Github user yhuai commented on a diff in the pull request: https://github.com/apache/spark/pull/15489#discussion_r83500257 --- Diff: sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala --- @@ -1106,6 +1106,30 @@ class SQLQuerySuite extends QueryTest with SharedSQLContext { ) } + test("SPARK-17863: SELECT distinct does not work correctly if order by missing attribute") { + checkAnswer( + sql("""select distinct struct.a, struct.b + |from ( + | select named_struct('a', 1, 'b', 2, 'c', 3) as struct + | union all + | select named_struct('a', 1, 'b', 2, 'c', 4) as struct) tmp + |order by a, b + |""".stripMargin), + Row(1, 2) :: Nil) + + val error = intercept[AnalysisException] { + sql("""select distinct struct.a, struct.b + |from ( + | select named_struct('a', 1, 'b', 2, 'c', 3) as struct + | union all + | select named_struct('a', 1, 'b', 2, 'c', 4) as struct) tmp + |order by struct.a, struct.b + |""".stripMargin) + } + assert(error.message contains "cannot resolve '`struct.a`' given input columns: [a, b]") --- End diff -- Oh, i see. Seems this error is thrown by check analysis, which does not have info about what is the query. So, it is hard to figure out what messages (for the workaround) to put at here.
--- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org