Synchronize new proto/yaml changes.

PiperOrigin-RevId: 194299451

google/privacy/dlp/v2/dlp.proto

@@ -863,6 +863,18 @@ message PrivacyMetric {
     // supported so long as they are not structs themselves or nested within
     // a repeated field.
     repeated FieldId quasi_ids = 1;
+
+    // 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 distict 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.
+    EntityId entity_id = 2;
   }
 
   // l-diversity metric, used for analysis of reidentification risk.
@@ -1933,7 +1945,9 @@ message JobTrigger {
 // A task to execute on the completion of a job.
 message Action {
   // If set, the detailed findings will be persisted to the specified
-  // OutputStorageConfig. Compatible with: Inspect
+  // OutputStorageConfig. Only a single instance of this action can be
+  // specified.
+  // Compatible with: Inspect
   message SaveFindings {
     OutputStorageConfig output_config = 1;
   }
@@ -1948,12 +1962,29 @@ message Action {
     string topic = 1;
   }
 
+  // Publish the result summary of a DlpJob to the Cloud Security
+  // 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
+  message PublishSummaryToCscc {
+
+  }
+
   oneof action {
     // Save resulting findings in a provided location.
     SaveFindings save_findings = 1;
 
     // Publish a notification to a pubsub topic.
     PublishToPubSub pub_sub = 2;
+
+    // Publish summary to Cloud Security Command Center (Alpha).
+    PublishSummaryToCscc publish_summary_to_cscc = 3;
   }
 }
 

google/privacy/dlp/v2/storage.proto

@@ -67,6 +67,10 @@ message CustomInfoType {
     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;
     }
   }
 
@@ -231,6 +235,13 @@ message CloudStorageOptions {
   repeated FileType file_types = 5;
 }
 
+// Message representing a 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 {
   // Complete BigQuery table reference.
@@ -239,6 +250,11 @@ message BigQueryOptions {
   // References to fields uniquely identifying rows within the table.
   // Nested fields in the format, like `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. Cannot be used in conjunction with TimespanConfig.
+  int64 rows_limit = 3;
 }
 
 // Shared message indicating Cloud storage type.
@@ -373,6 +389,16 @@ message BigQueryTable {
   string table_id = 3;
 }
 
+// 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;
+}
+
 // 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 {
@@ -398,14 +424,14 @@ enum FileType {
   // Includes all files.
   FILE_TYPE_UNSPECIFIED = 0;
 
-  // Includes all file extensions not covered by other types.
+  // Includes all file extensions not covered by text file types.
   BINARY_FILE = 1;
 
   // Included file extensions:
-  //   c, cc, cpp, cxx, c++, cs, css, dart, eml, go, h, hh, hpp, hxx, h++, hs,
-  //   html, htm, shtml, shtm, xhtml, lhs, ini, java, js, json, ocaml, md, mkd,
-  //   markdown, m, ml, mli, pl, pm, php, phtml, pht, py, pyw, rb, rbw, rs, rc,
-  //   scala, sh, sql, tex, txt, asc, text, brf, vcard, vcs, wml, xml, xsl, xsd,
-  //   yml, yaml.
+  //   asc, brf, c, cc, cpp, csv, cxx, c++, cs, css, dart, eml, go, h, hh, hpp,
+  //   hxx, h++, hs, html, htm, shtml, shtm, xhtml, lhs, ini, java, js, json,
+  //   ocaml, md, mkd, markdown, m, ml, mli, pl, pm, php, phtml, pht, py, pyw,
+  //   rb, rbw, rs, rc, scala, sh, sql, tex, txt, text, tsv, vcard, vcs, wml,
+  //   xml, xsl, xsd, yml, yaml.
   TEXT_FILE = 2;
 }