Github user gatorsmile commented on a diff in the pull request: https://github.com/apache/spark/pull/14815#discussion_r76336122 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala --- @@ -1386,15 +1386,17 @@ object EliminateOuterJoin extends Rule[LogicalPlan] with PredicateHelper { object PushPredicateThroughJoin extends Rule[LogicalPlan] with PredicateHelper { /** * Splits join condition expressions into three categories based on the attributes required - * to evaluate them. + * to evaluate them. Note that we explicitly exclude non-deterministic (i.e., stateful) condition + * expressions in canEvaluateInLeft or canEvaluateInRight to prevent pushing these predicates on + * either side of the join. * * @return (canEvaluateInLeft, canEvaluateInRight, haveToEvaluateInBoth) */ private def split(condition: Seq[Expression], left: LogicalPlan, right: LogicalPlan) = { val (leftEvaluateCondition, rest) = - condition.partition(_.references subsetOf left.outputSet) + condition.partition(expr => expr.references.subsetOf(left.outputSet) && expr.deterministic) --- End diff -- Maybe we need to use `span` here. See another PR: https://github.com/apache/spark/pull/14012
--- 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