Github user zhichao-li commented on a diff in the pull request:
https://github.com/apache/spark/pull/7181#discussion_r33754409
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/math.scala
---
@@ -303,6 +295,66 @@ case class Hex(child: Expression) extends
UnaryExpression with Serializable {
}
}
+/**
+ * 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 nullable: Boolean = true
+ override def dataType: DataType = BinaryType
+ override def inputTypes: Seq[DataType] = Seq(BinaryType)
+
+ override def eval(input: InternalRow): Any = {
+ val num = child.eval(input)
+ if (num == null) {
+ null
+ } else {
+ unhex(num.asInstanceOf[UTF8String].getBytes)
+ }
+ }
+
+ // lookup table to translate '0' -> 0 ... 'F'/'f' -> 15
+ private[this] val unhexDigits = {
+ val array = Array.fill[Byte](128)(-1)
+ (0 to 9).foreach(i => array('0' + i) = i.toByte)
+ (0 to 5).foreach(i => array('A' + i) = (i + 10).toByte)
+ (0 to 5).foreach(i => array('a' + i) = (i + 10).toByte)
+ array
+ }
+
+ private[this] def unhex(bytes: Array[Byte]): Array[Byte] = {
+ val out = new Array[Byte]((bytes.length + 1) >> 1)
+ var i = 0
+ if ((bytes.length & 0x01) != 0) {
+ // padding with '0'
+ if (bytes(0) < 0) {
+ return null
+ }
+ val v = unhexDigits(bytes(0))
+ if (v == -1) {
+ return null
+ }
+ out(0) = v
+ i += 1
+ }
+ // two characters form the hex value.
+ while (i < bytes.length) {
+ if (bytes(i) < 0 || bytes(i + 1) < 0) {
--- End diff --
There would be exception on my previous logic when facing non-ascii
character. Thanks for fixing this.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
