cloud-fan commented on code in PR #50304:
URL: https://github.com/apache/spark/pull/50304#discussion_r2002677839
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala:
##########
@@ -1031,18 +1036,39 @@ class Analyzer(override val catalogManager:
CatalogManager) extends RuleExecutor
private def addMetadataCol(
plan: LogicalPlan,
- requiredAttrIds: Set[ExprId]): LogicalPlan = plan match {
+ requiredAttrIds: Set[ExprId],
+ onlyUniqueAndNecessaryMetadataColumns: Boolean = true): LogicalPlan =
plan match {
case s: ExposesMetadataColumns if s.metadataOutput.exists( a =>
requiredAttrIds.contains(a.exprId)) =>
s.withMetadataColumns()
case p: Project if p.metadataOutput.exists(a =>
requiredAttrIds.contains(a.exprId)) =>
+ val existingExprIds = new util.HashSet[ExprId]
+ p.projectList.foreach(attr => existingExprIds.add(attr.exprId))
Review Comment:
I don't quite get this part. If the metadata column is already added to the
project list, then `requiredAttrIds` will not contain it and we won't add this
metadata column anyway.
--
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
