jchen5 commented on code in PR #40865:
URL: https://github.com/apache/spark/pull/40865#discussion_r1173128023
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala:
##########
@@ -599,10 +600,32 @@ object RewriteCorrelatedScalarSubquery extends
Rule[LogicalPlan] with AliasHelpe
if (Utils.isTesting) {
assert(mayHaveCountBug.isDefined)
}
+
+ def queryOutputFoldable(list: Seq[NamedExpression]): Boolean = {
+ trimAliases(list.filter(p =>
p.exprId.equals(query.output.head.exprId)).head).foldable
+ }
+
+ lazy val resultFoldable = {
+ query match {
+ case Project(expressions, _) =>
+ queryOutputFoldable(expressions)
+ case Aggregate(_, expressions, _) =>
+ queryOutputFoldable(expressions)
+ case _ =>
+ false
+ }
+ }
+
if (resultWithZeroTups.isEmpty) {
// CASE 1: Subquery guaranteed not to have the COUNT bug because it
evaluates to NULL
// with zero tuples.
planWithoutCountBug
+ } else if (resultFoldable) {
Review Comment:
I just changed this code in https://github.com/apache/spark/pull/40811 so
you'll need to merge with that - your check should go after my new one, because
if the subquery is something like `select false from ... group by c` then it
will still actually return null on empty inputs. I have a test case for it
added in my PR.
--
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]
