Github user gatorsmile commented on a diff in the pull request:
https://github.com/apache/spark/pull/21839#discussion_r204286954
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
---
@@ -450,13 +450,16 @@ object ColumnPruning extends Rule[LogicalPlan] {
case d @ DeserializeToObject(_, _, child) if (child.outputSet --
d.references).nonEmpty =>
d.copy(child = prunedChild(child, d.references))
- // Prunes the unused columns from child of Aggregate/Expand/Generate
+ // Prunes the unused columns from child of
Aggregate/Expand/Generate/ScriptTransformation
case a @ Aggregate(_, _, child) if (child.outputSet --
a.references).nonEmpty =>
a.copy(child = prunedChild(child, a.references))
case f @ FlatMapGroupsInPandas(_, _, _, child) if (child.outputSet --
f.references).nonEmpty =>
f.copy(child = prunedChild(child, f.references))
case e @ Expand(_, _, child) if (child.outputSet --
e.references).nonEmpty =>
e.copy(child = prunedChild(child, e.references))
+ case s @ ScriptTransformation(_, _, _, child, _)
+ if (child.outputSet -- s.references).nonEmpty =>
--- End diff --
Nit: two more spaces before `if`.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
