Search in sources :

Example 1 with MergingWindowAssigner

use of org.apache.flink.streaming.api.windowing.assigners.MergingWindowAssigner in project flink by apache.

the class WindowedStream method apply.

/**
	 * 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 fold function.
	 *
	 * @param initialValue The initial value of the fold.
	 * @param foldFunction The fold function that is used for incremental aggregation.
	 * @param function The window 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.
	 *
	 * @deprecated Use {@link #fold(Object, FoldFunction, WindowFunction, TypeInformation, TypeInformation)} instead.
	 */
@Deprecated
public <R> SingleOutputStreamOperator<R> apply(R initialValue, FoldFunction<T, R> foldFunction, WindowFunction<R, R, K, W> function, TypeInformation<R> resultType) {
    if (foldFunction instanceof RichFunction) {
        throw new UnsupportedOperationException("FoldFunction of apply can not be a RichFunction.");
    }
    if (windowAssigner instanceof MergingWindowAssigner) {
        throw new UnsupportedOperationException("Fold cannot be used with a merging WindowAssigner.");
    }
    //clean the closures
    function = input.getExecutionEnvironment().clean(function);
    foldFunction = input.getExecutionEnvironment().clean(foldFunction);
    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 FoldApplyWindowFunction<>(initialValue, foldFunction, function, resultType)), trigger, evictor, allowedLateness, lateDataOutputTag);
    } else {
        FoldingStateDescriptor<T, R> stateDesc = new FoldingStateDescriptor<>("window-contents", initialValue, foldFunction, resultType.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<>(function), 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) 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) FoldingStateDescriptor(org.apache.flink.api.common.state.FoldingStateDescriptor) MergingWindowAssigner(org.apache.flink.streaming.api.windowing.assigners.MergingWindowAssigner) TypeSerializer(org.apache.flink.api.common.typeutils.TypeSerializer) StreamElementSerializer(org.apache.flink.streaming.runtime.streamrecord.StreamElementSerializer)

Example 2 with MergingWindowAssigner

use of org.apache.flink.streaming.api.windowing.assigners.MergingWindowAssigner in project flink by apache.

the class WindowedStream method fold.

/**
	 * 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 fold function.
	 *
	 * @param initialValue the initial value to be passed to the first invocation of the fold function
	 * @param foldFunction The fold function.
	 * @param foldResultType The result type of the fold function.
	 * @param windowFunction The process window function.
	 * @param windowResultType The process window function result type.
	 * @return The data stream that is the result of applying the fold function to the window.
	 */
@Internal
public <R, ACC> SingleOutputStreamOperator<R> fold(ACC initialValue, FoldFunction<T, ACC> foldFunction, ProcessWindowFunction<ACC, R, K, W> windowFunction, TypeInformation<ACC> foldResultType, TypeInformation<R> windowResultType) {
    if (foldFunction instanceof RichFunction) {
        throw new UnsupportedOperationException("FoldFunction can not be a RichFunction.");
    }
    if (windowAssigner instanceof MergingWindowAssigner) {
        throw new UnsupportedOperationException("Fold cannot be used with a merging WindowAssigner.");
    }
    //clean the closures
    windowFunction = input.getExecutionEnvironment().clean(windowFunction);
    foldFunction = input.getExecutionEnvironment().clean(foldFunction);
    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 InternalIterableProcessWindowFunction<>(new FoldApplyProcessWindowFunction<>(initialValue, foldFunction, windowFunction, foldResultType)), trigger, evictor, allowedLateness, lateDataOutputTag);
    } else {
        FoldingStateDescriptor<T, ACC> stateDesc = new FoldingStateDescriptor<>("window-contents", initialValue, foldFunction, foldResultType.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 InternalSingleValueProcessWindowFunction<>(windowFunction), trigger, allowedLateness, lateDataOutputTag);
    }
    return input.transform(opName, windowResultType, operator);
}
Also used : StreamRecord(org.apache.flink.streaming.runtime.streamrecord.StreamRecord) RichFunction(org.apache.flink.api.common.functions.RichFunction) ListStateDescriptor(org.apache.flink.api.common.state.ListStateDescriptor) FoldingStateDescriptor(org.apache.flink.api.common.state.FoldingStateDescriptor) MergingWindowAssigner(org.apache.flink.streaming.api.windowing.assigners.MergingWindowAssigner) TypeSerializer(org.apache.flink.api.common.typeutils.TypeSerializer) InternalSingleValueProcessWindowFunction(org.apache.flink.streaming.runtime.operators.windowing.functions.InternalSingleValueProcessWindowFunction) StreamElementSerializer(org.apache.flink.streaming.runtime.streamrecord.StreamElementSerializer) InternalIterableProcessWindowFunction(org.apache.flink.streaming.runtime.operators.windowing.functions.InternalIterableProcessWindowFunction) Internal(org.apache.flink.annotation.Internal)

Example 3 with MergingWindowAssigner

use of org.apache.flink.streaming.api.windowing.assigners.MergingWindowAssigner in project flink by apache.

the class AllWindowedStream method fold.

/**
	 * 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 fold function.
	 *
	 * @param initialValue The initial value of the fold.
	 * @param foldFunction The fold function that is used for incremental aggregation.
	 * @param function The window function.
	 * @param foldAccumulatorType Type information for the result type of the fold 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.
	 */
@PublicEvolving
public <ACC, R> SingleOutputStreamOperator<R> fold(ACC initialValue, FoldFunction<T, ACC> foldFunction, AllWindowFunction<ACC, R, W> function, TypeInformation<ACC> foldAccumulatorType, TypeInformation<R> resultType) {
    if (foldFunction instanceof RichFunction) {
        throw new UnsupportedOperationException("FoldFunction of fold can not be a RichFunction.");
    }
    if (windowAssigner instanceof MergingWindowAssigner) {
        throw new UnsupportedOperationException("Fold cannot be used with a merging WindowAssigner.");
    }
    //clean the closures
    function = input.getExecutionEnvironment().clean(function);
    foldFunction = input.getExecutionEnvironment().clean(foldFunction);
    String callLocation = Utils.getCallLocationName();
    String udfName = "AllWindowedStream." + callLocation;
    String opName;
    KeySelector<T, Byte> 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 InternalIterableAllWindowFunction<>(new FoldApplyAllWindowFunction<>(initialValue, foldFunction, function, foldAccumulatorType)), trigger, evictor, allowedLateness, lateDataOutputTag);
    } else {
        FoldingStateDescriptor<T, ACC> stateDesc = new FoldingStateDescriptor<>("window-contents", initialValue, foldFunction, foldAccumulatorType.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 InternalSingleValueAllWindowFunction<>(function), trigger, allowedLateness, lateDataOutputTag);
    }
    return input.transform(opName, resultType, operator).forceNonParallel();
}
Also used : StreamRecord(org.apache.flink.streaming.runtime.streamrecord.StreamRecord) RichFunction(org.apache.flink.api.common.functions.RichFunction) ListStateDescriptor(org.apache.flink.api.common.state.ListStateDescriptor) FoldingStateDescriptor(org.apache.flink.api.common.state.FoldingStateDescriptor) MergingWindowAssigner(org.apache.flink.streaming.api.windowing.assigners.MergingWindowAssigner) InternalSingleValueAllWindowFunction(org.apache.flink.streaming.runtime.operators.windowing.functions.InternalSingleValueAllWindowFunction) InternalIterableAllWindowFunction(org.apache.flink.streaming.runtime.operators.windowing.functions.InternalIterableAllWindowFunction) TypeSerializer(org.apache.flink.api.common.typeutils.TypeSerializer) StreamElementSerializer(org.apache.flink.streaming.runtime.streamrecord.StreamElementSerializer) PublicEvolving(org.apache.flink.annotation.PublicEvolving)

Example 4 with MergingWindowAssigner

use of org.apache.flink.streaming.api.windowing.assigners.MergingWindowAssigner in project flink by apache.

the class WindowedStream method fold.

/**
	 * 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 fold function.
	 *
	 * @param initialValue The initial value of the fold.
	 * @param foldFunction The fold function that is used for incremental aggregation.
	 * @param function The window function.
	 * @param foldAccumulatorType Type information for the result type of the fold 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.
	 */
@PublicEvolving
public <ACC, R> SingleOutputStreamOperator<R> fold(ACC initialValue, FoldFunction<T, ACC> foldFunction, WindowFunction<ACC, R, K, W> function, TypeInformation<ACC> foldAccumulatorType, TypeInformation<R> resultType) {
    if (foldFunction instanceof RichFunction) {
        throw new UnsupportedOperationException("FoldFunction of fold can not be a RichFunction.");
    }
    if (windowAssigner instanceof MergingWindowAssigner) {
        throw new UnsupportedOperationException("Fold cannot be used with a merging WindowAssigner.");
    }
    if (windowAssigner instanceof BaseAlignedWindowAssigner) {
        throw new UnsupportedOperationException("Fold cannot be used with a " + windowAssigner.getClass().getSimpleName() + " assigner.");
    }
    //clean the closures
    function = input.getExecutionEnvironment().clean(function);
    foldFunction = input.getExecutionEnvironment().clean(foldFunction);
    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 FoldApplyWindowFunction<>(initialValue, foldFunction, function, foldAccumulatorType)), trigger, evictor, allowedLateness, lateDataOutputTag);
    } else {
        FoldingStateDescriptor<T, ACC> stateDesc = new FoldingStateDescriptor<>("window-contents", initialValue, foldFunction, foldAccumulatorType.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<>(function), trigger, allowedLateness, lateDataOutputTag);
    }
    return input.transform(opName, resultType, operator);
}
Also used : 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) FoldingStateDescriptor(org.apache.flink.api.common.state.FoldingStateDescriptor) TypeSerializer(org.apache.flink.api.common.typeutils.TypeSerializer) StreamElementSerializer(org.apache.flink.streaming.runtime.streamrecord.StreamElementSerializer) StreamRecord(org.apache.flink.streaming.runtime.streamrecord.StreamRecord) RichFunction(org.apache.flink.api.common.functions.RichFunction) MergingWindowAssigner(org.apache.flink.streaming.api.windowing.assigners.MergingWindowAssigner) BaseAlignedWindowAssigner(org.apache.flink.streaming.api.windowing.assigners.BaseAlignedWindowAssigner) PublicEvolving(org.apache.flink.annotation.PublicEvolving)

Example 5 with MergingWindowAssigner

use of org.apache.flink.streaming.api.windowing.assigners.MergingWindowAssigner in project flink by apache.

the class EvictingWindowOperator method onProcessingTime.

@Override
public void onProcessingTime(InternalTimer<K, W> timer) throws Exception {
    triggerContext.key = timer.getKey();
    triggerContext.window = timer.getNamespace();
    evictorContext.key = timer.getKey();
    evictorContext.window = timer.getNamespace();
    MergingWindowSet<W> mergingWindows = null;
    if (windowAssigner instanceof MergingWindowAssigner) {
        mergingWindows = getMergingWindowSet();
        W stateWindow = mergingWindows.getStateWindow(triggerContext.window);
        if (stateWindow == null) {
            // window and therefore the Trigger state, however, so nothing to do.
            return;
        } else {
            evictingWindowState.setCurrentNamespace(stateWindow);
        }
    } else {
        evictingWindowState.setCurrentNamespace(triggerContext.window);
    }
    TriggerResult triggerResult = triggerContext.onProcessingTime(timer.getTimestamp());
    if (triggerResult.isFire()) {
        Iterable<StreamRecord<IN>> contents = evictingWindowState.get();
        if (contents != null) {
            emitWindowContents(triggerContext.window, contents, evictingWindowState);
        }
    }
    if (triggerResult.isPurge()) {
        evictingWindowState.clear();
    }
    if (!windowAssigner.isEventTime() && isCleanupTime(triggerContext.window, timer.getTimestamp())) {
        clearAllState(triggerContext.window, evictingWindowState, mergingWindows);
    }
    if (mergingWindows != null) {
        // need to make sure to update the merging state in state
        mergingWindows.persist();
    }
}
Also used : StreamRecord(org.apache.flink.streaming.runtime.streamrecord.StreamRecord) TriggerResult(org.apache.flink.streaming.api.windowing.triggers.TriggerResult) MergingWindowAssigner(org.apache.flink.streaming.api.windowing.assigners.MergingWindowAssigner)

Aggregations

MergingWindowAssigner (org.apache.flink.streaming.api.windowing.assigners.MergingWindowAssigner)12 StreamRecord (org.apache.flink.streaming.runtime.streamrecord.StreamRecord)9 RichFunction (org.apache.flink.api.common.functions.RichFunction)6 FoldingStateDescriptor (org.apache.flink.api.common.state.FoldingStateDescriptor)6 ListStateDescriptor (org.apache.flink.api.common.state.ListStateDescriptor)6 TypeSerializer (org.apache.flink.api.common.typeutils.TypeSerializer)6 TriggerResult (org.apache.flink.streaming.api.windowing.triggers.TriggerResult)6 StreamElementSerializer (org.apache.flink.streaming.runtime.streamrecord.StreamElementSerializer)6 PublicEvolving (org.apache.flink.annotation.PublicEvolving)3 InternalIterableAllWindowFunction (org.apache.flink.streaming.runtime.operators.windowing.functions.InternalIterableAllWindowFunction)2 InternalIterableWindowFunction (org.apache.flink.streaming.runtime.operators.windowing.functions.InternalIterableWindowFunction)2 InternalSingleValueAllWindowFunction (org.apache.flink.streaming.runtime.operators.windowing.functions.InternalSingleValueAllWindowFunction)2 InternalSingleValueWindowFunction (org.apache.flink.streaming.runtime.operators.windowing.functions.InternalSingleValueWindowFunction)2 Internal (org.apache.flink.annotation.Internal)1 BaseAlignedWindowAssigner (org.apache.flink.streaming.api.windowing.assigners.BaseAlignedWindowAssigner)1 InternalIterableProcessAllWindowFunction (org.apache.flink.streaming.runtime.operators.windowing.functions.InternalIterableProcessAllWindowFunction)1 InternalIterableProcessWindowFunction (org.apache.flink.streaming.runtime.operators.windowing.functions.InternalIterableProcessWindowFunction)1 InternalSingleValueProcessAllWindowFunction (org.apache.flink.streaming.runtime.operators.windowing.functions.InternalSingleValueProcessAllWindowFunction)1 InternalSingleValueProcessWindowFunction (org.apache.flink.streaming.runtime.operators.windowing.functions.InternalSingleValueProcessWindowFunction)1