viirya commented on a change in pull request #34062:
URL: https://github.com/apache/spark/pull/34062#discussion_r713398498
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/dynamicpruning/PartitionPruning.scala
##########
@@ -201,26 +201,28 @@ object PartitionPruning extends Rule[LogicalPlan] with
PredicateHelper with Join
}
/**
- * Returns whether an expression is likely to be selective
+ * Returns whether an expression is likely to be selective. If the filtering
predicate is on join
+ * key then partition filter can be inferred statically in optimization
phase, hence return false.
*/
- private def isLikelySelective(e: Expression): Boolean = e match {
- case Not(expr) => isLikelySelective(expr)
- case And(l, r) => isLikelySelective(l) || isLikelySelective(r)
- case Or(l, r) => isLikelySelective(l) && isLikelySelective(r)
- case _: StringRegexExpression => true
- case _: BinaryComparison => true
- case _: In | _: InSet => true
- case _: StringPredicate => true
- case _: MultiLikeBase => true
+ private def isLikelySelective(e: Expression, joinKey: Expression): Boolean =
e match {
+ case Not(expr) => isLikelySelective(expr, joinKey)
+ case And(l, r) => isLikelySelective(l, joinKey) || isLikelySelective(r,
joinKey)
+ case Or(l, r) => isLikelySelective(l, joinKey) && isLikelySelective(r,
joinKey)
+ case expr: StringRegexExpression => true &&
!expr.references.subsetOf(joinKey.references)
Review comment:
true seems redundant? just
`!expr.references.subsetOf(joinKey.references)`?
--
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]
