maropu commented on a change in pull request #28158: [SPARK-25154][SQL] Support
NOT IN sub-queries inside nested OR conditions
URL: https://github.com/apache/spark/pull/28158#discussion_r406592071
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala
##########
@@ -162,12 +162,21 @@ object RewritePredicateSubquery extends
Rule[LogicalPlan] with PredicateHelper {
plan: LogicalPlan): (Option[Expression], LogicalPlan) = {
var newPlan = plan
val newExprs = exprs.map { e =>
- e transformUp {
+ e transformDown {
case Exists(sub, conditions, _) =>
val exists = AttributeReference("exists", BooleanType, nullable =
false)()
newPlan =
buildJoin(newPlan, sub, ExistenceJoin(exists),
conditions.reduceLeftOption(And))
exists
+ case Not(InSubquery(values, ListQuery(sub, conditions, _, _))) =>
+ val exists = AttributeReference("exists", BooleanType, nullable =
false)()
+ // Deduplicate conflicting attributes if any.
+ val newSub = dedupSubqueryOnSelfJoin(newPlan, sub, Some(values))
+ val inConditions = values.zip(sub.output).map(EqualTo.tupled)
+ val nullAwareJoinConds = inConditions.map(c => Or(c, IsNull(c)))
Review comment:
Added.
----------------------------------------------------------------
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.
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]
