maropu commented on a change in pull request #29485:
URL: https://github.com/apache/spark/pull/29485#discussion_r475347837
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala
##########
@@ -328,27 +328,46 @@ object TypeCoercion {
*/
object WidenSetOperationTypes extends Rule[LogicalPlan] {
- def apply(plan: LogicalPlan): LogicalPlan = plan resolveOperatorsUp {
- case s @ Except(left, right, isAll) if s.childrenResolved &&
- left.output.length == right.output.length && !s.resolved =>
- val newChildren: Seq[LogicalPlan] =
buildNewChildrenWithWiderTypes(left :: right :: Nil)
- assert(newChildren.length == 2)
- Except(newChildren.head, newChildren.last, isAll)
-
- case s @ Intersect(left, right, isAll) if s.childrenResolved &&
- left.output.length == right.output.length && !s.resolved =>
- val newChildren: Seq[LogicalPlan] =
buildNewChildrenWithWiderTypes(left :: right :: Nil)
- assert(newChildren.length == 2)
- Intersect(newChildren.head, newChildren.last, isAll)
-
- case s: Union if s.childrenResolved && !s.byName &&
+ def apply(plan: LogicalPlan): LogicalPlan = {
+ val exprIdMapArray = mutable.ArrayBuffer[(ExprId, Attribute)]()
+ val newPlan = plan resolveOperatorsUp {
+ case s @ Except(left, right, isAll) if s.childrenResolved &&
+ left.output.length == right.output.length && !s.resolved =>
+ val (newChildren, newExprIds) = buildNewChildrenWithWiderTypes(left
:: right :: Nil)
+ exprIdMapArray ++= newExprIds
+ assert(newChildren.length == 2)
+ Except(newChildren.head, newChildren.last, isAll)
+
+ case s @ Intersect(left, right, isAll) if s.childrenResolved &&
+ left.output.length == right.output.length && !s.resolved =>
+ val (newChildren, newExprIds) = buildNewChildrenWithWiderTypes(left
:: right :: Nil)
+ exprIdMapArray ++= newExprIds
+ assert(newChildren.length == 2)
+ Intersect(newChildren.head, newChildren.last, isAll)
+
+ case s: Union if s.childrenResolved && !s.byName &&
s.children.forall(_.output.length == s.children.head.output.length)
&& !s.resolved =>
- val newChildren: Seq[LogicalPlan] =
buildNewChildrenWithWiderTypes(s.children)
- s.copy(children = newChildren)
+ val (newChildren, newExprIds) =
buildNewChildrenWithWiderTypes(s.children)
+ exprIdMapArray ++= newExprIds
+ s.copy(children = newChildren)
+ }
+
+ // Re-maps existing references to the new ones (exprId and dataType)
+ // for aliases added when widening columns' data types.
Review comment:
You meant re-alias with exprId=1 in the example above like this?
```
org.apache.spark.sql.AnalysisException: Resolved attribute(s) v#1 missing
from v#3 in operator !Project [v#1]. Attribute(s) with the same name appear in
the operation: v. Please check if the right attribute(s) are used.;;
!Project [v#1] <------ the reference got missing
+- SubqueryAlias t
+- Union
:- Project [cast(v#1 as decimal(11,0)) AS v#3] <----- !!!! re-alias
with exprId=#1 ?!!!!!
: +- Project [v#1]
: +- SubqueryAlias t3
: +- SubqueryAlias tbl
: +- LocalRelation [v#1]
+- Project [v#2]
+- Project [CheckOverflow((promote_precision(cast(v#1 as
decimal(11,0))) + promote_precision(cast(v#1 as decimal(11,0)))),
DecimalType(11,0), true) AS v#2]
+- SubqueryAlias t3
+- SubqueryAlias tbl
+- LocalRelation [v#1]
```
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
