feat: new Bytes and File types: POWERPOINT and EXCEL

Google APIs · copybara-github · commit 3c34a4075b81 · 2022-03-25T09:05:54.000-07:00
PiperOrigin-RevId: 437260831
diff --git a/google/privacy/dlp/v2/dlp.proto b/google/privacy/dlp/v2/dlp.proto
@@ -1,4 +1,4 @@
-// Copyright 2021 Google LLC
+// 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.
@@ -16,6 +16,7 @@ syntax = "proto3";
 
 package google.privacy.dlp.v2;
 
+import "google/api/annotations.proto";
 import "google/api/client.proto";
 import "google/api/field_behavior.proto";
 import "google/api/resource.proto";
@@ -28,7 +29,6 @@ import "google/rpc/status.proto";
 import "google/type/date.proto";
 import "google/type/dayofweek.proto";
 import "google/type/timeofday.proto";
-import "google/api/annotations.proto";
 
 option csharp_namespace = "Google.Cloud.Dlp.V2";
 option go_package = "google.golang.org/genproto/googleapis/privacy/dlp/v2;dlp";
@@ -719,8 +719,8 @@ message InspectionRuleSet {
 // When used with redactContent only info_types and min_likelihood are currently
 // used.
 message InspectConfig {
-  // Configuration to control the number of findings returned. Cannot be set if
-  // de-identification is requested.
+  // Configuration to control the number of findings returned for inspection.
+  // This is not used for de-identification or data profiling.
   message FindingLimits {
     // Max findings configuration per infoType, per content item or long
     // running DlpJob.
@@ -769,21 +769,23 @@ message InspectConfig {
   Likelihood min_likelihood = 2;
 
   // Configuration to control the number of findings returned.
+  // This is not used for data profiling.
   FindingLimits limits = 3;
 
   // When true, a contextual quote from the data that triggered a finding is
   // included in the response; see Finding.quote.
+  // This is not used for data profiling.
   bool include_quote = 4;
 
   // When true, excludes type information of the findings.
+  // This is not used for data profiling.
   bool exclude_info_types = 5;
 
   // CustomInfoTypes provided by the user. See
   // https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.
   repeated CustomInfoType custom_info_types = 6;
 
-  // List of options defining data content to scan.
-  // If empty, text, images, and other content will be included.
+  // Deprecated and unused.
   repeated ContentOption content_options = 8;
 
   // Set of rules to apply to the findings for this InspectConfig.
@@ -825,6 +827,12 @@ message ByteContentItem {
     // pdf
     PDF = 8;
 
+    // pptx, pptm, potx, potm, pot
+    POWERPOINT_DOCUMENT = 9;
+
+    // xlsx, xlsm, xltx, xltm
+    EXCEL_DOCUMENT = 10;
+
     // avro
     AVRO = 11;
 
@@ -2857,6 +2865,18 @@ message TransformationOverview {
 // Only one of 'transformation', 'field_transformation', or 'record_suppress'
 // will be set.
 message TransformationSummary {
+  // Possible outcomes of transformations.
+  enum TransformationResultCode {
+    // Unused
+    TRANSFORMATION_RESULT_CODE_UNSPECIFIED = 0;
+
+    // Transformation completed without an error.
+    SUCCESS = 1;
+
+    // Transformation had an error.
+    ERROR = 2;
+  }
+
   // A collection that informs the user the number of times a particular
   // `TransformationResultCode` and error details occurred.
   message SummaryResult {
@@ -2871,18 +2891,6 @@ message TransformationSummary {
     string details = 3;
   }
 
-  // Possible outcomes of transformations.
-  enum TransformationResultCode {
-    // Unused
-    TRANSFORMATION_RESULT_CODE_UNSPECIFIED = 0;
-
-    // Transformation completed without an error.
-    SUCCESS = 1;
-
-    // Transformation had an error.
-    ERROR = 2;
-  }
-
   // Set if the transformation was limited to a specific InfoType.
   InfoType info_type = 1;
 
@@ -4352,7 +4360,7 @@ enum MatchingType {
   MATCHING_TYPE_INVERSE_MATCH = 3;
 }
 
-// Options describing which parts of the provided content should be scanned.
+// Deprecated and unused.
 enum ContentOption {
   // Includes entire content of a file or a data stream.
   CONTENT_UNSPECIFIED = 0;
diff --git a/google/privacy/dlp/v2/storage.proto b/google/privacy/dlp/v2/storage.proto
@@ -1,4 +1,4 @@
-// Copyright 2021 Google LLC
+// 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.
@@ -16,7 +16,6 @@ syntax = "proto3";
 
 package google.privacy.dlp.v2;
 
-import "google/api/annotations.proto";
 import "google/api/resource.proto";
 import "google/protobuf/timestamp.proto";
 
@@ -41,18 +40,6 @@ message InfoType {
   string version = 2;
 }
 
-// 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;
-}
-
 // 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 {
@@ -73,6 +60,18 @@ enum Likelihood {
   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 {
@@ -85,7 +84,7 @@ message CustomInfoType {
   // 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",
-  // Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
+  // "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
@@ -98,7 +97,7 @@ message CustomInfoType {
   // [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
-  // [limits](https://cloud.google.com/dlp/limits) page contains details about
+  // `StoredInfoType` API.
   message Dictionary {
     // Message defining a list of words or phrases to search for in the data.
     message WordList {
@@ -124,7 +123,7 @@ message CustomInfoType {
     // (https://github.com/google/re2/wiki/Syntax) can be found under the
     // google/re2 repository on GitHub.
     string pattern = 1;
-    // (https://github.com/google/re2/wiki/Syntax) can be found under the
+
     // 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;
@@ -135,10 +134,12 @@ message CustomInfoType {
   // [`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
-  // [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).
+  // 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 {}
+  message SurrogateType {
+
+  }
 
   // Deprecated; use `InspectionRuleSet` instead. Rule for modifying a
   // `CustomInfoType` to alter behavior under certain circumstances, depending
@@ -284,6 +285,67 @@ message DatastoreOptions {
   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.
@@ -330,7 +392,7 @@ message CloudStorageRegexFileSet {
   // [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;
-  // [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found
+
   // 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.
@@ -339,7 +401,6 @@ message CloudStorageRegexFileSet {
   // [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;
-  // [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found
 }
 
 // Options defining a file or a set of files within a Google Cloud Storage
@@ -531,57 +592,6 @@ message StorageConfig {
   TimespanConfig timespan_config = 6;
 }
 
-// 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;
-}
-
 // Configuration to control jobs where the content being inspected is outside
 // of Google Cloud Platform.
 message HybridOptions {
