Github user gatorsmile commented on a diff in the pull request: https://github.com/apache/spark/pull/23153#discussion_r237944306 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala --- @@ -155,19 +155,20 @@ object EliminateOuterJoin extends Rule[LogicalPlan] with PredicateHelper { } /** - * PythonUDF in join condition can not be evaluated, this rule will detect the PythonUDF - * and pull them out from join condition. For python udf accessing attributes from only one side, - * they are pushed down by operation push down rules. If not (e.g. user disables filter push - * down rules), we need to pull them out in this rule too. + * PythonUDF in join condition can't be evaluated if it refers to attributes from both join sides. + * See `ExtractPythonUDFs` for details. This rule will detect un-evaluable PythonUDF and pull them + * out from join condition. */ object PullOutPythonUDFInJoinCondition extends Rule[LogicalPlan] with PredicateHelper { - def hasPythonUDF(expression: Expression): Boolean = { - expression.collectFirst { case udf: PythonUDF => udf }.isDefined + + private def hasUnevaluablePythonUDF(expr: Expression, j: Join): Boolean = { + expr.find { e => + PythonUDF.isScalarPythonUDF(e) && !canEvaluate(e, j.left) && !canEvaluate(e, j.right) --- End diff -- We might need a comment to explain why we only pull out the Scalar `PythonUDF`.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org