leanken commented on a change in pull request #29104:
URL: https://github.com/apache/spark/pull/29104#discussion_r459012565
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastHashJoinExec.scala
##########
@@ -133,10 +135,32 @@ case class BroadcastHashJoinExec(
val numOutputRows = longMetric("numOutputRows")
val broadcastRelation = buildPlan.executeBroadcast[HashedRelation]()
- streamedPlan.execute().mapPartitions { streamedIter =>
- val hashed = broadcastRelation.value.asReadOnlyCopy()
-
TaskContext.get().taskMetrics().incPeakExecutionMemory(hashed.estimatedSize)
- join(streamedIter, hashed, numOutputRows)
+ if (isNullAwareAntiJoin) {
+ streamedPlan.execute().mapPartitionsInternal { streamedIter =>
+ if (broadcastRelation.value.inputEmpty) {
+ streamedIter
+ } else if (broadcastRelation.value.anyNullKeyExists) {
+ Iterator.empty
+ } else {
+ val keyGenerator = UnsafeProjection.create(
+ BindReferences.bindReferences[Expression](
+ leftKeys,
+ AttributeSeq(left.output))
+ )
+ streamedIter.filter(row => {
+ val lookupKey: UnsafeRow = keyGenerator(row)
+ val streamedRowIsNull = lookupKey.isNullAt(0)
+ val notInKeyEqual = broadcastRelation.value.get(lookupKey) != null
+ !streamedRowIsNull && !notInKeyEqual
+ })
+ }
+ }
+ } else {
+ streamedPlan.execute().mapPartitions { streamedIter =>
+ val hashed = broadcastRelation.value.asReadOnlyCopy()
+
TaskContext.get().taskMetrics().incPeakExecutionMemory(hashed.estimatedSize)
Review comment:
ok. will do the update
----------------------------------------------------------------
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
