Inspecciona una string y excluye coincidencias de REGEX

Omite las direcciones de correo electrónico que terminan con un dominio específico del análisis del detector EMAIL_ADDRESS

Explora más

Para obtener documentación en la que se incluye esta muestra de código, consulta lo siguiente:

Muestra de código

C#

Para obtener información sobre cómo instalar y usar la biblioteca cliente de la protección de datos sensibles, consulta Bibliotecas cliente de la protección de datos sensibles.

Para autenticarte en la protección de datos sensibles, configura las credenciales predeterminadas de la aplicación. Si deseas obtener más información, consulta Configura la autenticación para un entorno de desarrollo local.


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

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

        var byteContentItem = new ByteContentItem
        {
            Type = ByteContentItem.Types.BytesType.TextUtf8,
            Data = Google.Protobuf.ByteString.CopyFromUtf8(textToInspect)
        };

        var contentItem = new ContentItem { ByteItem = byteContentItem };

        var infoTypes = new string[] { "PHONE_NUMBER", "EMAIL_ADDRESS", "CREDIT_CARD_NUMBER" }.Select(it => new InfoType { Name = it });

        var exclusionRule = new ExclusionRule
        {
            MatchingType = MatchingType.FullMatch,
            Regex = new CustomInfoType.Types.Regex { Pattern = excludedRegex }
        };

        var ruleSet = new InspectionRuleSet
        {
            InfoTypes = { new InfoType { Name = "EMAIL_ADDRESS" } },
            Rules = { new InspectionRule { ExclusionRule = exclusionRule } }
        };

        var config = new InspectConfig
        {
            InfoTypes = { infoTypes },
            IncludeQuote = true,
            RuleSet = { ruleSet }
        };

        var request = new InspectContentRequest
        {
            Parent = new LocationName(projectId, "global").ToString(),
            Item = contentItem,
            InspectConfig = config
        };

        var response = dlp.InspectContent(request);

        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

Para obtener información sobre cómo instalar y usar la biblioteca cliente de la protección de datos sensibles, consulta Bibliotecas cliente de la protección de datos sensibles.

Para autenticarte en la protección de datos sensibles, configura las credenciales predeterminadas de la aplicación. Si deseas obtener más información, consulta Configura la autenticación para un entorno de desarrollo local.

import (
	"context"
	"fmt"
	"io"

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

// inspectStringWithExclusionRegex inspects a string excluding REGEX matches
// in this function specifically the function omits email addresses ending with a specific
// domain from EMAIL_ADDRESS detector scan.
func inspectStringWithExclusionRegex(w io.Writer, projectID, textToInspect, excludedRegex string) error {
	// projectID := "my-project-id"
	// textToInspect := "Some email addresses: gary@example.com, bob@example.org"
	// excludedRegex := ".+@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: "PHONE_NUMBER"},
		{Name: "EMAIL_ADDRESS"},
		{Name: "CREDIT_CARD_NUMBER"},
	}

	// Exclude matches from the specified excludedMatchList.
	exclusionRule := &dlppb.ExclusionRule{
		Type: &dlppb.ExclusionRule_Regex{
			Regex: &dlppb.CustomInfoType_Regex{
				Pattern: excludedRegex,
			},
		},
		MatchingType: dlppb.MatchingType_MATCHING_TYPE_FULL_MATCH,
	}

	// Construct a ruleset that applies the exclusion rule to the EMAIL_ADDRESSES infotype.
	ruleSet := &dlppb.InspectionRuleSet{
		InfoTypes: []*dlppb.InfoType{
			{Name: "EMAIL_ADDRESS"},
		},
		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

Para obtener información sobre cómo instalar y usar la biblioteca cliente de la protección de datos sensibles, consulta Bibliotecas cliente de la protección de datos sensibles.

Para autenticarte en la protección de datos sensibles, configura las credenciales predeterminadas de la aplicación. Si deseas obtener más información, consulta Configura la autenticación para un entorno de desarrollo local.


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.CustomInfoType.Regex;
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 InspectStringWithExclusionRegex {

  public static void main(String[] args) throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-project-id";
    String textToInspect = "Some email addresses: gary@example.com, bob@example.org";
    String excludedRegex = ".+@example.com";
    inspectStringWithExclusionRegex(projectId, textToInspect, excludedRegex);
  }

  // Inspects the provided text, avoiding matches specified in the exclusion list.
  public static void inspectStringWithExclusionRegex(
      String projectId, String textToInspect, String excludedRegex) 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[] {"PHONE_NUMBER", "EMAIL_ADDRESS", "CREDIT_CARD_NUMBER"}) {
        infoTypes.add(InfoType.newBuilder().setName(typeName).build());
      }

      // Exclude matches from the specified excludedMatchList.
      ExclusionRule exclusionRule =
          ExclusionRule.newBuilder()
              .setMatchingType(MatchingType.MATCHING_TYPE_FULL_MATCH)
              .setRegex(Regex.newBuilder().setPattern(excludedRegex))
              .build();

      // Construct a ruleset that applies the exclusion rule to the EMAIL_ADDRESSES infotype.
      InspectionRuleSet ruleSet =
          InspectionRuleSet.newBuilder()
              .addInfoTypes(InfoType.newBuilder().setName("EMAIL_ADDRESS"))
              .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

Para obtener información sobre cómo instalar y usar la biblioteca cliente de la protección de datos sensibles, consulta Bibliotecas cliente de la protección de datos sensibles.

Para autenticarte en la protección de datos sensibles, configura las credenciales predeterminadas de la aplicación. Si deseas obtener más información, consulta Configura la autenticación para un entorno de desarrollo local.

// 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 = 'Some email addresses: gary@example.com, bob@example.org';

// Exclusion Regex
// const exclusionRegex = '.+@example.com';

async function inspectStringMultipleRules() {
  // Specify the type and content to be inspected.
  const item = {
    byteItem: {
      type: DLP.protos.google.privacy.dlp.v2.ByteContentItem.BytesType
        .TEXT_UTF8,
      data: Buffer.from(string, 'utf-8'),
    },
  };

  // Info Types for inspection
  const infoTypes = [{name: 'EMAIL_ADDRESS'}];

  // Construct a exclusion rule that uses a regex pattern
  const exclusionRule = {
    regex: {pattern: exclusionRegex},
    matchingType:
      DLP.protos.google.privacy.dlp.v2.MatchingType.MATCHING_TYPE_FULL_MATCH,
  };

  // Construct a ruleset that applies the exclusion rule to the EMAIL_ADDRESSES infotype.
  const ruleSet = [
    {
      infoTypes: infoTypes,
      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,
  };

  // 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.');
  }
}
inspectStringMultipleRules();

PHP

Para obtener información sobre cómo instalar y usar la biblioteca cliente de la protección de datos sensibles, consulta Bibliotecas cliente de la protección de datos sensibles.

Para autenticarte en la protección de datos sensibles, configura las credenciales predeterminadas de la aplicación. Si deseas obtener más información, consulta Configura la autenticación para un entorno de desarrollo local.

use Google\Cloud\Dlp\V2\Client\DlpServiceClient;
use Google\Cloud\Dlp\V2\ContentItem;
use Google\Cloud\Dlp\V2\CustomInfoType\Regex;
use Google\Cloud\Dlp\V2\ExclusionRule;
use Google\Cloud\Dlp\V2\InfoType;
use Google\Cloud\Dlp\V2\InspectConfig;
use Google\Cloud\Dlp\V2\InspectContentRequest;
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, excluding REGEX matches
 * Omit email addresses ending with a specific domain from an EMAIL_ADDRESS detector scan.
 *
 * @param string $projectId         The Google Cloud project id to use as a parent resource.
 * @param string $textToInspect     The string to inspect.
 */
function inspect_string_with_exclusion_regex(
    // TODO(developer): Replace sample parameters before running the code.
    string $projectId,
    string $textToInspect = 'Some email addresses: gary@example.com, bob@example.org'
): 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.
    $infotypes = [
        (new InfoType())->setName('PHONE_NUMBER'),
        (new InfoType())->setName('EMAIL_ADDRESS'),
        (new InfoType())->setName('CREDIT_CARD_NUMBER'),
    ];

    // Exclude matches from the specified excludedRegex.
    $excludedRegex = '.+@example.com';
    $exclusionRule = (new ExclusionRule())
        ->setMatchingType(MatchingType::MATCHING_TYPE_FULL_MATCH)
        ->setRegex((new Regex())
            ->setPattern($excludedRegex));

    // Construct a ruleset that applies the exclusion rule to the EMAIL_ADDRESSES infotype.
    $inspectionRuleSet = (new InspectionRuleSet())
        ->setInfoTypes([
            (new InfoType())
                ->setName('EMAIL_ADDRESS')
        ])
        ->setRules([
            (new InspectionRule())
                ->setExclusionRule($exclusionRule),
        ]);

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

    // Run request
    $inspectContentRequest = (new InspectContentRequest())
        ->setParent($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('  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

Para obtener información sobre cómo instalar y usar la biblioteca cliente de la protección de datos sensibles, consulta Bibliotecas cliente de la protección de datos sensibles.

Para autenticarte en la protección de datos sensibles, configura las credenciales predeterminadas de la aplicación. Si deseas obtener más información, consulta Configura la autenticación para un entorno de desarrollo local.

import google.cloud.dlp

def inspect_string_with_exclusion_regex(
    project: str, content_string: str, exclusion_regex: str = ".+@example.com"
) -> None:
    """Inspects the provided text, avoiding matches specified in the exclusion regex

    Uses the Data Loss Prevention API to omit matches on EMAIL_ADDRESS if they match
    the specified exclusion regex.

    Args:
        project: The Google Cloud project id to use as a parent resource.
        content_string: The string to inspect.
        exclusion_regex: The regular expression to exclude matches on

    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": "EMAIL_ADDRESS"}]

    # Construct a rule set that will only match on EMAIL_ADDRESS
    # if the specified regex doesn't also match.
    rule_set = [
        {
            "info_types": info_types_to_locate,
            "rules": [
                {
                    "exclusion_rule": {
                        "regex": {"pattern": exclusion_regex},
                        "matching_type": google.cloud.dlp_v2.MatchingType.MATCHING_TYPE_FULL_MATCH,
                    }
                }
            ],
        }
    ]

    # Construct the configuration dictionary
    inspect_config = {
        "info_types": info_types_to_locate,
        "rule_set": rule_set,
        "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.")

¿Qué sigue?

Para buscar y filtrar muestras de código de otros productos de Google Cloud, consulta el navegador de muestra de Google Cloud.