Inspecting images for sensitive data

Cloud Data Loss Prevention (DLP) can detect and classify sensitive data within an image. Using infoType detectors and optical character recognition (OCR), Cloud DLP inspects a base64-encoded image for text, detects sensitive data within the text, and then returns the locations of any sensitive data that it has detected.

Given an image as input, Cloud DLP detects sensitive data in the image. The output of an inspection operation includes the found infoTypes, the likelihood of the match, and pixel coordinate and length values that indicate the areas within which Cloud DLP found the sensitive data. The coordinates at the bottom left corner of an image are (0,0).

Inspecting an image for all default infoTypes

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

To inspect an image for default infoTypes:

  1. Encode the image as base64.
  2. Submit a request to the DLP API's content.inspect method. The request need only contain the base64-encoded image if you want to inspect for default infoTypes.

For example, consider the following image. This image is an example of a typical image file generated from a scan of a paper document.

Original image (click to enlarge)

To inspect this image for default infoTypes, send the following request to the DLP API's content.inspect method:

Protocol

{
  "item": {
    "byteItem": {
      "data": "[BASE64-ENCODED-IMAGE]",
      "type": "IMAGE_JPEG"
    }
  }
}

Cloud DLP returns the following:

{
  "result": {
    "findings": [
      {
        "infoType": {
          "name": "PHONE_NUMBER"
        },
        "likelihood": "UNLIKELY",
        "location": {
          "contentLocations": [
            {
              "imageLocation": {
                "boundingBoxes": [
                  {
                    "top": 98,
                    "left": 986,
                    "width": 102,
                    "height": 117
                  },
                  {
                    "top": 98,
                    "left": 1092,
                    "width": 29,
                    "height": 114
                  },
                  {
                    "top": 95,
                    "left": 1111,
                    "width": 82,
                    "height": 115
                  },
                  {
                    "top": 95,
                    "left": 1197,
                    "width": 29,
                    "height": 114
                  },
                  {
                    "top": 90,
                    "left": 1203,
                    "width": 185,
                    "height": 118
                  }
                ]
              }
            }
          ]
        },
        "createTime": "2019-11-01T22:07:05.870Z"
      },
      {
        "infoType": {
          "name": "US_SOCIAL_SECURITY_NUMBER"
        },
        "likelihood": "VERY_LIKELY",
        "location": {
          "contentLocations": [
            {
              "imageLocation": {
                "boundingBoxes": [
                  {
                    "top": 98,
                    "left": 986,
                    "width": 102,
                    "height": 117
                  },
                  {
                    "top": 98,
                    "left": 1092,
                    "width": 29,
                    "height": 114
                  },
                  {
                    "top": 95,
                    "left": 1111,
                    "width": 82,
                    "height": 115
                  },
                  {
                    "top": 95,
                    "left": 1197,
                    "width": 29,
                    "height": 114
                  },
                  {
                    "top": 90,
                    "left": 1203,
                    "width": 185,
                    "height": 118
                  }
                ]
              }
            }
          ]
        },
        "createTime": "2019-11-01T22:07:05.871Z"
      },
      {
        "infoType": {
          "name": "EMAIL_ADDRESS"
        },
        "likelihood": "LIKELY",
        "location": {
          "contentLocations": [
            {
              "imageLocation": {
                "boundingBoxes": [
                  {
                    "top": 340,
                    "left": 334,
                    "width": 57,
                    "height": 58
                  },
                  {
                    "top": 340,
                    "left": 384,
                    "width": 12,
                    "height": 58
                  },
                  {
                    "top": 340,
                    "left": 387,
                    "width": 79,
                    "height": 59
                  },
                  {
                    "top": 341,
                    "left": 467,
                    "width": 12,
                    "height": 58
                  },
                  {
                    "top": 340,
                    "left": 476,
                    "width": 119,
                    "height": 61
                  },
                  {
                    "top": 341,
                    "left": 589,
                    "width": 12,
                    "height": 58
                  },
                  {
                    "top": 342,
                    "left": 592,
                    "width": 45,
                    "height": 58
                  }
                ]
              }
            }
          ]
        },
        "createTime": "2019-11-01T22:07:05.869Z"
      },
      {
        "infoType": {
          "name": "PHONE_NUMBER"
        },
        "likelihood": "POSSIBLE",
        "location": {
          "contentLocations": [
            {
              "imageLocation": {
                "boundingBoxes": [
                  {
                    "top": 394,
                    "left": 335,
                    "width": 50,
                    "height": 77
                  },
                  {
                    "top": 394,
                    "left": 380,
                    "width": 17,
                    "height": 77
                  },
                  {
                    "top": 394,
                    "left": 387,
                    "width": 51,
                    "height": 77
                  },
                  {
                    "top": 394,
                    "left": 433,
                    "width": 17,
                    "height": 77
                  },
                  {
                    "top": 394,
                    "left": 436,
                    "width": 77,
                    "height": 77
                  }
                ]
              }
            }
          ]
        },
        "createTime": "2019-11-01T22:07:05.870Z"
      },
      {
        "infoType": {
          "name": "DATE"
        },
        "likelihood": "LIKELY",
        "location": {
          "contentLocations": [
            {
              "imageLocation": {
                "boundingBoxes": [
                  {
                    "top": 572,
                    "left": 1129,
                    "width": 71,
                    "height": 38
                  }
                ]
              }
            }
          ]
        },
        "createTime": "2019-11-01T22:07:05.921Z"
      }
    ]
  }
}

Java


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());
      }
    }
  }
}

Cloud DLP has found the following infoTypes, though its match confidence for each one varies:

  • A phone number (unlikely)
  • A US Social Security number (very likely)
  • An email address (likely)
  • A phone number (possible)
  • A date (likely)

If you were to draw each of the bounding boxes on the image, it would look like the following. Be aware that Cloud DLP often uses multiple boxes to indicate where a single instance of sensitive data is in the image.

Bounding boxes overlaid on image (click to enlarge)

Note that, in addition to detecting the handwritten Social Security number, the email address, and the phone number, Cloud DLP has also detected the year. Assuming that's not optimal behavior, the next example demonstrates how to inspect for only certain infoTypes.

Inspecting an image for specific infoTypes

If you want to inspect an image for only certain sensitive data types, specify their corresponding built-in infoTypes.

To inspect an image for specific infoTypes:

  1. Encode the image as base64.
  2. Submit a request to the DLP API's content.inspect method. The request must include:

Consider the original image from the previous section. To inspect for only US Social Security numbers, email addresses, and telephone numbers, send the following JSON to the DLP API's content.inspect method:

Protocol

{
  "item": {
    "byteItem": {
      "data": "[BASE64-ENCODED-IMAGE]",
      "type": "IMAGE_JPEG"
    }
  },
  "inspectConfig": {
    "infoTypes": [
      {
        "name": "US_SOCIAL_SECURITY_NUMBER"
      },
      {
        "name": "PHONE_NUMBER"
      },
      {
        "name": "EMAIL_ADDRESS"
      }
    ]
  }
}

Cloud DLP returns the following:

{
  "result": {
    "findings": [
      {
        "infoType": {
          "name": "US_SOCIAL_SECURITY_NUMBER"
        },
        "likelihood": "VERY_LIKELY",
        "location": {
          "contentLocations": [
            {
              "imageLocation": {
                "boundingBoxes": [
                  {
                    "top": 98,
                    "left": 986,
                    "width": 102,
                    "height": 117
                  },
                  {
                    "top": 98,
                    "left": 1092,
                    "width": 29,
                    "height": 114
                  },
                  {
                    "top": 95,
                    "left": 1111,
                    "width": 82,
                    "height": 115
                  },
                  {
                    "top": 95,
                    "left": 1197,
                    "width": 29,
                    "height": 114
                  },
                  {
                    "top": 90,
                    "left": 1203,
                    "width": 185,
                    "height": 118
                  }
                ]
              }
            }
          ]
        },
        "createTime": "2019-11-01T22:58:56.985Z"
      },
      {
        "infoType": {
          "name": "EMAIL_ADDRESS"
        },
        "likelihood": "LIKELY",
        "location": {
          "contentLocations": [
            {
              "imageLocation": {
                "boundingBoxes": [
                  {
                    "top": 340,
                    "left": 334,
                    "width": 57,
                    "height": 58
                  },
                  {
                    "top": 340,
                    "left": 384,
                    "width": 12,
                    "height": 58
                  },
                  {
                    "top": 340,
                    "left": 387,
                    "width": 79,
                    "height": 59
                  },
                  {
                    "top": 341,
                    "left": 467,
                    "width": 12,
                    "height": 58
                  },
                  {
                    "top": 340,
                    "left": 476,
                    "width": 119,
                    "height": 61
                  },
                  {
                    "top": 341,
                    "left": 589,
                    "width": 12,
                    "height": 58
                  },
                  {
                    "top": 342,
                    "left": 592,
                    "width": 45,
                    "height": 58
                  }
                ]
              }
            }
          ]
        },
        "createTime": "2019-11-01T22:58:56.984Z"
      },
      {
        "infoType": {
          "name": "PHONE_NUMBER"
        },
        "likelihood": "POSSIBLE",
        "location": {
          "contentLocations": [
            {
              "imageLocation": {
                "boundingBoxes": [
                  {
                    "top": 394,
                    "left": 335,
                    "width": 50,
                    "height": 77
                  },
                  {
                    "top": 394,
                    "left": 380,
                    "width": 17,
                    "height": 77
                  },
                  {
                    "top": 394,
                    "left": 387,
                    "width": 51,
                    "height": 77
                  },
                  {
                    "top": 394,
                    "left": 433,
                    "width": 17,
                    "height": 77
                  },
                  {
                    "top": 394,
                    "left": 436,
                    "width": 77,
                    "height": 77
                  }
                ]
              }
            }
          ]
        },
        "createTime": "2019-11-01T22:58:56.985Z"
      }
    ]
  }
}

Java


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());
      }
    }
  }
}

As you can see from the output, Cloud DLP has found a US Social Security number, an email address, and a telephone number.

See the JSON quickstart for more information about using the Cloud DLP API with JSON.

Code examples

Following is sample code in several languages that demonstrates how to use Cloud DLP to inspect an image for sensitive data.

Node.js

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

// Import other required libraries
const fs = require('fs');
const mime = require('mime');

// 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 text, JPG, or PNG file.
// const filepath = 'path/to/image.png';

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

// The maximum number of findings to report per request (0 = server maximum)
// const maxFindings = 0;

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

// The customInfoTypes of information to match
// const customInfoTypes = [{ infoType: { name: 'DICT_TYPE' }, dictionary: { wordList: { words: ['foo', 'bar', 'baz']}}},
//   { infoType: { name: 'REGEX_TYPE' }, regex: '\\(\\d{3}\\) \\d{3}-\\d{4}'}];

// Whether to include the matching string
// const includeQuote = true;

async function inspectFile() {
  // Construct file data to inspect
  const fileTypeConstant =
    ['image/jpeg', 'image/bmp', 'image/png', 'image/svg'].indexOf(
      mime.getType(filepath)
    ) + 1;
  const fileBytes = Buffer.from(fs.readFileSync(filepath)).toString('base64');
  const item = {
    byteItem: {
      type: fileTypeConstant,
      data: fileBytes,
    },
  };

  // Construct request
  const request = {
    parent: `projects/${projectId}/locations/global`,
    inspectConfig: {
      infoTypes: infoTypes,
      customInfoTypes: customInfoTypes,
      minLikelihood: minLikelihood,
      includeQuote: includeQuote,
      limits: {
        maxFindingsPerRequest: maxFindings,
      },
    },
    item: item,
  };

  // Run request
  const [response] = await dlp.inspectContent(request);
  const findings = response.result.findings;
  if (findings.length > 0) {
    console.log('Findings:');
    findings.forEach(finding => {
      if (includeQuote) {
        console.log(`\tQuote: ${finding.quote}`);
      }
      console.log(`\tInfo type: ${finding.infoType.name}`);
      console.log(`\tLikelihood: ${finding.likelihood}`);
    });
  } else {
    console.log('No findings.');
  }
}

Python



def inspect_file(
    project,
    filename,
    info_types,
    min_likelihood=None,
    custom_dictionaries=None,
    custom_regexes=None,
    max_findings=None,
    include_quote=True,
    mime_type=None,
):
    """Uses the Data Loss Prevention API to analyze a file for protected data.
    Args:
        project: The Google Cloud project id to use as a parent resource.
        filename: The path to the file to inspect.
        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'.
        max_findings: The maximum number of findings to report; 0 = no maximum.
        include_quote: Boolean for whether to display a quote of the detected
            information in the results.
        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 mimetypes

    # 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).
    if not info_types:
        info_types = ["FIRST_NAME", "LAST_NAME", "EMAIL_ADDRESS"]
    info_types = [{"name": info_type} for info_type in info_types]

    # Prepare custom_info_types by parsing the dictionary word lists and
    # regex patterns.
    if custom_dictionaries is None:
        custom_dictionaries = []
    dictionaries = [
        {
            "info_type": {"name": "CUSTOM_DICTIONARY_{}".format(i)},
            "dictionary": {"word_list": {"words": custom_dict.split(",")}},
        }
        for i, custom_dict in enumerate(custom_dictionaries)
    ]
    if custom_regexes is None:
        custom_regexes = []
    regexes = [
        {
            "info_type": {"name": "CUSTOM_REGEX_{}".format(i)},
            "regex": {"pattern": custom_regex},
        }
        for i, custom_regex in enumerate(custom_regexes)
    ]
    custom_info_types = dictionaries + regexes

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

    # 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]

    # 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 item, containing the file's byte data.
    with open(filename, mode="rb") as f:
        item = {"byte_item": {"type": content_type_index, "data": f.read()}}
    # Convert the project id into a full resource id.
    parent = dlp.project_path(project)

    # Call the API.
    response = dlp.inspect_content(parent, inspect_config, item)

    # Print out the results.
    if response.result.findings:
        for finding in response.result.findings:
            try:
                print("Quote: {}".format(finding.quote))
            except AttributeError:
                pass
            print("Info type: {}".format(finding.info_type.name))
            print("Likelihood: {}".format(finding.likelihood))
    else:
        print("No findings.")

Go

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

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

// inspectTextFile inspects a text file at a given filePath, and prints results.
func inspectTextFile(w io.Writer, projectID, filePath string) error {
	// projectID := "my-project-id"
	// filePath := "path/to/image.png"
	ctx := context.Background()

	// Initialize client.
	client, err := dlp.NewClient(ctx)
	if err != nil {
		return err
	}
	defer client.Close() // Closing the client safely cleans up background resources.

	// Gather the resources for the request.
	data, err := ioutil.ReadFile(filePath)
	if err != nil {
		return err
	}

	// Create and send the request.
	req := &dlppb.InspectContentRequest{
		Parent: fmt.Sprintf("projects/%s/locations/global", projectID),
		Item: &dlppb.ContentItem{
			DataItem: &dlppb.ContentItem_ByteItem{
				ByteItem: &dlppb.ByteContentItem{
					Type: dlppb.ByteContentItem_TEXT_UTF8,
					Data: data,
				},
			},
		},
		InspectConfig: &dlppb.InspectConfig{
			InfoTypes: []*dlppb.InfoType{
				{Name: "PHONE_NUMBER"},
				{Name: "EMAIL_ADDRESS"},
				{Name: "CREDIT_CARD_NUMBER"},
			},
			IncludeQuote: true,
		},
	}
	resp, err := client.InspectContent(ctx, req)
	if err != nil {
		return fmt.Errorf("InspectContent: %v", err)
	}

	// Process the results.
	fmt.Fprintf(w, "Findings: %d\n", len(resp.Result.Findings))
	for _, f := range resp.Result.Findings {
		fmt.Fprintf(w, "\tQoute: %s\n", f.Quote)
		fmt.Fprintf(w, "\tInfo type: %s\n", f.InfoType.Name)
		fmt.Fprintf(w, "\tLikelihood: %s\n", f.Likelihood)
	}
	return nil
}

PHP

use Google\Cloud\Dlp\V2\DlpServiceClient;
use Google\Cloud\Dlp\V2\ContentItem;
use Google\Cloud\Dlp\V2\InfoType;
use Google\Cloud\Dlp\V2\InspectConfig;
use Google\Cloud\Dlp\V2\ByteContentItem;
use Google\Cloud\Dlp\V2\ByteContentItem\BytesType;
use Google\Cloud\Dlp\V2\Likelihood;

/** Uncomment and populate these variables in your code */
// $projectId = 'YOUR_PROJECT_ID';
// $filepath = 'path/to/image.png';

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

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

// Construct request
$parent = "projects/$projectId/locations/global";
$item = (new ContentItem())
    ->setByteItem($fileBytes);
$inspectConfig = (new InspectConfig())
    // The infoTypes of information to match
    ->setInfoTypes([
        (new InfoType())->setName('PHONE_NUMBER'),
        (new InfoType())->setName('EMAIL_ADDRESS'),
        (new InfoType())->setName('CREDIT_CARD_NUMBER')
    ])
    // Whether to include the matching string
    ->setIncludeQuote(true);

// Run request
$response = $dlp->inspectContent([
    'parent' => $parent,
    'inspectConfig' => $inspectConfig,
    'item' => $item
]);

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

Ruby

# project_id   = "Your Google Cloud project ID"
# filename     = "The file path to the file to inspect"
# max_findings = "Maximum number of findings to report per request (0 = server maximum)"

require "google/cloud/dlp"

dlp = Google::Cloud::Dlp.dlp_service
inspect_config = {
  # The types of information to match
  info_types:     [{ name: "PERSON_NAME" }, { name: "PHONE_NUMBER" }],

  # Only return results above a likelihood threshold (0 for all)
  min_likelihood: :POSSIBLE,

  # Limit the number of findings (0 for no limit)
  limits:         { max_findings_per_request: max_findings },

  # Whether to include the matching string in the response
  include_quote:  true
}

# The item to inspect
file = File.open filename, "rb"
item_to_inspect = { byte_item: { type: :BYTES_TYPE_UNSPECIFIED, data: file.read } }

# Run request
parent = "projects/#{project_id}/locations/global"
response = dlp.inspect_content parent:         parent,
                               inspect_config: inspect_config,
                               item:           item_to_inspect

# Print the results
if response.result.findings.empty?
  puts "No findings"
else
  response.result.findings.each do |finding|
    puts "Quote:      #{finding.quote}"
    puts "Info type:  #{finding.info_type.name}"
    puts "Likelihood: #{finding.likelihood}"
  end
end

C#


using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using Google.Api.Gax.ResourceNames;
using Google.Cloud.Dlp.V2;
using Google.Protobuf;
using static Google.Cloud.Dlp.V2.ByteContentItem.Types;

public class DlpInspectFile
{
    public static IEnumerable<Finding> InspectFile(string projectId, string filePath, BytesType fileType)
    {
        // Instantiate a client.
        var dlp = DlpServiceClient.Create();

        // Get the bytes from the file.
        ByteString fileBytes;
        using (Stream f = new FileStream(filePath, FileMode.Open))
        {
            fileBytes = ByteString.FromStream(f);
        }

        // Construct a request.
        var request = new InspectContentRequest
        {
            Parent = new LocationName(projectId, "global").ToString(),
            Item = new ContentItem
            {
                ByteItem = new ByteContentItem()
                {
                    Data = fileBytes,
                    Type = fileType
                }
            },
            InspectConfig = new InspectConfig
            {
                // The info types of information to match
                InfoTypes =
                {
                    new InfoType { Name = "PHONE_NUMBER" },
                    new InfoType { Name = "EMAIL_ADDRESS" },
                    new InfoType { Name = "CREDIT_CARD_NUMBER" }
                },
                // The minimum likelihood before returning a match
                MinLikelihood = Likelihood.Unspecified,
                // Whether to include the matching string
                IncludeQuote = true,
                Limits = new InspectConfig.Types.FindingLimits
                {
                    // The maximum number of findings to report per request
                    // (0 = server maximum)
                    MaxFindingsPerRequest = 0
                }
            }
        };

        // Execute request
        var response = dlp.InspectContent(request);

        // Inspect response
        var findings = response.Result.Findings;
        if (findings.Any())
        {
            Console.WriteLine("Findings:");
            foreach (var finding in findings)
            {
                Console.WriteLine($"Quote: {finding.Quote}");
                Console.WriteLine($"InfoType: {finding.InfoType}");
                Console.WriteLine($"Likelihood: {finding.Likelihood}");
            }
        }
        else
        {
            Console.WriteLine("No findings.");
        }
        return findings;
    }
}

Try it out

You can try each of these examples out yourself—or experiment with your own images—in the API Explorer on the reference page for content.inspect:

Go to API Explorer

What's next