allisonwang-db commented on code in PR #37074: URL: https://github.com/apache/spark/pull/37074#discussion_r920409369
########## sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala: ########## @@ -742,12 +742,22 @@ 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) => Review Comment: Can we add a comment here to explain why this check is needed? ########## sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala: ########## @@ -72,12 +72,22 @@ object RewritePredicateSubquery extends Rule[LogicalPlan] with PredicateHelper { val outerRefs = outerPlan.outputSet ++ outerReferences val duplicates = outerRefs.intersect(subplan.outputSet) if (duplicates.nonEmpty) { - condition.foreach { e => + def throwOnConflictingAttrs(attrs: AttributeSet): Unit = { Review Comment: nit: we can move this to QueryCompilationError ########## sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala: ########## @@ -1788,4 +1788,60 @@ class SubquerySuite extends QueryTest with SharedSparkSession with AdaptiveSpark }.getMessage.contains("Correlated column is not allowed in predicate")) } } + + test("SPARK-39672: Fix removing project before filter with correlated subquery") { + withTempView("v1", "v2") { + Seq((1, 2, 3), (4, 5, 6)).toDF("a", "b", "c").createTempView("v1") + Seq((1, 3, 5), (4, 5, 6)).toDF("a", "b", "c").createTempView("v2") + + def findProjectExec(df: DataFrame): Seq[ProjectExec] = { + df.queryExecution.sparkPlan.collect { Review Comment: Would it be better to check the logical plan? -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org