Search in sources :

Example 11 with ImmutableMap

use of org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableMap in project beam by apache.

the class DoFnOperatorTest method keyedParDoPushbackDataCheckpointing.

@Test
public void keyedParDoPushbackDataCheckpointing() throws Exception {
    pushbackDataCheckpointing(() -> {
        StringUtf8Coder keyCoder = StringUtf8Coder.of();
        Coder<WindowedValue<String>> coder = WindowedValue.getFullCoder(keyCoder, IntervalWindow.getCoder());
        TupleTag<String> outputTag = new TupleTag<>("main-output");
        KeySelector<WindowedValue<String>, ByteBuffer> keySelector = e -> FlinkKeyUtils.encodeKey(e.getValue(), keyCoder);
        ImmutableMap<Integer, PCollectionView<?>> sideInputMapping = ImmutableMap.<Integer, PCollectionView<?>>builder().put(1, view1).put(2, view2).build();
        DoFnOperator<String, String> doFnOperator = new DoFnOperator<>(new IdentityDoFn<>(), "stepName", coder, Collections.emptyMap(), outputTag, Collections.emptyList(), new DoFnOperator.MultiOutputOutputManagerFactory<>(outputTag, coder, new SerializablePipelineOptions(FlinkPipelineOptions.defaults())), WindowingStrategy.of(FixedWindows.of(Duration.millis(100))), sideInputMapping, /* side-input mapping */
        ImmutableList.of(view1, view2), /* side inputs */
        FlinkPipelineOptions.defaults(), keyCoder, keySelector, DoFnSchemaInformation.create(), Collections.emptyMap());
        return new KeyedTwoInputStreamOperatorTestHarness<>(doFnOperator, keySelector, // we use a dummy key for the second input since it is considered to be broadcast
        null, new CoderTypeInformation<>(FlinkKeyUtils.ByteBufferCoder.of(), FlinkPipelineOptions.defaults()));
    });
}
Also used : StateSpec(org.apache.beam.sdk.state.StateSpec) Arrays(java.util.Arrays) StateNamespace(org.apache.beam.runners.core.StateNamespace) SerializablePipelineOptions(org.apache.beam.runners.core.construction.SerializablePipelineOptions) TimestampCombiner(org.apache.beam.sdk.transforms.windowing.TimestampCombiner) WindowedValue(org.apache.beam.sdk.util.WindowedValue) StreamRecordStripper.stripStreamRecordFromWindowedValue(org.apache.beam.runners.flink.translation.wrappers.streaming.StreamRecordStripper.stripStreamRecordFromWindowedValue) IsIterableContainingInOrder.contains(org.hamcrest.collection.IsIterableContainingInOrder.contains) FlinkPipelineOptions(org.apache.beam.runners.flink.FlinkPipelineOptions) TimerSpecs(org.apache.beam.sdk.state.TimerSpecs) DoFnRunner(org.apache.beam.runners.core.DoFnRunner) FlinkMetricContainer(org.apache.beam.runners.flink.metrics.FlinkMetricContainer) StepContext(org.apache.beam.runners.core.StepContext) ValueState(org.apache.beam.sdk.state.ValueState) ImmutableMap(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableMap) KeyedOneInputStreamOperatorTestHarness(org.apache.flink.streaming.util.KeyedOneInputStreamOperatorTestHarness) TimerInternals(org.apache.beam.runners.core.TimerInternals) ByteBuffer(java.nio.ByteBuffer) DoFnSchemaInformation(org.apache.beam.sdk.transforms.DoFnSchemaInformation) OneInputStreamOperatorTestHarness(org.apache.flink.streaming.util.OneInputStreamOperatorTestHarness) TypeFactory(com.fasterxml.jackson.databind.type.TypeFactory) Create(org.apache.beam.sdk.transforms.Create) TwoInputStreamOperatorTestHarness(org.apache.flink.streaming.util.TwoInputStreamOperatorTestHarness) Iterables(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.Iterables) LRUMap(com.fasterxml.jackson.databind.util.LRUMap) Window(org.apache.beam.sdk.transforms.windowing.Window) GlobalWindow(org.apache.beam.sdk.transforms.windowing.GlobalWindow) FluentIterable(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.FluentIterable) TypeInformation(org.apache.flink.api.common.typeinfo.TypeInformation) CoderTypeInformation(org.apache.beam.runners.flink.translation.types.CoderTypeInformation) KvCoder(org.apache.beam.sdk.coders.KvCoder) KeySelector(org.apache.flink.api.java.functions.KeySelector) KeyedTwoInputStreamOperatorTestHarness(org.apache.flink.streaming.util.KeyedTwoInputStreamOperatorTestHarness) PaneInfo(org.apache.beam.sdk.transforms.windowing.PaneInfo) FullWindowedValueCoder(org.apache.beam.sdk.util.WindowedValue.FullWindowedValueCoder) OutputTag(org.apache.flink.util.OutputTag) VarLongCoder(org.apache.beam.sdk.coders.VarLongCoder) OperatorSubtaskState(org.apache.flink.runtime.checkpoint.OperatorSubtaskState) Collectors(java.util.stream.Collectors) Matchers.instanceOf(org.hamcrest.Matchers.instanceOf) Objects(java.util.Objects) List(java.util.List) WatermarkHoldState(org.apache.beam.sdk.state.WatermarkHoldState) Matchers.containsInAnyOrder(org.hamcrest.Matchers.containsInAnyOrder) Timer(org.apache.beam.sdk.state.Timer) Matchers.equalTo(org.hamcrest.Matchers.equalTo) Optional(java.util.Optional) ImmutableList(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableList) Matchers.greaterThan(org.hamcrest.Matchers.greaterThan) Matchers.is(org.hamcrest.Matchers.is) StateTag(org.apache.beam.runners.core.StateTag) WindowingStrategy(org.apache.beam.sdk.values.WindowingStrategy) StatefulDoFnRunner(org.apache.beam.runners.core.StatefulDoFnRunner) Whitebox(org.powermock.reflect.Whitebox) KV(org.apache.beam.sdk.values.KV) Assert.assertThrows(org.junit.Assert.assertThrows) Duration(org.joda.time.Duration) RunWith(org.junit.runner.RunWith) Coder(org.apache.beam.sdk.coders.Coder) HashMap(java.util.HashMap) View(org.apache.beam.sdk.transforms.View) StateNamespaces(org.apache.beam.runners.core.StateNamespaces) Supplier(java.util.function.Supplier) StateTags(org.apache.beam.runners.core.StateTags) ArrayList(java.util.ArrayList) StringUtf8Coder(org.apache.beam.sdk.coders.StringUtf8Coder) RawUnionValue(org.apache.beam.sdk.transforms.join.RawUnionValue) StreamRecord(org.apache.flink.streaming.runtime.streamrecord.StreamRecord) TimerSpec(org.apache.beam.sdk.state.TimerSpec) CoderTypeSerializer(org.apache.beam.runners.flink.translation.types.CoderTypeSerializer) TupleTag(org.apache.beam.sdk.values.TupleTag) MatcherAssert.assertThat(org.hamcrest.MatcherAssert.assertThat) Pipeline(org.apache.beam.sdk.Pipeline) Nullable(org.checkerframework.checker.nullness.qual.Nullable) Before(org.junit.Before) DoFn(org.apache.beam.sdk.transforms.DoFn) PCollectionViewTesting(org.apache.beam.sdk.testing.PCollectionViewTesting) FixedWindows(org.apache.beam.sdk.transforms.windowing.FixedWindows) Function(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.base.Function) Test(org.junit.Test) JUnit4(org.junit.runners.JUnit4) PCollection(org.apache.beam.sdk.values.PCollection) Mockito(org.mockito.Mockito) Matchers.emptyIterable(org.hamcrest.Matchers.emptyIterable) StateSpecs(org.apache.beam.sdk.state.StateSpecs) PCollectionView(org.apache.beam.sdk.values.PCollectionView) BoundedWindow(org.apache.beam.sdk.transforms.windowing.BoundedWindow) Instant(org.joda.time.Instant) VarIntCoder(org.apache.beam.sdk.coders.VarIntCoder) IntervalWindow(org.apache.beam.sdk.transforms.windowing.IntervalWindow) Collections(java.util.Collections) TimeDomain(org.apache.beam.sdk.state.TimeDomain) Assert.assertEquals(org.junit.Assert.assertEquals) KeyedTwoInputStreamOperatorTestHarness(org.apache.flink.streaming.util.KeyedTwoInputStreamOperatorTestHarness) TupleTag(org.apache.beam.sdk.values.TupleTag) ByteBuffer(java.nio.ByteBuffer) PCollectionView(org.apache.beam.sdk.values.PCollectionView) WindowedValue(org.apache.beam.sdk.util.WindowedValue) StreamRecordStripper.stripStreamRecordFromWindowedValue(org.apache.beam.runners.flink.translation.wrappers.streaming.StreamRecordStripper.stripStreamRecordFromWindowedValue) StringUtf8Coder(org.apache.beam.sdk.coders.StringUtf8Coder) SerializablePipelineOptions(org.apache.beam.runners.core.construction.SerializablePipelineOptions) Test(org.junit.Test)

Example 12 with ImmutableMap

use of org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableMap in project beam by apache.

the class DataflowPipelineTranslatorTest method testStepDisplayData.

@Test
public void testStepDisplayData() throws Exception {
    DataflowPipelineOptions options = buildPipelineOptions();
    DataflowPipelineTranslator translator = DataflowPipelineTranslator.fromOptions(options);
    Pipeline pipeline = Pipeline.create(options);
    DoFn<Integer, Integer> fn1 = new DoFn<Integer, Integer>() {

        @ProcessElement
        public void processElement(ProcessContext c) throws Exception {
            c.output(c.element());
        }

        @Override
        public void populateDisplayData(DisplayData.Builder builder) {
            builder.add(DisplayData.item("foo", "bar")).add(DisplayData.item("foo2", DataflowPipelineTranslatorTest.class).withLabel("Test Class").withLinkUrl("http://www.google.com"));
        }
    };
    DoFn<Integer, Integer> fn2 = new DoFn<Integer, Integer>() {

        @ProcessElement
        public void processElement(ProcessContext c) throws Exception {
            c.output(c.element());
        }

        @Override
        public void populateDisplayData(DisplayData.Builder builder) {
            builder.add(DisplayData.item("foo3", 1234));
        }
    };
    ParDo.SingleOutput<Integer, Integer> parDo1 = ParDo.of(fn1);
    ParDo.SingleOutput<Integer, Integer> parDo2 = ParDo.of(fn2);
    pipeline.apply(Create.of(1, 2, 3)).apply(parDo1).apply(parDo2);
    DataflowRunner runner = DataflowRunner.fromOptions(options);
    runner.replaceV1Transforms(pipeline);
    SdkComponents sdkComponents = createSdkComponents(options);
    RunnerApi.Pipeline pipelineProto = PipelineTranslation.toProto(pipeline, sdkComponents, true);
    Job job = translator.translate(pipeline, pipelineProto, sdkComponents, runner, Collections.emptyList()).getJob();
    assertAllStepOutputsHaveUniqueIds(job);
    List<Step> steps = job.getSteps();
    assertEquals(3, steps.size());
    Map<String, Object> parDo1Properties = steps.get(1).getProperties();
    Map<String, Object> parDo2Properties = steps.get(2).getProperties();
    assertThat(parDo1Properties, hasKey("display_data"));
    @SuppressWarnings("unchecked") Collection<Map<String, String>> fn1displayData = (Collection<Map<String, String>>) parDo1Properties.get("display_data");
    @SuppressWarnings("unchecked") Collection<Map<String, String>> fn2displayData = (Collection<Map<String, String>>) parDo2Properties.get("display_data");
    ImmutableSet<ImmutableMap<String, Object>> expectedFn1DisplayData = ImmutableSet.of(ImmutableMap.<String, Object>builder().put("key", "foo").put("type", "STRING").put("value", "bar").put("namespace", fn1.getClass().getName()).build(), ImmutableMap.<String, Object>builder().put("key", "fn").put("label", "Transform Function").put("type", "JAVA_CLASS").put("value", fn1.getClass().getName()).put("shortValue", fn1.getClass().getSimpleName()).put("namespace", parDo1.getClass().getName()).build(), ImmutableMap.<String, Object>builder().put("key", "foo2").put("type", "JAVA_CLASS").put("value", DataflowPipelineTranslatorTest.class.getName()).put("shortValue", DataflowPipelineTranslatorTest.class.getSimpleName()).put("namespace", fn1.getClass().getName()).put("label", "Test Class").put("linkUrl", "http://www.google.com").build());
    ImmutableSet<ImmutableMap<String, Object>> expectedFn2DisplayData = ImmutableSet.of(ImmutableMap.<String, Object>builder().put("key", "fn").put("label", "Transform Function").put("type", "JAVA_CLASS").put("value", fn2.getClass().getName()).put("shortValue", fn2.getClass().getSimpleName()).put("namespace", parDo2.getClass().getName()).build(), ImmutableMap.<String, Object>builder().put("key", "foo3").put("type", "INTEGER").put("value", 1234L).put("namespace", fn2.getClass().getName()).build());
    assertEquals(expectedFn1DisplayData, ImmutableSet.copyOf(fn1displayData));
    assertEquals(expectedFn2DisplayData, ImmutableSet.copyOf(fn2displayData));
}
Also used : Step(com.google.api.services.dataflow.model.Step) Structs.getString(org.apache.beam.runners.dataflow.util.Structs.getString) ByteString(org.apache.beam.vendor.grpc.v1p43p2.com.google.protobuf.ByteString) SdkComponents(org.apache.beam.runners.core.construction.SdkComponents) RunnerApi(org.apache.beam.model.pipeline.v1.RunnerApi) Job(com.google.api.services.dataflow.model.Job) DataflowPipelineOptions(org.apache.beam.runners.dataflow.options.DataflowPipelineOptions) ImmutableMap(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableMap) Pipeline(org.apache.beam.sdk.Pipeline) DoFn(org.apache.beam.sdk.transforms.DoFn) ParDo(org.apache.beam.sdk.transforms.ParDo) Collection(java.util.Collection) PCollection(org.apache.beam.sdk.values.PCollection) CloudObject(org.apache.beam.runners.dataflow.util.CloudObject) ImmutableMap(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableMap) Map(java.util.Map) Test(org.junit.Test)

Example 13 with ImmutableMap

use of org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableMap in project beam by apache.

the class CreateExecutableStageNodeFunction method apply.

@Override
public Node apply(MutableNetwork<Node, Edge> input) {
    for (Node node : input.nodes()) {
        if (node instanceof RemoteGrpcPortNode || node instanceof ParallelInstructionNode || node instanceof InstructionOutputNode) {
            continue;
        }
        throw new IllegalArgumentException(String.format("Network contains unknown type of node: %s", input));
    }
    // Fix all non output nodes to have named edges.
    for (Node node : input.nodes()) {
        if (node instanceof InstructionOutputNode) {
            continue;
        }
        for (Node successor : input.successors(node)) {
            for (Edge edge : input.edgesConnecting(node, successor)) {
                if (edge instanceof DefaultEdge) {
                    input.removeEdge(edge);
                    input.addEdge(node, successor, MultiOutputInfoEdge.create(new MultiOutputInfo().setTag(idGenerator.getId())));
                }
            }
        }
    }
    RunnerApi.Components.Builder componentsBuilder = RunnerApi.Components.newBuilder();
    componentsBuilder.mergeFrom(this.pipeline.getComponents());
    // Default to use the Java environment if pipeline doesn't have environment specified.
    if (pipeline.getComponents().getEnvironmentsMap().isEmpty()) {
        String envId = Environments.JAVA_SDK_HARNESS_ENVIRONMENT.getUrn() + idGenerator.getId();
        componentsBuilder.putEnvironments(envId, Environments.JAVA_SDK_HARNESS_ENVIRONMENT);
    }
    // By default, use GlobalWindow for all languages.
    // For java, if there is a IntervalWindowCoder, then use FixedWindow instead.
    // TODO: should get real WindowingStategy from pipeline proto.
    String globalWindowingStrategyId = "generatedGlobalWindowingStrategy" + idGenerator.getId();
    String intervalWindowEncodingWindowingStrategyId = "generatedIntervalWindowEncodingWindowingStrategy" + idGenerator.getId();
    SdkComponents sdkComponents = SdkComponents.create(pipeline.getComponents(), null);
    try {
        registerWindowingStrategy(globalWindowingStrategyId, WindowingStrategy.globalDefault(), componentsBuilder, sdkComponents);
        registerWindowingStrategy(intervalWindowEncodingWindowingStrategyId, WindowingStrategy.of(FixedWindows.of(Duration.standardSeconds(1))), componentsBuilder, sdkComponents);
    } catch (IOException exc) {
        throw new RuntimeException("Could not convert default windowing stratey to proto", exc);
    }
    Map<Node, String> nodesToPCollections = new HashMap<>();
    ImmutableMap.Builder<String, NameContext> ptransformIdToNameContexts = ImmutableMap.builder();
    ImmutableMap.Builder<String, Iterable<SideInputInfo>> ptransformIdToSideInputInfos = ImmutableMap.builder();
    ImmutableMap.Builder<String, Iterable<PCollectionView<?>>> ptransformIdToPCollectionViews = ImmutableMap.builder();
    // A field of ExecutableStage which includes the PCollection goes to worker side.
    Set<PCollectionNode> executableStageOutputs = new HashSet<>();
    // A field of ExecutableStage which includes the PCollection goes to runner side.
    Set<PCollectionNode> executableStageInputs = new HashSet<>();
    for (InstructionOutputNode node : Iterables.filter(input.nodes(), InstructionOutputNode.class)) {
        InstructionOutput instructionOutput = node.getInstructionOutput();
        String coderId = "generatedCoder" + idGenerator.getId();
        String windowingStrategyId;
        try (ByteString.Output output = ByteString.newOutput()) {
            try {
                Coder<?> javaCoder = CloudObjects.coderFromCloudObject(CloudObject.fromSpec(instructionOutput.getCodec()));
                Coder<?> elementCoder = ((WindowedValueCoder<?>) javaCoder).getValueCoder();
                sdkComponents.registerCoder(elementCoder);
                RunnerApi.Coder coderProto = CoderTranslation.toProto(elementCoder, sdkComponents);
                componentsBuilder.putCoders(coderId, coderProto);
                // For now, Dataflow runner harness only deal with FixedWindow.
                if (javaCoder instanceof FullWindowedValueCoder) {
                    FullWindowedValueCoder<?> windowedValueCoder = (FullWindowedValueCoder<?>) javaCoder;
                    Coder<?> windowCoder = windowedValueCoder.getWindowCoder();
                    if (windowCoder instanceof IntervalWindowCoder) {
                        windowingStrategyId = intervalWindowEncodingWindowingStrategyId;
                    } else if (windowCoder instanceof GlobalWindow.Coder) {
                        windowingStrategyId = globalWindowingStrategyId;
                    } else {
                        throw new UnsupportedOperationException(String.format("Dataflow portable runner harness doesn't support windowing with %s", windowCoder));
                    }
                } else {
                    throw new UnsupportedOperationException("Dataflow portable runner harness only supports FullWindowedValueCoder");
                }
            } catch (IOException e) {
                throw new IllegalArgumentException(String.format("Unable to encode coder %s for output %s", instructionOutput.getCodec(), instructionOutput), e);
            } catch (Exception e) {
                // Coder probably wasn't a java coder
                OBJECT_MAPPER.writeValue(output, instructionOutput.getCodec());
                componentsBuilder.putCoders(coderId, RunnerApi.Coder.newBuilder().setSpec(RunnerApi.FunctionSpec.newBuilder().setPayload(output.toByteString())).build());
                // For non-java coder, hope it's GlobalWindows by default.
                // TODO(BEAM-6231): Actually discover the right windowing strategy.
                windowingStrategyId = globalWindowingStrategyId;
            }
        } catch (IOException e) {
            throw new IllegalArgumentException(String.format("Unable to encode coder %s for output %s", instructionOutput.getCodec(), instructionOutput), e);
        }
        // TODO(BEAM-6275): Set correct IsBounded on generated PCollections
        String pcollectionId = node.getPcollectionId();
        RunnerApi.PCollection pCollection = RunnerApi.PCollection.newBuilder().setCoderId(coderId).setWindowingStrategyId(windowingStrategyId).setIsBounded(RunnerApi.IsBounded.Enum.BOUNDED).build();
        nodesToPCollections.put(node, pcollectionId);
        componentsBuilder.putPcollections(pcollectionId, pCollection);
        // is set
        if (isExecutableStageOutputPCollection(input, node)) {
            executableStageOutputs.add(PipelineNode.pCollection(pcollectionId, pCollection));
        }
        if (isExecutableStageInputPCollection(input, node)) {
            executableStageInputs.add(PipelineNode.pCollection(pcollectionId, pCollection));
        }
    }
    componentsBuilder.putAllCoders(sdkComponents.toComponents().getCodersMap());
    Set<PTransformNode> executableStageTransforms = new HashSet<>();
    Set<TimerReference> executableStageTimers = new HashSet<>();
    List<UserStateId> userStateIds = new ArrayList<>();
    Set<SideInputReference> executableStageSideInputs = new HashSet<>();
    for (ParallelInstructionNode node : Iterables.filter(input.nodes(), ParallelInstructionNode.class)) {
        ImmutableMap.Builder<String, PCollectionNode> sideInputIds = ImmutableMap.builder();
        ParallelInstruction parallelInstruction = node.getParallelInstruction();
        String ptransformId = "generatedPtransform" + idGenerator.getId();
        ptransformIdToNameContexts.put(ptransformId, NameContext.create(null, parallelInstruction.getOriginalName(), parallelInstruction.getSystemName(), parallelInstruction.getName()));
        RunnerApi.PTransform.Builder pTransform = RunnerApi.PTransform.newBuilder();
        RunnerApi.FunctionSpec.Builder transformSpec = RunnerApi.FunctionSpec.newBuilder();
        List<String> timerIds = new ArrayList<>();
        if (parallelInstruction.getParDo() != null) {
            ParDoInstruction parDoInstruction = parallelInstruction.getParDo();
            CloudObject userFnSpec = CloudObject.fromSpec(parDoInstruction.getUserFn());
            String userFnClassName = userFnSpec.getClassName();
            if (userFnClassName.equals("CombineValuesFn") || userFnClassName.equals("KeyedCombineFn")) {
                transformSpec = transformCombineValuesFnToFunctionSpec(userFnSpec);
                ptransformIdToPCollectionViews.put(ptransformId, Collections.emptyList());
            } else {
                String parDoPTransformId = getString(userFnSpec, PropertyNames.SERIALIZED_FN);
                RunnerApi.PTransform parDoPTransform = pipeline.getComponents().getTransformsOrDefault(parDoPTransformId, null);
                // TODO: only the non-null branch should exist; for migration ease only
                if (parDoPTransform != null) {
                    checkArgument(parDoPTransform.getSpec().getUrn().equals(PTransformTranslation.PAR_DO_TRANSFORM_URN), "Found transform \"%s\" for ParallelDo instruction, " + " but that transform had unexpected URN \"%s\" (expected \"%s\")", parDoPTransformId, parDoPTransform.getSpec().getUrn(), PTransformTranslation.PAR_DO_TRANSFORM_URN);
                    RunnerApi.ParDoPayload parDoPayload;
                    try {
                        parDoPayload = RunnerApi.ParDoPayload.parseFrom(parDoPTransform.getSpec().getPayload());
                    } catch (InvalidProtocolBufferException exc) {
                        throw new RuntimeException("ParDo did not have a ParDoPayload", exc);
                    }
                    // user timers and user state.
                    for (Map.Entry<String, RunnerApi.TimerFamilySpec> entry : parDoPayload.getTimerFamilySpecsMap().entrySet()) {
                        timerIds.add(entry.getKey());
                    }
                    for (Map.Entry<String, RunnerApi.StateSpec> entry : parDoPayload.getStateSpecsMap().entrySet()) {
                        UserStateId.Builder builder = UserStateId.newBuilder();
                        builder.setTransformId(parDoPTransformId);
                        builder.setLocalName(entry.getKey());
                        userStateIds.add(builder.build());
                    }
                    // To facilitate the creation of Set executableStageSideInputs.
                    for (String sideInputTag : parDoPayload.getSideInputsMap().keySet()) {
                        String sideInputPCollectionId = parDoPTransform.getInputsOrThrow(sideInputTag);
                        RunnerApi.PCollection sideInputPCollection = pipeline.getComponents().getPcollectionsOrThrow(sideInputPCollectionId);
                        pTransform.putInputs(sideInputTag, sideInputPCollectionId);
                        PCollectionNode pCollectionNode = PipelineNode.pCollection(sideInputPCollectionId, sideInputPCollection);
                        sideInputIds.put(sideInputTag, pCollectionNode);
                    }
                    // To facilitate the creation of Map(ptransformId -> pCollectionView), which is
                    // required by constructing an ExecutableStageNode.
                    ImmutableList.Builder<PCollectionView<?>> pcollectionViews = ImmutableList.builder();
                    for (Map.Entry<String, RunnerApi.SideInput> sideInputEntry : parDoPayload.getSideInputsMap().entrySet()) {
                        pcollectionViews.add(RegisterNodeFunction.transformSideInputForRunner(pipeline, parDoPTransform, sideInputEntry.getKey(), sideInputEntry.getValue()));
                    }
                    ptransformIdToPCollectionViews.put(ptransformId, pcollectionViews.build());
                    transformSpec.setUrn(PTransformTranslation.PAR_DO_TRANSFORM_URN).setPayload(parDoPayload.toByteString());
                } else {
                    // legacy path - bytes are the FunctionSpec's payload field, basically, and
                    // SDKs expect it in the PTransform's payload field
                    byte[] userFnBytes = getBytes(userFnSpec, PropertyNames.SERIALIZED_FN);
                    transformSpec.setUrn(ParDoTranslation.CUSTOM_JAVA_DO_FN_URN).setPayload(ByteString.copyFrom(userFnBytes));
                }
                if (parDoInstruction.getSideInputs() != null) {
                    ptransformIdToSideInputInfos.put(ptransformId, forSideInputInfos(parDoInstruction.getSideInputs(), true));
                }
            }
        } else if (parallelInstruction.getRead() != null) {
            ReadInstruction readInstruction = parallelInstruction.getRead();
            CloudObject sourceSpec = CloudObject.fromSpec(CloudSourceUtils.flattenBaseSpecs(readInstruction.getSource()).getSpec());
            // TODO: Need to plumb through the SDK specific function spec.
            transformSpec.setUrn(JAVA_SOURCE_URN);
            try {
                byte[] serializedSource = Base64.getDecoder().decode(getString(sourceSpec, SERIALIZED_SOURCE));
                ByteString sourceByteString = ByteString.copyFrom(serializedSource);
                transformSpec.setPayload(sourceByteString);
            } catch (Exception e) {
                throw new IllegalArgumentException(String.format("Unable to process Read %s", parallelInstruction), e);
            }
        } else if (parallelInstruction.getFlatten() != null) {
            transformSpec.setUrn(PTransformTranslation.FLATTEN_TRANSFORM_URN);
        } else {
            throw new IllegalArgumentException(String.format("Unknown type of ParallelInstruction %s", parallelInstruction));
        }
        // predecessor in a ParDo. This PCollection is called the "main input".
        for (Node predecessorOutput : input.predecessors(node)) {
            pTransform.putInputs("generatedInput" + idGenerator.getId(), nodesToPCollections.get(predecessorOutput));
        }
        for (Edge edge : input.outEdges(node)) {
            Node nodeOutput = input.incidentNodes(edge).target();
            MultiOutputInfoEdge edge2 = (MultiOutputInfoEdge) edge;
            pTransform.putOutputs(edge2.getMultiOutputInfo().getTag(), nodesToPCollections.get(nodeOutput));
        }
        pTransform.setSpec(transformSpec);
        PTransformNode pTransformNode = PipelineNode.pTransform(ptransformId, pTransform.build());
        executableStageTransforms.add(pTransformNode);
        for (String timerId : timerIds) {
            executableStageTimers.add(TimerReference.of(pTransformNode, timerId));
        }
        ImmutableMap<String, PCollectionNode> sideInputIdToPCollectionNodes = sideInputIds.build();
        for (String sideInputTag : sideInputIdToPCollectionNodes.keySet()) {
            SideInputReference sideInputReference = SideInputReference.of(pTransformNode, sideInputTag, sideInputIdToPCollectionNodes.get(sideInputTag));
            executableStageSideInputs.add(sideInputReference);
        }
        executableStageTransforms.add(pTransformNode);
    }
    if (executableStageInputs.size() != 1) {
        throw new UnsupportedOperationException("ExecutableStage only support one input PCollection");
    }
    PCollectionNode executableInput = executableStageInputs.iterator().next();
    RunnerApi.Components executableStageComponents = componentsBuilder.build();
    // Get Environment from ptransform, otherwise, use JAVA_SDK_HARNESS_ENVIRONMENT as default.
    Environment executableStageEnv = getEnvironmentFromPTransform(executableStageComponents, executableStageTransforms);
    if (executableStageEnv == null) {
        executableStageEnv = Environments.JAVA_SDK_HARNESS_ENVIRONMENT;
    }
    Set<UserStateReference> executableStageUserStateReference = new HashSet<>();
    for (UserStateId userStateId : userStateIds) {
        executableStageUserStateReference.add(UserStateReference.fromUserStateId(userStateId, executableStageComponents));
    }
    ExecutableStage executableStage = ImmutableExecutableStage.ofFullComponents(executableStageComponents, executableStageEnv, executableInput, executableStageSideInputs, executableStageUserStateReference, executableStageTimers, executableStageTransforms, executableStageOutputs, DEFAULT_WIRE_CODER_SETTINGS);
    return ExecutableStageNode.create(executableStage, ptransformIdToNameContexts.build(), ptransformIdToSideInputInfos.build(), ptransformIdToPCollectionViews.build());
}
Also used : HashMap(java.util.HashMap) MultiOutputInfo(com.google.api.services.dataflow.model.MultiOutputInfo) ByteString(org.apache.beam.vendor.grpc.v1p43p2.com.google.protobuf.ByteString) PCollectionNode(org.apache.beam.runners.core.construction.graph.PipelineNode.PCollectionNode) InstructionOutputNode(org.apache.beam.runners.dataflow.worker.graph.Nodes.InstructionOutputNode) PTransformNode(org.apache.beam.runners.core.construction.graph.PipelineNode.PTransformNode) ParallelInstructionNode(org.apache.beam.runners.dataflow.worker.graph.Nodes.ParallelInstructionNode) Node(org.apache.beam.runners.dataflow.worker.graph.Nodes.Node) ExecutableStageNode(org.apache.beam.runners.dataflow.worker.graph.Nodes.ExecutableStageNode) PipelineNode(org.apache.beam.runners.core.construction.graph.PipelineNode) RemoteGrpcPortNode(org.apache.beam.runners.dataflow.worker.graph.Nodes.RemoteGrpcPortNode) InstructionOutput(com.google.api.services.dataflow.model.InstructionOutput) PTransformNode(org.apache.beam.runners.core.construction.graph.PipelineNode.PTransformNode) ArrayList(java.util.ArrayList) Structs.getString(org.apache.beam.runners.dataflow.util.Structs.getString) ByteString(org.apache.beam.vendor.grpc.v1p43p2.com.google.protobuf.ByteString) RehydratedComponents(org.apache.beam.runners.core.construction.RehydratedComponents) SdkComponents(org.apache.beam.runners.core.construction.SdkComponents) RunnerApi(org.apache.beam.model.pipeline.v1.RunnerApi) SideInputReference(org.apache.beam.runners.core.construction.graph.SideInputReference) ImmutableExecutableStage(org.apache.beam.runners.core.construction.graph.ImmutableExecutableStage) ExecutableStage(org.apache.beam.runners.core.construction.graph.ExecutableStage) HashSet(java.util.HashSet) DefaultEdge(org.apache.beam.runners.dataflow.worker.graph.Edges.DefaultEdge) MultiOutputInfoEdge(org.apache.beam.runners.dataflow.worker.graph.Edges.MultiOutputInfoEdge) ImmutableMap(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableMap) ParDoInstruction(com.google.api.services.dataflow.model.ParDoInstruction) PCollectionView(org.apache.beam.sdk.values.PCollectionView) Environment(org.apache.beam.model.pipeline.v1.RunnerApi.Environment) GlobalWindow(org.apache.beam.sdk.transforms.windowing.GlobalWindow) ImmutableMap(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableMap) Map(java.util.Map) HashMap(java.util.HashMap) IntervalWindowCoder(org.apache.beam.sdk.transforms.windowing.IntervalWindow.IntervalWindowCoder) RemoteGrpcPortNode(org.apache.beam.runners.dataflow.worker.graph.Nodes.RemoteGrpcPortNode) TimerReference(org.apache.beam.runners.core.construction.graph.TimerReference) ImmutableList(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableList) ParallelInstructionNode(org.apache.beam.runners.dataflow.worker.graph.Nodes.ParallelInstructionNode) SdkComponents(org.apache.beam.runners.core.construction.SdkComponents) ReadInstruction(com.google.api.services.dataflow.model.ReadInstruction) InstructionOutputNode(org.apache.beam.runners.dataflow.worker.graph.Nodes.InstructionOutputNode) FullWindowedValueCoder(org.apache.beam.sdk.util.WindowedValue.FullWindowedValueCoder) NameContext(org.apache.beam.runners.dataflow.worker.counters.NameContext) InvalidProtocolBufferException(org.apache.beam.vendor.grpc.v1p43p2.com.google.protobuf.InvalidProtocolBufferException) IOException(java.io.IOException) PCollectionNode(org.apache.beam.runners.core.construction.graph.PipelineNode.PCollectionNode) InvalidProtocolBufferException(org.apache.beam.vendor.grpc.v1p43p2.com.google.protobuf.InvalidProtocolBufferException) IOException(java.io.IOException) ParallelInstruction(com.google.api.services.dataflow.model.ParallelInstruction) WindowedValueCoder(org.apache.beam.sdk.util.WindowedValue.WindowedValueCoder) FullWindowedValueCoder(org.apache.beam.sdk.util.WindowedValue.FullWindowedValueCoder) CloudObject(org.apache.beam.runners.dataflow.util.CloudObject) UserStateId(org.apache.beam.model.pipeline.v1.RunnerApi.ExecutableStagePayload.UserStateId) UserStateReference(org.apache.beam.runners.core.construction.graph.UserStateReference) Edge(org.apache.beam.runners.dataflow.worker.graph.Edges.Edge) MultiOutputInfoEdge(org.apache.beam.runners.dataflow.worker.graph.Edges.MultiOutputInfoEdge) DefaultEdge(org.apache.beam.runners.dataflow.worker.graph.Edges.DefaultEdge)

Example 14 with ImmutableMap

use of org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableMap in project beam by apache.

the class DirectRunnerTest method byteArrayCountShouldSucceed.

@Test
public void byteArrayCountShouldSucceed() {
    Pipeline p = getPipeline();
    SerializableFunction<Integer, byte[]> getBytes = input -> {
        try {
            return CoderUtils.encodeToByteArray(VarIntCoder.of(), input);
        } catch (CoderException e) {
            fail("Unexpected Coder Exception " + e);
            throw new AssertionError("Unreachable");
        }
    };
    TypeDescriptor<byte[]> td = new TypeDescriptor<byte[]>() {
    };
    PCollection<byte[]> foos = p.apply(Create.of(1, 1, 1, 2, 2, 3)).apply(MapElements.into(td).via(getBytes));
    PCollection<byte[]> msync = p.apply(Create.of(1, -2, -8, -16)).apply(MapElements.into(td).via(getBytes));
    PCollection<byte[]> bytes = PCollectionList.of(foos).and(msync).apply(Flatten.pCollections());
    PCollection<KV<byte[], Long>> counts = bytes.apply(Count.perElement());
    PCollection<KV<Integer, Long>> countsBackToString = counts.apply(MapElements.via(new SimpleFunction<KV<byte[], Long>, KV<Integer, Long>>() {

        @Override
        public KV<Integer, Long> apply(KV<byte[], Long> input) {
            try {
                return KV.of(CoderUtils.decodeFromByteArray(VarIntCoder.of(), input.getKey()), input.getValue());
            } catch (CoderException e) {
                fail("Unexpected Coder Exception " + e);
                throw new AssertionError("Unreachable");
            }
        }
    }));
    Map<Integer, Long> expected = ImmutableMap.<Integer, Long>builder().put(1, 4L).put(2, 2L).put(3, 1L).put(-2, 1L).put(-8, 1L).put(-16, 1L).build();
    PAssert.thatMap(countsBackToString).isEqualTo(expected);
}
Also used : Count(org.apache.beam.sdk.transforms.Count) Arrays(java.util.Arrays) SerializableCoder(org.apache.beam.sdk.coders.SerializableCoder) PBegin(org.apache.beam.sdk.values.PBegin) Matchers.isA(org.hamcrest.Matchers.isA) CoderUtils(org.apache.beam.sdk.util.CoderUtils) PipelineResult(org.apache.beam.sdk.PipelineResult) UnboundedSource(org.apache.beam.sdk.io.UnboundedSource) ListCoder(org.apache.beam.sdk.coders.ListCoder) SerializableFunction(org.apache.beam.sdk.transforms.SerializableFunction) ImmutableMap(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableMap) SimpleFunction(org.apache.beam.sdk.transforms.SimpleFunction) ThrowableMessageMatcher(org.junit.internal.matchers.ThrowableMessageMatcher) Future(java.util.concurrent.Future) DirectPipelineResult(org.apache.beam.runners.direct.DirectRunner.DirectPipelineResult) PCollectionList(org.apache.beam.sdk.values.PCollectionList) AtomicInteger(java.util.concurrent.atomic.AtomicInteger) Create(org.apache.beam.sdk.transforms.Create) Map(java.util.Map) Window(org.apache.beam.sdk.transforms.windowing.Window) Assert.fail(org.junit.Assert.fail) Flatten(org.apache.beam.sdk.transforms.Flatten) MapElements(org.apache.beam.sdk.transforms.MapElements) ConcurrentHashMap(java.util.concurrent.ConcurrentHashMap) Sum(org.apache.beam.sdk.transforms.Sum) BlockingQueue(java.util.concurrent.BlockingQueue) GenerateSequence(org.apache.beam.sdk.io.GenerateSequence) VarLongCoder(org.apache.beam.sdk.coders.VarLongCoder) Executors(java.util.concurrent.Executors) Serializable(java.io.Serializable) ArrayBlockingQueue(java.util.concurrent.ArrayBlockingQueue) CoderException(org.apache.beam.sdk.coders.CoderException) List(java.util.List) ParDo(org.apache.beam.sdk.transforms.ParDo) Matchers.equalTo(org.hamcrest.Matchers.equalTo) TypeDescriptors(org.apache.beam.sdk.values.TypeDescriptors) Optional(java.util.Optional) State(org.apache.beam.sdk.PipelineResult.State) Matchers.greaterThan(org.hamcrest.Matchers.greaterThan) Matchers.is(org.hamcrest.Matchers.is) GlobalWindows(org.apache.beam.sdk.transforms.windowing.GlobalWindows) KV(org.apache.beam.sdk.values.KV) TypeDescriptor(org.apache.beam.sdk.values.TypeDescriptor) AfterWatermark(org.apache.beam.sdk.transforms.windowing.AfterWatermark) Default(org.apache.beam.sdk.options.Default) Duration(org.joda.time.Duration) RunWith(org.junit.runner.RunWith) Coder(org.apache.beam.sdk.coders.Coder) Callable(java.util.concurrent.Callable) PipelineOptionsFactory(org.apache.beam.sdk.options.PipelineOptionsFactory) PTransform(org.apache.beam.sdk.transforms.PTransform) Read(org.apache.beam.sdk.io.Read) PipelineRunner(org.apache.beam.sdk.PipelineRunner) TestPipeline(org.apache.beam.sdk.testing.TestPipeline) JsonIgnore(com.fasterxml.jackson.annotation.JsonIgnore) MatcherAssert.assertThat(org.hamcrest.MatcherAssert.assertThat) Pipeline(org.apache.beam.sdk.Pipeline) NoSuchElementException(java.util.NoSuchElementException) PipelineOptions(org.apache.beam.sdk.options.PipelineOptions) ExpectedException(org.junit.rules.ExpectedException) ExecutorService(java.util.concurrent.ExecutorService) Nullable(org.checkerframework.checker.nullness.qual.Nullable) OutputStream(java.io.OutputStream) DoFn(org.apache.beam.sdk.transforms.DoFn) DisplayData(org.apache.beam.sdk.transforms.display.DisplayData) CountingSource(org.apache.beam.sdk.io.CountingSource) PDone(org.apache.beam.sdk.values.PDone) PAssert(org.apache.beam.sdk.testing.PAssert) IllegalMutationException(org.apache.beam.sdk.util.IllegalMutationException) Matchers(org.hamcrest.Matchers) IOException(java.io.IOException) Test(org.junit.Test) JUnit4(org.junit.runners.JUnit4) PCollection(org.apache.beam.sdk.values.PCollection) AtomicLong(java.util.concurrent.atomic.AtomicLong) BoundedSource(org.apache.beam.sdk.io.BoundedSource) Rule(org.junit.Rule) Preconditions.checkState(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.base.Preconditions.checkState) BoundedWindow(org.apache.beam.sdk.transforms.windowing.BoundedWindow) Preconditions(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.base.Preconditions) Instant(org.joda.time.Instant) AtomicCoder(org.apache.beam.sdk.coders.AtomicCoder) VarIntCoder(org.apache.beam.sdk.coders.VarIntCoder) Assert.assertEquals(org.junit.Assert.assertEquals) InputStream(java.io.InputStream) KV(org.apache.beam.sdk.values.KV) TestPipeline(org.apache.beam.sdk.testing.TestPipeline) Pipeline(org.apache.beam.sdk.Pipeline) AtomicInteger(java.util.concurrent.atomic.AtomicInteger) TypeDescriptor(org.apache.beam.sdk.values.TypeDescriptor) SimpleFunction(org.apache.beam.sdk.transforms.SimpleFunction) AtomicLong(java.util.concurrent.atomic.AtomicLong) CoderException(org.apache.beam.sdk.coders.CoderException) Test(org.junit.Test)

Example 15 with ImmutableMap

use of org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableMap in project beam by apache.

the class BeamFnMapTaskExecutorFactory method createOperationTransformForRegisterFnNodes.

private Function<Node, Node> createOperationTransformForRegisterFnNodes(final IdGenerator idGenerator, final InstructionRequestHandler instructionRequestHandler, final StateDelegator beamFnStateDelegator, final String stageName, final DataflowExecutionContext<?> executionContext) {
    return new TypeSafeNodeFunction<RegisterRequestNode>(RegisterRequestNode.class) {

        @Override
        public Node typedApply(RegisterRequestNode input) {
            ImmutableMap.Builder<String, DataflowOperationContext> ptransformIdToOperationContextBuilder = ImmutableMap.builder();
            ImmutableMap.Builder<String, DataflowStepContext> ptransformIdToStepContext = ImmutableMap.builder();
            for (Map.Entry<String, NameContext> entry : input.getPTransformIdToPartialNameContextMap().entrySet()) {
                NameContext fullNameContext = NameContext.create(stageName, entry.getValue().originalName(), entry.getValue().systemName(), entry.getValue().userName());
                DataflowOperationContext operationContext = executionContext.createOperationContext(fullNameContext);
                ptransformIdToOperationContextBuilder.put(entry.getKey(), operationContext);
                ptransformIdToStepContext.put(entry.getKey(), executionContext.getStepContext(operationContext));
            }
            ImmutableMap.Builder<String, NameContext> pcollectionIdToNameContext = ImmutableMap.builder();
            for (Map.Entry<String, NameContext> entry : input.getPCollectionToPartialNameContextMap().entrySet()) {
                pcollectionIdToNameContext.put(entry.getKey(), NameContext.create(stageName, entry.getValue().originalName(), entry.getValue().systemName(), entry.getValue().userName()));
            }
            ImmutableMap<String, DataflowOperationContext> ptransformIdToOperationContexts = ptransformIdToOperationContextBuilder.build();
            ImmutableMap<String, SideInputReader> ptransformIdToSideInputReaders = buildPTransformIdToSideInputReadersMap(executionContext, input, ptransformIdToOperationContexts);
            ImmutableTable<String, String, PCollectionView<?>> ptransformIdToSideInputIdToPCollectionView = buildPTransformIdToSideInputIdToPCollectionView(input);
            return OperationNode.create(new RegisterAndProcessBundleOperation(idGenerator, instructionRequestHandler, beamFnStateDelegator, input.getRegisterRequest(), ptransformIdToOperationContexts, ptransformIdToStepContext.build(), ptransformIdToSideInputReaders, ptransformIdToSideInputIdToPCollectionView, pcollectionIdToNameContext.build(), // TODO: Set NameContext properly for these operations.
            executionContext.createOperationContext(NameContext.create(stageName, stageName, stageName, stageName))));
        }
    };
}
Also used : NameContext(org.apache.beam.runners.dataflow.worker.counters.NameContext) SideInputReader(org.apache.beam.runners.core.SideInputReader) DataflowStepContext(org.apache.beam.runners.dataflow.worker.DataflowExecutionContext.DataflowStepContext) RegisterAndProcessBundleOperation(org.apache.beam.runners.dataflow.worker.fn.control.RegisterAndProcessBundleOperation) ImmutableMap(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableMap) RegisterRequestNode(org.apache.beam.runners.dataflow.worker.graph.Nodes.RegisterRequestNode) PCollectionView(org.apache.beam.sdk.values.PCollectionView) TypeSafeNodeFunction(org.apache.beam.runners.dataflow.worker.graph.Networks.TypeSafeNodeFunction) ImmutableMap(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableMap) Map(java.util.Map) HashMap(java.util.HashMap)

Aggregations

ImmutableMap (org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableMap)19 HashMap (java.util.HashMap)14 Map (java.util.Map)14 Test (org.junit.Test)13 ArrayList (java.util.ArrayList)10 BoundedWindow (org.apache.beam.sdk.transforms.windowing.BoundedWindow)10 WindowedValue (org.apache.beam.sdk.util.WindowedValue)10 Callable (java.util.concurrent.Callable)8 Future (java.util.concurrent.Future)8 Source (com.google.api.services.dataflow.model.Source)7 SortedMap (java.util.SortedMap)7 TreeMap (java.util.TreeMap)7 KV (org.apache.beam.sdk.values.KV)6 List (java.util.List)5 Structs.getString (org.apache.beam.runners.dataflow.util.Structs.getString)5 ImmutableList (org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableList)5 Arrays (java.util.Arrays)4 Collection (java.util.Collection)4 RunnerApi (org.apache.beam.model.pipeline.v1.RunnerApi)4 Coder (org.apache.beam.sdk.coders.Coder)4