Java Code Examples for com.google.cloud.pubsub.v1.Subscriber#stopAsync()

private List<String> receiveLines(int expectedMessageCount) throws Exception {
  List<String> received = new CopyOnWriteArrayList<>();
  ProjectSubscriptionName subscriptionName = ProjectSubscriptionName.of(projectId,
      subscriptionId);

  MessageReceiver receiver = ((PubsubMessage message, AckReplyConsumer consumer) -> {
    try {
      String encoded = Json.asString(new org.apache.beam.sdk.io.gcp.pubsub.PubsubMessage(
          message.getData().toByteArray(), message.getAttributesMap()));
      received.add(encoded);
    } catch (IOException e) {
      throw new UncheckedIOException(e);
    }
    consumer.ack();
  });
  Subscriber subscriber = Subscriber.newBuilder(subscriptionName, receiver).build();
  subscriber.startAsync();
  while (received.size() < expectedMessageCount) {
    Thread.sleep(100);
  }
  subscriber.stopAsync();

  return received;
}
 

public static int pubSub(String subId, long timeoutSeconds, String projectId)
    throws InterruptedException {
  // String subId = "my-occurrence-subscription";
  // long timeoutSeconds = 20;
  // String projectId = "my-project-id";
  Subscriber subscriber = null;
  MessageReceiverExample receiver = new MessageReceiverExample();

  try {
    // Subscribe to the requested Pub/Sub channel
    ProjectSubscriptionName subName = ProjectSubscriptionName.of(projectId, subId);
    subscriber = Subscriber.newBuilder(subName, receiver).build();
    subscriber.startAsync().awaitRunning();
    // Sleep to listen for messages
    TimeUnit.SECONDS.sleep(timeoutSeconds);
  } finally {
    // Stop listening to the channel
    if (subscriber != null) {
      subscriber.stopAsync();
    }
  }
  // Print and return the number of Pub/Sub messages received
  System.out.println(receiver.messageCount);
  return receiver.messageCount;
}
 

public static void inspectGcsFile(
    String projectId, String gcsUri, 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 GCS file to be inspected.
    CloudStorageOptions cloudStorageOptions =
        CloudStorageOptions.newBuilder()
            .setFileSet(FileSet.newBuilder().setUrl(gcsUri))
            .build();

    StorageConfig storageConfig =
        StorageConfig.newBuilder().setCloudStorageOptions(cloudStorageOptions).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
    List<InfoType> infoTypes =
        Stream.of("PHONE_NUMBER", "EMAIL_ADDRESS", "CREDIT_CARD_NUMBER")
            .map(it -> InfoType.newBuilder().setName(it).build())
            .collect(Collectors.toList());

    // Specify how the content should be inspected.
    InspectConfig inspectConfig =
        InspectConfig.newBuilder()
            .addAllInfoTypes(infoTypes)
            .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());
    }
  }
}
 

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());
    }
  }
}
 

public static void inspectGcsFileWithSampling(
    String projectId, String gcsUri, 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 GCS file to be inspected and sampling configuration
    CloudStorageOptions cloudStorageOptions =
        CloudStorageOptions.newBuilder()
            .setFileSet(FileSet.newBuilder().setUrl(gcsUri))
            .setBytesLimitPerFile(200)
            .addFileTypes(FileType.TEXT_FILE)
            .setFilesLimitPercent(90)
            .setSampleMethod(SampleMethod.RANDOM_START)
            .build();

    StorageConfig storageConfig =
        StorageConfig.newBuilder().setCloudStorageOptions(cloudStorageOptions).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)
            .setExcludeInfoTypes(true)
            .setIncludeQuote(true)
            .setMinLikelihood(Likelihood.POSSIBLE)
            .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());
    }
  }
}
 

public static void numericalStatsAnalysis(
    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.
  try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {

    // Specify the BigQuery table to analyze
    BigQueryTable bigQueryTable =
        BigQueryTable.newBuilder()
            .setTableId(tableId)
            .setDatasetId(datasetId)
            .setProjectId(projectId)
            .build();

    // This represents the name of the column to analyze, which must contain numerical data
    String columnName = "Age";

    // Configure the privacy metric for the job
    FieldId fieldId = FieldId.newBuilder().setName(columnName).build();
    NumericalStatsConfig numericalStatsConfig =
        NumericalStatsConfig.newBuilder().setField(fieldId).build();
    PrivacyMetric privacyMetric =
        PrivacyMetric.newBuilder().setNumericalStatsConfig(numericalStatsConfig).build();

    // Create action to publish job status notifications over Google Cloud Pub/Sub
    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();

    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());

    // Get the result and parse through and process the information
    NumericalStatsResult result = completedJob.getRiskDetails().getNumericalStatsResult();

    System.out.printf(
        "Value range : [%.3f, %.3f]\n",
        result.getMinValue().getFloatValue(), result.getMaxValue().getFloatValue());

    int percent = 1;
    Double lastValue = null;
    for (Value quantileValue : result.getQuantileValuesList()) {
      Double currentValue = quantileValue.getFloatValue();
      if (lastValue == null || !lastValue.equals(currentValue)) {
        System.out.printf("Value at %s %% quantile : %.3f", percent, currentValue);
      }
      lastValue = currentValue;
    }
  }
}