Memeriksa string dari data sensitif menggunakan kata kunci panas kustom

Meningkatkan kemungkinan kecocokan PERSON_NAME jika ada kata kunci panas "pasien" di dekatnya. Menggambarkan penggunaan properti InspectConfig untuk tujuan memindai database medis guna menemukan nama pasien. Anda dapat menggunakan detektor infoType PERSON_NAME bawaan Cloud DLP, tetapi hal ini menyebabkan Cloud DLP mencocokkan semua nama orang, bukan hanya nama pasien. Untuk memperbaikinya, Anda dapat menyertakan aturan frasa pengaktif yang mencari kata "pasien" dalam kedekatan karakter tertentu dari karakter pertama dari kemungkinan kecocokan. Kemudian, Anda dapat menetapkan temuan yang cocok dengan pola ini dengan kemungkinan "sangat mungkin", karena temuan tersebut sesuai dengan kriteria khusus Anda. Menetapkan kemungkinan minimum ke VERY_LIKELY dalam InspectConfig memastikan bahwa hanya kecocokan dengan konfigurasi ini yang ditampilkan dalam temuan.

Mempelajari lebih lanjut

Untuk dokumentasi mendetail yang menyertakan contoh kode ini, lihat artikel berikut:

• Mengubah detektor infoType untuk meningkatkan kualitas hasil pemindaian

Contoh kode

C#

Untuk mempelajari cara menginstal dan menggunakan library klien untuk Perlindungan Data Sensitif, lihat library klien Perlindungan Data Sensitif.

Untuk melakukan autentikasi ke Perlindungan Data Sensitif, siapkan Kredensial Default Aplikasi. Untuk mengetahui informasi selengkapnya, baca Menyiapkan autentikasi untuk lingkungan pengembangan lokal.

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

public class InspectStringCustomHotword
{
    public static InspectContentResponse Inspect(string projectId, string textToInspect, string customHotword)
    {
        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 hotwordRule = new DetectionRule.Types.HotwordRule
        {
            HotwordRegex = new Regex { Pattern = customHotword },
            Proximity = new DetectionRule.Types.Proximity { WindowBefore = 50 },
            LikelihoodAdjustment = new DetectionRule.Types.LikelihoodAdjustment { FixedLikelihood = Likelihood.VeryLikely }
        };

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

        var inspectionRuleSet = new InspectionRuleSet
        {
            InfoTypes = { infoType },
            Rules = { new InspectionRule { HotwordRule = hotwordRule } }
        };

        var inspectConfig = new InspectConfig
        {
            InfoTypes = { infoType },
            IncludeQuote = true,
            RuleSet = { inspectionRuleSet },
            MinLikelihood = Likelihood.VeryLikely
        };

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

        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

Untuk mempelajari cara menginstal dan menggunakan library klien untuk Perlindungan Data Sensitif, lihat library klien Perlindungan Data Sensitif.

Untuk melakukan autentikasi ke Perlindungan Data Sensitif, siapkan Kredensial Default Aplikasi. Untuk mengetahui informasi selengkapnya, baca Menyiapkan autentikasi untuk lingkungan pengembangan lokal.

import (
	"context"
	"fmt"
	"io"

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

// inspectStringCustomHotWord inspects a string from sensitive data by using a custom hot word
func inspectStringCustomHotWord(w io.Writer, projectID, textToInspect, customHotWord, infoTypeName string) error {
	// projectID := "my-project-id"
	// textToInspect := "patient name: John Doe"
	// customHotWord := "patient"
	// infoTypeName := "PERSON_NAME"

	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),
			},
		},
	}

	// Increase likelihood of matches that have customHotword nearby
	hotwordRule := &dlppb.InspectionRule_HotwordRule{

		HotwordRule: &dlppb.CustomInfoType_DetectionRule_HotwordRule{
			HotwordRegex: &dlppb.CustomInfoType_Regex{
				Pattern: customHotWord,
			},
			Proximity: &dlppb.CustomInfoType_DetectionRule_Proximity{
				WindowBefore: 50,
			},
			LikelihoodAdjustment: &dlppb.CustomInfoType_DetectionRule_LikelihoodAdjustment{
				Adjustment: &dlppb.CustomInfoType_DetectionRule_LikelihoodAdjustment_FixedLikelihood{
					FixedLikelihood: dlppb.Likelihood_VERY_LIKELY,
				},
			},
		},
	}

	// Construct a ruleset that applies the hotword rule to the PERSON_NAME infotype.
	ruleSet := &dlppb.InspectionRuleSet{
		InfoTypes: []*dlppb.InfoType{
			{Name: infoTypeName}, //"PERSON_NAME"
		},
		Rules: []*dlppb.InspectionRule{
			{
				Type: &dlppb.InspectionRule_HotwordRule{
					HotwordRule: hotwordRule.HotwordRule,
				},
			},
		},
	}

	// 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: []*dlppb.InfoType{
				{Name: infoTypeName}, //"PERSON_NAME"
			},
			IncludeQuote:  true,
			MinLikelihood: dlppb.Likelihood_VERY_LIKELY,
			RuleSet: []*dlppb.InspectionRuleSet{
				ruleSet,
			},
		},
	}

	// 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

Untuk mempelajari cara menginstal dan menggunakan library klien untuk Perlindungan Data Sensitif, lihat library klien Perlindungan Data Sensitif.

Untuk melakukan autentikasi ke Perlindungan Data Sensitif, siapkan Kredensial Default Aplikasi. Untuk mengetahui informasi selengkapnya, baca Menyiapkan autentikasi untuk lingkungan pengembangan lokal.

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.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 InspectStringCustomHotword {

  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 name: John Doe";
    String customHotword = "patient";
    inspectStringCustomHotword(projectId, textToInspect, customHotword);
  }

  // Inspects the provided text.
  public static void inspectStringCustomHotword(
      String projectId, String textToInspect, String customHotword) 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();

      // Increase likelihood of matches that have customHotword nearby
      HotwordRule hotwordRule =
          HotwordRule.newBuilder()
              .setHotwordRegex(Regex.newBuilder().setPattern(customHotword))
              .setProximity(Proximity.newBuilder().setWindowBefore(50))
              .setLikelihoodAdjustment(
                  LikelihoodAdjustment.newBuilder().setFixedLikelihood(Likelihood.VERY_LIKELY))
              .build();

      // Construct a ruleset that applies the hotword rule to the PERSON_NAME infotype.
      InspectionRuleSet ruleSet =
          InspectionRuleSet.newBuilder()
              .addInfoTypes(InfoType.newBuilder().setName("PERSON_NAME").build())
              .addRules(InspectionRule.newBuilder().setHotwordRule(hotwordRule))
              .build();

      // Construct the configuration for the Inspect request.
      InspectConfig config =
          InspectConfig.newBuilder()
              .addInfoTypes(InfoType.newBuilder().setName("PERSON_NAME").build())
              .setIncludeQuote(true)
              .addRuleSet(ruleSet)
              .setMinLikelihood(Likelihood.VERY_LIKELY)
              .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

Untuk mempelajari cara menginstal dan menggunakan library klien untuk Perlindungan Data Sensitif, lihat library klien Perlindungan Data Sensitif.

Untuk melakukan autentikasi ke Perlindungan Data Sensitif, siapkan Kredensial Default Aplikasi. Untuk mengetahui informasi selengkapnya, baca Menyiapkan autentikasi untuk lingkungan pengembangan lokal.

// 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 = 'patient name: John Doe';

// Custom hotward
// const customHotword = 'patient';

async function inspectStringCustomHotword() {
  // 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'),
    },
  };

  // Increase likelihood of matches that have customHotword nearby.
  const hotwordRule = {
    hotwordRegex: {
      pattern: customHotword,
    },
    proximity: {
      windowBefore: 50,
    },
    likelihoodAdjustment: {
      fixedLikelihood:
        DLP.protos.google.privacy.dlp.v2.Likelihood.VERY_LIKELY,
    },
  };

  // Construct a ruleset that applies the hotword rule to the PERSON_NAME infotype.
  const ruleSet = [
    {
      infoTypes: [{name: 'PERSON_NAME'}],
      rules: [
        {
          hotwordRule: hotwordRule,
        },
      ],
    },
  ];

  // Construct the configuration for the Inspect request.
  const inspectConfig = {
    infoTypes: [{name: 'PERSON_NAME'}],
    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.');
  }
}
inspectStringCustomHotword();

PHP

Untuk mempelajari cara menginstal dan menggunakan library klien untuk Perlindungan Data Sensitif, lihat library klien Perlindungan Data Sensitif.

Untuk melakukan autentikasi ke Perlindungan Data Sensitif, siapkan Kredensial Default Aplikasi. Untuk mengetahui informasi selengkapnya, baca Menyiapkan autentikasi untuk lingkungan pengembangan lokal.

use Google\Cloud\Dlp\V2\Client\DlpServiceClient;
use Google\Cloud\Dlp\V2\ContentItem;
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 a string from sensitive data by using a custom hotword
 * Increase the likelihood of a PERSON_NAME match if there is the hotword "patient" nearby. Illustrates using the InspectConfig property for the purpose of scanning a medical database for patient names. You can use Cloud DLP's built-in PERSON_NAME infoType detector, but that causes Cloud DLP to match on all names of people, not just names of patients. To fix this, you can include a hotword rule that looks for the word "patient" within a certain character proximity from the first character of potential matches. You can then assign findings that match this pattern a likelihood of "very likely," since they correspond to your special criteria. Setting the minimum likelihood to VERY_LIKELY within InspectConfig ensures that only matches to this configuration are returned in findings.
 *
 * @param string $projectId         The Google Cloud project id to use as a parent resource.
 * @param string $textToInspect     The string to inspect.
 */
function inspect_string_custom_hotword(
    // TODO(developer): Replace sample parameters before running the code.
    string $projectId,
    string $textToInspect = 'patient name: John Doe'
): 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);

    // Construct hotword rules
    $hotwordRule = (new HotwordRule())
        ->setHotwordRegex(
            (new Regex())
                ->setPattern('patient')
        )
        ->setProximity(
            (new Proximity())
                ->setWindowBefore(50)
        )
        ->setLikelihoodAdjustment(
            (new LikelihoodAdjustment())
                ->setFixedLikelihood(Likelihood::VERY_LIKELY)
        );

    // Construct a ruleset that applies the hotword rule to the PERSON_NAME infotype.
    $personName = (new InfoType())
        ->setName('PERSON_NAME');
    $inspectionRuleSet = (new InspectionRuleSet())
        ->setInfoTypes([$personName])
        ->setRules([
            (new InspectionRule())
                ->setHotwordRule($hotwordRule),
        ]);

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

    // 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

Untuk mempelajari cara menginstal dan menggunakan library klien untuk Perlindungan Data Sensitif, lihat library klien Perlindungan Data Sensitif.

Untuk melakukan autentikasi ke Perlindungan Data Sensitif, siapkan Kredensial Default Aplikasi. Untuk mengetahui informasi selengkapnya, baca Menyiapkan autentikasi untuk lingkungan pengembangan lokal.

import google.cloud.dlp


def inspect_string_w_custom_hotword(
    project: str, content_string: str, custom_hotword: str = "patient"
) -> None:
    """Uses the Data Loss Prevention API increase likelihood for matches on
       PERSON_NAME if the user specified custom hot-word is present. Only
       includes findings with the increased likelihood by setting a minimum
       likelihood threshold of VERY_LIKELY.

    Args:
        project: The Google Cloud project id to use as a parent resource.
        content_string: The string to inspect.
        custom_hotword: The custom hot-word used for likelihood boosting.
    """

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

    # Construct a rule set with caller provided hotword, with a likelihood
    # boost to VERY_LIKELY when the hotword are present within the 50 character-
    # window preceding the PII finding.
    hotword_rule = {
        "hotword_regex": {"pattern": custom_hotword},
        "likelihood_adjustment": {
            "fixed_likelihood": google.cloud.dlp_v2.Likelihood.VERY_LIKELY
        },
        "proximity": {"window_before": 50},
    }

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

    # Construct the configuration dictionary with the custom regex info type.
    inspect_config = {
        "rule_set": rule_set,
        "min_likelihood": google.cloud.dlp_v2.Likelihood.VERY_LIKELY,
        "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.")

Langkah selanjutnya

Untuk menelusuri dan memfilter contoh kode untuk produk Google Cloud lainnya, lihat Google Cloud browser contoh.