dongjoon-hyun commented on a change in pull request #30018:
URL: https://github.com/apache/spark/pull/30018#discussion_r598160288
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
##########
@@ -488,6 +489,50 @@ 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] with AliasHelper {
+ def apply(plan: LogicalPlan): LogicalPlan = plan transformUp {
+ case upper @ Aggregate(_, _, lower: Aggregate) if lowerIsRedundant(upper,
lower) =>
+ val aliasMap = getAliasMap(lower)
+
+ val newAggregate = upper.copy(
+ child = lower.child,
+ groupingExpressions = upper.groupingExpressions.map(replaceAlias(_,
aliasMap)),
+ aggregateExpressions = upper.aggregateExpressions.map(
+ replaceAliasButKeepName(_, aliasMap))
+ )
+
+ // We might have introduces non-deterministic grouping expression
+ if (newAggregate.groupingExpressions.exists(!_.deterministic)) {
+ PullOutNondeterministic.applyLocally.applyOrElse(newAggregate,
identity[LogicalPlan])
+ } else {
+ newAggregate
+ }
+ }
+
+ private def lowerIsRedundant(upper: Aggregate, lower: Aggregate): Boolean = {
Review comment:
nit. Usually, `isXXX` is better and consistent with Apache Spark
convention.
--
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]
