maryannxue commented on a change in pull request #28676:
URL: https://github.com/apache/spark/pull/28676#discussion_r447105401
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastHashJoinExec.scala
##########
@@ -60,6 +62,92 @@ case class BroadcastHashJoinExec(
}
}
+ override def outputPartitioning: Partitioning = {
+ val (buildKeys, streamedKeys) = buildSide match {
+ case BuildLeft => (leftKeys, rightKeys)
+ case BuildRight => (rightKeys, leftKeys)
+ }
+
+ joinType match {
+ case _: InnerLike =>
+ streamedPlan.outputPartitioning match {
+ case h: HashPartitioning =>
+ getBuildSidePartitioning(h, streamedKeys, buildKeys) match {
+ case Some(p) => PartitioningCollection(Seq(h, p))
+ case None => h
+ }
+ case c: PartitioningCollection =>
+ c.partitionings.foreach {
+ case h: HashPartitioning =>
+ getBuildSidePartitioning(h, streamedKeys, buildKeys) match {
+ case Some(p) => return
PartitioningCollection(c.partitionings :+ p)
+ case None => ()
+ }
+ case _ => ()
+ }
+ c
+ case other => other
+ }
+ case _ => streamedPlan.outputPartitioning
+ }
+ }
+
+ /**
Review comment:
Does it have to so complicated??
It's simply an attribute substitution based on equality, right?
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
