Examples with RowDataKeySelector org.apache.flink.table.runtime.keyselector.RowDataKeySelector used on opensource projects

Example 16 with RowDataKeySelector

use of org.apache.flink.table.runtime.keyselector.RowDataKeySelector in project flink by apache.

the class CommonExecSink method applyKeyBy.

/**
 * Apply a primary key partition transformation to guarantee the strict ordering of changelog
 * messages.
 */
private Transformation<RowData> applyKeyBy(ReadableConfig config, Transformation<RowData> inputTransform, int[] primaryKeys, int sinkParallelism, int inputParallelism, boolean inputInsertOnly, boolean needMaterialize) {
    final ExecutionConfigOptions.SinkKeyedShuffle sinkShuffleByPk = config.get(ExecutionConfigOptions.TABLE_EXEC_SINK_KEYED_SHUFFLE);
    boolean sinkKeyBy = false;
    switch(sinkShuffleByPk) {
        case NONE:
            break;
        case AUTO:
            sinkKeyBy = inputInsertOnly && sinkParallelism != inputParallelism;
            break;
        case FORCE:
            // single parallelism has no problem
            sinkKeyBy = sinkParallelism != 1 || inputParallelism != 1;
            break;
    }
    if (!sinkKeyBy && !needMaterialize) {
        return inputTransform;
    }
    final RowDataKeySelector selector = KeySelectorUtil.getRowDataSelector(primaryKeys, getInputTypeInfo());
    final KeyGroupStreamPartitioner<RowData, RowData> partitioner = new KeyGroupStreamPartitioner<>(selector, KeyGroupRangeAssignment.DEFAULT_LOWER_BOUND_MAX_PARALLELISM);
    Transformation<RowData> partitionedTransform = new PartitionTransformation<>(inputTransform, partitioner);
    createTransformationMeta(PARTITIONER_TRANSFORMATION, "Partitioner", "Partitioner", config).fill(partitionedTransform);
    partitionedTransform.setParallelism(sinkParallelism);
    return partitionedTransform;
}

Example 17 with RowDataKeySelector

use of org.apache.flink.table.runtime.keyselector.RowDataKeySelector in project flink by apache.

the class CommonExecSink method applyUpsertMaterialize.

private Transformation<RowData> applyUpsertMaterialize(Transformation<RowData> inputTransform, int[] primaryKeys, int sinkParallelism, ReadableConfig config, RowType physicalRowType) {
    GeneratedRecordEqualiser equaliser = new EqualiserCodeGenerator(physicalRowType).generateRecordEqualiser("SinkMaterializeEqualiser");
    SinkUpsertMaterializer operator = new SinkUpsertMaterializer(StateConfigUtil.createTtlConfig(config.get(ExecutionConfigOptions.IDLE_STATE_RETENTION).toMillis()), InternalSerializers.create(physicalRowType), equaliser);
    final String[] fieldNames = physicalRowType.getFieldNames().toArray(new String[0]);
    final List<String> pkFieldNames = Arrays.stream(primaryKeys).mapToObj(idx -> fieldNames[idx]).collect(Collectors.toList());
    OneInputTransformation<RowData, RowData> materializeTransform = ExecNodeUtil.createOneInputTransformation(inputTransform, createTransformationMeta(UPSERT_MATERIALIZE_TRANSFORMATION, String.format("SinkMaterializer(pk=[%s])", String.join(", ", pkFieldNames)), "SinkMaterializer", config), operator, inputTransform.getOutputType(), sinkParallelism);
    RowDataKeySelector keySelector = KeySelectorUtil.getRowDataSelector(primaryKeys, InternalTypeInfo.of(physicalRowType));
    materializeTransform.setStateKeySelector(keySelector);
    materializeTransform.setStateKeyType(keySelector.getProducedType());
    return materializeTransform;
}

Example 18 with RowDataKeySelector

use of org.apache.flink.table.runtime.keyselector.RowDataKeySelector in project flink by apache.

the class StreamExecChangelogNormalize 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 InternalTypeInfo<RowData> rowTypeInfo = (InternalTypeInfo<RowData>) inputTransform.getOutputType();
    final OneInputStreamOperator<RowData, RowData> operator;
    final long stateIdleTime = config.getStateRetentionTime();
    final boolean isMiniBatchEnabled = config.get(ExecutionConfigOptions.TABLE_EXEC_MINIBATCH_ENABLED);
    GeneratedRecordEqualiser generatedEqualiser = new EqualiserCodeGenerator(rowTypeInfo.toRowType()).generateRecordEqualiser("DeduplicateRowEqualiser");
    if (isMiniBatchEnabled) {
        TypeSerializer<RowData> rowSerializer = rowTypeInfo.createSerializer(planner.getExecEnv().getConfig());
        ProcTimeMiniBatchDeduplicateKeepLastRowFunction processFunction = new ProcTimeMiniBatchDeduplicateKeepLastRowFunction(rowTypeInfo, rowSerializer, stateIdleTime, generateUpdateBefore, // generateInsert
        true, // inputInsertOnly
        false, generatedEqualiser);
        CountBundleTrigger<RowData> trigger = AggregateUtil.createMiniBatchTrigger(config);
        operator = new KeyedMapBundleOperator<>(processFunction, trigger);
    } else {
        ProcTimeDeduplicateKeepLastRowFunction processFunction = new ProcTimeDeduplicateKeepLastRowFunction(rowTypeInfo, stateIdleTime, generateUpdateBefore, // generateInsert
        true, // inputInsertOnly
        false, generatedEqualiser);
        operator = new KeyedProcessOperator<>(processFunction);
    }
    final OneInputTransformation<RowData, RowData> transform = ExecNodeUtil.createOneInputTransformation(inputTransform, createTransformationMeta(CHANGELOG_NORMALIZE_TRANSFORMATION, config), operator, rowTypeInfo, inputTransform.getParallelism());
    final RowDataKeySelector selector = KeySelectorUtil.getRowDataSelector(uniqueKeys, rowTypeInfo);
    transform.setStateKeySelector(selector);
    transform.setStateKeyType(selector.getProducedType());
    return transform;
}

Example 19 with RowDataKeySelector

use of org.apache.flink.table.runtime.keyselector.RowDataKeySelector in project flink by apache.

the class StreamExecPythonGroupAggregate 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);
    final int inputCountIndex = aggInfoList.getIndexOfCountStar();
    final boolean countStarInserted = aggInfoList.countStarInserted();
    Tuple2<PythonAggregateFunctionInfo[], DataViewSpec[][]> aggInfosAndDataViewSpecs = CommonPythonUtil.extractPythonAggregateFunctionInfos(aggInfoList, aggCalls);
    PythonAggregateFunctionInfo[] pythonFunctionInfos = aggInfosAndDataViewSpecs.f0;
    DataViewSpec[][] dataViewSpecs = aggInfosAndDataViewSpecs.f1;
    Configuration pythonConfig = CommonPythonUtil.getMergedConfig(planner.getExecEnv(), config.getTableConfig());
    final OneInputStreamOperator<RowData, RowData> operator = getPythonAggregateFunctionOperator(pythonConfig, inputRowType, InternalTypeInfo.of(getOutputType()).toRowType(), pythonFunctionInfos, dataViewSpecs, config.getStateRetentionTime(), config.getMaxIdleStateRetentionTime(), inputCountIndex, countStarInserted);
    // partitioned aggregation
    OneInputTransformation<RowData, RowData> transform = ExecNodeUtil.createOneInputTransformation(inputTransform, createTransformationName(config), createTransformationDescription(config), operator, 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;
}

Example 20 with RowDataKeySelector

use of org.apache.flink.table.runtime.keyselector.RowDataKeySelector in project flink by apache.

the class StreamExecPythonGroupWindowAggregate method translateToPlanInternal.

@SuppressWarnings("unchecked")
@Override
protected Transformation<RowData> translateToPlanInternal(PlannerBase planner, ExecNodeConfig config) {
    final boolean isCountWindow;
    if (window instanceof TumblingGroupWindow) {
        isCountWindow = hasRowIntervalType(((TumblingGroupWindow) window).size());
    } else if (window instanceof SlidingGroupWindow) {
        isCountWindow = hasRowIntervalType(((SlidingGroupWindow) window).size());
    } else {
        isCountWindow = false;
    }
    if (isCountWindow && grouping.length > 0 && config.getStateRetentionTime() < 0) {
        LOGGER.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 RowType outputRowType = InternalTypeInfo.of(getOutputType()).toRowType();
    final int inputTimeFieldIndex;
    if (isRowtimeAttribute(window.timeAttribute())) {
        inputTimeFieldIndex = timeFieldIndex(FlinkTypeFactory.INSTANCE().buildRelNodeRowType(inputRowType), planner.getRelBuilder(), window.timeAttribute());
        if (inputTimeFieldIndex < 0) {
            throw new TableException("Group window must defined on a time attribute, " + "but the time attribute can't be found.\n" + "This should never happen. Please file an issue.");
        }
    } else {
        inputTimeFieldIndex = -1;
    }
    final ZoneId shiftTimeZone = TimeWindowUtil.getShiftTimeZone(window.timeAttribute().getOutputDataType().getLogicalType(), config.getLocalTimeZone());
    Tuple2<WindowAssigner<?>, Trigger<?>> windowAssignerAndTrigger = generateWindowAssignerAndTrigger();
    WindowAssigner<?> windowAssigner = windowAssignerAndTrigger.f0;
    Trigger<?> trigger = windowAssignerAndTrigger.f1;
    Configuration pythonConfig = CommonPythonUtil.getMergedConfig(planner.getExecEnv(), config.getTableConfig());
    boolean isGeneralPythonUDAF = Arrays.stream(aggCalls).anyMatch(x -> PythonUtil.isPythonAggregate(x, PythonFunctionKind.GENERAL));
    OneInputTransformation<RowData, RowData> transform;
    WindowEmitStrategy emitStrategy = WindowEmitStrategy.apply(config, window);
    if (isGeneralPythonUDAF) {
        final boolean[] aggCallNeedRetractions = new boolean[aggCalls.length];
        Arrays.fill(aggCallNeedRetractions, needRetraction);
        final AggregateInfoList aggInfoList = transformToStreamAggregateInfoList(inputRowType, JavaScalaConversionUtil.toScala(Arrays.asList(aggCalls)), aggCallNeedRetractions, needRetraction, true, true);
        transform = createGeneralPythonStreamWindowGroupOneInputTransformation(inputTransform, inputRowType, outputRowType, inputTimeFieldIndex, windowAssigner, aggInfoList, emitStrategy.getAllowLateness(), pythonConfig, shiftTimeZone);
    } else {
        transform = createPandasPythonStreamWindowGroupOneInputTransformation(inputTransform, inputRowType, outputRowType, inputTimeFieldIndex, windowAssigner, trigger, emitStrategy.getAllowLateness(), pythonConfig, config, shiftTimeZone);
    }
    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;
}