Github user tdas commented on a diff in the pull request:
https://github.com/apache/spark/pull/16758#discussion_r98788458
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StatefulAggregate.scala
---
@@ -235,3 +240,86 @@ case class StateStoreSaveExec(
override def outputPartitioning: Partitioning = child.outputPartitioning
}
+
+
+/**
+ * Physical operator for executing streaming mapGroupsWithState.
+ */
+case class MapGroupsWithStateExec(
+ func: (Any, Iterator[Any], LogicalState[Any]) => Iterator[Any],
+ keyDeserializer: Expression, // probably not needed
+ valueDeserializer: Expression,
+ groupingAttributes: Seq[Attribute],
+ dataAttributes: Seq[Attribute],
+ outputObjAttr: Attribute,
+ stateId: Option[OperatorStateId],
+ stateDeserializer: Expression,
+ stateSerializer: Seq[NamedExpression],
+ child: SparkPlan) extends UnaryExecNode with ObjectProducerExec with
StateStoreWriter {
+
+ override def outputPartitioning: Partitioning = child.outputPartitioning
+
+ override def requiredChildDistribution: Seq[Distribution] =
+ ClusteredDistribution(groupingAttributes) :: Nil
+
+ override def requiredChildOrdering: Seq[Seq[SortOrder]] =
+ Seq(groupingAttributes.map(SortOrder(_, Ascending))) // is this
ordering needed?
--- End diff --
Thanks for confirming, will remove the comment.
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
