feat: add excluded field field for storage (#169)

feat: add excluded field field for storage

packages/google-privacy-dlp/protos/google/privacy/dlp/v2/dlp.proto

@@ -965,8 +965,9 @@ message OutputStorageConfig {
   // 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,
-  // and no changes will be made to an existing table.
+  // 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.
   OutputSchema output_schema = 3;
 }
 
@@ -1138,7 +1139,7 @@ message PrivacyMetric {
 
     // 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
+    // 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.
@@ -1556,11 +1557,13 @@ message Value {
 message QuoteInfo {
   // Object representation of the quote.
   oneof parsed_quote {
+    // The date time indicated by the quote.
     DateTime date_time = 2;
   }
 }
 
 // Message for a date time object.
+// e.g. 2018-01-01, 5th August.
 message DateTime {
   message TimeZone {
     // Set only if the offset can be determined. Positive for time ahead of UTC.
@@ -2284,7 +2287,7 @@ message JobTrigger {
   repeated Trigger triggers = 5;
 
   // A stream of errors encountered when the trigger was activated. Repeated
-  // errors may result in the JobTrigger automaticaly being paused.
+  // errors may result in the JobTrigger automatically being paused.
   // Will return the last 100 errors. Whenever the JobTrigger is modified
   // this list will be cleared. Output only field.
   repeated Error errors = 6;

packages/google-privacy-dlp/protos/google/privacy/dlp/v2/storage.proto

@@ -33,7 +33,8 @@ 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.
+  // a built-in type. InfoType names should conform to the pattern
+  // [a-zA-Z0-9_]{1,64}.
   string name = 1;
 }
 
@@ -359,7 +360,8 @@ message CloudStorageOptions {
 
   // List of file type groups to include in the scan.
   // If empty, all files are scanned and available data format processors
-  // are applied.
+  // are applied. In addition, the binary content of the selected files
+  // is always scanned as well.
   repeated FileType file_types = 5;
 
   SampleMethod sample_method = 6;
@@ -420,6 +422,10 @@ message BigQueryOptions {
   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;
 }
 
 // Shared message indicating Cloud storage type.

packages/google-privacy-dlp/src/v2/doc/google/privacy/dlp/v2/doc_dlp.js

@@ -905,8 +905,9 @@ const InspectContentResponse = {
  *   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,
- *   and no changes will be made to an existing table.
+ *   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.
  *
  *   The number should be among the values of [OutputSchema]{@link google.privacy.dlp.v2.OutputSchema}
  *
@@ -1287,7 +1288,7 @@ const PrivacyMetric = {
    * @property {Object} entityId
    *   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
+   *   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.
@@ -1954,6 +1955,8 @@ const Value = {
  * Message for infoType-dependent details parsed from quote.
  *
  * @property {Object} dateTime
+ *   The date time indicated by the quote.
+ *
  *   This object should have the same structure as [DateTime]{@link google.privacy.dlp.v2.DateTime}
  *
  * @typedef QuoteInfo
@@ -1966,6 +1969,7 @@ const QuoteInfo = {
 
 /**
  * Message for a date time object.
+ * e.g. 2018-01-01, 5th August.
  *
  * @property {Object} date
  *   One or more of the following must be set. All fields are optional, but
@@ -3090,7 +3094,7 @@ const Error = {
  *
  * @property {Object[]} errors
  *   A stream of errors encountered when the trigger was activated. Repeated
- *   errors may result in the JobTrigger automaticaly being paused.
+ *   errors may result in the JobTrigger automatically being paused.
  *   Will return the last 100 errors. Whenever the JobTrigger is modified
  *   this list will be cleared. Output only field.
  *

packages/google-privacy-dlp/src/v2/doc/google/privacy/dlp/v2/doc_storage.js

@@ -22,7 +22,8 @@
  *   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.
+ *   a built-in type. InfoType names should conform to the pattern
+ *   [a-zA-Z0-9_]{1,64}.
  *
  * @typedef InfoType
  * @memberof google.privacy.dlp.v2
@@ -486,7 +487,8 @@ const CloudStorageRegexFileSet = {
  * @property {number[]} fileTypes
  *   List of file type groups to include in the scan.
  *   If empty, all files are scanned and available data format processors
- *   are applied.
+ *   are applied. In addition, the binary content of the selected files
+ *   is always scanned as well.
  *
  *   The number should be among the values of [FileType]{@link google.privacy.dlp.v2.FileType}
  *
@@ -611,6 +613,12 @@ const CloudStoragePath = {
  * @property {number} sampleMethod
  *   The number should be among the values of [SampleMethod]{@link google.privacy.dlp.v2.SampleMethod}
  *
+ * @property {Object[]} excludedFields
+ *   References to fields excluded from scanning. This allows you to skip
+ *   inspection of entire columns which you know have no findings.
+ *
+ *   This object should have the same structure as [FieldId]{@link google.privacy.dlp.v2.FieldId}
+ *
  * @typedef BigQueryOptions
  * @memberof google.privacy.dlp.v2
  * @see [google.privacy.dlp.v2.BigQueryOptions definition in proto format]{@link https://github.com/googleapis/googleapis/blob/master/google/privacy/dlp/v2/storage.proto}