Examples with Pipeline org.apache.beam.sdk.Pipeline used on opensource projects

Example 71 with Pipeline

use of org.apache.beam.sdk.Pipeline in project beam by apache.

the class BatchStatefulParDoOverridesTest method testMultiOutputOverrideNonCrashing.

@Test
public void testMultiOutputOverrideNonCrashing() throws Exception {
    DataflowPipelineOptions options = buildPipelineOptions();
    options.setRunner(DataflowRunner.class);
    Pipeline pipeline = Pipeline.create(options);
    TupleTag<Integer> mainOutputTag = new TupleTag<Integer>() {
    };
    DummyStatefulDoFn fn = new DummyStatefulDoFn();
    pipeline.apply(Create.of(KV.of(1, 2))).apply(ParDo.of(fn).withOutputTags(mainOutputTag, TupleTagList.empty()));
    DataflowRunner runner = DataflowRunner.fromOptions(options);
    runner.replaceTransforms(pipeline);
    assertThat(findBatchStatefulDoFn(pipeline), equalTo((DoFn) fn));
}

Example 72 with Pipeline

use of org.apache.beam.sdk.Pipeline in project beam by apache.

the class DataflowPipelineTranslatorTest method testTaggedNamesOverridden.

/**
   * Test that in translation the name for collections of a multi-output ParDo - a special case
   * because the user can name tags - are overridden to be what the Dataflow service expects.
   */
@Test
public void testTaggedNamesOverridden() throws Exception {
    DataflowPipelineOptions options = buildPipelineOptions();
    DataflowRunner runner = DataflowRunner.fromOptions(options);
    options.setStreaming(false);
    DataflowPipelineTranslator translator = DataflowPipelineTranslator.fromOptions(options);
    Pipeline pipeline = Pipeline.create(options);
    TupleTag<Integer> tag1 = new TupleTag<Integer>("frazzle") {
    };
    TupleTag<Integer> tag2 = new TupleTag<Integer>("bazzle") {
    };
    TupleTag<Integer> tag3 = new TupleTag<Integer>() {
    };
    PCollectionTuple outputs = pipeline.apply(Create.of(3)).apply(ParDo.of(new DoFn<Integer, Integer>() {

        @ProcessElement
        public void drop() {
        }
    }).withOutputTags(tag1, TupleTagList.of(tag2).and(tag3)));
    outputs.get(tag1).setName("bizbazzle");
    outputs.get(tag2).setName("gonzaggle");
    outputs.get(tag3).setName("froonazzle");
    runner.replaceTransforms(pipeline);
    Job job = translator.translate(pipeline, runner, Collections.<DataflowPackage>emptyList()).getJob();
    // The ParDo step
    Step step = job.getSteps().get(1);
    String stepName = Structs.getString(step.getProperties(), PropertyNames.USER_NAME);
    List<Map<String, Object>> outputInfos = Structs.getListOfMaps(step.getProperties(), PropertyNames.OUTPUT_INFO, null);
    assertThat(outputInfos.size(), equalTo(3));
    // The names set by the user _and_ the tags _must_ be ignored, or metrics will not show up.
    for (int i = 0; i < outputInfos.size(); ++i) {
        assertThat(Structs.getString(outputInfos.get(i), PropertyNames.USER_NAME), equalTo(String.format("%s.out%s", stepName, i)));
    }
}

Example 73 with Pipeline

use of org.apache.beam.sdk.Pipeline in project beam by apache.

the class DataflowPipelineTranslatorTest method testMultiGraphPipelineSerialization.

@Test
public void testMultiGraphPipelineSerialization() throws Exception {
    DataflowPipelineOptions options = buildPipelineOptions();
    Pipeline p = Pipeline.create(options);
    PCollection<Integer> input = p.begin().apply(Create.of(1, 2, 3));
    input.apply(new UnrelatedOutputCreator());
    input.apply(new UnboundOutputCreator());
    DataflowPipelineTranslator t = DataflowPipelineTranslator.fromOptions(PipelineOptionsFactory.as(DataflowPipelineOptions.class));
    // Check that translation doesn't fail.
    JobSpecification jobSpecification = t.translate(p, DataflowRunner.fromOptions(options), Collections.<DataflowPackage>emptyList());
    assertAllStepOutputsHaveUniqueIds(jobSpecification.getJob());
}

Example 74 with Pipeline

use of org.apache.beam.sdk.Pipeline in project beam by apache.

the class BatchStatefulParDoOverridesTest method testSingleOutputOverrideNonCrashing.

@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));
}

Example 75 with Pipeline

use of org.apache.beam.sdk.Pipeline in project beam by apache.

the class DisplayDataEvaluator method displayDataForPrimitiveTransforms.

/**
   * Traverse the specified {@link PTransform}, collecting {@link DisplayData} registered on the
   * inner primitive {@link PTransform PTransforms}.
   *
   * @param root The root {@link PTransform} to traverse
   * @param inputCoder The coder to set for the {@link PTransform} input, or null to infer the
   *                   default coder.
   *
   * @return the set of {@link DisplayData} for primitive {@link PTransform PTransforms}.
   */
public <InputT> Set<DisplayData> displayDataForPrimitiveTransforms(final PTransform<? super PCollection<InputT>, ? extends POutput> root, Coder<InputT> inputCoder) {
    Create.Values<InputT> input;
    if (inputCoder != null) {
        input = Create.empty(inputCoder);
    } else {
        // These types don't actually work, but the pipeline will never be run
        input = (Create.Values<InputT>) Create.empty(VoidCoder.of());
    }
    Pipeline pipeline = Pipeline.create(options);
    pipeline.apply("Input", input).apply("Transform", root);
    return displayDataForPipeline(pipeline, root);
}