dbtsai commented on a change in pull request #24049: [SPARK-27123][SQL] Improve
CollapseProject to handle projects cross limit/repartition/sample
URL: https://github.com/apache/spark/pull/24049#discussion_r264537524
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
##########
@@ -699,6 +699,24 @@ object CollapseProject extends Rule[LogicalPlan] {
agg.copy(aggregateExpressions = buildCleanedProjectList(
p.projectList, agg.aggregateExpressions))
}
+ case p1 @ Project(_, g @ GlobalLimit(_, l @ LocalLimit(_, p2: Project))) =>
+ if (haveCommonNonDeterministicOutput(p1.projectList, p2.projectList)) {
+ p1
+ } else {
+ val newProjectList = buildCleanedProjectList(p1.projectList,
p2.projectList)
+ g.copy(child = l.copy(child = p2.copy(projectList = newProjectList)))
+ }
+ case p1 @ Project(_, l @ LocalLimit(_, p2: Project)) =>
+ if (haveCommonNonDeterministicOutput(p1.projectList, p2.projectList)) {
+ p1
+ } else {
+ val newProjectList = buildCleanedProjectList(p1.projectList,
p2.projectList)
+ l.copy(child = p2.copy(projectList = newProjectList))
+ }
+ case Project(list, r @ Repartition(_, _, p: Project)) if
list.forall(_.deterministic) =>
+ r.copy(child = p.copy(projectList = buildCleanedProjectList(list,
p.projectList)))
+ case Project(list, s @ Sample(_, _, _, _, p2: Project)) if
list.forall(_.deterministic) =>
+ s.copy(child = p2.copy(projectList = buildCleanedProjectList(list,
p2.projectList)))
Review comment:
Could `Sample` have similar issue above?
----------------------------------------------------------------
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]
