Examples with ParDoFn org.apache.beam.runners.dataflow.worker.util.common.worker.ParDoFn used on opensource projects

Example 16 with ParDoFn

use of org.apache.beam.runners.dataflow.worker.util.common.worker.ParDoFn in project beam by apache.

the class BeamFnMapTaskExecutorFactory method createPartialGroupByKeyOperation.

<K> OperationNode createPartialGroupByKeyOperation(Network<Node, Edge> network, ParallelInstructionNode node, PipelineOptions options, DataflowExecutionContext<?> executionContext, DataflowOperationContext operationContext) throws Exception {
    ParallelInstruction instruction = node.getParallelInstruction();
    PartialGroupByKeyInstruction pgbk = instruction.getPartialGroupByKey();
    OutputReceiver[] receivers = getOutputReceivers(network, node);
    Coder<?> windowedCoder = CloudObjects.coderFromCloudObject(CloudObject.fromSpec(pgbk.getInputElementCodec()));
    if (!(windowedCoder instanceof WindowedValueCoder)) {
        throw new IllegalArgumentException(String.format("unexpected kind of input coder for PartialGroupByKeyOperation: %s", windowedCoder));
    }
    Coder<?> elemCoder = ((WindowedValueCoder<?>) windowedCoder).getValueCoder();
    if (!(elemCoder instanceof KvCoder)) {
        throw new IllegalArgumentException(String.format("unexpected kind of input element coder for PartialGroupByKeyOperation: %s", elemCoder));
    }
    @SuppressWarnings("unchecked") KvCoder<K, ?> keyedElementCoder = (KvCoder<K, ?>) elemCoder;
    CloudObject cloudUserFn = pgbk.getValueCombiningFn() != null ? CloudObject.fromSpec(pgbk.getValueCombiningFn()) : null;
    ParDoFn fn = PartialGroupByKeyParDoFns.create(options, keyedElementCoder, cloudUserFn, pgbk.getSideInputs(), Arrays.<Receiver>asList(receivers), executionContext, operationContext);
    return OperationNode.create(new ParDoOperation(fn, receivers, operationContext));
}

Example 17 with ParDoFn

use of org.apache.beam.runners.dataflow.worker.util.common.worker.ParDoFn in project beam by apache.

the class IntrinsicMapTaskExecutorFactory method createParDoOperation.

private OperationNode createParDoOperation(Network<Node, Edge> network, ParallelInstructionNode node, PipelineOptions options, DataflowExecutionContext<?> executionContext, DataflowOperationContext operationContext) throws Exception {
    ParallelInstruction instruction = node.getParallelInstruction();
    ParDoInstruction parDo = instruction.getParDo();
    TupleTag<?> mainOutputTag = tupleTag(parDo.getMultiOutputInfos().get(0));
    ImmutableMap.Builder<TupleTag<?>, Integer> outputTagsToReceiverIndicesBuilder = ImmutableMap.builder();
    int successorOffset = 0;
    for (Node successor : network.successors(node)) {
        for (Edge edge : network.edgesConnecting(node, successor)) {
            outputTagsToReceiverIndicesBuilder.put(tupleTag(((MultiOutputInfoEdge) edge).getMultiOutputInfo()), successorOffset);
        }
        successorOffset += 1;
    }
    ParDoFn fn = parDoFnFactory.create(options, CloudObject.fromSpec(parDo.getUserFn()), parDo.getSideInputs(), mainOutputTag, outputTagsToReceiverIndicesBuilder.build(), executionContext, operationContext);
    OutputReceiver[] receivers = getOutputReceivers(network, node);
    return OperationNode.create(new ParDoOperation(fn, receivers, operationContext));
}

Example 18 with ParDoFn

use of org.apache.beam.runners.dataflow.worker.util.common.worker.ParDoFn in project beam by apache.

the class IntrinsicMapTaskExecutorFactory method createPartialGroupByKeyOperation.

<K> OperationNode createPartialGroupByKeyOperation(Network<Node, Edge> network, ParallelInstructionNode node, PipelineOptions options, DataflowExecutionContext<?> executionContext, DataflowOperationContext operationContext) throws Exception {
    ParallelInstruction instruction = node.getParallelInstruction();
    PartialGroupByKeyInstruction pgbk = instruction.getPartialGroupByKey();
    OutputReceiver[] receivers = getOutputReceivers(network, node);
    Coder<?> windowedCoder = CloudObjects.coderFromCloudObject(CloudObject.fromSpec(pgbk.getInputElementCodec()));
    if (!(windowedCoder instanceof WindowedValueCoder)) {
        throw new IllegalArgumentException(String.format("unexpected kind of input coder for PartialGroupByKeyOperation: %s", windowedCoder));
    }
    Coder<?> elemCoder = ((WindowedValueCoder<?>) windowedCoder).getValueCoder();
    if (!(elemCoder instanceof KvCoder)) {
        throw new IllegalArgumentException(String.format("unexpected kind of input element coder for PartialGroupByKeyOperation: %s", elemCoder));
    }
    @SuppressWarnings("unchecked") KvCoder<K, ?> keyedElementCoder = (KvCoder<K, ?>) elemCoder;
    CloudObject cloudUserFn = pgbk.getValueCombiningFn() != null ? CloudObject.fromSpec(pgbk.getValueCombiningFn()) : null;
    ParDoFn fn = PartialGroupByKeyParDoFns.create(options, keyedElementCoder, cloudUserFn, pgbk.getSideInputs(), Arrays.<Receiver>asList(receivers), executionContext, operationContext);
    return OperationNode.create(new ParDoOperation(fn, receivers, operationContext));
}

Example 19 with ParDoFn

use of org.apache.beam.runners.dataflow.worker.util.common.worker.ParDoFn in project beam by apache.

the class GroupAlsoByWindowParDoFnFactory method create.

@Override
public ParDoFn create(PipelineOptions options, CloudObject cloudUserFn, @Nullable List<SideInputInfo> sideInputInfos, TupleTag<?> mainOutputTag, Map<TupleTag<?>, Integer> outputTupleTagsToReceiverIndices, final DataflowExecutionContext<?> executionContext, DataflowOperationContext operationContext) throws Exception {
    Map.Entry<TupleTag<?>, Integer> entry = Iterables.getOnlyElement(outputTupleTagsToReceiverIndices.entrySet());
    checkArgument(entry.getKey().equals(mainOutputTag), "Output tags should reference only the main output tag: %s vs %s", entry.getKey(), mainOutputTag);
    checkArgument(entry.getValue() == 0, "There should be a single receiver, but using receiver index %s", entry.getValue());
    byte[] encodedWindowingStrategy = getBytes(cloudUserFn, PropertyNames.SERIALIZED_FN);
    WindowingStrategy windowingStrategy;
    try {
        windowingStrategy = deserializeWindowingStrategy(encodedWindowingStrategy);
    } catch (Exception e) {
        // TODO: Catch block disappears, becoming an error once Python SDK is compliant.
        if (DataflowRunner.hasExperiment(options.as(DataflowPipelineDebugOptions.class), "beam_fn_api")) {
            LOG.info("FnAPI: Unable to deserialize windowing strategy, assuming default", e);
            windowingStrategy = WindowingStrategy.globalDefault();
        } else {
            throw e;
        }
    }
    byte[] serializedCombineFn = getBytes(cloudUserFn, WorkerPropertyNames.COMBINE_FN, null);
    AppliedCombineFn<?, ?, ?, ?> combineFn = null;
    if (serializedCombineFn != null) {
        Object combineFnObj = SerializableUtils.deserializeFromByteArray(serializedCombineFn, "serialized combine fn");
        checkArgument(combineFnObj instanceof AppliedCombineFn, "unexpected kind of AppliedCombineFn: " + combineFnObj.getClass().getName());
        combineFn = (AppliedCombineFn<?, ?, ?, ?>) combineFnObj;
    }
    Map<String, Object> inputCoderObject = getObject(cloudUserFn, WorkerPropertyNames.INPUT_CODER);
    Coder<?> inputCoder = CloudObjects.coderFromCloudObject(CloudObject.fromSpec(inputCoderObject));
    checkArgument(inputCoder instanceof WindowedValueCoder, "Expected WindowedValueCoder for inputCoder, got: " + inputCoder.getClass().getName());
    @SuppressWarnings("unchecked") WindowedValueCoder<?> windowedValueCoder = (WindowedValueCoder<?>) inputCoder;
    Coder<?> elemCoder = windowedValueCoder.getValueCoder();
    checkArgument(elemCoder instanceof KvCoder, "Expected KvCoder for inputCoder, got: " + elemCoder.getClass().getName());
    @SuppressWarnings("unchecked") KvCoder<?, ?> kvCoder = (KvCoder<?, ?>) elemCoder;
    boolean isStreamingPipeline = options.as(StreamingOptions.class).isStreaming();
    SideInputReader sideInputReader = NullSideInputReader.empty();
    @Nullable AppliedCombineFn<?, ?, ?, ?> maybeMergingCombineFn = null;
    if (combineFn != null) {
        sideInputReader = executionContext.getSideInputReader(sideInputInfos, combineFn.getSideInputViews(), operationContext);
        String phase = getString(cloudUserFn, WorkerPropertyNames.PHASE, CombinePhase.ALL);
        checkArgument(phase.equals(CombinePhase.ALL) || phase.equals(CombinePhase.MERGE), "Unexpected phase: %s", phase);
        if (phase.equals(CombinePhase.MERGE)) {
            maybeMergingCombineFn = makeAppliedMergingFunction(combineFn);
        } else {
            maybeMergingCombineFn = combineFn;
        }
    }
    StateInternalsFactory<?> stateInternalsFactory = key -> executionContext.getStepContext(operationContext).stateInternals();
    // This will be a GABW Fn for either batch or streaming, with combiner in it or not
    GroupAlsoByWindowFn<?, ?> fn;
    // This will be a FakeKeyedWorkItemCoder for streaming or null for batch
    Coder<?> gabwInputCoder;
    // TODO: do not do this with mess of "if"
    if (isStreamingPipeline) {
        if (maybeMergingCombineFn == null) {
            fn = StreamingGroupAlsoByWindowsDoFns.createForIterable(windowingStrategy, stateInternalsFactory, ((KvCoder) kvCoder).getValueCoder());
            gabwInputCoder = WindmillKeyedWorkItem.FakeKeyedWorkItemCoder.of(kvCoder);
        } else {
            fn = StreamingGroupAlsoByWindowsDoFns.create(windowingStrategy, stateInternalsFactory, (AppliedCombineFn) maybeMergingCombineFn, ((KvCoder) kvCoder).getKeyCoder());
            gabwInputCoder = WindmillKeyedWorkItem.FakeKeyedWorkItemCoder.of(((AppliedCombineFn) maybeMergingCombineFn).getKvCoder());
        }
    } else {
        if (maybeMergingCombineFn == null) {
            fn = BatchGroupAlsoByWindowsDoFns.createForIterable(windowingStrategy, stateInternalsFactory, ((KvCoder) kvCoder).getValueCoder());
            gabwInputCoder = null;
        } else {
            fn = BatchGroupAlsoByWindowsDoFns.create(windowingStrategy, (AppliedCombineFn) maybeMergingCombineFn);
            gabwInputCoder = null;
        }
    }
    // TODO: or anyhow related to it, do not do this with mess of "if"
    if (maybeMergingCombineFn != null) {
        return new GroupAlsoByWindowsParDoFn(options, fn, windowingStrategy, ((AppliedCombineFn) maybeMergingCombineFn).getSideInputViews(), gabwInputCoder, sideInputReader, mainOutputTag, executionContext.getStepContext(operationContext));
    } else {
        return new GroupAlsoByWindowsParDoFn(options, fn, windowingStrategy, null, gabwInputCoder, sideInputReader, mainOutputTag, executionContext.getStepContext(operationContext));
    }
}

Example 20 with ParDoFn

use of org.apache.beam.runners.dataflow.worker.util.common.worker.ParDoFn in project beam by apache.

the class DefaultParDoFnFactoryTest method testCreateSimpleParDoFn.

/**
 * Tests that a {@link SimpleParDoFn} is correctly dispatched to {@code UserParDoFnFactory} and
 * instantiated correctly.
 */
@Test
public void testCreateSimpleParDoFn() throws Exception {
    // A serialized DoFn
    String stringFieldValue = "some state";
    long longFieldValue = 42L;
    TestDoFn fn = new TestDoFn(stringFieldValue, longFieldValue);
    String serializedFn = StringUtils.byteArrayToJsonString(SerializableUtils.serializeToByteArray(DoFnInfo.forFn(fn, WindowingStrategy.globalDefault(), null, /* side input views */
    null, /* input coder */
    new TupleTag<>("output"), /* main output */
    DoFnSchemaInformation.create(), Collections.emptyMap())));
    CloudObject cloudUserFn = CloudObject.forClassName("DoFn");
    addString(cloudUserFn, "serialized_fn", serializedFn);
    // Create the ParDoFn from the serialized DoFn
    ParDoFn parDoFn = DEFAULT_FACTORY.create(DEFAULT_OPTIONS, cloudUserFn, null, MAIN_OUTPUT, ImmutableMap.<TupleTag<?>, Integer>of(MAIN_OUTPUT, 0), DEFAULT_EXECUTION_CONTEXT, TestOperationContext.create(counterSet));
    // Test that the factory created the correct class
    assertThat(parDoFn, instanceOf(SimpleParDoFn.class));
    // TODO: move the asserts below into new tests in UserParDoFnFactoryTest, and this test should
    // simply assert that DefaultParDoFnFactory.create() matches UserParDoFnFactory.create()
    // Test that the DoFnInfo reflects the one passed in
    SimpleParDoFn simpleParDoFn = (SimpleParDoFn) parDoFn;
    parDoFn.startBundle(new OutputReceiver());
    // DoFnInfo may not yet be initialized until an element is processed
    parDoFn.processElement(WindowedValue.valueInGlobalWindow("foo"));
    @SuppressWarnings("rawtypes") DoFnInfo doFnInfo = simpleParDoFn.getDoFnInfo();
    DoFn innerDoFn = (TestDoFn) doFnInfo.getDoFn();
    assertThat(innerDoFn, instanceOf(TestDoFn.class));
    assertThat(doFnInfo.getWindowingStrategy().getWindowFn(), instanceOf(GlobalWindows.class));
    assertThat(doFnInfo.getWindowingStrategy().getTrigger(), instanceOf(DefaultTrigger.class));
    // Test that the deserialized user DoFn is as expected
    TestDoFn actualTestDoFn = (TestDoFn) innerDoFn;
    assertEquals(stringFieldValue, actualTestDoFn.stringField);
    assertEquals(longFieldValue, actualTestDoFn.longField);
}