Search in sources :

Example 51 with ListStateDescriptor

use of org.apache.flink.api.common.state.ListStateDescriptor in project flink by apache.

the class AllWindowedStream method apply.

private <R> SingleOutputStreamOperator<R> apply(InternalWindowFunction<Iterable<T>, R, Byte, W> function, TypeInformation<R> resultType, String callLocation) {
    String udfName = "AllWindowedStream." + callLocation;
    String opName;
    KeySelector<T, Byte> keySel = input.getKeySelector();
    WindowOperator<Byte, T, Iterable<T>, R, W> operator;
    if (evictor != null) {
        @SuppressWarnings({ "unchecked", "rawtypes" }) TypeSerializer<StreamRecord<T>> streamRecordSerializer = (TypeSerializer<StreamRecord<T>>) new StreamElementSerializer(input.getType().createSerializer(getExecutionEnvironment().getConfig()));
        ListStateDescriptor<StreamRecord<T>> stateDesc = new ListStateDescriptor<>("window-contents", streamRecordSerializer);
        opName = "TriggerWindow(" + windowAssigner + ", " + stateDesc + ", " + trigger + ", " + evictor + ", " + udfName + ")";
        operator = new EvictingWindowOperator<>(windowAssigner, windowAssigner.getWindowSerializer(getExecutionEnvironment().getConfig()), keySel, input.getKeyType().createSerializer(getExecutionEnvironment().getConfig()), stateDesc, function, trigger, evictor, allowedLateness, lateDataOutputTag);
    } else {
        ListStateDescriptor<T> stateDesc = new ListStateDescriptor<>("window-contents", input.getType().createSerializer(getExecutionEnvironment().getConfig()));
        opName = "TriggerWindow(" + windowAssigner + ", " + stateDesc + ", " + trigger + ", " + udfName + ")";
        operator = new WindowOperator<>(windowAssigner, windowAssigner.getWindowSerializer(getExecutionEnvironment().getConfig()), keySel, input.getKeyType().createSerializer(getExecutionEnvironment().getConfig()), stateDesc, function, trigger, allowedLateness, lateDataOutputTag);
    }
    return input.transform(opName, resultType, operator).forceNonParallel();
}
Also used : StreamRecord(org.apache.flink.streaming.runtime.streamrecord.StreamRecord) ListStateDescriptor(org.apache.flink.api.common.state.ListStateDescriptor) TypeSerializer(org.apache.flink.api.common.typeutils.TypeSerializer) StreamElementSerializer(org.apache.flink.streaming.runtime.streamrecord.StreamElementSerializer)

Example 52 with ListStateDescriptor

use of org.apache.flink.api.common.state.ListStateDescriptor in project flink by apache.

the class WindowedStream method aggregate.

/**
	 * Applies the given window function to each window. The window function is called for each
	 * evaluation of the window for each key individually. The output of the window function is
	 * interpreted as a regular non-windowed stream.
	 *
	 * <p>Arriving data is incrementally aggregated using the given aggregate function. This means
	 * that the window function typically has only a single value to process when called.
	 *
	 * @param aggregateFunction The aggregation function that is used for incremental aggregation.
	 * @param windowFunction The window function.
	 * @param accumulatorType Type information for the internal accumulator type of the aggregation function
	 * @param resultType Type information for the result type of the window function
	 *
	 * @return The data stream that is the result of applying the window function to the window.
	 *
	 * @param <ACC> The type of the AggregateFunction's accumulator
	 * @param <V> The type of AggregateFunction's result, and the WindowFunction's input
	 * @param <R> The type of the elements in the resulting stream, equal to the
	 *            WindowFunction's result type
	 */
@PublicEvolving
public <ACC, V, R> SingleOutputStreamOperator<R> aggregate(AggregateFunction<T, ACC, V> aggregateFunction, WindowFunction<V, R, K, W> windowFunction, TypeInformation<ACC> accumulatorType, TypeInformation<V> aggregateResultType, TypeInformation<R> resultType) {
    checkNotNull(aggregateFunction, "aggregateFunction");
    checkNotNull(windowFunction, "windowFunction");
    checkNotNull(accumulatorType, "accumulatorType");
    checkNotNull(aggregateResultType, "aggregateResultType");
    checkNotNull(resultType, "resultType");
    if (aggregateFunction instanceof RichFunction) {
        throw new UnsupportedOperationException("This aggregate function cannot be a RichFunction.");
    }
    //clean the closures
    windowFunction = input.getExecutionEnvironment().clean(windowFunction);
    aggregateFunction = input.getExecutionEnvironment().clean(aggregateFunction);
    String callLocation = Utils.getCallLocationName();
    String udfName = "WindowedStream." + callLocation;
    String opName;
    KeySelector<T, K> keySel = input.getKeySelector();
    OneInputStreamOperator<T, R> operator;
    if (evictor != null) {
        @SuppressWarnings({ "unchecked", "rawtypes" }) TypeSerializer<StreamRecord<T>> streamRecordSerializer = (TypeSerializer<StreamRecord<T>>) new StreamElementSerializer(input.getType().createSerializer(getExecutionEnvironment().getConfig()));
        ListStateDescriptor<StreamRecord<T>> stateDesc = new ListStateDescriptor<>("window-contents", streamRecordSerializer);
        opName = "TriggerWindow(" + windowAssigner + ", " + stateDesc + ", " + trigger + ", " + evictor + ", " + udfName + ")";
        operator = new EvictingWindowOperator<>(windowAssigner, windowAssigner.getWindowSerializer(getExecutionEnvironment().getConfig()), keySel, input.getKeyType().createSerializer(getExecutionEnvironment().getConfig()), stateDesc, new InternalIterableWindowFunction<>(new AggregateApplyWindowFunction<>(aggregateFunction, windowFunction)), trigger, evictor, allowedLateness, lateDataOutputTag);
    } else {
        AggregatingStateDescriptor<T, ACC, V> stateDesc = new AggregatingStateDescriptor<>("window-contents", aggregateFunction, accumulatorType.createSerializer(getExecutionEnvironment().getConfig()));
        opName = "TriggerWindow(" + windowAssigner + ", " + stateDesc + ", " + trigger + ", " + udfName + ")";
        operator = new WindowOperator<>(windowAssigner, windowAssigner.getWindowSerializer(getExecutionEnvironment().getConfig()), keySel, input.getKeyType().createSerializer(getExecutionEnvironment().getConfig()), stateDesc, new InternalSingleValueWindowFunction<>(windowFunction), trigger, allowedLateness, lateDataOutputTag);
    }
    return input.transform(opName, resultType, operator);
}
Also used : StreamRecord(org.apache.flink.streaming.runtime.streamrecord.StreamRecord) RichFunction(org.apache.flink.api.common.functions.RichFunction) AggregatingStateDescriptor(org.apache.flink.api.common.state.AggregatingStateDescriptor) InternalSingleValueWindowFunction(org.apache.flink.streaming.runtime.operators.windowing.functions.InternalSingleValueWindowFunction) ListStateDescriptor(org.apache.flink.api.common.state.ListStateDescriptor) InternalIterableWindowFunction(org.apache.flink.streaming.runtime.operators.windowing.functions.InternalIterableWindowFunction) TypeSerializer(org.apache.flink.api.common.typeutils.TypeSerializer) StreamElementSerializer(org.apache.flink.streaming.runtime.streamrecord.StreamElementSerializer) PublicEvolving(org.apache.flink.annotation.PublicEvolving)

Example 53 with ListStateDescriptor

use of org.apache.flink.api.common.state.ListStateDescriptor in project flink by apache.

the class StateDescriptorPassingTest method validateListStateDescriptorConfigured.

private void validateListStateDescriptorConfigured(SingleOutputStreamOperator<?> result) {
    OneInputTransformation<?, ?> transform = (OneInputTransformation<?, ?>) result.getTransformation();
    WindowOperator<?, ?, ?, ?, ?> op = (WindowOperator<?, ?, ?, ?, ?>) transform.getOperator();
    StateDescriptor<?, ?> descr = op.getStateDescriptor();
    assertTrue(descr instanceof ListStateDescriptor);
    ListStateDescriptor<?> listDescr = (ListStateDescriptor<?>) descr;
    // this would be the first statement to fail if state descriptors were not properly initialized
    TypeSerializer<?> serializer = listDescr.getSerializer();
    assertTrue(serializer instanceof ListSerializer);
    TypeSerializer<?> elementSerializer = listDescr.getElementSerializer();
    assertTrue(elementSerializer instanceof KryoSerializer);
    Kryo kryo = ((KryoSerializer<?>) elementSerializer).getKryo();
    assertTrue("serializer registration was not properly passed on", kryo.getSerializer(File.class) instanceof JavaSerializer);
}
Also used : WindowOperator(org.apache.flink.streaming.runtime.operators.windowing.WindowOperator) ListSerializer(org.apache.flink.api.common.typeutils.base.ListSerializer) ListStateDescriptor(org.apache.flink.api.common.state.ListStateDescriptor) OneInputTransformation(org.apache.flink.streaming.api.transformations.OneInputTransformation) JavaSerializer(com.esotericsoftware.kryo.serializers.JavaSerializer) Kryo(com.esotericsoftware.kryo.Kryo) KryoSerializer(org.apache.flink.api.java.typeutils.runtime.kryo.KryoSerializer)

Example 54 with ListStateDescriptor

use of org.apache.flink.api.common.state.ListStateDescriptor in project flink by apache.

the class AllWindowTranslationTest method testFoldWithEvictor.

@Test
@SuppressWarnings({ "rawtypes", "unchecked" })
public void testFoldWithEvictor() throws Exception {
    StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
    env.setStreamTimeCharacteristic(TimeCharacteristic.IngestionTime);
    DataStream<Tuple2<String, Integer>> source = env.fromElements(Tuple2.of("hello", 1), Tuple2.of("hello", 2));
    DataStream<Tuple3<String, String, Integer>> window1 = source.windowAll(SlidingEventTimeWindows.of(Time.of(1, TimeUnit.SECONDS), Time.of(100, TimeUnit.MILLISECONDS))).evictor(CountEvictor.of(100)).fold(new Tuple3<>("", "", 1), new DummyFolder());
    OneInputTransformation<Tuple2<String, Integer>, Tuple3<String, String, Integer>> transform = (OneInputTransformation<Tuple2<String, Integer>, Tuple3<String, String, Integer>>) window1.getTransformation();
    OneInputStreamOperator<Tuple2<String, Integer>, Tuple3<String, String, Integer>> operator = transform.getOperator();
    Assert.assertTrue(operator instanceof EvictingWindowOperator);
    EvictingWindowOperator<String, Tuple2<String, Integer>, ?, ?> winOperator = (EvictingWindowOperator<String, Tuple2<String, Integer>, ?, ?>) operator;
    Assert.assertTrue(winOperator.getTrigger() instanceof EventTimeTrigger);
    Assert.assertTrue(winOperator.getWindowAssigner() instanceof SlidingEventTimeWindows);
    Assert.assertTrue(winOperator.getEvictor() instanceof CountEvictor);
    Assert.assertTrue(winOperator.getStateDescriptor() instanceof ListStateDescriptor);
    winOperator.setOutputType((TypeInformation) window1.getType(), new ExecutionConfig());
    processElementAndEnsureOutput(winOperator, winOperator.getKeySelector(), BasicTypeInfo.STRING_TYPE_INFO, new Tuple2<>("hello", 1));
}
Also used : SlidingEventTimeWindows(org.apache.flink.streaming.api.windowing.assigners.SlidingEventTimeWindows) ListStateDescriptor(org.apache.flink.api.common.state.ListStateDescriptor) ExecutionConfig(org.apache.flink.api.common.ExecutionConfig) CountEvictor(org.apache.flink.streaming.api.windowing.evictors.CountEvictor) Tuple2(org.apache.flink.api.java.tuple.Tuple2) Tuple3(org.apache.flink.api.java.tuple.Tuple3) StreamExecutionEnvironment(org.apache.flink.streaming.api.environment.StreamExecutionEnvironment) OneInputTransformation(org.apache.flink.streaming.api.transformations.OneInputTransformation) EventTimeTrigger(org.apache.flink.streaming.api.windowing.triggers.EventTimeTrigger) Test(org.junit.Test)

Example 55 with ListStateDescriptor

use of org.apache.flink.api.common.state.ListStateDescriptor in project flink by apache.

the class AllWindowTranslationTest method testProcessEventTime.

// ------------------------------------------------------------------------
//  process() translation tests
// ------------------------------------------------------------------------
@Test
@SuppressWarnings("rawtypes")
public void testProcessEventTime() throws Exception {
    StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
    env.setStreamTimeCharacteristic(TimeCharacteristic.IngestionTime);
    DataStream<Tuple2<String, Integer>> source = env.fromElements(Tuple2.of("hello", 1), Tuple2.of("hello", 2));
    DataStream<Tuple2<String, Integer>> window1 = source.windowAll(TumblingEventTimeWindows.of(Time.of(1, TimeUnit.SECONDS))).process(new ProcessAllWindowFunction<Tuple2<String, Integer>, Tuple2<String, Integer>, TimeWindow>() {

        private static final long serialVersionUID = 1L;

        @Override
        public void process(Context ctx, Iterable<Tuple2<String, Integer>> values, Collector<Tuple2<String, Integer>> out) throws Exception {
            for (Tuple2<String, Integer> in : values) {
                out.collect(in);
            }
        }
    });
    OneInputTransformation<Tuple2<String, Integer>, Tuple2<String, Integer>> transform = (OneInputTransformation<Tuple2<String, Integer>, Tuple2<String, Integer>>) window1.getTransformation();
    OneInputStreamOperator<Tuple2<String, Integer>, Tuple2<String, Integer>> operator = transform.getOperator();
    Assert.assertTrue(operator instanceof WindowOperator);
    WindowOperator<String, Tuple2<String, Integer>, ?, ?, ?> winOperator = (WindowOperator<String, Tuple2<String, Integer>, ?, ?, ?>) operator;
    Assert.assertTrue(winOperator.getTrigger() instanceof EventTimeTrigger);
    Assert.assertTrue(winOperator.getWindowAssigner() instanceof TumblingEventTimeWindows);
    Assert.assertTrue(winOperator.getStateDescriptor() instanceof ListStateDescriptor);
    processElementAndEnsureOutput(winOperator, winOperator.getKeySelector(), BasicTypeInfo.STRING_TYPE_INFO, new Tuple2<>("hello", 1));
}
Also used : TumblingEventTimeWindows(org.apache.flink.streaming.api.windowing.assigners.TumblingEventTimeWindows) ListStateDescriptor(org.apache.flink.api.common.state.ListStateDescriptor) TimeWindow(org.apache.flink.streaming.api.windowing.windows.TimeWindow) Tuple2(org.apache.flink.api.java.tuple.Tuple2) StreamExecutionEnvironment(org.apache.flink.streaming.api.environment.StreamExecutionEnvironment) OneInputTransformation(org.apache.flink.streaming.api.transformations.OneInputTransformation) EventTimeTrigger(org.apache.flink.streaming.api.windowing.triggers.EventTimeTrigger) Test(org.junit.Test)

Aggregations

ListStateDescriptor (org.apache.flink.api.common.state.ListStateDescriptor)82 Test (org.junit.Test)60 Tuple2 (org.apache.flink.api.java.tuple.Tuple2)49 TimeWindow (org.apache.flink.streaming.api.windowing.windows.TimeWindow)37 ExecutionConfig (org.apache.flink.api.common.ExecutionConfig)33 OneInputTransformation (org.apache.flink.streaming.api.transformations.OneInputTransformation)32 StreamExecutionEnvironment (org.apache.flink.streaming.api.environment.StreamExecutionEnvironment)31 TypeSerializer (org.apache.flink.api.common.typeutils.TypeSerializer)29 StreamElementSerializer (org.apache.flink.streaming.runtime.streamrecord.StreamElementSerializer)27 StreamRecord (org.apache.flink.streaming.runtime.streamrecord.StreamRecord)27 EventTimeTrigger (org.apache.flink.streaming.api.windowing.triggers.EventTimeTrigger)19 ConcurrentLinkedQueue (java.util.concurrent.ConcurrentLinkedQueue)18 KeyedOneInputStreamOperatorTestHarness (org.apache.flink.streaming.util.KeyedOneInputStreamOperatorTestHarness)18 AtomicInteger (java.util.concurrent.atomic.AtomicInteger)17 RichFunction (org.apache.flink.api.common.functions.RichFunction)16 TumblingEventTimeWindows (org.apache.flink.streaming.api.windowing.assigners.TumblingEventTimeWindows)15 SlidingEventTimeWindows (org.apache.flink.streaming.api.windowing.assigners.SlidingEventTimeWindows)12 Tuple3 (org.apache.flink.api.java.tuple.Tuple3)11 PublicEvolving (org.apache.flink.annotation.PublicEvolving)9 Watermark (org.apache.flink.streaming.api.watermark.Watermark)9