Cloud Data Loss Prevention (Cloud DLP) is now a part of Sensitive Data Protection. The API name remains the same: Cloud Data Loss Prevention API (DLP API). For information about the services that make up Sensitive Data Protection, see Sensitive Data Protection overview.

Update a stored infoType

This sample demonstrates how to update the source term list of a stored infoType and rebuild the dictionary.

Explore further

For detailed documentation that includes this code sample, see the following:

Create a large custom dictionary detector

Code sample

C#

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries.

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.


using System;
using Google.Cloud.Dlp.V2;
using Google.Protobuf.WellKnownTypes;

public class UpdateStoredInfoTypes
{
    public static StoredInfoType Update(
        string gcsFileUri,
        string storedInfoTypePath,
        string outputPath)
    {
        // Instantiate the client.
        var dlp = DlpServiceClient.Create();

        // Construct the stored infotype config. Here, we will change the source from bigquery table to GCS file.
        var storedConfig = new StoredInfoTypeConfig
        {
            LargeCustomDictionary = new LargeCustomDictionaryConfig
            {
                CloudStorageFileSet = new CloudStorageFileSet
                {
                    Url = gcsFileUri
                },
                OutputPath = new CloudStoragePath
                {
                    Path = outputPath
                }
            }
        };

        // Construct the request using the stored config by specifying the update mask object
        // which represent the path of field to be updated.
        var request = new UpdateStoredInfoTypeRequest
        {
            Config = storedConfig,
            Name = storedInfoTypePath,
            UpdateMask = new FieldMask
            {
                Paths =
                {
                    "large_custom_dictionary.cloud_storage_file_set.url"
                }
            }
        };

        // Call the API.
        StoredInfoType response = dlp.UpdateStoredInfoType(request);

        // Inspect the result.
        Console.WriteLine(response);
        return response;
    }
}

Go

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries.

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import (
	"context"
	"fmt"
	"io"

	dlp "cloud.google.com/go/dlp/apiv2"
	"cloud.google.com/go/dlp/apiv2/dlppb"
	"google.golang.org/protobuf/types/known/fieldmaskpb"
)

// updateStoredInfoType uses the Data Loss Prevention API to update stored infoType
// detector by changing the source term list from one stored in Bigquery
// to one stored in Cloud Storage.
func updateStoredInfoType(w io.Writer, projectID, gcsUri, fileSetUrl, infoTypeId string) error {
	// projectId := "your-project-id"
	// gcsUri := "gs://" + "your-bucket-name" + "/path/to/your/file.txt"
	// fileSetUrl := "your-cloud-storage-file-set"
	// infoTypeId := "your-stored-info-type-id"

	ctx := context.Background()

	// Initialize a client once and reuse it to send multiple requests. Clients
	// are safe to use across goroutines. When the client is no longer needed,
	// call the Close method to cleanup its resources.
	client, err := dlp.NewClient(ctx)
	if err != nil {
		return err
	}

	// Closing the client safely cleans up background resources.
	defer client.Close()

	// Set path in Cloud Storage.
	cloudStoragePath := &dlppb.CloudStoragePath{
		Path: gcsUri,
	}
	cloudStorageFileSet := &dlppb.CloudStorageFileSet{
		Url: fileSetUrl,
	}

	// Configuration for a custom dictionary created from a data source of any size
	largeCustomDictionaryConfig := &dlppb.LargeCustomDictionaryConfig{
		OutputPath: cloudStoragePath,
		Source: &dlppb.LargeCustomDictionaryConfig_CloudStorageFileSet{
			CloudStorageFileSet: cloudStorageFileSet,
		},
	}

	// Set configuration for stored infoTypes.
	storedInfoTypeConfig := &dlppb.StoredInfoTypeConfig{
		Type: &dlppb.StoredInfoTypeConfig_LargeCustomDictionary{
			LargeCustomDictionary: largeCustomDictionaryConfig,
		},
	}

	// Set mask to control which fields get updated.
	fieldMask := &fieldmaskpb.FieldMask{
		Paths: []string{"large_custom_dictionary.cloud_storage_file_set.url"},
	}
	// Construct the job creation request to be sent by the client.
	req := &dlppb.UpdateStoredInfoTypeRequest{
		Name:       fmt.Sprint("projects/" + projectID + "/storedInfoTypes/" + infoTypeId),
		Config:     storedInfoTypeConfig,
		UpdateMask: fieldMask,
	}

	// Use the client to send the API request.
	resp, err := client.UpdateStoredInfoType(ctx, req)
	if err != nil {
		return err
	}

	// Print the result.
	fmt.Fprintf(w, "output: %v", resp.Name)
	return nil
}

Java

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries.

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.


import com.google.cloud.dlp.v2.DlpServiceClient;
import com.google.privacy.dlp.v2.CloudStorageFileSet;
import com.google.privacy.dlp.v2.CloudStoragePath;
import com.google.privacy.dlp.v2.LargeCustomDictionaryConfig;
import com.google.privacy.dlp.v2.StoredInfoType;
import com.google.privacy.dlp.v2.StoredInfoTypeConfig;
import com.google.privacy.dlp.v2.StoredInfoTypeName;
import com.google.privacy.dlp.v2.UpdateStoredInfoTypeRequest;
import com.google.protobuf.FieldMask;
import java.io.IOException;

public class UpdateStoredInfoType {
  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    // The Google Cloud project id to use as a parent resource.
    String projectId = "your-project-id";
    // The path to file in GCS bucket that holds a collection of words and phrases to be searched by
    // the new infoType detector.
    String filePath = "gs://" + "your-bucket-name" + "/path/to/your/file.txt";
    // The path to the location in a GCS bucket to store the created dictionary.
    String outputPath = "your-cloud-storage-file-set";
    // The name of the stored InfoType which is to be updated.
    String infoTypeId = "your-stored-info-type-id";
    updateStoredInfoType(projectId, filePath, outputPath, infoTypeId);
  }

  // Update the stored info type rebuilding the Custom dictionary.
  public static void updateStoredInfoType(
      String projectId, String filePath, String outputPath, String infoTypeId) throws IOException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (DlpServiceClient dlp = DlpServiceClient.create()) {
      // Set path in Cloud Storage.
      CloudStoragePath cloudStoragePath = CloudStoragePath.newBuilder().setPath(outputPath).build();
      CloudStorageFileSet cloudStorageFileSet =
          CloudStorageFileSet.newBuilder().setUrl(filePath).build();

      // Configuration for a custom dictionary created from a data source of any size
      LargeCustomDictionaryConfig largeCustomDictionaryConfig =
          LargeCustomDictionaryConfig.newBuilder()
              .setOutputPath(cloudStoragePath)
              .setCloudStorageFileSet(cloudStorageFileSet)
              .build();

      // Set configuration for stored infoTypes.
      StoredInfoTypeConfig storedInfoTypeConfig =
          StoredInfoTypeConfig.newBuilder()
              .setLargeCustomDictionary(largeCustomDictionaryConfig)
              .build();

      // Set mask to control which fields get updated.
      // Refer https://protobuf.dev/reference/protobuf/google.protobuf/#field-mask for constructing the field mask paths.
      FieldMask fieldMask =
          FieldMask.newBuilder()
              .addPaths("large_custom_dictionary.cloud_storage_file_set.url")
              .build();

      // Construct the job creation request to be sent by the client.
      UpdateStoredInfoTypeRequest updateStoredInfoTypeRequest =
          UpdateStoredInfoTypeRequest.newBuilder()
              .setName(
                  StoredInfoTypeName.ofProjectStoredInfoTypeName(projectId, infoTypeId).toString())
              .setConfig(storedInfoTypeConfig)
              .setUpdateMask(fieldMask)
              .build();

      // Send the job creation request and process the response.
      StoredInfoType response = dlp.updateStoredInfoType(updateStoredInfoTypeRequest);

      // Print the results.
      System.out.println("Updated stored InfoType successfully: " + response.getName());
    }
  }
}

Node.js

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries.

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

// Import the required libraries
const dlp = require('@google-cloud/dlp');

// Create a DLP client
const dlpClient = new dlp.DlpServiceClient();

// The project ID to run the API call under.
// const projectId = "your-project-id";

// The identifier for the stored infoType
// const infoTypeId = 'github-usernames';

// The path to the location in a Cloud Storage bucket to store the created dictionary
// const outputPath = 'cloud-bucket-path';

// Path of file containing term list
// const cloudStorageFileSet = 'gs://[PATH_TO_GS]';

async function updateStoredInfoType() {
  // Specify configuration of the large custom dictionary including cloudStorageFileSet and outputPath
  const largeCustomDictionaryConfig = {
    outputPath: {
      path: outputPath,
    },
    cloudStorageFileSet: {
      url: fileSetUrl,
    },
  };

  // Construct the job creation request to be sent by the client.
  const updateStoredInfoTypeRequest = {
    name: `projects/${projectId}/storedInfoTypes/${infoTypeId}`,
    config: {
      largeCustomDictionary: largeCustomDictionaryConfig,
    },
    updateMask: {
      paths: ['large_custom_dictionary.cloud_storage_file_set.url'],
    },
  };

  // Send the job creation request and process the response.
  const [response] = await dlpClient.updateStoredInfoType(
    updateStoredInfoTypeRequest
  );

  // Print the results.
  console.log(`InfoType updated successfully: ${JSON.stringify(response)}`);
}
await updateStoredInfoType();

PHP

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries.

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

use Google\Cloud\Dlp\V2\DlpServiceClient;
use Google\Cloud\Dlp\V2\CloudStorageFileSet;
use Google\Cloud\Dlp\V2\CloudStoragePath;
use Google\Cloud\Dlp\V2\LargeCustomDictionaryConfig;
use Google\Cloud\Dlp\V2\StoredInfoTypeConfig;
use Google\Protobuf\FieldMask;

/**
 * Rebuild/Update the stored infoType.
 *
 * @param string $callingProjectId  The Google Cloud Project ID to run the API call under.
 * @param string $gcsPath           The path to file in GCS bucket that holds a collection of words and phrases to be searched by the new infoType detector.
 * @param string $outputgcsPath     The path to the location in a Cloud Storage bucket to store the created dictionary.
 * @param string $storedInfoTypeId  The name of the stored InfoType which is to be updated.
 *
 */
function update_stored_infotype(
    string $callingProjectId,
    string $gcsPath,
    string $outputgcsPath,
    string $storedInfoTypeId
): void {
    // Instantiate a client.
    $dlp = new DlpServiceClient();

    // Set path in Cloud Storage.
    $cloudStorageFileSet = (new CloudStorageFileSet())
        ->setUrl($gcsPath);

    // Configuration for a custom dictionary created from a data source of any size
    $largeCustomDictionaryConfig = (new LargeCustomDictionaryConfig())
        ->setOutputPath((new CloudStoragePath())
            ->setPath($outputgcsPath))
        ->setCloudStorageFileSet($cloudStorageFileSet);

    // Set configuration for stored infoTypes.
    $storedInfoTypeConfig = (new StoredInfoTypeConfig())
        ->setLargeCustomDictionary($largeCustomDictionaryConfig);

    // Send the stored infoType creation request and process the response.

    $name = "projects/$callingProjectId/locations/global/storedInfoTypes/" . $storedInfoTypeId;
    // Set mask to control which fields get updated.
    // Refer https://protobuf.dev/reference/protobuf/google.protobuf/#field-mask for constructing the field mask paths.
    $fieldMask = (new FieldMask())
        ->setPaths([
            'large_custom_dictionary.cloud_storage_file_set.url'
        ]);

    // Run request
    $response = $dlp->updateStoredInfoType($name, [
        'config' => $storedInfoTypeConfig,
        'updateMask' => $fieldMask
    ]);

    // Print results
    printf('Successfully update Stored InforType : %s' . PHP_EOL, $response->getName());
}

Python

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries.

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import google.cloud.dlp


def update_stored_infotype(
    project: str,
    stored_info_type_id: str,
    gcs_input_file_path: str,
    output_bucket_name: str,
) -> None:
    """Uses the Data Loss Prevention API to update stored infoType
    detector by changing the source term list from one stored in Bigquery
    to one stored in Cloud Storage.
    Args:
        project: The Google Cloud project id to use as a parent resource.
        stored_info_type_id: The identifier of stored infoType which is to
            be updated.
        gcs_input_file_path: The url in the format <bucket>/<path_to_file>
            for the location of the source term list.
        output_bucket_name: The name of the bucket in Google Cloud Storage
            where large dictionary is stored.
    """

    # Instantiate a client.
    dlp = google.cloud.dlp_v2.DlpServiceClient()

    # Construct the stored infoType configuration dictionary.
    stored_info_type_config = {
        "large_custom_dictionary": {
            "output_path": {"path": f"gs://{output_bucket_name}"},
            "cloud_storage_file_set": {"url": f"gs://{gcs_input_file_path}"},
        }
    }

    # Set mask to control which fields get updated. For more details, refer
    # https://protobuf.dev/reference/protobuf/google.protobuf/#field-mask
    # for constructing the field mask paths.
    field_mask = {"paths": ["large_custom_dictionary.cloud_storage_file_set.url"]}

    # Convert the stored infoType id into a full resource id.
    stored_info_type_name = (
        f"projects/{project}/locations/global/storedInfoTypes/{stored_info_type_id}"
    )

    # Call the API.
    response = dlp.update_stored_info_type(
        request={
            "name": stored_info_type_name,
            "config": stored_info_type_config,
            "update_mask": field_mask,
        }
    )

    # Print the result
    print(f"Updated stored infoType successfully: {response.name}")

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.