Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/19451#discussion_r144461898
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
---
@@ -1242,6 +1244,53 @@ object ReplaceIntersectWithSemiJoin extends
Rule[LogicalPlan] {
}
/**
+ * If one or both of the datasets in the logical [[Except]] operator are
purely transformed using
+ * [[Filter]], this rule will replace logical [[Except]] operator with a
[[Filter]] operator by
+ * flipping the filter condition of the right child.
+ * {{{
+ * SELECT a1, a2 FROM Tab1 WHERE a2 = 12 EXCEPT SELECT a1, a2 FROM Tab1
WHERE a1 = 5
+ * ==> SELECT DISTINCT a1, a2 FROM Tab1 WHERE a2 = 12 AND a1 <> 5
+ * }}}
+ *
+ * Note:
+ * 1. We should combine all the [[Filter]] of the right node before
flipping it using NOT operator.
+ */
+object ReplaceExceptWithFilter extends Rule[LogicalPlan] {
+
+ def apply(plan: LogicalPlan): LogicalPlan = plan transform {
+ case Except(left, right) if isEligible(left, right) =>
+ val filterCondition =
combineFilters(right).asInstanceOf[Filter].condition
+ Distinct(
+ Filter(Not(replaceAttributesIn(filterCondition, left)), left)
+ )
+ }
+
+ def isEligible(left: LogicalPlan, right: LogicalPlan): Boolean = (left,
right) match {
+ case (left, right: Filter) =>
nonFilterChild(left).sameResult(nonFilterChild(right))
+ case _ => false
+ }
+
+ def nonFilterChild(plan: LogicalPlan): LogicalPlan =
plan.find(!_.isInstanceOf[Filter]).get
--- End diff --
it shouldn't be an analysisexception, if there is a bug in catalyst.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
