Add identifying fields to DLP job trigger (#7037) (#5085)

* Add identifying fields to DLP job trigger

* Updated identifyingFields description.

* Removed unused variable and converted tabs to spaces in example file.

* Added DLP identifying fields update test

* Updated bigquery field name description

* Removed changes to terraform.yaml file

Signed-off-by: Modular Magician <[email protected]>

Signed-off-by: Modular Magician <[email protected]>

Author: modular-magician

.changelog/7037.txt

@@ -0,0 +1,3 @@
+```release-note:enhancement
+dlp: Added field 'identifyingFields' to 'bigQueryOptions' for creating DLP jobs.
+```

google-beta/resource_data_loss_prevention_job_trigger.go

@@ -225,6 +225,21 @@ Only for use with external storage. Possible values: ["BASIC_COLUMNS", "GCS_COLU
 														},
 													},
 												},
+												"identifying_fields": {
+													Type:     schema.TypeList,
+													Optional: true,
+													Description: `Specifies the BigQuery fields that will be returned with findings.
+If not specified, no identifying fields will be returned for findings.`,
+													Elem: &schema.Resource{
+														Schema: map[string]*schema.Schema{
+															"name": {
+																Type:        schema.TypeString,
+																Required:    true,
+																Description: `Name of a BigQuery field to be returned with the findings.`,
+															},
+														},
+													},
+												},
 												"rows_limit": {
 													Type:     schema.TypeInt,
 													Optional: true,
@@ -1114,6 +1129,8 @@ func flattenDataLossPreventionJobTriggerInspectJobStorageConfigBigQueryOptions(v
 		flattenDataLossPreventionJobTriggerInspectJobStorageConfigBigQueryOptionsRowsLimitPercent(original["rowsLimitPercent"], d, config)
 	transformed["sample_method"] =
 		flattenDataLossPreventionJobTriggerInspectJobStorageConfigBigQueryOptionsSampleMethod(original["sampleMethod"], d, config)
+	transformed["identifying_fields"] =
+		flattenDataLossPreventionJobTriggerInspectJobStorageConfigBigQueryOptionsIdentifyingFields(original["identifyingFields"], d, config)
 	return []interface{}{transformed}
 }
 func flattenDataLossPreventionJobTriggerInspectJobStorageConfigBigQueryOptionsTableReference(v interface{}, d *schema.ResourceData, config *Config) interface{} {
@@ -1183,6 +1200,28 @@ func flattenDataLossPreventionJobTriggerInspectJobStorageConfigBigQueryOptionsSa
 	return v
 }
 
+func flattenDataLossPreventionJobTriggerInspectJobStorageConfigBigQueryOptionsIdentifyingFields(v interface{}, d *schema.ResourceData, config *Config) interface{} {
+	if v == nil {
+		return v
+	}
+	l := v.([]interface{})
+	transformed := make([]interface{}, 0, len(l))
+	for _, raw := range l {
+		original := raw.(map[string]interface{})
+		if len(original) < 1 {
+			// Do not include empty json objects coming back from the api
+			continue
+		}
+		transformed = append(transformed, map[string]interface{}{
+			"name": flattenDataLossPreventionJobTriggerInspectJobStorageConfigBigQueryOptionsIdentifyingFieldsName(original["name"], d, config),
+		})
+	}
+	return transformed
+}
+func flattenDataLossPreventionJobTriggerInspectJobStorageConfigBigQueryOptionsIdentifyingFieldsName(v interface{}, d *schema.ResourceData, config *Config) interface{} {
+	return v
+}
+
 func flattenDataLossPreventionJobTriggerInspectJobActions(v interface{}, d *schema.ResourceData, config *Config) interface{} {
 	if v == nil {
 		return v
@@ -1758,6 +1797,13 @@ func expandDataLossPreventionJobTriggerInspectJobStorageConfigBigQueryOptions(v
 		transformed["sampleMethod"] = transformedSampleMethod
 	}
 
+	transformedIdentifyingFields, err := expandDataLossPreventionJobTriggerInspectJobStorageConfigBigQueryOptionsIdentifyingFields(original["identifying_fields"], d, config)
+	if err != nil {
+		return nil, err
+	} else if val := reflect.ValueOf(transformedIdentifyingFields); val.IsValid() && !isEmptyValue(val) {
+		transformed["identifyingFields"] = transformedIdentifyingFields
+	}
+
 	return transformed, nil
 }
 
@@ -1818,6 +1864,32 @@ func expandDataLossPreventionJobTriggerInspectJobStorageConfigBigQueryOptionsSam
 	return v, nil
 }
 
+func expandDataLossPreventionJobTriggerInspectJobStorageConfigBigQueryOptionsIdentifyingFields(v interface{}, d TerraformResourceData, config *Config) (interface{}, error) {
+	l := v.([]interface{})
+	req := make([]interface{}, 0, len(l))
+	for _, raw := range l {
+		if raw == nil {
+			continue
+		}
+		original := raw.(map[string]interface{})
+		transformed := make(map[string]interface{})
+
+		transformedName, err := expandDataLossPreventionJobTriggerInspectJobStorageConfigBigQueryOptionsIdentifyingFieldsName(original["name"], d, config)
+		if err != nil {
+			return nil, err
+		} else if val := reflect.ValueOf(transformedName); val.IsValid() && !isEmptyValue(val) {
+			transformed["name"] = transformedName
+		}
+
+		req = append(req, transformed)
+	}
+	return req, nil
+}
+
+func expandDataLossPreventionJobTriggerInspectJobStorageConfigBigQueryOptionsIdentifyingFieldsName(v interface{}, d TerraformResourceData, config *Config) (interface{}, error) {
+	return v, nil
+}
+
 func expandDataLossPreventionJobTriggerInspectJobActions(v interface{}, d TerraformResourceData, config *Config) (interface{}, error) {
 	l := v.([]interface{})
 	req := make([]interface{}, 0, len(l))

google-beta/resource_data_loss_prevention_job_trigger_test.go

@@ -41,6 +41,41 @@ func TestAccDataLossPreventionJobTrigger_dlpJobTriggerUpdateExample(t *testing.T
 	})
 }
 
+func TestAccDataLossPreventionJobTrigger_dlpJobTriggerUpdateExample2(t *testing.T) {
+	t.Parallel()
+
+	context := map[string]interface{}{
+		"project":       getTestProjectFromEnv(),
+		"random_suffix": randString(t, 10),
+	}
+
+	vcrTest(t, resource.TestCase{
+		PreCheck:     func() { testAccPreCheck(t) },
+		Providers:    testAccProviders,
+		CheckDestroy: testAccCheckDataLossPreventionJobTriggerDestroyProducer(t),
+		Steps: []resource.TestStep{
+			{
+				Config: testAccDataLossPreventionJobTrigger_dlpJobTriggerIdentifyingFields(context),
+			},
+			{
+				ResourceName:            "google_data_loss_prevention_job_trigger.identifying_fields",
+				ImportState:             true,
+				ImportStateVerify:       true,
+				ImportStateVerifyIgnore: []string{"parent"},
+			},
+			{
+				Config: testAccDataLossPreventionJobTrigger_dlpJobTriggerIdentifyingFieldsUpdate(context),
+			},
+			{
+				ResourceName:            "google_data_loss_prevention_job_trigger.identifying_fields_update",
+				ImportState:             true,
+				ImportStateVerify:       true,
+				ImportStateVerifyIgnore: []string{"parent"},
+			},
+		},
+	})
+}
+
 func TestAccDataLossPreventionJobTrigger_dlpJobTriggerPubsub(t *testing.T) {
 	t.Parallel()
 
@@ -103,6 +138,50 @@ resource "google_data_loss_prevention_job_trigger" "basic" {
 `, context)
 }
 
+func testAccDataLossPreventionJobTrigger_dlpJobTriggerIdentifyingFields(context map[string]interface{}) string {
+	return Nprintf(`
+resource "google_data_loss_prevention_job_trigger" "identifying_fields" {
+	parent = "projects/%{project}"
+	description = "Starting description"
+	display_name = "display"
+
+	triggers {
+		schedule {
+			recurrence_period_duration = "86400s"
+		}
+	}
+
+	inspect_job {
+		inspect_template_name = "fake"
+		actions {
+			save_findings {
+				output_config {
+					table {
+						project_id = "project"
+						dataset_id = "dataset123"
+					}
+				}
+			}
+		}
+		storage_config {
+			big_query_options {
+				table_reference {
+					project_id = "project"
+					dataset_id = "dataset"
+					table_id = "table_to_scan"
+				}
+				rows_limit = 1000
+				sample_method = "RANDOM_START"
+				identifying_fields {
+					name = "field"
+				}
+			}
+		}
+	}
+}
+`, context)
+}
+
 func testAccDataLossPreventionJobTrigger_dlpJobTriggerUpdate(context map[string]interface{}) string {
 	return Nprintf(`
 resource "google_data_loss_prevention_job_trigger" "basic" {
@@ -140,6 +219,50 @@ resource "google_data_loss_prevention_job_trigger" "basic" {
 `, context)
 }
 
+func testAccDataLossPreventionJobTrigger_dlpJobTriggerIdentifyingFieldsUpdate(context map[string]interface{}) string {
+	return Nprintf(`
+resource "google_data_loss_prevention_job_trigger" "identifying_fields_update" {
+	parent = "projects/%{project}"
+	description = "An updated description"
+	display_name = "Different"
+
+	triggers {
+		schedule {
+			recurrence_period_duration = "86400s"
+		}
+	}
+
+	inspect_job {
+		inspect_template_name = "fake"
+		actions {
+			save_findings {
+				output_config {
+					table {
+						project_id = "project"
+						dataset_id = "dataset123"
+					}
+				}
+			}
+		}
+		storage_config {
+			big_query_options {
+				table_reference {
+					project_id = "project"
+					dataset_id = "dataset"
+					table_id = "table_to_scan"
+				}
+				rows_limit = 1000
+				sample_method = "RANDOM_START"
+				identifying_fields {
+					name = "different"
+				}
+			}
+		}
+	}
+}
+`, context)
+}
+
 func testAccDataLossPreventionJobTrigger_publishToPubSub(context map[string]interface{}) string {
 	return Nprintf(`
 resource "google_data_loss_prevention_job_trigger" "pubsub" {

website/docs/r/data_loss_prevention_job_trigger.html.markdown

@@ -406,6 +406,12 @@ The following arguments are supported:
   Default value is `TOP`.
   Possible values are `TOP` and `RANDOM_START`.
 
+* `identifying_fields` -
+  (Optional)
+  Specifies the BigQuery fields that will be returned with findings.
+  If not specified, no identifying fields will be returned for findings.
+  Structure is [documented below](#nested_identifying_fields).
+
 
 <a name="nested_table_reference"></a>The `table_reference` block supports:
 
@@ -421,6 +427,12 @@ The following arguments are supported:
   (Required)
   The name of the table.
 
+<a name="nested_identifying_fields"></a>The `identifying_fields` block supports:
+
+* `name` -
+  (Required)
+  Name of a BigQuery field to be returned with the findings.
+
 <a name="nested_actions"></a>The `actions` block supports:
 
 * `save_findings` -