Search in sources :

Example 1 with ImmutableMap

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

the class ExternalSchemaIOTransformRegistrar method knownBuilderInstances.

@Override
public Map<String, ExternalTransformBuilder<?, ?, ?>> knownBuilderInstances() {
    ImmutableMap.Builder builder = ImmutableMap.<String, ExternalTransformRegistrar>builder();
    try {
        for (SchemaIOProvider schemaIOProvider : ServiceLoader.load(SchemaIOProvider.class)) {
            builder.put("beam:transform:org.apache.beam:schemaio_" + schemaIOProvider.identifier() + "_read:v1", new ReaderBuilder(schemaIOProvider));
            builder.put("beam:transform:org.apache.beam:schemaio_" + schemaIOProvider.identifier() + "_write:v1", new WriterBuilder(schemaIOProvider));
        }
    } catch (Exception e) {
        throw new RuntimeException(e.getMessage());
    }
    return builder.build();
}
Also used : ExternalTransformRegistrar(org.apache.beam.sdk.expansion.ExternalTransformRegistrar) SchemaIOProvider(org.apache.beam.sdk.schemas.io.SchemaIOProvider) ImmutableMap(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableMap) IOException(java.io.IOException) InvalidProtocolBufferException(org.apache.beam.vendor.grpc.v1p43p2.com.google.protobuf.InvalidProtocolBufferException)

Example 2 with ImmutableMap

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

the class FlinkExecutableStageFunctionTest method setUpMocks.

@Before
public void setUpMocks() throws Exception {
    MockitoAnnotations.initMocks(this);
    when(runtimeContext.getDistributedCache()).thenReturn(distributedCache);
    when(stageContext.getStageBundleFactory(any())).thenReturn(stageBundleFactory);
    RemoteBundle remoteBundle = Mockito.mock(RemoteBundle.class);
    when(stageBundleFactory.getBundle(any(), any(StateRequestHandler.class), any(BundleProgressHandler.class), any(BundleFinalizationHandler.class), any(BundleCheckpointHandler.class))).thenReturn(remoteBundle);
    when(stageBundleFactory.getBundle(any(), any(TimerReceiverFactory.class), any(StateRequestHandler.class), any(BundleProgressHandler.class))).thenReturn(remoteBundle);
    ImmutableMap input = ImmutableMap.builder().put("input", Mockito.mock(FnDataReceiver.class)).build();
    when(remoteBundle.getInputReceivers()).thenReturn(input);
    when(processBundleDescriptor.getTimerSpecs()).thenReturn(Collections.emptyMap());
}
Also used : StateRequestHandler(org.apache.beam.runners.fnexecution.state.StateRequestHandler) BundleFinalizationHandler(org.apache.beam.runners.fnexecution.control.BundleFinalizationHandler) TimerReceiverFactory(org.apache.beam.runners.fnexecution.control.TimerReceiverFactory) RemoteBundle(org.apache.beam.runners.fnexecution.control.RemoteBundle) BundleProgressHandler(org.apache.beam.runners.fnexecution.control.BundleProgressHandler) BundleCheckpointHandler(org.apache.beam.runners.fnexecution.control.BundleCheckpointHandler) ImmutableMap(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableMap) Before(org.junit.Before)

Example 3 with ImmutableMap

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

the class ExecutableStageDoFnOperatorTest method testWatermarkHandling.

@Test
public void testWatermarkHandling() throws Exception {
    TupleTag<Integer> mainOutput = new TupleTag<>("main-output");
    DoFnOperator.MultiOutputOutputManagerFactory<Integer> outputManagerFactory = new DoFnOperator.MultiOutputOutputManagerFactory(mainOutput, VoidCoder.of(), new SerializablePipelineOptions(FlinkPipelineOptions.defaults()));
    ExecutableStageDoFnOperator<KV<String, Integer>, Integer> operator = getOperator(mainOutput, Collections.emptyList(), outputManagerFactory, WindowingStrategy.of(FixedWindows.of(Duration.millis(10))), StringUtf8Coder.of(), WindowedValue.getFullCoder(KvCoder.of(StringUtf8Coder.of(), VarIntCoder.of()), IntervalWindow.getCoder()));
    KeyedOneInputStreamOperatorTestHarness<String, WindowedValue<KV<String, Integer>>, WindowedValue<Integer>> testHarness = new KeyedOneInputStreamOperatorTestHarness<>(operator, val -> val.getValue().getKey(), new CoderTypeInformation<>(StringUtf8Coder.of(), FlinkPipelineOptions.defaults()));
    RemoteBundle bundle = Mockito.mock(RemoteBundle.class);
    when(bundle.getInputReceivers()).thenReturn(ImmutableMap.<String, FnDataReceiver<WindowedValue>>builder().put("input", Mockito.mock(FnDataReceiver.class)).build());
    when(bundle.getTimerReceivers()).thenReturn(ImmutableMap.<KV<String, String>, FnDataReceiver<WindowedValue>>builder().put(KV.of("transform", "timer"), Mockito.mock(FnDataReceiver.class)).put(KV.of("transform", "timer2"), Mockito.mock(FnDataReceiver.class)).put(KV.of("transform", "timer3"), Mockito.mock(FnDataReceiver.class)).build());
    when(stageBundleFactory.getBundle(any(), any(), any(), any(), any(), any())).thenReturn(bundle);
    testHarness.open();
    assertThat(operator.getCurrentOutputWatermark(), is(BoundedWindow.TIMESTAMP_MIN_VALUE.getMillis()));
    // No bundle has been started, watermark can be freely advanced
    testHarness.processWatermark(0);
    assertThat(operator.getCurrentOutputWatermark(), is(0L));
    // Trigger a new bundle
    IntervalWindow intervalWindow = new IntervalWindow(new Instant(0), new Instant(9));
    WindowedValue<KV<String, Integer>> windowedValue = WindowedValue.of(KV.of("one", 1), Instant.now(), intervalWindow, PaneInfo.NO_FIRING);
    testHarness.processElement(new StreamRecord<>(windowedValue));
    // The output watermark should be held back during the bundle
    testHarness.processWatermark(1);
    assertThat(operator.getEffectiveInputWatermark(), is(1L));
    assertThat(operator.getCurrentOutputWatermark(), is(0L));
    // After the bundle has been finished, the watermark should be advanced
    operator.invokeFinishBundle();
    assertThat(operator.getCurrentOutputWatermark(), is(1L));
    // Bundle finished, watermark can be freely advanced
    testHarness.processWatermark(2);
    assertThat(operator.getEffectiveInputWatermark(), is(2L));
    assertThat(operator.getCurrentOutputWatermark(), is(2L));
    // Trigger a new bundle
    testHarness.processElement(new StreamRecord<>(windowedValue));
    // cleanup timer
    assertThat(testHarness.numEventTimeTimers(), is(1));
    // Set at timer
    Instant timerTarget = new Instant(5);
    Instant timerTarget2 = new Instant(6);
    operator.getLockToAcquireForStateAccessDuringBundles().lock();
    BiConsumer<String, Instant> timerConsumer = (timerId, timestamp) -> operator.setTimer(Timer.of(windowedValue.getValue().getKey(), "", windowedValue.getWindows(), timestamp, timestamp, PaneInfo.NO_FIRING), TimerInternals.TimerData.of("", TimerReceiverFactory.encodeToTimerDataTimerId("transform", timerId), StateNamespaces.window(IntervalWindow.getCoder(), intervalWindow), timestamp, timestamp, TimeDomain.EVENT_TIME));
    timerConsumer.accept("timer", timerTarget);
    timerConsumer.accept("timer2", timerTarget2);
    assertThat(testHarness.numEventTimeTimers(), is(3));
    // Advance input watermark past the timer
    // Check the output watermark is held back
    long targetWatermark = timerTarget.getMillis() + 100;
    testHarness.processWatermark(targetWatermark);
    // Do not yet advance the output watermark because we are still processing a bundle
    assertThat(testHarness.numEventTimeTimers(), is(3));
    assertThat(operator.getCurrentOutputWatermark(), is(2L));
    // Check that the timers are fired but the output watermark is advanced no further than
    // the minimum timer timestamp of the previous bundle because we are still processing a
    // bundle which might contain more timers.
    // Timers can create loops if they keep rescheduling themselves when firing
    // Thus, we advance the watermark asynchronously to allow for checkpointing to run
    operator.invokeFinishBundle();
    assertThat(testHarness.numEventTimeTimers(), is(3));
    testHarness.setProcessingTime(testHarness.getProcessingTime() + 1);
    assertThat(testHarness.numEventTimeTimers(), is(0));
    assertThat(operator.getCurrentOutputWatermark(), is(5L));
    // Output watermark is advanced synchronously when the bundle finishes,
    // no more timers are scheduled
    operator.invokeFinishBundle();
    assertThat(operator.getCurrentOutputWatermark(), is(targetWatermark));
    assertThat(testHarness.numEventTimeTimers(), is(0));
    // Watermark is advanced in a blocking fashion on close, not via a timers
    // Create a bundle with a pending timer to simulate that
    testHarness.processElement(new StreamRecord<>(windowedValue));
    timerConsumer.accept("timer3", new Instant(targetWatermark));
    assertThat(testHarness.numEventTimeTimers(), is(1));
    // This should be blocking until the watermark reaches Long.MAX_VALUE.
    testHarness.close();
    assertThat(testHarness.numEventTimeTimers(), is(0));
    assertThat(operator.getCurrentOutputWatermark(), is(Long.MAX_VALUE));
}
Also used : Arrays(java.util.Arrays) RuntimeContext(org.apache.flink.api.common.functions.RuntimeContext) InMemoryStateInternals(org.apache.beam.runners.core.InMemoryStateInternals) FlinkExecutableStageContextFactory(org.apache.beam.runners.flink.translation.functions.FlinkExecutableStageContextFactory) CoderUtils(org.apache.beam.sdk.util.CoderUtils) 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) OneInputStreamOperatorTestHarness(org.apache.flink.streaming.util.OneInputStreamOperatorTestHarness) Mockito.doThrow(org.mockito.Mockito.doThrow) MockitoAnnotations(org.mockito.MockitoAnnotations) Mockito.doAnswer(org.mockito.Mockito.doAnswer) Map(java.util.Map) GlobalWindow(org.apache.beam.sdk.transforms.windowing.GlobalWindow) Components(org.apache.beam.model.pipeline.v1.RunnerApi.Components) CoderTypeInformation(org.apache.beam.runners.flink.translation.types.CoderTypeInformation) KvCoder(org.apache.beam.sdk.coders.KvCoder) StageBundleFactory(org.apache.beam.runners.fnexecution.control.StageBundleFactory) PAR_DO_TRANSFORM_URN(org.apache.beam.runners.core.construction.PTransformTranslation.PAR_DO_TRANSFORM_URN) FnDataReceiver(org.apache.beam.sdk.fn.data.FnDataReceiver) BundleProgressHandler(org.apache.beam.runners.fnexecution.control.BundleProgressHandler) SerializationUtils(org.apache.beam.repackaged.core.org.apache.commons.lang3.SerializationUtils) Struct(org.apache.beam.vendor.grpc.v1p43p2.com.google.protobuf.Struct) OutputTag(org.apache.flink.util.OutputTag) BeamFnApi(org.apache.beam.model.fnexecution.v1.BeamFnApi) StandardCharsets(java.nio.charset.StandardCharsets) Matchers.instanceOf(org.hamcrest.Matchers.instanceOf) Matchers.any(org.mockito.Matchers.any) Matchers.is(org.hamcrest.Matchers.is) StatefulDoFnRunner(org.apache.beam.runners.core.StatefulDoFnRunner) KV(org.apache.beam.sdk.values.KV) Mock(org.mockito.Mock) Duration(org.joda.time.Duration) RunWith(org.junit.runner.RunWith) ExecutableStagePayload(org.apache.beam.model.pipeline.v1.RunnerApi.ExecutableStagePayload) StateTags(org.apache.beam.runners.core.StateTags) PCollection(org.apache.beam.model.pipeline.v1.RunnerApi.PCollection) TupleTag(org.apache.beam.sdk.values.TupleTag) BiConsumer(java.util.function.BiConsumer) Matchers.hasSize(org.hamcrest.Matchers.hasSize) MatcherAssert.assertThat(org.hamcrest.MatcherAssert.assertThat) StateRequestHandler(org.apache.beam.runners.fnexecution.state.StateRequestHandler) Before(org.junit.Before) RunnerApi(org.apache.beam.model.pipeline.v1.RunnerApi) OutputReceiverFactory(org.apache.beam.runners.fnexecution.control.OutputReceiverFactory) StateRequestHandlers(org.apache.beam.runners.fnexecution.state.StateRequestHandlers) Test(org.junit.Test) BundleCheckpointHandler(org.apache.beam.runners.fnexecution.control.BundleCheckpointHandler) Assert.assertNotEquals(org.junit.Assert.assertNotEquals) NoopLock(org.apache.beam.sdk.util.NoopLock) Lock(java.util.concurrent.locks.Lock) InMemoryTimerInternals(org.apache.beam.runners.core.InMemoryTimerInternals) Timer(org.apache.beam.runners.core.construction.Timer) BoundedWindow(org.apache.beam.sdk.transforms.windowing.BoundedWindow) VarIntCoder(org.apache.beam.sdk.coders.VarIntCoder) VoidCoder(org.apache.beam.sdk.coders.VoidCoder) IntervalWindow(org.apache.beam.sdk.transforms.windowing.IntervalWindow) TimeDomain(org.apache.beam.sdk.state.TimeDomain) Assert.assertEquals(org.junit.Assert.assertEquals) ArgumentMatchers.anyString(org.mockito.ArgumentMatchers.anyString) StateNamespace(org.apache.beam.runners.core.StateNamespace) SerializablePipelineOptions(org.apache.beam.runners.core.construction.SerializablePipelineOptions) 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) ByteBuffer(java.nio.ByteBuffer) Mockito.verifyNoMoreInteractions(org.mockito.Mockito.verifyNoMoreInteractions) Iterables(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.Iterables) BundleFinalizationHandler(org.apache.beam.runners.fnexecution.control.BundleFinalizationHandler) JobInfo(org.apache.beam.runners.fnexecution.provisioning.JobInfo) TypeInformation(org.apache.flink.api.common.typeinfo.TypeInformation) TimerReceiverFactory(org.apache.beam.runners.fnexecution.control.TimerReceiverFactory) PaneInfo(org.apache.beam.sdk.transforms.windowing.PaneInfo) Collection(java.util.Collection) DistributedCache(org.apache.flink.api.common.cache.DistributedCache) List(java.util.List) InstructionRequestHandler(org.apache.beam.runners.fnexecution.control.InstructionRequestHandler) ImmutableList(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableList) WindowingStrategy(org.apache.beam.sdk.values.WindowingStrategy) Whitebox(org.powermock.reflect.Whitebox) AtomicBoolean(java.util.concurrent.atomic.AtomicBoolean) Coder(org.apache.beam.sdk.coders.Coder) Watermark(org.apache.flink.streaming.api.watermark.Watermark) HashMap(java.util.HashMap) MutableObject(org.apache.beam.repackaged.core.org.apache.commons.lang3.mutable.MutableObject) StateNamespaces(org.apache.beam.runners.core.StateNamespaces) StringUtf8Coder(org.apache.beam.sdk.coders.StringUtf8Coder) RemoteBundle(org.apache.beam.runners.fnexecution.control.RemoteBundle) StreamRecord(org.apache.flink.streaming.runtime.streamrecord.StreamRecord) ByteString(org.apache.beam.vendor.grpc.v1p43p2.com.google.protobuf.ByteString) ExpectedException(org.junit.rules.ExpectedException) Nullable(org.checkerframework.checker.nullness.qual.Nullable) DoFnRunnerWithMetricsUpdate(org.apache.beam.runners.flink.metrics.DoFnRunnerWithMetricsUpdate) ProcessBundleDescriptors(org.apache.beam.runners.fnexecution.control.ProcessBundleDescriptors) ByteStringCoder(org.apache.beam.runners.fnexecution.wire.ByteStringCoder) Assert.assertNotNull(org.junit.Assert.assertNotNull) Charsets(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.base.Charsets) FixedWindows(org.apache.beam.sdk.transforms.windowing.FixedWindows) Mockito.when(org.mockito.Mockito.when) JUnit4(org.junit.runners.JUnit4) KeyedStateBackend(org.apache.flink.runtime.state.KeyedStateBackend) Mockito.verify(org.mockito.Mockito.verify) Mockito(org.mockito.Mockito) BagState(org.apache.beam.sdk.state.BagState) Rule(org.junit.Rule) Instant(org.joda.time.Instant) Collections(java.util.Collections) FlinkStateInternalsTest(org.apache.beam.runners.flink.streaming.FlinkStateInternalsTest) ExecutableStageContext(org.apache.beam.runners.fnexecution.control.ExecutableStageContext) FnDataReceiver(org.apache.beam.sdk.fn.data.FnDataReceiver) Instant(org.joda.time.Instant) TupleTag(org.apache.beam.sdk.values.TupleTag) KV(org.apache.beam.sdk.values.KV) ArgumentMatchers.anyString(org.mockito.ArgumentMatchers.anyString) ByteString(org.apache.beam.vendor.grpc.v1p43p2.com.google.protobuf.ByteString) KeyedOneInputStreamOperatorTestHarness(org.apache.flink.streaming.util.KeyedOneInputStreamOperatorTestHarness) WindowedValue(org.apache.beam.sdk.util.WindowedValue) StreamRecordStripper.stripStreamRecordFromWindowedValue(org.apache.beam.runners.flink.translation.wrappers.streaming.StreamRecordStripper.stripStreamRecordFromWindowedValue) SerializablePipelineOptions(org.apache.beam.runners.core.construction.SerializablePipelineOptions) RemoteBundle(org.apache.beam.runners.fnexecution.control.RemoteBundle) IntervalWindow(org.apache.beam.sdk.transforms.windowing.IntervalWindow) Test(org.junit.Test) FlinkStateInternalsTest(org.apache.beam.runners.flink.streaming.FlinkStateInternalsTest)

Example 4 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 keyedParDoSideInputCheckpointing.

@Test
public void keyedParDoSideInputCheckpointing() throws Exception {
    sideInputCheckpointing(() -> {
        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 5 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 createOperationTransformForExecutableStageNode.

private Function<Node, Node> createOperationTransformForExecutableStageNode(final Network<Node, Edge> network, final String stageName, final DataflowExecutionContext<?> executionContext, final JobBundleFactory jobBundleFactory) {
    return new TypeSafeNodeFunction<ExecutableStageNode>(ExecutableStageNode.class) {

        @Override
        public Node typedApply(ExecutableStageNode input) {
            StageBundleFactory stageBundleFactory = jobBundleFactory.forStage(input.getExecutableStage());
            Iterable<OutputReceiverNode> outputReceiverNodes = Iterables.filter(network.successors(input), OutputReceiverNode.class);
            Map<String, OutputReceiver> outputReceiverMap = new HashMap<>();
            Lists.newArrayList(outputReceiverNodes).stream().forEach(outputReceiverNode -> outputReceiverMap.put(outputReceiverNode.getPcollectionId(), outputReceiverNode.getOutputReceiver()));
            ImmutableMap.Builder<String, DataflowOperationContext> ptransformIdToOperationContextBuilder = 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);
            }
            ImmutableMap<String, DataflowOperationContext> ptransformIdToOperationContexts = ptransformIdToOperationContextBuilder.build();
            ImmutableMap<String, SideInputReader> ptransformIdToSideInputReaders = buildPTransformIdToSideInputReadersMap(executionContext, input, ptransformIdToOperationContexts);
            Map<RunnerApi.ExecutableStagePayload.SideInputId, PCollectionView<?>> ptransformIdToSideInputIdToPCollectionView = buildSideInputIdToPCollectionView(input);
            return OperationNode.create(new ProcessRemoteBundleOperation(input.getExecutableStage(), executionContext.createOperationContext(NameContext.create(stageName, stageName, stageName, stageName)), stageBundleFactory, outputReceiverMap, ptransformIdToSideInputReaders, ptransformIdToSideInputIdToPCollectionView));
        }
    };
}
Also used : HashMap(java.util.HashMap) NameContext(org.apache.beam.runners.dataflow.worker.counters.NameContext) ProcessRemoteBundleOperation(org.apache.beam.runners.dataflow.worker.fn.control.ProcessRemoteBundleOperation) OutputReceiver(org.apache.beam.runners.dataflow.worker.util.common.worker.OutputReceiver) SideInputReader(org.apache.beam.runners.core.SideInputReader) ImmutableMap(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableMap) OutputReceiverNode(org.apache.beam.runners.dataflow.worker.graph.Nodes.OutputReceiverNode) RunnerApi(org.apache.beam.model.pipeline.v1.RunnerApi) StageBundleFactory(org.apache.beam.runners.fnexecution.control.StageBundleFactory) PCollectionView(org.apache.beam.sdk.values.PCollectionView) TypeSafeNodeFunction(org.apache.beam.runners.dataflow.worker.graph.Networks.TypeSafeNodeFunction) ExecutableStageNode(org.apache.beam.runners.dataflow.worker.graph.Nodes.ExecutableStageNode) 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