Github user fhueske commented on a diff in the pull request:
https://github.com/apache/flink/pull/3550#discussion_r107020630
--- Diff:
flink-libraries/flink-table/src/main/scala/org/apache/flink/table/plan/nodes/datastream/DataStreamOverAggregate.scala
---
@@ -119,6 +152,60 @@ class DataStreamOverAggregate(
}
+ def createTimeBoundedProcessingTimeOverWindow(inputDS: DataStream[Row]):
DataStream[Row] = {
+
+ val overWindow: Group = logicWindow.groups.get(0)
+ val partitionKeys: Array[Int] = overWindow.keys.toArray
+ val namedAggregates: Seq[CalcitePair[AggregateCall, String]] =
generateNamedAggregates
+
+ val index =
overWindow.lowerBound.getOffset.asInstanceOf[RexInputRef].getIndex
+ val count = input.getRowType().getFieldCount()
+ val lowerboundIndex = index - count
+
+
+ val time_boundary =
logicWindow.constants.get(lowerboundIndex).getValue2 match {
+ case _: java.math.BigDecimal =>
logicWindow.constants.get(lowerboundIndex)
+ .getValue2.asInstanceOf[java.math.BigDecimal].longValue()
+ case _ => throw new TableException("OVER Window boundaries must be
numeric")
+ }
+
+ val (aggFields, aggregates) =
AggregateUtil.transformToAggregateFunctions(
+ namedAggregates.map(_.getKey),inputType, needRetraction = false)
+
+
+ // As we it is not possible to operate neither on sliding count neither
+ // on sliding time we need to manage the eviction of the events that
+ // expire ourselves based on the proctime (system time).
+
+ // get the output types
+ val rowTypeInfo =
FlinkTypeFactory.toInternalRowTypeInfo(getRowType).asInstanceOf[RowTypeInfo]
+
+ val result: DataStream[Row] =
+ if (partitionKeys.nonEmpty) {
+ inputDS.keyBy(partitionKeys:_*)
+ .window(GlobalWindows.create())
+ .trigger(CountTrigger.of(1))
+ .evictor(TimeEvictor.of(Time.milliseconds(time_boundary)))
+ .apply(new
DataStreamProcTimeAggregateWindowFunction[GlobalWindow]
+ (aggregates,aggFields,inputType.getFieldCount))
+ .returns(rowTypeInfo)
+ .name(aggOpName)
+ .asInstanceOf[DataStream[Row]]
+
+ } else {
+
inputDS.windowAll(GlobalWindows.create()).trigger(CountTrigger.of(1))
+ .evictor(TimeEvictor.of(Time.milliseconds(time_boundary)))
+ .apply(new
DataStreamProcTimeAggregateGlobalWindowFunction[GlobalWindow](
+ aggregates,aggFields,inputType.getFieldCount))
+ .setParallelism(1)
--- End diff --
`windowAll` is always executed with parallelism 1
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
