yliou commented on a change in pull request #30788:
URL: https://github.com/apache/spark/pull/30788#discussion_r560657787
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
##########
@@ -1079,6 +1079,18 @@ class DataFrameAggregateSuite extends QueryTest
assert(aggs.head.output.map(_.dataType.simpleString).head ===
aggs.last.output.map(_.dataType.simpleString).head)
}
+
+ test("SPARK-33726 Duplicate field name aggregation should not have null
values in dataframe") {
+ val query =
+ """|with T as (select id as a, -id as x from range(3)), U as (select id
as b,
+ |cast(id as string) as x from range(3)) select T.x, U.x, min(a) as
ma, min(b) as mb
+ |from T join U on a=b group by U.x, T.x
+ """.stripMargin
+ val df = spark.sql(query)
+ val nullCount = df.filter($"ma".isNull ).count + df.filter($"mb".isNull
).count
+ + df.filter($"U.x".isNull ).count + df.filter($"T.x".isNull).count
+ assert(nullCount == 0)
Review comment:
Updated the PR description. Let me know if you have additional
suggestions to my description change.
----------------------------------------------------------------
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]
