use of org.apache.flink.table.runtime.operators.window.assigners.WindowAssigner in project flink by apache.
the class StreamExecPythonGroupWindowAggregate method getGeneralPythonStreamGroupWindowAggregateFunctionOperator.
@SuppressWarnings({ "unchecked", "rawtypes" })
private OneInputStreamOperator<RowData, RowData> getGeneralPythonStreamGroupWindowAggregateFunctionOperator(Configuration config, RowType inputType, RowType outputType, WindowAssigner<?> windowAssigner, PythonAggregateFunctionInfo[] aggregateFunctions, DataViewSpec[][] dataViewSpecs, int inputTimeFieldIndex, int indexOfCountStar, boolean generateUpdateBefore, boolean countStarInserted, long allowance, ZoneId shiftTimeZone) {
Class clazz = CommonPythonUtil.loadClass(GENERAL_STREAM_PYTHON_GROUP_WINDOW_AGGREGATE_FUNCTION_OPERATOR_NAME);
boolean isRowTime = AggregateUtil.isRowtimeAttribute(window.timeAttribute());
try {
if (window instanceof TumblingGroupWindow) {
ValueLiteralExpression size = ((TumblingGroupWindow) window).size();
Method create = clazz.getMethod(GENERAL_STREAM_PYTHON_CREATE_TUMBLING_GROUP_WINDOW_METHOD, Configuration.class, RowType.class, RowType.class, PythonAggregateFunctionInfo[].class, DataViewSpec[][].class, int[].class, int.class, boolean.class, boolean.class, int.class, WindowAssigner.class, boolean.class, boolean.class, long.class, long.class, NamedWindowProperty[].class, ZoneId.class);
return (OneInputStreamOperator<RowData, RowData>) create.invoke(null, config, inputType, outputType, aggregateFunctions, dataViewSpecs, grouping, indexOfCountStar, generateUpdateBefore, countStarInserted, inputTimeFieldIndex, windowAssigner, isRowTime, AggregateUtil.hasTimeIntervalType(size), AggregateUtil.toDuration(size).toMillis(), allowance, namedWindowProperties, shiftTimeZone);
} else if (window instanceof SlidingGroupWindow) {
ValueLiteralExpression size = ((SlidingGroupWindow) window).size();
ValueLiteralExpression slide = ((SlidingGroupWindow) window).slide();
Method create = clazz.getMethod(GENERAL_STREAM_PYTHON_CREATE_SLIDING_GROUP_WINDOW_METHOD, Configuration.class, RowType.class, RowType.class, PythonAggregateFunctionInfo[].class, DataViewSpec[][].class, int[].class, int.class, boolean.class, boolean.class, int.class, WindowAssigner.class, boolean.class, boolean.class, long.class, long.class, long.class, NamedWindowProperty[].class, ZoneId.class);
return (OneInputStreamOperator<RowData, RowData>) create.invoke(null, config, inputType, outputType, aggregateFunctions, dataViewSpecs, grouping, indexOfCountStar, generateUpdateBefore, countStarInserted, inputTimeFieldIndex, windowAssigner, isRowTime, AggregateUtil.hasTimeIntervalType(size), AggregateUtil.toDuration(size).toMillis(), AggregateUtil.toDuration(slide).toMillis(), allowance, namedWindowProperties, shiftTimeZone);
} else if (window instanceof SessionGroupWindow) {
ValueLiteralExpression gap = ((SessionGroupWindow) window).gap();
Method create = clazz.getMethod(GENERAL_STREAM_PYTHON_CREATE_SESSION_GROUP_WINDOW_METHOD, Configuration.class, RowType.class, RowType.class, PythonAggregateFunctionInfo[].class, DataViewSpec[][].class, int[].class, int.class, boolean.class, boolean.class, int.class, WindowAssigner.class, boolean.class, long.class, long.class, NamedWindowProperty[].class, ZoneId.class);
return (OneInputStreamOperator<RowData, RowData>) create.invoke(null, config, inputType, outputType, aggregateFunctions, dataViewSpecs, grouping, indexOfCountStar, generateUpdateBefore, countStarInserted, inputTimeFieldIndex, windowAssigner, isRowTime, AggregateUtil.toDuration(gap).toMillis(), allowance, namedWindowProperties, shiftTimeZone);
}
} catch (NoSuchMethodException | IllegalAccessException | InvocationTargetException e) {
throw new TableException("Python PythonStreamGroupWindowAggregateOperator constructed failed.", e);
}
throw new RuntimeException(String.format("Unsupported LogicWindow Type %s", window));
}
use of org.apache.flink.table.runtime.operators.window.assigners.WindowAssigner 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;
}
Aggregations