `TIMESTAMP`. See the [known issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-timespan) related to this operation.
"name": "A String", # Name describing the field.
},
},
},
},
"snapshotInspectTemplate": { # The inspectTemplate contains a configuration (set of types of sensitive data to be detected) to be used anywhere you otherwise would normally specify InspectConfig. See https://cloud.google.com/sensitive-data-protection/docs/concepts-templates to learn more. # If run with an InspectTemplate, a snapshot of its state at the time of this run.
"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.
"description": "A String", # Short description (max 256 chars).
"displayName": "A String", # Display name (max 256 chars).
"inspectConfig": { # Configuration description of the scanning process. When used with redactContent only info_types and min_likelihood are currently used. # The core content of the template. Configuration of the scanning process.
"contentOptions": [ # Deprecated and unused.
"A String",
],
"customInfoTypes": [ # CustomInfoTypes provided by the user. See https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes to learn more.
{ # Custom information type provided by the user. Used to find domain-specific sensitive information configurable to the data in question.
"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. Rules are applied in order that they are specified. Not supported for the `surrogate_type` CustomInfoType.
{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a `CustomInfoType` to alter behavior under certain circumstances, depending on the specific details of the rule. Not supported for the `surrogate_type` custom infoType.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "$\d{3}$ \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "$xxx$", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # A list of phrases to detect as a CustomInfoType.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding to be returned. It still can be used for rules matching.
"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in infoType, when the name matches one of existing infoTypes and that infoType is specified in `InspectContent.info_types` field. Specifying the latter adds findings to the one detected by the system. If built-in info type is not specified in `InspectContent.info_types` list then the name is treated as a custom info type.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be altered by a detection rule if the finding meets the criteria specified by the rule. Defaults to `VERY_LIKELY` if not specified.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Sensitivity for this CustomInfoType. If this CustomInfoType extends an existing InfoType, the sensitivity here will take precedence over that of the original InfoType. If unset for a CustomInfoType, it will default to HIGH. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in `InspectDataSource`. Not currently supported in `InspectContent`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for inspection was created. Output-only field, populated by the system.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example `organizations/433245324/storedInfoTypes/432452342` or `projects/project-id/storedInfoTypes/432452342`.
},
"surrogateType": { # Message for detecting output from deidentification transformations such as [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). These types of transformations are those that perform pseudonymization, thereby producing a "surrogate" as output. This should be used in conjunction with a field on the transformation such as `surrogate_info_type`. This CustomInfoType does not support the use of `detection_rules`. # Message for detecting output from deidentification transformations that support reversing.
},
},
],
"excludeInfoTypes": True or False, # When true, excludes type information of the findings. This is not used for data profiling.
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is included in the response; see Finding.quote. This is not used for data profiling.
"infoTypes": [ # Restricts what info_types to look for. The values must correspond to InfoType values returned by ListInfoTypes or listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference. When no InfoTypes or CustomInfoTypes are specified in a request, the system may automatically choose a default list of detectors to run, which may change over time. If you need precise control and predictability as to what detectors are run you should specify specific InfoTypes listed in the reference, otherwise a default list will be used, which may change over time.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"limits": { # Configuration to control the number of findings returned for inspection. This is not used for de-identification or data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. # Configuration to control the number of findings returned. This is not used for data profiling. When redacting sensitive data from images, finding limits don't apply. They can cause unexpected or inconsistent results, where only some data is redacted. Don't include finding limits in RedactImage requests. Otherwise, Cloud DLP returns an error. When set within an InspectJobConfig, the specified maximum values aren't hard limits. If an inspection job reaches these limits, the job ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than these maximum values.
"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
{ # Max findings configuration per infoType, per content item or long running DlpJob.
"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per info_type should be provided. If InfoTypeLimit does not have an info_type, the DLP API applies the limit against all info_types that are found but not specified in another InfoTypeLimit.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that are returned for each item scanned. When set within an InspectContentRequest, this field is ignored. This value isn't a hard limit. If the number of findings for an item reaches this limit, the inspection of that item ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns for the item can be multiple times higher than this value.
"maxFindingsPerRequest": 42, # Max number of findings that are returned per request or job. If you set this field in an InspectContentRequest, the resulting maximum value is the value that you set or 3,000, whichever is lower. This value isn't a hard limit. If an inspection reaches this limit, the inspection ends gradually, not abruptly. Therefore, the actual number of findings that Cloud DLP returns can be multiple times higher than this value.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. The default is POSSIBLE. In general, the highest likelihood setting yields the fewest findings in results and the lowest chance of a false positive. For more information, see [Match likelihood](https://cloud.google.com/sensitive-data-protection/docs/likelihood).
"minLikelihoodPerInfoType": [ # Minimum likelihood per infotype. For each infotype, a user can specify a minimum likelihood. The system only returns a finding if its likelihood is above this threshold. If this field is not set, the system uses the InspectConfig min_likelihood.
{ # Configuration for setting a minimum likelihood per infotype. Used to customize the minimum likelihood level for specific infotypes in the request. For example, use this if you want to lower the precision for PERSON_NAME without lowering the precision for the other infotypes in the request.
"infoType": { # Type of information detected by the API. # Type of information the likelihood threshold applies to. Only one likelihood per info_type should be provided. If InfoTypeLikelihood does not have an info_type, the configuration fails.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
"minLikelihood": "A String", # Only returns findings equal to or above this threshold. This field is required or else the configuration fails.
},
],
"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. Exclusion rules, contained in the set are executed in the end, other rules are executed in the order they are specified for each info type.
{ # Rule set for modifying a set of infoTypes to alter behavior under certain circumstances, depending on the specific details of the rules within the set.
"infoTypes": [ # List of infoTypes this rule set is applied to.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
{ # A single inspection rule to be applied to infoTypes, specified in `InspectionRuleSet`.
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in `InspectionRuleSet` are removed from results. # Exclusion rule.
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can be used to match sensitive information specific to the data, such as a list of employee IDs or job titles. Dictionary words are case-insensitive and all characters other than letters and digits in the unicode [Basic Multilingual Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) will be replaced with whitespace when scanning for matches, so the dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters surrounding any match must be of a different type than the adjacent characters within the word, so letters must be next to non-letters and digits next to non-digits. For example, the dictionary word "jen" will match the first three letters of the text "jen123" but will return no matches for "jennifer". Dictionary words containing a large number of characters that are not letters or digits may result in unexpected findings because such characters are treated as whitespace. The [limits](https://cloud.google.com/sensitive-data-protection/limits) page contains details about the size limits of dictionaries. For dictionaries that do not fit within these constraints, consider using `LargeCustomDictionaryConfig` in the `StoredInfoType` API. # Dictionary which defines the rule.
"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file is accepted.
"path": "A String", # A URL representing a file or path (no wildcards) in Cloud Storage. Example: `gs://[BUCKET_NAME]/dictionary.txt`
},
"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
"words": [ # Words or phrases defining the dictionary. The dictionary must contain at least one phrase and every phrase must contain at least 2 characters that are letters or digits. [required]
"A String",
],
},
},
"excludeByHotword": { # The rule to exclude findings based on a hotword. For record inspection of tables, column names are considered hotwords. An example of this is to exclude a finding if it belongs to a BigQuery column that matches a specific pattern. # Drop if the hotword rule is contained in the proximate context. For tabular data, the context includes the column name.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The windowBefore property in proximity should be set to 1 if the hotword needs to be included in a column header.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
"excludeInfoTypes": { # List of excluded infoTypes. # Set of infoTypes for which findings would affect this rule.
"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or contained within with a finding of an infoType from this list. For example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and `exclusion_rule` containing `exclude_info_types.info_types` with "EMAIL_ADDRESS" the phone number findings are dropped if they overlap with EMAIL_ADDRESS finding. That leads to "555-222-2222@example.org" to generate only a single finding, namely email address.
{ # Type of information detected by the API.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
],
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
},
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain proximity of hotwords. # Hotword-based detection rule.
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"groupIndexes": [ # The index of the submatch to extract as findings. When not specified, the entire match is returned. No more than 3 may be included.
42,
],
"pattern": "A String", # Pattern defining the regular expression. Its syntax (https://github.com/google/re2/wiki/Syntax) can be found under the google/re2 repository on GitHub.
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as part of a detection rule. # Likelihood adjustment to apply to all matching findings.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of levels. For example, if a finding would be `POSSIBLE` without the detection rule and `relative_likelihood` is 1, then it is upgraded to `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. Likelihood may never drop below `VERY_UNLIKELY` or exceed `VERY_LIKELY`, so applying an adjustment of 1 followed by an adjustment of -1 when base likelihood is `VERY_LIKELY` will result in a final likelihood of `LIKELY`.
},
"proximity": { # Message for specifying a window around a finding to apply a detection rule. # Range of characters within which the entire hotword must reside. The total length of the window cannot exceed 1000 characters. The finding itself will be included in the window, so that hotwords can be used to match substrings of the finding itself. Suppose you want Cloud DLP to promote the likelihood of the phone number regex "$\d{3}$ \d{3}-\d{4}" if the area code is known to be the area code of a company's office. In this case, use the hotword regex "$xxx$", where "xxx" is the area code in question. For tabular data, if you want to modify the likelihood of an entire column of findngs, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider. For tabular data, if you want to modify the likelihood of an entire column of findngs, set this to 1. For more information, see [Hotword example: Set the match likelihood of a table column] (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
},
},
},
],
},
],
},
"name": "A String", # Output only. The template name. The template will have one of the following formats: `projects/PROJECT_ID/inspectTemplates/TEMPLATE_ID` OR `organizations/ORGANIZATION_ID/inspectTemplates/TEMPLATE_ID`;
"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.
},
},
"result": { # All result fields mentioned below are updated while the job is processing. # A summary of the outcome of this inspection job.
"hybridStats": { # Statistics related to processing hybrid inspect requests. # Statistics related to the processing of hybrid inspect.
"abortedCount": "A String", # The number of hybrid inspection requests aborted because the job ran out of quota or was ended before they could be processed.
"pendingCount": "A String", # The number of hybrid requests currently being processed. Only populated when called via method `getDlpJob`. A burst of traffic may cause hybrid inspect requests to be enqueued. Processing will take place as quickly as possible, but resource limitations may impact how long a request is enqueued for.
"processedCount": "A String", # The number of hybrid inspection requests processed within this job.
},
"infoTypeStats": [ # Statistics of how many instances of each info type were found during inspect job.
{ # Statistics regarding a specific InfoType.
"count": "A String", # Number of findings for this infoType.
"infoType": { # Type of information detected by the API. # The type of finding this stat is for.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"numRowsProcessed": "A String", # Number of rows scanned after sampling and time filtering (applicable for row based stores such as BigQuery).
"processedBytes": "A String", # Total size in bytes that were processed.
"totalEstimatedBytes": "A String", # Estimate of the number of bytes to process.
},
},
"jobTriggerName": "A String", # If created by a job trigger, the resource name of the trigger that instantiated the job.
"lastModified": "A String", # Time when the job was last modified by the system.
"name": "A String", # The server-assigned name.
"riskDetails": { # Result of a risk analysis operation request. # Results from analyzing risk of a data source.
"categoricalStatsResult": { # Result of the categorical stats computation. # Categorical stats result
"valueFrequencyHistogramBuckets": [ # Histogram of value frequencies in the column.
{ # Histogram of value frequencies in the column.
"bucketSize": "A String", # Total number of values in this bucket.
"bucketValueCount": "A String", # Total number of distinct values in this bucket.
"bucketValues": [ # Sample of value frequencies in this bucket. The total number of values returned per bucket is capped at 20.
{ # A value of a field, including its frequency.
"count": "A String", # How many times the value is contained in the field.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # A value contained in the field in question.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
"valueFrequencyLowerBound": "A String", # Lower bound on the value frequency of the values in this bucket.
"valueFrequencyUpperBound": "A String", # Upper bound on the value frequency of the values in this bucket.
},
],
},
"deltaPresenceEstimationResult": { # Result of the δ-presence computation. Note that these results are an estimation, not exact values. # Delta-presence result
"deltaPresenceEstimationHistogram": [ # The intervals [min_probability, max_probability) do not overlap. If a value doesn't correspond to any such interval, the associated frequency is zero. For example, the following records: {min_probability: 0, max_probability: 0.1, frequency: 17} {min_probability: 0.2, max_probability: 0.3, frequency: 42} {min_probability: 0.3, max_probability: 0.4, frequency: 99} mean that there are no record with an estimated probability in [0.1, 0.2) nor larger or equal to 0.4.
{ # A DeltaPresenceEstimationHistogramBucket message with the following values: min_probability: 0.1 max_probability: 0.2 frequency: 42 means that there are 42 records for which δ is in [0.1, 0.2). An important particular case is when min_probability = max_probability = 1: then, every individual who shares this quasi-identifier combination is in the dataset.
"bucketSize": "A String", # Number of records within these probability bounds.
"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.
"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total number of classes returned per bucket is capped at 20.
{ # A tuple of values for the quasi-identifier columns.
"estimatedProbability": 3.14, # The estimated probability that a given individual sharing these quasi-identifier values is in the dataset. This value, typically called δ, is the ratio between the number of records in the dataset with these quasi-identifier values, and the total number of individuals (inside *and* outside the dataset) with these quasi-identifier values. For example, if there are 15 individuals in the dataset who share the same quasi-identifier values, and an estimated 100 people in the entire population with these values, then δ is 0.15.
"quasiIdsValues": [ # The quasi-identifier values.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
},
],
"maxProbability": 3.14, # Always greater than or equal to min_probability.
"minProbability": 3.14, # Between 0 and 1.
},
],
},
"kAnonymityResult": { # Result of the k-anonymity computation. # K-anonymity result
"equivalenceClassHistogramBuckets": [ # Histogram of k-anonymity equivalence classes.
{ # Histogram of k-anonymity equivalence classes.
"bucketSize": "A String", # Total number of equivalence classes in this bucket.
"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.
"bucketValues": [ # Sample of equivalence classes in this bucket. The total number of classes returned per bucket is capped at 20.
{ # The set of columns' values that share the same ldiversity value
"equivalenceClassSize": "A String", # Size of the equivalence class, for example number of rows with the above set of values.
"quasiIdsValues": [ # Set of values defining the equivalence class. One value per quasi-identifier column in the original KAnonymity metric message. The order is always the same as the original request.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
},
],
"equivalenceClassSizeLowerBound": "A String", # Lower bound on the size of the equivalence classes in this bucket.
"equivalenceClassSizeUpperBound": "A String", # Upper bound on the size of the equivalence classes in this bucket.
},
],
},
"kMapEstimationResult": { # Result of the reidentifiability analysis. Note that these results are an estimation, not exact values. # K-map result
"kMapEstimationHistogram": [ # The intervals [min_anonymity, max_anonymity] do not overlap. If a value doesn't correspond to any such interval, the associated frequency is zero. For example, the following records: {min_anonymity: 1, max_anonymity: 1, frequency: 17} {min_anonymity: 2, max_anonymity: 3, frequency: 42} {min_anonymity: 5, max_anonymity: 10, frequency: 99} mean that there are no record with an estimated anonymity of 4, 5, or larger than 10.
{ # A KMapEstimationHistogramBucket message with the following values: min_anonymity: 3 max_anonymity: 5 frequency: 42 means that there are 42 records whose quasi-identifier values correspond to 3, 4 or 5 people in the overlying population. An important particular case is when min_anonymity = max_anonymity = 1: the frequency field then corresponds to the number of uniquely identifiable records.
"bucketSize": "A String", # Number of records within these anonymity bounds.
"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.
"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total number of classes returned per bucket is capped at 20.
{ # A tuple of values for the quasi-identifier columns.
"estimatedAnonymity": "A String", # The estimated anonymity for these quasi-identifier values.
"quasiIdsValues": [ # The quasi-identifier values.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
},
],
"maxAnonymity": "A String", # Always greater than or equal to min_anonymity.
"minAnonymity": "A String", # Always positive.
},
],
},
"lDiversityResult": { # Result of the l-diversity computation. # L-divesity result
"sensitiveValueFrequencyHistogramBuckets": [ # Histogram of l-diversity equivalence class sensitive value frequencies.
{ # Histogram of l-diversity equivalence class sensitive value frequencies.
"bucketSize": "A String", # Total number of equivalence classes in this bucket.
"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.
"bucketValues": [ # Sample of equivalence classes in this bucket. The total number of classes returned per bucket is capped at 20.
{ # The set of columns' values that share the same ldiversity value.
"equivalenceClassSize": "A String", # Size of the k-anonymity equivalence class.
"numDistinctSensitiveValues": "A String", # Number of distinct sensitive values in this equivalence class.
"quasiIdsValues": [ # Quasi-identifier values defining the k-anonymity equivalence class. The order is always the same as the original request.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
"topSensitiveValues": [ # Estimated frequencies of top sensitive values.
{ # A value of a field, including its frequency.
"count": "A String", # How many times the value is contained in the field.
"value": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # A value contained in the field in question.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
},
],
},
],
"sensitiveValueFrequencyLowerBound": "A String", # Lower bound on the sensitive value frequencies of the equivalence classes in this bucket.
"sensitiveValueFrequencyUpperBound": "A String", # Upper bound on the sensitive value frequencies of the equivalence classes in this bucket.
},
],
},
"numericalStatsResult": { # Result of the numerical stats computation. # Numerical stats result
"maxValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Maximum value appearing in the column.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"minValue": { # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data. # Minimum value appearing in the column.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
"quantileValues": [ # List of 99 values that partition the set of field values into 100 equal sized buckets.
{ # Set of primitive values supported by the system. Note that for the purposes of inspection or transformation, the number of bytes considered to comprise a 'Value' is based on its representation as a UTF-8 encoded string. For example, if 'integer_value' is set to 123456789, the number of bytes would be counted as 9, even though an int64 only holds up to 8 bytes of data.
"booleanValue": True or False, # boolean
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # date
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"dayOfWeekValue": "A String", # day of week
"floatValue": 3.14, # float
"integerValue": "A String", # integer
"stringValue": "A String", # string
"timeValue": { # Represents a time of day. The date and time zone are either not significant or are specified elsewhere. An API may choose to allow leap seconds. Related types are google.type.Date and `google.protobuf.Timestamp`. # time of day
"hours": 42, # Hours of a day in 24 hour format. Must be greater than or equal to 0 and typically must be less than or equal to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Minutes of an hour. Must be greater than or equal to 0 and less than or equal to 59.
"nanos": 42, # Fractions of seconds, in nanoseconds. Must be greater than or equal to 0 and less than or equal to 999,999,999.
"seconds": 42, # Seconds of a minute. Must be greater than or equal to 0 and typically must be less than or equal to 59. An API may allow the value 60 if it allows leap-seconds.
},
"timestampValue": "A String", # timestamp
},
],
},
"requestedOptions": { # Risk analysis options. # The configuration used for this job.
"jobConfig": { # Configuration for a risk analysis job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-risk-analysis to learn more. # The job config for the risk job.
"actions": [ # Actions to execute at the completion of the job. Are executed in the order provided.
{ # A task to execute on the completion of a job. See https://cloud.google.com/sensitive-data-protection/docs/concepts-actions to learn more.
"deidentify": { # Create a de-identified copy of the requested table or files. A TransformationDetail will be created for each transformation. If any rows in BigQuery are skipped during de-identification (transformation errors or row size exceeds BigQuery insert API limits) they are placed in the failure output table. If the original row exceeds the BigQuery insert API limit it will be truncated when written to the failure output table. The failure output table can be set in the action.deidentify.output.big_query_output.deidentified_failure_output_table field, if no table is set, a table will be automatically created in the same project and dataset as the original table. Compatible with: Inspect # Create a de-identified copy of the input data.
"cloudStorageOutput": "A String", # Required. User settable Cloud Storage bucket and folders to store de-identified files. This field must be set for Cloud Storage deidentification. The output Cloud Storage bucket must be different from the input bucket. De-identified files will overwrite files in the output path. Form of: gs://bucket/folder/ or gs://bucket
"fileTypesToTransform": [ # List of user-specified file type groups to transform. If specified, only the files with these file types will be transformed. If empty, all supported files will be transformed. Supported types may be automatically added over time. If a file type is set in this field that isn't supported by the Deidentify action then the job will fail and will not be successfully created/started. Currently the only file types supported are: IMAGES, TEXT_FILES, CSV, TSV.
"A String",
],
"transformationConfig": { # User specified templates and configs for how to deidentify structured, unstructures, and image files. User must provide either a unstructured deidentify template or at least one redact image config. # User specified deidentify templates and configs for structured, unstructured, and image files.
"deidentifyTemplate": "A String", # De-identify template. If this template is specified, it will serve as the default de-identify template. This template cannot contain `record_transformations` since it can be used for unstructured content such as free-form text files. If this template is not set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify unstructured content.
"imageRedactTemplate": "A String", # Image redact template. If this template is specified, it will serve as the de-identify template for images. If this template is not set, all findings in the image will be redacted with a black box.
"structuredDeidentifyTemplate": "A String", # Structured de-identify template. If this template is specified, it will serve as the de-identify template for structured content such as delimited files and tables. If this template is not set but the `deidentify_template` is set, then `deidentify_template` will also apply to the structured content. If neither template is set, a default `ReplaceWithInfoTypeConfig` will be used to de-identify structured content.
},
"transformationDetailsStorageConfig": { # Config for storing transformation details. # Config for storing transformation details. This is separate from the de-identified content, and contains metadata about the successful transformations and/or failures that occurred while de-identifying. This needs to be set in order for users to access information about the status of each transformation (see TransformationDetails message for more information about what is noted).
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # The BigQuery table in which to store the output. This may be an existing table or in a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_transformation_details_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"jobNotificationEmails": { # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts). # Sends an email when the job completes. The email goes to IAM project owners and technical [Essential Contacts](https://cloud.google.com/resource-manager/docs/managing-notification-contacts).
},
"pubSub": { # Publish a message into a given Pub/Sub topic when DlpJob has completed. The message contains a single field, `DlpJobName`, which is equal to the finished job's [`DlpJob.name`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/projects.dlpJobs#DlpJob). Compatible with: Inspect, Risk # Publish a notification to a Pub/Sub topic.
"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given publishing access rights to the DLP API service account executing the long running DlpJob sending the notifications. Format is projects/{project}/topics/{topic}.
},
"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Data Catalog. In Data Catalog, tag templates are applied to the resource that Cloud DLP scanned. Data Catalog tag templates are stored in the same project and region where the BigQuery table exists. For Cloud DLP to create and apply the tag template, the Cloud DLP service agent must have the `roles/datacatalog.tagTemplateOwner` permission on the project. The tag template contains fields summarizing the results of the DlpJob. Any field values previously written by another DlpJob are deleted. InfoType naming patterns are strictly enforced when using this feature. Findings are persisted in Data Catalog storage and are governed by service-specific policies for Data Catalog. For more information, see [Service Specific Terms](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. This action is allowed only if all resources being scanned are BigQuery tables. Compatible with: Inspect # Publish findings to Cloud Datahub.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to [Security Command Center](https://cloud.google.com/security-command-center). This action is available for only projects that belong to an organization. This action publishes the count of finding instances and their infoTypes. The summary of findings are persisted in Security Command Center and are governed by [service-specific policies for Security Command Center](https://cloud.google.com/terms/service-terms). Only a single instance of this action can be specified. Compatible with: Inspect # Publish summary to Cloud Security Command Center (Alpha).
},
"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This will publish a metric to stack driver on each infotype requested and how many findings were found for it. CustomDetectors will be bucketed as 'Custom' under the Stackdriver label 'info_type'. # Enable Stackdriver metric dlp.googleapis.com/finding_count.
},
"saveFindings": { # If set, the detailed findings will be persisted to the specified OutputStorageConfig. Only a single instance of this action can be specified. Compatible with: Inspect, Risk # Save resulting findings in a provided location.
"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only used for Inspect and must be unspecified for Risk jobs. Columns are derived from the `Finding` object. If appending to an existing table, any columns from the predefined schema that are missing will be added. No columns in the existing table will be deleted. If unspecified, then all available columns will be used for a new table or an (existing) table with no schema, and no changes will be made to an existing table that has a schema. Only for use with external storage.
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Store findings in an existing table or a new table in an existing dataset. If table_id is not set a new one will be generated for you with the following format: dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific time zone will be used for generating the date details. For Inspect, each column in an existing output table must have the same name, type, and mode of a field in the `Finding` object. For Risk, an existing output table should be the output of a previous Risk analysis job run on the same source table, with the same privacy metric and quasi-identifiers. Risk jobs that analyze the same table but compute a different privacy metric, or use different sets of quasi-identifiers, cannot store their results in the same table.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
},
],
"privacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.
"categoricalStatsConfig": { # Compute numerical stats over an individual column, including number of distinct values and value count distribution. # Categorical stats
"field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are supported except for arrays and structs. However, it may be more informative to use NumericalStats when the field type is supported, depending on the data.
"name": "A String", # Name describing the field.
},
},
"deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to figure out that one given individual appears in a de-identified dataset. Similarly to the k-map metric, we cannot compute δ-presence exactly without knowing the attack dataset, so we use a statistical model instead. # delta-presence
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers field must appear in exactly one field of one auxiliary table.
{ # An auxiliary table containing statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity
"entityId": { # An entity in a dataset is a field or set of fields that correspond to a single person. For example, in medical records the `EntityId` might be a patient identifier, or for financial records it might be an account identifier. This message is used when generalizations or analysis must take into account that multiple rows correspond to the same entity. # Message indicating that multiple rows might be associated to a single individual. If the same entity_id is associated to multiple quasi-identifier tuples over distinct rows, we consider the entire collection of tuples as the composite quasi-identifier. This collection is a multiset: the order in which the different tuples appear in the dataset is ignored, but their frequency is taken into account. Important note: a maximum of 1000 rows can be associated to a single entity ID. If more rows are associated with the same entity ID, some might be ignored.
"field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier.
"name": "A String", # Name describing the field.
},
},
"quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are specified, they are considered a single composite key. Structs and repeated data types are not supported; however, nested fields are supported so long as they are not structs themselves or nested within a repeated field.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
"kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what is called "journalist risk" in the literature, except the attack dataset is statistically modeled instead of being perfectly known. This can be done using publicly available data (like the US Census), or using a custom statistical model (indicated as one or several BigQuery tables), or by extrapolating from the distribution of values in the input dataset. # k-map
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers column must appear in exactly one column of one auxiliary table.
{ # An auxiliary table contains statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A auxiliary field.
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity
"quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are defined for the l-diversity computation. When multiple fields are specified, they are considered a single composite key.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value.
"name": "A String", # Name describing the field.
},
},
"numericalStatsConfig": { # Compute numerical stats over an individual column, including min, max, and quantiles. # Numerical stats
"field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are integer, float, date, datetime, timestamp, time.
"name": "A String", # Name describing the field.
},
},
},
"sourceTable": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Input dataset to compute metrics over.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
},
"requestedPrivacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.
"categoricalStatsConfig": { # Compute numerical stats over an individual column, including number of distinct values and value count distribution. # Categorical stats
"field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are supported except for arrays and structs. However, it may be more informative to use NumericalStats when the field type is supported, depending on the data.
"name": "A String", # Name describing the field.
},
},
"deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to figure out that one given individual appears in a de-identified dataset. Similarly to the k-map metric, we cannot compute δ-presence exactly without knowing the attack dataset, so we use a statistical model instead. # delta-presence
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers field must appear in exactly one field of one auxiliary table.
{ # An auxiliary table containing statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity
"entityId": { # An entity in a dataset is a field or set of fields that correspond to a single person. For example, in medical records the `EntityId` might be a patient identifier, or for financial records it might be an account identifier. This message is used when generalizations or analysis must take into account that multiple rows correspond to the same entity. # Message indicating that multiple rows might be associated to a single individual. If the same entity_id is associated to multiple quasi-identifier tuples over distinct rows, we consider the entire collection of tuples as the composite quasi-identifier. This collection is a multiset: the order in which the different tuples appear in the dataset is ignored, but their frequency is taken into account. Important note: a maximum of 1000 rows can be associated to a single entity ID. If more rows are associated with the same entity ID, some might be ignored.
"field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier.
"name": "A String", # Name describing the field.
},
},
"quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are specified, they are considered a single composite key. Structs and repeated data types are not supported; however, nested fields are supported so long as they are not structs themselves or nested within a repeated field.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
},
"kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what is called "journalist risk" in the literature, except the attack dataset is statistically modeled instead of being perfectly known. This can be done using publicly available data (like the US Census), or using a custom statistical model (indicated as one or several BigQuery tables), or by extrapolating from the distribution of values in the input dataset. # k-map
"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag used to tag a quasi-identifiers column must appear in exactly one column of one auxiliary table.
{ # An auxiliary table contains statistical information on the relative frequency of different quasi-identifiers values. It has one or several quasi-identifiers columns, and one column that indicates the relative frequency of each quasi-identifier tuple. If a tuple is present in the data but not in the auxiliary table, the corresponding relative frequency is assumed to be zero (and thus, the tuple is highly reidentifiable).
"quasiIds": [ # Required. Quasi-identifier columns.
{ # A quasi-identifier column has a custom_tag, used to know which column in the data corresponds to which column in the statistical model.
"customTag": "A String", # A auxiliary field.
"field": { # General identifier of a data field in a storage service. # Identifies the column.
"name": "A String", # Name describing the field.
},
},
],
"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number between 0 and 1 (inclusive). Null values are assumed to be zero.
"name": "A String", # Name describing the field.
},
"table": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Required. Auxiliary table location.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
],
"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the same tag.
{ # A column with a semantic tag attached.
"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must indicate an auxiliary table that contains statistical information on the possible values of this column (below).
"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
"name": "A String", # Name describing the field.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } # If no semantic tag is indicated, we infer the statistical model from the distribution of values in the input data
},
"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public dataset as a statistical model of population, if available. We currently support US ZIP codes, region codes, ages and genders. To programmatically obtain the list of supported InfoTypes, use ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
"name": "A String", # Name of the information type. Either a name of your choosing when creating a CustomInfoType, or one of the names listed at https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference when specifying a built-in type. When sending Cloud DLP results to Data Catalog, infoType names should conform to the pattern `[A-Za-z0-9$_-]{1,64}`.
"sensitivityScore": { # Score is calculated from of all elements in the data profile. A higher level means the data is more sensitive. # Optional custom sensitivity for this InfoType. This only applies to data profiling.
"score": "A String", # The sensitivity score applied to the resource.
},
"version": "A String", # Optional version name for this InfoType.
},
},
],
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. Set if no column is tagged with a region-specific InfoType (like US_ZIP_5) or a region code.
},
"lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity
"quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are defined for the l-diversity computation. When multiple fields are specified, they are considered a single composite key.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value.
"name": "A String", # Name describing the field.
},
},
"numericalStatsConfig": { # Compute numerical stats over an individual column, including min, max, and quantiles. # Numerical stats
"field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are integer, float, date, datetime, timestamp, time.
"name": "A String", # Name describing the field.
},
},
},
"requestedSourceTable": { # Message defining the location of a BigQuery table. A table is uniquely identified by its project_id, dataset_id, and table_name. Within a query a table is often referenced with a string in the format of: `:.` or `..`. # Input dataset to compute metrics over.
"datasetId": "A String", # Dataset ID of the table.
"projectId": "A String", # The Google Cloud project ID of the project containing the table. If omitted, project ID is inferred from the API call.
"tableId": "A String", # Name of the table.
},
},
"startTime": "A String", # Time when the job started.
"state": "A String", # State of a job.
"type": "A String", # The type of job.
},
],
"nextPageToken": "A String", # The standard List next-page token.
}

list_next()

Retrieves the next page of results.

        Args:
          previous_request: The request for the previous page. (required)
          previous_response: The response from the request for the previous page. (required)

        Returns:
          A request object that you can call 'execute()' on to request the next
          page. Returns None if there are no more items in the collection.

Sensitive Data Protection (DLP) . projects . locations . dlpJobs

Instance Methods

Method Details