jchen5 commented on code in PR #40865:
URL: https://github.com/apache/spark/pull/40865#discussion_r1176630244
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala:
##########
@@ -599,10 +600,33 @@ 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 (mayHaveCountBug.getOrElse(false) && resultFoldable &&
+
!conf.getConf(SQLConf.DECORRELATE_SUBQUERY_LEGACY_INCORRECT_COUNT_HANDLING_ENABLED))
{
+ val alias = Alias(resultWithZeroTups.get, origOutput.name)()
+ subqueryAttrMapping += (origOutput -> alias.toAttribute)
+ Project(
+ currentChild.output :+ alias,
+ Join(currentChild, query, LeftOuter, conditions.reduceOption(And),
joinHint))
Review Comment:
Quick PR to add some test coverage for it:
https://github.com/apache/spark/pull/40946
--
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]
