Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/11130#discussion_r52838756
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastHashJoin.scala
---
@@ -105,75 +107,129 @@ case class BroadcastHashJoin(
val broadcastRelation = Await.result(broadcastFuture, timeout)
streamedPlan.execute().mapPartitions { streamedIter =>
- val hashedRelation = broadcastRelation.value
-
TaskContext.get().taskMetrics().incPeakExecutionMemory(hashedRelation.getMemorySize)
- hashJoin(streamedIter, hashedRelation, numOutputRows)
+ val joinedRow = new JoinedRow()
+ val hashTable = broadcastRelation.value
+
TaskContext.get().taskMetrics().incPeakExecutionMemory(hashTable.getMemorySize)
+ val keyGenerator = streamSideKeyGenerator
+ val resultProj = createResultProjection
+
+ joinType match {
+ case Inner =>
+ hashJoin(streamedIter, hashTable, numOutputRows)
+
+ case LeftOuter =>
+ streamedIter.flatMap(currentRow => {
--- End diff --
These are copied and pasted here, usually don't modify them to reduce the
budget of review.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
