use of org.apache.flink.api.common.typeutils.TypeSerializer in project flink by apache.
the class StateBackendTestBase method testMapStateRestoreWithWrongSerializers.
@Test
@SuppressWarnings("unchecked")
public void testMapStateRestoreWithWrongSerializers() {
try {
CheckpointStreamFactory streamFactory = createStreamFactory();
AbstractKeyedStateBackend<Integer> backend = createKeyedBackend(IntSerializer.INSTANCE);
MapStateDescriptor<String, String> kvId = new MapStateDescriptor<>("id", StringSerializer.INSTANCE, StringSerializer.INSTANCE);
MapState<String, String> state = backend.getPartitionedState(VoidNamespace.INSTANCE, VoidNamespaceSerializer.INSTANCE, kvId);
backend.setCurrentKey(1);
state.put("1", "First");
backend.setCurrentKey(2);
state.put("2", "Second");
// draw a snapshot
KeyGroupsStateHandle snapshot1 = FutureUtil.runIfNotDoneAndGet(backend.snapshot(682375462378L, 2, streamFactory, CheckpointOptions.forFullCheckpoint()));
backend.dispose();
// restore the first snapshot and validate it
backend = restoreKeyedBackend(IntSerializer.INSTANCE, snapshot1);
snapshot1.discardState();
@SuppressWarnings("unchecked") TypeSerializer<String> fakeStringSerializer = (TypeSerializer<String>) (TypeSerializer<?>) FloatSerializer.INSTANCE;
try {
kvId = new MapStateDescriptor<>("id", fakeStringSerializer, StringSerializer.INSTANCE);
state = backend.getPartitionedState(VoidNamespace.INSTANCE, VoidNamespaceSerializer.INSTANCE, kvId);
state.entries();
fail("should recognize wrong serializers");
} catch (IOException e) {
if (!e.getMessage().contains("Trying to access state using wrong ")) {
fail("wrong exception " + e);
}
// expected
} catch (Exception e) {
fail("wrong exception " + e);
}
backend.dispose();
} catch (Exception e) {
e.printStackTrace();
fail(e.getMessage());
}
}
use of org.apache.flink.api.common.typeutils.TypeSerializer 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 process 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, ProcessAllWindowFunction<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 InternalAggregateProcessAllWindowFunction<>(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 InternalSingleValueProcessAllWindowFunction<>(windowFunction), trigger, allowedLateness, lateDataOutputTag);
}
return input.transform(opName, resultType, operator).forceNonParallel();
}
use of org.apache.flink.api.common.typeutils.TypeSerializer 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 process 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, ProcessAllWindowFunction<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 InternalIterableProcessAllWindowFunction<>(new FoldApplyProcessAllWindowFunction<>(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 InternalSingleValueProcessAllWindowFunction<>(function), trigger, allowedLateness, lateDataOutputTag);
}
return input.transform(opName, resultType, operator).forceNonParallel();
}
use of org.apache.flink.api.common.typeutils.TypeSerializer in project flink by apache.
the class AllWindowedStream 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
* @return The data stream that is the result of applying the window function to the window.
*/
@PublicEvolving
public <R> SingleOutputStreamOperator<R> reduce(ReduceFunction<T> reduceFunction, AllWindowFunction<T, R, W> function, TypeInformation<R> resultType) {
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 = "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 ReduceApplyAllWindowFunction<>(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 InternalSingleValueAllWindowFunction<>(function), trigger, allowedLateness, lateDataOutputTag);
}
return input.transform(opName, resultType, operator).forceNonParallel();
}
use of org.apache.flink.api.common.typeutils.TypeSerializer in project flink by apache.
the class AllWindowedStream 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, AllWindowFunction, TypeInformation, TypeInformation)} instead.
*/
@Deprecated
public <R> SingleOutputStreamOperator<R> apply(R initialValue, FoldFunction<T, R> foldFunction, AllWindowFunction<R, R, W> function, TypeInformation<R> resultType) {
if (foldFunction instanceof RichFunction) {
throw new UnsupportedOperationException("ReduceFunction 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 = "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, 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 InternalSingleValueAllWindowFunction<>(function), trigger, allowedLateness, lateDataOutputTag);
}
return input.transform(opName, resultType, operator).forceNonParallel();
}
Aggregations