// Copyright 2022 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
//
//     http://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.

syntax = "proto3";

package google.privacy.dlp.v2;

import "google/api/resource.proto";
import "google/protobuf/timestamp.proto";

option csharp_namespace = "Google.Cloud.Dlp.V2";
option go_package = "google.golang.org/genproto/googleapis/privacy/dlp/v2;dlp";
option java_multiple_files = true;
option java_outer_classname = "DlpStorage";
option java_package = "com.google.privacy.dlp.v2";
option php_namespace = "Google\\Cloud\\Dlp\\V2";
option ruby_package = "Google::Cloud::Dlp::V2";

// Type of information detected by the API.
message InfoType {
  // 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.  When sending Cloud DLP results to Data Catalog, infoType
  // names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.
  string name = 1;

  // Optional version name for this InfoType.
  string version = 2;
}

// Score is a summary of all elements in the data profile.
// A higher number means more sensitive.
message SensitivityScore {
  // Various score levels for resources.
  enum SensitivityScoreLevel {
    // Unused.
    SENSITIVITY_SCORE_UNSPECIFIED = 0;

    // No sensitive information detected. Limited access.
    SENSITIVITY_LOW = 10;

    // Medium risk - PII, potentially sensitive data, or fields with free-text
    // data that are at higher risk of having intermittent sensitive data.
    // Consider limiting access.
    SENSITIVITY_MODERATE = 20;

    // High risk – SPII may be present. Exfiltration of data may lead to user
    // data loss. Re-identification of users may be possible. Consider limiting
    // usage and or removing SPII.
    SENSITIVITY_HIGH = 30;
  }

  // The score applied to the resource.
  SensitivityScoreLevel score = 1;
}

// Categorization of results based on how likely they are to represent a match,
// based on the number of elements they contain which imply a match.
enum Likelihood {
  // Default value; same as POSSIBLE.
  LIKELIHOOD_UNSPECIFIED = 0;

  // Few matching elements.
  VERY_UNLIKELY = 1;

  UNLIKELY = 2;

  // Some matching elements.
  POSSIBLE = 3;

  LIKELY = 4;

  // Many matching elements.
  VERY_LIKELY = 5;
}

// A reference to a StoredInfoType to use with scanning.
message StoredType {
  // Resource name of the requested `StoredInfoType`, for example
  // `organizations/433245324/storedInfoTypes/432452342` or
  // `projects/project-id/storedInfoTypes/432452342`.
  string name = 1;

  // Timestamp indicating when the version of the `StoredInfoType` used for
  // inspection was created. Output-only field, populated by the system.
  google.protobuf.Timestamp create_time = 2;
}

// Custom information type provided by the user. Used to find domain-specific
// sensitive information configurable to the data in question.
message CustomInfoType {
  // 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/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.
  message Dictionary {
    // Message defining a list of words or phrases to search for in the data.
    message WordList {
      // 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]
      repeated string words = 1;
    }

    oneof source {
      // List of words or phrases to search for.
      WordList word_list = 1;

      // Newline-delimited file of words in Cloud Storage. Only a single file
      // is accepted.
      CloudStoragePath cloud_storage_path = 3;
    }
  }

  // Message defining a custom regular expression.
  message Regex {
    // Pattern defining the regular expression. Its syntax
    // (https://github.com/google/re2/wiki/Syntax) can be found under the
    // google/re2 repository on GitHub.
    string pattern = 1;

    // The index of the submatch to extract as findings. When not
    // specified, the entire match is returned. No more than 3 may be included.
    repeated int32 group_indexes = 2;
  }

  // Message for detecting output from deidentification transformations
  // such as
  // [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/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`.
  message SurrogateType {

  }

  // 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.
  message DetectionRule {
    // Message for specifying a window around a finding to apply a detection
    // rule.
    message Proximity {
      // 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/dlp/docs/creating-custom-infotypes-likelihood#match-column-values).
      int32 window_before = 1;

      // Number of characters after the finding to consider.
      int32 window_after = 2;
    }

    // Message for specifying an adjustment to the likelihood of a finding as
    // part of a detection rule.
    message LikelihoodAdjustment {
      oneof adjustment {
        // Set the likelihood of a finding to a fixed value.
        Likelihood fixed_likelihood = 1;

        // 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`.
        int32 relative_likelihood = 2;
      }
    }

    // The rule that adjusts the likelihood of findings within a certain
    // proximity of hotwords.
    message HotwordRule {
      // Regular expression pattern defining what qualifies as a hotword.
      Regex hotword_regex = 1;

      // 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/dlp/docs/creating-custom-infotypes-likelihood#match-column-values).
      Proximity proximity = 2;

      // Likelihood adjustment to apply to all matching findings.
      LikelihoodAdjustment likelihood_adjustment = 3;
    }

    oneof type {
      // Hotword-based detection rule.
      HotwordRule hotword_rule = 1;
    }
  }

  enum 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;
  }

  // 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.
  InfoType info_type = 1;

  // 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.
  Likelihood likelihood = 6;

  oneof type {
    // A list of phrases to detect as a CustomInfoType.
    Dictionary dictionary = 2;

    // Regular expression based CustomInfoType.
    Regex regex = 3;

    // Message for detecting output from deidentification transformations that
    // support reversing.
    SurrogateType surrogate_type = 4;

    // Load an existing `StoredInfoType` resource for use in
    // `InspectDataSource`. Not currently supported in `InspectContent`.
    StoredType stored_type = 5;
  }

  // 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.
  repeated DetectionRule detection_rules = 7;

  // If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding
  // to be returned. It still can be used for rules matching.
  ExclusionType exclusion_type = 8;
}

// General identifier of a data field in a storage service.
message FieldId {
  // Name describing the field.
  string name = 1;
}

// 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.
message PartitionId {
  // The ID of the project to which the entities belong.
  string project_id = 2;

  // If not empty, the ID of the namespace to which the entities belong.
  string namespace_id = 4;
}

// A representation of a Datastore kind.
message KindExpression {
  // The name of the kind.
  string name = 1;
}

// Options defining a data set within Google Cloud Datastore.
message DatastoreOptions {
  // A partition ID identifies a grouping of entities. The grouping is always
  // by project and namespace, however the namespace ID may be empty.
  PartitionId partition_id = 1;

  // The kind to process.
  KindExpression kind = 2;
}

// Definitions of file type groups to scan. New types will be added to this
// list.
enum 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
  // FileType's 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, 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.
  // bytes_limit_per_file has no effect on image files.
  // Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
  IMAGE = 3;

  // Word files >30 MB will be scanned as binary files.
  // Included file extensions:
  //   docx, dotx, docm, dotm
  WORD = 5;

  // PDF files >30 MB will be scanned as binary files.
  // Included file extensions:
  //   pdf
  PDF = 6;

  // Included file extensions:
  //   avro
  AVRO = 7;

  // Included file extensions:
  //   csv
  CSV = 8;

  // Included file extensions:
  //   tsv
  TSV = 9;

  // Powerpoint files >30 MB will be scanned as binary files.
  // Included file extensions:
  //   pptx, pptm, potx, potm, pot
  POWERPOINT = 11;

  // Excel files >30 MB will be scanned as binary files.
  // Included file extensions:
  //   xlsx, xlsm, xltx, xltm
  EXCEL = 12;
}

// 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 `/`
message CloudStorageRegexFileSet {
  // The name of a Cloud Storage bucket. Required.
  string bucket_name = 1;

  // 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.
  repeated string include_regex = 2;

  // 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.
  repeated string exclude_regex = 3;
}

// Options defining a file or a set of files within a Cloud Storage
// bucket.
message CloudStorageOptions {
  // Set of files to scan.
  message FileSet {
    // 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.
    string url = 1;

    // The regex-filtered set of files to scan. Exactly one of `url` or
    // `regex_file_set` must be set.
    CloudStorageRegexFileSet regex_file_set = 2;
  }

  // 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.
  enum SampleMethod {
    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;
  }

  // The set of one or more files to scan.
  FileSet file_set = 1;

  // 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.
  // Cannot be set if de-identification is requested.
  int64 bytes_limit_per_file = 4;

  // 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.
  // Cannot be set if de-identification is requested.
  int32 bytes_limit_per_file_percent = 8;

  // 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'.
  repeated FileType file_types = 5;

  SampleMethod sample_method = 6;

  // 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.
  int32 files_limit_percent = 7;
}

// Message representing a set of files in Cloud Storage.
message CloudStorageFileSet {
  // The url, in the format `gs://<bucket>/<path>`. Trailing wildcard in the
  // path is allowed.
  string url = 1;
}

// Message representing a single file or path in Cloud Storage.
message CloudStoragePath {
  // A url representing a file or path (no wildcards) in Cloud Storage.
  // Example: gs://[BUCKET_NAME]/dictionary.txt
  string path = 1;
}

// Options defining BigQuery table and row identifiers.
message BigQueryOptions {
  // 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.
  enum SampleMethod {
    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;
  }

  // Complete BigQuery table reference.
  BigQueryTable table_reference = 1;

  // 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.
  repeated FieldId identifying_fields = 2;

  // 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.
  int64 rows_limit = 3;

  // 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.
  int32 rows_limit_percent = 6;

  SampleMethod sample_method = 4;

  // References to fields excluded from scanning. This allows you to skip
  // inspection of entire columns which you know have no findings.
  repeated FieldId excluded_fields = 5;

  // Limit scanning only to these fields.
  repeated FieldId included_fields = 7;
}

// Shared message indicating Cloud storage type.
message StorageConfig {
  // Configuration of the timespan of the items to include in scanning.
  // Currently only supported when inspecting Cloud Storage and BigQuery.
  message TimespanConfig {
    // Exclude files, tables, or rows older than this value.
    // If not set, no lower time limit is applied.
    google.protobuf.Timestamp start_time = 1;

    // Exclude files, tables, or rows newer than this value.
    // If not set, no upper time limit is applied.
    google.protobuf.Timestamp end_time = 2;

    // 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/dlp/docs/known-issues#bq-timespan)
    // related to this operation.
    FieldId timestamp_field = 3;

    // 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.
    bool enable_auto_population_of_timespan_config = 4;
  }

  oneof type {
    // Google Cloud Datastore options.
    DatastoreOptions datastore_options = 2;

    // Cloud Storage options.
    CloudStorageOptions cloud_storage_options = 3;

    // BigQuery options.
    BigQueryOptions big_query_options = 4;

    // Hybrid inspection options.
    HybridOptions hybrid_options = 9;
  }

  TimespanConfig timespan_config = 6;
}

// Configuration to control jobs where the content being inspected is outside
// of Google Cloud Platform.
message HybridOptions {
  // A short description of where the data is coming from. Will be stored once
  // in the job. 256 max length.
  string description = 1;

  // 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.
  repeated string required_finding_label_keys = 2;

  // 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"`
  map<string, string> labels = 3;

  // If the container is a table, additional information to make findings
  // meaningful such as the columns that are primary keys.
  TableOptions table_options = 4;
}

// Row key for identifying a record in BigQuery table.
message BigQueryKey {
  // Complete BigQuery table reference.
  BigQueryTable table_reference = 1;

  // 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`.
  int64 row_number = 2;
}

// Record key for a finding in Cloud Datastore.
message DatastoreKey {
  // Datastore entity key.
  Key entity_key = 1;
}

// 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.
message Key {
  // 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.
  message PathElement {
    // 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 `""`.
    string kind = 1;

    // The type of ID.
    oneof id_type {
      // 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.
      int64 id = 2;

      // 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 `""`.
      string name = 3;
    }
  }

  // Entities are partitioned into subsets, currently identified by a project
  // ID and namespace ID.
  // Queries are scoped to a single partition.
  PartitionId partition_id = 1;

  // 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.
  repeated PathElement path = 2;
}

// Message for a unique key indicating a record that contains a finding.
message RecordKey {
  oneof type {
    DatastoreKey datastore_key = 2;

    BigQueryKey big_query_key = 3;
  }

  // Values of identifying columns in the given row. Order of values matches
  // the order of `identifying_fields` specified in the scanning request.
  repeated string id_values = 5;
}

// 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>`.
message BigQueryTable {
  // The Google Cloud Platform project ID of the project containing the table.
  // If omitted, project ID is inferred from the API call.
  string project_id = 1;

  // Dataset ID of the table.
  string dataset_id = 2;

  // Name of the table.
  string table_id = 3;
}

// Message defining a field of a BigQuery table.
message BigQueryField {
  // Source table of the field.
  BigQueryTable table = 1;

  // Designated field in the BigQuery table.
  FieldId field = 2;
}

// An entity in a dataset is a field or set of fields that correspond to a
// single person. For example, in medical records the `EntityId` might be a
// patient identifier, or for financial records it might be an account
// identifier. This message is used when generalizations or analysis must take
// into account that multiple rows correspond to the same entity.
message EntityId {
  // Composite key indicating which field contains the entity identifier.
  FieldId field = 1;
}

// Instructions regarding the table content being inspected.
message TableOptions {
  // 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.
  repeated FieldId identifying_fields = 1;
}