Examples with StreamRecord org.apache.flink.streaming.runtime.streamrecord.StreamRecord used on opensource projects

Example 6 with StreamRecord

use of org.apache.flink.streaming.runtime.streamrecord.StreamRecord in project flink by apache.

the class CEPMigration11to13Test method testKeyedCEPOperatorMigratation.

@Test
public void testKeyedCEPOperatorMigratation() throws Exception {
    KeySelector<Event, Integer> keySelector = new KeySelector<Event, Integer>() {

        private static final long serialVersionUID = -4873366487571254798L;

        @Override
        public Integer getKey(Event value) throws Exception {
            return value.getId();
        }
    };
    final Event startEvent = new Event(42, "start", 1.0);
    final SubEvent middleEvent = new SubEvent(42, "foo", 1.0, 10.0);
    final Event endEvent = new Event(42, "end", 1.0);
    // uncomment these lines for regenerating the snapshot on Flink 1.1
    /*
		OneInputStreamOperatorTestHarness<Event, Map<String, Event>> harness = new OneInputStreamOperatorTestHarness<>(
				new KeyedCEPPatternOperator<>(
						Event.createTypeSerializer(),
						false,
						keySelector,
						IntSerializer.INSTANCE,
						new NFAFactory()));
		harness.configureForKeyedStream(keySelector, BasicTypeInfo.INT_TYPE_INFO);
		harness.open();
		harness.processElement(new StreamRecord<Event>(startEvent, 1));
		harness.processElement(new StreamRecord<Event>(new Event(42, "foobar", 1.0), 2));
		harness.processElement(new StreamRecord<Event>(new SubEvent(42, "barfoo", 1.0, 5.0), 3));
		harness.processWatermark(new Watermark(2));
		// simulate snapshot/restore with empty element queue but NFA state
		StreamTaskState snapshot = harness.snapshot(1, 1);
		FileOutputStream out = new FileOutputStream(
				"src/test/resources/cep-keyed-snapshot-1.1");
		ObjectOutputStream oos = new ObjectOutputStream(out);
		oos.writeObject(snapshot);
		out.close();
		harness.close();
		*/
    OneInputStreamOperatorTestHarness<Event, Map<String, Event>> harness = new KeyedOneInputStreamOperatorTestHarness<>(new KeyedCEPPatternOperator<>(Event.createTypeSerializer(), false, keySelector, IntSerializer.INSTANCE, new NFAFactory(), true), keySelector, BasicTypeInfo.INT_TYPE_INFO);
    harness.setup();
    harness.initializeStateFromLegacyCheckpoint(getResourceFilename("cep-keyed-snapshot-1.1"));
    harness.open();
    harness.processElement(new StreamRecord<Event>(middleEvent, 3));
    harness.processElement(new StreamRecord<>(new Event(42, "start", 1.0), 4));
    harness.processElement(new StreamRecord<>(endEvent, 5));
    harness.processWatermark(new Watermark(20));
    ConcurrentLinkedQueue<Object> result = harness.getOutput();
    // watermark and the result
    assertEquals(2, result.size());
    Object resultObject = result.poll();
    assertTrue(resultObject instanceof StreamRecord);
    StreamRecord<?> resultRecord = (StreamRecord<?>) resultObject;
    assertTrue(resultRecord.getValue() instanceof Map);
    @SuppressWarnings("unchecked") Map<String, Event> patternMap = (Map<String, Event>) resultRecord.getValue();
    assertEquals(startEvent, patternMap.get("start"));
    assertEquals(middleEvent, patternMap.get("middle"));
    assertEquals(endEvent, patternMap.get("end"));
    harness.close();
}

Example 7 with StreamRecord

use of org.apache.flink.streaming.runtime.streamrecord.StreamRecord in project flink by apache.

the class AllWindowedStream 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, AllWindowFunction<V, R, 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);
    final String callLocation = Utils.getCallLocationName();
    final String udfName = "AllWindowedStream." + callLocation;
    final String opName;
    final 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 AggregateApplyAllWindowFunction<>(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 InternalSingleValueAllWindowFunction<>(windowFunction), trigger, allowedLateness, lateDataOutputTag);
    }
    return input.transform(opName, resultType, operator).forceNonParallel();
}

Example 8 with StreamRecord

use of org.apache.flink.streaming.runtime.streamrecord.StreamRecord 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);
}

Example 9 with StreamRecord

use of org.apache.flink.streaming.runtime.streamrecord.StreamRecord 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);
}

Example 10 with StreamRecord

use of org.apache.flink.streaming.runtime.streamrecord.StreamRecord in project flink by apache.

the class WindowedStream method reduce.

/**
	 * 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 reducer.
	 *
	 * @param reduceFunction The reduce function that is used for incremental aggregation.
	 * @param function The window function.
	 * @param resultType Type information for the result type of the window function.
	 * @param legacyWindowOpType When migrating from an older Flink version, this flag indicates
	 *                           the type of the previous operator whose state we inherit.
	 * @return The data stream that is the result of applying the window function to the window.
	 */
private <R> SingleOutputStreamOperator<R> reduce(ReduceFunction<T> reduceFunction, WindowFunction<T, R, K, W> function, TypeInformation<R> resultType, LegacyWindowOperatorType legacyWindowOpType) {
    if (reduceFunction instanceof RichFunction) {
        throw new UnsupportedOperationException("ReduceFunction of reduce can not be a RichFunction.");
    }
    //clean the closures
    function = input.getExecutionEnvironment().clean(function);
    reduceFunction = input.getExecutionEnvironment().clean(reduceFunction);
    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 ReduceApplyWindowFunction<>(reduceFunction, function)), trigger, evictor, allowedLateness, lateDataOutputTag);
    } else {
        ReducingStateDescriptor<T> stateDesc = new ReducingStateDescriptor<>("window-contents", reduceFunction, 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, new InternalSingleValueWindowFunction<>(function), trigger, allowedLateness, lateDataOutputTag, legacyWindowOpType);
    }
    return input.transform(opName, resultType, operator);
}