karenfeng commented on a change in pull request #31666:
URL: https://github.com/apache/spark/pull/31666#discussion_r608850552
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
##########
@@ -958,6 +947,34 @@ class Analyzer(override val catalogManager: CatalogManager)
}
}
}
+
+ private def getMetadataAttributes(plan: LogicalPlan): Seq[Attribute] = {
+ lazy val childMetadataOutput = plan.children.flatMap(_.metadataOutput)
+ plan.expressions.flatMap(_.collect {
+ case a: Attribute if a.isMetadataCol => a
+ case a: Attribute if childMetadataOutput.exists(_.exprId == a.exprId)
=>
+ childMetadataOutput.find(_.exprId == a.exprId).get
+ })
+ }
+
+ private def hasMetadataCol(plan: LogicalPlan): Boolean = {
+ lazy val childMetadataOutput = plan.children.flatMap(_.metadataOutput)
+ val hasMetaCol = plan.expressions.exists(_.find {
+ case a: Attribute =>
+ a.isMetadataCol || childMetadataOutput.exists(_.exprId == a.exprId)
Review comment:
The regression test for this is in `DataFrameJoinSuite`.
--
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
