Inspect BigQuery for sensitive data with sampling

The following examples demonstrate using the Cloud Data Loss Prevention API to scan a 1000-row subset of a BigQuery table. The scan starts from a random row.

Documentation pages that include this code sample

To view the code sample used in context, see the following documentation:

Code sample

Java

To learn how to install and use the client library for Cloud DLP, see the Cloud DLP Client Libraries.


import com.google.api.core.SettableApiFuture;
import com.google.cloud.dlp.v2.DlpServiceClient;
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.BigQueryOptions;
import com.google.privacy.dlp.v2.BigQueryOptions.SampleMethod;
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.InfoType;
import com.google.privacy.dlp.v2.InfoTypeStats;
import com.google.privacy.dlp.v2.InspectConfig;
import com.google.privacy.dlp.v2.InspectDataSourceDetails;
import com.google.privacy.dlp.v2.InspectJobConfig;
import com.google.privacy.dlp.v2.LocationName;
import com.google.privacy.dlp.v2.StorageConfig;
import com.google.pubsub.v1.ProjectSubscriptionName;
import com.google.pubsub.v1.PubsubMessage;
import java.io.IOException;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;

public class InspectBigQueryTableWithSampling {

  public static void main(String[] args) throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-project-id";
    String topicId = "your-pubsub-topic-id";
    String subscriptionId = "your-pubsub-subscription-id";
    inspectBigQueryTableWithSampling(projectId, topicId, subscriptionId);
  }

  // Inspects a BigQuery Table
  public static void inspectBigQueryTableWithSampling(
      String projectId, 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.
    try (DlpServiceClient dlp = DlpServiceClient.create()) {
      // Specify the BigQuery table to be inspected.
      BigQueryTable tableReference =
          BigQueryTable.newBuilder()
              .setProjectId("bigquery-public-data")
              .setDatasetId("usa_names")
              .setTableId("usa_1910_current")
              .build();

      BigQueryOptions bigQueryOptions =
          BigQueryOptions.newBuilder()
              .setTableReference(tableReference)
              .setRowsLimit(1000)
              .setSampleMethod(SampleMethod.RANDOM_START)
              .addIdentifyingFields(FieldId.newBuilder().setName("name"))
              .build();

      StorageConfig storageConfig =
          StorageConfig.newBuilder().setBigQueryOptions(bigQueryOptions).build();

      // Specify the type of info the inspection will look for.
      // See https://cloud.google.com/dlp/docs/infotypes-reference for complete list of info types
      InfoType infoType = InfoType.newBuilder().setName("PERSON_NAME").build();

      // Specify how the content should be inspected.
      InspectConfig inspectConfig =
          InspectConfig.newBuilder().addInfoTypes(infoType).setIncludeQuote(true).build();

      // Specify the action that is triggered when the job completes.
      String pubSubTopic = String.format("projects/%s/topics/%s", projectId, topicId);
      Action.PublishToPubSub publishToPubSub =
          Action.PublishToPubSub.newBuilder().setTopic(pubSubTopic).build();
      Action action = Action.newBuilder().setPubSub(publishToPubSub).build();

      // Configure the long running job we want the service to perform.
      InspectJobConfig inspectJobConfig =
          InspectJobConfig.newBuilder()
              .setStorageConfig(storageConfig)
              .setInspectConfig(inspectConfig)
              .addActions(action)
              .build();

      // Create the request for the job configured above.
      CreateDlpJobRequest createDlpJobRequest =
          CreateDlpJobRequest.newBuilder()
              .setParent(LocationName.of(projectId, "global").toString())
              .setInspectJob(inspectJobConfig)
              .build();

      // Use the client to send the request.
      final DlpJob dlpJob = dlp.createDlpJob(createDlpJobRequest);
      System.out.println("Job created: " + dlpJob.getName());

      // 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();
      }

      // Get the latest state of the job from the service
      GetDlpJobRequest request = GetDlpJobRequest.newBuilder().setName(dlpJob.getName()).build();
      DlpJob completedJob = dlp.getDlpJob(request);

      // Parse the response and process results.
      System.out.println("Job status: " + completedJob.getState());
      InspectDataSourceDetails.Result result = completedJob.getInspectDetails().getResult();
      System.out.println("Findings: ");
      for (InfoTypeStats infoTypeStat : result.getInfoTypeStatsList()) {
        System.out.print("\tInfo type: " + infoTypeStat.getInfoType().getName());
        System.out.println("\tCount: " + infoTypeStat.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();
    }
  }
}

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser