maropu commented on a change in pull request #29585:
URL: https://github.com/apache/spark/pull/29585#discussion_r490722752
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlan.scala
##########
@@ -203,3 +203,62 @@ abstract class BinaryNode extends LogicalPlan {
abstract class OrderPreservingUnaryNode extends UnaryNode {
override final def outputOrdering: Seq[SortOrder] = child.outputOrdering
}
+
+object LogicalPlanIntegrity {
+
+ private def canGetOutputAttrs(p: LogicalPlan): Boolean = {
+ p.resolved && !p.expressions.exists { e =>
+ e.collectFirst {
+ // We cannot call `output` in plans with a `ScalarSubquery` expr
having no column,
+ // so, we filter out them in advance.
+ case s: ScalarSubquery if s.plan.schema.fields.isEmpty => true
+ }.isDefined
+ }
+ }
+
+ /**
+ * Since some logical plans (e.g., `Union`) can build `AttributeReference`s
in their `output`,
+ * this method checks if the same `ExprId` refers to a semantically-equal
attribute
+ * in a plan output.
+ */
+ def hasUniqueExprIdsForOutput(plan: LogicalPlan): Boolean = {
+ val allOutputAttrs = plan.collect { case p if canGetOutputAttrs(p) =>
+ // NOTE: we still need to filter resolved expressions here because the
output of
+ // some resolved logical plans can have unresolved references,
+ // e.g., outer references in `ExistenceJoin`.
+ p.output.filter(_.resolved).map(_.canonicalized.asInstanceOf[Attribute])
Review comment:
sure, I'll update.
----------------------------------------------------------------
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]
