james-willis commented on code in PR #58293:
URL: https://github.com/apache/spark/pull/58293#discussion_r3864705070
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/columnar/InMemoryRelationSuite.scala:
##########
@@ -34,6 +35,20 @@ class InMemoryRelationSuite extends SparkFunSuite
assert(r1.sameResult(r2))
}
+ test("SPARK-59009: newInstance() re-maps outputOrdering onto the new
attributes") {
+ val d = spark.range(10).selectExpr("id", "id % 3 AS k").orderBy("k", "id")
+ val r1 = InMemoryRelation(StorageLevel.MEMORY_ONLY, d.queryExecution, None)
+ assert(r1.outputOrdering.nonEmpty)
+
+ val r2 = r1.newInstance()
+ assert(r2.output.map(_.exprId) != r1.output.map(_.exprId))
+ // The ordering must be re-mapped onto the new attributes, not left
referencing the old ones.
+ assert(r2.outputOrdering.nonEmpty)
+
assert(AttributeSet(r2.outputOrdering.flatMap(_.references)).subsetOf(AttributeSet(r2.output)))
+ // Canonicalization re-maps `outputOrdering` through `output`, so a stale
ordering would throw.
+ r2.canonicalized
Review Comment:
done. thanks
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
