Add function unhex

Author: zhichao-li

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala

@@ -156,6 +156,7 @@ object FunctionRegistry {
     expression[Substring]("substr"),
     expression[Substring]("substring"),
     expression[Upper]("ucase"),
+    expression[UnHex]("unhex"),
     expression[Upper]("upper")
   )
 

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/math.scala

@@ -354,6 +354,44 @@ case class Pow(left: Expression, right: Expression)
   }
 }
 
+/**
+ * Performs the inverse operation of HEX.
+ * Resulting characters are returned as a byte array.
+ */
+case class UnHex(child: Expression)
+  extends UnaryExpression with ExpectsInputTypes with Serializable  {
+
+  override def expectedChildTypes: Seq[DataType] = Seq(StringType)
+
+  override def dataType: DataType = BinaryType
+
+  override def eval(input: InternalRow): Any = {
+    val num = child.eval(input)
+    if (num == null) {
+      null
+    } else {
+      unhex(num.asInstanceOf[UTF8String].toString)
+    }
+  }
+  
+  private def unhex(s: String): Array[Byte] = {
+    // append a leading 0 if needed
+    val str = if (s.length % 2 == 1) {"0" + s} else {s}
+    val result = new Array[Byte](str.length / 2)
+    var i = 0
+    while (i < str.length()) {
+      try {
+        result(i / 2) = Integer.parseInt(str.substring(i, i + 2), 16).asInstanceOf[Byte]
+      } catch {
+        // invalid character present, return null
+        case _: NumberFormatException => return null
+      }
+      i += 2
+    }
+    result
+  }
+}
+
 case class Hypot(left: Expression, right: Expression)
   extends BinaryMathExpression(math.hypot, "HYPOT")
 

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/MathFunctionsSuite.scala

@@ -238,6 +238,14 @@ class MathFunctionsSuite extends SparkFunSuite with ExpressionEvalHelper {
     // scalastyle:on
   }
 
+  test("unhex") {
+    checkEvaluation(UnHex(Literal("737472696E67")), "string".getBytes)
+    // scalastyle:off
+    // Turn off scala style for non-ascii chars
+    checkEvaluation(UnHex(Literal("E4B889E9878DE79A84")), "三重的".getBytes)
+    // scalastyle:on
+  }
+
   test("hypot") {
     testBinary(Hypot, math.hypot)
   }

sql/core/src/main/scala/org/apache/spark/sql/functions.scala

@@ -1062,6 +1062,24 @@ 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.
    *

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))
+
+  }
+
   test("hypot") {
     testTwoToOneMathFunction(hypot, hypot, math.hypot)
   }