Github user JoshRosen commented on a diff in the pull request:
https://github.com/apache/spark/pull/7904#discussion_r36283150
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/OuterJoin.scala ---
@@ -111,51 +124,41 @@ trait HashOuterJoin {
// iterator for performance purpose.
protected[this] def leftOuterIterator(
- key: InternalRow,
joinedRow: JoinedRow,
rightIter: Iterable[InternalRow]): Iterator[InternalRow] = {
val ret: Iterable[InternalRow] = {
- if (!key.anyNull) {
- val temp = if (rightIter != null) {
- rightIter.collect {
- case r if boundCondition(joinedRow.withRight(r)) =>
resultProjection(joinedRow).copy()
- }
- } else {
- List.empty
- }
- if (temp.isEmpty) {
- resultProjection(joinedRow.withRight(rightNullRow)).copy :: Nil
- } else {
- temp
+ val temp = if (rightIter != null) {
+ rightIter.collect {
+ case r if boundCondition(joinedRow.withRight(r)) =>
resultProjection(joinedRow).copy()
}
} else {
+ List.empty
+ }
+ if (temp.isEmpty) {
resultProjection(joinedRow.withRight(rightNullRow)).copy :: Nil
+ } else {
+ temp
}
}
ret.iterator
}
protected[this] def rightOuterIterator(
- key: InternalRow,
leftIter: Iterable[InternalRow],
joinedRow: JoinedRow): Iterator[InternalRow] = {
val ret: Iterable[InternalRow] = {
--- End diff --
Constructing an `Iterable` only to turn around and call `.iterator` doesn't
make a lot of sense to me, especially since it forces us to defensively copy in
the `collect`. Instead, I think this should accept and return iterators.
---
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]
