MrHappyEnding commented on code in PR #57791:
URL: https://github.com/apache/spark/pull/57791#discussion_r3733643369
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeJoinCondition.scala:
##########
@@ -30,16 +30,24 @@ object OptimizeJoinCondition extends Rule[LogicalPlan] with
PredicateHelper {
override def apply(plan: LogicalPlan): LogicalPlan =
plan.transformWithPruning(
_.containsPattern(JOIN), ruleId) {
case j @ Join(_, _, _, condition, _) if condition.nonEmpty =>
- val newCondition =
condition.map(_.transformWithPruning(_.containsPattern(OR), ruleId) {
- case Or(EqualTo(l, r), And(IsNull(c1), IsNull(c2)))
- if (l.semanticEquals(c1) && r.semanticEquals(c2))
- || (l.semanticEquals(c2) && r.semanticEquals(c1)) =>
- EqualNullSafe(l, r)
- case Or(And(IsNull(c1), IsNull(c2)), EqualTo(l, r))
- if (l.semanticEquals(c1) && r.semanticEquals(c2))
- || (l.semanticEquals(c2) && r.semanticEquals(c1)) =>
- EqualNullSafe(l, r)
- })
+ val newCondition = condition.map(optimizeCondition)
j.copy(condition = newCondition)
}
+
+ // Rewriting the pattern to EqualNullSafe maps NULL to FALSE, so only
recurse through And/Or.
+ private def optimizeCondition(condition: Expression): Expression = condition
match {
+ case Or(EqualTo(l, r), And(IsNull(c1), IsNull(c2)))
+ if (l.semanticEquals(c1) && r.semanticEquals(c2))
+ || (l.semanticEquals(c2) && r.semanticEquals(c1)) =>
+ EqualNullSafe(l, r)
+ case Or(And(IsNull(c1), IsNull(c2)), EqualTo(l, r))
+ if (l.semanticEquals(c1) && r.semanticEquals(c2))
+ || (l.semanticEquals(c2) && r.semanticEquals(c1)) =>
+ EqualNullSafe(l, r)
+ case And(left, right) =>
+ And(optimizeCondition(left), optimizeCondition(right))
Review Comment:
Thanks! Updated the traversal to preserve tree-pattern pruning and reuse
unchanged AND/OR nodes.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
