חישוב של l-diversity עבור מערך נתונים

using Google.Api.Gax.ResourceNames;
using Google.Cloud.Dlp.V2;
using Google.Cloud.PubSub.V1;
using Newtonsoft.Json;
using System;
using System.Collections.Generic;
using System.Linq;
using System.Threading;
using System.Threading.Tasks;
using static Google.Cloud.Dlp.V2.Action.Types;
using static Google.Cloud.Dlp.V2.PrivacyMetric.Types;

public class RiskAnalysisCreateLDiversity
{
    public static object LDiversity(
        string callingProjectId,
        string tableProjectId,
        string datasetId,
        string tableId,
        string topicId,
        string subscriptionId,
        IEnumerable<FieldId> quasiIds,
        string sensitiveAttribute)
    {
        var dlp = DlpServiceClient.Create();

        // Construct + submit the job
        var ldiversityConfig = new LDiversityConfig
        {
            SensitiveAttribute = new FieldId { Name = sensitiveAttribute },
            QuasiIds = { quasiIds }
        };

        var config = new RiskAnalysisJobConfig
        {
            PrivacyMetric = new PrivacyMetric
            {
                LDiversityConfig = ldiversityConfig
            },
            SourceTable = new BigQueryTable
            {
                ProjectId = tableProjectId,
                DatasetId = datasetId,
                TableId = tableId
            },
            Actions =
            {
                new Google.Cloud.Dlp.V2.Action
                {
                    PubSub = new PublishToPubSub
                    {
                        Topic = $"projects/{callingProjectId}/topics/{topicId}"
                    }
                }
            }
        };

        var submittedJob = dlp.CreateDlpJob(
            new CreateDlpJobRequest
            {
                ParentAsProjectName = new ProjectName(callingProjectId),
                RiskJob = config
            });

        // Listen to pub/sub for the job
        var subscriptionName = new SubscriptionName(callingProjectId, subscriptionId);
        var subscriber = SubscriberClient.CreateAsync(subscriptionName).Result;

        // SimpleSubscriber runs your message handle function on multiple
        // threads to maximize throughput.
        var done = new ManualResetEventSlim(false);
        subscriber.StartAsync((PubsubMessage message, CancellationToken cancel) =>
        {
            if (message.Attributes["DlpJobName"] == submittedJob.Name)
            {
                Thread.Sleep(500); // Wait for DLP API results to become consistent
                done.Set();
                return Task.FromResult(SubscriberClient.Reply.Ack);
            }
            else
            {
                return Task.FromResult(SubscriberClient.Reply.Nack);
            }
        });

        done.Wait(TimeSpan.FromMinutes(10)); // 10 minute timeout; may not work for large jobs
        subscriber.StopAsync(CancellationToken.None).Wait();

        // Process results
        var resultJob = dlp.GetDlpJob(
            new GetDlpJobRequest
            {
                DlpJobName = DlpJobName.Parse(submittedJob.Name)
            });

        var result = resultJob.RiskDetails.LDiversityResult;

        for (var bucketIdx = 0; bucketIdx < result.SensitiveValueFrequencyHistogramBuckets.Count; bucketIdx++)
        {
            var bucket = result.SensitiveValueFrequencyHistogramBuckets[bucketIdx];
            Console.WriteLine($"Bucket {bucketIdx}");
            Console.WriteLine($"  Bucket size range: [{bucket.SensitiveValueFrequencyLowerBound}, {bucket.SensitiveValueFrequencyUpperBound}].");
            Console.WriteLine($"  {bucket.BucketSize} unique value(s) total.");

            foreach (var bucketValue in bucket.BucketValues)
            {
                // 'UnpackValue(x)' is a prettier version of 'x.toString()'
                Console.WriteLine($"    Quasi-ID values: [{String.Join(',', bucketValue.QuasiIdsValues.Select(x => UnpackValue(x)))}]");
                Console.WriteLine($"    Class size: {bucketValue.EquivalenceClassSize}");

                foreach (var topValue in bucketValue.TopSensitiveValues)
                {
                    Console.WriteLine($"    Sensitive value {UnpackValue(topValue.Value)} occurs {topValue.Count} time(s).");
                }
            }
        }

        return result;
    }

    public static string UnpackValue(Value protoValue)
    {
        var jsonValue = JsonConvert.DeserializeObject<Dictionary<string, object>>(protoValue.ToString());
        return jsonValue.Values.ElementAt(0).ToString();
    }
}

import (
	"context"
	"fmt"
	"io"
	"strings"
	"time"

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

// riskLDiversity computes the L Diversity of the given columns.
func riskLDiversity(w io.Writer, projectID, dataProject, pubSubTopic, pubSubSub, datasetID, tableID, sensitiveAttribute string, columnNames ...string) error {
	// projectID := "my-project-id"
	// dataProject := "bigquery-public-data"
	// pubSubTopic := "dlp-risk-sample-topic"
	// pubSubSub := "dlp-risk-sample-sub"
	// datasetID := "nhtsa_traffic_fatalities"
	// tableID := "accident_2015"
	// sensitiveAttribute := "city"
	// columnNames := "state_number", "county"
	ctx := context.Background()
	client, err := dlp.NewClient(ctx)
	if err != nil {
		return fmt.Errorf("dlp.NewClient: %w", err)
	}
	defer client.Close()

	// Create a PubSub Client used to listen for when the inspect job finishes.
	pubsubClient, err := pubsub.NewClient(ctx, projectID)
	if err != nil {
		return err
	}
	defer pubsubClient.Close()

	// Create a PubSub subscription we can use to listen for messages.
	// Create the Topic if it doesn't exist.
	t := pubsubClient.Topic(pubSubTopic)
	topicExists, err := t.Exists(ctx)
	if err != nil {
		return err
	}
	if !topicExists {
		if t, err = pubsubClient.CreateTopic(ctx, pubSubTopic); err != nil {
			return err
		}
	}

	// Create the Subscription if it doesn't exist.
	s := pubsubClient.Subscription(pubSubSub)
	subExists, err := s.Exists(ctx)
	if err != nil {
		return err
	}
	if !subExists {
		if s, err = pubsubClient.CreateSubscription(ctx, pubSubSub, pubsub.SubscriptionConfig{Topic: t}); err != nil {
			return err
		}
	}

	// topic is the PubSub topic string where messages should be sent.
	topic := "projects/" + projectID + "/topics/" + pubSubTopic

	// Build the QuasiID slice.
	var q []*dlppb.FieldId
	for _, c := range columnNames {
		q = append(q, &dlppb.FieldId{Name: c})
	}

	// Create a configured request.
	req := &dlppb.CreateDlpJobRequest{
		Parent: fmt.Sprintf("projects/%s/locations/global", projectID),
		Job: &dlppb.CreateDlpJobRequest_RiskJob{
			RiskJob: &dlppb.RiskAnalysisJobConfig{
				// PrivacyMetric configures what to compute.
				PrivacyMetric: &dlppb.PrivacyMetric{
					Type: &dlppb.PrivacyMetric_LDiversityConfig_{
						LDiversityConfig: &dlppb.PrivacyMetric_LDiversityConfig{
							QuasiIds: q,
							SensitiveAttribute: &dlppb.FieldId{
								Name: sensitiveAttribute,
							},
						},
					},
				},
				// SourceTable describes where to find the data.
				SourceTable: &dlppb.BigQueryTable{
					ProjectId: dataProject,
					DatasetId: datasetID,
					TableId:   tableID,
				},
				// Send a message to PubSub using Actions.
				Actions: []*dlppb.Action{
					{
						Action: &dlppb.Action_PubSub{
							PubSub: &dlppb.Action_PublishToPubSub{
								Topic: topic,
							},
						},
					},
				},
			},
		},
	}
	// Create the risk job.
	j, err := client.CreateDlpJob(ctx, req)
	if err != nil {
		return fmt.Errorf("CreateDlpJob: %w", err)
	}
	fmt.Fprintf(w, "Created job: %v\n", j.GetName())
	// Wait for the risk job to finish by waiting for a PubSub message.
	// This only waits for 10 minutes. For long jobs, consider using a truly
	// asynchronous execution model such as Cloud Functions.
	ctx, cancel := context.WithTimeout(ctx, 10*time.Minute)
	defer cancel()
	err = s.Receive(ctx, func(ctx context.Context, msg *pubsub.Message) {
		// If this is the wrong job, do not process the result.
		if msg.Attributes["DlpJobName"] != j.GetName() {
			msg.Nack()
			return
		}
		msg.Ack()
		time.Sleep(500 * time.Millisecond)
		j, err := client.GetDlpJob(ctx, &dlppb.GetDlpJobRequest{
			Name: j.GetName(),
		})
		if err != nil {
			fmt.Fprintf(w, "GetDlpJob: %v", err)
			return
		}
		h := j.GetRiskDetails().GetLDiversityResult().GetSensitiveValueFrequencyHistogramBuckets()
		for i, b := range h {
			fmt.Fprintf(w, "Histogram bucket %v\n", i)
			fmt.Fprintf(w, "  Size range: [%v,%v]\n", b.GetSensitiveValueFrequencyLowerBound(), b.GetSensitiveValueFrequencyUpperBound())
			fmt.Fprintf(w, "  %v unique values total\n", b.GetBucketSize())
			for _, v := range b.GetBucketValues() {
				var qvs []string
				for _, qv := range v.GetQuasiIdsValues() {
					qvs = append(qvs, qv.String())
				}
				fmt.Fprintf(w, "    QuasiID values: %s\n", strings.Join(qvs, ", "))
				fmt.Fprintf(w, "    Class size: %v\n", v.GetEquivalenceClassSize())
				for _, sv := range v.GetTopSensitiveValues() {
					fmt.Fprintf(w, "    Sensitive value %v occurs %v times\n", sv.GetValue(), sv.GetCount())
				}
			}
		}
		// Stop listening for more messages.
		cancel()
	})
	if err != nil {
		return fmt.Errorf("Recieve: %w", err)
	}
	return nil
}

import com.google.api.core.SettableApiFuture;
import com.google.cloud.dlp.v2.DlpServiceClient;
import com.google.cloud.dlp.v2.DlpServiceSettings;
import com.google.cloud.pubsub.v1.AckReplyConsumer;
import com.google.cloud.pubsub.v1.MessageReceiver;
import com.google.cloud.pubsub.v1.Subscriber;
import com.google.privacy.dlp.v2.Action;
import com.google.privacy.dlp.v2.Action.PublishToPubSub;
import com.google.privacy.dlp.v2.AnalyzeDataSourceRiskDetails.LDiversityResult;
import com.google.privacy.dlp.v2.AnalyzeDataSourceRiskDetails.LDiversityResult.LDiversityEquivalenceClass;
import com.google.privacy.dlp.v2.AnalyzeDataSourceRiskDetails.LDiversityResult.LDiversityHistogramBucket;
import com.google.privacy.dlp.v2.BigQueryTable;
import com.google.privacy.dlp.v2.CreateDlpJobRequest;
import com.google.privacy.dlp.v2.DlpJob;
import com.google.privacy.dlp.v2.FieldId;
import com.google.privacy.dlp.v2.GetDlpJobRequest;
import com.google.privacy.dlp.v2.LocationName;
import com.google.privacy.dlp.v2.PrivacyMetric;
import com.google.privacy.dlp.v2.PrivacyMetric.LDiversityConfig;
import com.google.privacy.dlp.v2.RiskAnalysisJobConfig;
import com.google.privacy.dlp.v2.Value;
import com.google.privacy.dlp.v2.ValueFrequency;
import com.google.pubsub.v1.ProjectSubscriptionName;
import com.google.pubsub.v1.ProjectTopicName;
import com.google.pubsub.v1.PubsubMessage;
import java.io.IOException;
import java.util.Arrays;
import java.util.List;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;
import java.util.stream.Collectors;
import org.threeten.bp.Duration;

@SuppressWarnings("checkstyle:AbbreviationAsWordInName")
class RiskAnalysisLDiversity {

  public static void main(String[] args) throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-project-id";
    String datasetId = "your-bigquery-dataset-id";
    String tableId = "your-bigquery-table-id";
    String topicId = "pub-sub-topic";
    String subscriptionId = "pub-sub-subscription";
    calculateLDiversity(projectId, datasetId, tableId, topicId, subscriptionId);
  }

  public static void calculateLDiversity(
      String projectId, String datasetId, String tableId, String topicId, String subscriptionId)
      throws ExecutionException, InterruptedException, 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.
    DlpServiceSettings.Builder dlpServiceSettingsBuilder = DlpServiceSettings.newBuilder();
    dlpServiceSettingsBuilder
        .getDlpJobSettings()
        .setRetrySettings(
            dlpServiceSettingsBuilder
                .getDlpJobSettings()
                .getRetrySettings()
                .toBuilder()
                .setTotalTimeout(Duration.ofSeconds(600))
                .build());
    try (DlpServiceClient dlpServiceClient =
        DlpServiceClient.create(dlpServiceSettingsBuilder.build())) {
      // Specify the BigQuery table to analyze
      BigQueryTable bigQueryTable =
          BigQueryTable.newBuilder()
              .setProjectId(projectId)
              .setDatasetId(datasetId)
              .setTableId(tableId)
              .build();

      // These values represent the column names of quasi-identifiers to analyze
      List<String> quasiIds = Arrays.asList("Age", "Mystery");

      // This value represents the column name to compare the quasi-identifiers against
      String sensitiveAttribute = "Name";

      // Configure the privacy metric for the job
      FieldId sensitiveAttributeField = FieldId.newBuilder().setName(sensitiveAttribute).build();
      List<FieldId> quasiIdFields =
          quasiIds.stream()
              .map(columnName -> FieldId.newBuilder().setName(columnName).build())
              .collect(Collectors.toList());
      LDiversityConfig ldiversityConfig =
          LDiversityConfig.newBuilder()
              .addAllQuasiIds(quasiIdFields)
              .setSensitiveAttribute(sensitiveAttributeField)
              .build();
      PrivacyMetric privacyMetric =
          PrivacyMetric.newBuilder().setLDiversityConfig(ldiversityConfig).build();

      // Create action to publish job status notifications over Google Cloud Pub/
      ProjectTopicName topicName = ProjectTopicName.of(projectId, topicId);
      PublishToPubSub publishToPubSub =
          PublishToPubSub.newBuilder().setTopic(topicName.toString()).build();
      Action action = Action.newBuilder().setPubSub(publishToPubSub).build();

      // Configure the risk analysis job to perform
      RiskAnalysisJobConfig riskAnalysisJobConfig =
          RiskAnalysisJobConfig.newBuilder()
              .setSourceTable(bigQueryTable)
              .setPrivacyMetric(privacyMetric)
              .addActions(action)
              .build();

      // Build the request to be sent by the client
      CreateDlpJobRequest createDlpJobRequest =
          CreateDlpJobRequest.newBuilder()
              .setParent(LocationName.of(projectId, "global").toString())
              .setRiskJob(riskAnalysisJobConfig)
              .build();

      // Send the request to the API using the client
      DlpJob dlpJob = dlpServiceClient.createDlpJob(createDlpJobRequest);

      // Set up a Pub/Sub subscriber to listen on the job completion status
      final SettableApiFuture<Boolean> done = SettableApiFuture.create();

      ProjectSubscriptionName subscriptionName =
          ProjectSubscriptionName.of(projectId, subscriptionId);

      MessageReceiver messageHandler =
          (PubsubMessage pubsubMessage, AckReplyConsumer ackReplyConsumer) -> {
            handleMessage(dlpJob, done, pubsubMessage, ackReplyConsumer);
          };
      Subscriber subscriber = Subscriber.newBuilder(subscriptionName, messageHandler).build();
      subscriber.startAsync();

      // Wait for job completion semi-synchronously
      // For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
      try {
        done.get(15, TimeUnit.MINUTES);
      } catch (TimeoutException e) {
        System.out.println("Job was not completed after 15 minutes.");
        return;
      } finally {
        subscriber.stopAsync();
        subscriber.awaitTerminated();
      }

      // Build a request to get the completed job
      GetDlpJobRequest getDlpJobRequest =
          GetDlpJobRequest.newBuilder().setName(dlpJob.getName()).build();

      // Retrieve completed job status
      DlpJob completedJob = dlpServiceClient.getDlpJob(getDlpJobRequest);
      System.out.println("Job status: " + completedJob.getState());
      System.out.println("Job name: " + dlpJob.getName());

      // Get the result and parse through and process the information
      LDiversityResult ldiversityResult = completedJob.getRiskDetails().getLDiversityResult();
      List<LDiversityHistogramBucket> histogramBucketList =
          ldiversityResult.getSensitiveValueFrequencyHistogramBucketsList();
      for (LDiversityHistogramBucket result : histogramBucketList) {
        for (LDiversityEquivalenceClass bucket : result.getBucketValuesList()) {
          List<String> quasiIdValues =
              bucket.getQuasiIdsValuesList().stream()
                  .map(Value::toString)
                  .collect(Collectors.toList());

          System.out.println("\tQuasi-ID values: " + String.join(", ", quasiIdValues));
          System.out.println("\tClass size: " + bucket.getEquivalenceClassSize());

          for (ValueFrequency valueFrequency : bucket.getTopSensitiveValuesList()) {
            System.out.printf(
                "\t\tSensitive value %s occurs %d time(s).\n",
                valueFrequency.getValue().toString(), valueFrequency.getCount());
          }
        }
      }
    }
  }

  // handleMessage injects the job and settableFuture into the message reciever interface
  private static void handleMessage(
      DlpJob job,
      SettableApiFuture<Boolean> done,
      PubsubMessage pubsubMessage,
      AckReplyConsumer ackReplyConsumer) {
    String messageAttribute = pubsubMessage.getAttributesMap().get("DlpJobName");
    if (job.getName().equals(messageAttribute)) {
      done.set(true);
      ackReplyConsumer.ack();
    } else {
      ackReplyConsumer.nack();
    }
  }
}

// Import the Google Cloud client libraries
const DLP = require('@google-cloud/dlp');
const {PubSub} = require('@google-cloud/pubsub');

// Instantiates clients
const dlp = new DLP.DlpServiceClient();
const pubsub = new PubSub();

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

// The project ID the table is stored under
// This may or (for public datasets) may not equal the calling project ID
// const tableProjectId = 'my-project';

// The ID of the dataset to inspect, e.g. 'my_dataset'
// const datasetId = 'my_dataset';

// The ID of the table to inspect, e.g. 'my_table'
// const tableId = 'my_table';

// The name of the Pub/Sub topic to notify once the job completes
// TODO(developer): create a Pub/Sub topic to use for this
// const topicId = 'MY-PUBSUB-TOPIC'

// The name of the Pub/Sub subscription to use when listening for job
// completion notifications
// TODO(developer): create a Pub/Sub subscription to use for this
// const subscriptionId = 'MY-PUBSUB-SUBSCRIPTION'

// The column to measure l-diversity relative to, e.g. 'firstName'
// const sensitiveAttribute = 'name';

// A set of columns that form a composite key ('quasi-identifiers')
// const quasiIds = [{ name: 'age' }, { name: 'city' }];

async function lDiversityAnalysis() {
  const sourceTable = {
    projectId: tableProjectId,
    datasetId: datasetId,
    tableId: tableId,
  };

  // Construct request for creating a risk analysis job
  const request = {
    parent: `projects/${projectId}/locations/global`,
    riskJob: {
      privacyMetric: {
        lDiversityConfig: {
          quasiIds: quasiIds,
          sensitiveAttribute: {
            name: sensitiveAttribute,
          },
        },
      },
      sourceTable: sourceTable,
      actions: [
        {
          pubSub: {
            topic: `projects/${projectId}/topics/${topicId}`,
          },
        },
      ],
    },
  };

  // Create helper function for unpacking values
  const getValue = obj => obj[Object.keys(obj)[0]];

  // Run risk analysis job
  const [topicResponse] = await pubsub.topic(topicId).get();
  const subscription = await topicResponse.subscription(subscriptionId);
  const [jobsResponse] = await dlp.createDlpJob(request);
  const jobName = jobsResponse.name;
  console.log(`Job created. Job name: ${jobName}`);
  // Watch the Pub/Sub topic until the DLP job finishes
  await new Promise((resolve, reject) => {
    const messageHandler = message => {
      if (message.attributes && message.attributes.DlpJobName === jobName) {
        message.ack();
        subscription.removeListener('message', messageHandler);
        subscription.removeListener('error', errorHandler);
        resolve(jobName);
      } else {
        message.nack();
      }
    };

    const errorHandler = err => {
      subscription.removeListener('message', messageHandler);
      subscription.removeListener('error', errorHandler);
      reject(err);
    };

    subscription.on('message', messageHandler);
    subscription.on('error', errorHandler);
  });
  setTimeout(() => {
    console.log(' Waiting for DLP job to fully complete');
  }, 500);
  const [job] = await dlp.getDlpJob({name: jobName});
  const histogramBuckets =
    job.riskDetails.lDiversityResult.sensitiveValueFrequencyHistogramBuckets;

  histogramBuckets.forEach((histogramBucket, histogramBucketIdx) => {
    console.log(`Bucket ${histogramBucketIdx}:`);

    console.log(
      `Bucket size range: [${histogramBucket.sensitiveValueFrequencyLowerBound}, ${histogramBucket.sensitiveValueFrequencyUpperBound}]`
    );
    histogramBucket.bucketValues.forEach(valueBucket => {
      const quasiIdValues = valueBucket.quasiIdsValues
        .map(getValue)
        .join(', ');
      console.log(`  Quasi-ID values: {${quasiIdValues}}`);
      console.log(`  Class size: ${valueBucket.equivalenceClassSize}`);
      valueBucket.topSensitiveValues.forEach(valueObj => {
        console.log(
          `    Sensitive value ${getValue(valueObj.value)} occurs ${
            valueObj.count
          } time(s).`
        );
      });
    });
  });
}

await lDiversityAnalysis();

use Google\Cloud\Dlp\V2\Action;
use Google\Cloud\Dlp\V2\Action\PublishToPubSub;
use Google\Cloud\Dlp\V2\BigQueryTable;
use Google\Cloud\Dlp\V2\Client\DlpServiceClient;
use Google\Cloud\Dlp\V2\CreateDlpJobRequest;
use Google\Cloud\Dlp\V2\DlpJob\JobState;
use Google\Cloud\Dlp\V2\FieldId;
use Google\Cloud\Dlp\V2\GetDlpJobRequest;
use Google\Cloud\Dlp\V2\PrivacyMetric;
use Google\Cloud\Dlp\V2\PrivacyMetric\LDiversityConfig;
use Google\Cloud\Dlp\V2\RiskAnalysisJobConfig;
use Google\Cloud\PubSub\PubSubClient;

/**
 * Computes the l-diversity of a column set in a Google BigQuery table.
 *
 * @param string    $callingProjectId    The project ID to run the API call under
 * @param string    $dataProjectId       The project ID containing the target Datastore
 * @param string    $topicId             The name of the Pub/Sub topic to notify once the job completes
 * @param string    $subscriptionId      The name of the Pub/Sub subscription to use when listening for job
 * @param string    $datasetId           The ID of the dataset to inspect
 * @param string    $tableId             The ID of the table to inspect
 * @param string    $sensitiveAttribute  The column to measure l-diversity relative to, e.g. "firstName"
 * @param string[]  $quasiIdNames        Array columns that form a composite key (quasi-identifiers)
 */
function l_diversity(
    string $callingProjectId,
    string $dataProjectId,
    string $topicId,
    string $subscriptionId,
    string $datasetId,
    string $tableId,
    string $sensitiveAttribute,
    array $quasiIdNames
): void {
    // Instantiate a client.
    $dlp = new DlpServiceClient();
    $pubsub = new PubSubClient();
    $topic = $pubsub->topic($topicId);

    // Construct risk analysis config
    $quasiIds = array_map(
        function ($id) {
            return (new FieldId())->setName($id);
        },
        $quasiIdNames
    );

    $sensitiveField = (new FieldId())
        ->setName($sensitiveAttribute);

    $statsConfig = (new LDiversityConfig())
        ->setQuasiIds($quasiIds)
        ->setSensitiveAttribute($sensitiveField);

    $privacyMetric = (new PrivacyMetric())
        ->setLDiversityConfig($statsConfig);

    // Construct items to be analyzed
    $bigqueryTable = (new BigQueryTable())
        ->setProjectId($dataProjectId)
        ->setDatasetId($datasetId)
        ->setTableId($tableId);

    // Construct the action to run when job completes
    $pubSubAction = (new PublishToPubSub())
        ->setTopic($topic->name());

    $action = (new Action())
        ->setPubSub($pubSubAction);

    // Construct risk analysis job config to run
    $riskJob = (new RiskAnalysisJobConfig())
        ->setPrivacyMetric($privacyMetric)
        ->setSourceTable($bigqueryTable)
        ->setActions([$action]);

    // Listen for job notifications via an existing topic/subscription.
    $subscription = $topic->subscription($subscriptionId);

    // Submit request
    $parent = "projects/$callingProjectId/locations/global";
    $createDlpJobRequest = (new CreateDlpJobRequest())
        ->setParent($parent)
        ->setRiskJob($riskJob);
    $job = $dlp->createDlpJob($createDlpJobRequest);

    // Poll Pub/Sub using exponential backoff until job finishes
    // Consider using an asynchronous execution model such as Cloud Functions
    $attempt = 1;
    $startTime = time();
    do {
        foreach ($subscription->pull() as $message) {
            if (
                isset($message->attributes()['DlpJobName']) &&
                $message->attributes()['DlpJobName'] === $job->getName()
            ) {
                $subscription->acknowledge($message);
                // Get the updated job. Loop to avoid race condition with DLP API.
                do {
                    $getDlpJobRequest = (new GetDlpJobRequest())
                        ->setName($job->getName());
                    $job = $dlp->getDlpJob($getDlpJobRequest);
                } while ($job->getState() == JobState::RUNNING);
                break 2; // break from parent do while
            }
        }
        print('Waiting for job to complete' . PHP_EOL);
        // Exponential backoff with max delay of 60 seconds
        sleep(min(60, pow(2, ++$attempt)));
    } while (time() - $startTime < 600); // 10 minute timeout

    // Print finding counts
    printf('Job %s status: %s' . PHP_EOL, $job->getName(), JobState::name($job->getState()));
    switch ($job->getState()) {
        case JobState::DONE:
            $histBuckets = $job->getRiskDetails()->getLDiversityResult()->getSensitiveValueFrequencyHistogramBuckets();

            foreach ($histBuckets as $bucketIndex => $histBucket) {
                // Print bucket stats
                printf('Bucket %s:' . PHP_EOL, $bucketIndex);
                printf(
                    '  Bucket size range: [%s, %s]' . PHP_EOL,
                    $histBucket->getSensitiveValueFrequencyLowerBound(),
                    $histBucket->getSensitiveValueFrequencyUpperBound()
                );

                // Print bucket values
                foreach ($histBucket->getBucketValues() as $percent => $valueBucket) {
                    printf(
                        '  Class size: %s' . PHP_EOL,
                        $valueBucket->getEquivalenceClassSize()
                    );

                    // Pretty-print quasi-ID values
                    print('  Quasi-ID values:' . PHP_EOL);
                    foreach ($valueBucket->getQuasiIdsValues() as $index => $value) {
                        print('    ' . $value->serializeToJsonString() . PHP_EOL);
                    }

                    // Pretty-print sensitive values
                    $topValues = $valueBucket->getTopSensitiveValues();
                    foreach ($topValues as $topValue) {
                        printf(
                            '  Sensitive value %s occurs %s time(s).' . PHP_EOL,
                            $topValue->getValue()->serializeToJsonString(),
                            $topValue->getCount()
                        );
                    }
                }
            }
            break;
        case JobState::FAILED:
            printf('Job %s had errors:' . PHP_EOL, $job->getName());
            $errors = $job->getErrors();
            foreach ($errors as $error) {
                var_dump($error->getDetails());
            }
            break;
        case JobState::PENDING:
            print('Job has not completed. Consider a longer timeout or an asynchronous execution model' . PHP_EOL);
            break;
        default:
            print('Unexpected job state. Most likely, the job is either running or has not yet started.');
    }
}

import concurrent.futures
from typing import List

import google.cloud.dlp
from google.cloud.dlp_v2 import types
import google.cloud.pubsub


def l_diversity_analysis(
    project: str,
    table_project_id: str,
    dataset_id: str,
    table_id: str,
    topic_id: str,
    subscription_id: str,
    sensitive_attribute: str,
    quasi_ids: List[str],
    timeout: int = 300,
) -> None:
    """Uses the Data Loss Prevention API to compute the l-diversity of a
        column set in a Google BigQuery table.
    Args:
        project: The Google Cloud project id to use as a parent resource.
        table_project_id: The Google Cloud project id where the BigQuery table
            is stored.
        dataset_id: The id of the dataset to inspect.
        table_id: The id of the table to inspect.
        topic_id: The name of the Pub/Sub topic to notify once the job
            completes.
        subscription_id: The name of the Pub/Sub subscription to use when
            listening for job completion notifications.
        sensitive_attribute: The column to measure l-diversity relative to.
        quasi_ids: A set of columns that form a composite key.
        timeout: The number of seconds to wait for a response from the API.

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

    # Create helper function for unpacking values
    def get_values(obj: types.Value) -> int:
        return int(obj.integer_value)

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

    # Convert the project id into a full resource id.
    topic = google.cloud.pubsub.PublisherClient.topic_path(project, topic_id)
    parent = f"projects/{project}/locations/global"

    # Location info of the BigQuery table.
    source_table = {
        "project_id": table_project_id,
        "dataset_id": dataset_id,
        "table_id": table_id,
    }

    # Convert quasi id list to Protobuf type
    def map_fields(field: str) -> dict:
        return {"name": field}

    quasi_ids = map(map_fields, quasi_ids)

    # Tell the API where to send a notification when the job is complete.
    actions = [{"pub_sub": {"topic": topic}}]

    # Configure risk analysis job
    # Give the name of the numeric column to compute risk metrics for
    risk_job = {
        "privacy_metric": {
            "l_diversity_config": {
                "quasi_ids": quasi_ids,
                "sensitive_attribute": {"name": sensitive_attribute},
            }
        },
        "source_table": source_table,
        "actions": actions,
    }

    # Call API to start risk analysis job
    operation = dlp.create_dlp_job(request={"parent": parent, "risk_job": risk_job})

    def callback(message: google.cloud.pubsub_v1.subscriber.message.Message) -> None:
        if message.attributes["DlpJobName"] == operation.name:
            # This is the message we're looking for, so acknowledge it.
            message.ack()

            # Now that the job is done, fetch the results and print them.
            job = dlp.get_dlp_job(request={"name": operation.name})
            print(f"Job name: {job.name}")
            histogram_buckets = (
                job.risk_details.l_diversity_result.sensitive_value_frequency_histogram_buckets  # noqa: E501
            )
            # Print bucket stats
            for i, bucket in enumerate(histogram_buckets):
                print(f"Bucket {i}:")
                print(
                    "   Bucket size range: [{}, {}]".format(
                        bucket.sensitive_value_frequency_lower_bound,
                        bucket.sensitive_value_frequency_upper_bound,
                    )
                )
                for value_bucket in bucket.bucket_values:
                    print(
                        "   Quasi-ID values: {}".format(
                            map(get_values, value_bucket.quasi_ids_values)
                        )
                    )
                    print(f"   Class size: {value_bucket.equivalence_class_size}")
                    for value in value_bucket.top_sensitive_values:
                        print(
                            "   Sensitive value {} occurs {} time(s)".format(
                                value.value, value.count
                            )
                        )
            subscription.set_result(None)
        else:
            # This is not the message we're looking for.
            message.drop()

    # Create a Pub/Sub client and find the subscription. The subscription is
    # expected to already be listening to the topic.
    subscriber = google.cloud.pubsub.SubscriberClient()
    subscription_path = subscriber.subscription_path(project, subscription_id)
    subscription = subscriber.subscribe(subscription_path, callback)

    try:
        subscription.result(timeout=timeout)
    except concurrent.futures.TimeoutError:
        print(
            "No event received before the timeout. Please verify that the "
            "subscription provided is subscribed to the topic provided."
        )
        subscription.close()