创建例外列表进行去标识化处理

为常规自定义字典检测器创建例外列表。

深入探索

如需查看包含此代码示例的详细文档，请参阅以下内容：

代码示例

C#

如需了解如何安装和使用敏感数据保护客户端库，请参阅 敏感数据保护客户端库。

如需向 Sensitive Data Protection 进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。 


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

public class DeidentifyWithExceptionList
{
    public static DeidentifyContentResponse Deidentify(string projectId, string text)
    {
        // Instantiate a client.
        var dlp = DlpServiceClient.Create();

        var contentItem = new ContentItem { Value = text };

        var wordList = new CustomInfoType.Types.Dictionary.Types.WordList
        {
            Words = { new string[] { "jack@example.org", "jill@example.org" } }
        };

        var exclusionRule = new ExclusionRule
        {
            MatchingType = MatchingType.FullMatch,
            Dictionary = new CustomInfoType.Types.Dictionary
            {
                WordList = wordList
            }
        };

        var infoType = new InfoType { Name = "EMAIL_ADDRESS" };

        var inspectionRuleSet = new InspectionRuleSet
        {
            InfoTypes = { infoType },
            Rules = { new InspectionRule { ExclusionRule = exclusionRule } }
        };

        var inspectConfig = new InspectConfig
        {
            InfoTypes = { infoType },
            RuleSet = { inspectionRuleSet }
        };
        var primitiveTransformation = new PrimitiveTransformation
        {
            ReplaceWithInfoTypeConfig = new ReplaceWithInfoTypeConfig { }
        };

        var transformation = new InfoTypeTransformations.Types.InfoTypeTransformation
        {
            InfoTypes = { infoType },
            PrimitiveTransformation = primitiveTransformation
        };

        var deidentifyConfig = new DeidentifyConfig
        {
            InfoTypeTransformations = new InfoTypeTransformations
            {
                Transformations = { transformation }
            }
        };

        var request = new DeidentifyContentRequest
        {
            Parent = new LocationName(projectId, "global").ToString(),
            InspectConfig = inspectConfig,
            DeidentifyConfig = deidentifyConfig,
            Item = contentItem
        };

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

        // Inspect the results.
        Console.WriteLine($"Deidentified content: {response.Item.Value}");
        return response;
    }
}

Go

如需了解如何安装和使用敏感数据保护客户端库，请参阅 敏感数据保护客户端库。

如需向 Sensitive Data Protection 进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。 

import (
	"context"
	"fmt"
	"io"

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

// deidentifyExceptionList creates an exception list for a regular custom dictionary detector.
func deidentifyExceptionList(w io.Writer, projectID, input string) error {
	// projectID := "my-project-id"
	// input := "jack@example.org accessed customer record of user5@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 fmt.Errorf("dlp.NewClient: %w", err)
	}

	// Closing the client safely cleans up background resousrces.
	defer client.Close()

	// Specify what content you want the service to DeIdentify.
	item := &dlppb.ContentItem{
		DataItem: &dlppb.ContentItem_Value{
			Value: input,
		},
	}

	// Specify the word list custom info type and build-in info type the inspection will look for.
	infoTypes := []*dlppb.InfoType{
		{Name: "EMAIL_ADDRESS"},
	}

	dictionary := &dlppb.CustomInfoType_Dictionary{
		Source: &dlppb.CustomInfoType_Dictionary_WordList_{
			WordList: &dlppb.CustomInfoType_Dictionary_WordList{
				Words: []string{"jack@example.org", "jill@example.org"},
			},
		},
	}

	exclusionRule := &dlppb.ExclusionRule{
		MatchingType: dlppb.MatchingType_MATCHING_TYPE_FULL_MATCH,
		Type: &dlppb.ExclusionRule_Dictionary{
			Dictionary: dictionary,
		},
	}

	inspectRuleSet := &dlppb.InspectionRuleSet{
		InfoTypes: infoTypes,
		Rules: []*dlppb.InspectionRule{
			{
				Type: &dlppb.InspectionRule_ExclusionRule{
					ExclusionRule: exclusionRule,
				},
			},
		},
	}

	// Construct the configuration for the de-id request and list all desired transformations.
	primitiveTransformation := &dlppb.PrimitiveTransformation{
		Transformation: &dlppb.PrimitiveTransformation_ReplaceWithInfoTypeConfig{},
	}

	infoTypeTransformation := &dlppb.InfoTypeTransformations{
		Transformations: []*dlppb.InfoTypeTransformations_InfoTypeTransformation{
			{
				PrimitiveTransformation: primitiveTransformation,
			},
		},
	}

	deIdentifyConfig := &dlppb.DeidentifyConfig{
		Transformation: &dlppb.DeidentifyConfig_InfoTypeTransformations{
			InfoTypeTransformations: infoTypeTransformation,
		},
	}

	// Create a configured request.
	req := &dlppb.DeidentifyContentRequest{
		Parent:           fmt.Sprintf("projects/%s/locations/global", projectID),
		DeidentifyConfig: deIdentifyConfig,
		InspectConfig: &dlppb.InspectConfig{
			InfoTypes:       infoTypes,
			CustomInfoTypes: []*dlppb.CustomInfoType{},
			RuleSet:         []*dlppb.InspectionRuleSet{inspectRuleSet},
		},
		// The item to analyze.
		Item: item,
	}

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

	// Print the result.
	fmt.Fprintf(w, "output : %v", resp.GetItem().GetValue())
	return nil

}

Java

如需了解如何安装和使用敏感数据保护客户端库，请参阅 敏感数据保护客户端库。

如需向 Sensitive Data Protection 进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。 


import com.google.cloud.dlp.v2.DlpServiceClient;
import com.google.privacy.dlp.v2.ContentItem;
import com.google.privacy.dlp.v2.CustomInfoType;
import com.google.privacy.dlp.v2.CustomInfoType.Dictionary;
import com.google.privacy.dlp.v2.CustomInfoType.Dictionary.WordList;
import com.google.privacy.dlp.v2.DeidentifyConfig;
import com.google.privacy.dlp.v2.DeidentifyContentRequest;
import com.google.privacy.dlp.v2.DeidentifyContentResponse;
import com.google.privacy.dlp.v2.ExclusionRule;
import com.google.privacy.dlp.v2.InfoType;
import com.google.privacy.dlp.v2.InfoTypeTransformations;
import com.google.privacy.dlp.v2.InfoTypeTransformations.InfoTypeTransformation;
import com.google.privacy.dlp.v2.InspectConfig;
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.privacy.dlp.v2.PrimitiveTransformation;
import com.google.privacy.dlp.v2.ReplaceWithInfoTypeConfig;
import java.io.IOException;

public class DeIdentifyWithExceptionList {

  public static void main(String[] args) throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-project-id";
    String textToDeIdentify = "jack@example.org accessed customer record of user5@example.com";
    deIdentifyWithExceptionList(projectId, textToDeIdentify);
  }

  public static void deIdentifyWithExceptionList(String projectId, String textToDeIdentify)
      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 what content you want the service to DeIdentify.
      ContentItem contentItem = ContentItem.newBuilder().setValue(textToDeIdentify).build();

      // Construct the custom word list to be detected.
      Dictionary wordList =
          Dictionary.newBuilder()
              .setWordList(
                  WordList.newBuilder()
                      .addWords("jack@example.org")
                      .addWords("jill@example.org")
                      .build())
              .build();

      // Construct the custom dictionary detector associated with the word list.
      InfoType developerEmail = InfoType.newBuilder().setName("DEVELOPER_EMAIL").build();
      CustomInfoType customInfoType =
          CustomInfoType.newBuilder().setInfoType(developerEmail).setDictionary(wordList).build();

      ExclusionRule exclusionRule =
          ExclusionRule.newBuilder()
              .setDictionary(wordList)
              .setMatchingType(MatchingType.MATCHING_TYPE_FULL_MATCH)
              .build();

      InspectionRule inspectionRule =
          InspectionRule.newBuilder()
              .setExclusionRule(exclusionRule)
              .build();

      // Specify the word list custom info type and build-in info type the inspection will look for.
      InfoType emailAddress = InfoType.newBuilder().setName("EMAIL_ADDRESS").build();

      InspectionRuleSet inspectionRuleSet =
          InspectionRuleSet.newBuilder()
              .addInfoTypes(emailAddress)
              .addRules(inspectionRule)
              .build();

      InspectConfig inspectConfig =
          InspectConfig.newBuilder()
              .addInfoTypes(emailAddress)
              .addCustomInfoTypes(customInfoType)
              .addRuleSet(inspectionRuleSet)
              .build();

      // Define type of deidentification as replacement.
      PrimitiveTransformation primitiveTransformation =
          PrimitiveTransformation.newBuilder()
              .setReplaceWithInfoTypeConfig(ReplaceWithInfoTypeConfig.getDefaultInstance())
              .build();

      // Associate de-identification type with info type.
      InfoTypeTransformation transformation =
          InfoTypeTransformation.newBuilder()
              .addInfoTypes(emailAddress)
              .setPrimitiveTransformation(primitiveTransformation)
              .build();

      // Construct the configuration for the de-id request and list all desired transformations.
      DeidentifyConfig deidentifyConfig =
          DeidentifyConfig.newBuilder()
              .setInfoTypeTransformations(
                  InfoTypeTransformations.newBuilder().addTransformations(transformation))
              .build();

      // Combine configurations into a request for the service.
      DeidentifyContentRequest request =
          DeidentifyContentRequest.newBuilder()
              .setParent(LocationName.of(projectId, "global").toString())
              .setItem(contentItem)
              .setInspectConfig(inspectConfig)
              .setDeidentifyConfig(deidentifyConfig)
              .build();

      // Send the request and receive response from the service
      DeidentifyContentResponse response = dlp.deidentifyContent(request);

      // Print the results
      System.out.println(
          "Text after replace with infotype config: " + response.getItem().getValue());
    }
  }
}

Node.js

如需了解如何安装和使用敏感数据保护客户端库，请参阅 敏感数据保护客户端库。

如需向 Sensitive Data Protection 进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。 

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

// 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.
const dlp = new DLP.DlpServiceClient();

// TODO(developer): Replace these variables before running the sample.
// const projectId = "your-project-id";

// The string to deidentify
// const textToInspect = 'jack@example.org accessed customer record of user5@example.com';

// Words to exclude for during inspection
// const words = ['jack@example.org', 'jill@example.org'];

// The infoTypes of information to match
// See https://cloud.google.com/dlp/docs/concepts-infotypes for more information
// about supported infoTypes.
// const infoTypes = [{ name: 'EMAIL_ADDRESS' }];

async function deIdentifyWithExceptionList() {
  // Construct item to inspect
  const item = {value: textToInspect};

  // Construct the custom dictionary detector associated with the word list.
  const wordListDict = {
    wordList: {
      words: words,
    },
  };

  // Construct a rule set that will only match if the match text does not
  // contains tokens from the exclusion list.
  const ruleSet = [
    {
      infoTypes: infoTypes,
      rules: [
        {
          exclusionRule: {
            matchingType:
              DLP.protos.google.privacy.dlp.v2.MatchingType
                .MATCHING_TYPE_FULL_MATCH,
            dictionary: wordListDict,
          },
        },
      ],
    },
  ];

  // Combine configurations to construct inspect config.
  const inspectConfig = {
    infoTypes: infoTypes,
    ruleSet: ruleSet,
  };

  // Define type of de-identification as replacement & associate de-identification type with info type.
  const transformation = {
    infoTypes: [],
    primitiveTransformation: {
      replaceWithInfoTypeConfig: {},
    },
  };

  // Construct the configuration for the de-identification request and list all desired transformations.
  const deidentifyConfig = {
    infoTypeTransformations: {
      transformations: [transformation],
    },
  };

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

  // Send the request and receive response from the service.
  const [response] = await dlp.deidentifyContent(request);

  // Print the results
  console.log(
    `Text after replace with infotype config: ${response.item.value}`
  );
}

deIdentifyWithExceptionList();

PHP

如需了解如何安装和使用敏感数据保护客户端库，请参阅 敏感数据保护客户端库。

如需向 Sensitive Data Protection 进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。 

use Google\Cloud\Dlp\V2\Client\DlpServiceClient;
use Google\Cloud\Dlp\V2\ContentItem;
use Google\Cloud\Dlp\V2\CustomInfoType\Dictionary;
use Google\Cloud\Dlp\V2\CustomInfoType\Dictionary\WordList;
use Google\Cloud\Dlp\V2\DeidentifyConfig;
use Google\Cloud\Dlp\V2\DeidentifyContentRequest;
use Google\Cloud\Dlp\V2\ExclusionRule;
use Google\Cloud\Dlp\V2\InfoType;
use Google\Cloud\Dlp\V2\InfoTypeTransformations;
use Google\Cloud\Dlp\V2\InfoTypeTransformations\InfoTypeTransformation;
use Google\Cloud\Dlp\V2\InspectConfig;
use Google\Cloud\Dlp\V2\InspectionRule;
use Google\Cloud\Dlp\V2\InspectionRuleSet;
use Google\Cloud\Dlp\V2\MatchingType;
use Google\Cloud\Dlp\V2\PrimitiveTransformation;
use Google\Cloud\Dlp\V2\ReplaceWithInfoTypeConfig;

/**
 * Create an exception list for de-identification
 * Create an exception list for a regular custom dictionary detector.
 *
 * @param string $callingProjectId  The project ID to run the API call under
 * @param string $textToDeIdentify  The String you want the service to DeIdentify
 */
function deidentify_exception_list(
    // TODO(developer): Replace sample parameters before running the code.
    string $callingProjectId,
    string $textToDeIdentify = 'jack@example.org accessed customer record of user5@example.com'
): void {
    // Instantiate a client.
    $dlp = new DlpServiceClient();

    // Specify what content you want the service to DeIdentify.
    $contentItem = (new ContentItem())
        ->setValue($textToDeIdentify);

    // Construct the custom word list to be detected.
    $wordList = (new Dictionary())
        ->setWordList((new WordList())
            ->setWords(['jack@example.org', 'jill@example.org']));

    // Specify the exclusion rule and build-in info type the inspection will look for.
    $exclusionRule = (new ExclusionRule())
        ->setMatchingType(MatchingType::MATCHING_TYPE_FULL_MATCH)
        ->setDictionary($wordList);

    $emailAddress = (new InfoType())
        ->setName('EMAIL_ADDRESS');
    $inspectionRuleSet = (new InspectionRuleSet())
        ->setInfoTypes([$emailAddress])
        ->setRules([
            (new InspectionRule())
                ->setExclusionRule($exclusionRule)
        ]);

    $inspectConfig = (new InspectConfig())
        ->setInfoTypes([$emailAddress])
        ->setRuleSet([$inspectionRuleSet]);

    // Define type of deidentification as replacement.
    $primitiveTransformation = (new PrimitiveTransformation())
        ->setReplaceWithInfoTypeConfig(new ReplaceWithInfoTypeConfig());

    // Associate de-identification type with info type.
    $transformation = (new InfoTypeTransformation())
        ->setInfoTypes([$emailAddress])
        ->setPrimitiveTransformation($primitiveTransformation);

    // Construct the configuration for the de-id request and list all desired transformations.
    $deidentifyConfig = (new DeidentifyConfig())
        ->setInfoTypeTransformations(
            (new InfoTypeTransformations())
                ->setTransformations([$transformation])
        );

    // Send the request and receive response from the service
    $parent = "projects/$callingProjectId/locations/global";
    $deidentifyContentRequest = (new DeidentifyContentRequest())
        ->setParent($parent)
        ->setDeidentifyConfig($deidentifyConfig)
        ->setInspectConfig($inspectConfig)
        ->setItem($contentItem);
    $response = $dlp->deidentifyContent($deidentifyContentRequest);

    // Print the results
    printf('Text after replace with infotype config: %s', $response->getItem()->getValue());
}

Python

如需了解如何安装和使用敏感数据保护客户端库，请参阅 敏感数据保护客户端库。

如需向 Sensitive Data Protection 进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。 

from typing import List

import google.cloud.dlp


def deidentify_with_exception_list(
    project: str, content_string: str, info_types: List[str], exception_list: List[str]
) -> None:
    """Uses the Data Loss Prevention API to de-identify sensitive data in a
      string but ignore matches against custom list.

    Args:
        project: The Google Cloud project id to use as a parent resource.
        content_string: The string to deidentify (will be treated as text).
        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.
        exception_list: The list of strings to ignore 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 = [{"name": info_type} for info_type in info_types]

    # Construct a rule set that will only match on info_type
    # if the matched text is not in the exception list.
    rule_set = [
        {
            "info_types": info_types,
            "rules": [
                {
                    "exclusion_rule": {
                        "dictionary": {"word_list": {"words": exception_list}},
                        "matching_type": google.cloud.dlp_v2.MatchingType.MATCHING_TYPE_FULL_MATCH,
                    }
                }
            ],
        }
    ]

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

    # Construct deidentify configuration dictionary
    deidentify_config = {
        "info_type_transformations": {
            "transformations": [
                {"primitive_transformation": {"replace_with_info_type_config": {}}}
            ]
        }
    }

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

    # Convert the project id into a full resource id.
    parent = f"projects/{project}/locations/global"

    # Call the API
    response = dlp.deidentify_content(
        request={
            "parent": parent,
            "deidentify_config": deidentify_config,
            "inspect_config": inspect_config,
            "item": item,
        }
    )

    # Print out the results.
    print(response.item.value)

后续步骤

如需搜索和过滤其他 Google Cloud 产品的代码示例，请参阅 Google Cloud 示例浏览器。