Github user yhuai commented on a diff in the pull request: https://github.com/apache/spark/pull/9055#discussion_r42581785 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala --- @@ -270,6 +273,146 @@ class Analyzer( } /** + * Rewrite the [[Exists]] [[In]] with left semi join or anti join. + */ + object RewriteFilterSubQuery extends Rule[LogicalPlan] with PredicateHelper { + def unapply(condition: Expression): Option[(Expression, Seq[Expression])] = { + if (condition.resolved == false) { + return None + } + + val conjuctions = splitConjunctivePredicates(condition).map(_ transformDown { + // Remove the Cast expression for SubQueryExpression. + case Cast(f: SubQueryExpression, BooleanType) => f + } + ) + + val (subqueries, others) = conjuctions.partition(c => c.isInstanceOf[SubQueryExpression]) + if (subqueries.isEmpty) { + None + } else if (subqueries.length > 1) { + throw new AnalysisException( + s"Only 1 SubQuery expression is supported, but we got $subqueries") + } else { + val subQueryExpr = subqueries(0).asInstanceOf[SubQueryExpression] + // try to resolve the subquery + + val subquery = Analyzer.this.execute(subQueryExpr.subquery) match { + case Distinct(child) => child // Distinct is useless for semi join, ignore it. --- End diff -- Can you add comment to explain when we will get a `Distinct`?
--- 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