Redact an image

Demonstrates redacting sensitive data from an image.

Documentation pages that include this code sample

To view the code sample used in context, see the following documentation:

Code sample

Go

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

import (
	"context"
	"fmt"
	"io"
	"io/ioutil"

	dlp "cloud.google.com/go/dlp/apiv2"
	dlppb "google.golang.org/genproto/googleapis/privacy/dlp/v2"
)

// redactImage blacks out the identified portions of the input image (with type bytesType)
// and stores the result in outputPath.
func redactImage(w io.Writer, projectID string, infoTypeNames []string, bytesType dlppb.ByteContentItem_BytesType, inputPath, outputPath string) error {
	// projectID := "my-project-id"
	// infoTypeNames := []string{"US_SOCIAL_SECURITY_NUMBER"}
	// bytesType := dlppb.ByteContentItem_IMAGE_PNG
	// inputPath := /tmp/input
	// outputPath := /tmp/output

	ctx := context.Background()

	client, err := dlp.NewClient(ctx)
	if err != nil {
		return fmt.Errorf("dlp.NewClient: %v", err)
	}
	defer client.Close()

	// Convert the info type strings to a list of InfoTypes.
	var infoTypes []*dlppb.InfoType
	for _, it := range infoTypeNames {
		infoTypes = append(infoTypes, &dlppb.InfoType{Name: it})
	}

	// Convert the info type strings to a list of types to redact in the image.
	var redactInfoTypes []*dlppb.RedactImageRequest_ImageRedactionConfig
	for _, it := range infoTypeNames {
		redactInfoTypes = append(redactInfoTypes, &dlppb.RedactImageRequest_ImageRedactionConfig{
			Target: &dlppb.RedactImageRequest_ImageRedactionConfig_InfoType{
				InfoType: &dlppb.InfoType{Name: it},
			},
		})
	}

	// Read the input file.
	b, err := ioutil.ReadFile(inputPath)
	if err != nil {
		return fmt.Errorf("ioutil.ReadFile: %v", err)
	}

	// Create a configured request.
	req := &dlppb.RedactImageRequest{
		Parent: fmt.Sprintf("projects/%s/locations/global", projectID),
		InspectConfig: &dlppb.InspectConfig{
			InfoTypes:     infoTypes,
			MinLikelihood: dlppb.Likelihood_POSSIBLE,
		},
		// The item to analyze.
		ByteItem: &dlppb.ByteContentItem{
			Type: bytesType,
			Data: b,
		},
		ImageRedactionConfigs: redactInfoTypes,
	}
	// Send the request.
	resp, err := client.RedactImage(ctx, req)
	if err != nil {
		return fmt.Errorf("RedactImage: %v", err)
	}
	// Write the output file.
	if err := ioutil.WriteFile(outputPath, resp.GetRedactedImage(), 0644); err != nil {
		return fmt.Errorf("ioutil.WriteFile: %v", err)
	}
	fmt.Fprintf(w, "Wrote output to %s", outputPath)
	return nil
}

Java

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


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.InfoType;
import com.google.privacy.dlp.v2.InspectConfig;
import com.google.privacy.dlp.v2.Likelihood;
import com.google.privacy.dlp.v2.LocationName;
import com.google.privacy.dlp.v2.RedactImageRequest;
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.ArrayList;
import java.util.List;

class RedactImageFile {

  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";
    redactImageFile(projectId, inputPath, outputPath);
  }

  static void redactImageFile(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 inspected.
      ByteString fileBytes = ByteString.readFrom(new FileInputStream(inputPath));
      ByteContentItem byteItem =
          ByteContentItem.newBuilder().setType(BytesType.IMAGE).setData(fileBytes).build();

      // Specify the type of info and likelihood necessary to redact.
      List<InfoType> infoTypes = new ArrayList<>();
      // See https://cloud.google.com/dlp/docs/infotypes-reference for complete list of info types
      for (String typeName : new String[] {"PHONE_NUMBER", "EMAIL_ADDRESS", "CREDIT_CARD_NUMBER"}) {
        infoTypes.add(InfoType.newBuilder().setName(typeName).build());
      }
      InspectConfig config =
          InspectConfig.newBuilder()
              .addAllInfoTypes(infoTypes)
              .setMinLikelihood(Likelihood.LIKELY)
              .build();

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

Node.js

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

// Imports the Google Cloud Data Loss Prevention library
const DLP = require('@google-cloud/dlp');

// Imports required Node.js libraries
const mime = require('mime');
const fs = require('fs');

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

// The project ID to run the API call under
// const projectId = 'my-project';

// The path to a local file to inspect. Can be a JPG or PNG image file.
// const filepath = 'path/to/image.png';

// The minimum likelihood required before redacting a match
// const minLikelihood = 'LIKELIHOOD_UNSPECIFIED';

// The infoTypes of information to redact
// const infoTypes = [{ name: 'EMAIL_ADDRESS' }, { name: 'PHONE_NUMBER' }];

// The local path to save the resulting image to.
// const outputPath = 'result.png';
async function redactImage() {
  const imageRedactionConfigs = infoTypes.map(infoType => {
    return {infoType: infoType};
  });

  // Load image
  const fileTypeConstant =
    ['image/jpeg', 'image/bmp', 'image/png', 'image/svg'].indexOf(
      mime.getType(filepath)
    ) + 1;
  const fileBytes = Buffer.from(fs.readFileSync(filepath)).toString('base64');

  // Construct image redaction request
  const request = {
    parent: `projects/${projectId}/locations/global`,
    byteItem: {
      type: fileTypeConstant,
      data: fileBytes,
    },
    inspectConfig: {
      minLikelihood: minLikelihood,
      infoTypes: infoTypes,
    },
    imageRedactionConfigs: imageRedactionConfigs,
  };

  // Run image redaction request
  const [response] = await dlp.redactImage(request);
  const image = response.redactedImage;
  fs.writeFileSync(outputPath, image);
  console.log(`Saved image redaction results to path: ${outputPath}`);
}
redactImage();

PHP

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

/**
 * Redact sensitive data from an image.
 */
use Google\Cloud\Dlp\V2\DlpServiceClient;
use Google\Cloud\Dlp\V2\InfoType;
use Google\Cloud\Dlp\V2\InspectConfig;
use Google\Cloud\Dlp\V2\RedactImageRequest\ImageRedactionConfig;
use Google\Cloud\Dlp\V2\Likelihood;
use Google\Cloud\Dlp\V2\ByteContentItem;

/** Uncomment and populate these variables in your code */
// $callingProjectId = 'The project ID to run the API call under';
// $imagePath = 'The local filepath of the image to inspect';
// $outputPath = 'The local filepath to save the resulting image to';

// Instantiate a client.
$dlp = new DlpServiceClient();

// The infoTypes of information to match
$phoneNumberInfoType = (new InfoType())
    ->setName('PHONE_NUMBER');
$infoTypes = [$phoneNumberInfoType];

// The minimum likelihood required before returning a match
$minLikelihood = likelihood::LIKELIHOOD_UNSPECIFIED;

// Whether to include the matching string in the response
$includeQuote = true;

// Create the configuration object
$inspectConfig = (new InspectConfig())
    ->setMinLikelihood($minLikelihood)
    ->setInfoTypes($infoTypes);

// 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);

// Create the image redaction config objects
$imageRedactionConfigs = [];
foreach ($infoTypes as $infoType) {
    $config = (new ImageRedactionConfig())
        ->setInfoType($infoType);
    $imageRedactionConfigs[] = $config;
}

$parent = "projects/$callingProjectId/locations/global";

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

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

// Print completion message
print('Redacted image saved to ' . $outputPath . PHP_EOL);

Python

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

import mimetypes



def redact_image(
    project, filename, output_filename, info_types, min_likelihood=None, mime_type=None,
):
    """Uses the Data Loss Prevention API to redact protected data in an image.
    Args:
        project: The Google Cloud project id to use as a parent resource.
        filename: The path to the file to inspect.
        output_filename: The path to which the redacted image will be written.
        info_types: A list of strings representing info types to look for.
            A full list of info type categories can be fetched from the API.
        min_likelihood: A string representing the minimum likelihood threshold
            that constitutes a match. One of: 'LIKELIHOOD_UNSPECIFIED',
            'VERY_UNLIKELY', 'UNLIKELY', 'POSSIBLE', 'LIKELY', 'VERY_LIKELY'.
        mime_type: The MIME type of the file. If not specified, the type is
            inferred via the Python standard library's mimetypes module.
    Returns:
        None; the response from the API is printed to the terminal.
    """
    # Import the client library
    import google.cloud.dlp

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

    # Prepare info_types by converting the list of strings into a list of
    # dictionaries (protos are also accepted).
    info_types = [{"name": info_type} for info_type in info_types]

    # Prepare image_redaction_configs, a list of dictionaries. Each dictionary
    # contains an info_type and optionally the color used for the replacement.
    # The color is omitted in this sample, so the default (black) will be used.
    image_redaction_configs = []

    if info_types is not None:
        for info_type in info_types:
            image_redaction_configs.append({"info_type": info_type})

    # Construct the configuration dictionary. Keys which are None may
    # optionally be omitted entirely.
    inspect_config = {
        "min_likelihood": min_likelihood,
        "info_types": info_types,
    }

    # If mime_type is not specified, guess it from the filename.
    if mime_type is None:
        mime_guess = mimetypes.MimeTypes().guess_type(filename)
        mime_type = mime_guess[0] or "application/octet-stream"

    # Select the content type index from the list of supported types.
    supported_content_types = {
        None: 0,  # "Unspecified"
        "image/jpeg": 1,
        "image/bmp": 2,
        "image/png": 3,
        "image/svg": 4,
        "text/plain": 5,
    }
    content_type_index = supported_content_types.get(mime_type, 0)

    # Construct the byte_item, containing the file's byte data.
    with open(filename, mode="rb") as f:
        byte_item = {"type_": content_type_index, "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)
    print(
        "Wrote {byte_count} to {filename}".format(
            byte_count=len(response.redacted_image), filename=output_filename
        )
    )

What's next

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