Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/10762#discussion_r50801713
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicOperators.scala
---
@@ -164,11 +164,42 @@ case class Join(
left.output.map(_.withNullability(true)) ++ right.output
case FullOuter =>
left.output.map(_.withNullability(true)) ++
right.output.map(_.withNullability(true))
+ case NaturalJoin(jt) =>
+ outerProjectList(jt).map(_.toAttribute)
case _ =>
left.output ++ right.output
}
}
+ def outerProjectList(jt: JoinType): Seq[NamedExpression] = {
+ val leftNames = left.output.map(_.name)
+ val rightNames = right.output.map(_.name)
+ val commonNames = leftNames.intersect(rightNames)
+ val commonOutputFromLeft = left.output.filter(att =>
commonNames.contains(att.name))
+ val lUniqueOutput = left.output.filterNot(att =>
commonNames.contains(att.name))
+ val rUniqueOutput = right.output.filterNot(att =>
commonNames.contains(att.name))
+ jt match {
+ case LeftOuter =>
+ commonOutputFromLeft ++ lUniqueOutput ++
rUniqueOutput.map(_.withNullability(true))
+ case RightOuter =>
+ val commonOutputFromRight =
+ commonNames.map(cn => right.output.find(att => att.name ==
cn).get)
+ commonOutputFromRight ++
lUniqueOutput.map(_.withNullability(true)) ++ rUniqueOutput
+ case FullOuter =>
+ val commonOutputFromRight =
+ commonNames.map(cn => right.output.find(att => att.name ==
cn).get)
+ val commonPairs = commonOutputFromLeft.zip(commonOutputFromRight)
+ val commonOutputExp = commonPairs.map {
+ case (l: Attribute, r: Attribute) =>
+ Alias(Coalesce(Seq(l, r)), l.name)()
+ }
+ commonOutputExp ++
+ lUniqueOutput.map(_.withNullability(true)) ++
rUniqueOutput.map(_.withNullability(true))
+ case _ =>
+ commonOutputFromLeft ++ lUniqueOutput ++ rUniqueOutput
+ }
+ }
+
def selfJoinResolved: Boolean =
left.outputSet.intersect(right.outputSet).isEmpty
// Joins are only resolved if they don't introduce ambiguous expression
ids.
--- End diff --
we should make resolved false if the type is natural join
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
