Search in sources :

Example 6 with TwoInputTransformation

use of org.apache.flink.streaming.api.transformations.TwoInputTransformation 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 7 with TwoInputTransformation

use of org.apache.flink.streaming.api.transformations.TwoInputTransformation in project flink by apache.

the class StreamExecIntervalJoin method translateToPlanInternal.

@Override
@SuppressWarnings("unchecked")
protected Transformation<RowData> translateToPlanInternal(PlannerBase planner, ExecNodeConfig config) {
    ExecEdge leftInputEdge = getInputEdges().get(0);
    ExecEdge rightInputEdge = getInputEdges().get(1);
    RowType leftRowType = (RowType) leftInputEdge.getOutputType();
    RowType rightRowType = (RowType) rightInputEdge.getOutputType();
    Transformation<RowData> leftInputTransform = (Transformation<RowData>) leftInputEdge.translateToPlan(planner);
    Transformation<RowData> rightInputTransform = (Transformation<RowData>) rightInputEdge.translateToPlan(planner);
    RowType returnType = (RowType) getOutputType();
    InternalTypeInfo<RowData> returnTypeInfo = InternalTypeInfo.of(returnType);
    JoinSpec joinSpec = intervalJoinSpec.getJoinSpec();
    IntervalJoinSpec.WindowBounds windowBounds = intervalJoinSpec.getWindowBounds();
    switch(joinSpec.getJoinType()) {
        case INNER:
        case LEFT:
        case RIGHT:
        case FULL:
            long relativeWindowSize = windowBounds.getLeftUpperBound() - windowBounds.getLeftLowerBound();
            if (relativeWindowSize < 0) {
                LOGGER.warn("The relative time interval size " + relativeWindowSize + "is negative, please check the join conditions.");
                return createNegativeWindowSizeJoin(joinSpec, leftInputTransform, rightInputTransform, leftRowType.getFieldCount(), rightRowType.getFieldCount(), returnTypeInfo, config);
            } else {
                GeneratedJoinCondition joinCondition = JoinUtil.generateConditionFunction(config.getTableConfig(), joinSpec, leftRowType, rightRowType);
                IntervalJoinFunction joinFunction = new IntervalJoinFunction(joinCondition, returnTypeInfo, joinSpec.getFilterNulls());
                TwoInputTransformation<RowData, RowData, RowData> transform;
                if (windowBounds.isEventTime()) {
                    transform = createRowTimeJoin(leftInputTransform, rightInputTransform, returnTypeInfo, joinFunction, joinSpec, windowBounds, config);
                } else {
                    transform = createProcTimeJoin(leftInputTransform, rightInputTransform, returnTypeInfo, joinFunction, joinSpec, windowBounds, config);
                }
                if (inputsContainSingleton()) {
                    transform.setParallelism(1);
                    transform.setMaxParallelism(1);
                }
                // set KeyType and Selector for state
                RowDataKeySelector leftSelect = KeySelectorUtil.getRowDataSelector(joinSpec.getLeftKeys(), InternalTypeInfo.of(leftRowType));
                RowDataKeySelector rightSelect = KeySelectorUtil.getRowDataSelector(joinSpec.getRightKeys(), InternalTypeInfo.of(rightRowType));
                transform.setStateKeySelectors(leftSelect, rightSelect);
                transform.setStateKeyType(leftSelect.getProducedType());
                return transform;
            }
        default:
            throw new TableException("Interval Join: " + joinSpec.getJoinType() + " Join between stream " + "and stream is not supported yet.\nplease re-check " + "interval join statement according to description above.");
    }
}
Also used : TwoInputTransformation(org.apache.flink.streaming.api.transformations.TwoInputTransformation) UnionTransformation(org.apache.flink.streaming.api.transformations.UnionTransformation) OneInputTransformation(org.apache.flink.streaming.api.transformations.OneInputTransformation) Transformation(org.apache.flink.api.dag.Transformation) TableException(org.apache.flink.table.api.TableException) ExecEdge(org.apache.flink.table.planner.plan.nodes.exec.ExecEdge) JoinSpec(org.apache.flink.table.planner.plan.nodes.exec.spec.JoinSpec) IntervalJoinSpec(org.apache.flink.table.planner.plan.nodes.exec.spec.IntervalJoinSpec) RowType(org.apache.flink.table.types.logical.RowType) IntervalJoinFunction(org.apache.flink.table.runtime.operators.join.interval.IntervalJoinFunction) RowData(org.apache.flink.table.data.RowData) GeneratedJoinCondition(org.apache.flink.table.runtime.generated.GeneratedJoinCondition) RowDataKeySelector(org.apache.flink.table.runtime.keyselector.RowDataKeySelector) IntervalJoinSpec(org.apache.flink.table.planner.plan.nodes.exec.spec.IntervalJoinSpec)

Example 8 with TwoInputTransformation

use of org.apache.flink.streaming.api.transformations.TwoInputTransformation in project flink by apache.

the class StreamExecJoin method translateToPlanInternal.

@Override
@SuppressWarnings("unchecked")
protected Transformation<RowData> translateToPlanInternal(PlannerBase planner, ExecNodeConfig config) {
    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 JoinInputSideSpec leftInputSpec = JoinUtil.analyzeJoinInput(leftTypeInfo, leftJoinKey, leftUniqueKeys);
    final InternalTypeInfo<RowData> rightTypeInfo = InternalTypeInfo.of(rightType);
    final JoinInputSideSpec rightInputSpec = JoinUtil.analyzeJoinInput(rightTypeInfo, rightJoinKey, rightUniqueKeys);
    GeneratedJoinCondition generatedCondition = JoinUtil.generateConditionFunction(config.getTableConfig(), joinSpec, leftType, rightType);
    long minRetentionTime = config.getStateRetentionTime();
    AbstractStreamingJoinOperator operator;
    FlinkJoinType joinType = joinSpec.getJoinType();
    if (joinType == FlinkJoinType.ANTI || joinType == FlinkJoinType.SEMI) {
        operator = new StreamingSemiAntiJoinOperator(joinType == FlinkJoinType.ANTI, leftTypeInfo, rightTypeInfo, generatedCondition, leftInputSpec, rightInputSpec, joinSpec.getFilterNulls(), minRetentionTime);
    } else {
        boolean leftIsOuter = joinType == FlinkJoinType.LEFT || joinType == FlinkJoinType.FULL;
        boolean rightIsOuter = joinType == FlinkJoinType.RIGHT || joinType == FlinkJoinType.FULL;
        operator = new StreamingJoinOperator(leftTypeInfo, rightTypeInfo, generatedCondition, leftInputSpec, rightInputSpec, leftIsOuter, rightIsOuter, joinSpec.getFilterNulls(), minRetentionTime);
    }
    final RowType returnType = (RowType) getOutputType();
    final TwoInputTransformation<RowData, RowData, RowData> transform = ExecNodeUtil.createTwoInputTransformation(leftTransform, rightTransform, createTransformationMeta(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) RowType(org.apache.flink.table.types.logical.RowType) FlinkJoinType(org.apache.flink.table.runtime.operators.join.FlinkJoinType) JoinInputSideSpec(org.apache.flink.table.runtime.operators.join.stream.state.JoinInputSideSpec) RowData(org.apache.flink.table.data.RowData) GeneratedJoinCondition(org.apache.flink.table.runtime.generated.GeneratedJoinCondition) AbstractStreamingJoinOperator(org.apache.flink.table.runtime.operators.join.stream.AbstractStreamingJoinOperator) StreamingJoinOperator(org.apache.flink.table.runtime.operators.join.stream.StreamingJoinOperator) RowDataKeySelector(org.apache.flink.table.runtime.keyselector.RowDataKeySelector) AbstractStreamingJoinOperator(org.apache.flink.table.runtime.operators.join.stream.AbstractStreamingJoinOperator) StreamingSemiAntiJoinOperator(org.apache.flink.table.runtime.operators.join.stream.StreamingSemiAntiJoinOperator)

Example 9 with TwoInputTransformation

use of org.apache.flink.streaming.api.transformations.TwoInputTransformation in project flink by apache.

the class StreamExecTemporalJoin method translateToPlanInternal.

@Override
@SuppressWarnings("unchecked")
protected Transformation<RowData> translateToPlanInternal(PlannerBase planner, ExecNodeConfig config) {
    ExecEdge leftInputEdge = getInputEdges().get(0);
    ExecEdge rightInputEdge = getInputEdges().get(1);
    RowType leftInputType = (RowType) leftInputEdge.getOutputType();
    RowType rightInputType = (RowType) rightInputEdge.getOutputType();
    JoinUtil.validateJoinSpec(joinSpec, leftInputType, rightInputType, true);
    FlinkJoinType joinType = joinSpec.getJoinType();
    if (isTemporalFunctionJoin) {
        if (joinType != FlinkJoinType.INNER) {
            throw new ValidationException("Temporal table function join currently only support INNER JOIN, " + "but was " + joinType + " JOIN.");
        }
    } else {
        if (joinType != FlinkJoinType.LEFT && joinType != FlinkJoinType.INNER) {
            throw new TableException("Temporal table join currently only support INNER JOIN and LEFT JOIN, " + "but was " + joinType + " JOIN.");
        }
    }
    RowType returnType = (RowType) getOutputType();
    TwoInputStreamOperator<RowData, RowData, RowData> joinOperator = getJoinOperator(config, leftInputType, rightInputType);
    Transformation<RowData> leftTransform = (Transformation<RowData>) leftInputEdge.translateToPlan(planner);
    Transformation<RowData> rightTransform = (Transformation<RowData>) rightInputEdge.translateToPlan(planner);
    TwoInputTransformation<RowData, RowData, RowData> ret = ExecNodeUtil.createTwoInputTransformation(leftTransform, rightTransform, createTransformationMeta(TEMPORAL_JOIN_TRANSFORMATION, config), joinOperator, InternalTypeInfo.of(returnType), leftTransform.getParallelism());
    // set KeyType and Selector for state
    RowDataKeySelector leftKeySelector = getLeftKeySelector(leftInputType);
    RowDataKeySelector rightKeySelector = getRightKeySelector(rightInputType);
    ret.setStateKeySelectors(leftKeySelector, rightKeySelector);
    ret.setStateKeyType(leftKeySelector.getProducedType());
    return ret;
}
Also used : TableException(org.apache.flink.table.api.TableException) RowData(org.apache.flink.table.data.RowData) TwoInputTransformation(org.apache.flink.streaming.api.transformations.TwoInputTransformation) Transformation(org.apache.flink.api.dag.Transformation) ValidationException(org.apache.flink.table.api.ValidationException) ExecEdge(org.apache.flink.table.planner.plan.nodes.exec.ExecEdge) RowDataKeySelector(org.apache.flink.table.runtime.keyselector.RowDataKeySelector) RowType(org.apache.flink.table.types.logical.RowType) FlinkJoinType(org.apache.flink.table.runtime.operators.join.FlinkJoinType)

Aggregations

TwoInputTransformation (org.apache.flink.streaming.api.transformations.TwoInputTransformation)9 Transformation (org.apache.flink.api.dag.Transformation)6 OneInputTransformation (org.apache.flink.streaming.api.transformations.OneInputTransformation)4 RowData (org.apache.flink.table.data.RowData)4 ExecEdge (org.apache.flink.table.planner.plan.nodes.exec.ExecEdge)4 RowDataKeySelector (org.apache.flink.table.runtime.keyselector.RowDataKeySelector)4 RowType (org.apache.flink.table.types.logical.RowType)4 GeneratedJoinCondition (org.apache.flink.table.runtime.generated.GeneratedJoinCondition)3 UnionTransformation (org.apache.flink.streaming.api.transformations.UnionTransformation)2 TableException (org.apache.flink.table.api.TableException)2 FlinkJoinType (org.apache.flink.table.runtime.operators.join.FlinkJoinType)2 Test (org.junit.Test)2 IOException (java.io.IOException)1 Field (java.lang.reflect.Field)1 ZoneId (java.time.ZoneId)1 ArrayList (java.util.ArrayList)1 HashMap (java.util.HashMap)1 Map (java.util.Map)1 RunnerApi (org.apache.beam.model.pipeline.v1.RunnerApi)1 SerializablePipelineOptions (org.apache.beam.runners.core.construction.SerializablePipelineOptions)1