Redact data from an image with color-coded infoTypes

Redacting infoTypes from an image with color coding.

Explore further

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

• Redacting sensitive data from images

Code sample

Java

To learn how to install and use the client library for Cloud DLP, see Cloud DLP client libraries.

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

View on GitHub Feedback

import com.google.cloud.dlp.v2.DlpServiceClient;
import com.google.privacy.dlp.v2.ByteContentItem;
import com.google.privacy.dlp.v2.ByteContentItem.BytesType;
import com.google.privacy.dlp.v2.Color;
import com.google.privacy.dlp.v2.InfoType;
import com.google.privacy.dlp.v2.InspectConfig;
import com.google.privacy.dlp.v2.LocationName;
import com.google.privacy.dlp.v2.RedactImageRequest;
import com.google.privacy.dlp.v2.RedactImageRequest.ImageRedactionConfig;
import com.google.privacy.dlp.v2.RedactImageResponse;
import com.google.protobuf.ByteString;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.util.Arrays;
import java.util.List;
import java.util.stream.Collectors;

class RedactImageFileColoredInfoTypes {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "my-project-id";
    String inputPath = "src/test/resources/test.png";
    String outputPath = "redacted.png";
    redactImageFileColoredInfoTypes(projectId, inputPath, outputPath);
  }

  static void redactImageFileColoredInfoTypes(String projectId, String inputPath, String outputPath)
      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()) {
      // Specify the content to be redacted.
      ByteString fileBytes = ByteString.readFrom(new FileInputStream(inputPath));
      ByteContentItem byteItem =
          ByteContentItem.newBuilder().setType(BytesType.IMAGE_JPEG).setData(fileBytes).build();

      // Define types of info to redact associate each one with a different color.
      // See https://cloud.google.com/dlp/docs/infotypes-reference for complete list of info types
      ImageRedactionConfig ssnRedactionConfig =
          ImageRedactionConfig.newBuilder()
              .setInfoType(InfoType.newBuilder().setName("US_SOCIAL_SECURITY_NUMBER").build())
              .setRedactionColor(Color.newBuilder().setRed(.3f).setGreen(.1f).setBlue(.6f).build())
              .build();
      ImageRedactionConfig emailRedactionConfig =
          ImageRedactionConfig.newBuilder()
              .setInfoType(InfoType.newBuilder().setName("EMAIL_ADDRESS").build())
              .setRedactionColor(Color.newBuilder().setRed(.5f).setGreen(.5f).setBlue(1).build())
              .build();
      ImageRedactionConfig phoneRedactionConfig =
          ImageRedactionConfig.newBuilder()
              .setInfoType(InfoType.newBuilder().setName("PHONE_NUMBER").build())
              .setRedactionColor(Color.newBuilder().setRed(1).setGreen(0).setBlue(.6f).build())
              .build();

      // Create collection of all redact configurations.
      List<ImageRedactionConfig> imageRedactionConfigs =
          Arrays.asList(ssnRedactionConfig, emailRedactionConfig, phoneRedactionConfig);

      // List types of info to search for.
      InspectConfig config =
          InspectConfig.newBuilder()
              .addAllInfoTypes(
                  imageRedactionConfigs.stream()
                      .map(ImageRedactionConfig::getInfoType)
                      .collect(Collectors.toList()))
              .build();

      // Construct the Redact request to be sent by the client.
      RedactImageRequest request =
          RedactImageRequest.newBuilder()
              .setParent(LocationName.of(projectId, "global").toString())
              .setByteItem(byteItem)
              .addAllImageRedactionConfigs(imageRedactionConfigs)
              .setInspectConfig(config)
              .build();

      // Use the client to send the API request.
      RedactImageResponse response = dlp.redactImage(request);

      // Parse the response and process results.
      FileOutputStream redacted = new FileOutputStream(outputPath);
      redacted.write(response.getRedactedImage().toByteArray());
      redacted.close();
      System.out.println("Redacted image written to " + outputPath);
    }
  }
}

PHP

To learn how to install and use the client library for Cloud DLP, see Cloud DLP client libraries.

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

View on GitHub Feedback

use Google\Cloud\Dlp\V2\DlpServiceClient;
use Google\Cloud\Dlp\V2\RedactImageRequest\ImageRedactionConfig;
use Google\Cloud\Dlp\V2\ByteContentItem;
use Google\Cloud\Dlp\V2\Color;
use Google\Cloud\Dlp\V2\InfoType;
use Google\Cloud\Dlp\V2\InspectConfig;

/**
 * Redact data from an image with color-coded infoTypes.
 *
 * @param string $callingProjectId    The project ID to run the API call under.
 * @param string $imagePath           The local filepath of the image to inspect.
 * @param string $outputPath          The local filepath to save the resulting image to.
 */
function redact_image_colored_infotypes(
    // TODO(developer): Replace sample parameters before running the code.
    string $callingProjectId,
    string $imagePath = './test/data/test.png',
    string $outputPath = './test/data/sensitive-data-image-redacted-color-coding.png'
): void {
    // Instantiate a client.
    $dlp = new DlpServiceClient();

    // Read image file into a buffer.
    $imageRef = fopen($imagePath, 'rb');
    $imageBytes = fread($imageRef, filesize($imagePath));
    fclose($imageRef);

    // Get the image's content type.
    $typeConstant = (int) array_search(
        mime_content_type($imagePath),
        [false, 'image/jpeg', 'image/bmp', 'image/png', 'image/svg']
    );

    // Create the byte-storing object.
    $byteContent = (new ByteContentItem())
        ->setType($typeConstant)
        ->setData($imageBytes);

    // Define the types of information to redact and associate each one with a different color.
    $ssnInfotype = (new InfoType())
        ->setName('US_SOCIAL_SECURITY_NUMBER');
    $emailInfotype = (new InfoType())
        ->setName('EMAIL_ADDRESS');
    $phoneInfotype = (new InfoType())
        ->setName('PHONE_NUMBER');
    $infotypes = [$ssnInfotype, $emailInfotype, $phoneInfotype];

    $ssnRedactionConfig = (new ImageRedactionConfig())
        ->setInfoType($ssnInfotype)
        ->setRedactionColor((new Color())
            ->setRed(.3)
            ->setGreen(.1)
            ->setBlue(.6));

    $emailRedactionConfig = (new ImageRedactionConfig())
        ->setInfoType($emailInfotype)
        ->setRedactionColor((new Color())
            ->setRed(.5)
            ->setGreen(.5)
            ->setBlue(1));

    $phoneRedactionConfig = (new ImageRedactionConfig())
        ->setInfoType($phoneInfotype)
        ->setRedactionColor((new Color())
            ->setRed(1)
            ->setGreen(0)
            ->setBlue(.6));

    $imageRedactionConfigs = [$ssnRedactionConfig, $emailRedactionConfig, $phoneRedactionConfig];

    // Create the configuration object.
    $inspectConfig = (new InspectConfig())
        ->setInfoTypes($infotypes);
    $parent = "projects/$callingProjectId/locations/global";

    // Run request.
    $response = $dlp->redactImage([
        'parent' => $parent,
        'byteItem' => $byteContent,
        'inspectConfig' => $inspectConfig,
        'imageRedactionConfigs' => $imageRedactionConfigs
    ]);

    // Save result to file.
    file_put_contents($outputPath, $response->getRedactedImage());

    // Print completion message.
    printf('Redacted image saved to %s ' . PHP_EOL, $outputPath);
}

Python

To learn how to install and use the client library for Cloud DLP, see Cloud DLP client libraries.

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

View on GitHub Feedback

import google.cloud.dlp  # noqa: E402, F811


def redact_image_with_colored_info_types(
    project: str,
    filename: str,
    output_filename: str,
) -> None:
    """Uses the Data Loss Prevention API to redact protected data in an image by
    color coding the infoTypes.
       Args:
           project: The Google Cloud project id to use as a parent resource.
           filename: The path of the image file to inspect.
           output_filename: The path to which the redacted image will be written.
    """

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

    # Prepare image_redaction_configs, a list of dictionaries. Each dictionary
    # contains an infoType and the color used for the replacement.

    ssn_redaction_config = {
        "info_type": {"name": "US_SOCIAL_SECURITY_NUMBER"},
        "redaction_color": {
            "red": 0.3,
            "green": 0.1,
            "blue": 0.6,
        },
    }

    email_redaction_config = {
        "info_type": {"name": "EMAIL_ADDRESS"},
        "redaction_color": {
            "red": 0.5,
            "green": 0.5,
            "blue": 1.0,
        },
    }

    phone_redaction_config = {
        "info_type": {"name": "PHONE_NUMBER"},
        "redaction_color": {
            "red": 1.0,
            "green": 0.0,
            "blue": 0.6,
        },
    }

    image_redaction_configs = [
        ssn_redaction_config,
        email_redaction_config,
        phone_redaction_config,
    ]

    # Construct the configuration dictionary.
    inspect_config = {"info_types": [_i["info_type"] for _i in image_redaction_configs]}

    # Construct the byte_item, containing the file's byte data.
    with open(filename, mode="rb") as f:
        byte_item = {"type_": "IMAGE", "data": f.read()}

    # Convert the project id into a full resource id.
    parent = f"projects/{project}"

    # Call the API.
    response = dlp.redact_image(
        request={
            "parent": parent,
            "inspect_config": inspect_config,
            "image_redaction_configs": image_redaction_configs,
            "byte_item": byte_item,
        }
    )

    # Write out the results.
    with open(output_filename, mode="wb") as f:
        f.write(response.redacted_image)

    byte_count = len(response.redacted_image)
    print(f"Wrote {byte_count} to {output_filename}")

What's next

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