Java Code Examples for org.apache.beam.runners.dataflow.options.DataflowPipelineOptions#setRunner()

private static DataflowPipelineOptions buildPipelineOptions(String... args) throws IOException {
  GcsUtil mockGcsUtil = mock(GcsUtil.class);
  when(mockGcsUtil.expand(any(GcsPath.class)))
      .then(invocation -> ImmutableList.of((GcsPath) invocation.getArguments()[0]));
  when(mockGcsUtil.bucketAccessible(any(GcsPath.class))).thenReturn(true);

  DataflowPipelineOptions options =
      PipelineOptionsFactory.fromArgs(args).as(DataflowPipelineOptions.class);
  options.setRunner(DataflowRunner.class);
  options.setGcpCredential(new TestCredential());
  options.setJobName("some-job-name");
  options.setProject("some-project");
  options.setRegion("some-region");
  options.setTempLocation(GcsPath.fromComponents("somebucket", "some/path").toString());
  options.setFilesToStage(new ArrayList<>());
  options.setGcsUtil(mockGcsUtil);

  // Enable the FileSystems API to know about gs:// URIs in this test.
  FileSystems.setDefaultPipelineOptions(options);

  return options;
}
 

@Test
public void testGcsUploadBufferSizeUnchangedWhenNotDefault() throws IOException {
  int gcsUploadBufferSizeBytes = 12345678;
  DataflowPipelineOptions batchOptions = buildPipelineOptions();
  batchOptions.setGcsUploadBufferSizeBytes(gcsUploadBufferSizeBytes);
  batchOptions.setRunner(DataflowRunner.class);
  Pipeline.create(batchOptions);
  assertEquals(gcsUploadBufferSizeBytes, batchOptions.getGcsUploadBufferSizeBytes().intValue());

  DataflowPipelineOptions streamingOptions = buildPipelineOptions();
  streamingOptions.setStreaming(true);
  streamingOptions.setGcsUploadBufferSizeBytes(gcsUploadBufferSizeBytes);
  streamingOptions.setRunner(DataflowRunner.class);
  Pipeline.create(streamingOptions);
  assertEquals(
      gcsUploadBufferSizeBytes, streamingOptions.getGcsUploadBufferSizeBytes().intValue());
}
 

@Test
public void testGcsUploadBufferSizeIsSetForStreamingWhenDefault() throws IOException {
  DataflowPipelineOptions streamingOptions = buildPipelineOptions();
  streamingOptions.setStreaming(true);
  streamingOptions.setRunner(DataflowRunner.class);
  Pipeline p = Pipeline.create(streamingOptions);

  // Instantiation of a runner prior to run() currently has a side effect of mutating the options.
  // This could be tested by DataflowRunner.fromOptions(streamingOptions) but would not ensure
  // that the pipeline itself had the expected options set.
  p.run();

  assertEquals(
      DataflowRunner.GCS_UPLOAD_BUFFER_SIZE_BYTES_DEFAULT,
      streamingOptions.getGcsUploadBufferSizeBytes().intValue());
}
 

private DataflowPipelineOptions buildPipelineOptions() throws IOException {
  DataflowPipelineOptions options = PipelineOptionsFactory.as(DataflowPipelineOptions.class);
  options.setRunner(DataflowRunner.class);
  options.setProject(PROJECT_ID);
  options.setTempLocation(VALID_TEMP_BUCKET);
  options.setRegion(REGION_ID);
  // Set FILES_PROPERTY to empty to prevent a default value calculated from classpath.
  options.setFilesToStage(new ArrayList<>());
  options.setDataflowClient(buildMockDataflow());
  options.setGcsUtil(mockGcsUtil);
  options.setGcpCredential(new TestCredential());

  // Configure the FileSystem registrar to use these options.
  FileSystems.setDefaultPipelineOptions(options);

  return options;
}
 

/**
 * Tests that the {@link DataflowRunner} with {@code --templateLocation} returns normally when the
 * runner is successfully run with upload_graph experiment turned on. The result template should
 * not contain raw steps and stepsLocation file should be set.
 */
@Test
public void testTemplateRunnerWithUploadGraph() throws Exception {
  File existingFile = tmpFolder.newFile();
  DataflowPipelineOptions options = PipelineOptionsFactory.as(DataflowPipelineOptions.class);
  options.setExperiments(Arrays.asList("upload_graph"));
  options.setJobName("TestJobName");
  options.setGcpCredential(new TestCredential());
  options.setPathValidatorClass(NoopPathValidator.class);
  options.setProject("test-project");
  options.setRegion(REGION_ID);
  options.setRunner(DataflowRunner.class);
  options.setTemplateLocation(existingFile.getPath());
  options.setTempLocation(tmpFolder.getRoot().getPath());
  Pipeline p = Pipeline.create(options);
  p.apply(Create.of(ImmutableList.of(1)));
  p.run();
  expectedLogs.verifyInfo("Template successfully created");
  ObjectMapper objectMapper = new ObjectMapper();
  JsonNode node = objectMapper.readTree(existingFile);
  assertEquals(0, node.get("steps").size());
  assertNotNull(node.get("stepsLocation"));
}
 

@Test
@Ignore(
    "TODO: BEAM-2902 Add support for user state in a ParDo.Multi once PTransformMatcher "
        + "exposes a way to know when the replacement is not required by checking that the "
        + "preceding ParDos to a GBK are key preserving.")
public void testFnApiMultiOutputOverrideNonCrashing() throws Exception {
  DataflowPipelineOptions options = buildPipelineOptions("--experiments=beam_fn_api");
  options.setRunner(DataflowRunner.class);
  Pipeline pipeline = Pipeline.create(options);

  TupleTag<Integer> mainOutputTag = new TupleTag<Integer>() {};
  TupleTag<Integer> sideOutputTag = new TupleTag<Integer>() {};

  DummyStatefulDoFn fn = new DummyStatefulDoFn();
  pipeline
      .apply(Create.of(KV.of(1, 2)))
      .apply(ParDo.of(fn).withOutputTags(mainOutputTag, TupleTagList.of(sideOutputTag)));

  DataflowRunner runner = DataflowRunner.fromOptions(options);
  runner.replaceTransforms(pipeline);
  assertThat(findBatchStatefulDoFn(pipeline), equalTo((DoFn) fn));
}
 

@Test
public void testMultiOutputOverrideNonCrashing() throws Exception {
  DataflowPipelineOptions options = buildPipelineOptions();
  options.setRunner(DataflowRunner.class);
  Pipeline pipeline = Pipeline.create(options);

  TupleTag<Integer> mainOutputTag = new TupleTag<Integer>() {};
  TupleTag<Integer> sideOutputTag = new TupleTag<Integer>() {};

  DummyStatefulDoFn fn = new DummyStatefulDoFn();
  pipeline
      .apply(Create.of(KV.of(1, 2)))
      .apply(ParDo.of(fn).withOutputTags(mainOutputTag, TupleTagList.of(sideOutputTag)));

  DataflowRunner runner = DataflowRunner.fromOptions(options);
  runner.replaceTransforms(pipeline);
  assertThat(findBatchStatefulDoFn(pipeline), equalTo((DoFn) fn));
}
 

/**
 * Tests that the {@link DataflowRunner} with {@code --templateLocation} throws the appropriate
 * exception when an output file is not writable.
 */
@Test
public void testTemplateRunnerLoggedErrorForFile() throws Exception {
  DataflowPipelineOptions options = PipelineOptionsFactory.as(DataflowPipelineOptions.class);
  options.setJobName("TestJobName");
  options.setRunner(DataflowRunner.class);
  options.setTemplateLocation("//bad/path");
  options.setProject("test-project");
  options.setRegion(REGION_ID);
  options.setTempLocation(tmpFolder.getRoot().getPath());
  options.setGcpCredential(new TestCredential());
  options.setPathValidatorClass(NoopPathValidator.class);
  Pipeline p = Pipeline.create(options);

  thrown.expectMessage("Cannot create output file at");
  thrown.expect(RuntimeException.class);
  p.run();
}
 

private static DataflowPipelineOptions buildPipelineOptions() throws IOException {
  GcsUtil mockGcsUtil = mock(GcsUtil.class);
  when(mockGcsUtil.expand(any(GcsPath.class)))
      .then(invocation -> ImmutableList.of((GcsPath) invocation.getArguments()[0]));
  when(mockGcsUtil.bucketAccessible(any(GcsPath.class))).thenReturn(true);

  DataflowPipelineOptions options = PipelineOptionsFactory.as(DataflowPipelineOptions.class);
  options.setRunner(DataflowRunner.class);
  options.setGcpCredential(new TestCredential());
  options.setJobName("some-job-name");
  options.setProject("some-project");
  options.setRegion("some-region");
  options.setTempLocation(GcsPath.fromComponents("somebucket", "some/path").toString());
  options.setFilesToStage(new ArrayList<>());
  options.setDataflowClient(buildMockDataflow(new IsValidCreateRequest()));
  options.setGcsUtil(mockGcsUtil);

  // Enable the FileSystems API to know about gs:// URIs in this test.
  FileSystems.setDefaultPipelineOptions(options);

  return options;
}
 

@Test
public void testSingleOutputOverrideNonCrashing() throws Exception {
  DataflowPipelineOptions options = buildPipelineOptions();
  options.setRunner(DataflowRunner.class);
  Pipeline pipeline = Pipeline.create(options);

  DummyStatefulDoFn fn = new DummyStatefulDoFn();
  pipeline.apply(Create.of(KV.of(1, 2))).apply(ParDo.of(fn));

  DataflowRunner runner = DataflowRunner.fromOptions(options);
  runner.replaceTransforms(pipeline);
  assertThat(findBatchStatefulDoFn(pipeline), equalTo((DoFn) fn));
}
 

private Pipeline buildPipeline(DataflowPipelineOptions options) {
  options.setRunner(DataflowRunner.class);
  Pipeline p = Pipeline.create(options);

  p.apply("ReadMyFile", TextIO.read().from("gs://bucket/object"))
      .apply("WriteMyFile", TextIO.write().to("gs://bucket/object"));
  DataflowRunner runner = DataflowRunner.fromOptions(options);
  runner.replaceTransforms(p);

  return p;
}
 

private Pipeline createTestStreamingRunner() {
  DataflowPipelineOptions options = PipelineOptionsFactory.as(DataflowPipelineOptions.class);
  options.setRunner(DataflowRunner.class);
  options.setStreaming(true);
  options.setProject("someproject");
  options.setRegion("some-region1");
  options.setGcpTempLocation("gs://staging");
  options.setPathValidatorClass(NoopPathValidator.class);
  options.setDataflowClient(dataflow);
  return Pipeline.create(options);
}
 

@Test
public void testGcsStagingLocationInitialization() throws Exception {
  // Set temp location (required), and check that staging location is set.
  DataflowPipelineOptions options = PipelineOptionsFactory.as(DataflowPipelineOptions.class);
  options.setTempLocation(VALID_TEMP_BUCKET);
  options.setProject(PROJECT_ID);
  options.setRegion(REGION_ID);
  options.setGcpCredential(new TestCredential());
  options.setGcsUtil(mockGcsUtil);
  options.setRunner(DataflowRunner.class);

  DataflowRunner.fromOptions(options);

  assertNotNull(options.getStagingLocation());
}
 

@Test
public void testNoStagingLocationAndNoTempLocationFails() {
  DataflowPipelineOptions options = PipelineOptionsFactory.as(DataflowPipelineOptions.class);
  options.setRunner(DataflowRunner.class);
  options.setProject("foo-project");
  options.setRegion(REGION_ID);

  thrown.expect(IllegalArgumentException.class);
  thrown.expectMessage(
      "DataflowRunner requires gcpTempLocation, "
          + "but failed to retrieve a value from PipelineOption");
  DataflowRunner.fromOptions(options);
}
 

@Test
public void testGcpTempAndNoTempLocationSucceeds() throws Exception {
  DataflowPipelineOptions options = PipelineOptionsFactory.as(DataflowPipelineOptions.class);
  options.setRunner(DataflowRunner.class);
  options.setGcpCredential(new TestCredential());
  options.setProject("foo-project");
  options.setRegion(REGION_ID);
  options.setGcpTempLocation(VALID_TEMP_BUCKET);
  options.setGcsUtil(mockGcsUtil);

  DataflowRunner.fromOptions(options);
}
 

@Test
public void testGcsUploadBufferSizeIsUnsetForBatchWhenDefault() throws IOException {
  DataflowPipelineOptions batchOptions = buildPipelineOptions();
  batchOptions.setRunner(DataflowRunner.class);
  Pipeline.create(batchOptions);
  assertNull(batchOptions.getGcsUploadBufferSizeBytes());
}
 

private Pipeline createTestBatchRunner() {
  DataflowPipelineOptions options = PipelineOptionsFactory.as(DataflowPipelineOptions.class);
  options.setRunner(DataflowRunner.class);
  options.setProject("someproject");
  options.setRegion("some-region1");
  options.setGcpTempLocation("gs://staging");
  options.setPathValidatorClass(NoopPathValidator.class);
  options.setDataflowClient(dataflow);
  return Pipeline.create(options);
}
 

/**
 * Create a test pipeline that uses the {@link DataflowRunner} so that {@link GroupByKey} is not
 * expanded. This is used for verifying that even without expansion the proper errors show up.
 */
private Pipeline createTestServiceRunner() {
  DataflowPipelineOptions options = PipelineOptionsFactory.as(DataflowPipelineOptions.class);
  options.setRunner(DataflowRunner.class);
  options.setProject("someproject");
  options.setRegion("some-region1");
  options.setGcpTempLocation("gs://staging");
  options.setPathValidatorClass(NoopPathValidator.class);
  options.setDataflowClient(dataflow);
  return Pipeline.create(options);
}
 

public static void main(String[] args) throws GeneralSecurityException, IOException, ParseException, ParserConfigurationException, SAXException {
	String params = null;
	for (int i = 0; i < args.length; i++) {
		if (args[i].startsWith("--params="))
			params = args[i].replaceFirst("--params=", "");
	}

	System.out.println(params);
	init(params);

	GoogleCredentials credentials = ServiceAccountCredentials.fromStream(new FileInputStream(keyFile))
	        .createScoped(Arrays.asList(new String[] { "https://www.googleapis.com/auth/cloud-platform" }));

	DataflowPipelineOptions options = PipelineOptionsFactory.create().as(DataflowPipelineOptions.class);
	
	options.setRunner(DataflowRunner.class);
	// Your project ID is required in order to run your pipeline on the Google Cloud.
	options.setProject(projectId);
	// Your Google Cloud Storage path is required for staging local files.
	options.setStagingLocation(workingBucket);
	options.setTempLocation(workingBucket + "/temp");
	options.setGcpCredential(credentials);
	options.setServiceAccount(accountEmail);
	options.setMaxNumWorkers(maxNumWorkers);
	options.setDiskSizeGb(diskSizeGb);
	options.setWorkerMachineType(machineType);
	options.setAutoscalingAlgorithm(AutoscalingAlgorithmType.THROUGHPUT_BASED);
	options.setZone(zone);
	options.setStreaming(isStreaming);
	options.setJobName(pipelineName);
	Pipeline pipeline = Pipeline.create(options);
	
	Gson gson = new Gson();
	TableSchema schema = gson.fromJson(schemaStr, TableSchema.class);
	
	PCollection<String> streamData = null;
	if(pubSubTopicSub != null && !StringUtils.isEmpty(pubSubTopicSub)){
		streamData = pipeline.apply("ReadPubSub",PubsubIO.readStrings().fromSubscription(String.format("projects/%1$s/subscriptions/%2$s",projectId,pubSubTopicSub)));
	}
	else if(pubSubTopic != null && !StringUtils.isEmpty(pubSubTopic)){
		streamData = pipeline.apply("ReadPubSub",PubsubIO.readStrings().fromTopic(String.format("projects/%1$s/topics/%2$s",projectId,pubSubTopic)));
	}
	
	PCollection<TableRow> tableRow = streamData.apply("ToTableRow",ParDo.of(new PrepData.ToTableRow(owTimestamp, debugMode)));
	
	
	tableRow.apply("WriteToBQ",
			BigQueryIO.writeTableRows()
			.to(String.format("%1$s.%2$s",bqDataSet, bqTable))
			.withSchema(schema)
			.withWriteDisposition(BigQueryIO.Write.WriteDisposition.WRITE_APPEND));

	System.out.println("Starting pipeline " + pipelineName);
	pipeline.run();
}
 

@Test
public void testAllSplitsAreReturned() throws Exception {
  final long apiSizeLimitForTest = 500 * 1024;
  DataflowPipelineOptions options = PipelineOptionsFactory.as(DataflowPipelineOptions.class);
  options.setAppName("TestAppName");
  options.setProject("test-project");
  options.setRegion("some-region1");
  options.setTempLocation("gs://test/temp/location");
  options.setGcpCredential(new TestCredential());
  options.setRunner(DataflowRunner.class);
  options.setPathValidatorClass(NoopPathValidator.class);
  // Generate a CountingSource and split it into the desired number of splits
  // (desired size = 1 byte), triggering the re-split with a larger bundle size.
  // Thus below we expect to produce 'numberOfSplits' splits.
  com.google.api.services.dataflow.model.Source source =
      WorkerCustomSourcesTest.translateIOToCloudSource(
          CountingSource.upTo(numberOfSplits), options);
  SourceSplitResponse split =
      WorkerCustomSourcesTest.performSplit(
          source, options, 1L, null /* numBundles limit */, apiSizeLimitForTest);
  assertThat(
      split.getBundles().size(),
      lessThanOrEqualTo(WorkerCustomSources.DEFAULT_NUM_BUNDLES_LIMIT));

  List<OffsetBasedSource<?>> originalSplits = new ArrayList<>(numberOfSplits);
  // Collect all the splits
  for (DerivedSource derivedSource : split.getBundles()) {
    Object deserializedSource =
        WorkerCustomSources.deserializeFromCloudSource(derivedSource.getSource().getSpec());
    if (deserializedSource instanceof SplittableOnlyBoundedSource) {
      SplittableOnlyBoundedSource<?> splittableOnlySource =
          (SplittableOnlyBoundedSource<?>) deserializedSource;
      originalSplits.addAll((List) splittableOnlySource.split(1L, options));
    } else {
      originalSplits.add((OffsetBasedSource<?>) deserializedSource);
    }
  }

  assertEquals(numberOfSplits, originalSplits.size());
  for (int i = 0; i < originalSplits.size(); i++) {
    OffsetBasedSource<?> offsetBasedSource = (OffsetBasedSource<?>) originalSplits.get(i);
    assertEquals(i, offsetBasedSource.getStartOffset());
    assertEquals(i + 1, offsetBasedSource.getEndOffset());
  }
}