[SPARK-7269] [SQL] Incorrect analysis for aggregation(use semanticEquals)

A modified version of https://github.com/apache/spark/pull/6110, use `semanticEquals` to make it more efficient.

Author: Wenchen Fan <cloud0fan@outlook.com>

Closes #6173 from cloud-fan/7269 and squashes the following commits:

e4a3cc7 [Wenchen Fan] address comments
cc02045 [Wenchen Fan] consider elements length equal
d7ff8f4 [Wenchen Fan] fix 7269

1 files changed, 18 insertions, 0 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 ca2c4b4019..e60d00e635 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
@@ -773,4 +773,22 @@ class SQLQuerySuite extends QueryTest {
         | select * from v2 order by key limit 1
       """.stripMargin), Row(0, 3))
   }
+
+  test("SPARK-7269 Check analysis failed in case in-sensitive") {
+    Seq(1, 2, 3).map { i =>
+      (i.toString, i.toString)
+    }.toDF("key", "value").registerTempTable("df_analysis")
+    sql("SELECT kEy from df_analysis group by key").collect()
+    sql("SELECT kEy+3 from df_analysis group by key+3").collect()
+    sql("SELECT kEy+3, a.kEy, A.kEy from df_analysis A group by key").collect()
+    sql("SELECT cast(kEy+1 as Int) from df_analysis A group by cast(key+1 as int)").collect()
+    sql("SELECT cast(kEy+1 as Int) from df_analysis A group by key+1").collect()
+    sql("SELECT 2 from df_analysis A group by key+1").collect()
+    intercept[AnalysisException] {
+      sql("SELECT kEy+1 from df_analysis group by key+3")
+    }
+    intercept[AnalysisException] {
+      sql("SELECT cast(key+2 as Int) from df_analysis A group by cast(key+1 as int)")
+    }
+  }
 }