Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/10678#discussion_r49563404
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
---
@@ -521,38 +522,90 @@ class Analyzer(
*/
object ResolveSortReferences extends Rule[LogicalPlan] {
def apply(plan: LogicalPlan): LogicalPlan = plan resolveOperators {
- case s @ Sort(ordering, global, p @ Project(projectList, child))
- if !s.resolved && p.resolved =>
- val (newOrdering, missing) = resolveAndFindMissing(ordering, p,
child)
+ case s @ Sort(_, _, child) if !s.resolved && child.resolved =>
+ val (newOrdering, missingResolvableAttrs) =
collectResolvedMissingAttrs(s.order, child)
- // If this rule was not a no-op, return the transformed plan,
otherwise return the original.
- if (missing.nonEmpty) {
- // Add missing attributes and then project them away after the
sort.
- Project(p.output,
- Sort(newOrdering, global,
- Project(projectList ++ missing, child)))
- } else {
- logDebug(s"Failed to find $missing in ${p.output.mkString(",
")}")
+ if (missingResolvableAttrs.isEmpty) {
+ val unresolvableAttrs = s.order.filterNot(_.resolved)
+ logDebug(s"Failed to find $unresolvableAttrs in
${child.output.mkString(", ")}")
s // Nothing we can do here. Return original plan.
}
+ else {
+ var stop: Boolean = false
+ var missingAttrs: Seq[Attribute] = missingResolvableAttrs
+ val newChild = child transform {
+ case p: Project if !stop && missingAttrs.nonEmpty =>
+ val newList = p.projectList ++ missingAttrs
+ missingAttrs = missingAttrs.filterNot(
+ attr => p.child.outputSet.exists(_.semanticEquals(attr)))
+ p.copy(projectList = newList)
+ case w: Window if !stop && missingAttrs.nonEmpty =>
+ val newList = w.projectList ++ missingAttrs
+ missingAttrs = missingAttrs.filterNot(
+ attr => w.child.outputSet.exists(_.semanticEquals(attr)))
+ w.copy(projectList = newList)
+ case a: Aggregate if !stop && missingAttrs.nonEmpty =>
+ // Grouping expressions could already have the missing
attributes.
+ // Do not add the duplicate attributes.
+ val newGroupExpressions = a.groupingExpressions ++
missingAttrs.filterNot(
+ attr =>
a.groupingExpressions.exists(_.semanticEquals(attr)))
+ val newAggregateExpressions = a.aggregateExpressions ++
missingAttrs
+ missingAttrs = missingAttrs.filterNot(
+ attr => a.child.outputSet.exists(_.semanticEquals(attr)))
+ a.copy(groupingExpressions = newGroupExpressions,
+ aggregateExpressions = newAggregateExpressions)
+ case s: Subquery if !stop && missingAttrs.nonEmpty => s
+ case o =>
--- End diff --
How about Filter (having clause)?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
