[GitHub] [spark] cloud-fan commented on a diff in pull request #41554: [SPARK-43781][SQL] Fix IllegalStateException when cogrouping two datasets derived from the same source

["cloud-fan (via GitHub)" <gi...@apache.org>]

cloud-fan commented on code in PR #41554:
URL: https://github.com/apache/spark/pull/41554#discussion_r1278929955


##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DeduplicateRelations.scala:
##########
@@ -220,7 +220,52 @@ object DeduplicateRelations extends Rule[LogicalPlan] {
           if (attrMap.isEmpty) {
             planWithNewChildren
           } else {
-            planWithNewChildren.rewriteAttrs(attrMap)
+            def rewriteAttrsMatchWithSubPlan(
+                attrs: Seq[Attribute],
+                attrMap: AttributeMap[Attribute],
+                planOutput: Seq[Attribute]): Seq[Attribute] = {
+              val canRewriteAttrs = attrMap.filter(a => planOutput.contains(a._2))
+              attrs.map(attr => canRewriteAttrs.getOrElse(attr, attr))
+            }
+
+            def rewriteOrderMatchWithSubPlan(
+                attrs: Seq[SortOrder],
+                attrMap: AttributeMap[Attribute],
+                planOutput: Seq[Attribute]): Seq[SortOrder] = {
+              val canRewriteAttrs = attrMap.filter(a => planOutput.contains(a._2))
+              attrs.filter(_.child.isInstanceOf[Attribute]).map(attr => {
+                if (canRewriteAttrs.contains(attr.child.asInstanceOf[Attribute])) {
+                  attr.copy(child = canRewriteAttrs(attr.child.asInstanceOf[Attribute]))
+                } else {
+                  attr
+                }
+              })
+            }
+
+            planWithNewChildren match {
+              case c @ CoGroup(_, keyDeserializer, leftDeserializer, rightDeserializer,
+              leftGroup, rightGroup, leftAttr, rightAttr, leftOrder, rightOrder, _, left,

Review Comment:
   nit: let's not use pattern match if there are too many parameters. `case c: CoGroup` is better.



-- 
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-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org