wankunde commented on code in PR #39923:
URL: https://github.com/apache/spark/pull/39923#discussion_r1108164536
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/JoinEstimation.scala:
##########
@@ -56,10 +56,13 @@ case class JoinEstimation(join: Join) extends Logging {
case _ if !rowCountsExist(join.left, join.right) =>
None
- case ExtractEquiJoinKeys(joinType, leftKeys, rightKeys, _, _, _, _, _) =>
+ case ExtractEquiJoinKeys(joinType, leftKeys, rightKeys, _, _, left, right,
_) =>
// 1. Compute join selectivity
val joinKeyPairs = extractJoinKeysWithColStats(leftKeys, rightKeys)
- val (numInnerJoinedRows, keyStatsAfterJoin) =
computeCardinalityAndStats(joinKeyPairs)
+ val leftUniqueness =
left.distinctKeys.exists(_.subsetOf(ExpressionSet(leftKeys)))
+ val rightUniqueness =
right.distinctKeys.exists(_.subsetOf(ExpressionSet(rightKeys)))
Review Comment:
Updated, thanks
--
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]
