Cloud Data Loss Prevention (Cloud DLP) is now a part of Sensitive Data Protection. The API name remains the same: Cloud Data Loss Prevention API (DLP API). For information about the services that make up Sensitive Data Protection, see Sensitive Data Protection overview.

Inspect a string for sensitive data, omitting overlapping matches on person and email

Omit matches on a PERSON_NAME detector if also matched by an EMAIL_ADDRESS detector.

Explore further

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

Modifying infoType detectors to refine scan results

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.

View on GitHub Feedback


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

public class InspectStringOmitOverlap
{
    public static InspectContentResponse Inspect(string projectId, string textToInspect)
    {
        // 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.
        var dlp = DlpServiceClient.Create();

        // Specify the type and content to be inspected.
        var byteItem = new ByteContentItem
        {
            Type = ByteContentItem.Types.BytesType.TextUtf8,
            Data = Google.Protobuf.ByteString.CopyFromUtf8(textToInspect)
        };
        var contentItem = new ContentItem { ByteItem = byteItem };

        // Specify the type of info the inspection will look for.
        // See https://cloud.google.com/dlp/docs/infotypes-reference for complete list of info types.
        var infoTypes = new string[] { "PERSON_NAME", "EMAIL_ADDRESS" }.Select(it => new InfoType { Name = it });

        // Exclude EMAIL_ADDRESS matches
        var exclusionRule = new ExclusionRule
        {
            ExcludeInfoTypes = new ExcludeInfoTypes { InfoTypes = { new InfoType { Name = "EMAIL_ADDRESS" } } },
            MatchingType = MatchingType.PartialMatch
        };

        // Construct a ruleset that applies the exclusion rule to the PERSON_NAME infotype.
        // If a PERSON_NAME match overlaps with an EMAIL_ADDRESS match, the PERSON_NAME match will
        // be excluded.
        var ruleSet = new InspectionRuleSet
        {
            InfoTypes = { new InfoType { Name = "PERSON_NAME" } },
            Rules = { new InspectionRule { ExclusionRule = exclusionRule } }
        };

        // Construct the configuration for the Inspect request, including the ruleset.
        var config = new InspectConfig
        {
            InfoTypes = { infoTypes },
            IncludeQuote = true,
            RuleSet = { ruleSet }
        };

        // Construct the Inspect request to be sent by the client.
        var request = new InspectContentRequest
        {
            Parent = new LocationName(projectId, "global").ToString(),
            Item = contentItem,
            InspectConfig = config
        };

        // Use the client to send the API request.
        var response = dlp.InspectContent(request);

        // Parse the response and process results
        Console.WriteLine($"Findings: {response.Result.Findings.Count}");
        foreach (var f in response.Result.Findings)
        {
            Console.WriteLine("\tQuote: " + f.Quote);
            Console.WriteLine("\tInfo type: " + f.InfoType.Name);
            Console.WriteLine("\tLikelihood: " + f.Likelihood);
        }

        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.

View on GitHub Feedback

import (
	"context"
	"fmt"
	"io"

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

// inspectStringOmitOverlap inspects a string for sensitive data and
// omitting overlapping matches on person and email
func inspectStringOmitOverlap(w io.Writer, projectID, textToInspect string) error {
	// projectID := "my-project-id"
	// textToInspect := "gary@example.com"

	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()

	// Specify the type and content to be inspected.
	contentItem := &dlppb.ContentItem{
		DataItem: &dlppb.ContentItem_ByteItem{
			ByteItem: &dlppb.ByteContentItem{
				Type: dlppb.ByteContentItem_TEXT_UTF8,
				Data: []byte(textToInspect),
			},
		},
	}

	// Specify the type of info the inspection will look for.
	// See https://cloud.google.com/dlp/docs/infotypes-reference for complete list of info types.
	infoTypes := []*dlppb.InfoType{
		{Name: "PERSON_NAME"},
		{Name: "EMAIL_ADDRESS"},
	}

	// Exclude EMAIL_ADDRESS matches
	exclusionRule := &dlppb.ExclusionRule{
		Type: &dlppb.ExclusionRule_ExcludeInfoTypes{
			ExcludeInfoTypes: &dlppb.ExcludeInfoTypes{
				InfoTypes: []*dlppb.InfoType{
					{Name: "EMAIL_ADDRESS"},
				},
			},
		},
		MatchingType: dlppb.MatchingType_MATCHING_TYPE_PARTIAL_MATCH,
	}

	// Construct a ruleSet that applies the exclusion rule to the PERSON_NAME infoType.
	// If a PERSON_NAME match overlaps with an EMAIL_ADDRESS match, the PERSON_NAME match will
	// be excluded.
	ruleSet := &dlppb.InspectionRuleSet{
		InfoTypes: []*dlppb.InfoType{
			{Name: "PERSON_NAME"},
		},
		Rules: []*dlppb.InspectionRule{
			{
				Type: &dlppb.InspectionRule_ExclusionRule{
					ExclusionRule: exclusionRule,
				},
			},
		},
	}

	// Construct the Inspect request to be sent by the client.
	req := &dlppb.InspectContentRequest{
		Parent: fmt.Sprintf("projects/%s/locations/global", projectID),
		Item:   contentItem,
		InspectConfig: &dlppb.InspectConfig{
			InfoTypes:    infoTypes,
			IncludeQuote: true,
			RuleSet: []*dlppb.InspectionRuleSet{
				ruleSet,
			},
		},
	}

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

	// Process the results.
	fmt.Fprintf(w, "Findings: %v\n", len(resp.Result.Findings))
	for _, v := range resp.GetResult().Findings {
		fmt.Fprintf(w, "Quote: %v\n", v.GetQuote())
		fmt.Fprintf(w, "Infotype Name: %v\n", v.GetInfoType().GetName())
		fmt.Fprintf(w, "Likelihood: %v\n", v.GetLikelihood())
	}
	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.

View on GitHub Feedback


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.ExcludeInfoTypes;
import com.google.privacy.dlp.v2.ExclusionRule;
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.InspectionRule;
import com.google.privacy.dlp.v2.InspectionRuleSet;
import com.google.privacy.dlp.v2.LocationName;
import com.google.privacy.dlp.v2.MatchingType;
import com.google.protobuf.ByteString;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

public class InspectStringOmitOverlap {

  public static void main(String[] args) throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-project-id";
    String textToInspect = "james@example.com";
    inspectStringOmitOverlap(projectId, textToInspect);
  }

  // Inspects the provided text, avoiding matches specified in the exclusion list.
  public static void inspectStringOmitOverlap(String projectId, String textToInspect)
      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 type and content to be inspected.
      ByteContentItem byteItem =
          ByteContentItem.newBuilder()
              .setType(BytesType.TEXT_UTF8)
              .setData(ByteString.copyFromUtf8(textToInspect))
              .build();
      ContentItem item = ContentItem.newBuilder().setByteItem(byteItem).build();

      // Specify the type of info the inspection will look for.
      // See https://cloud.google.com/dlp/docs/infotypes-reference for complete list of info types.
      List<InfoType> infoTypes = new ArrayList<>();
      for (String typeName : new String[] {"PERSON_NAME", "EMAIL_ADDRESS"}) {
        infoTypes.add(InfoType.newBuilder().setName(typeName).build());
      }

      // Exclude EMAIL_ADDRESS matches
      ExclusionRule exclusionRule =
          ExclusionRule.newBuilder()
              .setExcludeInfoTypes(
                  ExcludeInfoTypes.newBuilder()
                      .addInfoTypes(InfoType.newBuilder().setName("EMAIL_ADDRESS")))
              .setMatchingType(MatchingType.MATCHING_TYPE_PARTIAL_MATCH)
              .build();

      // Construct a ruleset that applies the exclusion rule to the PERSON_NAME infotype.
      // If a PERSON_NAME match overlaps with an EMAIL_ADDRESS match, the PERSON_NAME match will
      // be excluded.
      InspectionRuleSet ruleSet =
          InspectionRuleSet.newBuilder()
              .addInfoTypes(InfoType.newBuilder().setName("PERSON_NAME"))
              .addRules(InspectionRule.newBuilder().setExclusionRule(exclusionRule))
              .build();

      // Construct the configuration for the Inspect request, including the ruleset.
      InspectConfig config =
          InspectConfig.newBuilder()
              .addAllInfoTypes(infoTypes)
              .setIncludeQuote(true)
              .addRuleSet(ruleSet)
              .build();

      // Construct the Inspect request to be sent by the client.
      InspectContentRequest request =
          InspectContentRequest.newBuilder()
              .setParent(LocationName.of(projectId, "global").toString())
              .setItem(item)
              .setInspectConfig(config)
              .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.

View on GitHub Feedback

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

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

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

// The string to inspect
// const string = 'james@example.com';

async function inspectStringWithoutOverlapPersonEmail() {
  // Construct item to inspect
  const item = {
    byteItem: {
      type: DLP.protos.google.privacy.dlp.v2.ByteContentItem.BytesType
        .TEXT_UTF8,
      data: Buffer.from(string, 'utf-8'),
    },
  };

  // Specify the type of info the inspection will look for.
  const infoTypes = [{name: 'PERSON_NAME'}, {name: 'EMAIL_ADDRESS'}];

  // Exclude EMAIL_ADDRESS matches
  const exclusionRule = {
    excludeInfoTypes: {
      infoTypes: [{name: 'EMAIL_ADDRESS'}],
    },
    matchingType:
      DLP.protos.google.privacy.dlp.v2.MatchingType
        .MATCHING_TYPE_PARTIAL_MATCH,
  };

  // Construct a ruleset that applies the exclusion rule to the PERSON_NAME infotype.
  // If a PERSON_NAME match overlaps with an EMAIL_ADDRESS match, the PERSON_NAME match will
  // be excluded.
  const ruleSet = [
    {
      infoTypes: [{name: 'PERSON_NAME'}],
      rules: [
        {
          exclusionRule: exclusionRule,
        },
      ],
    },
  ];

  // Construct the configuration for the Inspect request, including the ruleset.
  const inspectConfig = {
    infoTypes: infoTypes,
    ruleSet: ruleSet,
    includeQuote: true,
  };

  // Construct the Inspect request to be sent by the client.
  const request = {
    parent: `projects/${projectId}/locations/global`,
    inspectConfig: inspectConfig,
    item: item,
  };

  // Run 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.');
  }
}
inspectStringWithoutOverlapPersonEmail();

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.

View on GitHub Feedback

use Google\Cloud\Dlp\V2\DlpServiceClient;
use Google\Cloud\Dlp\V2\ContentItem;
use Google\Cloud\Dlp\V2\ExcludeInfoTypes;
use Google\Cloud\Dlp\V2\ExclusionRule;
use Google\Cloud\Dlp\V2\InfoType;
use Google\Cloud\Dlp\V2\InspectConfig;
use Google\Cloud\Dlp\V2\InspectionRule;
use Google\Cloud\Dlp\V2\InspectionRuleSet;
use Google\Cloud\Dlp\V2\Likelihood;
use Google\Cloud\Dlp\V2\MatchingType;

/**
 * Inspect a string for sensitive data, omitting overlapping matches on person and email
 * Omit matches on a PERSON_NAME detector if also matched by an EMAIL_ADDRESS detector.
 *
 * @param string $projectId         The Google Cloud project id to use as a parent resource.
 * @param string $textToInspect     The string to inspect.
 */
function inspect_string_omit_overlap(
    // TODO(developer): Replace sample parameters before running the code.
    string $projectId,
    string $textToInspect = 'james@example.org is an email.'
): void {
    // Instantiate a client.
    $dlp = new DlpServiceClient();

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

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

    // Specify the type of info the inspection will look for.
    $personName = (new InfoType())
        ->setName('PERSON_NAME');
    $emailAddress = (new InfoType())
        ->setName('EMAIL_ADDRESS');
    $infoTypes = [$personName, $emailAddress];

    // Exclude EMAIL_ADDRESS matches
    $exclusionRule = (new ExclusionRule())
        ->setMatchingType(MatchingType::MATCHING_TYPE_PARTIAL_MATCH)
        ->setExcludeInfoTypes((new ExcludeInfoTypes())
                ->setInfoTypes([$emailAddress])
        );

    // Construct a ruleset that applies the exclusion rule to the PERSON_NAME infotype.
    // If a PERSON_NAME match overlaps with an EMAIL_ADDRESS match, the PERSON_NAME match will
    // be excluded.
    $inspectionRuleSet = (new InspectionRuleSet())
        ->setInfoTypes([$personName])
        ->setRules([
            (new InspectionRule())
                ->setExclusionRule($exclusionRule),
        ]);

    // Construct the configuration for the Inspect request, including the ruleset.
    $inspectConfig = (new InspectConfig())
        ->setInfoTypes($infoTypes)
        ->setIncludeQuote(true)
        ->setRuleSet([$inspectionRuleSet]);

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

    // 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('  Quote: %s' . PHP_EOL, $finding->getQuote());
            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.

View on GitHub Feedback

import google.cloud.dlp


def inspect_string_omit_overlap(
    project: str,
    content_string: str,
) -> None:
    """Matches PERSON_NAME and EMAIL_ADDRESS, but not both.

    Uses the Data Loss Prevention API omit matches on PERSON_NAME if the
    EMAIL_ADDRESS detector also matches.

    Args:
        project: The Google Cloud project id to use as a parent resource.
        content_string: The string to inspect.

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

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

    # Construct a list of infoTypes for DLP to locate in `content_string`. See
    # https://cloud.google.com/dlp/docs/concepts-infotypes for more information
    # about supported infoTypes.
    info_types_to_locate = [{"name": "PERSON_NAME"}, {"name": "EMAIL_ADDRESS"}]

    # Construct the configuration dictionary that will only match on PERSON_NAME
    # if the EMAIL_ADDRESS doesn't also match. This configuration helps reduce
    # the total number of findings when there is a large overlap between different
    # infoTypes.
    inspect_config = {
        "info_types": info_types_to_locate,
        "rule_set": [
            {
                "info_types": [{"name": "PERSON_NAME"}],
                "rules": [
                    {
                        "exclusion_rule": {
                            "exclude_info_types": {
                                "info_types": [{"name": "EMAIL_ADDRESS"}]
                            },
                            "matching_type": google.cloud.dlp_v2.MatchingType.MATCHING_TYPE_PARTIAL_MATCH,
                        }
                    }
                ],
            }
        ],
        "include_quote": True,
    }

    # Construct the `item`.
    item = {"value": content_string}

    # 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": item}
    )

    # Print out the results.
    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.