Github user gatorsmile commented on a diff in the pull request:
https://github.com/apache/spark/pull/11106#discussion_r52316817
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
---
@@ -1059,19 +1059,24 @@ object ReplaceDistinctWithAggregate extends
Rule[LogicalPlan] {
* {{{
* SELECT a1, a2 FROM Tab1 INTERSECT SELECT b1, b2 FROM Tab2
* ==> SELECT DISTINCT a1, a2 FROM Tab1 LEFT SEMI JOIN Tab2 ON a1<=>b1
AND a2<=>b2
+ * SELECT a1, a2 FROM Tab1 INTERSECT ALL SELECT b1, b2 FROM Tab2
+ * ==> SELECT a1, a2 FROM Tab1 LEFT SEMI JOIN Tab2 ON a1<=>b1 AND
a2<=>b2
* }}}
*
- * Note:
- * 1. This rule is only applicable to INTERSECT DISTINCT. Do not use it
for INTERSECT ALL.
- * 2. This rule has to be done after de-duplicating the attributes;
otherwise, the generated
+ * Note: This rule has to be done after de-duplicating the attributes;
otherwise, the generated
* join conditions will be incorrect.
*/
object ReplaceIntersectWithSemiJoin extends Rule[LogicalPlan] {
def apply(plan: LogicalPlan): LogicalPlan = plan transform {
- case Intersect(left, right) =>
+ case Intersect(left, right, distinct) =>
assert(left.output.size == right.output.size)
- val joinCond = left.output.zip(right.output).map { case (l, r) =>
EqualNullSafe(l, r) }
- Distinct(Join(left, right, LeftSemi, joinCond.reduceLeftOption(And)))
+ val joinCond =
left.output.zip(right.output).map(EqualNullSafe.tupled)
+ if (distinct) {
+ Distinct(Join(left, right, LeftSemi,
joinCond.reduceLeftOption(And)))
--- End diff --
Yeah, let me change it now.
---
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]
