Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/22326#discussion_r220288991 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala --- @@ -152,3 +153,56 @@ object EliminateOuterJoin extends Rule[LogicalPlan] with PredicateHelper { if (j.joinType == newJoinType) f else Filter(condition, j.copy(joinType = newJoinType)) } } + +/** + * Correctly handle PythonUDF which need access both side of join side by changing the new join + * type to Cross. + */ +object HandlePythonUDFInJoinCondition extends Rule[LogicalPlan] with PredicateHelper { --- End diff -- nit: PullOutputPythonUDFInJoinCondition
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org