Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/13155#discussion_r63626483
--- Diff: sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala
---
@@ -293,4 +293,65 @@ class SubquerySuite extends QueryTest with
SharedSQLContext {
""".stripMargin),
Row(3) :: Nil)
}
+
+ test("COUNT bug in WHERE clause (Filter)") {
+
+ // Case 1: Canonical example of the COUNT bug
+ checkAnswer(
+ sql("select l.a from l where (select count(*) from r where l.a =
r.c) < l.a"),
+ Row(1) :: Row(1) :: Row(3) :: Row(6) :: Nil)
+
+ // Case 2: count(*) = 0; could be rewritten to NOT EXISTS but
currently uses
+ // a rewrite that is vulnerable to the COUNT bug
+ checkAnswer(
+ sql("select l.a from l where (select count(*) from r where l.a =
r.c) = 0"),
+ Row(1) :: Row(1) :: Row(null) :: Row(null) :: Nil)
+
+ // Case 3: COUNT bug without a COUNT aggregate
+ checkAnswer(
+ sql("select l.a from l where (select sum(r.d) is null from r where
l.a = r.c)"),
+ Row(1) :: Row(1) ::Row(null) :: Row(null) :: Row(6) :: Nil)
+
--- End diff --
(Maybe remove these blank lines,
https://github.com/databricks/scala-style-guide#blanklines)
---
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]
