Redact all detected text in an image

Redact all detected text in an image.

Documentation pages that include this code sample

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

Code sample

Java

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

class RedactImageFileAllText {

  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/sensitive-data-image.jpeg";
    String outputPath = "sensitive-data-image-redacted.jpeg";
    redactImageFileAllText(projectId, inputPath, outputPath);
  }

  static void redactImageFileAllText(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();

      // Enable redaction of all text.
      ImageRedactionConfig imageRedactionConfig =
          ImageRedactionConfig.newBuilder().setRedactAllText(true).build();

      // Construct the Redact request to be sent by the client.
      // Do not specify the type of info to redact.
      RedactImageRequest request =
          RedactImageRequest.newBuilder()
              .setParent(LocationName.of(projectId, "global").toString())
              .setByteItem(byteItem)
              .addImageRedactionConfigs(imageRedactionConfig)
              .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);
    }
  }
}

Python

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



def redact_image_all_text(
    project, filename, output_filename,
):
    """Uses the Data Loss Prevention API to redact all text 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.

    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()

    # Construct the image_redaction_configs, indicating to DLP that all text in
    # the input image should be redacted.
    image_redaction_configs = [{"redact_all_text": True}]

    # Construct the byte_item, containing the file's byte data.
    with open(filename, mode="rb") as f:
        byte_item = {"type_": google.cloud.dlp_v2.FileType.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,
            "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.