Github user dongjoon-hyun commented on a diff in the pull request:
https://github.com/apache/spark/pull/16193#discussion_r91285472
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/python/ExtractPythonUDFs.scala
---
@@ -166,3 +174,40 @@ object ExtractPythonUDFs extends Rule[SparkPlan] {
}
}
}
+
+// This rule is to push deterministic predicates through
BatchEvalPythonExec
+object PushPredicateThroughBatchEvalPython extends Rule[SparkPlan] with
PredicateHelper {
+ def apply(plan: SparkPlan): SparkPlan = plan transform {
+ case filter @ FilterExec(_, child: BatchEvalPythonExec)
+ if child.expressions.forall(_.deterministic) =>
+ pushDownPredicate(filter, child.child) { predicate =>
+ child.withNewChildren(Seq(FilterExec(predicate, child.child)))
+ }
+ }
+
+ private def pushDownPredicate(
+ filter: FilterExec,
+ grandchild: SparkPlan)(insertFilter: Expression => SparkPlan):
SparkPlan = {
+ // Only push down the predicates that is deterministic and all the
referenced attributes
+ // come from grandchild.
+ val (candidates, containingNonDeterministic) =
+ splitConjunctivePredicates(filter.condition).span(_.deterministic)
--- End diff --
nit. Indentation?
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
