tanelk commented on a change in pull request #30018:
URL: https://github.com/apache/spark/pull/30018#discussion_r506346510
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
##########
@@ -477,6 +478,25 @@ object RemoveRedundantAliases extends Rule[LogicalPlan] {
def apply(plan: LogicalPlan): LogicalPlan = removeRedundantAliases(plan,
AttributeSet.empty)
}
+/**
+ * Remove redundant aggregates from a query plan. A redundant aggregate is an
aggregate whose
+ * only goal is to keep distinct values, while its parent aggregate would
ignore duplicate values.
+ */
+object RemoveRedundantAggregates extends Rule[LogicalPlan] {
+ def apply(plan: LogicalPlan): LogicalPlan = plan transformUp {
+ case upper @ Aggregate(_, _, lower: Aggregate) if lowerIsRedundant(upper,
lower) =>
+ upper.copy(child = lower.child)
+ }
+
+ private def lowerIsRedundant(upper: Aggregate, lower: Aggregate): Boolean = {
+ val upperReferencesOnlyGrouping = upper.references
+ .subsetOf(AttributeSet(lower.groupingExpressions))
Review comment:
Done
----------------------------------------------------------------
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
