# frozen_string_literal: true
# Copyright 2020 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# Auto-generated by gapic-generator-ruby. DO NOT EDIT!
module Google
module Cloud
module Dlp
module V2
# Type of information detected by the API.
# @!attribute [rw] name
# @return [::String]
# Name of the information type. Either a name of your choosing when
# creating a CustomInfoType, or one of the names listed
# at
# https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference
# when specifying a built-in type. When sending Cloud DLP results to Data
# Catalog, infoType names should conform to the pattern
# `[A-Za-z0-9$_-]{1,64}`.
# @!attribute [rw] version
# @return [::String]
# Optional version name for this InfoType.
# @!attribute [rw] sensitivity_score
# @return [::Google::Cloud::Dlp::V2::SensitivityScore]
# Optional custom sensitivity for this InfoType.
# This only applies to data profiling.
class InfoType
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Score is calculated from of all elements in the data profile.
# A higher level means the data is more sensitive.
# @!attribute [rw] score
# @return [::Google::Cloud::Dlp::V2::SensitivityScore::SensitivityScoreLevel]
# The sensitivity score applied to the resource.
class SensitivityScore
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
# Various sensitivity score levels for resources.
module SensitivityScoreLevel
# Unused.
SENSITIVITY_SCORE_UNSPECIFIED = 0
# No sensitive information detected. The resource isn't publicly
# accessible.
SENSITIVITY_LOW = 10
# Medium risk. Contains personally identifiable information (PII),
# potentially sensitive data, or fields with free-text data that are at a
# higher risk of having intermittent sensitive data. Consider limiting
# access.
SENSITIVITY_MODERATE = 20
# High risk. Sensitive personally identifiable information (SPII) can be
# present. Exfiltration of data can lead to user data loss.
# Re-identification of users might be possible. Consider limiting usage and
# or removing SPII.
SENSITIVITY_HIGH = 30
end
end
# A reference to a StoredInfoType to use with scanning.
# @!attribute [rw] name
# @return [::String]
# Resource name of the requested `StoredInfoType`, for example
# `organizations/433245324/storedInfoTypes/432452342` or
# `projects/project-id/storedInfoTypes/432452342`.
# @!attribute [rw] create_time
# @return [::Google::Protobuf::Timestamp]
# Timestamp indicating when the version of the `StoredInfoType` used for
# inspection was created. Output-only field, populated by the system.
class StoredType
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Custom information type provided by the user. Used to find domain-specific
# sensitive information configurable to the data in question.
# @!attribute [rw] info_type
# @return [::Google::Cloud::Dlp::V2::InfoType]
# 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.
# @!attribute [rw] likelihood
# @return [::Google::Cloud::Dlp::V2::Likelihood]
# 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.
# @!attribute [rw] dictionary
# @return [::Google::Cloud::Dlp::V2::CustomInfoType::Dictionary]
# A list of phrases to detect as a CustomInfoType.
# @!attribute [rw] regex
# @return [::Google::Cloud::Dlp::V2::CustomInfoType::Regex]
# Regular expression based CustomInfoType.
# @!attribute [rw] surrogate_type
# @return [::Google::Cloud::Dlp::V2::CustomInfoType::SurrogateType]
# Message for detecting output from deidentification transformations that
# support reversing.
# @!attribute [rw] stored_type
# @return [::Google::Cloud::Dlp::V2::StoredType]
# Load an existing `StoredInfoType` resource for use in
# `InspectDataSource`. Not currently supported in `InspectContent`.
# @!attribute [rw] detection_rules
# @return [::Array<::Google::Cloud::Dlp::V2::CustomInfoType::DetectionRule>]
# 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.
# @!attribute [rw] exclusion_type
# @return [::Google::Cloud::Dlp::V2::CustomInfoType::ExclusionType]
# If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding
# to be returned. It still can be used for rules matching.
# @!attribute [rw] sensitivity_score
# @return [::Google::Cloud::Dlp::V2::SensitivityScore]
# Sensitivity for this CustomInfoType. If this CustomInfoType extends an
# existing InfoType, the sensitivity here will take precedence over that of
# the original InfoType. If unset for a CustomInfoType, it will default to
# HIGH.
# This only applies to data profiling.
class CustomInfoType
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
# Custom information type based on a dictionary of words or phrases. This can
# be used to match sensitive information specific to the data, such as a list
# of employee IDs or job titles.
#
# Dictionary words are case-insensitive and all characters other than letters
# and digits in the unicode [Basic Multilingual
# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
# will be replaced with whitespace when scanning for matches, so the
# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",
# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters
# surrounding any match must be of a different type than the adjacent
# characters within the word, so letters must be next to non-letters and
# digits next to non-digits. For example, the dictionary word "jen" will
# match the first three letters of the text "jen123" but will return no
# matches for "jennifer".
#
# Dictionary words containing a large number of characters that are not
# letters or digits may result in unexpected findings because such characters
# are treated as whitespace. The
# [limits](https://cloud.google.com/sensitive-data-protection/limits) page
# contains details about the size limits of dictionaries. For dictionaries
# that do not fit within these constraints, consider using
# `LargeCustomDictionaryConfig` in the `StoredInfoType` API.
# @!attribute [rw] word_list
# @return [::Google::Cloud::Dlp::V2::CustomInfoType::Dictionary::WordList]
# List of words or phrases to search for.
# @!attribute [rw] cloud_storage_path
# @return [::Google::Cloud::Dlp::V2::CloudStoragePath]
# Newline-delimited file of words in Cloud Storage. Only a single file
# is accepted.
class Dictionary
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
# Message defining a list of words or phrases to search for in the data.
# @!attribute [rw] words
# @return [::Array<::String>]
# 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]
class WordList
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
end
# Message defining a custom regular expression.
# @!attribute [rw] pattern
# @return [::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.
# @!attribute [rw] group_indexes
# @return [::Array<::Integer>]
# The index of the submatch to extract as findings. When not
# specified, the entire match is returned. No more than 3 may be included.
class Regex
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Message for detecting output from deidentification transformations
# such as
# [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/sensitive-data-protection/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).
# These types of transformations are
# those that perform pseudonymization, thereby producing a "surrogate" as
# output. This should be used in conjunction with a field on the
# transformation such as `surrogate_info_type`. This CustomInfoType does
# not support the use of `detection_rules`.
class SurrogateType
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# 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.
# @!attribute [rw] hotword_rule
# @return [::Google::Cloud::Dlp::V2::CustomInfoType::DetectionRule::HotwordRule]
# Hotword-based detection rule.
class DetectionRule
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
# Message for specifying a window around a finding to apply a detection
# rule.
# @!attribute [rw] window_before
# @return [::Integer]
# Number of characters before the finding to consider. For tabular data,
# if you want to modify the likelihood of an entire column of findngs,
# set this to 1. For more information, see
# [Hotword example: Set the match likelihood of a table column]
# (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
# @!attribute [rw] window_after
# @return [::Integer]
# Number of characters after the finding to consider.
class Proximity
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Message for specifying an adjustment to the likelihood of a finding as
# part of a detection rule.
# @!attribute [rw] fixed_likelihood
# @return [::Google::Cloud::Dlp::V2::Likelihood]
# Set the likelihood of a finding to a fixed value.
# @!attribute [rw] relative_likelihood
# @return [::Integer]
# 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`.
class LikelihoodAdjustment
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# The rule that adjusts the likelihood of findings within a certain
# proximity of hotwords.
# @!attribute [rw] hotword_regex
# @return [::Google::Cloud::Dlp::V2::CustomInfoType::Regex]
# Regular expression pattern defining what qualifies as a hotword.
# @!attribute [rw] proximity
# @return [::Google::Cloud::Dlp::V2::CustomInfoType::DetectionRule::Proximity]
# Range of characters within which the entire hotword must reside.
# The total length of the window cannot exceed 1000 characters.
# The finding itself will be included in the window, so that hotwords can
# be used to match substrings of the finding itself. Suppose you
# want Cloud DLP to promote the likelihood of the phone number
# regex "\(\d\\{3}\) \d\\{3}-\d\\{4}" if the area code is known to be the
# area code of a company's office. In this case, use the hotword regex
# "\(xxx\)", where "xxx" is the area code in question.
#
# For tabular data, if you want to modify the likelihood of an entire
# column of findngs, see
# [Hotword example: Set the match likelihood of a table column]
# (https://cloud.google.com/sensitive-data-protection/docs/creating-custom-infotypes-likelihood#match-column-values).
# @!attribute [rw] likelihood_adjustment
# @return [::Google::Cloud::Dlp::V2::CustomInfoType::DetectionRule::LikelihoodAdjustment]
# Likelihood adjustment to apply to all matching findings.
class HotwordRule
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
end
# Type of exclusion rule.
module ExclusionType
# A finding of this custom info type will not be excluded from results.
EXCLUSION_TYPE_UNSPECIFIED = 0
# A finding of this custom info type will be excluded from final results,
# but can still affect rule execution.
EXCLUSION_TYPE_EXCLUDE = 1
end
end
# General identifier of a data field in a storage service.
# @!attribute [rw] name
# @return [::String]
# Name describing the field.
class FieldId
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Datastore partition ID.
# A partition ID identifies a grouping of entities. The grouping is always
# by project and namespace, however the namespace ID may be empty.
#
# A partition ID contains several dimensions:
# project ID and namespace ID.
# @!attribute [rw] project_id
# @return [::String]
# The ID of the project to which the entities belong.
# @!attribute [rw] namespace_id
# @return [::String]
# If not empty, the ID of the namespace to which the entities belong.
class PartitionId
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# A representation of a Datastore kind.
# @!attribute [rw] name
# @return [::String]
# The name of the kind.
class KindExpression
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Options defining a data set within Google Cloud Datastore.
# @!attribute [rw] partition_id
# @return [::Google::Cloud::Dlp::V2::PartitionId]
# A partition ID identifies a grouping of entities. The grouping is always
# by project and namespace, however the namespace ID may be empty.
# @!attribute [rw] kind
# @return [::Google::Cloud::Dlp::V2::KindExpression]
# The kind to process.
class DatastoreOptions
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Message representing a set of files in a Cloud Storage bucket. Regular
# expressions are used to allow fine-grained control over which files in the
# bucket to include.
#
# Included files are those that match at least one item in `include_regex` and
# do not match any items in `exclude_regex`. Note that a file that matches
# items from both lists will _not_ be included. For a match to occur, the
# entire file path (i.e., everything in the url after the bucket name) must
# match the regular expression.
#
# For example, given the input `{bucket_name: "mybucket", include_regex:
# ["directory1/.*"], exclude_regex:
# ["directory1/excluded.*"]}`:
#
# * `gs://mybucket/directory1/myfile` will be included
# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches
# across `/`)
# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the
# full path doesn't match any items in `include_regex`)
# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path
# matches an item in `exclude_regex`)
#
# If `include_regex` is left empty, it will match all files by default
# (this is equivalent to setting `include_regex: [".*"]`).
#
# Some other common use cases:
#
# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all
# files in `mybucket` except for .pdf files
# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will
# include all files directly under `gs://mybucket/directory/`, without matching
# across `/`
# @!attribute [rw] bucket_name
# @return [::String]
# The name of a Cloud Storage bucket. Required.
# @!attribute [rw] include_regex
# @return [::Array<::String>]
# 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.
# @!attribute [rw] exclude_regex
# @return [::Array<::String>]
# 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.
class CloudStorageRegexFileSet
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Options defining a file or a set of files within a Cloud Storage
# bucket.
# @!attribute [rw] file_set
# @return [::Google::Cloud::Dlp::V2::CloudStorageOptions::FileSet]
# The set of one or more files to scan.
# @!attribute [rw] bytes_limit_per_file
# @return [::Integer]
# Max number of bytes to scan from a file. If a scanned file's size is bigger
# than this value then the rest of the bytes are omitted. Only one of
# `bytes_limit_per_file` and `bytes_limit_per_file_percent` can be specified.
# This field can't be set if de-identification is requested. For certain file
# types, setting this field has no effect. For more information, see [Limits
# on bytes scanned per
# file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
# @!attribute [rw] bytes_limit_per_file_percent
# @return [::Integer]
# Max percentage of bytes to scan from a file. The rest are omitted. The
# number of bytes scanned is rounded down. Must be between 0 and 100,
# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of
# bytes_limit_per_file and bytes_limit_per_file_percent can be specified.
# This field can't be set if de-identification is requested. For certain file
# types, setting this field has no effect. For more information, see [Limits
# on bytes scanned per
# file](https://cloud.google.com/sensitive-data-protection/docs/supported-file-types#max-byte-size-per-file).
# @!attribute [rw] file_types
# @return [::Array<::Google::Cloud::Dlp::V2::FileType>]
# List of file type groups to include in the scan.
# If empty, all files are scanned and available data format processors
# are applied. In addition, the binary content of the selected files
# is always scanned as well.
# Images are scanned only as binary if the specified region
# does not support image inspection and no file_types were specified.
# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
# @!attribute [rw] sample_method
# @return [::Google::Cloud::Dlp::V2::CloudStorageOptions::SampleMethod]
# How to sample the data.
# @!attribute [rw] files_limit_percent
# @return [::Integer]
# 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.
class CloudStorageOptions
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
# Set of files to scan.
# @!attribute [rw] url
# @return [::String]
# The Cloud Storage url of the file(s) to scan, in the format
# `gs://<bucket>/<path>`. 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.
# @!attribute [rw] regex_file_set
# @return [::Google::Cloud::Dlp::V2::CloudStorageRegexFileSet]
# The regex-filtered set of files to scan. Exactly one of `url` or
# `regex_file_set` must be set.
class FileSet
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# How to sample bytes if not all bytes are scanned. Meaningful only when used
# in conjunction with bytes_limit_per_file. If not specified, scanning would
# start from the top.
module SampleMethod
# No sampling.
SAMPLE_METHOD_UNSPECIFIED = 0
# Scan from the top (default).
TOP = 1
# For each file larger than bytes_limit_per_file, randomly pick the offset
# to start scanning. The scanned bytes are contiguous.
RANDOM_START = 2
end
end
# Message representing a set of files in Cloud Storage.
# @!attribute [rw] url
# @return [::String]
# The url, in the format `gs://<bucket>/<path>`. Trailing wildcard in the
# path is allowed.
class CloudStorageFileSet
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Message representing a single file or path in Cloud Storage.
# @!attribute [rw] path
# @return [::String]
# A URL representing a file or path (no wildcards) in Cloud Storage.
# Example: `gs://[BUCKET_NAME]/dictionary.txt`
class CloudStoragePath
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Options defining BigQuery table and row identifiers.
# @!attribute [rw] table_reference
# @return [::Google::Cloud::Dlp::V2::BigQueryTable]
# Complete BigQuery table reference.
# @!attribute [rw] identifying_fields
# @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
# Table fields that may uniquely identify a row within the table. When
# `actions.saveFindings.outputConfig.table` is specified, the values of
# columns specified here are available in the output table under
# `location.content_locations.record_location.record_key.id_values`. Nested
# fields such as `person.birthdate.year` are allowed.
# @!attribute [rw] rows_limit
# @return [::Integer]
# 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.
# @!attribute [rw] rows_limit_percent
# @return [::Integer]
# Max percentage of rows to scan. The rest are omitted. The number of rows
# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and
# 100 means no limit. Defaults to 0. Only one of rows_limit and
# rows_limit_percent can be specified. Cannot be used in conjunction with
# TimespanConfig.
#
# Caution: A [known
# issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-sampling)
# is causing the `rowsLimitPercent` field to behave unexpectedly. We
# recommend using `rowsLimit` instead.
# @!attribute [rw] sample_method
# @return [::Google::Cloud::Dlp::V2::BigQueryOptions::SampleMethod]
# How to sample the data.
# @!attribute [rw] excluded_fields
# @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
# References to fields excluded from scanning. This allows you to skip
# inspection of entire columns which you know have no findings.
# When inspecting a table, we recommend that you inspect all columns.
# Otherwise, findings might be affected because hints from excluded columns
# will not be used.
# @!attribute [rw] included_fields
# @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
# Limit scanning only to these fields.
# When inspecting a table, we recommend that you inspect all columns.
# Otherwise, findings might be affected because hints from excluded columns
# will not be used.
class BigQueryOptions
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
# How to sample rows if not all rows are scanned. Meaningful only when used
# in conjunction with either rows_limit or rows_limit_percent. If not
# specified, rows are scanned in the order BigQuery reads them.
module SampleMethod
# No sampling.
SAMPLE_METHOD_UNSPECIFIED = 0
# Scan groups of rows in the order BigQuery provides (default). Multiple
# groups of rows may be scanned in parallel, so results may not appear in
# the same order the rows are read.
TOP = 1
# Randomly pick groups of rows to scan.
RANDOM_START = 2
end
end
# Shared message indicating Cloud storage type.
# @!attribute [rw] datastore_options
# @return [::Google::Cloud::Dlp::V2::DatastoreOptions]
# Google Cloud Datastore options.
# @!attribute [rw] cloud_storage_options
# @return [::Google::Cloud::Dlp::V2::CloudStorageOptions]
# Cloud Storage options.
# @!attribute [rw] big_query_options
# @return [::Google::Cloud::Dlp::V2::BigQueryOptions]
# BigQuery options.
# @!attribute [rw] hybrid_options
# @return [::Google::Cloud::Dlp::V2::HybridOptions]
# Hybrid inspection options.
# @!attribute [rw] timespan_config
# @return [::Google::Cloud::Dlp::V2::StorageConfig::TimespanConfig]
# Configuration of the timespan of the items to include in scanning.
class StorageConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
# Configuration of the timespan of the items to include in scanning.
# Currently only supported when inspecting Cloud Storage and BigQuery.
# @!attribute [rw] start_time
# @return [::Google::Protobuf::Timestamp]
# Exclude files, tables, or rows older than this value.
# If not set, no lower time limit is applied.
# @!attribute [rw] end_time
# @return [::Google::Protobuf::Timestamp]
# Exclude files, tables, or rows newer than this value.
# If not set, no upper time limit is applied.
# @!attribute [rw] timestamp_field
# @return [::Google::Cloud::Dlp::V2::FieldId]
# Specification of the field containing the timestamp of scanned items.
# Used for data sources like Datastore and BigQuery.
#
# <b>For BigQuery</b>
#
# If this value is not specified and the table was modified between the
# given start and end times, the entire table will be scanned. If this
# value is specified, then rows are filtered based on the given start and
# end times. Rows with a `NULL` value in the provided BigQuery column are
# skipped.
# Valid data types of the provided BigQuery column are: `INTEGER`, `DATE`,
# `TIMESTAMP`, and `DATETIME`.
#
# If your BigQuery table is [partitioned at ingestion
# time](https://cloud.google.com/bigquery/docs/partitioned-tables#ingestion_time),
# you can use any of the following pseudo-columns as your timestamp field.
# When used with Cloud DLP, these pseudo-column names are case sensitive.
#
# <ul>
# <li><code>_PARTITIONTIME</code></li>
# <li><code>_PARTITIONDATE</code></li>
# <li><code>_PARTITION_LOAD_TIME</code></li>
# </ul>
#
# <b>For Datastore</b>
#
# If this value is specified, then entities are filtered based on the given
# start and end times. If an entity does not contain the provided timestamp
# property or contains empty or invalid values, then it is included.
# Valid data types of the provided timestamp property are: `TIMESTAMP`.
#
# See the
# [known
# issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#bq-timespan)
# related to this operation.
# @!attribute [rw] enable_auto_population_of_timespan_config
# @return [::Boolean]
# When the job is started by a JobTrigger we will automatically figure out
# a valid start_time to avoid scanning files that have not been modified
# since the last time the JobTrigger executed. This will be based on the
# time of the execution of the last run of the JobTrigger or the timespan
# end_time used in the last run of the JobTrigger.
#
# **For BigQuery**
#
# Inspect jobs triggered by automatic population will scan data that is at
# least three hours old when the job starts. This is because streaming
# buffer rows are not read during inspection and reading up to the current
# timestamp will result in skipped rows.
#
# See the [known
# issue](https://cloud.google.com/sensitive-data-protection/docs/known-issues#recently-streamed-data)
# related to this operation.
class TimespanConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
end
# Configuration to control jobs where the content being inspected is outside
# of Google Cloud Platform.
# @!attribute [rw] description
# @return [::String]
# A short description of where the data is coming from. Will be stored once
# in the job. 256 max length.
# @!attribute [rw] required_finding_label_keys
# @return [::Array<::String>]
# These are labels that each inspection request must include within their
# 'finding_labels' map. Request may contain others, but any missing one of
# these will be rejected.
#
# Label keys must be between 1 and 63 characters long and must conform
# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.
#
# No more than 10 keys can be required.
# @!attribute [rw] labels
# @return [::Google::Protobuf::Map{::String => ::String}]
# To organize findings, these labels will be added to each finding.
#
# Label keys must be between 1 and 63 characters long and must conform
# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.
#
# Label values must be between 0 and 63 characters long and must conform
# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.
#
# No more than 10 labels can be associated with a given finding.
#
# Examples:
# * `"environment" : "production"`
# * `"pipeline" : "etl"`
# @!attribute [rw] table_options
# @return [::Google::Cloud::Dlp::V2::TableOptions]
# If the container is a table, additional information to make findings
# meaningful such as the columns that are primary keys.
class HybridOptions
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
# @!attribute [rw] key
# @return [::String]
# @!attribute [rw] value
# @return [::String]
class LabelsEntry
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
end
# Row key for identifying a record in BigQuery table.
# @!attribute [rw] table_reference
# @return [::Google::Cloud::Dlp::V2::BigQueryTable]
# Complete BigQuery table reference.
# @!attribute [rw] row_number
# @return [::Integer]
# Row number inferred at the time the table was scanned. This value is
# nondeterministic, cannot be queried, and may be null for inspection
# jobs. To locate findings within a table, specify
# `inspect_job.storage_config.big_query_options.identifying_fields` in
# `CreateDlpJobRequest`.
class BigQueryKey
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Record key for a finding in Cloud Datastore.
# @!attribute [rw] entity_key
# @return [::Google::Cloud::Dlp::V2::Key]
# Datastore entity key.
class DatastoreKey
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# A unique identifier for a Datastore entity.
# If a key's partition ID or any of its path kinds or names are
# reserved/read-only, the key is reserved/read-only.
# A reserved/read-only key is forbidden in certain documented contexts.
# @!attribute [rw] partition_id
# @return [::Google::Cloud::Dlp::V2::PartitionId]
# Entities are partitioned into subsets, currently identified by a project
# ID and namespace ID.
# Queries are scoped to a single partition.
# @!attribute [rw] path
# @return [::Array<::Google::Cloud::Dlp::V2::Key::PathElement>]
# The entity path.
# An entity path consists of one or more elements composed of a kind and a
# string or numerical identifier, which identify entities. The first
# element identifies a _root entity_, the second element identifies
# a _child_ of the root entity, the third element identifies a child of the
# second entity, and so forth. The entities identified by all prefixes of
# the path are called the element's _ancestors_.
#
# A path can never be empty, and a path can have at most 100 elements.
class Key
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
# A (kind, ID/name) pair used to construct a key path.
#
# If either name or ID is set, the element is complete.
# If neither is set, the element is incomplete.
# @!attribute [rw] kind
# @return [::String]
# The kind of the entity.
# A kind matching regex `__.*__` is reserved/read-only.
# A kind must not contain more than 1500 bytes when UTF-8 encoded.
# Cannot be `""`.
# @!attribute [rw] id
# @return [::Integer]
# The auto-allocated ID of the entity.
# Never equal to zero. Values less than zero are discouraged and may not
# be supported in the future.
# @!attribute [rw] name
# @return [::String]
# The name of the entity.
# A name matching regex `__.*__` is reserved/read-only.
# A name must not be more than 1500 bytes when UTF-8 encoded.
# Cannot be `""`.
class PathElement
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
end
# Message for a unique key indicating a record that contains a finding.
# @!attribute [rw] datastore_key
# @return [::Google::Cloud::Dlp::V2::DatastoreKey]
# BigQuery key
# @!attribute [rw] big_query_key
# @return [::Google::Cloud::Dlp::V2::BigQueryKey]
# Datastore key
# @!attribute [rw] id_values
# @return [::Array<::String>]
# Values of identifying columns in the given row. Order of values matches
# the order of `identifying_fields` specified in the scanning request.
class RecordKey
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Message defining the location of a BigQuery table. A table is uniquely
# identified by its project_id, dataset_id, and table_name. Within a query
# a table is often referenced with a string in the format of:
# `<project_id>:<dataset_id>.<table_id>` or
# `<project_id>.<dataset_id>.<table_id>`.
# @!attribute [rw] project_id
# @return [::String]
# The Google Cloud Platform project ID of the project containing the table.
# If omitted, project ID is inferred from the API call.
# @!attribute [rw] dataset_id
# @return [::String]
# Dataset ID of the table.
# @!attribute [rw] table_id
# @return [::String]
# Name of the table.
class BigQueryTable
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Message defining the location of a BigQuery table with the projectId inferred
# from the parent project.
# @!attribute [rw] dataset_id
# @return [::String]
# Dataset ID of the table.
# @!attribute [rw] table_id
# @return [::String]
# Name of the table.
class TableReference
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Message defining a field of a BigQuery table.
# @!attribute [rw] table
# @return [::Google::Cloud::Dlp::V2::BigQueryTable]
# Source table of the field.
# @!attribute [rw] field
# @return [::Google::Cloud::Dlp::V2::FieldId]
# Designated field in the BigQuery table.
class BigQueryField
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# An entity in a dataset is a field or set of fields that correspond to a
# single person. For example, in medical records the `EntityId` might be a
# patient identifier, or for financial records it might be an account
# identifier. This message is used when generalizations or analysis must take
# into account that multiple rows correspond to the same entity.
# @!attribute [rw] field
# @return [::Google::Cloud::Dlp::V2::FieldId]
# Composite key indicating which field contains the entity identifier.
class EntityId
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Instructions regarding the table content being inspected.
# @!attribute [rw] identifying_fields
# @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
# The columns that are the primary keys for table objects included in
# ContentItem. A copy of this cell's value will stored alongside alongside
# each finding so that the finding can be traced to the specific row it came
# from. No more than 3 may be provided.
class TableOptions
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Coarse-grained confidence level of how well a particular finding
# satisfies the criteria to match a particular infoType.
#
# Likelihood is calculated based on the number of signals a
# finding has that implies that the finding matches the infoType. For
# example, a string that has an '@' and a '.com' is more likely to be a
# match for an email address than a string that only has an '@'.
#
# In general, the highest likelihood level has the strongest signals that
# indicate a match. That is, a finding with a high likelihood has a low chance
# of being a false positive.
#
# For more information about each likelihood level
# and how likelihood works, see [Match
# likelihood](https://cloud.google.com/sensitive-data-protection/docs/likelihood).
module Likelihood
# Default value; same as POSSIBLE.
LIKELIHOOD_UNSPECIFIED = 0
# Highest chance of a false positive.
VERY_UNLIKELY = 1
# High chance of a false positive.
UNLIKELY = 2
# Some matching signals. The default value.
POSSIBLE = 3
# Low chance of a false positive.
LIKELY = 4
# Confidence level is high. Lowest chance of a false positive.
VERY_LIKELY = 5
end
# Definitions of file type groups to scan. New types will be added to this
# list.
module FileType
# Includes all files.
FILE_TYPE_UNSPECIFIED = 0
# Includes all file extensions not covered by another entry. Binary
# scanning attempts to convert the content of the file to utf_8 to scan
# the file.
# If you wish to avoid this fall back, specify one or more of the other
# file types in your storage scan.
BINARY_FILE = 1
# Included file extensions:
# asc,asp, aspx, brf, c, cc,cfm, cgi, cpp, csv, cxx, c++, cs, css, dart,
# dat, dot, eml,, epbub, ged, go, h, hh, hpp, hxx, h++, hs, html, htm,
# mkd, markdown, m, ml, mli, perl, pl, plist, pm, php, phtml, pht,
# properties, py, pyw, rb, rbw, rs, rss, rc, scala, sh, sql, swift, tex,
# shtml, shtm, xhtml, lhs, ics, ini, java, js, json, jsonl, kix, kml,
# ocaml, md, txt, text, tsv, vb, vcard, vcs, wml, xcodeproj, xml, xsl, xsd,
# yml, yaml.
TEXT_FILE = 2
# Included file extensions:
# bmp, gif, jpg, jpeg, jpe, png. Setting
# {::Google::Cloud::Dlp::V2::CloudStorageOptions#bytes_limit_per_file bytes_limit_per_file}
# or
# {::Google::Cloud::Dlp::V2::CloudStorageOptions#bytes_limit_per_file bytes_limit_per_file_percent}
# has no effect on image files. Image inspection is restricted to the
# `global`, `us`, `asia`, and `europe` regions.
IMAGE = 3
# Microsoft Word files larger than 30 MB will be scanned as binary files.
# Included file extensions:
# docx, dotx, docm, dotm. Setting `bytes_limit_per_file` or
# `bytes_limit_per_file_percent` has no effect on Word files.
WORD = 5
# PDF files larger than 30 MB will be scanned as binary files.
# Included file extensions:
# pdf. Setting `bytes_limit_per_file` or `bytes_limit_per_file_percent`
# has no effect on PDF files.
PDF = 6
# Included file extensions:
# avro
AVRO = 7
# Included file extensions:
# csv
CSV = 8
# Included file extensions:
# tsv
TSV = 9
# Microsoft PowerPoint files larger than 30 MB will be scanned as binary
# files. Included file extensions:
# pptx, pptm, potx, potm, pot. Setting `bytes_limit_per_file` or
# `bytes_limit_per_file_percent` has no effect on PowerPoint files.
POWERPOINT = 11
# Microsoft Excel files larger than 30 MB will be scanned as binary files.
# Included file extensions:
# xlsx, xlsm, xltx, xltm. Setting `bytes_limit_per_file` or
# `bytes_limit_per_file_percent` has no effect on Excel files.
EXCEL = 12
end
end
end
end
end