[SPARK-2554][SQL] Supporting SumDistinct partial aggregation

Adding support to the partial aggregation of SumDistinct

Author: ravipesala <ravindra.pesala@huawei.com>

Closes #3348 from ravipesala/SPARK-2554 and squashes the following commits:

fd28e4d [ravipesala] Fixed review comments
e60e67f [ravipesala] Fixed test cases and made it as nullable
32fe234 [ravipesala] Supporting SumDistinct partial aggregation Conflicts: 	sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregates.scala

1 files changed, 9 insertions, 4 deletions

diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala
index 96f3430207..f57f31af15 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala
@@ -185,9 +185,14 @@ class SQLQuerySuite extends QueryTest {
       sql("SELECT case when ~1=-2 then 1 else 0 end FROM src"),
       sql("SELECT 1 FROM src").collect().toSeq)
   }
-  
- test("SPARK-4154 Query does not work if it has 'not between' in Spark SQL and HQL") {
-    checkAnswer(sql("SELECT key FROM src WHERE key not between 0 and 10 order by key"), 
-        sql("SELECT key FROM src WHERE key between 11 and 500 order by key").collect().toSeq)
+
+  test("SPARK-4154 Query does not work if it has 'not between' in Spark SQL and HQL") {
+    checkAnswer(sql("SELECT key FROM src WHERE key not between 0 and 10 order by key"),
+      sql("SELECT key FROM src WHERE key between 11 and 500 order by key").collect().toSeq)
+  }
+
+  test("SPARK-2554 SumDistinct partial aggregation") {
+    checkAnswer(sql("SELECT sum( distinct key) FROM src group by key order by key"),
+      sql("SELECT distinct key FROM src order by key").collect().toSeq)
   }
 }