Github user ueshin commented on a diff in the pull request:

    https://github.com/apache/spark/pull/21857#discussion_r205656881
  
    --- Diff: 
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
 ---
    @@ -1400,13 +1401,71 @@ object ReplaceIntersectWithSemiJoin extends 
Rule[LogicalPlan] {
      */
     object ReplaceExceptWithAntiJoin extends Rule[LogicalPlan] {
       def apply(plan: LogicalPlan): LogicalPlan = plan transform {
    -    case Except(left, right) =>
    +    case Except(left, right, false) =>
           assert(left.output.size == right.output.size)
           val joinCond = left.output.zip(right.output).map { case (l, r) => 
EqualNullSafe(l, r) }
           Distinct(Join(left, right, LeftAnti, joinCond.reduceLeftOption(And)))
       }
     }
     
    +/**
    + * Replaces logical [[ExceptAll]] operator using a combination of Union, 
Aggregate
    + * and Generate operator.
    + *
    + * Input Query :
    + * {{{
    + *    SELECT c1 FROM ut1 EXCEPT ALL SELECT c1 FROM ut2
    + * }}}
    + *
    + * Rewritten Query:
    + * {{{
    + *   SELECT c1
    + *   FROM (
    + *     SELECT replicate_rows(sum_val, c1) AS (sum_val, c1)
    --- End diff --
    
    Please don't forget to update the pr description as well.


---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org

Reply via email to