Search in sources :

Example 86 with TupleTag

use of org.apache.beam.sdk.values.TupleTag in project beam by apache.

the class DoFnOperatorTest method testExactlyOnceBufferingKeyed.

@Test
public void testExactlyOnceBufferingKeyed() throws Exception {
    FlinkPipelineOptions options = FlinkPipelineOptions.defaults();
    options.setMaxBundleSize(2L);
    options.setCheckpointingInterval(1L);
    TupleTag<KV<String, String>> outputTag = new TupleTag<>("main-output");
    StringUtf8Coder keyCoder = StringUtf8Coder.of();
    KvToByteBufferKeySelector<String, String> keySelector = new KvToByteBufferKeySelector<>(keyCoder, new SerializablePipelineOptions(options));
    KvCoder<String, String> kvCoder = KvCoder.of(keyCoder, StringUtf8Coder.of());
    WindowedValue.ValueOnlyWindowedValueCoder<KV<String, String>> windowedValueCoder = WindowedValue.getValueOnlyCoder(kvCoder);
    DoFn<KV<String, String>, KV<String, String>> doFn = new DoFn<KV<String, String>, KV<String, String>>() {

        @StartBundle
        public void startBundle() {
            numStartBundleCalled++;
        }

        @ProcessElement
        // Use RequiresStableInput to force buffering elements
        @RequiresStableInput
        public void processElement(ProcessContext context) {
            context.output(context.element());
        }

        @FinishBundle
        public void finishBundle(FinishBundleContext context) {
            context.output(KV.of("key3", "finishBundle"), BoundedWindow.TIMESTAMP_MIN_VALUE, GlobalWindow.INSTANCE);
        }
    };
    DoFnOperator.MultiOutputOutputManagerFactory<KV<String, String>> outputManagerFactory = new DoFnOperator.MultiOutputOutputManagerFactory<>(outputTag, WindowedValue.getFullCoder(kvCoder, GlobalWindow.Coder.INSTANCE), new SerializablePipelineOptions(options));
    Supplier<DoFnOperator<KV<String, String>, KV<String, String>>> doFnOperatorSupplier = () -> new DoFnOperator<>(doFn, "stepName", windowedValueCoder, Collections.emptyMap(), outputTag, Collections.emptyList(), outputManagerFactory, WindowingStrategy.globalDefault(), new HashMap<>(), /* side-input mapping */
    Collections.emptyList(), /* side inputs */
    options, keyCoder, keySelector, DoFnSchemaInformation.create(), Collections.emptyMap());
    DoFnOperator<KV<String, String>, KV<String, String>> doFnOperator = doFnOperatorSupplier.get();
    OneInputStreamOperatorTestHarness<WindowedValue<KV<String, String>>, WindowedValue<KV<String, String>>> testHarness = new KeyedOneInputStreamOperatorTestHarness<>(doFnOperator, keySelector, keySelector.getProducedType());
    testHarness.open();
    testHarness.processElement(new StreamRecord<>(WindowedValue.valueInGlobalWindow(KV.of("key", "a"))));
    testHarness.processElement(new StreamRecord<>(WindowedValue.valueInGlobalWindow(KV.of("key", "b"))));
    testHarness.processElement(new StreamRecord<>(WindowedValue.valueInGlobalWindow(KV.of("key2", "c"))));
    testHarness.processElement(new StreamRecord<>(WindowedValue.valueInGlobalWindow(KV.of("key2", "d"))));
    assertThat(Iterables.size(testHarness.getOutput()), is(0));
    OperatorSubtaskState backup = testHarness.snapshot(0, 0);
    doFnOperator.notifyCheckpointComplete(0L);
    assertThat(numStartBundleCalled, is(1));
    assertThat(stripStreamRecordFromWindowedValue(testHarness.getOutput()), contains(WindowedValue.valueInGlobalWindow(KV.of("key", "a")), WindowedValue.valueInGlobalWindow(KV.of("key", "b")), WindowedValue.valueInGlobalWindow(KV.of("key2", "c")), WindowedValue.valueInGlobalWindow(KV.of("key2", "d")), WindowedValue.valueInGlobalWindow(KV.of("key3", "finishBundle"))));
    doFnOperator = doFnOperatorSupplier.get();
    testHarness = new KeyedOneInputStreamOperatorTestHarness<>(doFnOperator, keySelector, keySelector.getProducedType());
    // restore from the snapshot
    testHarness.initializeState(backup);
    testHarness.open();
    doFnOperator.notifyCheckpointComplete(0L);
    assertThat(numStartBundleCalled, is(2));
    assertThat(stripStreamRecordFromWindowedValue(testHarness.getOutput()), contains(WindowedValue.valueInGlobalWindow(KV.of("key", "a")), WindowedValue.valueInGlobalWindow(KV.of("key", "b")), WindowedValue.valueInGlobalWindow(KV.of("key2", "c")), WindowedValue.valueInGlobalWindow(KV.of("key2", "d")), WindowedValue.valueInGlobalWindow(KV.of("key3", "finishBundle"))));
    // repeat to see if elements are evicted
    doFnOperator.notifyCheckpointComplete(1L);
    assertThat(numStartBundleCalled, is(2));
    assertThat(stripStreamRecordFromWindowedValue(testHarness.getOutput()), contains(WindowedValue.valueInGlobalWindow(KV.of("key", "a")), WindowedValue.valueInGlobalWindow(KV.of("key", "b")), WindowedValue.valueInGlobalWindow(KV.of("key2", "c")), WindowedValue.valueInGlobalWindow(KV.of("key2", "d")), WindowedValue.valueInGlobalWindow(KV.of("key3", "finishBundle"))));
}
Also used : TupleTag(org.apache.beam.sdk.values.TupleTag) FlinkPipelineOptions(org.apache.beam.runners.flink.FlinkPipelineOptions) KeyedOneInputStreamOperatorTestHarness(org.apache.flink.streaming.util.KeyedOneInputStreamOperatorTestHarness) OperatorSubtaskState(org.apache.flink.runtime.checkpoint.OperatorSubtaskState) 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) KV(org.apache.beam.sdk.values.KV) DoFn(org.apache.beam.sdk.transforms.DoFn) Test(org.junit.Test)

Example 87 with TupleTag

use of org.apache.beam.sdk.values.TupleTag in project beam by apache.

the class DoFnOperatorTest method testStateRestore.

@Test
public void testStateRestore() throws Exception {
    DoFn<KV<String, Long>, KV<String, Long>> filterElementsEqualToCountFn = new DoFn<KV<String, Long>, KV<String, Long>>() {

        @StateId("counter")
        private final StateSpec<ValueState<Long>> counterSpec = StateSpecs.value(VarLongCoder.of());

        @ProcessElement
        public void processElement(ProcessContext context, @StateId("counter") ValueState<Long> count) {
            long currentCount = Optional.ofNullable(count.read()).orElse(0L);
            currentCount = currentCount + 1;
            count.write(currentCount);
            KV<String, Long> currentElement = context.element();
            if (currentCount == currentElement.getValue()) {
                context.output(currentElement);
            }
        }
    };
    WindowingStrategy<Object, GlobalWindow> windowingStrategy = WindowingStrategy.globalDefault();
    TupleTag<KV<String, Long>> outputTag = new TupleTag<>("main-output");
    StringUtf8Coder keyCoder = StringUtf8Coder.of();
    KvToByteBufferKeySelector<String, Long> keySelector = new KvToByteBufferKeySelector<>(keyCoder, null);
    KvCoder<String, Long> coder = KvCoder.of(keyCoder, VarLongCoder.of());
    FullWindowedValueCoder<KV<String, Long>> kvCoder = WindowedValue.getFullCoder(coder, windowingStrategy.getWindowFn().windowCoder());
    CoderTypeInformation<ByteBuffer> keyCoderInfo = new CoderTypeInformation<>(FlinkKeyUtils.ByteBufferCoder.of(), FlinkPipelineOptions.defaults());
    OneInputStreamOperatorTestHarness<WindowedValue<KV<String, Long>>, WindowedValue<KV<String, Long>>> testHarness = createTestHarness(windowingStrategy, filterElementsEqualToCountFn, kvCoder, kvCoder, keyCoder, outputTag, keyCoderInfo, keySelector);
    testHarness.open();
    testHarness.processElement(new StreamRecord<>(WindowedValue.valueInGlobalWindow(KV.of("a", 100L))));
    testHarness.processElement(new StreamRecord<>(WindowedValue.valueInGlobalWindow(KV.of("a", 100L))));
    OperatorSubtaskState snapshot = testHarness.snapshot(0, 0);
    testHarness.close();
    testHarness = createTestHarness(windowingStrategy, filterElementsEqualToCountFn, kvCoder, kvCoder, keyCoder, outputTag, keyCoderInfo, keySelector);
    testHarness.initializeState(snapshot);
    testHarness.open();
    // after restore: counter = 2
    testHarness.processElement(new StreamRecord<>(WindowedValue.valueInGlobalWindow(KV.of("a", 100L))));
    testHarness.processElement(new StreamRecord<>(WindowedValue.valueInGlobalWindow(KV.of("a", 4L))));
    testHarness.processElement(new StreamRecord<>(WindowedValue.valueInGlobalWindow(KV.of("a", 5L))));
    testHarness.processElement(new StreamRecord<>(WindowedValue.valueInGlobalWindow(KV.of("a", 100L))));
    assertThat(stripStreamRecordFromWindowedValue(testHarness.getOutput()), contains(WindowedValue.valueInGlobalWindow(KV.of("a", 4L)), WindowedValue.valueInGlobalWindow(KV.of("a", 5L))));
    testHarness.close();
}
Also used : TupleTag(org.apache.beam.sdk.values.TupleTag) OperatorSubtaskState(org.apache.flink.runtime.checkpoint.OperatorSubtaskState) StateSpec(org.apache.beam.sdk.state.StateSpec) 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) CoderTypeInformation(org.apache.beam.runners.flink.translation.types.CoderTypeInformation) KV(org.apache.beam.sdk.values.KV) ByteBuffer(java.nio.ByteBuffer) DoFn(org.apache.beam.sdk.transforms.DoFn) ValueState(org.apache.beam.sdk.state.ValueState) GlobalWindow(org.apache.beam.sdk.transforms.windowing.GlobalWindow) Test(org.junit.Test)

Example 88 with TupleTag

use of org.apache.beam.sdk.values.TupleTag in project beam by apache.

the class DoFnOperatorTest method testFailOnRequiresStableInputAndDisabledCheckpointing.

@Test(expected = IllegalStateException.class)
public void testFailOnRequiresStableInputAndDisabledCheckpointing() {
    TupleTag<KV<String, String>> outputTag = new TupleTag<>("main-output");
    StringUtf8Coder keyCoder = StringUtf8Coder.of();
    KvToByteBufferKeySelector<String, String> keySelector = new KvToByteBufferKeySelector<>(keyCoder, null);
    KvCoder<String, String> kvCoder = KvCoder.of(keyCoder, StringUtf8Coder.of());
    WindowedValue.ValueOnlyWindowedValueCoder<KV<String, String>> windowedValueCoder = WindowedValue.getValueOnlyCoder(kvCoder);
    DoFn<KV<String, String>, KV<String, String>> doFn = new DoFn<KV<String, String>, KV<String, String>>() {

        @ProcessElement
        // Use RequiresStableInput to force buffering elements
        @RequiresStableInput
        public void processElement(ProcessContext context) {
            context.output(context.element());
        }
    };
    FlinkPipelineOptions options = FlinkPipelineOptions.defaults();
    DoFnOperator.MultiOutputOutputManagerFactory<KV<String, String>> outputManagerFactory = new DoFnOperator.MultiOutputOutputManagerFactory<>(outputTag, WindowedValue.getFullCoder(kvCoder, GlobalWindow.Coder.INSTANCE), new SerializablePipelineOptions(options));
    // should make the DoFnOperator creation fail
    options.setCheckpointingInterval(-1L);
    new DoFnOperator<>(doFn, "stepName", windowedValueCoder, Collections.emptyMap(), outputTag, Collections.emptyList(), outputManagerFactory, WindowingStrategy.globalDefault(), new HashMap<>(), /* side-input mapping */
    Collections.emptyList(), /* side inputs */
    options, keyCoder, keySelector, DoFnSchemaInformation.create(), Collections.emptyMap());
}
Also used : TupleTag(org.apache.beam.sdk.values.TupleTag) KV(org.apache.beam.sdk.values.KV) FlinkPipelineOptions(org.apache.beam.runners.flink.FlinkPipelineOptions) DoFn(org.apache.beam.sdk.transforms.DoFn) 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 89 with TupleTag

use of org.apache.beam.sdk.values.TupleTag in project beam by apache.

the class DoFnOperatorTest method testTimersRestore.

@Test
public void testTimersRestore() throws Exception {
    final Instant timerTimestamp = new Instant(1000);
    final String outputMessage = "Timer fired";
    WindowingStrategy<Object, IntervalWindow> windowingStrategy = WindowingStrategy.of(FixedWindows.of(Duration.millis(10_000)));
    DoFn<Integer, String> fn = new DoFn<Integer, String>() {

        private static final String EVENT_TIMER_ID = "eventTimer";

        @TimerId(EVENT_TIMER_ID)
        private final TimerSpec eventTimer = TimerSpecs.timer(TimeDomain.EVENT_TIME);

        @ProcessElement
        public void processElement(ProcessContext context, @TimerId(EVENT_TIMER_ID) Timer timer) {
            timer.set(timerTimestamp);
        }

        @OnTimer(EVENT_TIMER_ID)
        public void onEventTime(OnTimerContext context) {
            assertEquals("Timer timestamp must match set timestamp.", timerTimestamp, context.timestamp());
            context.outputWithTimestamp(outputMessage, context.timestamp());
        }
    };
    VarIntCoder keyCoder = VarIntCoder.of();
    WindowedValue.FullWindowedValueCoder<Integer> inputCoder = WindowedValue.getFullCoder(keyCoder, windowingStrategy.getWindowFn().windowCoder());
    WindowedValue.FullWindowedValueCoder<String> outputCoder = WindowedValue.getFullCoder(StringUtf8Coder.of(), windowingStrategy.getWindowFn().windowCoder());
    TupleTag<String> outputTag = new TupleTag<>("main-output");
    final CoderTypeSerializer<WindowedValue<String>> outputSerializer = new CoderTypeSerializer<>(outputCoder, new SerializablePipelineOptions(FlinkPipelineOptions.defaults()));
    CoderTypeInformation<ByteBuffer> keyCoderInfo = new CoderTypeInformation<>(FlinkKeyUtils.ByteBufferCoder.of(), FlinkPipelineOptions.defaults());
    KeySelector<WindowedValue<Integer>, ByteBuffer> keySelector = e -> FlinkKeyUtils.encodeKey(e.getValue(), keyCoder);
    OneInputStreamOperatorTestHarness<WindowedValue<Integer>, WindowedValue<String>> testHarness = createTestHarness(windowingStrategy, fn, inputCoder, outputCoder, keyCoder, outputTag, keyCoderInfo, keySelector);
    testHarness.setup(outputSerializer);
    testHarness.open();
    testHarness.processWatermark(0);
    IntervalWindow window1 = new IntervalWindow(new Instant(0), Duration.millis(10_000));
    // this should register a timer
    testHarness.processElement(new StreamRecord<>(WindowedValue.of(13, new Instant(0), window1, PaneInfo.NO_FIRING)));
    assertThat(stripStreamRecordFromWindowedValue(testHarness.getOutput()), emptyIterable());
    // snapshot and restore
    final OperatorSubtaskState snapshot = testHarness.snapshot(0, 0);
    testHarness.close();
    testHarness = createTestHarness(windowingStrategy, fn, inputCoder, outputCoder, VarIntCoder.of(), outputTag, keyCoderInfo, keySelector);
    testHarness.setup(outputSerializer);
    testHarness.initializeState(snapshot);
    testHarness.open();
    // this must fire the timer
    testHarness.processWatermark(timerTimestamp.getMillis() + 1);
    assertThat(stripStreamRecordFromWindowedValue(testHarness.getOutput()), contains(WindowedValue.of(outputMessage, timerTimestamp, window1, PaneInfo.NO_FIRING)));
    testHarness.close();
}
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) VarIntCoder(org.apache.beam.sdk.coders.VarIntCoder) TupleTag(org.apache.beam.sdk.values.TupleTag) OperatorSubtaskState(org.apache.flink.runtime.checkpoint.OperatorSubtaskState) WindowedValue(org.apache.beam.sdk.util.WindowedValue) StreamRecordStripper.stripStreamRecordFromWindowedValue(org.apache.beam.runners.flink.translation.wrappers.streaming.StreamRecordStripper.stripStreamRecordFromWindowedValue) CoderTypeSerializer(org.apache.beam.runners.flink.translation.types.CoderTypeSerializer) SerializablePipelineOptions(org.apache.beam.runners.core.construction.SerializablePipelineOptions) IntervalWindow(org.apache.beam.sdk.transforms.windowing.IntervalWindow) TimerSpec(org.apache.beam.sdk.state.TimerSpec) CoderTypeInformation(org.apache.beam.runners.flink.translation.types.CoderTypeInformation) Instant(org.joda.time.Instant) ByteBuffer(java.nio.ByteBuffer) DoFn(org.apache.beam.sdk.transforms.DoFn) Timer(org.apache.beam.sdk.state.Timer) Test(org.junit.Test)

Example 90 with TupleTag

use of org.apache.beam.sdk.values.TupleTag 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)

Aggregations

TupleTag (org.apache.beam.sdk.values.TupleTag)186 Test (org.junit.Test)100 WindowedValue (org.apache.beam.sdk.util.WindowedValue)55 KV (org.apache.beam.sdk.values.KV)54 PCollectionTuple (org.apache.beam.sdk.values.PCollectionTuple)49 PCollection (org.apache.beam.sdk.values.PCollection)42 DoFn (org.apache.beam.sdk.transforms.DoFn)32 Instant (org.joda.time.Instant)32 Map (java.util.Map)30 SerializablePipelineOptions (org.apache.beam.runners.core.construction.SerializablePipelineOptions)30 PCollectionView (org.apache.beam.sdk.values.PCollectionView)30 Pipeline (org.apache.beam.sdk.Pipeline)29 HashMap (java.util.HashMap)28 Coder (org.apache.beam.sdk.coders.Coder)27 StreamRecordStripper.stripStreamRecordFromWindowedValue (org.apache.beam.runners.flink.translation.wrappers.streaming.StreamRecordStripper.stripStreamRecordFromWindowedValue)25 Matchers.containsString (org.hamcrest.Matchers.containsString)25 List (java.util.List)24 BoundedWindow (org.apache.beam.sdk.transforms.windowing.BoundedWindow)23 ArrayList (java.util.ArrayList)22 KvCoder (org.apache.beam.sdk.coders.KvCoder)22