szehon-ho commented on code in PR #41398:
URL: https://github.com/apache/spark/pull/41398#discussion_r1213341195
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/ShuffledHashJoinExec.scala:
##########
@@ -145,31 +157,38 @@ case class ShuffledHashJoinExec(
}
/**
- * Full outer shuffled hash join with unique join keys:
+ * Shuffled hash join with unique join keys, where an outer side is the
build side.
* 1. Process rows from stream side by looking up hash relation.
* Mark the matched rows from build side be looked up.
* A bit set is used to track matched rows with key index.
* 2. Process rows from build side by iterating hash relation.
* Filter out rows from build side being matched already,
* by checking key index from bit set.
*/
- private def fullOuterJoinWithUniqueKey(
- streamIter: Iterator[InternalRow],
- hashedRelation: HashedRelation,
- joinKeys: UnsafeProjection,
- joinRowWithStream: InternalRow => JoinedRow,
- joinRowWithBuild: InternalRow => JoinedRow,
- streamNullJoinRowWithBuild: => InternalRow => JoinedRow,
- buildNullRow: GenericInternalRow): Iterator[InternalRow] = {
+ private def buildSideOuterJoinUniqueKey(
+ streamIter: Iterator[InternalRow],
Review Comment:
Oh I think my intellij auto-formatted it,let me change it back
--
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]
