Search in sources :

Example 56 with ExecEdge

use of org.apache.flink.table.planner.plan.nodes.exec.ExecEdge in project flink by apache.

the class StreamExecWindowJoin method translateToPlanInternal.

@Override
@SuppressWarnings("unchecked")
protected Transformation<RowData> translateToPlanInternal(PlannerBase planner, ExecNodeConfig config) {
    int leftWindowEndIndex = ((WindowAttachedWindowingStrategy) leftWindowing).getWindowEnd();
    int rightWindowEndIndex = ((WindowAttachedWindowingStrategy) rightWindowing).getWindowEnd();
    final ExecEdge leftInputEdge = getInputEdges().get(0);
    final ExecEdge rightInputEdge = getInputEdges().get(1);
    final Transformation<RowData> leftTransform = (Transformation<RowData>) leftInputEdge.translateToPlan(planner);
    final Transformation<RowData> rightTransform = (Transformation<RowData>) rightInputEdge.translateToPlan(planner);
    final RowType leftType = (RowType) leftInputEdge.getOutputType();
    final RowType rightType = (RowType) rightInputEdge.getOutputType();
    JoinUtil.validateJoinSpec(joinSpec, leftType, rightType, true);
    final int[] leftJoinKey = joinSpec.getLeftKeys();
    final int[] rightJoinKey = joinSpec.getRightKeys();
    final InternalTypeInfo<RowData> leftTypeInfo = InternalTypeInfo.of(leftType);
    final InternalTypeInfo<RowData> rightTypeInfo = InternalTypeInfo.of(rightType);
    GeneratedJoinCondition generatedCondition = JoinUtil.generateConditionFunction(config.getTableConfig(), joinSpec, leftType, rightType);
    ZoneId shiftTimeZone = TimeWindowUtil.getShiftTimeZone(leftWindowing.getTimeAttributeType(), config.getLocalTimeZone());
    WindowJoinOperator operator = WindowJoinOperatorBuilder.builder().leftSerializer(leftTypeInfo.toRowSerializer()).rightSerializer(rightTypeInfo.toRowSerializer()).generatedJoinCondition(generatedCondition).leftWindowEndIndex(leftWindowEndIndex).rightWindowEndIndex(rightWindowEndIndex).filterNullKeys(joinSpec.getFilterNulls()).joinType(joinSpec.getJoinType()).withShiftTimezone(shiftTimeZone).build();
    final RowType returnType = (RowType) getOutputType();
    final TwoInputTransformation<RowData, RowData, RowData> transform = ExecNodeUtil.createTwoInputTransformation(leftTransform, rightTransform, createTransformationMeta(WINDOW_JOIN_TRANSFORMATION, config), operator, InternalTypeInfo.of(returnType), leftTransform.getParallelism());
    // set KeyType and Selector for state
    RowDataKeySelector leftSelect = KeySelectorUtil.getRowDataSelector(leftJoinKey, leftTypeInfo);
    RowDataKeySelector rightSelect = KeySelectorUtil.getRowDataSelector(rightJoinKey, rightTypeInfo);
    transform.setStateKeySelectors(leftSelect, rightSelect);
    transform.setStateKeyType(leftSelect.getProducedType());
    return transform;
}
Also used : TwoInputTransformation(org.apache.flink.streaming.api.transformations.TwoInputTransformation) Transformation(org.apache.flink.api.dag.Transformation) ExecEdge(org.apache.flink.table.planner.plan.nodes.exec.ExecEdge) ZoneId(java.time.ZoneId) WindowAttachedWindowingStrategy(org.apache.flink.table.planner.plan.logical.WindowAttachedWindowingStrategy) RowType(org.apache.flink.table.types.logical.RowType) RowData(org.apache.flink.table.data.RowData) GeneratedJoinCondition(org.apache.flink.table.runtime.generated.GeneratedJoinCondition) RowDataKeySelector(org.apache.flink.table.runtime.keyselector.RowDataKeySelector) WindowJoinOperator(org.apache.flink.table.runtime.operators.join.window.WindowJoinOperator)

Example 57 with ExecEdge

use of org.apache.flink.table.planner.plan.nodes.exec.ExecEdge in project flink by apache.

the class StreamExecLocalWindowAggregate method translateToPlanInternal.

@SuppressWarnings("unchecked")
@Override
protected Transformation<RowData> translateToPlanInternal(PlannerBase planner, ExecNodeConfig config) {
    final ExecEdge inputEdge = getInputEdges().get(0);
    final Transformation<RowData> inputTransform = (Transformation<RowData>) inputEdge.translateToPlan(planner);
    final RowType inputRowType = (RowType) inputEdge.getOutputType();
    final ZoneId shiftTimeZone = TimeWindowUtil.getShiftTimeZone(windowing.getTimeAttributeType(), config.getLocalTimeZone());
    final SliceAssigner sliceAssigner = createSliceAssigner(windowing, shiftTimeZone);
    final AggregateInfoList aggInfoList = AggregateUtil.deriveStreamWindowAggregateInfoList(inputRowType, JavaScalaConversionUtil.toScala(Arrays.asList(aggCalls)), windowing.getWindow(), // isStateBackendDataViews
    false);
    final GeneratedNamespaceAggsHandleFunction<Long> generatedAggsHandler = createAggsHandler(sliceAssigner, aggInfoList, config, planner.getRelBuilder(), inputRowType.getChildren(), shiftTimeZone);
    final RowDataKeySelector selector = KeySelectorUtil.getRowDataSelector(grouping, InternalTypeInfo.of(inputRowType));
    PagedTypeSerializer<RowData> keySer = (PagedTypeSerializer<RowData>) selector.getProducedType().toSerializer();
    AbstractRowDataSerializer<RowData> valueSer = new RowDataSerializer(inputRowType);
    WindowBuffer.LocalFactory bufferFactory = new RecordsWindowBuffer.LocalFactory(keySer, valueSer, new LocalAggCombiner.Factory(generatedAggsHandler));
    final OneInputStreamOperator<RowData, RowData> localAggOperator = new LocalSlicingWindowAggOperator(selector, sliceAssigner, bufferFactory, shiftTimeZone);
    return ExecNodeUtil.createOneInputTransformation(inputTransform, createTransformationMeta(LOCAL_WINDOW_AGGREGATE_TRANSFORMATION, config), SimpleOperatorFactory.of(localAggOperator), InternalTypeInfo.of(getOutputType()), inputTransform.getParallelism(), // use less memory here to let the chained head operator can have more memory
    WINDOW_AGG_MEMORY_RATIO / 2);
}
Also used : SliceAssigner(org.apache.flink.table.runtime.operators.window.slicing.SliceAssigner) Transformation(org.apache.flink.api.dag.Transformation) AggregateInfoList(org.apache.flink.table.planner.plan.utils.AggregateInfoList) ExecEdge(org.apache.flink.table.planner.plan.nodes.exec.ExecEdge) ZoneId(java.time.ZoneId) LocalAggCombiner(org.apache.flink.table.runtime.operators.aggregate.window.combines.LocalAggCombiner) RowType(org.apache.flink.table.types.logical.RowType) WindowBuffer(org.apache.flink.table.runtime.operators.aggregate.window.buffers.WindowBuffer) RecordsWindowBuffer(org.apache.flink.table.runtime.operators.aggregate.window.buffers.RecordsWindowBuffer) RowData(org.apache.flink.table.data.RowData) PagedTypeSerializer(org.apache.flink.table.runtime.typeutils.PagedTypeSerializer) RowDataKeySelector(org.apache.flink.table.runtime.keyselector.RowDataKeySelector) LocalSlicingWindowAggOperator(org.apache.flink.table.runtime.operators.aggregate.window.LocalSlicingWindowAggOperator) RowDataSerializer(org.apache.flink.table.runtime.typeutils.RowDataSerializer) AbstractRowDataSerializer(org.apache.flink.table.runtime.typeutils.AbstractRowDataSerializer)

Example 58 with ExecEdge

use of org.apache.flink.table.planner.plan.nodes.exec.ExecEdge in project flink by apache.

the class StreamExecPythonGroupTableAggregate method translateToPlanInternal.

@SuppressWarnings("unchecked")
@Override
protected Transformation<RowData> translateToPlanInternal(PlannerBase planner, ExecNodeConfig config) {
    if (grouping.length > 0 && config.getStateRetentionTime() < 0) {
        LOG.warn("No state retention interval configured for a query which accumulates state. " + "Please provide a query configuration with valid retention interval " + "to prevent excessive state size. You may specify a retention time " + "of 0 to not clean up the state.");
    }
    final ExecEdge inputEdge = getInputEdges().get(0);
    final Transformation<RowData> inputTransform = (Transformation<RowData>) inputEdge.translateToPlan(planner);
    final RowType inputRowType = (RowType) inputEdge.getOutputType();
    final AggregateInfoList aggInfoList = AggregateUtil.transformToStreamAggregateInfoList(inputRowType, JavaScalaConversionUtil.toScala(Arrays.asList(aggCalls)), aggCallNeedRetractions, needRetraction, // isStateBackendDataViews
    true, // needDistinctInfo
    true);
    int inputCountIndex = aggInfoList.getIndexOfCountStar();
    Tuple2<PythonAggregateFunctionInfo[], DataViewSpec[][]> aggInfosAndDataViewSpecs = CommonPythonUtil.extractPythonAggregateFunctionInfos(aggInfoList, aggCalls);
    PythonAggregateFunctionInfo[] pythonFunctionInfos = aggInfosAndDataViewSpecs.f0;
    DataViewSpec[][] dataViewSpecs = aggInfosAndDataViewSpecs.f1;
    Configuration pythonConfig = CommonPythonUtil.getMergedConfig(planner.getExecEnv(), config.getTableConfig());
    OneInputStreamOperator<RowData, RowData> pythonOperator = getPythonTableAggregateFunctionOperator(pythonConfig, inputRowType, InternalTypeInfo.of(getOutputType()).toRowType(), pythonFunctionInfos, dataViewSpecs, config.getStateRetentionTime(), config.getMaxIdleStateRetentionTime(), generateUpdateBefore, inputCountIndex);
    OneInputTransformation<RowData, RowData> transform = ExecNodeUtil.createOneInputTransformation(inputTransform, createTransformationName(config), createTransformationDescription(config), pythonOperator, InternalTypeInfo.of(getOutputType()), inputTransform.getParallelism());
    if (CommonPythonUtil.isPythonWorkerUsingManagedMemory(pythonConfig)) {
        transform.declareManagedMemoryUseCaseAtSlotScope(ManagedMemoryUseCase.PYTHON);
    }
    // set KeyType and Selector for state
    final RowDataKeySelector selector = KeySelectorUtil.getRowDataSelector(grouping, InternalTypeInfo.of(inputRowType));
    transform.setStateKeySelector(selector);
    transform.setStateKeyType(selector.getProducedType());
    return transform;
}
Also used : OneInputTransformation(org.apache.flink.streaming.api.transformations.OneInputTransformation) Transformation(org.apache.flink.api.dag.Transformation) AggregateInfoList(org.apache.flink.table.planner.plan.utils.AggregateInfoList) ExecEdge(org.apache.flink.table.planner.plan.nodes.exec.ExecEdge) DataViewSpec(org.apache.flink.table.runtime.dataview.DataViewSpec) Configuration(org.apache.flink.configuration.Configuration) RowType(org.apache.flink.table.types.logical.RowType) RowData(org.apache.flink.table.data.RowData) PythonAggregateFunctionInfo(org.apache.flink.table.functions.python.PythonAggregateFunctionInfo) RowDataKeySelector(org.apache.flink.table.runtime.keyselector.RowDataKeySelector)

Example 59 with ExecEdge

use of org.apache.flink.table.planner.plan.nodes.exec.ExecEdge in project flink by apache.

the class StreamExecWindowDeduplicate method translateToPlanInternal.

@SuppressWarnings("unchecked")
@Override
protected Transformation<RowData> translateToPlanInternal(PlannerBase planner, ExecNodeConfig config) {
    // validate window strategy
    if (!windowing.isRowtime()) {
        throw new TableException("Processing time Window Deduplication is not supported yet.");
    }
    int windowEndIndex;
    if (windowing instanceof WindowAttachedWindowingStrategy) {
        windowEndIndex = ((WindowAttachedWindowingStrategy) windowing).getWindowEnd();
    } else {
        throw new UnsupportedOperationException(windowing.getClass().getName() + " is not supported yet.");
    }
    ExecEdge inputEdge = getInputEdges().get(0);
    Transformation<RowData> inputTransform = (Transformation<RowData>) inputEdge.translateToPlan(planner);
    ZoneId shiftTimeZone = TimeWindowUtil.getShiftTimeZone(windowing.getTimeAttributeType(), config.getLocalTimeZone());
    RowType inputType = (RowType) inputEdge.getOutputType();
    RowDataKeySelector selector = KeySelectorUtil.getRowDataSelector(partitionKeys, InternalTypeInfo.of(inputType));
    OneInputStreamOperator<RowData, RowData> operator = RowTimeWindowDeduplicateOperatorBuilder.builder().inputSerializer(new RowDataSerializer(inputType)).shiftTimeZone(shiftTimeZone).keySerializer((PagedTypeSerializer<RowData>) selector.getProducedType().toSerializer()).keepLastRow(keepLastRow).rowtimeIndex(orderKey).windowEndIndex(windowEndIndex).build();
    OneInputTransformation<RowData, RowData> transform = ExecNodeUtil.createOneInputTransformation(inputTransform, createTransformationMeta(WINDOW_DEDUPLICATE_TRANSFORMATION, config), SimpleOperatorFactory.of(operator), InternalTypeInfo.of(getOutputType()), inputTransform.getParallelism(), WINDOW_RANK_MEMORY_RATIO);
    // set KeyType and Selector for state
    transform.setStateKeySelector(selector);
    transform.setStateKeyType(selector.getProducedType());
    return transform;
}
Also used : TableException(org.apache.flink.table.api.TableException) OneInputTransformation(org.apache.flink.streaming.api.transformations.OneInputTransformation) Transformation(org.apache.flink.api.dag.Transformation) ExecEdge(org.apache.flink.table.planner.plan.nodes.exec.ExecEdge) ZoneId(java.time.ZoneId) WindowAttachedWindowingStrategy(org.apache.flink.table.planner.plan.logical.WindowAttachedWindowingStrategy) RowType(org.apache.flink.table.types.logical.RowType) RowData(org.apache.flink.table.data.RowData) RowDataKeySelector(org.apache.flink.table.runtime.keyselector.RowDataKeySelector) RowDataSerializer(org.apache.flink.table.runtime.typeutils.RowDataSerializer)

Example 60 with ExecEdge

use of org.apache.flink.table.planner.plan.nodes.exec.ExecEdge in project flink by apache.

the class StreamExecWindowRank method translateToPlanInternal.

@SuppressWarnings("unchecked")
@Override
protected Transformation<RowData> translateToPlanInternal(PlannerBase planner, ExecNodeConfig config) {
    // validate rank type
    switch(rankType) {
        case ROW_NUMBER:
            break;
        case RANK:
            throw new TableException("RANK() function is not supported on Window TopN currently, only ROW_NUMBER() is supported.");
        case DENSE_RANK:
            throw new TableException("DENSE_RANK() function is not supported on Window TopN currently, only ROW_NUMBER() is supported.");
        default:
            throw new TableException(String.format("%s() function is not supported on Window TopN currently, only ROW_NUMBER() is supported.", rankType));
    }
    // validate window strategy
    if (!windowing.isRowtime()) {
        throw new TableException("Processing time Window TopN is not supported yet.");
    }
    int windowEndIndex;
    if (windowing instanceof WindowAttachedWindowingStrategy) {
        windowEndIndex = ((WindowAttachedWindowingStrategy) windowing).getWindowEnd();
    } else {
        throw new UnsupportedOperationException(windowing.getClass().getName() + " is not supported yet.");
    }
    ExecEdge inputEdge = getInputEdges().get(0);
    RowType inputType = (RowType) inputEdge.getOutputType();
    // validate rank range
    ConstantRankRange constantRankRange;
    if (rankRange instanceof ConstantRankRange) {
        constantRankRange = (ConstantRankRange) rankRange;
    } else {
        throw new TableException(String.format("Rank strategy %s is not supported on window rank currently.", rankRange.toString(inputType.getFieldNames())));
    }
    Transformation<RowData> inputTransform = (Transformation<RowData>) inputEdge.translateToPlan(planner);
    InternalTypeInfo<RowData> inputRowTypeInfo = InternalTypeInfo.of(inputType);
    int[] sortFields = sortSpec.getFieldIndices();
    RowDataKeySelector sortKeySelector = KeySelectorUtil.getRowDataSelector(sortFields, inputRowTypeInfo);
    SortSpec.SortSpecBuilder builder = SortSpec.builder();
    IntStream.range(0, sortFields.length).forEach(idx -> builder.addField(idx, sortSpec.getFieldSpec(idx).getIsAscendingOrder(), sortSpec.getFieldSpec(idx).getNullIsLast()));
    SortSpec sortSpecInSortKey = builder.build();
    ZoneId shiftTimeZone = TimeWindowUtil.getShiftTimeZone(windowing.getTimeAttributeType(), config.getLocalTimeZone());
    GeneratedRecordComparator sortKeyComparator = ComparatorCodeGenerator.gen(config.getTableConfig(), "StreamExecSortComparator", RowType.of(sortSpec.getFieldTypes(inputType)), sortSpecInSortKey);
    RowDataKeySelector selector = KeySelectorUtil.getRowDataSelector(partitionSpec.getFieldIndices(), inputRowTypeInfo);
    OneInputStreamOperator<RowData, RowData> operator = WindowRankOperatorBuilder.builder().inputSerializer(new RowDataSerializer(inputType)).shiftTimeZone(shiftTimeZone).keySerializer((PagedTypeSerializer<RowData>) selector.getProducedType().toSerializer()).sortKeySelector(sortKeySelector).sortKeyComparator(sortKeyComparator).outputRankNumber(outputRankNumber).rankStart(constantRankRange.getRankStart()).rankEnd(constantRankRange.getRankEnd()).windowEndIndex(windowEndIndex).build();
    OneInputTransformation<RowData, RowData> transform = ExecNodeUtil.createOneInputTransformation(inputTransform, createTransformationMeta(WINDOW_RANK_TRANSFORMATION, config), SimpleOperatorFactory.of(operator), InternalTypeInfo.of(getOutputType()), inputTransform.getParallelism(), WINDOW_RANK_MEMORY_RATIO);
    // set KeyType and Selector for state
    transform.setStateKeySelector(selector);
    transform.setStateKeyType(selector.getProducedType());
    return transform;
}
Also used : TableException(org.apache.flink.table.api.TableException) OneInputTransformation(org.apache.flink.streaming.api.transformations.OneInputTransformation) Transformation(org.apache.flink.api.dag.Transformation) ExecEdge(org.apache.flink.table.planner.plan.nodes.exec.ExecEdge) ZoneId(java.time.ZoneId) ConstantRankRange(org.apache.flink.table.runtime.operators.rank.ConstantRankRange) WindowAttachedWindowingStrategy(org.apache.flink.table.planner.plan.logical.WindowAttachedWindowingStrategy) RowType(org.apache.flink.table.types.logical.RowType) RowData(org.apache.flink.table.data.RowData) PagedTypeSerializer(org.apache.flink.table.runtime.typeutils.PagedTypeSerializer) RowDataKeySelector(org.apache.flink.table.runtime.keyselector.RowDataKeySelector) GeneratedRecordComparator(org.apache.flink.table.runtime.generated.GeneratedRecordComparator) SortSpec(org.apache.flink.table.planner.plan.nodes.exec.spec.SortSpec) RowDataSerializer(org.apache.flink.table.runtime.typeutils.RowDataSerializer)

Aggregations

ExecEdge (org.apache.flink.table.planner.plan.nodes.exec.ExecEdge)65 Transformation (org.apache.flink.api.dag.Transformation)52 RowData (org.apache.flink.table.data.RowData)52 RowType (org.apache.flink.table.types.logical.RowType)42 OneInputTransformation (org.apache.flink.streaming.api.transformations.OneInputTransformation)25 RowDataKeySelector (org.apache.flink.table.runtime.keyselector.RowDataKeySelector)24 TableException (org.apache.flink.table.api.TableException)21 CodeGeneratorContext (org.apache.flink.table.planner.codegen.CodeGeneratorContext)18 AggregateInfoList (org.apache.flink.table.planner.plan.utils.AggregateInfoList)17 LogicalType (org.apache.flink.table.types.logical.LogicalType)14 ArrayList (java.util.ArrayList)12 InputProperty (org.apache.flink.table.planner.plan.nodes.exec.InputProperty)11 Configuration (org.apache.flink.configuration.Configuration)10 ExecNode (org.apache.flink.table.planner.plan.nodes.exec.ExecNode)10 ZoneId (java.time.ZoneId)9 List (java.util.List)5 EqualiserCodeGenerator (org.apache.flink.table.planner.codegen.EqualiserCodeGenerator)5 AggsHandlerCodeGenerator (org.apache.flink.table.planner.codegen.agg.AggsHandlerCodeGenerator)5 GeneratedAggsHandleFunction (org.apache.flink.table.runtime.generated.GeneratedAggsHandleFunction)5 GeneratedJoinCondition (org.apache.flink.table.runtime.generated.GeneratedJoinCondition)5