maropu commented on a change in pull request #27058: [SPARK-30276][SQL] Support Filter expression allows simultaneous use of DISTINCT URL: https://github.com/apache/spark/pull/27058#discussion_r368808155
########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteDistinctAggregates.scala ########## @@ -148,24 +207,106 @@ object RewriteDistinctAggregates extends Rule[LogicalPlan] { val distinctAggs = exprs.flatMap { _.collect { case ae: AggregateExpression if ae.isDistinct => ae }} - // We need at least two distinct aggregates for this rule because aggregation - // strategy can handle a single distinct group. + // This rule serves two purposes: + // One is to rewrite when there exists at least two distinct aggregates. We need at least + // two distinct aggregates for this rule because aggregation strategy can handle a single + // distinct group. + // Another is to expand distinct aggregates which exists filter clause so that we can + // evaluate the filter locally. // This check can produce false-positives, e.g., SUM(DISTINCT a) & COUNT(DISTINCT a). - distinctAggs.size > 1 + distinctAggs.size >= 1 || distinctAggs.exists(_.filter.isDefined) } def apply(plan: LogicalPlan): LogicalPlan = plan transformUp { - case a: Aggregate if mayNeedtoRewrite(a.aggregateExpressions) => rewrite(a) + case a: Aggregate if mayNeedtoRewrite(a.aggregateExpressions) => + val expandAggregate = extractFiltersInDistinctAggregate(a) + rewriteDistinctAggregate(expandAggregate) } - def rewrite(a: Aggregate): Aggregate = { + private def extractFiltersInDistinctAggregate(a: Aggregate): Aggregate = { Review comment: also nit: `extractFiltersInDistinctAggregate` -> `extractFiltersInDistinctAggregates` ---------------------------------------------------------------- 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 With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org