Inspecionar dados com uma regra de hotword

Esse exemplo usa um regex personalizado com uma regra de hotword para aumentar a probabilidade de correspondência.

Mais informações

Para ver a documentação detalhada que inclui este exemplo de código, consulte:

Exemplo de código

C#

Para saber como instalar e usar a biblioteca de cliente para proteção de dados sensíveis, consulte Bibliotecas de cliente de proteção de dados sensíveis.

Para usar a proteção de dados sensíveis, configure o Application Default Credentials. Para mais informações, consulte Configurar a autenticação para um ambiente de desenvolvimento local.


using System;
using Google.Api.Gax.ResourceNames;
using Google.Cloud.Dlp.V2;
using static Google.Cloud.Dlp.V2.CustomInfoType.Types;

public class InspectDataWithHotwordRule
{
    public static InspectContentResponse InspectDataHotwordRule(
        string projectId,
        string text,
        string customRegex,
        string hotwordRegex,
        InfoType infoType = null)
    {
        // Instantiate dlp client.
        var dlp = DlpServiceClient.Create();

        // Construct the content item.
        var contentItem = new ContentItem
        {
            ByteItem = new ByteContentItem
            {
                Type = ByteContentItem.Types.BytesType.TextUtf8,
                Data = Google.Protobuf.ByteString.CopyFromUtf8(text)
            }
        };

        // Construct the info type if null.
        var infotype = infoType ?? new InfoType { Name = "C_MRN" };

        // Construct the custom regex detector.
        var customInfoType = new CustomInfoType
        {
            InfoType = infotype,
            Regex = new Regex { Pattern = customRegex },
            Likelihood = Likelihood.Possible
        };

        // Construct hotword rule.
        var hotwordRule = new DetectionRule.Types.HotwordRule
        {
            HotwordRegex = new Regex { Pattern = hotwordRegex },
            LikelihoodAdjustment = new DetectionRule.Types.LikelihoodAdjustment
            {
                FixedLikelihood = Likelihood.VeryLikely
            },
            Proximity = new DetectionRule.Types.Proximity
            {
                WindowBefore = 10
            }
        };

        // Construct the rule set for the inspect config.
        var inspectionRuleSet = new InspectionRuleSet
        {
            InfoTypes = { infotype },
            Rules =
            {
                new InspectionRule
                {
                    HotwordRule = hotwordRule
                }
            }
        };

        // Construct the inspect config.
        var inspectConfig = new InspectConfig
        {
            CustomInfoTypes = { customInfoType },
            IncludeQuote = true,
            RuleSet = { inspectionRuleSet },
        };

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

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

        // Inspect the response.
        Console.WriteLine($"Findings: {response.Result.Findings.Count}");
        foreach (var f in response.Result.Findings)
        {
            Console.WriteLine("Quote: " + f.Quote);
            Console.WriteLine("Info type: " + f.InfoType.Name);
            Console.WriteLine("Likelihood: " + f.Likelihood);
        }
        return response;
    }
}

Go

Para saber como instalar e usar a biblioteca de cliente para proteção de dados sensíveis, consulte Bibliotecas de cliente de proteção de dados sensíveis.

Para usar a proteção de dados sensíveis, configure o Application Default Credentials. Para mais informações, consulte Configurar a autenticação para um ambiente de desenvolvimento local.

import (
	"context"
	"fmt"
	"io"

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

// inspectWithHotWordRules inspects data with hot word rule, it uses custom
// regex with a hot word rule to increase the likelihood match
func inspectWithHotWordRules(w io.Writer, projectID, textToInspect string) error {
	// projectID := "my-project-id"
	// textToInspect := "Patient's MRN 444-5-22222 and just a number 333-2-33333"

	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),
			},
		},
	}

	// Construct the custom regex detectors
	customInfoType := &dlppb.CustomInfoType{
		InfoType: &dlppb.InfoType{
			Name: "C_MRN",
		},
		Type: &dlppb.CustomInfoType_Regex_{
			Regex: &dlppb.CustomInfoType_Regex{
				Pattern: "[1-9]{3}-[1-9]{1}-[1-9]{5}",
			},
		},
		Likelihood: dlppb.Likelihood_POSSIBLE,
	}

	// Construct hotword rule.
	hotWordRule := &dlppb.CustomInfoType_DetectionRule_HotwordRule{
		HotwordRegex: &dlppb.CustomInfoType_Regex{
			Pattern: "(?i)(mrn|medical)(?-i)",
		},
		Proximity: &dlppb.CustomInfoType_DetectionRule_Proximity{
			WindowBefore: int32(10),
		},
		LikelihoodAdjustment: &dlppb.CustomInfoType_DetectionRule_LikelihoodAdjustment{
			Adjustment: &dlppb.CustomInfoType_DetectionRule_LikelihoodAdjustment_FixedLikelihood{
				FixedLikelihood: dlppb.Likelihood_VERY_LIKELY,
			},
		},
	}

	inspectionRuleSet := &dlppb.InspectionRuleSet{
		Rules: []*dlppb.InspectionRule{
			{
				Type: &dlppb.InspectionRule_HotwordRule{
					HotwordRule: hotWordRule,
				},
			},
		},
		InfoTypes: []*dlppb.InfoType{
			customInfoType.InfoType,
		},
	}

	// 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{
			CustomInfoTypes: []*dlppb.CustomInfoType{
				customInfoType,
			},
			RuleSet: []*dlppb.InspectionRuleSet{
				inspectionRuleSet,
			},
			IncludeQuote: true,
		},
	}

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

	// Parse the response and process 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 saber como instalar e usar a biblioteca de cliente para proteção de dados sensíveis, consulte Bibliotecas de cliente de proteção de dados sensíveis.

Para usar a proteção de dados sensíveis, configure o Application Default Credentials. Para mais informações, consulte Configurar a autenticação para um ambiente de desenvolvimento 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;
import com.google.privacy.dlp.v2.CustomInfoType.DetectionRule.HotwordRule;
import com.google.privacy.dlp.v2.CustomInfoType.DetectionRule.LikelihoodAdjustment;
import com.google.privacy.dlp.v2.CustomInfoType.DetectionRule.Proximity;
import com.google.privacy.dlp.v2.CustomInfoType.Regex;
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.Likelihood;
import com.google.privacy.dlp.v2.LocationName;
import com.google.protobuf.ByteString;
import java.io.IOException;

public class InspectWithHotwordRules {

  public static void main(String[] args) throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-project-id";
    String textToInspect = "Patient's MRN 444-5-22222 and just a number 333-2-33333";
    String customRegexPattern = "[1-9]{3}-[1-9]{1}-[1-9]{5}";
    String hotwordRegexPattern = "(?i)(mrn|medical)(?-i)";
    inspectWithHotwordRules(projectId, textToInspect, customRegexPattern, hotwordRegexPattern);
  }

  // Inspects a BigQuery Table
  public static void inspectWithHotwordRules(
      String projectId, String textToInspect, String customRegexPattern, String hotwordRegexPattern)
      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 regex pattern the inspection will look for.
      Regex regex = Regex.newBuilder().setPattern(customRegexPattern).build();

      // Construct the custom regex detector.
      InfoType infoType = InfoType.newBuilder().setName("C_MRN").build();
      CustomInfoType customInfoType =
          CustomInfoType.newBuilder().setInfoType(infoType).setRegex(regex).build();

      // Specify hotword likelihood adjustment.
      LikelihoodAdjustment likelihoodAdjustment =
          LikelihoodAdjustment.newBuilder().setFixedLikelihood(Likelihood.VERY_LIKELY).build();

      // Specify a window around a finding to apply a detection rule.
      Proximity proximity = Proximity.newBuilder().setWindowBefore(10).build();

      // Construct hotword rule.
      HotwordRule hotwordRule =
          HotwordRule.newBuilder()
              .setHotwordRegex(Regex.newBuilder().setPattern(hotwordRegexPattern).build())
              .setLikelihoodAdjustment(likelihoodAdjustment)
              .setProximity(proximity)
              .build();

      // Construct rule set for the inspect config.
      InspectionRuleSet inspectionRuleSet =
          InspectionRuleSet.newBuilder()
              .addInfoTypes(infoType)
              .addRules(InspectionRule.newBuilder().setHotwordRule(hotwordRule))
              .build();

      // Construct the configuration for the Inspect request.
      InspectConfig config =
          InspectConfig.newBuilder()
              .addCustomInfoTypes(customInfoType)
              .setIncludeQuote(true)
              .setMinLikelihood(Likelihood.POSSIBLE)
              .addRuleSet(inspectionRuleSet)
              .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 saber como instalar e usar a biblioteca de cliente para proteção de dados sensíveis, consulte Bibliotecas de cliente de proteção de dados sensíveis.

Para usar a proteção de dados sensíveis, configure o Application Default Credentials. Para mais informações, consulte Configurar a autenticação para um ambiente de desenvolvimento 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 = 'Patients MRN 444-5-22222';

// The minimum likelihood required before returning a match
// const minLikelihood = DLP.protos.google.privacy.dlp.v2.Likelihood.POSSIBLE;

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

// 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' }];

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

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

// Custom hotword regex patten
// const hotwordRegexPattern = '(?i)(mrn|medical)(?-i)';

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

  // Construct a hot word rule
  const hotwordRule = {
    hotwordRegex: {
      pattern: hotwordRegexPattern,
    },
    proximity: {
      windowBefore: 10,
    },
    likelihoodAdjustment: {
      fixedLikelihood:
        DLP.protos.google.privacy.dlp.v2.Likelihood.VERY_LIKELY,
    },
  };

  // Construct a hotword inspection rule
  const inpectionRuleSet = [
    {
      infoTypes: customInfoTypes.map(
        customInfoType => customInfoType.infoType
      ),
      rules: [{hotwordRule: hotwordRule}],
    },
  ];

  // Assigns likelihood to each match
  customInfoTypes = customInfoTypes.map(customInfoType => {
    customInfoType.likelihood =
      DLP.protos.google.privacy.dlp.v2.Likelihood.POSSIBLE;
    return customInfoType;
  });

  // Construct request
  const request = {
    parent: `projects/${projectId}/locations/global`,
    inspectConfig: {
      infoTypes: infoTypes,
      customInfoTypes: customInfoTypes,
      minLikelihood: minLikelihood,
      includeQuote: includeQuote,
      limits: {
        maxFindingsPerRequest: maxFindings,
      },
      ruleSet: inpectionRuleSet,
    },
    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.');
  }
}
inspectWithHotwordRule();

PHP

Para saber como instalar e usar a biblioteca de cliente para proteção de dados sensíveis, consulte Bibliotecas de cliente de proteção de dados sensíveis.

Para usar a proteção de dados sensíveis, configure o Application Default Credentials. Para mais informações, consulte Configurar a autenticação para um ambiente de desenvolvimento local.

use Google\Cloud\Dlp\V2\Client\DlpServiceClient;
use Google\Cloud\Dlp\V2\ContentItem;
use Google\Cloud\Dlp\V2\CustomInfoType;
use Google\Cloud\Dlp\V2\CustomInfoType\DetectionRule\HotwordRule;
use Google\Cloud\Dlp\V2\CustomInfoType\DetectionRule\LikelihoodAdjustment;
use Google\Cloud\Dlp\V2\CustomInfoType\DetectionRule\Proximity;
use Google\Cloud\Dlp\V2\CustomInfoType\Regex;
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;

/**
 * Inspect data with a hotword rule
 * This sample uses a custom regex with a hotword rule to increase the likelihood of match.
 *
 * @param string $projectId         The Google Cloud project id to use as a parent resource.
 * @param string $textToInspect     The string to inspect.
 */
function inspect_hotword_rule(
    // TODO(developer): Replace sample parameters before running the code.
    string $projectId,
    string $textToInspect = "Patient's MRN 444-5-22222 and just a number 333-2-33333"
): 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 regex pattern the inspection will look for.
    $customRegexPattern = '[1-9]{3}-[1-9]{1}-[1-9]{5}';
    $hotwordRegexPattern = '(?i)(mrn|medical)(?-i)';

    // Construct the custom regex detector.
    $cMrnDetector = (new InfoType())
        ->setName('C_MRN');
    $customInfoType = (new CustomInfoType())
        ->setInfoType($cMrnDetector)
        ->setLikelihood(Likelihood::POSSIBLE)
        ->setRegex((new Regex())
            ->setPattern($customRegexPattern));

    // Specify hotword likelihood adjustment.
    $likelihoodAdjustment = (new LikelihoodAdjustment())
        ->setFixedLikelihood(Likelihood::VERY_LIKELY);

    // Specify a window around a finding to apply a detection rule.
    $proximity = (new Proximity())
        ->setWindowBefore(10);

    $hotwordRule = (new HotwordRule())
        ->setHotwordRegex((new Regex())
            ->setPattern($hotwordRegexPattern))
        ->setLikelihoodAdjustment($likelihoodAdjustment)
        ->setProximity($proximity);

    // Construct rule set for the inspect config.
    $inspectionRuleSet = (new InspectionRuleSet())
        ->setInfoTypes([$cMrnDetector])
        ->setRules([
            (new InspectionRule())
                ->setHotwordRule($hotwordRule)
        ]);

    // Construct the configuration for the Inspect request.
    $inspectConfig = (new InspectConfig())
        ->setCustomInfoTypes([$customInfoType])
        ->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 saber como instalar e usar a biblioteca de cliente para proteção de dados sensíveis, consulte Bibliotecas de cliente de proteção de dados sensíveis.

Para usar a proteção de dados sensíveis, configure o Application Default Credentials. Para mais informações, consulte Configurar a autenticação para um ambiente de desenvolvimento local.

import google.cloud.dlp

def inspect_data_w_custom_hotwords(
    project: str,
    content_string: str,
) -> None:
    """Uses the Data Loss Prevention API to analyze string with medical record
       number custom regex detector, with custom hotwords rules to boost finding
       certainty under some circumstances.

    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 custom regex detector info type called "C_MRN",
    # with ###-#-##### pattern, where each # represents a digit from 1 to 9.
    # The detector has a detection likelihood of POSSIBLE.
    custom_info_types = [
        {
            "info_type": {"name": "C_MRN"},
            "regex": {"pattern": "[1-9]{3}-[1-9]{1}-[1-9]{5}"},
            "likelihood": google.cloud.dlp_v2.Likelihood.POSSIBLE,
        }
    ]

    # Construct a rule set with hotwords "mrn" and "medical", with a likelohood
    # boost to VERY_LIKELY when hotwords are present within the 10 character-
    # window preceding the PII finding.
    hotword_rule = {
        "hotword_regex": {"pattern": "(?i)(mrn|medical)(?-i)"},
        "likelihood_adjustment": {
            "fixed_likelihood": google.cloud.dlp_v2.Likelihood.VERY_LIKELY
        },
        "proximity": {"window_before": 10},
    }

    rule_set = [
        {"info_types": [{"name": "C_MRN"}], "rules": [{"hotword_rule": hotword_rule}]}
    ]

    # Construct the configuration dictionary with the custom regex info type.
    inspect_config = {
        "custom_info_types": custom_info_types,
        "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.")

A seguir

Para pesquisar e filtrar exemplos de código de outros produtos do Google Cloud, consulte o navegador de amostra do Google Cloud.