Github user chenghao-intel commented on a diff in the pull request:
https://github.com/apache/spark/pull/5717#discussion_r31195205
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoin.scala
---
@@ -36,46 +36,91 @@ import org.apache.spark.util.collection.CompactBuffer
case class SortMergeJoin(
leftKeys: Seq[Expression],
rightKeys: Seq[Expression],
+ joinType: JoinType,
left: SparkPlan,
- right: SparkPlan) extends BinaryNode {
+ right: SparkPlan,
+ condition: Option[Expression] = None) extends BinaryNode {
- override def output: Seq[Attribute] = left.output ++ right.output
+ val (streamed, buffered, streamedKeys, bufferedKeys) = joinType match {
+ case RightOuter => (right, left, rightKeys, leftKeys)
+ case _ => (left, right, leftKeys, rightKeys)
+ }
+
+ override def output: Seq[Attribute] = joinType match {
+ case Inner =>
+ 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.map(_.withNullability(true)) ++
right.output.map(_.withNullability(true))
+ case x =>
+ sys.error(s"SortMergeJoin should not take $x as the JoinType")
+ }
- override def outputPartitioning: Partitioning = left.outputPartitioning
+ override def outputPartitioning: Partitioning = joinType match {
--- End diff --
NOTICE: Should always be `streamed.outputPartitioning` once #6413 merged,
see
https://github.com/apache/spark/pull/6413/files#diff-48230fdc68c8c172d22709ed90f8817dR50
---
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]
