[SPARK-8235] [SQL] misc function sha / sha1

Jira: https://issues.apache.org/jira/browse/SPARK-8235

I added the support for sha1. If I understood rxin correctly, sha and sha1 should execute the same algorithm, shouldn't they?

Please take a close look on the Python part. This is adopted from #6934

Author: Tarek Auel <tarek.auel@gmail.com>
Author: Tarek Auel <tarek.auel@googlemail.com>

Closes #6963 from tarekauel/SPARK-8235 and squashes the following commits:

f064563 [Tarek Auel] change to shaHex
7ce3cdc [Tarek Auel] rely on automatic cast
a1251d6 [Tarek Auel] Merge remote-tracking branch 'upstream/master' into SPARK-8235
68eb043 [Tarek Auel] added docstring
be5aff1 [Tarek Auel] improved error message
7336c96 [Tarek Auel] added type check
cf23a80 [Tarek Auel] simplified example
ebf75ef [Tarek Auel] [SPARK-8301] updated the python documentation. Removed sha in python and scala
6d6ff0d [Tarek Auel] [SPARK-8233] added docstring
ea191a9 [Tarek Auel] [SPARK-8233] fixed signatureof python function. Added expected type to misc
e3fd7c3 [Tarek Auel] SPARK[8235] added sha to the list of __all__
e5dad4e [Tarek Auel] SPARK[8235] sha / sha1

2 files changed, 28 insertions, 0 deletions

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 355ce0e342..ef92801548 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
@@ -1415,6 +1415,22 @@ object functions {
   def md5(columnName: String): Column = md5(Column(columnName))
 
   /**
+   * Calculates the SHA-1 digest and returns the value as a 40 character hex string.
+   *
+   * @group misc_funcs
+   * @since 1.5.0
+   */
+  def sha1(e: Column): Column = Sha1(e.expr)
+
+  /**
+   * Calculates the SHA-1 digest and returns the value as a 40 character hex string.
+   *
+   * @group misc_funcs
+   * @since 1.5.0
+   */
+  def sha1(columnName: String): Column = sha1(Column(columnName))
+
+  /**
    * Calculates the SHA-2 family of hash functions and returns the value as a hex string.
    *
    * @group misc_funcs
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 8baed57a7f..abfd47c811 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
@@ -144,6 +144,18 @@ class DataFrameFunctionsSuite extends QueryTest {
       Row("902fbdd2b1df0c4f70b4a5d23525e932", "6ac1e56bc78f031059be7be854522c4c"))
   }
 
+  test("misc sha1 function") {
+    val df = Seq(("ABC", "ABC".getBytes)).toDF("a", "b")
+    checkAnswer(
+      df.select(sha1($"a"), sha1("b")),
+      Row("3c01bdbb26f358bab27f267924aa2c9a03fcfdb8", "3c01bdbb26f358bab27f267924aa2c9a03fcfdb8"))
+
+    val dfEmpty = Seq(("", "".getBytes)).toDF("a", "b")
+    checkAnswer(
+      dfEmpty.selectExpr("sha1(a)", "sha1(b)"),
+      Row("da39a3ee5e6b4b0d3255bfef95601890afd80709", "da39a3ee5e6b4b0d3255bfef95601890afd80709"))
+  }
+
   test("misc sha2 function") {
     val df = Seq(("ABC", Array[Byte](1, 2, 3, 4, 5, 6))).toDF("a", "b")
     checkAnswer(