kazuyukitanimura commented on a change in pull request #33930:
URL: https://github.com/apache/spark/pull/33930#discussion_r742356732
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala
##########
@@ -813,6 +860,39 @@ object NullPropagation extends Rule[LogicalPlan] {
}
+/**
+ * Unwrap the input of IsNull/IsNotNull if the input is NullIntolerant
+ * E.g. IsNull(Not(null)) == IsNull(null)
+ */
+object NullDownPropagation extends Rule[LogicalPlan] {
+ // Not all NullIntolerant can be propagated
+ // Return false if the expression may return null without non-null inputs.
+ // E.g. Cast is NullIntolerant; however, cast('Infinity' as integer) returns
null.
+ // Cannot apply to `ExtractValue` as the query planner uses the trait to
resolve the columns.
+ // E.g. the planner may resolve column `a` to `a#123`, then IsNull(a#123)
cannot be optimized
+ // Applying to `EqualTo` is too disruptive for [SPARK-32290] test cases
+ // e with multiple children requires the deterministic check because
optimizing IsNull(a > b) to
+ // Or(IsNull(a), IsNull(b)), for example, may cause skipping the evaluation
of b
+ private def supportedNullIntolerant(e: NullIntolerant): Boolean = (e match {
+ case _: Not => true
+ case _: GreaterThan | _: GreaterThanOrEqual | _: LessThan | _:
LessThanOrEqual
Review comment:
This is due to earlier feedback in this review. Addressed in this part
of the comment;
**"Applying to `EqualTo` is too disruptive for [SPARK-32290] optimization,
not supported for now."**
--
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]
