sigmod commented on code in PR #35864:
URL: https://github.com/apache/spark/pull/35864#discussion_r842230227
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/NestedColumnAliasing.scala:
##########
@@ -312,6 +312,32 @@ object NestedColumnAliasing {
}
}
+object GeneratorUnrequiredChildrenPruning {
+ def unapply(plan: LogicalPlan): Option[LogicalPlan] = plan match {
+ case p@Project(_, g: Generate) =>
+ val requiredAttrs = p.references ++ g.generator.references
+ var pruned = false
+ val newChild = if (!g.child.outputSet.subsetOf(requiredAttrs)) {
+ pruned = true
+ Project(g.child.output.filter(requiredAttrs.contains), g.child)
+ } else {
+ g.child
+ }
+ val unrequired = g.generator.references -- p.references
+ val unrequiredIndices = newChild.output.zipWithIndex.filter(t =>
unrequired.contains(t._1))
+ .map(_._2)
+ if (unrequiredIndices.toSet != g.unrequiredChildIndex.toSet) {
+ pruned = true
+ }
+ if (pruned) {
+ Some(p.copy(child = g.copy(child = newChild, unrequiredChildIndex =
unrequiredIndices)))
+ } else {
+ None
+ }
Review Comment:
Nit: it seems that we don't really need `var pruned`:
```
if (!newChild.fastEq(g.Child) || unrequiredIndices.toSet !=
g.unrequiredChildIndex.toSet) {
p.copy(child = g.copy(child = newChild, unrequiredChildIndex =
unrequiredIndices))
} else {
None
}
```
`||` can short circuit the second set equality check condition. But I think
in reality, your code should also be fine. So it's your call.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
