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_r369310786
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteDistinctAggregates.scala
##########
@@ -148,24 +205,102 @@ 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.
+ // We need at least two distinct aggregates or a single distinct aggregate
with a filter for
+ // this rule because aggregation strategy can handle a single distinct
group without a filter.
// 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 = extractFiltersInDistinctAggregates(a)
+ rewriteDistinctAggregates(expandAggregate)
}
- def rewrite(a: Aggregate): Aggregate = {
+ private def extractFiltersInDistinctAggregates(a: Aggregate): Aggregate = {
+ val aggExpressions = collectAggregateExprs(a)
+ val (distinctAggExpressions, regularAggExpressions) =
aggExpressions.partition(_.isDistinct)
+ if (distinctAggExpressions.exists(_.filter.isDefined)) {
+ // Constructs pairs between old and new expressions for regular
aggregates. Because we
+ // will construct a new aggregate, the children of the distinct
aggregates will be
+ // changed to the generate ones, so we need creates new references to
avoid collisions
+ // between distinct and regular aggregate children.
+ val regularAggExprs =
regularAggExpressions.filter(_.children.exists(!_.foldable))
+ val regularFunChildren = regularAggExprs
+ .flatMap(_.aggregateFunction.children.filter(!_.foldable))
+ val regularFilterAttrs = regularAggExprs.flatMap(_.filterAttributes)
+ val regularAggChildren = (regularFunChildren ++
regularFilterAttrs).distinct
+ val regularAggChildAttrMap =
regularAggChildren.map(expressionAttributePair)
+ val regularAggChildAttrLookup = regularAggChildAttrMap.toMap
+ val regularAggPairs = regularAggExprs.map {
+ case ae @ AggregateExpression(af, _, _, filter, _) =>
+ val newChildren = af.children.map(c =>
regularAggChildAttrLookup.getOrElse(c, c))
+ val raf =
af.withNewChildren(newChildren).asInstanceOf[AggregateFunction]
+ val filterOpt = filter.map(_.transform {
+ case a: Attribute => regularAggChildAttrLookup.getOrElse(a, a)
+ })
+ val aggExpr = ae.copy(aggregateFunction = raf, filter = filterOpt)
+ (ae, aggExpr)
+ }
- // Collect all aggregate expressions.
- val aggExpressions = a.aggregateExpressions.flatMap { e =>
- e.collect {
- case ae: AggregateExpression => ae
+ // Setup expand for the distinct aggregate expressions.
Review comment:
`Constructs pairs between old and new expressions for distinct aggregates,
too.`
----------------------------------------------------------------
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]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
