Inspect images for sensitive data

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;
    }
}

import (
	"context"
	"fmt"
	"io"
	"os"

	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 := os.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

}

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());
      }
    }
  }
}

// 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();

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()));
        }
    }
}

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.")

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

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

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

        // Specify the type of info the inspection will look for.
        var infoTypes = new InfoType[]
        {
            new InfoType { Name = "PHONE_NUMBER" },
            new InfoType { Name = "EMAIL_ADDRESS" },
            new InfoType { Name = "US_SOCIAL_SECURITY_NUMBER" }
        };

        // Construct the Inspect config.
        var inspectConfig = new InspectConfig
        {
            InfoTypes = { infoTypes },
            IncludeQuote = true
        };

        // Construct the request.
        var request = new InspectContentRequest
        {
            ParentAsLocationName = new LocationName(projectId, "global"),
            InspectConfig = inspectConfig,
            Item = contentItem
        };

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

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

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

        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("\tQuote: " + f.Quote);
            Console.WriteLine("\tImageLocations: " + string.Join(",", data));
            Console.WriteLine("\tLikelihood: " + f.Likelihood);
        }

        return response;
    }
}

import (
	"context"
	"fmt"
	"io"
	"os"

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

// inspectImageFileListedInfoTypes inspects an image for sensitive data listed infoTypes.
func inspectImageFileListedInfoTypes(w io.Writer, projectID, filePath string) error {
	// projectId := "my-project-id"
	// filePath := "testdata/image.jpg"

	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 a image file
	data, err := os.ReadFile(filePath)
	if err != nil {
		return err
	}

	// Specify the type and content to be inspected.
	item := &dlppb.ContentItem{
		DataItem: &dlppb.ContentItem_ByteItem{
			ByteItem: &dlppb.ByteContentItem{
				Type: dlppb.ByteContentItem_IMAGE_JPEG,
				Data: data,
			},
		},
	}

	// Construct the configuration for the Inspect request.
	inspectConfig := &dlppb.InspectConfig{
		InfoTypes: []*dlppb.InfoType{
			{Name: "PHONE_NUMBER"},
			{Name: "EMAIL_ADDRESS"},
			{Name: "US_SOCIAL_SECURITY_NUMBER"},
		},
		IncludeQuote: true,
	}

	// Construct the Inspect request to be sent by the client.
	req := &dlppb.InspectContentRequest{
		Parent:        fmt.Sprintf("projects/%s/locations/global", projectID),
		Item:          item,
		InspectConfig: inspectConfig,
	}

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

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

class InspectImageFileListedInfoTypes {

  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";
    inspectImageFileListedInfoTypes(projectId, inputPath);
  }

  static void inspectImageFileListedInfoTypes(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();

      // Specify the type of info the inspection will look for.
      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[] {"US_SOCIAL_SECURITY_NUMBER", "EMAIL_ADDRESS", "PHONE_NUMBER"}) {
        infoTypes.add(InfoType.newBuilder().setName(typeName).build());
      }

      // Construct the configuration for the Inspect request.
      InspectConfig inspectConfig = InspectConfig.newBuilder().addAllInfoTypes(infoTypes).build();

      // Construct the Inspect request to be sent by the client.
      InspectContentRequest request =
          InspectContentRequest.newBuilder()
              .setParent(LocationName.of(projectId, "global").toString())
              .setItem(ContentItem.newBuilder().setByteItem(byteItem).build())
              .setInspectConfig(inspectConfig)
              .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());
      }
    }
  }
}

// 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 imagePath = './test.pdf';

// InfoTypes
const infoTypes = [
  {name: 'PHONE_NUMBER'},
  {name: 'EMAIL_ADDRESS'},
  {name: 'US_SOCIAL_SECURITY_NUMBER'},
];

async function inspectImageFileListedInfoTypes() {
  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.log(error);
    return;
  }
  // Specify item to inspect
  const item = {
    byteItem: {
      type: fileTypeConstant,
      data: fileBytes,
    },
  };

  // Specify inspect configuration to match information with mentioned infotypes.
  const inspectConfig = {
    infoTypes: infoTypes,
    includeQuote: true,
  };

  // Combine configurations into a request for the service.
  const request = {
    parent: `projects/${projectId}/locations/global`,
    inspectConfig: inspectConfig,
    item: item,
  };

  // Use the client to send the 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.');
  }
}
inspectImageFileListedInfoTypes();

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\InfoType;
use Google\Cloud\Dlp\V2\InspectConfig;
use Google\Cloud\Dlp\V2\InspectContentRequest;
use Google\Cloud\Dlp\V2\Likelihood;

/**
 * Inspect an image for sensitive data with listed infoTypes.
 * If you want to inspect an image for only certain sensitive data types, specify their corresponding
 * built-in 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_listed_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);

    // Create inspect config configuration.
    $inspectConfig = (new InspectConfig())
        // The infoTypes of information to match.
        ->setInfoTypes([
            (new InfoType())->setName('PHONE_NUMBER'),
            (new InfoType())->setName('EMAIL_ADDRESS'),
            (new InfoType())->setName('US_SOCIAL_SECURITY_NUMBER')
        ]);

    // Run request.
    $inspectContentRequest = (new InspectContentRequest())
        ->setParent($parent)
        ->setInspectConfig($inspectConfig)
        ->setItem($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()));
        }
    }
}

from typing import List

import google.cloud.dlp


def inspect_image_file_listed_infotypes(
    project: str,
    filename: str,
    info_types: List[str],
    include_quote: bool = True,
) -> None:
    """Uses the Data Loss Prevention API to analyze strings in an image for
    data matching the given infoTypes.
    Args:
        project: The Google Cloud project id to use as a parent resource.
        filename: The path of the image file to inspect.
        info_types:  A list of strings representing infoTypes to look for.
            A full list of info type categories can be fetched from the API.
        include_quote: Boolean for whether to display a matching snippet of
            the detected information in the results.
    """

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

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

    # Construct the configuration dictionary.
    inspect_config = {
        "info_types": info_types,
        "include_quote": include_quote,
    }

    # 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": inspect_config,
            "item": {"byte_item": byte_item},
        }
    )

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