Java Code Examples for com.google.cloud.dataflow.sdk.Pipeline#run()

public static void main(String[] args) {
  CloudBigtableOptions options =
      PipelineOptionsFactory.fromArgs(args).withValidation().as(CloudBigtableOptions.class);

  CloudBigtableScanConfiguration config =
      new CloudBigtableScanConfiguration.Builder()
          .withProjectId(options.getBigtableProjectId())
          .withInstanceId(options.getBigtableInstanceId())
          .withTableId(options.getBigtableTableId())
          .build();

  options.setStreaming(true);
  options.setRunner(DataflowPipelineRunner.class);

  Pipeline p = Pipeline.create(options);
  CloudBigtableIO.initializeForWrite(p);

  p.apply(Read.from(new CoinbaseSource()))
      .apply(ParDo.named("DeserializeCoinbase").of(new DeserializeCoinbase()))
      .apply(ParDo.of(new HBaseBigtableWriter()))
      .apply(CloudBigtableIO.writeToTable(config));

  p.run();
}
 

@Override
protected void testProgram() throws Exception {

	List<String> strings = Arrays.asList("k1", "k5", "k5", "k2", "k1", "k2", "k3");

	Pipeline p = FlinkTestPipeline.createForBatch();

	PCollection<String> input =
			p.apply(Create.of(strings))
					.setCoder(StringUtf8Coder.of());

	PCollection<String> output =
			input.apply(RemoveDuplicates.<String>create());

	output.apply(TextIO.Write.to(resultPath));
	p.run();
}
 

private static void runProgram(String resultPath) {

		Pipeline p = FlinkTestPipeline.createForBatch();

		PCollection<String> result = p
				.apply(Read.from(new ReadSource(1, 10)))
				.apply(ParDo.of(new DoFn<Integer, String>() {
					@Override
					public void processElement(ProcessContext c) throws Exception {
						c.output(c.element().toString());
					}
				}));

		result.apply(TextIO.Write.to(resultPath));
		p.run();
	}
 

private static void runProgram(String resultPath) {

		Pipeline p = FlinkTestPipeline.createForStreaming();

		PCollection<String> result = p
			.apply(Read.from(new RangeReadSource(1, 10)))
			.apply(Window.<Integer>into(new GlobalWindows())
				.triggering(AfterPane.elementCountAtLeast(10))
				.discardingFiredPanes())
			.apply(ParDo.of(new DoFn<Integer, String>() {
				@Override
				public void processElement(ProcessContext c) throws Exception {
				c.output(c.element().toString());
				}
			}));

		result.apply(TextIO.Write.to(resultPath));

		try {
			p.run();
			fail();
		} catch(Exception e) {
			assertEquals("The source terminates as expected.", e.getCause().getCause().getMessage());
		}
	}
 

@Override
protected void testProgram() throws Exception {

	List<String> strings = Collections.emptyList();

	Pipeline p = FlinkTestPipeline.createForBatch();

	PCollection<String> input =
			p.apply(Create.of(strings))
					.setCoder(StringUtf8Coder.of());

	PCollection<String> output =
			input.apply(RemoveDuplicates.<String>create());

	output.apply(TextIO.Write.to(resultPath));
	p.run();
}
 

@org.junit.Test
public void testCompleteWindowData() {

  Pipeline pipeline = setup();

  List<KV<String, TSProto>> pipelineData = GenerateSampleData.getTestData();
  List<KV<String, TSProto>> testData = new ArrayList<KV<String, TSProto>>(pipelineData);
  WorkPacketConfig packetConfig = GenerateSampleData.generateWorkPacketConfig(2);

  PCollection<KV<String, TSProto>> completeWindowData =
      generateCompleteWindowData(pipeline, pipelineData, packetConfig);

  testData.add(KV.of(GenerateSampleData.TS3, TSProto.newBuilder().setKey(GenerateSampleData.TS3)
          .setIsLive(false).setTime(1451577839999L).build()));
  testData.add(KV.of(GenerateSampleData.TS4, TSProto.newBuilder().setKey(GenerateSampleData.TS4)
          .setIsLive(false).setTime(1451577839999L).build()));
  
  DataflowAssert.that(completeWindowData).containsInAnyOrder(testData);
  pipeline.run();
}
 

@Override
protected void testProgram() throws Exception {

	Pipeline pipeline = FlinkTestPipeline.createForBatch();

	pipeline.getCoderRegistry().registerCoder(URI.class, StringDelegateCoder.of(URI.class));

	PCollection<KV<String, KV<URI, Double>>> wordToUriAndTfIdf = pipeline
			.apply(Create.of(
					KV.of(new URI("x"), "a b c d"),
					KV.of(new URI("y"), "a b c"),
					KV.of(new URI("z"), "a m n")))
			.apply(new TfIdf.ComputeTfIdf());

	PCollection<String> words = wordToUriAndTfIdf
			.apply(Keys.<String>create())
			.apply(RemoveDuplicates.<String>create());

	words.apply(TextIO.Write.to(resultPath));

	pipeline.run();
}
 

/** Run a Docker workflow on Dataflow. */
public static void run(Workflow w, Map<String, WorkflowArgs> a, DataflowPipelineOptions o)
    throws IOException {
  LOG.info("Running workflow graph");
  if (w.getArgs().getProjectId() == null) {
    throw new IllegalArgumentException("Project id is required");
  }

  Pipeline p = DataflowFactory.dataflow(w, a, o);

  LOG.info("Created Dataflow pipeline");
  LOG.debug(w.toString());

  PipelineResult r = p.run();

  LOG.info("Dataflow pipeline completed");
  LOG.info("Result state: " + r.getState());
}
 

public static void main(String[] args) {
  CustomPipelineOptions options =
      PipelineOptionsFactory.fromArgs(args).withValidation().as(CustomPipelineOptions.class);
  Pipeline p = Pipeline.create(options);

  p.apply(PubsubIO.Read.named("read from PubSub")
      .topic(String.format("projects/%s/topics/%s", options.getSourceProject(), options.getSourceTopic()))
      .timestampLabel("ts")
      .withCoder(TableRowJsonCoder.of()))

   .apply("filter lower Manhattan", ParDo.of(new FilterLowerManhattan()))

   .apply(PubsubIO.Write.named("WriteToPubsub")
      .topic(String.format("projects/%s/topics/%s", options.getSinkProject(), options.getSinkTopic()))
      .withCoder(TableRowJsonCoder.of()));
  p.run();
}
 

public static void main(String[] args) {
  // CloudBigtableOptions is one way to retrieve the options.  It's not required.
  // https://github.com/GoogleCloudPlatform/cloud-bigtable-examples/blob/master/java/dataflow-connector-examples/src/main/java/com/google/cloud/bigtable/dataflow/example/HelloWorldWrite.java
  BigtableCsvOptions options =
      PipelineOptionsFactory.fromArgs(args).withValidation().as(BigtableCsvOptions.class);
  CloudBigtableTableConfiguration config =
      CloudBigtableTableConfiguration.fromCBTOptions(options);

  Pipeline p = Pipeline.create(options);

  CloudBigtableIO.initializeForWrite(p);

  PCollection<KV<String, Integer>> ngrams =
      applyPipelineToParseBooks(p.apply(TextIO.Read.from(options.getInputFile())));
  PCollection<Mutation> mutations = ngrams.apply(ParDo.of(ENCODE_NGRAM));
  mutations.apply(CloudBigtableIO.writeToTable(config));

  // Run the pipeline.
  p.run();
}
 

public static void main(String[] args) {
  CustomPipelineOptions options =
      PipelineOptionsFactory.fromArgs(args).withValidation().as(CustomPipelineOptions.class);
  Pipeline p = Pipeline.create(options);

  p.apply(PubsubIO.Read.named("read from PubSub")
      .topic(String.format("projects/%s/topics/%s", options.getSourceProject(), options.getSourceTopic()))
      .timestampLabel("ts")
      .withCoder(TableRowJsonCoder.of()))

   .apply("key rides by rideid",
      MapElements.via((TableRow ride) -> KV.of(ride.get("ride_id").toString(), ride))
        .withOutputType(new TypeDescriptor<KV<String, TableRow>>() {}))

   .apply("session windows on rides with early firings",
      Window.<KV<String, TableRow>>into(
        Sessions.withGapDuration(Duration.standardMinutes(60)))
          .triggering(
            AfterWatermark.pastEndOfWindow()
              .withEarlyFirings(AfterProcessingTime.pastFirstElementInPane().plusDelayOf(Duration.millis(2000))))
          .accumulatingFiredPanes()
          .withAllowedLateness(Duration.ZERO))

   .apply("group ride points on same ride", Combine.perKey(new LatestPointCombine()))

   .apply("discard key",
      MapElements.via((KV<String, TableRow> a) -> a.getValue())
        .withOutputType(TypeDescriptor.of(TableRow.class)))

   .apply(PubsubIO.Write.named("WriteToPubsub")
      .topic(String.format("projects/%s/topics/%s", options.getSinkProject(), options.getSinkTopic()))
      .withCoder(TableRowJsonCoder.of()));
  p.run();
}
 

public static void main(String[] args) {
  CustomPipelineOptions options =
      PipelineOptionsFactory.fromArgs(args).withValidation().as(CustomPipelineOptions.class);
  Pipeline p = Pipeline.create(options);

  p.apply(PubsubIO.Read.named("read from PubSub")
      .topic(String.format("projects/%s/topics/%s", options.getSourceProject(), options.getSourceTopic()))
      .timestampLabel("ts")
      .withCoder(TableRowJsonCoder.of()))

   .apply("filter a few rides",
      Filter.byPredicate(
        (TableRow t) -> {
          String rideId = t.get("ride_id").toString();

          // You can change the filter here to allow more or fewer rides through:
          // rideIds starting with "a" are quite common
          // rideIds starting with "ab" are rarer
          // rideIds starting with "abc" are rarer still
          if (rideId.startsWith("ab")) {
            LOG.info("Accepted point on ride {} with order number {}} timestamp {}",
              t.get("ride_id"), t.get("point_idx"), t.get("timestamp"));
            return true;
          }
          return false;
        }))

   .apply(PubsubIO.Write.named("WriteToPubsub")
      .topic(String.format("projects/%s/topics/%s", options.getSinkProject(), options.getSinkTopic()))
      .withCoder(TableRowJsonCoder.of()));

  p.run();
}
 

public static void main(String[] args) {

		Options options = PipelineOptionsFactory.fromArgs(args).withValidation()
				.as(Options.class);
		options.setRunner(FlinkPipelineRunner.class);

		Pipeline p = Pipeline.create(options);

		p.apply(TextIO.Read.named("ReadLines").from(options.getInput()))
				.apply(new CountWords())
				.apply(MapElements.via(new FormatAsTextFn()))
				.apply(TextIO.Write.named("WriteCounts").to(options.getOutput()));

		p.run();
	}
 

public static void main(String[] args) {
	PipelineOptionsFactory.register(KafkaStreamingWordCountOptions.class);
	KafkaStreamingWordCountOptions options = PipelineOptionsFactory.fromArgs(args).as(KafkaStreamingWordCountOptions.class);
	options.setJobName("KafkaExample - WindowSize: " + options.getWindowSize() + " seconds");
	options.setStreaming(true);
	options.setCheckpointingInterval(1000L);
	options.setNumberOfExecutionRetries(5);
	options.setExecutionRetryDelay(3000L);
	options.setRunner(FlinkPipelineRunner.class);

	System.out.println(options.getKafkaTopic() +" "+ options.getZookeeper() +" "+ options.getBroker() +" "+ options.getGroup() );
	Pipeline pipeline = Pipeline.create(options);

	Properties p = new Properties();
	p.setProperty("zookeeper.connect", options.getZookeeper());
	p.setProperty("bootstrap.servers", options.getBroker());
	p.setProperty("group.id", options.getGroup());

	// this is the Flink consumer that reads the input to
	// the program from a kafka topic.
	FlinkKafkaConsumer08<String> kafkaConsumer = new FlinkKafkaConsumer08<>(
			options.getKafkaTopic(),
			new SimpleStringSchema(), p);

	PCollection<String> words = pipeline
			.apply(Read.from(new UnboundedFlinkSource<>(kafkaConsumer)).named("StreamingWordCount"))
			.apply(ParDo.of(new ExtractWordsFn()))
			.apply(Window.<String>into(FixedWindows.of(Duration.standardSeconds(options.getWindowSize())))
					.triggering(AfterWatermark.pastEndOfWindow()).withAllowedLateness(Duration.ZERO)
					.discardingFiredPanes());

	PCollection<KV<String, Long>> wordCounts =
			words.apply(Count.<String>perElement());

	wordCounts.apply(ParDo.of(new FormatAsStringFn()))
			.apply(TextIO.Write.to("./outputKafka.txt"));

	pipeline.run();
}
 

private static void runProgram(String tmpPath, String resultPath) {
	Pipeline p = FlinkTestPipeline.createForBatch();

	p
		.apply(Create.of(
				new User("Joe", 3, "red"),
				new User("Mary", 4, "blue"),
				new User("Mark", 1, "green"),
				new User("Julia", 5, "purple"))
			.withCoder(AvroCoder.of(User.class)))

		.apply(AvroIO.Write.to(tmpPath)
			.withSchema(User.class));

	p.run();

	p = FlinkTestPipeline.createForBatch();

	p
		.apply(AvroIO.Read.from(tmpPath).withSchema(User.class).withoutValidation())

			.apply(ParDo.of(new DoFn<User, String>() {
				@Override
				public void processElement(ProcessContext c) throws Exception {
					User u = c.element();
					String result = u.getName() + " " + u.getFavoriteColor() + " " + u.getFavoriteNumber();
					c.output(result);
				}
			}))

		.apply(TextIO.Write.to(resultPath));

	p.run();
}
 

@Override
protected void testProgram() throws Exception {

	Pipeline p = FlinkTestPipeline.createForBatch();

	/* Create two PCollections and join them */
	PCollection<KV<String,Long>> occurences1 = p.apply(Create.of(WORDS_1))
			.apply(ParDo.of(new ExtractWordsFn()))
			.apply(Count.<String>perElement());

	PCollection<KV<String,Long>> occurences2 = p.apply(Create.of(WORDS_2))
			.apply(ParDo.of(new ExtractWordsFn()))
			.apply(Count.<String>perElement());

	PCollection<KV<String,Long>> occurences3 = p.apply(Create.of(WORDS_3))
			.apply(ParDo.of(new ExtractWordsFn()))
			.apply(Count.<String>perElement());

	/* CoGroup the two collections */
	PCollection<KV<String, CoGbkResult>> mergedOccurences = KeyedPCollectionTuple
			.of(tag1, occurences1)
			.and(tag2, occurences2)
			.and(tag3, occurences3)
			.apply(CoGroupByKey.<String>create());

	/* Format output */
	mergedOccurences.apply(ParDo.of(new FormatCountsFn()))
			.apply(TextIO.Write.named("test").to(resultPath));

	p.run();
}
 

public static void main(String[] args) {
  CustomPipelineOptions options =
      PipelineOptionsFactory.fromArgs(args).withValidation().as(CustomPipelineOptions.class);
  Pipeline p = Pipeline.create(options);

  p.apply(PubsubIO.Read.named("read from PubSub")
      .topic(String.format("projects/%s/topics/%s", options.getSourceProject(), options.getSourceTopic()))
      .timestampLabel("ts")
      .withCoder(TableRowJsonCoder.of()))

   .apply("window 1s", Window.into(FixedWindows.of(Duration.standardSeconds(1))))

   .apply("parse timestamps",
      MapElements.via(
        (TableRow e) ->
          Instant.from(DateTimeFormatter.ISO_DATE_TIME.parse(e.get("timestamp").toString())).toEpochMilli())
      .withOutputType(TypeDescriptor.of(Long.class)))

   .apply("max timestamp in window", Max.longsGlobally().withoutDefaults())

   .apply("transform",
      MapElements.via(
        (Long t) -> {
          TableRow ride = new TableRow();
          ride.set("timestamp", Instant.ofEpochMilli(t).toString());
          return ride;
        })
      .withOutputType(TypeDescriptor.of(TableRow.class)))

   .apply(PubsubIO.Write.named("write to PubSub")
      .topic(String.format("projects/%s/topics/%s", options.getSinkProject(), options.getSinkTopic()))
      .withCoder(TableRowJsonCoder.of()));
  p.run();
}
 

private static void runProgram(String resultPath) {
	Pipeline p = FlinkTestPipeline.createForBatch();

	p.apply(Create.of(EXPECTED_RESULT)).setCoder(StringUtf8Coder.of())
		.apply("CustomSink", Write.to(new MyCustomSink(resultPath)));

	p.run();
}
 

@Override
protected void testProgram() throws Exception {
	Pipeline p = FlinkTestPipeline.createForBatch();

	PCollection<String> words = p.apply(Create.of("Hello", "Whatupmyman", "hey", "SPECIALthere", "MAAA", "MAAFOOO"));

	// Select words whose length is below a cut off,
	// plus the lengths of words that are above the cut off.
	// Also select words starting with "MARKER".
	final int wordLengthCutOff = 3;
	// Create tags to use for the main and side outputs.
	final TupleTag<String> wordsBelowCutOffTag = new TupleTag<String>(){};
	final TupleTag<Integer> wordLengthsAboveCutOffTag = new TupleTag<Integer>(){};
	final TupleTag<String> markedWordsTag = new TupleTag<String>(){};

	PCollectionTuple results =
			words.apply(ParDo
					.withOutputTags(wordsBelowCutOffTag, TupleTagList.of(wordLengthsAboveCutOffTag)
							.and(markedWordsTag))
					.of(new DoFn<String, String>() {
						final TupleTag<String> specialWordsTag = new TupleTag<String>() {
						};

						public void processElement(ProcessContext c) {
							String word = c.element();
							if (word.length() <= wordLengthCutOff) {
								c.output(word);
							} else {
								c.sideOutput(wordLengthsAboveCutOffTag, word.length());
							}
							if (word.startsWith("MAA")) {
								c.sideOutput(markedWordsTag, word);
							}

							if (word.startsWith("SPECIAL")) {
								c.sideOutput(specialWordsTag, word);
							}
						}
					}));

	// Extract the PCollection results, by tag.
	PCollection<String> wordsBelowCutOff = results.get(wordsBelowCutOffTag);
	PCollection<Integer> wordLengthsAboveCutOff = results.get
			(wordLengthsAboveCutOffTag);
	PCollection<String> markedWords = results.get(markedWordsTag);

	markedWords.apply(TextIO.Write.to(resultPath));

	p.run();
}
 

@Override
protected void testProgram() throws Exception {

	Pipeline p = FlinkTestPipeline.createForBatch();

	PCollection<TableRow> input1 = p.apply(Create.of(EVENT_ARRAY));
	PCollection<TableRow> input2 = p.apply(Create.of(CC_ARRAY));

	PCollection<String> output = JoinExamples.joinEvents(input1, input2);

	output.apply(TextIO.Write.to(resultPath));

	p.run();
}