maropu commented on a change in pull request #23750: [SPARK-19712][SQL] Pushing
Left Semi and Left Anti joins through Project, Aggregate, Window, Union etc.
URL: https://github.com/apache/spark/pull/23750#discussion_r256821463
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
##########
@@ -1188,6 +1189,190 @@ object PushDownPredicate extends Rule[LogicalPlan]
with PredicateHelper {
}
}
+object PushDownLeftSemiAntiJoin extends Rule[LogicalPlan] with PredicateHelper
{
+ def apply(plan: LogicalPlan): LogicalPlan = plan transform {
+ // Similar to the above Filter over Project
+ // LeftSemi/LeftAnti over Project
+ case join @ Join(p @ Project(pList, gChild), rightOp,
LeftSemiOrAnti(joinType), joinCond, hint)
+ if pList.forall(_.deterministic) &&
!ScalarSubquery.hasScalarSubquery(pList) &&
+ canPushThroughCondition(Seq(gChild), joinCond, rightOp) =>
+ if (joinCond.isEmpty) {
+ // No join condition, just push down the Join below Project
+ Project(pList, Join(gChild, rightOp, joinType, joinCond, hint))
+ } else {
+ // Create a map of Aliases to their values from the child projection.
+ // e.g., 'SELECT a + b AS c, d ...' produces Map(c -> a + b).
+ val aliasMap = AttributeMap(pList.collect {
+ case a: Alias => (a.toAttribute, a.child)
+ })
+ val newJoinCond = if (aliasMap.nonEmpty) {
+ Option(replaceAlias(joinCond.get, aliasMap))
+ } else {
+ joinCond
+ }
+ Project(pList, Join(gChild, rightOp, joinType, newJoinCond, hint))
Review comment:
ditto
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
