Github user davies commented on a diff in the pull request: https://github.com/apache/spark/pull/16193#discussion_r91609923 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/python/ExtractPythonUDFs.scala --- @@ -165,4 +167,31 @@ object ExtractPythonUDFs extends Rule[SparkPlan] { } } } + + // Split the original FilterExec to two FilterExecs. The upper FilterExec only contains + // Python UDF and non-deterministic predicates. + private def trySplitFilter(plan: SparkPlan): SparkPlan = { + plan match { + case filter: FilterExec => + // Only push down the predicates that is deterministic and all the referenced attributes + // come from child. + val (candidates, containingNonDeterministic) = + splitConjunctivePredicates(filter.condition).span(_.deterministic) + val (pushDown, rest) = candidates.partition(!hasPythonUDF(_)) + val stayUp = rest ++ containingNonDeterministic + + if (pushDown.nonEmpty) { + val newChild = FilterExec(pushDown.reduceLeft(And), filter.child) + if (stayUp.nonEmpty) { --- End diff -- There are should be some UDFs, so this will not be empty
--- 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