[SPARK-12480][FOLLOW-UP] use a single column vararg for hash

address comments in #10435

This makes the API easier to use if user programmatically generate the call to hash, and they will get analysis exception if the arguments of hash is empty.

Author: Wenchen Fan <wenchen@databricks.com>

Closes #10588 from cloud-fan/hash.

3 files changed, 4 insertions, 3 deletions

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
index 8834924687..6697d46361 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
@@ -200,7 +200,7 @@ case class Murmur3Hash(children: Seq[Expression], seed: Int) extends Expression
 
   override def checkInputDataTypes(): TypeCheckResult = {
     if (children.isEmpty) {
-      TypeCheckResult.TypeCheckFailure("arguments of function hash cannot be empty")
+      TypeCheckResult.TypeCheckFailure("function hash requires at least one argument")
     } else {
       TypeCheckResult.TypeCheckSuccess
     }
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ExpressionTypeCheckingSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ExpressionTypeCheckingSuite.scala
index 915c585ec9..f3df716a57 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ExpressionTypeCheckingSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ExpressionTypeCheckingSuite.scala
@@ -163,6 +163,7 @@ class ExpressionTypeCheckingSuite extends SparkFunSuite {
     assertError(Coalesce(Seq('intField, 'booleanField)),
       "input to function coalesce should all be the same type")
     assertError(Coalesce(Nil), "input to function coalesce cannot be empty")
+    assertError(new Murmur3Hash(Nil), "function hash requires at least one argument")
     assertError(Explode('intField),
       "input to function explode should be array or map type")
   }
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
index e223e32fd7..1c96f647b6 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
@@ -1820,8 +1820,8 @@ object functions extends LegacyFunctions {
    * @since 2.0
    */
   @scala.annotation.varargs
-  def hash(col: Column, cols: Column*): Column = withExpr {
-    new Murmur3Hash((col +: cols).map(_.expr))
+  def hash(cols: Column*): Column = withExpr {
+    new Murmur3Hash(cols.map(_.expr))
   }
 
   //////////////////////////////////////////////////////////////////////////////////////////////