Inspect image for sensitive data with infoTypes

To inspect an image for sensitive data, you submit a base64-encoded image to the Cloud DLP API's content.inspect method. Unless you specify information types (infoTypes) to search for, Cloud DLP searches for the most common infoTypes.

Explore further

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

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 System.IO;
using System.Linq;
using Google.Api.Gax.ResourceNames;
using Google.Cloud.Dlp.V2;
using Google.Protobuf;

public class InspectImageForSensitiveDataWithInfoTypes
{
    public static InspectContentResponse InspectImage(
        string projectId,
        string filePath)
    {
        // Instantiate dlp client.
        var dlp = DlpServiceClient.Create();

        // Construct the content item.
        var contentItem = new ContentItem
        {
            ByteItem = new ByteContentItem
            {
                Type = ByteContentItem.Types.BytesType.ImagePng,
                Data = ByteString.FromStream(new FileStream(filePath, FileMode.Open))
            }
        };

        // Construct the request.
        var request = new InspectContentRequest
        {
            ParentAsLocationName = new LocationName(projectId, "global"),
            Item = contentItem,
            InspectConfig = new InspectConfig
            {
                IncludeQuote = true,
                InfoTypes =
                    {
                        new InfoType { Name = "PHONE_NUMBER" },
                        new InfoType { Name = "EMAIL_ADDRESS" },
                        new InfoType { Name = "PERSON_NAME" }
                    }
            }
        };

        // Call the API.
        var response = dlp.InspectContent(request);

        // Inspect the response.
        var resultFindings = response.Result.Findings;

        Console.WriteLine($"Findings: {resultFindings.Count}\n");

        foreach (var f in resultFindings)
        {
            var data = from location in f.Location.ContentLocations
                       from b in location.ImageLocation.BoundingBoxes
                       select new { b.Height, b.Width, b.Top, b.Left };
            Console.WriteLine("Info type: " + f.InfoType.Name);
            Console.WriteLine("\tImageLocations: " + string.Join(',', data));
            Console.WriteLine("\tQuote: " + f.Quote);
            Console.WriteLine("\tLikelihood: " + f.Likelihood + "\n");
        }

        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"
	"io/ioutil"

	dlp "cloud.google.com/go/dlp/apiv2"
	"cloud.google.com/go/dlp/apiv2/dlppb"
)

// inspectImageFileAllInfoTypes inspects a image for sensitive data with infoTypes
func inspectImageFileAllInfoTypes(w io.Writer, projectID, inputPath string) error {
	// projectId := "your-project-id"
	// inputPath := "your-input-path"

	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()

	// read the image file
	data, err := ioutil.ReadFile(inputPath)
	if err != nil {
		return err
	}

	// Create and send the request.
	req := &dlppb.InspectContentRequest{
		Parent: fmt.Sprintf("projects/%s/locations/global", projectID),
		Item: &dlppb.ContentItem{
			// Specify the content to be inspected.
			DataItem: &dlppb.ContentItem_ByteItem{
				ByteItem: &dlppb.ByteContentItem{
					Type: dlppb.ByteContentItem_IMAGE_JPEG,
					Data: data,
				},
			},
		},
	}

	// Send the request.
	resp, err := client.InspectContent(ctx, req)
	if err != nil {
		return fmt.Errorf("InspectContent: %w", err)
	}

	// Process the results.
	fmt.Fprintf(w, "Findings: %d\n", len(resp.Result.Findings))
	for _, f := range resp.Result.Findings {
		fmt.Fprintf(w, "\tQuote: %s\n", f.Quote)
		fmt.Fprintf(w, "\tInfo type: %s\n", f.InfoType.Name)
		fmt.Fprintf(w, "\tLikelihood: %s\n", f.Likelihood)
	}
	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.ByteContentItem;
import com.google.privacy.dlp.v2.ByteContentItem.BytesType;
import com.google.privacy.dlp.v2.ContentItem;
import com.google.privacy.dlp.v2.Finding;
import com.google.privacy.dlp.v2.InspectContentRequest;
import com.google.privacy.dlp.v2.InspectContentResponse;
import com.google.privacy.dlp.v2.LocationName;
import com.google.protobuf.ByteString;
import java.io.FileInputStream;
import java.io.IOException;

class InspectImageFileAllInfoTypes {

  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";
    inspectImageFileAllInfoTypes(projectId, inputPath);
  }

  static void inspectImageFileAllInfoTypes(String projectId, String inputPath) 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_JPEG).setData(fileBytes).build();

      // Construct the Inspect request to be sent by the client.
      // Do not specify the type of info to inspect.
      InspectContentRequest request =
          InspectContentRequest.newBuilder()
              .setParent(LocationName.of(projectId, "global").toString())
              .setItem(ContentItem.newBuilder().setByteItem(byteItem).build())
              .build();

      // Use the client to send the API request.
      InspectContentResponse response = dlp.inspectContent(request);

      // Parse the response and process results.
      System.out.println("Findings: " + response.getResult().getFindingsCount());
      for (Finding f : response.getResult().getFindingsList()) {
        System.out.println("\tQuote: " + f.getQuote());
        System.out.println("\tInfo type: " + f.getInfoType().getName());
        System.out.println("\tLikelihood: " + f.getLikelihood());
      }
    }
  }
}

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.

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

// Image Path
// const imagePath = './test.jpeg';

async function inspectImageFileAllType() {
  let fileBytes = null;
  let fileTypeConstant = null;
  try {
    // Load Image
    fileTypeConstant =
      ['image/jpeg', 'image/bmp', 'image/png', 'image/svg'].indexOf(
        mime.getType(imagePath)
      ) + 1;
    fileBytes = Buffer.from(fs.readFileSync(imagePath)).toString('base64');
  } catch (error) {
    console.error(error.message);
    return;
  }
  // Specify the content to be inspected.
  const item = {
    byteItem: {
      type: fileTypeConstant,
      data: fileBytes,
    },
  };

  // Construct the Inspect request to be sent by the client.
  // Do not specify the type of info to inspect.
  const request = {
    parent: `projects/${projectId}/locations/global`,
    item: item,
    inspectConfig: {
      includeQuote: true,
    },
  };

  // Use the client to send the API request.
  const [response] = await dlp.inspectContent(request);

  // Print findings.
  const findings = response.result.findings;
  if (findings.length > 0) {
    console.log(`Findings: ${findings.length}\n`);
    findings.forEach(finding => {
      console.log(`InfoType: ${finding.infoType.name}`);
      console.log(`\tQuote: ${finding.quote}`);
      console.log(`\tLikelihood: ${finding.likelihood} \n`);
    });
  } else {
    console.log('No findings.');
  }
}
inspectImageFileAllType();

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\ByteContentItem;
use Google\Cloud\Dlp\V2\ByteContentItem\BytesType;
use Google\Cloud\Dlp\V2\Client\DlpServiceClient;
use Google\Cloud\Dlp\V2\ContentItem;
use Google\Cloud\Dlp\V2\InspectContentRequest;
use Google\Cloud\Dlp\V2\Likelihood;

/**
 * Inspect image for sensitive data with infoTypes.
 * To inspect an image for sensitive data, you submit a base64-encoded image to the Cloud DLP API's
 * content.inspect method. Unless you specify information types (infoTypes) to search for, Cloud DLP
 * searches for the most common infoTypes.
 *
 * @param string $projectId         The Google Cloud project id to use as a parent resource.
 * @param string $inputPath         The image path to inspect.
 */
function inspect_image_all_infotypes(
    // TODO(developer): Replace sample parameters before running the code.
    string $projectId,
    string $inputPath = './test/data/test.png'
): void {
    // Instantiate a client.
    $dlp = new DlpServiceClient();

    // Get the bytes of the file.
    $fileBytes = (new ByteContentItem())
        ->setType(BytesType::IMAGE_PNG)
        ->setData(file_get_contents($inputPath));

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

    // Specify what content you want the service to Inspect.
    $item = (new ContentItem())
        ->setByteItem($fileBytes);

    // Run request.
    $inspectContentRequest = (new InspectContentRequest())
        ->setParent($parent)
        ->setItem($item);
    $response = $dlp->inspectContent($inspectContentRequest);

    // Print the results.
    $findings = $response->getResult()->getFindings();
    if (count($findings) == 0) {
        printf('No findings.' . PHP_EOL);
    } else {
        printf('Findings:' . PHP_EOL);
        foreach ($findings as $finding) {
            printf('  Info type: %s' . PHP_EOL, $finding->getInfoType()->getName());
            printf('  Likelihood: %s' . PHP_EOL, Likelihood::name($finding->getLikelihood()));
        }
    }
}

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 inspect_image_file_all_infotypes(
    project: str,
    filename: str,
    include_quote: bool = True,
) -> None:
    """Uses the Data Loss Prevention API to analyze strings for protected data in image file.
    Args:
        project: The Google Cloud project id to use as a parent resource.
        filename: The path to the file to inspect.
        include_quote: Boolean for whether to display a quote of the detected
            information in the results.

    Returns:
        None; the response from the API is printed to the terminal.
    """

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

    # Construct the byte_item, containing the image 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.inspect_content(
        request={
            "parent": parent,
            "inspect_config": {"include_quote": include_quote},
            "item": {"byte_item": byte_item},
        }
    )

    # Print out the results.
    print("Findings: ", response.result.findings.count)
    if response.result.findings:
        for finding in response.result.findings:
            print(f"Quote: {finding.quote}")
            print(f"Info type: {finding.info_type.name}")
            print(f"Likelihood: {finding.likelihood}")
    else:
        print("No findings.")

What's next

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