zhenlineo commented on code in PR #40796:
URL: https://github.com/apache/spark/pull/40796#discussion_r1184417644
##########
sql/core/src/main/scala/org/apache/spark/sql/RelationalGroupedDataset.scala:
##########
@@ -700,6 +684,34 @@ private[sql] object RelationalGroupedDataset {
new RelationalGroupedDataset(df, groupingExprs, groupType: GroupType)
}
+ private[sql] def handleGroupingExpression(
+ logicalPlan: LogicalPlan,
+ sparkSession: SparkSession,
+ groupingExprs: Seq[Expression]): (QueryExecution, Seq[Attribute]) = {
+ // Resolves grouping expressions.
+ val dummyPlan = Project(groupingExprs.map(alias),
LocalRelation(logicalPlan.output))
+ val analyzedPlan = sparkSession.sessionState.analyzer.execute(dummyPlan)
+ .asInstanceOf[Project]
+ sparkSession.sessionState.analyzer.checkAnalysis(analyzedPlan)
+ val aliasedGroupings = analyzedPlan.projectList
+
+ // Adds the grouping expressions that are not in base DataFrame into
outputs.
+ val addedCols = aliasedGroupings.filter(g =>
!logicalPlan.outputSet.contains(g.toAttribute))
+ val qe = Dataset.ofRows(
+ sparkSession,
+ Project(logicalPlan.output ++ addedCols, logicalPlan)).queryExecution
+
+ (qe, aliasedGroupings.map(_.toAttribute))
+ }
+
+ private def alias(expr: Expression): NamedExpression = expr match {
Review Comment:
This is soooo subtle, I moved the aggExpr a bit earlier, then everything
breaks.
--
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]
