Github user rxin commented on a diff in the pull request: https://github.com/apache/spark/pull/13876#discussion_r69834749 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala --- @@ -820,16 +820,25 @@ object ConstantFolding extends Rule[LogicalPlan] { } /** - * Replaces [[In (value, seq[Literal])]] with optimized version[[InSet (value, HashSet[Literal])]] - * which is much faster + * Optimize IN predicates: + * 1. Removes deterministic repetitions. + * 2. Replaces [[In (value, seq[Literal])]] with optimized version + * [[InSet (value, HashSet[Literal])]] which is much faster. */ case class OptimizeIn(conf: CatalystConf) extends Rule[LogicalPlan] { def apply(plan: LogicalPlan): LogicalPlan = plan transform { case q: LogicalPlan => q transformExpressionsDown { - case In(v, list) if !list.exists(!_.isInstanceOf[Literal]) && - list.size > conf.optimizerInSetConversionThreshold => - val hSet = list.map(e => e.eval(EmptyRow)) - InSet(v, HashSet() ++ hSet) + case i @ In(v, list) if i.inSetConvertible => + val newList = ExpressionSet(list).toSeq + if (newList.forall(_.isInstanceOf[Literal]) && + newList.size > conf.optimizerInSetConversionThreshold) { + val hSet = newList.map(e => e.eval(EmptyRow)) + InSet(v, HashSet() ++ hSet) + } else if (newList.length < list.length) { --- End diff -- length -> size
--- 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