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();
}
/**
* Applies {@code ApproximateUnique(sampleSize)} verifying that the estimation error falls within
* the maximum allowed error of {@code 2/sqrt(sampleSize)}.
*/
private void runApproximateUniquePipeline(int sampleSize) {
Pipeline p = TestPipeline.create();
PCollection<String> collection = readPCollection(p);
final PCollectionView<Long> exact =
collection
.apply(RemoveDuplicates.<String>create())
.apply(Combine.globally(new CountElements<String>()))
.apply(View.<Long>asSingleton());
PCollection<Long> approximate =
collection.apply(ApproximateUnique.<String>globally(sampleSize));
PCollection<KV<Long, Long>> approximateAndExact =
approximate.apply(
ParDo.of(
new DoFn<Long, KV<Long, Long>>() {
@Override
public void processElement(ProcessContext c) {
c.output(KV.of(c.element(), c.sideInput(exact)));
}
})
.withSideInputs(exact));
DataflowAssert.that(approximateAndExact).satisfies(new VerifyEstimatePerKeyFn(sampleSize));
p.run();
}
/** Example test that tests a PTransform by using an in-memory input and inspecting the output. */
@Test
@Category(RunnableOnService.class)
public void testCountWords() throws Exception {
Pipeline p = TestPipeline.create();
PCollection<String> input = p.apply(Create.of(WORDS).withCoder(StringUtf8Coder.of()));
PCollection<String> output = input.apply(new CountWords())
.apply(ParDo.of(new FormatAsTextFn()));
DataflowAssert.that(output).containsInAnyOrder(COUNTS_ARRAY);
p.run();
}
@Override
public PCollection<GATKRead> apply(PCollection<GATKRead> input) {
return input.apply(
ParDo.named("ApplyBQSR")
.of(
new DoFnWLog<GATKRead, GATKRead>("ApplyBQSRStub") {
private static final long serialVersionUID = 1L;
@Override
public void processElement(ProcessContext c) throws Exception {
c.output(c.element());
}
})
.withSideInputs(header, recalibrationReport));
}
@Override
public PCollection<RecalibrationTables> apply(
PCollection<KV<GATKRead, ReadContextData>> input) {
return input.apply(
ParDo.named("BaseRecalibrator")
.of(
new DoFnWLog<KV<GATKRead, ReadContextData>, RecalibrationTables>(
"BaseRecalibratorStub") {
private static final long serialVersionUID = 1L;
@Override
public void processElement(ProcessContext c) throws Exception {
c.output(
new RecalibrationTables(
new StandardCovariateList(
new RecalibrationArgumentCollection(), Collections.emptyList())));
}
})
.withSideInputs(header));
}
@Override
public PCollection<KV<ReferenceShard, Iterable<GATKRead>>> apply(PCollection<GATKRead> input) {
PCollection<KV<ReferenceShard, GATKRead>> keyReadByReferenceShard =
input.apply(
ParDo.of(
new DoFn<GATKRead, KV<ReferenceShard, GATKRead>>() {
private static final long serialVersionUID = 1L;
@Override
public void processElement(ProcessContext c) throws Exception {
// Apply our reference window function to each read before deciding which
// reference shard it belongs to.
ReferenceShard shard =
ReferenceShard.getShardNumberFromInterval(
referenceWindowFunction.apply(c.element()));
c.output(KV.of(shard, c.element()));
}
})
.named("KeyReadByRefShard"));
return keyReadByReferenceShard.apply(GroupByKey.<ReferenceShard, GATKRead>create());
}
@Override
public PCollection<T> apply(PCollection<T> in) {
return in.apply(
ParDo.named("CreateIndex")
.of(
new DoFn<T, KV<T, Void>>() {
@Override
public void processElement(ProcessContext c) {
c.output(KV.of(c.element(), (Void) null));
}
}))
.apply(
Combine.<T, Void>perKey(
new SerializableFunction<Iterable<Void>, Void>() {
@Override
public Void apply(Iterable<Void> iter) {
return null; // ignore input
}
}))
.apply(Keys.<T>create());
}
@Override
public PCollection<OutputT> apply(PCollection<? extends InputT> input) {
return input.apply(
ParDo.of(new MultiThreadedIntraBundleProcessingDoFn<>(doFn, maxParallelism)));
}
