maropu commented on a change in pull request #28560:
URL: https://github.com/apache/spark/pull/28560#discussion_r426341109
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/NestedColumnAliasing.scala
##########
@@ -68,10 +76,23 @@ object NestedColumnAliasing {
*/
def replaceChildrenWithAliases(
plan: LogicalPlan,
+ nestedFieldToAlias: Map[ExtractValue, Alias],
attrToAliases: Map[ExprId, Seq[Alias]]): LogicalPlan = {
plan.withNewChildren(plan.children.map { plan =>
Project(plan.output.flatMap(a => attrToAliases.getOrElse(a.exprId,
Seq(a))), plan)
- })
+ }).transformExpressions {
+ case f: ExtractValue if nestedFieldToAlias.contains(f) =>
+ nestedFieldToAlias(f).toAttribute
+ }
+ }
+
+ /**
+ * Returns true for those operators that we can prune nested column on it.
+ */
+ private def canPruneOn(plan: LogicalPlan) = plan match {
+ case _: Aggregate => true
+ case _: Expand => true
+ case _ => false
Review comment:
Are the current entries all the case we can support for nested column
pruning? How about `FlatMapGroupsInPandas`?
----------------------------------------------------------------
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:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
