[SPARK-8227] [SQL] Add function unhex

cc chenghao-intel  adrian-wang

Author: zhichao.li <zhichao.li@intel.com>

Closes #7113 from zhichao-li/unhex and squashes the following commits:

379356e [zhichao.li] remove exception checking
a4ae6dc [zhichao.li] add udf_unhex to whitelist
fe5c14a [zhichao.li] add todigit
607d7a3 [zhichao.li] use checkInputTypes
bffd37f [zhichao.li] change to use Hex in apache common package
cde73f5 [zhichao.li] update to use AutoCastInputTypes
11945c7 [zhichao.li] style
c852d46 [zhichao.li] Add function unhex

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 4e8f3f96bf..e6f623bdf3 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
@@ -1054,6 +1054,24 @@ object functions {
   def hex(colName: String): Column = hex(Column(colName))
 
   /**
+   * Inverse of hex. Interprets each pair of characters as a hexadecimal number
+   * and converts to the byte representation of number.
+   *
+   * @group math_funcs
+   * @since 1.5.0
+   */
+  def unhex(column: Column): Column = UnHex(column.expr)
+
+  /**
+   * Inverse of hex. Interprets each pair of characters as a hexadecimal number
+   * and converts to the byte representation of number.
+   *
+   * @group math_funcs
+   * @since 1.5.0
+   */
+  def unhex(colName: String): Column = unhex(Column(colName))
+
+  /**
    * Computes `sqrt(a^2^ + b^2^)` without intermediate overflow or underflow.
    *
    * @group math_funcs
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/MathExpressionsSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/MathExpressionsSuite.scala
index d6331aa4ff..c03cde38d7 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/MathExpressionsSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/MathExpressionsSuite.scala
@@ -225,6 +225,16 @@ class MathExpressionsSuite extends QueryTest {
     checkAnswer(data.selectExpr("hex(cast(d as binary))"), Seq(Row("68656C6C6F")))
   }
 
+  test("unhex") {
+    val data = Seq(("1C", "737472696E67")).toDF("a", "b")
+    checkAnswer(data.select(unhex('a)), Row(Array[Byte](28.toByte)))
+    checkAnswer(data.select(unhex('b)), Row("string".getBytes))
+    checkAnswer(data.selectExpr("unhex(a)"), Row(Array[Byte](28.toByte)))
+    checkAnswer(data.selectExpr("unhex(b)"), Row("string".getBytes))
+    checkAnswer(data.selectExpr("""unhex("##")"""), Row(null))
+    checkAnswer(data.selectExpr("""unhex("G123")"""), Row(null))
+  }
+
   test("hypot") {
     testTwoToOneMathFunction(hypot, hypot, math.hypot)
   }