mcdull-zhang commented on code in PR #43938:
URL: https://github.com/apache/spark/pull/43938#discussion_r1403085112
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala:
##########
@@ -138,9 +138,8 @@ trait HashJoin extends JoinCodegenSupport {
UnsafeProjection.create(streamedBoundKeys)
@transient protected[this] lazy val boundCondition = if
(condition.isDefined) {
- if (joinType == FullOuter && buildSide == BuildLeft) {
- // Put join left side before right side. This is to be consistent with
- // `ShuffledHashJoinExec.fullOuterJoin`.
+ if ((joinType == FullOuter || joinType == LeftOuter) && buildSide ==
BuildLeft) {
+ // Put join left side before right side. This is to be consistent with
ShuffledHashJoinExec.
Review Comment:
HashJoin.scala
```scala
override def output: Seq[Attribute] = {
joinType match {
case _: InnerLike =>
left.output ++ right.output
case LeftOuter =>
left.output ++ right.output.map(_.withNullability(true))
case RightOuter =>
left.output.map(_.withNullability(true)) ++ right.output
case j: ExistenceJoin =>
left.output :+ j.exists
case LeftExistence(_) =>
left.output
case x =>
throw new IllegalArgumentException(s"HashJoin should not take $x as
the JoinType")
}
}
```
ShuffledJoin.scala
```scala
override def output: Seq[Attribute] = {
joinType match {
case _: InnerLike =>
left.output ++ right.output
case LeftOuter =>
left.output ++ right.output.map(_.withNullability(true))
case RightOuter =>
left.output.map(_.withNullability(true)) ++ right.output
case FullOuter =>
(left.output ++ right.output).map(_.withNullability(true))
case j: ExistenceJoin =>
left.output :+ j.exists
case LeftExistence(_) =>
left.output
case x =>
throw new IllegalArgumentException(
s"${getClass.getSimpleName} not take $x as the JoinType")
}
}
```
@cloud-fan Output determines that we cannot simply put streaming side left
and build side right.
Am I understanding correctly?
--
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]
