Github user mgaido91 commented on a diff in the pull request: https://github.com/apache/spark/pull/22326#discussion_r220518059 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala --- @@ -152,3 +153,51 @@ 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 PullOutPythonUDFInJoinCondition extends Rule[LogicalPlan] with PredicateHelper { + def hasPythonUDF(expression: Expression): Boolean = { + expression.collectFirst { case udf: PythonUDF => udf }.isDefined --- End diff -- thanks for the explanation @cloud-fan , makes sense, can we then update the comment of this class in order to reflect what it actually does?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org