cloud-fan commented on a change in pull request #28676:
URL: https://github.com/apache/spark/pull/28676#discussion_r455705846
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastHashJoinExec.scala
##########
@@ -60,6 +63,81 @@ case class BroadcastHashJoinExec(
}
}
+ override lazy val outputPartitioning: Partitioning = {
+ joinType match {
+ case Inner =>
+ streamedPlan.outputPartitioning match {
+ case h: HashPartitioning => expandOutputPartitioning(h)
+ case c: PartitioningCollection => expandOutputPartitioning(c)
+ case other => other
+ }
+ case _ => streamedPlan.outputPartitioning
+ }
+ }
+
+ // An one-to-many mapping from a streamed key to build keys.
+ private lazy val streamedKeyToBuildKeyMapping = {
+ val mapping = mutable.Map.empty[Expression, Seq[Expression]]
+ streamedKeys.zip(buildKeys).foreach {
+ case (streamedKey, buildKey) =>
+ val key = streamedKey.canonicalized
+ mapping.get(key) match {
+ case Some(v) => mapping.put(key, v :+ buildKey)
+ case None => mapping.put(key, Seq(buildKey))
+ }
+ }
+ mapping.toMap
+ }
+
+ // Expands the given partitioning collection recursively.
+ private def expandOutputPartitioning(
+ partitioning: PartitioningCollection): PartitioningCollection = {
+ PartitioningCollection(partitioning.partitionings.flatMap {
+ case h: HashPartitioning => expandOutputPartitioning(h).partitionings
+ case c: PartitioningCollection => Seq(expandOutputPartitioning(c))
Review comment:
nit: `expandOutputPartitioning(c).partitionings`
----------------------------------------------------------------
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:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
