cloud-fan commented on code in PR #37074:
URL: https://github.com/apache/spark/pull/37074#discussion_r920151229
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala:
##########
@@ -742,12 +742,28 @@ object ColumnPruning extends Rule[LogicalPlan] {
* order, otherwise lower Projects can be missed.
*/
private def removeProjectBeforeFilter(plan: LogicalPlan): LogicalPlan = plan
transformUp {
- case p1 @ Project(_, f @ Filter(_, p2 @ Project(_, child)))
+ case p1 @ Project(_, f @ Filter(e, p2 @ Project(_, child)))
if p2.outputSet.subsetOf(child.outputSet) &&
// We only remove attribute-only project.
- p2.projectList.forall(_.isInstanceOf[AttributeReference]) =>
+ p2.projectList.forall(_.isInstanceOf[AttributeReference]) &&
+ !hasConflictingAttrsWithSubquery(e, child) =>
p1.copy(child = f.copy(child = child))
}
+
+ private def hasConflictingAttrsWithSubquery(predicate: Expression,
+ child: LogicalPlan): Boolean = {
+ def hasConflictingAttrs(s: SubqueryExpression): Boolean = {
+ s.references.intersect(child.outputSet).nonEmpty
+ }
+
+ splitConjunctivePredicates(predicate).exists { e =>
Review Comment:
why do we need `splitConjunctivePredicates`? `predicate.find` should be
sufficient.
--
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]
