HeartSaVioR commented on a change in pull request #33081:
URL: https://github.com/apache/spark/pull/33081#discussion_r670214319
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/python/AggregateInPandasExec.scala
##########
@@ -53,12 +54,23 @@ case class AggregateInPandasExec(
override def producedAttributes: AttributeSet = AttributeSet(output)
- override def requiredChildDistribution: Seq[Distribution] = {
- if (groupingExpressions.isEmpty) {
- AllTuples :: Nil
- } else {
- ClusteredDistribution(groupingExpressions) :: Nil
- }
+ val sessionWindowOption = groupingExpressions.find { p =>
+ p.metadata.contains(SessionWindow.marker)
+ }
+
+ val groupingWithoutSessionExpressions = sessionWindowOption match {
+ case Some(sessionExpression) =>
+ groupingExpressions.filterNot { p => p.semanticEquals(sessionExpression)
}
+
+ case None => groupingExpressions
+ }
+
+ override def requiredChildOrdering: Seq[Seq[SortOrder]] =
sessionWindowOption match {
+ case Some(sessionExpression) =>
+ Seq((groupingWithoutSessionExpressions ++ Seq(sessionExpression))
+ .map(SortOrder(_, Ascending)))
+
+ case None => Seq(groupingExpressions.map(SortOrder(_, Ascending)))
Review comment:
My bad. I guess it was removed somehow during refactor. Nice finding.
--
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]
