jingz-db commented on code in PR #48124:
URL: https://github.com/apache/spark/pull/48124#discussion_r1837408393
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/python/TransformWithStateInPandasExec.scala:
##########
@@ -191,8 +223,15 @@ case class TransformWithStateInPandasExec(
val updatesStartTimeNs = currentTimeNs
val (dedupAttributes, argOffsets) = resolveArgOffsets(child.output,
groupingAttributes)
- val data =
- groupAndProject(dataIterator, groupingAttributes, child.output,
dedupAttributes)
+ // If timeout is based on event time, then filter late data based on
watermark
+ val filteredIter = watermarkPredicateForDataForLateEvents match {
Review Comment:
Included a check on eviction of late events in the test case.
--
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]
