eejbyfeldt commented on code in PR #43435:
URL: https://github.com/apache/spark/pull/43435#discussion_r1368212280
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/physical/partitioning.scala:
##########
@@ -700,14 +723,38 @@ case class HashShuffleSpec(
}
}
- override def createPartitioning(clustering: Seq[Expression]): Partitioning =
{
+ override def createPartitioning(clustering: Seq[Expression]):
HashPartitioning = {
val exprs = hashKeyPositions.map(v => clustering(v.head))
HashPartitioning(exprs, partitioning.numPartitions)
}
override def numPartitions: Int = partitioning.numPartitions
}
+case class CoalescedHashShuffleSpec(
+ from: HashShuffleSpec,
+ partitions: Seq[CoalescedBoundary]) extends ShuffleSpec {
+
+ override def isCompatibleWith(other: ShuffleSpec): Boolean = other match {
+ case SinglePartitionShuffleSpec =>
+ numPartitions == 1
+ case CoalescedHashShuffleSpec(otherParent, otherPartitions) =>
+ partitions == otherPartitions &&
+ from.isCompatibleWith(otherParent)
+ case ShuffleSpecCollection(specs) =>
+ specs.exists(isCompatibleWith)
+ case _ =>
+ false
+ }
+
+ override def canCreatePartitioning: Boolean = from.canCreatePartitioning
Review Comment:
That make sense, removed this and that made the spec reproducing the bug
pass.
--
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]
