HeartSaVioR commented on code in PR #38503:
URL: https://github.com/apache/spark/pull/38503#discussion_r1016177874
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationChecker.scala:
##########
@@ -41,34 +42,58 @@ object UnsupportedOperationChecker extends Logging {
}
}
+ private def hasRangeExprAgainstEventTimeCol(e: Expression): Boolean =
e.exists {
+ case neq @ (_: LessThanOrEqual | _: LessThan | _: GreaterThanOrEqual | _:
GreaterThan) =>
+ hasEventTimeColNeq(neq)
+ case _ => false
+ }
+
+ private def hasEventTimeColNeq(neq: Expression): Boolean = {
+ val exp = neq.asInstanceOf[BinaryComparison]
+ hasEventTimeCol(exp.left) || hasEventTimeCol(exp.right)
+ }
+
+ private def hasEventTimeCol(exps: Expression): Boolean =
+ exps.exists {
+ case a: AttributeReference =>
a.metadata.contains(EventTimeWatermark.delayKey)
+ case _ => false
+ }
+
+ /**
+ * Check if the given logical plan is a streaming stateful operations.
+ * @param p: The logical plan to be checked.
+ */
+ def isStatefulOperation(p: LogicalPlan): Boolean = {
+ p match {
+ case s: Aggregate if s.isStreaming => true
+ // Since the Distinct node will be replaced to Aggregate in the
optimizer rule
+ // [[ReplaceDistinctWithAggregate]], here we also need to check all
Distinct node by
+ // assuming it as Aggregate.
+ case d @ Distinct(_: LogicalPlan) if d.isStreaming => true
Review Comment:
Yeah, nice finding!
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
