[SPARK-17427][SQL] function SIZE should return -1 when parameter is null

## What changes were proposed in this pull request?

`select size(null)` returns -1 in Hive. In order to be compatible, we should return `-1`.

## How was this patch tested?

unit test in `CollectionFunctionsSuite` and `DataFrameFunctionsSuite`.

Author: Daoyuan Wang <daoyuan.wang@intel.com>

Closes #14991 from adrian-wang/size.

1 files changed, 8 insertions, 6 deletions

diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameFunctionsSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameFunctionsSuite.scala
index 0f6c49e759..45db61515e 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameFunctionsSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameFunctionsSuite.scala
@@ -324,15 +324,16 @@ class DataFrameFunctionsSuite extends QueryTest with SharedSQLContext {
     val df = Seq(
       (Seq[Int](1, 2), "x"),
       (Seq[Int](), "y"),
-      (Seq[Int](1, 2, 3), "z")
+      (Seq[Int](1, 2, 3), "z"),
+      (null, "empty")
     ).toDF("a", "b")
     checkAnswer(
       df.select(size($"a")),
-      Seq(Row(2), Row(0), Row(3))
+      Seq(Row(2), Row(0), Row(3), Row(-1))
     )
     checkAnswer(
       df.selectExpr("size(a)"),
-      Seq(Row(2), Row(0), Row(3))
+      Seq(Row(2), Row(0), Row(3), Row(-1))
     )
   }
 
@@ -340,15 +341,16 @@ class DataFrameFunctionsSuite extends QueryTest with SharedSQLContext {
     val df = Seq(
       (Map[Int, Int](1 -> 1, 2 -> 2), "x"),
       (Map[Int, Int](), "y"),
-      (Map[Int, Int](1 -> 1, 2 -> 2, 3 -> 3), "z")
+      (Map[Int, Int](1 -> 1, 2 -> 2, 3 -> 3), "z"),
+      (null, "empty")
     ).toDF("a", "b")
     checkAnswer(
       df.select(size($"a")),
-      Seq(Row(2), Row(0), Row(3))
+      Seq(Row(2), Row(0), Row(3), Row(-1))
     )
     checkAnswer(
       df.selectExpr("size(a)"),
-      Seq(Row(2), Row(0), Row(3))
+      Seq(Row(2), Row(0), Row(3), Row(-1))
     )
   }