cancel(name, body=None, x__xgafv=None)
Starts asynchronous cancellation on a long-running DlpJob. The server
create(parent, body, x__xgafv=None)
Creates a new job to inspect storage or calculate risk metrics.
Deletes a long-running DlpJob. This method indicates that the client is
Gets the latest state of a long-running DlpJob.
list(parent, orderBy=None, type=None, pageSize=None, pageToken=None, x__xgafv=None, filter=None)
Lists DlpJobs that match the specified filter in the request.
list_next(previous_request, previous_response)
Retrieves the next page of results.
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/dlp/docs/inspecting-storage and
https://cloud.google.com/dlp/docs/compute-risk-analysis to learn more.
Args:
name: string, 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);
# }
#
# The JSON representation for `Empty` is empty JSON object `{}`.
}
create(parent, body, x__xgafv=None)
Creates a new job to inspect storage or calculate risk metrics.
See https://cloud.google.com/dlp/docs/inspecting-storage and
https://cloud.google.com/dlp/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, The parent resource name, for example projects/my-project-id. (required)
body: object, The request body. (required)
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.
"riskJob": { # Configuration for a risk analysis job. See
# https://cloud.google.com/dlp/docs/concepts-risk-analysis to learn more.
"privacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.
"numericalStatsConfig": { # Compute numerical stats over an individual column, including
# min, max, and quantiles.
"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.
},
},
"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.
# A column with a semantic tag attached.
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.
# Required if no column is tagged with a region-specific InfoType (like
# US_ZIP_5) or a region code.
"quasiIds": [ # Fields considered to be quasi-identifiers. No two columns can have the
# same tag. [required]
{
"field": { # General identifier of a data field in a storage service. # Identifies the column. [required]
"name": "A String", # Name describing the field.
},
"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).
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated # If no semantic tag is indicated, we infer the statistical model from
# the distribution of values in the input data
# 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);
# }
#
# The JSON representation for `Empty` is empty JSON object `{}`.
},
},
],
"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).
"relativeFrequency": { # General identifier of a data field in a storage service. # The relative frequency column must contain a floating-point number
# between 0 and 1 (inclusive). Null values are assumed to be zero.
# [required]
"name": "A String", # Name describing the field.
},
"quasiIds": [ # Quasi-identifier columns. [required]
{ # A quasi-identifier column has a custom_tag, used to know which column
# in the data corresponds to which column in the statistical model.
"field": { # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
"customTag": "A String",
},
],
"table": { # Message defining the location of a BigQuery table. A table is uniquely # Auxiliary table location. [required]
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
},
],
},
"lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk.
"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.
},
"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.
},
],
},
"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.
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.
# Required if no column is tagged with a region-specific InfoType (like
# US_ZIP_5) or a region code.
"quasiIds": [ # Fields considered to be quasi-identifiers. No two fields can have the
# same tag. [required]
{ # A column with a semantic tag attached.
"field": { # General identifier of a data field in a storage service. # Identifies the column. [required]
"name": "A String", # Name describing the field.
},
"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).
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated # If no semantic tag is indicated, we infer the statistical model from
# the distribution of values in the input data
# 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);
# }
#
# The JSON representation for `Empty` is empty JSON object `{}`.
},
},
],
"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).
"relativeFrequency": { # General identifier of a data field in a storage service. # The relative frequency column must contain a floating-point number
# between 0 and 1 (inclusive). Null values are assumed to be zero.
# [required]
"name": "A String", # Name describing the field.
},
"quasiIds": [ # Quasi-identifier columns. [required]
{ # A quasi-identifier column has a custom_tag, used to know which column
# in the data corresponds to which column in the statistical model.
"field": { # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
"customTag": "A String",
},
],
"table": { # Message defining the location of a BigQuery table. A table is uniquely # Auxiliary table location. [required]
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
},
],
},
"categoricalStatsConfig": { # Compute numerical stats over an individual column, including
# number of distinct values and value count distribution.
"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.
},
},
"kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk.
"entityId": { # An entity in a dataset is a field or set of fields that correspond to a # Optional 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.
# 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.
"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.
},
],
},
},
"sourceTable": { # Message defining the location of a BigQuery table. A table is uniquely # Input dataset to compute metrics over.
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the 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/dlp/docs/concepts-actions to learn more.
"saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location.
# OutputStorageConfig. Only a single instance of this action can be
# specified.
# Compatible with: Inspect, Risk
"outputConfig": { # Cloud repository for storing output.
"table": { # Message defining the location of a BigQuery table. A table is uniquely # 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 timezone 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.
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
"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.
},
},
"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification to project owners and editors on job's
# completion/failure.
# completion/failure.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).
# Command Center (CSCC Alpha).
# This action is only available for projects which are parts of
# an organization and whitelisted for the alpha Cloud Security Command
# Center.
# The action will publish count of finding instances and their info types.
# The summary of findings will be persisted in CSCC and are governed by CSCC
# service-specific policy, see https://cloud.google.com/terms/service-terms
# Only a single instance of this action can be specified.
# Compatible with: Inspect
},
"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.
# message contains a single field, `DlpJobName`, which is equal to the
# finished job's
# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).
# Compatible with: Inspect, Risk
"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}.
},
},
],
},
"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.
"inspectJob": {
"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options specification.
"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 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.
"projectId": "A String", # The ID of the project to which the entities belong.
"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
},
"kind": { # A representation of a Datastore kind. # The kind to process.
"name": "A String", # The name of the kind.
},
},
"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options specification.
"excludedFields": [ # References to fields excluded from scanning. This allows you to skip
# inspection of entire columns which you know have no findings.
{ # 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.
"sampleMethod": "A String",
"identifyingFields": [ # References to fields uniquely identifying rows within the table.
# Nested fields in the format, like `person.birthdate.year`, are allowed.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"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.
"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
},
"timespanConfig": { # Configuration of the timespan of the items to include in scanning.
# Currently only supported when inspecting Google Cloud Storage and BigQuery.
"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 or BigQuery.
# If not specified for BigQuery, table last modification timestamp
# is checked against given time span.
# The valid data types of the timestamp field are:
# for BigQuery - timestamp, date, datetime;
# for Datastore - timestamp.
# Datastore entity will be scanned if the timestamp property does not exist
# or its value is empty or invalid.
"name": "A String", # Name describing the field.
},
"endTime": "A String", # Exclude files or rows newer than this value.
# If set to zero, no upper time limit is applied.
"startTime": "A String", # Exclude files or rows older than this value.
"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.
},
"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options specification.
# bucket.
"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.
"sampleMethod": "A String",
"fileSet": { # Set of files to scan. # The set of one or more files to scan.
"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.
"regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular # The regex-filtered set of files to scan. Exactly one of `url` or
# `regex_file_set` must be set.
# 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 `/`
"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",
],
"bucketName": "A String", # The name of a Cloud Storage bucket. Required.
"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",
],
},
},
"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.
"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.
"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.
"A String",
],
},
},
"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.
# When used with redactContent only info_types and min_likelihood are currently
# used.
"excludeInfoTypes": True or False, # When true, excludes type information of the findings.
"limits": {
"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.
# When set within `InspectContentRequest`, the maximum returned is 2000
# regardless if this is set higher.
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.
# When set within `InspectDataSourceRequest`,
# the maximum returned is 2000 regardless if this is set higher.
# When set within `InspectContentRequest`, this field is ignored.
},
"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is
# POSSIBLE.
# See https://cloud.google.com/dlp/docs/likelihood to learn more.
"customInfoTypes": [ # CustomInfoTypes provided by the user. See
# https://cloud.google.com/dlp/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.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"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.
"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,
],
},
"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that
# support reversing.
# such as
# [`CryptoReplaceFfxFpeConfig`](/dlp/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`.
},
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.
# 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/dlp/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.
"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",
],
},
"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
},
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in
# `InspectDataSource`. Not currently supported in `InspectContent`.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example
# `organizations/433245324/storedInfoTypes/432452342` or
# `projects/project-id/storedInfoTypes/432452342`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for
# inspection was created. Output-only field, populated by the system.
},
"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 # Hotword-based detection rule.
# proximity of hotwords.
"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
# The total length of the window cannot exceed 1000 characters. Note that
# the finding itself will be included in the window, so that hotwords may
# be used to match substrings of the finding itself. For example, the
# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
# adjusted upwards if the area code is known to be the local area code of
# a company office using the hotword regex "\(xxx\)", where "xxx"
# is the area code in question.
# rule.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider.
},
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"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.
"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,
],
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
# part of a detection rule.
"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`.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
},
},
},
],
"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.
"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.
},
],
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is
# included in the response; see Finding.quote.
"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.
"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`.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
# proximity of hotwords.
"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
# The total length of the window cannot exceed 1000 characters. Note that
# the finding itself will be included in the window, so that hotwords may
# be used to match substrings of the finding itself. For example, the
# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
# adjusted upwards if the area code is known to be the local area code of
# a company office using the hotword regex "\(xxx\)", where "xxx"
# is the area code in question.
# rule.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider.
},
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"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.
"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,
],
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
# part of a detection rule.
"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`.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
},
},
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.
# `InspectionRuleSet` are removed from results.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"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.
"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,
],
},
"excludeInfoTypes": { # List of exclude 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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.
# 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/dlp/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.
"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",
],
},
"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
},
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
},
},
],
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
],
"contentOptions": [ # List of options defining data content to scan.
# If empty, text, images, and other content will be included.
"A String",
],
"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/dlp/docs/infotypes-reference.
#
# When no InfoTypes or CustomInfoTypes are specified in a request, the
# system may automatically choose what detectors to run. By default this may
# be all types, but may change over time as detectors are updated.
#
# The special InfoType name "ALL_BASIC" can be used to trigger all detectors,
# but may change over time as new InfoTypes are added. If you need precise
# control and predictability as to what detectors are run you should specify
# specific InfoTypes listed in the reference.
{ # 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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
"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.
"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/dlp/docs/concepts-actions to learn more.
"saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location.
# OutputStorageConfig. Only a single instance of this action can be
# specified.
# Compatible with: Inspect, Risk
"outputConfig": { # Cloud repository for storing output.
"table": { # Message defining the location of a BigQuery table. A table is uniquely # 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 timezone 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.
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
"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.
},
},
"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification to project owners and editors on job's
# completion/failure.
# completion/failure.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).
# Command Center (CSCC Alpha).
# This action is only available for projects which are parts of
# an organization and whitelisted for the alpha Cloud Security Command
# Center.
# The action will publish count of finding instances and their info types.
# The summary of findings will be persisted in CSCC and are governed by CSCC
# service-specific policy, see https://cloud.google.com/terms/service-terms
# Only a single instance of this action can be specified.
# Compatible with: Inspect
},
"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.
# message contains a single field, `DlpJobName`, which is equal to the
# finished job's
# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).
# Compatible with: Inspect, Risk
"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}.
},
},
],
},
}
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.
"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.
# Output only field.
"timestamps": [ # The times the error occurred.
"A String",
],
"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).
"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.
"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.
},
],
},
},
],
"name": "A String", # The server-assigned name.
"inspectDetails": { # The results of an inspect DataSource job. # Results from inspecting a data source.
"requestedOptions": { # The configuration used for this job.
"snapshotInspectTemplate": { # The inspectTemplate contains a configuration (set of types of sensitive data # If run with an InspectTemplate, a snapshot of its state at the time of
# this run.
# to be detected) to be used anywhere you otherwise would normally specify
# InspectConfig. See https://cloud.google.com/dlp/docs/concepts-templates
# to learn more.
"updateTime": "A String", # The last update timestamp of a inspectTemplate, output only field.
"displayName": "A String", # Display name (max 256 chars).
"description": "A String", # Short description (max 256 chars).
"inspectConfig": { # Configuration description of the scanning process. # The core content of the template. Configuration of the scanning process.
# When used with redactContent only info_types and min_likelihood are currently
# used.
"excludeInfoTypes": True or False, # When true, excludes type information of the findings.
"limits": {
"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.
# When set within `InspectContentRequest`, the maximum returned is 2000
# regardless if this is set higher.
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.
# When set within `InspectDataSourceRequest`,
# the maximum returned is 2000 regardless if this is set higher.
# When set within `InspectContentRequest`, this field is ignored.
},
"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is
# POSSIBLE.
# See https://cloud.google.com/dlp/docs/likelihood to learn more.
"customInfoTypes": [ # CustomInfoTypes provided by the user. See
# https://cloud.google.com/dlp/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.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"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.
"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,
],
},
"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that
# support reversing.
# such as
# [`CryptoReplaceFfxFpeConfig`](/dlp/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`.
},
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.
# 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/dlp/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.
"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",
],
},
"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
},
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in
# `InspectDataSource`. Not currently supported in `InspectContent`.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example
# `organizations/433245324/storedInfoTypes/432452342` or
# `projects/project-id/storedInfoTypes/432452342`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for
# inspection was created. Output-only field, populated by the system.
},
"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 # Hotword-based detection rule.
# proximity of hotwords.
"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
# The total length of the window cannot exceed 1000 characters. Note that
# the finding itself will be included in the window, so that hotwords may
# be used to match substrings of the finding itself. For example, the
# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
# adjusted upwards if the area code is known to be the local area code of
# a company office using the hotword regex "\(xxx\)", where "xxx"
# is the area code in question.
# rule.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider.
},
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"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.
"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,
],
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
# part of a detection rule.
"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`.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
},
},
},
],
"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.
"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.
},
],
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is
# included in the response; see Finding.quote.
"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.
"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`.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
# proximity of hotwords.
"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
# The total length of the window cannot exceed 1000 characters. Note that
# the finding itself will be included in the window, so that hotwords may
# be used to match substrings of the finding itself. For example, the
# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
# adjusted upwards if the area code is known to be the local area code of
# a company office using the hotword regex "\(xxx\)", where "xxx"
# is the area code in question.
# rule.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider.
},
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"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.
"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,
],
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
# part of a detection rule.
"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`.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
},
},
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.
# `InspectionRuleSet` are removed from results.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"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.
"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,
],
},
"excludeInfoTypes": { # List of exclude 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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.
# 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/dlp/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.
"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",
],
},
"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
},
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
},
},
],
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
],
"contentOptions": [ # List of options defining data content to scan.
# If empty, text, images, and other content will be included.
"A String",
],
"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/dlp/docs/infotypes-reference.
#
# When no InfoTypes or CustomInfoTypes are specified in a request, the
# system may automatically choose what detectors to run. By default this may
# be all types, but may change over time as detectors are updated.
#
# The special InfoType name "ALL_BASIC" can be used to trigger all detectors,
# but may change over time as new InfoTypes are added. If you need precise
# control and predictability as to what detectors are run you should specify
# specific InfoTypes listed in the reference.
{ # 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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
"createTime": "A String", # The creation timestamp of a inspectTemplate, output only field.
"name": "A String", # The template name. Output only.
#
# The template will have one of the following formats:
# `projects/PROJECT_ID/inspectTemplates/TEMPLATE_ID` OR
# `organizations/ORGANIZATION_ID/inspectTemplates/TEMPLATE_ID`
},
"jobConfig": {
"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options specification.
"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 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.
"projectId": "A String", # The ID of the project to which the entities belong.
"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
},
"kind": { # A representation of a Datastore kind. # The kind to process.
"name": "A String", # The name of the kind.
},
},
"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options specification.
"excludedFields": [ # References to fields excluded from scanning. This allows you to skip
# inspection of entire columns which you know have no findings.
{ # 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.
"sampleMethod": "A String",
"identifyingFields": [ # References to fields uniquely identifying rows within the table.
# Nested fields in the format, like `person.birthdate.year`, are allowed.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"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.
"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
},
"timespanConfig": { # Configuration of the timespan of the items to include in scanning.
# Currently only supported when inspecting Google Cloud Storage and BigQuery.
"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 or BigQuery.
# If not specified for BigQuery, table last modification timestamp
# is checked against given time span.
# The valid data types of the timestamp field are:
# for BigQuery - timestamp, date, datetime;
# for Datastore - timestamp.
# Datastore entity will be scanned if the timestamp property does not exist
# or its value is empty or invalid.
"name": "A String", # Name describing the field.
},
"endTime": "A String", # Exclude files or rows newer than this value.
# If set to zero, no upper time limit is applied.
"startTime": "A String", # Exclude files or rows older than this value.
"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.
},
"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options specification.
# bucket.
"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.
"sampleMethod": "A String",
"fileSet": { # Set of files to scan. # The set of one or more files to scan.
"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.
"regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular # The regex-filtered set of files to scan. Exactly one of `url` or
# `regex_file_set` must be set.
# 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 `/`
"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",
],
"bucketName": "A String", # The name of a Cloud Storage bucket. Required.
"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",
],
},
},
"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.
"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.
"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.
"A String",
],
},
},
"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.
# When used with redactContent only info_types and min_likelihood are currently
# used.
"excludeInfoTypes": True or False, # When true, excludes type information of the findings.
"limits": {
"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.
# When set within `InspectContentRequest`, the maximum returned is 2000
# regardless if this is set higher.
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.
# When set within `InspectDataSourceRequest`,
# the maximum returned is 2000 regardless if this is set higher.
# When set within `InspectContentRequest`, this field is ignored.
},
"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is
# POSSIBLE.
# See https://cloud.google.com/dlp/docs/likelihood to learn more.
"customInfoTypes": [ # CustomInfoTypes provided by the user. See
# https://cloud.google.com/dlp/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.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"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.
"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,
],
},
"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that
# support reversing.
# such as
# [`CryptoReplaceFfxFpeConfig`](/dlp/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`.
},
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.
# 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/dlp/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.
"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",
],
},
"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
},
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in
# `InspectDataSource`. Not currently supported in `InspectContent`.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example
# `organizations/433245324/storedInfoTypes/432452342` or
# `projects/project-id/storedInfoTypes/432452342`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for
# inspection was created. Output-only field, populated by the system.
},
"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 # Hotword-based detection rule.
# proximity of hotwords.
"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
# The total length of the window cannot exceed 1000 characters. Note that
# the finding itself will be included in the window, so that hotwords may
# be used to match substrings of the finding itself. For example, the
# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
# adjusted upwards if the area code is known to be the local area code of
# a company office using the hotword regex "\(xxx\)", where "xxx"
# is the area code in question.
# rule.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider.
},
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"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.
"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,
],
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
# part of a detection rule.
"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`.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
},
},
},
],
"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.
"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.
},
],
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is
# included in the response; see Finding.quote.
"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.
"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`.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
# proximity of hotwords.
"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
# The total length of the window cannot exceed 1000 characters. Note that
# the finding itself will be included in the window, so that hotwords may
# be used to match substrings of the finding itself. For example, the
# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
# adjusted upwards if the area code is known to be the local area code of
# a company office using the hotword regex "\(xxx\)", where "xxx"
# is the area code in question.
# rule.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider.
},
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"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.
"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,
],
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
# part of a detection rule.
"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`.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
},
},
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.
# `InspectionRuleSet` are removed from results.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"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.
"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,
],
},
"excludeInfoTypes": { # List of exclude 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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.
# 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/dlp/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.
"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",
],
},
"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
},
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
},
},
],
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
],
"contentOptions": [ # List of options defining data content to scan.
# If empty, text, images, and other content will be included.
"A String",
],
"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/dlp/docs/infotypes-reference.
#
# When no InfoTypes or CustomInfoTypes are specified in a request, the
# system may automatically choose what detectors to run. By default this may
# be all types, but may change over time as detectors are updated.
#
# The special InfoType name "ALL_BASIC" can be used to trigger all detectors,
# but may change over time as new InfoTypes are added. If you need precise
# control and predictability as to what detectors are run you should specify
# specific InfoTypes listed in the reference.
{ # 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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
"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.
"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/dlp/docs/concepts-actions to learn more.
"saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location.
# OutputStorageConfig. Only a single instance of this action can be
# specified.
# Compatible with: Inspect, Risk
"outputConfig": { # Cloud repository for storing output.
"table": { # Message defining the location of a BigQuery table. A table is uniquely # 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 timezone 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.
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
"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.
},
},
"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification to project owners and editors on job's
# completion/failure.
# completion/failure.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).
# Command Center (CSCC Alpha).
# This action is only available for projects which are parts of
# an organization and whitelisted for the alpha Cloud Security Command
# Center.
# The action will publish count of finding instances and their info types.
# The summary of findings will be persisted in CSCC and are governed by CSCC
# service-specific policy, see https://cloud.google.com/terms/service-terms
# Only a single instance of this action can be specified.
# Compatible with: Inspect
},
"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.
# message contains a single field, `DlpJobName`, which is equal to the
# finished job's
# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).
# Compatible with: Inspect, Risk
"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}.
},
},
],
},
},
"result": { # All result fields mentioned below are updated while the job is processing. # A summary of the outcome of this inspect 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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
},
],
"totalEstimatedBytes": "A String", # Estimate of the number of bytes to process.
"processedBytes": "A String", # Total size in bytes that were processed.
},
},
"riskDetails": { # Result of a risk analysis operation request. # Results from analyzing risk of a data source.
"numericalStatsResult": { # Result of the numerical stats computation.
"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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
],
"maxValue": { # Set of primitive values supported by the system. # Maximum value appearing in the column.
# 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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
"minValue": { # Set of primitive values supported by the system. # Minimum value appearing in the column.
# 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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
},
"kMapEstimationResult": { # Result of the reidentifiability analysis. Note that these results are an
# estimation, not exact values.
"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.
"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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
],
},
],
"minAnonymity": "A String", # Always positive.
"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.
"maxAnonymity": "A String", # Always greater than or equal to min_anonymity.
"bucketSize": "A String", # Number of records within these anonymity bounds.
},
],
},
"kAnonymityResult": { # Result of the k-anonymity computation.
"equivalenceClassHistogramBuckets": [ # Histogram of k-anonymity equivalence classes.
{
"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
"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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
],
"equivalenceClassSize": "A String", # Size of the equivalence class, for example number of rows with the
# above set of values.
},
],
"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.
"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.
"bucketSize": "A String", # Total number of equivalence classes in this bucket.
},
],
},
"lDiversityResult": { # Result of the l-diversity computation.
"sensitiveValueFrequencyHistogramBuckets": [ # Histogram of l-diversity equivalence class sensitive value frequencies.
{
"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.
"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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
],
"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. # A value contained in the field in question.
# 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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
},
],
"equivalenceClassSize": "A String", # Size of the k-anonymity equivalence class.
},
],
"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.
"bucketSize": "A String", # Total number of equivalence classes in this bucket.
"sensitiveValueFrequencyUpperBound": "A String", # Upper bound on the sensitive value frequencies of the equivalence
# classes in this bucket.
"sensitiveValueFrequencyLowerBound": "A String", # Lower bound on the sensitive value frequencies of the equivalence
# classes in this bucket.
},
],
},
"requestedPrivacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.
"numericalStatsConfig": { # Compute numerical stats over an individual column, including
# min, max, and quantiles.
"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.
},
},
"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.
# A column with a semantic tag attached.
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.
# Required if no column is tagged with a region-specific InfoType (like
# US_ZIP_5) or a region code.
"quasiIds": [ # Fields considered to be quasi-identifiers. No two columns can have the
# same tag. [required]
{
"field": { # General identifier of a data field in a storage service. # Identifies the column. [required]
"name": "A String", # Name describing the field.
},
"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).
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated # If no semantic tag is indicated, we infer the statistical model from
# the distribution of values in the input data
# 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);
# }
#
# The JSON representation for `Empty` is empty JSON object `{}`.
},
},
],
"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).
"relativeFrequency": { # General identifier of a data field in a storage service. # The relative frequency column must contain a floating-point number
# between 0 and 1 (inclusive). Null values are assumed to be zero.
# [required]
"name": "A String", # Name describing the field.
},
"quasiIds": [ # Quasi-identifier columns. [required]
{ # A quasi-identifier column has a custom_tag, used to know which column
# in the data corresponds to which column in the statistical model.
"field": { # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
"customTag": "A String",
},
],
"table": { # Message defining the location of a BigQuery table. A table is uniquely # Auxiliary table location. [required]
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
},
],
},
"lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk.
"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.
},
"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.
},
],
},
"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.
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.
# Required if no column is tagged with a region-specific InfoType (like
# US_ZIP_5) or a region code.
"quasiIds": [ # Fields considered to be quasi-identifiers. No two fields can have the
# same tag. [required]
{ # A column with a semantic tag attached.
"field": { # General identifier of a data field in a storage service. # Identifies the column. [required]
"name": "A String", # Name describing the field.
},
"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).
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated # If no semantic tag is indicated, we infer the statistical model from
# the distribution of values in the input data
# 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);
# }
#
# The JSON representation for `Empty` is empty JSON object `{}`.
},
},
],
"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).
"relativeFrequency": { # General identifier of a data field in a storage service. # The relative frequency column must contain a floating-point number
# between 0 and 1 (inclusive). Null values are assumed to be zero.
# [required]
"name": "A String", # Name describing the field.
},
"quasiIds": [ # Quasi-identifier columns. [required]
{ # A quasi-identifier column has a custom_tag, used to know which column
# in the data corresponds to which column in the statistical model.
"field": { # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
"customTag": "A String",
},
],
"table": { # Message defining the location of a BigQuery table. A table is uniquely # Auxiliary table location. [required]
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
},
],
},
"categoricalStatsConfig": { # Compute numerical stats over an individual column, including
# number of distinct values and value count distribution.
"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.
},
},
"kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk.
"entityId": { # An entity in a dataset is a field or set of fields that correspond to a # Optional 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.
# 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.
"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.
},
],
},
},
"categoricalStatsResult": { # Result of the categorical stats computation.
"valueFrequencyHistogramBuckets": [ # Histogram of value frequencies in the column.
{
"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. # A value contained in the field in question.
# 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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
},
],
"bucketValueCount": "A String", # Total number of distinct values in this bucket.
"valueFrequencyUpperBound": "A String", # Upper bound on the value frequency of the values in this bucket.
"valueFrequencyLowerBound": "A String", # Lower bound on the value frequency of the values in this bucket.
"bucketSize": "A String", # Total number of values in this bucket.
},
],
},
"deltaPresenceEstimationResult": { # Result of the δ-presence computation. Note that these results are an
# estimation, not exact values.
"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.
"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.
"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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
],
"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.
},
],
"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.
"bucketSize": "A String", # Number of records within these probability bounds.
"maxProbability": 3.14, # Always greater than or equal to min_probability.
"minProbability": 3.14, # Between 0 and 1.
},
],
},
"requestedSourceTable": { # Message defining the location of a BigQuery table. A table is uniquely # Input dataset to compute metrics over.
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
},
"state": "A String", # State of a job.
"jobTriggerName": "A String", # If created by a job trigger, the resource name of the trigger that
# instantiated the job.
"startTime": "A String", # Time when the job started.
"endTime": "A String", # Time when the job finished.
"type": "A String", # The type of job.
"createTime": "A String", # Time when the job was created.
}
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 cancelled if
possible.
See https://cloud.google.com/dlp/docs/inspecting-storage and
https://cloud.google.com/dlp/docs/compute-risk-analysis to learn more.
Args:
name: string, 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);
# }
#
# The JSON representation for `Empty` is empty JSON object `{}`.
}
get(name, x__xgafv=None)
Gets the latest state of a long-running DlpJob.
See https://cloud.google.com/dlp/docs/inspecting-storage and
https://cloud.google.com/dlp/docs/compute-risk-analysis to learn more.
Args:
name: string, 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.
"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.
# Output only field.
"timestamps": [ # The times the error occurred.
"A String",
],
"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).
"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.
"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.
},
],
},
},
],
"name": "A String", # The server-assigned name.
"inspectDetails": { # The results of an inspect DataSource job. # Results from inspecting a data source.
"requestedOptions": { # The configuration used for this job.
"snapshotInspectTemplate": { # The inspectTemplate contains a configuration (set of types of sensitive data # If run with an InspectTemplate, a snapshot of its state at the time of
# this run.
# to be detected) to be used anywhere you otherwise would normally specify
# InspectConfig. See https://cloud.google.com/dlp/docs/concepts-templates
# to learn more.
"updateTime": "A String", # The last update timestamp of a inspectTemplate, output only field.
"displayName": "A String", # Display name (max 256 chars).
"description": "A String", # Short description (max 256 chars).
"inspectConfig": { # Configuration description of the scanning process. # The core content of the template. Configuration of the scanning process.
# When used with redactContent only info_types and min_likelihood are currently
# used.
"excludeInfoTypes": True or False, # When true, excludes type information of the findings.
"limits": {
"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.
# When set within `InspectContentRequest`, the maximum returned is 2000
# regardless if this is set higher.
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.
# When set within `InspectDataSourceRequest`,
# the maximum returned is 2000 regardless if this is set higher.
# When set within `InspectContentRequest`, this field is ignored.
},
"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is
# POSSIBLE.
# See https://cloud.google.com/dlp/docs/likelihood to learn more.
"customInfoTypes": [ # CustomInfoTypes provided by the user. See
# https://cloud.google.com/dlp/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.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"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.
"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,
],
},
"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that
# support reversing.
# such as
# [`CryptoReplaceFfxFpeConfig`](/dlp/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`.
},
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.
# 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/dlp/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.
"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",
],
},
"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
},
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in
# `InspectDataSource`. Not currently supported in `InspectContent`.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example
# `organizations/433245324/storedInfoTypes/432452342` or
# `projects/project-id/storedInfoTypes/432452342`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for
# inspection was created. Output-only field, populated by the system.
},
"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 # Hotword-based detection rule.
# proximity of hotwords.
"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
# The total length of the window cannot exceed 1000 characters. Note that
# the finding itself will be included in the window, so that hotwords may
# be used to match substrings of the finding itself. For example, the
# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
# adjusted upwards if the area code is known to be the local area code of
# a company office using the hotword regex "\(xxx\)", where "xxx"
# is the area code in question.
# rule.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider.
},
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"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.
"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,
],
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
# part of a detection rule.
"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`.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
},
},
},
],
"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.
"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.
},
],
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is
# included in the response; see Finding.quote.
"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.
"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`.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
# proximity of hotwords.
"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
# The total length of the window cannot exceed 1000 characters. Note that
# the finding itself will be included in the window, so that hotwords may
# be used to match substrings of the finding itself. For example, the
# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
# adjusted upwards if the area code is known to be the local area code of
# a company office using the hotword regex "\(xxx\)", where "xxx"
# is the area code in question.
# rule.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider.
},
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"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.
"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,
],
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
# part of a detection rule.
"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`.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
},
},
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.
# `InspectionRuleSet` are removed from results.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"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.
"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,
],
},
"excludeInfoTypes": { # List of exclude 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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.
# 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/dlp/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.
"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",
],
},
"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
},
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
},
},
],
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
],
"contentOptions": [ # List of options defining data content to scan.
# If empty, text, images, and other content will be included.
"A String",
],
"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/dlp/docs/infotypes-reference.
#
# When no InfoTypes or CustomInfoTypes are specified in a request, the
# system may automatically choose what detectors to run. By default this may
# be all types, but may change over time as detectors are updated.
#
# The special InfoType name "ALL_BASIC" can be used to trigger all detectors,
# but may change over time as new InfoTypes are added. If you need precise
# control and predictability as to what detectors are run you should specify
# specific InfoTypes listed in the reference.
{ # 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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
"createTime": "A String", # The creation timestamp of a inspectTemplate, output only field.
"name": "A String", # The template name. Output only.
#
# The template will have one of the following formats:
# `projects/PROJECT_ID/inspectTemplates/TEMPLATE_ID` OR
# `organizations/ORGANIZATION_ID/inspectTemplates/TEMPLATE_ID`
},
"jobConfig": {
"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options specification.
"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 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.
"projectId": "A String", # The ID of the project to which the entities belong.
"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
},
"kind": { # A representation of a Datastore kind. # The kind to process.
"name": "A String", # The name of the kind.
},
},
"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options specification.
"excludedFields": [ # References to fields excluded from scanning. This allows you to skip
# inspection of entire columns which you know have no findings.
{ # 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.
"sampleMethod": "A String",
"identifyingFields": [ # References to fields uniquely identifying rows within the table.
# Nested fields in the format, like `person.birthdate.year`, are allowed.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"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.
"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
},
"timespanConfig": { # Configuration of the timespan of the items to include in scanning.
# Currently only supported when inspecting Google Cloud Storage and BigQuery.
"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 or BigQuery.
# If not specified for BigQuery, table last modification timestamp
# is checked against given time span.
# The valid data types of the timestamp field are:
# for BigQuery - timestamp, date, datetime;
# for Datastore - timestamp.
# Datastore entity will be scanned if the timestamp property does not exist
# or its value is empty or invalid.
"name": "A String", # Name describing the field.
},
"endTime": "A String", # Exclude files or rows newer than this value.
# If set to zero, no upper time limit is applied.
"startTime": "A String", # Exclude files or rows older than this value.
"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.
},
"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options specification.
# bucket.
"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.
"sampleMethod": "A String",
"fileSet": { # Set of files to scan. # The set of one or more files to scan.
"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.
"regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular # The regex-filtered set of files to scan. Exactly one of `url` or
# `regex_file_set` must be set.
# 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 `/`
"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",
],
"bucketName": "A String", # The name of a Cloud Storage bucket. Required.
"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",
],
},
},
"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.
"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.
"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.
"A String",
],
},
},
"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.
# When used with redactContent only info_types and min_likelihood are currently
# used.
"excludeInfoTypes": True or False, # When true, excludes type information of the findings.
"limits": {
"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.
# When set within `InspectContentRequest`, the maximum returned is 2000
# regardless if this is set higher.
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.
# When set within `InspectDataSourceRequest`,
# the maximum returned is 2000 regardless if this is set higher.
# When set within `InspectContentRequest`, this field is ignored.
},
"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is
# POSSIBLE.
# See https://cloud.google.com/dlp/docs/likelihood to learn more.
"customInfoTypes": [ # CustomInfoTypes provided by the user. See
# https://cloud.google.com/dlp/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.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"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.
"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,
],
},
"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that
# support reversing.
# such as
# [`CryptoReplaceFfxFpeConfig`](/dlp/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`.
},
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.
# 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/dlp/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.
"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",
],
},
"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
},
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in
# `InspectDataSource`. Not currently supported in `InspectContent`.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example
# `organizations/433245324/storedInfoTypes/432452342` or
# `projects/project-id/storedInfoTypes/432452342`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for
# inspection was created. Output-only field, populated by the system.
},
"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 # Hotword-based detection rule.
# proximity of hotwords.
"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
# The total length of the window cannot exceed 1000 characters. Note that
# the finding itself will be included in the window, so that hotwords may
# be used to match substrings of the finding itself. For example, the
# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
# adjusted upwards if the area code is known to be the local area code of
# a company office using the hotword regex "\(xxx\)", where "xxx"
# is the area code in question.
# rule.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider.
},
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"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.
"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,
],
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
# part of a detection rule.
"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`.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
},
},
},
],
"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.
"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.
},
],
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is
# included in the response; see Finding.quote.
"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.
"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`.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
# proximity of hotwords.
"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
# The total length of the window cannot exceed 1000 characters. Note that
# the finding itself will be included in the window, so that hotwords may
# be used to match substrings of the finding itself. For example, the
# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
# adjusted upwards if the area code is known to be the local area code of
# a company office using the hotword regex "\(xxx\)", where "xxx"
# is the area code in question.
# rule.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider.
},
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"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.
"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,
],
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
# part of a detection rule.
"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`.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
},
},
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.
# `InspectionRuleSet` are removed from results.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"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.
"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,
],
},
"excludeInfoTypes": { # List of exclude 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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.
# 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/dlp/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.
"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",
],
},
"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
},
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
},
},
],
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
],
"contentOptions": [ # List of options defining data content to scan.
# If empty, text, images, and other content will be included.
"A String",
],
"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/dlp/docs/infotypes-reference.
#
# When no InfoTypes or CustomInfoTypes are specified in a request, the
# system may automatically choose what detectors to run. By default this may
# be all types, but may change over time as detectors are updated.
#
# The special InfoType name "ALL_BASIC" can be used to trigger all detectors,
# but may change over time as new InfoTypes are added. If you need precise
# control and predictability as to what detectors are run you should specify
# specific InfoTypes listed in the reference.
{ # 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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
"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.
"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/dlp/docs/concepts-actions to learn more.
"saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location.
# OutputStorageConfig. Only a single instance of this action can be
# specified.
# Compatible with: Inspect, Risk
"outputConfig": { # Cloud repository for storing output.
"table": { # Message defining the location of a BigQuery table. A table is uniquely # 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 timezone 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.
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
"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.
},
},
"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification to project owners and editors on job's
# completion/failure.
# completion/failure.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).
# Command Center (CSCC Alpha).
# This action is only available for projects which are parts of
# an organization and whitelisted for the alpha Cloud Security Command
# Center.
# The action will publish count of finding instances and their info types.
# The summary of findings will be persisted in CSCC and are governed by CSCC
# service-specific policy, see https://cloud.google.com/terms/service-terms
# Only a single instance of this action can be specified.
# Compatible with: Inspect
},
"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.
# message contains a single field, `DlpJobName`, which is equal to the
# finished job's
# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).
# Compatible with: Inspect, Risk
"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}.
},
},
],
},
},
"result": { # All result fields mentioned below are updated while the job is processing. # A summary of the outcome of this inspect 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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
},
],
"totalEstimatedBytes": "A String", # Estimate of the number of bytes to process.
"processedBytes": "A String", # Total size in bytes that were processed.
},
},
"riskDetails": { # Result of a risk analysis operation request. # Results from analyzing risk of a data source.
"numericalStatsResult": { # Result of the numerical stats computation.
"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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
],
"maxValue": { # Set of primitive values supported by the system. # Maximum value appearing in the column.
# 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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
"minValue": { # Set of primitive values supported by the system. # Minimum value appearing in the column.
# 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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
},
"kMapEstimationResult": { # Result of the reidentifiability analysis. Note that these results are an
# estimation, not exact values.
"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.
"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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
],
},
],
"minAnonymity": "A String", # Always positive.
"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.
"maxAnonymity": "A String", # Always greater than or equal to min_anonymity.
"bucketSize": "A String", # Number of records within these anonymity bounds.
},
],
},
"kAnonymityResult": { # Result of the k-anonymity computation.
"equivalenceClassHistogramBuckets": [ # Histogram of k-anonymity equivalence classes.
{
"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
"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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
],
"equivalenceClassSize": "A String", # Size of the equivalence class, for example number of rows with the
# above set of values.
},
],
"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.
"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.
"bucketSize": "A String", # Total number of equivalence classes in this bucket.
},
],
},
"lDiversityResult": { # Result of the l-diversity computation.
"sensitiveValueFrequencyHistogramBuckets": [ # Histogram of l-diversity equivalence class sensitive value frequencies.
{
"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.
"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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
],
"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. # A value contained in the field in question.
# 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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
},
],
"equivalenceClassSize": "A String", # Size of the k-anonymity equivalence class.
},
],
"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.
"bucketSize": "A String", # Total number of equivalence classes in this bucket.
"sensitiveValueFrequencyUpperBound": "A String", # Upper bound on the sensitive value frequencies of the equivalence
# classes in this bucket.
"sensitiveValueFrequencyLowerBound": "A String", # Lower bound on the sensitive value frequencies of the equivalence
# classes in this bucket.
},
],
},
"requestedPrivacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.
"numericalStatsConfig": { # Compute numerical stats over an individual column, including
# min, max, and quantiles.
"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.
},
},
"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.
# A column with a semantic tag attached.
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.
# Required if no column is tagged with a region-specific InfoType (like
# US_ZIP_5) or a region code.
"quasiIds": [ # Fields considered to be quasi-identifiers. No two columns can have the
# same tag. [required]
{
"field": { # General identifier of a data field in a storage service. # Identifies the column. [required]
"name": "A String", # Name describing the field.
},
"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).
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated # If no semantic tag is indicated, we infer the statistical model from
# the distribution of values in the input data
# 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);
# }
#
# The JSON representation for `Empty` is empty JSON object `{}`.
},
},
],
"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).
"relativeFrequency": { # General identifier of a data field in a storage service. # The relative frequency column must contain a floating-point number
# between 0 and 1 (inclusive). Null values are assumed to be zero.
# [required]
"name": "A String", # Name describing the field.
},
"quasiIds": [ # Quasi-identifier columns. [required]
{ # A quasi-identifier column has a custom_tag, used to know which column
# in the data corresponds to which column in the statistical model.
"field": { # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
"customTag": "A String",
},
],
"table": { # Message defining the location of a BigQuery table. A table is uniquely # Auxiliary table location. [required]
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
},
],
},
"lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk.
"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.
},
"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.
},
],
},
"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.
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.
# Required if no column is tagged with a region-specific InfoType (like
# US_ZIP_5) or a region code.
"quasiIds": [ # Fields considered to be quasi-identifiers. No two fields can have the
# same tag. [required]
{ # A column with a semantic tag attached.
"field": { # General identifier of a data field in a storage service. # Identifies the column. [required]
"name": "A String", # Name describing the field.
},
"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).
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated # If no semantic tag is indicated, we infer the statistical model from
# the distribution of values in the input data
# 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);
# }
#
# The JSON representation for `Empty` is empty JSON object `{}`.
},
},
],
"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).
"relativeFrequency": { # General identifier of a data field in a storage service. # The relative frequency column must contain a floating-point number
# between 0 and 1 (inclusive). Null values are assumed to be zero.
# [required]
"name": "A String", # Name describing the field.
},
"quasiIds": [ # Quasi-identifier columns. [required]
{ # A quasi-identifier column has a custom_tag, used to know which column
# in the data corresponds to which column in the statistical model.
"field": { # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
"customTag": "A String",
},
],
"table": { # Message defining the location of a BigQuery table. A table is uniquely # Auxiliary table location. [required]
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
},
],
},
"categoricalStatsConfig": { # Compute numerical stats over an individual column, including
# number of distinct values and value count distribution.
"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.
},
},
"kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk.
"entityId": { # An entity in a dataset is a field or set of fields that correspond to a # Optional 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.
# 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.
"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.
},
],
},
},
"categoricalStatsResult": { # Result of the categorical stats computation.
"valueFrequencyHistogramBuckets": [ # Histogram of value frequencies in the column.
{
"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. # A value contained in the field in question.
# 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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
},
],
"bucketValueCount": "A String", # Total number of distinct values in this bucket.
"valueFrequencyUpperBound": "A String", # Upper bound on the value frequency of the values in this bucket.
"valueFrequencyLowerBound": "A String", # Lower bound on the value frequency of the values in this bucket.
"bucketSize": "A String", # Total number of values in this bucket.
},
],
},
"deltaPresenceEstimationResult": { # Result of the δ-presence computation. Note that these results are an
# estimation, not exact values.
"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.
"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.
"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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
],
"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.
},
],
"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.
"bucketSize": "A String", # Number of records within these probability bounds.
"maxProbability": 3.14, # Always greater than or equal to min_probability.
"minProbability": 3.14, # Between 0 and 1.
},
],
},
"requestedSourceTable": { # Message defining the location of a BigQuery table. A table is uniquely # Input dataset to compute metrics over.
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
},
"state": "A String", # State of a job.
"jobTriggerName": "A String", # If created by a job trigger, the resource name of the trigger that
# instantiated the job.
"startTime": "A String", # Time when the job started.
"endTime": "A String", # Time when the job finished.
"type": "A String", # The type of job.
"createTime": "A String", # Time when the job was created.
}
list(parent, orderBy=None, type=None, pageSize=None, pageToken=None, x__xgafv=None, filter=None)
Lists DlpJobs that match the specified filter in the request.
See https://cloud.google.com/dlp/docs/inspecting-storage and
https://cloud.google.com/dlp/docs/compute-risk-analysis to learn more.
Args:
parent: string, The parent resource name, for example projects/my-project-id. (required)
orderBy: string, Optional comma separated list of fields to order by,
followed by `asc` or `desc` postfix. This list is case-insensitive,
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 time the job was created.
- `end_time`: corresponds to time the job ended.
- `name`: corresponds to job's name.
- `state`: corresponds to `state`
type: string, The type of job. Defaults to `DlpJobType.INSPECT`
pageSize: integer, The standard list page size.
pageToken: string, The standard list page token.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
filter: string, Optional. 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 ` `.
* Supported fields/values for inspect jobs:
- `state` - PENDING|RUNNING|CANCELED|FINISHED|FAILED
- `inspected_storage` - DATASTORE|CLOUD_STORAGE|BIGQUERY
- `trigger_name` - The resource name of the trigger that created job.
- 'end_time` - Corresponds to time the job finished.
- 'start_time` - Corresponds to time the job finished.
* Supported fields for risk analysis jobs:
- `state` - RUNNING|CANCELED|FINISHED|FAILED
- 'end_time` - Corresponds to time the job finished.
- 'start_time` - Corresponds to 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.
Returns:
An object of the form:
{ # The response message for listing DLP jobs.
"nextPageToken": "A String", # The standard List next-page token.
"jobs": [ # A list of DlpJobs that matches the specified filter in the request.
{ # Combines all of the information about a DLP job.
"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.
# Output only field.
"timestamps": [ # The times the error occurred.
"A String",
],
"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).
"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.
"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.
},
],
},
},
],
"name": "A String", # The server-assigned name.
"inspectDetails": { # The results of an inspect DataSource job. # Results from inspecting a data source.
"requestedOptions": { # The configuration used for this job.
"snapshotInspectTemplate": { # The inspectTemplate contains a configuration (set of types of sensitive data # If run with an InspectTemplate, a snapshot of its state at the time of
# this run.
# to be detected) to be used anywhere you otherwise would normally specify
# InspectConfig. See https://cloud.google.com/dlp/docs/concepts-templates
# to learn more.
"updateTime": "A String", # The last update timestamp of a inspectTemplate, output only field.
"displayName": "A String", # Display name (max 256 chars).
"description": "A String", # Short description (max 256 chars).
"inspectConfig": { # Configuration description of the scanning process. # The core content of the template. Configuration of the scanning process.
# When used with redactContent only info_types and min_likelihood are currently
# used.
"excludeInfoTypes": True or False, # When true, excludes type information of the findings.
"limits": {
"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.
# When set within `InspectContentRequest`, the maximum returned is 2000
# regardless if this is set higher.
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.
# When set within `InspectDataSourceRequest`,
# the maximum returned is 2000 regardless if this is set higher.
# When set within `InspectContentRequest`, this field is ignored.
},
"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is
# POSSIBLE.
# See https://cloud.google.com/dlp/docs/likelihood to learn more.
"customInfoTypes": [ # CustomInfoTypes provided by the user. See
# https://cloud.google.com/dlp/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.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"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.
"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,
],
},
"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that
# support reversing.
# such as
# [`CryptoReplaceFfxFpeConfig`](/dlp/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`.
},
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.
# 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/dlp/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.
"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",
],
},
"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
},
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in
# `InspectDataSource`. Not currently supported in `InspectContent`.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example
# `organizations/433245324/storedInfoTypes/432452342` or
# `projects/project-id/storedInfoTypes/432452342`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for
# inspection was created. Output-only field, populated by the system.
},
"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 # Hotword-based detection rule.
# proximity of hotwords.
"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
# The total length of the window cannot exceed 1000 characters. Note that
# the finding itself will be included in the window, so that hotwords may
# be used to match substrings of the finding itself. For example, the
# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
# adjusted upwards if the area code is known to be the local area code of
# a company office using the hotword regex "\(xxx\)", where "xxx"
# is the area code in question.
# rule.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider.
},
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"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.
"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,
],
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
# part of a detection rule.
"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`.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
},
},
},
],
"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.
"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.
},
],
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is
# included in the response; see Finding.quote.
"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.
"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`.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
# proximity of hotwords.
"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
# The total length of the window cannot exceed 1000 characters. Note that
# the finding itself will be included in the window, so that hotwords may
# be used to match substrings of the finding itself. For example, the
# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
# adjusted upwards if the area code is known to be the local area code of
# a company office using the hotword regex "\(xxx\)", where "xxx"
# is the area code in question.
# rule.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider.
},
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"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.
"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,
],
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
# part of a detection rule.
"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`.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
},
},
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.
# `InspectionRuleSet` are removed from results.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"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.
"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,
],
},
"excludeInfoTypes": { # List of exclude 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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.
# 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/dlp/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.
"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",
],
},
"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
},
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
},
},
],
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
],
"contentOptions": [ # List of options defining data content to scan.
# If empty, text, images, and other content will be included.
"A String",
],
"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/dlp/docs/infotypes-reference.
#
# When no InfoTypes or CustomInfoTypes are specified in a request, the
# system may automatically choose what detectors to run. By default this may
# be all types, but may change over time as detectors are updated.
#
# The special InfoType name "ALL_BASIC" can be used to trigger all detectors,
# but may change over time as new InfoTypes are added. If you need precise
# control and predictability as to what detectors are run you should specify
# specific InfoTypes listed in the reference.
{ # 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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
"createTime": "A String", # The creation timestamp of a inspectTemplate, output only field.
"name": "A String", # The template name. Output only.
#
# The template will have one of the following formats:
# `projects/PROJECT_ID/inspectTemplates/TEMPLATE_ID` OR
# `organizations/ORGANIZATION_ID/inspectTemplates/TEMPLATE_ID`
},
"jobConfig": {
"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options specification.
"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 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.
"projectId": "A String", # The ID of the project to which the entities belong.
"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
},
"kind": { # A representation of a Datastore kind. # The kind to process.
"name": "A String", # The name of the kind.
},
},
"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options specification.
"excludedFields": [ # References to fields excluded from scanning. This allows you to skip
# inspection of entire columns which you know have no findings.
{ # 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.
"sampleMethod": "A String",
"identifyingFields": [ # References to fields uniquely identifying rows within the table.
# Nested fields in the format, like `person.birthdate.year`, are allowed.
{ # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
],
"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.
"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
},
"timespanConfig": { # Configuration of the timespan of the items to include in scanning.
# Currently only supported when inspecting Google Cloud Storage and BigQuery.
"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 or BigQuery.
# If not specified for BigQuery, table last modification timestamp
# is checked against given time span.
# The valid data types of the timestamp field are:
# for BigQuery - timestamp, date, datetime;
# for Datastore - timestamp.
# Datastore entity will be scanned if the timestamp property does not exist
# or its value is empty or invalid.
"name": "A String", # Name describing the field.
},
"endTime": "A String", # Exclude files or rows newer than this value.
# If set to zero, no upper time limit is applied.
"startTime": "A String", # Exclude files or rows older than this value.
"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.
},
"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options specification.
# bucket.
"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.
"sampleMethod": "A String",
"fileSet": { # Set of files to scan. # The set of one or more files to scan.
"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.
"regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular # The regex-filtered set of files to scan. Exactly one of `url` or
# `regex_file_set` must be set.
# 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 `/`
"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",
],
"bucketName": "A String", # The name of a Cloud Storage bucket. Required.
"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",
],
},
},
"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.
"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.
"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.
"A String",
],
},
},
"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.
# When used with redactContent only info_types and min_likelihood are currently
# used.
"excludeInfoTypes": True or False, # When true, excludes type information of the findings.
"limits": {
"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.
# When set within `InspectContentRequest`, the maximum returned is 2000
# regardless if this is set higher.
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"maxFindings": 42, # Max findings limit for the given infoType.
},
],
"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.
# When set within `InspectDataSourceRequest`,
# the maximum returned is 2000 regardless if this is set higher.
# When set within `InspectContentRequest`, this field is ignored.
},
"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is
# POSSIBLE.
# See https://cloud.google.com/dlp/docs/likelihood to learn more.
"customInfoTypes": [ # CustomInfoTypes provided by the user. See
# https://cloud.google.com/dlp/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.
"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
"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.
"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,
],
},
"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that
# support reversing.
# such as
# [`CryptoReplaceFfxFpeConfig`](/dlp/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`.
},
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.
# 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/dlp/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.
"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",
],
},
"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
},
},
"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in
# `InspectDataSource`. Not currently supported in `InspectContent`.
"name": "A String", # Resource name of the requested `StoredInfoType`, for example
# `organizations/433245324/storedInfoTypes/432452342` or
# `projects/project-id/storedInfoTypes/432452342`.
"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for
# inspection was created. Output-only field, populated by the system.
},
"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 # Hotword-based detection rule.
# proximity of hotwords.
"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
# The total length of the window cannot exceed 1000 characters. Note that
# the finding itself will be included in the window, so that hotwords may
# be used to match substrings of the finding itself. For example, the
# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
# adjusted upwards if the area code is known to be the local area code of
# a company office using the hotword regex "\(xxx\)", where "xxx"
# is the area code in question.
# rule.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider.
},
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"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.
"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,
],
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
# part of a detection rule.
"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`.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
},
},
},
],
"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.
"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.
},
],
"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is
# included in the response; see Finding.quote.
"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.
"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`.
"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
# proximity of hotwords.
"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
# The total length of the window cannot exceed 1000 characters. Note that
# the finding itself will be included in the window, so that hotwords may
# be used to match substrings of the finding itself. For example, the
# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
# adjusted upwards if the area code is known to be the local area code of
# a company office using the hotword regex "\(xxx\)", where "xxx"
# is the area code in question.
# rule.
"windowAfter": 42, # Number of characters after the finding to consider.
"windowBefore": 42, # Number of characters before the finding to consider.
},
"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
"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.
"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,
],
},
"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
# part of a detection rule.
"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`.
"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
},
},
"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.
# `InspectionRuleSet` are removed from results.
"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
"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.
"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,
],
},
"excludeInfoTypes": { # List of exclude 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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.
# 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/dlp/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.
"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",
],
},
"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
},
},
"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
},
},
],
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
],
"contentOptions": [ # List of options defining data content to scan.
# If empty, text, images, and other content will be included.
"A String",
],
"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/dlp/docs/infotypes-reference.
#
# When no InfoTypes or CustomInfoTypes are specified in a request, the
# system may automatically choose what detectors to run. By default this may
# be all types, but may change over time as detectors are updated.
#
# The special InfoType name "ALL_BASIC" can be used to trigger all detectors,
# but may change over time as new InfoTypes are added. If you need precise
# control and predictability as to what detectors are run you should specify
# specific InfoTypes listed in the reference.
{ # 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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
],
},
"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.
"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/dlp/docs/concepts-actions to learn more.
"saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location.
# OutputStorageConfig. Only a single instance of this action can be
# specified.
# Compatible with: Inspect, Risk
"outputConfig": { # Cloud repository for storing output.
"table": { # Message defining the location of a BigQuery table. A table is uniquely # 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 timezone 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.
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
"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.
},
},
"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification to project owners and editors on job's
# completion/failure.
# completion/failure.
},
"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).
# Command Center (CSCC Alpha).
# This action is only available for projects which are parts of
# an organization and whitelisted for the alpha Cloud Security Command
# Center.
# The action will publish count of finding instances and their info types.
# The summary of findings will be persisted in CSCC and are governed by CSCC
# service-specific policy, see https://cloud.google.com/terms/service-terms
# Only a single instance of this action can be specified.
# Compatible with: Inspect
},
"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.
# message contains a single field, `DlpJobName`, which is equal to the
# finished job's
# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).
# Compatible with: Inspect, Risk
"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}.
},
},
],
},
},
"result": { # All result fields mentioned below are updated while the job is processing. # A summary of the outcome of this inspect 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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
},
],
"totalEstimatedBytes": "A String", # Estimate of the number of bytes to process.
"processedBytes": "A String", # Total size in bytes that were processed.
},
},
"riskDetails": { # Result of a risk analysis operation request. # Results from analyzing risk of a data source.
"numericalStatsResult": { # Result of the numerical stats computation.
"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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
],
"maxValue": { # Set of primitive values supported by the system. # Maximum value appearing in the column.
# 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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
"minValue": { # Set of primitive values supported by the system. # Minimum value appearing in the column.
# 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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
},
"kMapEstimationResult": { # Result of the reidentifiability analysis. Note that these results are an
# estimation, not exact values.
"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.
"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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
],
},
],
"minAnonymity": "A String", # Always positive.
"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.
"maxAnonymity": "A String", # Always greater than or equal to min_anonymity.
"bucketSize": "A String", # Number of records within these anonymity bounds.
},
],
},
"kAnonymityResult": { # Result of the k-anonymity computation.
"equivalenceClassHistogramBuckets": [ # Histogram of k-anonymity equivalence classes.
{
"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
"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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
],
"equivalenceClassSize": "A String", # Size of the equivalence class, for example number of rows with the
# above set of values.
},
],
"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.
"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.
"bucketSize": "A String", # Total number of equivalence classes in this bucket.
},
],
},
"lDiversityResult": { # Result of the l-diversity computation.
"sensitiveValueFrequencyHistogramBuckets": [ # Histogram of l-diversity equivalence class sensitive value frequencies.
{
"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.
"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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
],
"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. # A value contained in the field in question.
# 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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
},
],
"equivalenceClassSize": "A String", # Size of the k-anonymity equivalence class.
},
],
"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.
"bucketSize": "A String", # Total number of equivalence classes in this bucket.
"sensitiveValueFrequencyUpperBound": "A String", # Upper bound on the sensitive value frequencies of the equivalence
# classes in this bucket.
"sensitiveValueFrequencyLowerBound": "A String", # Lower bound on the sensitive value frequencies of the equivalence
# classes in this bucket.
},
],
},
"requestedPrivacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.
"numericalStatsConfig": { # Compute numerical stats over an individual column, including
# min, max, and quantiles.
"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.
},
},
"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.
# A column with a semantic tag attached.
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.
# Required if no column is tagged with a region-specific InfoType (like
# US_ZIP_5) or a region code.
"quasiIds": [ # Fields considered to be quasi-identifiers. No two columns can have the
# same tag. [required]
{
"field": { # General identifier of a data field in a storage service. # Identifies the column. [required]
"name": "A String", # Name describing the field.
},
"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).
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated # If no semantic tag is indicated, we infer the statistical model from
# the distribution of values in the input data
# 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);
# }
#
# The JSON representation for `Empty` is empty JSON object `{}`.
},
},
],
"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).
"relativeFrequency": { # General identifier of a data field in a storage service. # The relative frequency column must contain a floating-point number
# between 0 and 1 (inclusive). Null values are assumed to be zero.
# [required]
"name": "A String", # Name describing the field.
},
"quasiIds": [ # Quasi-identifier columns. [required]
{ # A quasi-identifier column has a custom_tag, used to know which column
# in the data corresponds to which column in the statistical model.
"field": { # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
"customTag": "A String",
},
],
"table": { # Message defining the location of a BigQuery table. A table is uniquely # Auxiliary table location. [required]
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
},
],
},
"lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk.
"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.
},
"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.
},
],
},
"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.
"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.
# Required if no column is tagged with a region-specific InfoType (like
# US_ZIP_5) or a region code.
"quasiIds": [ # Fields considered to be quasi-identifiers. No two fields can have the
# same tag. [required]
{ # A column with a semantic tag attached.
"field": { # General identifier of a data field in a storage service. # Identifies the column. [required]
"name": "A String", # Name describing the field.
},
"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).
"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/dlp/docs/infotypes-reference when specifying
# a built-in type. InfoType names should conform to the pattern
# [a-zA-Z0-9_]{1,64}.
},
"inferred": { # A generic empty message that you can re-use to avoid defining duplicated # If no semantic tag is indicated, we infer the statistical model from
# the distribution of values in the input data
# 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);
# }
#
# The JSON representation for `Empty` is empty JSON object `{}`.
},
},
],
"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).
"relativeFrequency": { # General identifier of a data field in a storage service. # The relative frequency column must contain a floating-point number
# between 0 and 1 (inclusive). Null values are assumed to be zero.
# [required]
"name": "A String", # Name describing the field.
},
"quasiIds": [ # Quasi-identifier columns. [required]
{ # A quasi-identifier column has a custom_tag, used to know which column
# in the data corresponds to which column in the statistical model.
"field": { # General identifier of a data field in a storage service.
"name": "A String", # Name describing the field.
},
"customTag": "A String",
},
],
"table": { # Message defining the location of a BigQuery table. A table is uniquely # Auxiliary table location. [required]
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
},
],
},
"categoricalStatsConfig": { # Compute numerical stats over an individual column, including
# number of distinct values and value count distribution.
"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.
},
},
"kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk.
"entityId": { # An entity in a dataset is a field or set of fields that correspond to a # Optional 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.
# 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.
"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.
},
],
},
},
"categoricalStatsResult": { # Result of the categorical stats computation.
"valueFrequencyHistogramBuckets": [ # Histogram of value frequencies in the column.
{
"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. # A value contained in the field in question.
# 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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
},
],
"bucketValueCount": "A String", # Total number of distinct values in this bucket.
"valueFrequencyUpperBound": "A String", # Upper bound on the value frequency of the values in this bucket.
"valueFrequencyLowerBound": "A String", # Lower bound on the value frequency of the values in this bucket.
"bucketSize": "A String", # Total number of values in this bucket.
},
],
},
"deltaPresenceEstimationResult": { # Result of the δ-presence computation. Note that these results are an
# estimation, not exact values.
"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.
"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.
"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.
"floatValue": 3.14,
"timestampValue": "A String",
"dayOfWeekValue": "A 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`.
"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
# to allow the value "24:00:00" for scenarios like business closing time.
"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
# allow the value 60 if it allows leap-seconds.
"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
},
"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day
# and time zone are either specified elsewhere or are not significant. The date
# is relative to the Proleptic Gregorian Calendar. This can represent:
#
# * A full date, with non-zero year, month and day values
# * A month and day value, with a zero year, e.g. an anniversary
# * A year on its own, with zero month and day values
# * A year and month value, with a zero day, e.g. a credit card expiration date
#
# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
# a year.
"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
# if specifying a year by itself or a year and month where the day is not
# significant.
"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
# month and day.
},
"stringValue": "A String",
"booleanValue": True or False,
"integerValue": "A String",
},
],
"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.
},
],
"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.
"bucketSize": "A String", # Number of records within these probability bounds.
"maxProbability": 3.14, # Always greater than or equal to min_probability.
"minProbability": 3.14, # Between 0 and 1.
},
],
},
"requestedSourceTable": { # Message defining the location of a BigQuery table. A table is uniquely # Input dataset to compute metrics over.
# 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
# `..`.
"projectId": "A String", # The Google Cloud Platform 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.
"datasetId": "A String", # Dataset ID of the table.
},
},
"state": "A String", # State of a job.
"jobTriggerName": "A String", # If created by a job trigger, the resource name of the trigger that
# instantiated the job.
"startTime": "A String", # Time when the job started.
"endTime": "A String", # Time when the job finished.
"type": "A String", # The type of job.
"createTime": "A String", # Time when the job was created.
},
],
}
list_next(previous_request, previous_response)
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.