flink-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From fhueske <...@git.apache.org>
Subject [GitHub] flink pull request #3386: [FLINK-5658][table] support unbounded eventtime ov...
Date Fri, 17 Mar 2017 10:58:46 GMT
Github user fhueske commented on a diff in the pull request:

    https://github.com/apache/flink/pull/3386#discussion_r106620612
  
    --- Diff: flink-libraries/flink-table/src/main/scala/org/apache/flink/table/plan/nodes/datastream/DataStreamOverAggregate.scala
---
    @@ -159,6 +167,46 @@ class DataStreamOverAggregate(
         result
       }
     
    +  def createUnboundedAndCurrentRowEventTimeOverWindow(
    +    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
    +
    +    // get the output types
    +    val rowTypeInfo = FlinkTypeFactory.toInternalRowTypeInfo(getRowType).asInstanceOf[RowTypeInfo]
    +
    +    val result: DataStream[Row] =
    +      // partitioned aggregation
    +      if (partitionKeys.nonEmpty) {
    +        val keyedStream = inputDS.keyBy(partitionKeys: _*)
    +        val processFunction = AggregateUtil.CreateUnboundedEventTimeOverProcessFunction(
    +          namedAggregates,
    +          inputType)
    +
    +        keyedStream
    +          .process(processFunction)
    +          .returns(rowTypeInfo)
    +          .name(aggOpName)
    +          .asInstanceOf[DataStream[Row]]
    +      }
    +      // global non-partitioned aggregation
    +      else {
    +        val processFunction = AggregateUtil.CreateUnboundedEventTimeOverProcessFunction(
    +          namedAggregates,
    +          inputType)
    +
    +        inputDS.keyBy(new NullByteKeySelector[Row])
    +          .process(processFunction)
    +          .setParallelism(1)
    --- End diff --
    
    also `setMaxParallelism(1)` to prevent that this operator can be scaled out.


---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

Mime
View raw message