AngersZhuuuu commented on a change in pull request #28490:
URL: https://github.com/apache/spark/pull/28490#discussion_r480838768
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
##########
@@ -1425,11 +1433,48 @@ class Analyzer(
// rule: ResolveDeserializer.
case plan if containsDeserializer(plan.expressions) => plan
- // SPARK-25942: Resolves aggregate expressions with `AppendColumns`'s
children, instead of
- // `AppendColumns`, because `AppendColumns`'s serializer might produce
conflict attribute
- // names leading to ambiguous references exception.
- case a @ Aggregate(groupingExprs, aggExprs, appendColumns:
AppendColumns) =>
- a.mapExpressions(resolveExpressionTopDown(_, appendColumns))
+ case a: Aggregate =>
+ val planForResolve = a.child match {
+ case appendColumns: AppendColumns => appendColumns
+ case _ => a
+ }
+
+ val resolvedGroupingExprs = a.groupingExpressions
+ .map(resolveExpressionTopDown(_, planForResolve, true))
Review comment:
> nit `trimAlias = true`
Done
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
##########
@@ -1425,11 +1433,48 @@ class Analyzer(
// rule: ResolveDeserializer.
case plan if containsDeserializer(plan.expressions) => plan
- // SPARK-25942: Resolves aggregate expressions with `AppendColumns`'s
children, instead of
- // `AppendColumns`, because `AppendColumns`'s serializer might produce
conflict attribute
- // names leading to ambiguous references exception.
- case a @ Aggregate(groupingExprs, aggExprs, appendColumns:
AppendColumns) =>
- a.mapExpressions(resolveExpressionTopDown(_, appendColumns))
+ case a: Aggregate =>
+ val planForResolve = a.child match {
+ case appendColumns: AppendColumns => appendColumns
+ case _ => a
+ }
+
+ val resolvedGroupingExprs = a.groupingExpressions
+ .map(resolveExpressionTopDown(_, planForResolve, true))
+ .map {
+ // trim Alias over top-level GetStructField
+ case Alias(s: GetStructField, _) => s
+ case other => other
+ }
+
+ val resolvedAggExprs = a.aggregateExpressions
+ .map(resolveExpressionTopDown(_, planForResolve, true, true))
Review comment:
> `isTopLevel` should be controlled by the method itself, not caller
side.
Updated
----------------------------------------------------------------
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]
