HeartSaVioR commented on code in PR #44884:
URL: https://github.com/apache/spark/pull/44884#discussion_r1473467963
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/TransformWithStateExec.scala:
##########
@@ -171,3 +175,44 @@ case class TransformWithStateExec(
}
}
}
+
+
+object TransformWithStateExec {
+
+ // Plan logical transformWithState for batch queries
+ def generateSparkPlanForBatchQueries(
+ keyDeserializer: Expression,
+ valueDeserializer: Expression,
+ groupingAttributes: Seq[Attribute],
+ dataAttributes: Seq[Attribute],
+ statefulProcessor: StatefulProcessor[Any, Any, Any],
+ timeoutMode: TimeoutMode,
+ outputMode: OutputMode,
+ outputObjAttr: Attribute,
+ child: SparkPlan): SparkPlan = {
+ val shufflePartitions =
child.session.sessionState.conf.numShufflePartitions
+ val statefulOperatorStateInfo = StatefulOperatorStateInfo(
+ Utils.createTempDir().getAbsolutePath,
Review Comment:
> Do we see a usecase where the user would want to read the State files
(from DFS) post query?
It could be, but let's keep the common UX for batch query.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
