dongjoon-hyun commented on a change in pull request #29950:
URL: https://github.com/apache/spark/pull/29950#discussion_r502314576
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala
##########
@@ -124,14 +128,34 @@ object ScanOperation extends OperationHelper with
PredicateHelper {
}.exists(!_.deterministic))
}
+ def moreThanMaxAllowedCommonOutput(
+ expr: Seq[NamedExpression],
+ aliases: AttributeMap[Expression]): Boolean = {
+ val exprMap = mutable.HashMap.empty[Attribute, Int]
+
+ expr.foreach(_.collect {
+ case a: Attribute if aliases.contains(a) => exprMap.update(a,
exprMap.getOrElse(a, 0) + 1)
+ })
+
+ val commonOutputs = if (exprMap.size > 0) {
+ exprMap.maxBy(_._2)._2
+ } else {
+ 0
+ }
+
+ commonOutputs > maxCommonExprs
+ }
+
private def collectProjectsAndFilters(plan: LogicalPlan): ScanReturnType = {
plan match {
case Project(fields, child) =>
collectProjectsAndFilters(child) match {
case Some((_, filters, other, aliases)) =>
// Follow CollapseProject and only keep going if the collected
Projects
- // do not have common non-deterministic expressions.
- if (!hasCommonNonDeterministic(fields, aliases)) {
+ // do not have common non-deterministic expressions, or do not
have equal to/more than
+ // maximum allowed common outputs.
+ if (!hasCommonNonDeterministic(fields, aliases)
+ || !moreThanMaxAllowedCommonOutput(fields, aliases)) {
Review comment:
nit, you may want to move `||` into line 157.
----------------------------------------------------------------
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]
