Java PipelineOptionsFactory类代码示例

import org.apache.beam.sdk.options.PipelineOptionsFactory; //导入依赖的package包/类
/** Run a batch pipeline to calculate hourly team scores. */
public static void main(String[] args) throws Exception {

  Options options =
      PipelineOptionsFactory.fromArgs(args).withValidation().as(Options.class);
  Pipeline pipeline = Pipeline.create(options);

  pipeline
  .apply("ReadLogs", TextIO.read().from(options.getInput()))
  .apply("SetTimestamps", WithTimestamps.of(new SetTimestampFn()))

  .apply("FixedWindows", Window.<String>into(FixedWindows.of(ONE_HOUR)))

  .apply("TeamScores", new CalculateTeamScores(options.getOutputPrefix()));

  pipeline.run();
}
 

import org.apache.beam.sdk.options.PipelineOptionsFactory; //导入依赖的package包/类
public static void main(String[] args) {
  Pipeline p = Pipeline.create(
      PipelineOptionsFactory.fromArgs(args).withValidation().create());

  p.apply(Create.of("Hello", "World"))
  .apply(MapElements.via(new SimpleFunction<String, String>() {
    @Override
    public String apply(String input) {
      return input.toUpperCase();
    }
  }))
  .apply(ParDo.of(new DoFn<String, Void>() {
    @ProcessElement
    public void processElement(ProcessContext c)  {
      LOG.info(c.element());
    }
  }));

  p.run();
}
 

import org.apache.beam.sdk.options.PipelineOptionsFactory; //导入依赖的package包/类
/**
 * Runs the DatastoreToGcs dataflow pipeline
 */
public static void main(String[] args) throws IOException, ScriptException {
  Options options = PipelineOptionsFactory.fromArgs(args)
      .withValidation()
      .as(Options.class);

  options.setRunner(DataflowRunner.class);

  Pipeline pipeline = Pipeline.create(options);

  pipeline
      .apply("IngestEntities",
          DatastoreIO.v1().read()
              .withProjectId(options.getDatastoreProjectId())
              .withLiteralGqlQuery(options.getGqlQuery())
              .withNamespace(options.getNamespace()))
      .apply("EntityToJson", ParDo.of(EntityToJson.newBuilder()
          .setJsTransformPath(options.getJsTransformPath())
          .setJsTransformFunctionName(options.getJsTransformFunctionName())
          .build()))
      .apply("JsonToGcs", TextIO.write().to(options.getSavePath())
          .withSuffix(".json"));

  pipeline.run();
}
 

import org.apache.beam.sdk.options.PipelineOptionsFactory; //导入依赖的package包/类
/**
 * Runs the GcsToDatastore dataflow pipeline
 */
public static void main(String[] args) throws IOException, ScriptException {
  Options options = PipelineOptionsFactory.fromArgs(args)
      .withValidation()
      .as(Options.class);

  options.setRunner(DataflowRunner.class);

  Pipeline pipeline = Pipeline.create(options);

  pipeline
      .apply("IngestJson", TextIO.read()
          .from(options.getJsonPathPrefix()))
      .apply("GcsToEntity", ParDo.of(JsonToEntity.newBuilder()
          .setJsTransformPath(options.getJsTransformPath())
          .setJsTransformFunctionName(options.getJsTransformFunctionName())
          .build()))
      .apply(DatastoreIO.v1().write()
          .withProjectId(options.getDatastoreProjectId()));

  pipeline.run();
}
 

import org.apache.beam.sdk.options.PipelineOptionsFactory; //导入依赖的package包/类
public static void main(String[] args) throws Exception {

    Options options =
        PipelineOptionsFactory.fromArgs(args).withValidation().as(Options.class);
    Pipeline pipeline = Pipeline.create(options);

    pipeline
    .apply(KafkaIO.<String, String>read()
        .withBootstrapServers(options.getKafkaBootstrapServer())
        .withTopic(options.getTopic())
        .withKeyDeserializer(StringDeserializer.class)
        .withValueDeserializer(StringDeserializer.class)
        .withTimestampFn(new SetTimestampFn()))
    .apply("Values", ParDo.of(new ValuesFn()))

    .apply("FixedWindows", Window.<String>into(FixedWindows.of(FIVE_MINUTES))
        .triggering(AfterWatermark.pastEndOfWindow()
            .withEarlyFirings(AfterProcessingTime.pastFirstElementInPane()
                .plusDelayOf(TWO_MINUTES))
            .withLateFirings(AfterPane.elementCountAtLeast(1)))
        .withAllowedLateness(TEN_MINUTES)
        .accumulatingFiredPanes())

    .apply("TeamScore", new CalculateTeamScores(options.getOutputPrefix()));

    pipeline.run();
  }
 

import org.apache.beam.sdk.options.PipelineOptionsFactory; //导入依赖的package包/类
public static void main(String[] args) throws Exception {
    PipelineOptionsFactory.register(TemplateOptions.class);
    TemplateOptions options = PipelineOptionsFactory
            .fromArgs(args)
            .withValidation()
            .as(TemplateOptions.class);
    options.setAutoscalingAlgorithm(THROUGHPUT_BASED);
    Pipeline pipeline = Pipeline.create(options);
    pipeline.apply(BigQueryIO.read().from(options.getBigQueryTableName()))
            .apply(ParDo.of(new DoFn<TableRow, String>() {
                @ProcessElement
                public void processElement(ProcessContext c) throws Exception {
                    String commaSep = c.element().values()
                            .stream()
                            .map(cell -> cell.toString().trim())
                            .collect(Collectors.joining("\",\""));
                    c.output(commaSep);
                }
            }))
            .apply(TextIO.write().to(options.getOutputFile())
                    .withoutSharding()
                    .withWritableByteChannelFactory(GZIP)
            );
    pipeline.run();
}
 

import org.apache.beam.sdk.options.PipelineOptionsFactory; //导入依赖的package包/类
public static void main(String[] args) {
  PipelineOptions options = PipelineOptionsFactory.create();
  options.setRunner(DirectRunner.class); // forced for this demo
  Pipeline p = Pipeline.create(options);

  // register Avro coders for serializing our messages
  Coders.registerAvroCoders(p, ExtendedRecord.class, UntypedOccurrence.class);

  PCollection<UntypedOccurrence> verbatimRecords = p.apply(
    "Read Avro", AvroIO.read(UntypedOccurrence.class).from("demo/output/data*"));

  verbatimRecords.apply("Write file per Genus",
                        AvroIO.write(UntypedOccurrence.class)
                              .to("demo/output-split/data*") // prefix, is required but overwritten
                              .to(new GenusDynamicAvroDestinations(
                                FileSystems.matchNewResource("demo/output-split/data*", true))));


  LOG.info("Starting the pipeline");
  PipelineResult result = p.run();
  result.waitUntilFinish();
  LOG.info("Pipeline finished with state: {} ", result.getState());
}
 

import org.apache.beam.sdk.options.PipelineOptionsFactory; //导入依赖的package包/类
@Test
public void testSizes() throws Exception {
  SolrIOTestUtils.insertTestDocuments(SOLR_COLLECTION, NUM_DOCS, solrClient);

  PipelineOptions options = PipelineOptionsFactory.create();
  SolrIO.Read read =
      SolrIO.read().withConnectionConfiguration(connectionConfiguration).from(SOLR_COLLECTION);
  SolrIO.BoundedSolrSource initialSource = new SolrIO.BoundedSolrSource(read, null);
  // can't use equal assert as Solr collections never have same size
  // (due to internal Lucene implementation)
  long estimatedSize = initialSource.getEstimatedSizeBytes(options);
  LOG.info("Estimated size: {}", estimatedSize);
  assertThat(
      "Wrong estimated size bellow minimum",
      estimatedSize,
      greaterThan(SolrIOTestUtils.MIN_DOC_SIZE * NUM_DOCS));
  assertThat(
      "Wrong estimated size beyond maximum",
      estimatedSize,
      lessThan(SolrIOTestUtils.MAX_DOC_SIZE * NUM_DOCS));
}
 

import org.apache.beam.sdk.options.PipelineOptionsFactory; //导入依赖的package包/类
@Test
public void testProgressEmptySource() throws IOException {
  PipelineOptions options = PipelineOptionsFactory.create();
  CoarseRangeSource source = new CoarseRangeSource(13, 17, 1, 100);
  try (OffsetBasedReader<Integer> reader = source.createReader(options)) {
    // before starting
    assertEquals(0.0, reader.getFractionConsumed(), 1e-6);
    assertEquals(0, reader.getSplitPointsConsumed());
    assertEquals(BoundedReader.SPLIT_POINTS_UNKNOWN, reader.getSplitPointsRemaining());

    // confirm empty
    assertFalse(reader.start());

    // after reading empty source
    assertEquals(1.0, reader.getFractionConsumed(), 1e-6);
    assertEquals(0, reader.getSplitPointsConsumed());
    assertEquals(0, reader.getSplitPointsRemaining());
  }
}
 

import org.apache.beam.sdk.options.PipelineOptionsFactory; //导入依赖的package包/类
public static void main(String[] args)
    throws Exception {

  Options options = PipelineOptionsFactory.fromArgs(args).withValidation().as(Options.class);
  Pipeline p = Pipeline.create(options);

  // Build the table schema for the output table.
  List<TableFieldSchema> fields = new ArrayList<>();
  fields.add(new TableFieldSchema().setName("word").setType("STRING"));
  fields.add(new TableFieldSchema().setName("all_plays").setType("STRING"));
  TableSchema schema = new TableSchema().setFields(fields);

  p.apply(BigQueryIO.readTableRows().from(options.getInput()))
   .apply(new PlaysForWord())
   .apply(BigQueryIO.writeTableRows()
      .to(options.getOutput())
      .withSchema(schema)
      .withCreateDisposition(BigQueryIO.Write.CreateDisposition.CREATE_IF_NEEDED)
      .withWriteDisposition(BigQueryIO.Write.WriteDisposition.WRITE_TRUNCATE));

  p.run().waitUntilFinish();
}
 

import org.apache.beam.sdk.options.PipelineOptionsFactory; //导入依赖的package包/类
private <T> void testBoundedToUnboundedSourceAdapterCheckpoint(
    BoundedSource<T> boundedSource,
    List<T> expectedElements) throws Exception {
  BoundedToUnboundedSourceAdapter<T> unboundedSource =
      new BoundedToUnboundedSourceAdapter<>(boundedSource);

  PipelineOptions options = PipelineOptionsFactory.create();
  BoundedToUnboundedSourceAdapter<T>.Reader reader =
      unboundedSource.createReader(options, null);

  List<T> actual = Lists.newArrayList();
  for (boolean hasNext = reader.start(); hasNext; hasNext = reader.advance()) {
    actual.add(reader.getCurrent());
    // checkpoint every 9 elements
    if (actual.size() % 9 == 0) {
      Checkpoint<T> checkpoint = reader.getCheckpointMark();
      checkpoint.finalizeCheckpoint();
    }
  }
  Checkpoint<T> checkpointDone = reader.getCheckpointMark();
  assertTrue(checkpointDone.getResidualElements() == null
      || checkpointDone.getResidualElements().isEmpty());

  assertEquals(expectedElements.size(), actual.size());
  assertEquals(Sets.newHashSet(expectedElements), Sets.newHashSet(actual));
}
 

import org.apache.beam.sdk.options.PipelineOptionsFactory; //导入依赖的package包/类
@Test
@SuppressWarnings({"rawtypes", "unchecked"})
public void testTranslate() {
  ReadBoundedTranslator translator = new ReadBoundedTranslator();
  GearpumpPipelineOptions options =
      PipelineOptionsFactory.create().as(GearpumpPipelineOptions.class);
  Read.Bounded transform = mock(Read.Bounded.class);
  BoundedSource source = mock(BoundedSource.class);
  when(transform.getSource()).thenReturn(source);

  TranslationContext translationContext = mock(TranslationContext.class);
  when(translationContext.getPipelineOptions()).thenReturn(options);

  JavaStream stream = mock(JavaStream.class);
  PValue mockOutput = mock(PValue.class);
  when(translationContext.getOutput()).thenReturn(mockOutput);
  when(translationContext.getSourceStream(any(DataSource.class))).thenReturn(stream);

  translator.translate(transform, translationContext);
  verify(translationContext).getSourceStream(argThat(new BoundedSourceWrapperMatcher()));
  verify(translationContext).setOutputStream(mockOutput, stream);
}
 

import org.apache.beam.sdk.options.PipelineOptionsFactory; //导入依赖的package包/类
@Test
public void testProgress() throws IOException {
  final int numRecords = 5;
  @SuppressWarnings("deprecation")  // testing CountingSource
  BoundedSource<Long> source = CountingSource.upTo(numRecords);
  try (BoundedReader<Long> reader = source.createReader(PipelineOptionsFactory.create())) {
    // Check preconditions before starting. Note that CountingReader can always give an accurate
    // remaining parallelism.
    assertEquals(0.0, reader.getFractionConsumed(), 1e-6);
    assertEquals(0, reader.getSplitPointsConsumed());
    assertEquals(numRecords, reader.getSplitPointsRemaining());

    assertTrue(reader.start());
    int i = 0;
    do {
      assertEquals(i, reader.getSplitPointsConsumed());
      assertEquals(numRecords - i, reader.getSplitPointsRemaining());
      ++i;
    } while (reader.advance());

    assertEquals(numRecords, i); // exactly numRecords calls to advance()
    assertEquals(1.0, reader.getFractionConsumed(), 1e-6);
    assertEquals(numRecords, reader.getSplitPointsConsumed());
    assertEquals(0, reader.getSplitPointsRemaining());
  }
}
 

import org.apache.beam.sdk.options.PipelineOptionsFactory; //导入依赖的package包/类
@Test
public void testGetTableSucceeds() throws Exception {
  TableReference tableRef = new TableReference()
      .setProjectId("projectId")
      .setDatasetId("datasetId")
      .setTableId("tableId");

  Table testTable = new Table();
  testTable.setTableReference(tableRef);

  when(response.getContentType()).thenReturn(Json.MEDIA_TYPE);
  when(response.getStatusCode()).thenReturn(403).thenReturn(200);
  when(response.getContent())
      .thenReturn(toStream(errorWithReasonAndStatus("rateLimitExceeded", 403)))
      .thenReturn(toStream(testTable));

  BigQueryServicesImpl.DatasetServiceImpl datasetService =
      new BigQueryServicesImpl.DatasetServiceImpl(bigquery, PipelineOptionsFactory.create());

  Table table = datasetService.getTable(tableRef, BackOff.ZERO_BACKOFF, Sleeper.DEFAULT);

  assertEquals(testTable, table);
  verify(response, times(2)).getStatusCode();
  verify(response, times(2)).getContent();
  verify(response, times(2)).getContentType();
}
 

import org.apache.beam.sdk.options.PipelineOptionsFactory; //导入依赖的package包/类
@Test
public void testMatchingAllCalls() throws Exception {
  String[] args = new String[] {STORAGE_TRACE};
  GcsOptions options =
      PipelineOptionsFactory.fromArgs(args).as(GcsOptions.class);
  options.setGcpCredential(new TestCredential());

  assertNotNull(options.getGoogleApiTrace());

  Storage.Objects.Get getRequest =
      Transport.newStorageClient(options).build().objects().get("testBucketId", "testObjectId");
  assertEquals("TraceDestination", getRequest.get("$trace"));

  Storage.Objects.List listRequest =
      Transport.newStorageClient(options).build().objects().list("testProjectId");
  assertEquals("TraceDestination", listRequest.get("$trace"));
}