Github user chenghao-intel commented on a diff in the pull request:
https://github.com/apache/spark/pull/6971#discussion_r33906097
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
---
@@ -47,4 +48,44 @@ case class Md5(child: Expression)
"org.apache.spark.unsafe.types.UTF8String.fromString" +
s"(org.apache.commons.codec.digest.DigestUtils.md5Hex($c))")
}
+
+}
+
+/**
+ * A function that returns a hash value of the argument
+ */
+case class Hash(children: Expression*) extends Expression {
+
+ override def foldable: Boolean = children.forall(_.foldable)
+ override def nullable: Boolean = children(0).nullable
+ override def dataType: DataType = IntegerType
+
+ override def eval(input: InternalRow): Any = {
+ val arglist = children.map(_.eval(input).asInstanceOf[AnyRef])
+ hashCode(arglist)
+ }
+
+ def hashCode(v: Any): Int = v match {
+ case null => 0
+ case arr: Array[_] => {
+ arr.foldLeft(0) { (acc, n) => acc + hashCode(n) }
+ }
+ case seq: Seq[_] => {
+ seq.foldLeft(0) { (acc, n) => acc + hashCode(n) }
+ }
+ case m: Map[_, _] => {
+ var res: Int = 0
+ m.foreach { case (k, v) => res += (hashCode(k) + hashCode(v)) }
+ res
+ }
+ case r: Row => {
+ var res: Int = 0
+ for (i <- 0 until r.length) {
+ res += 31 * res + hashCode(r.get(i))
+ }
+ res
+ }
+ case others => others.hashCode()
+ }
+
--- End diff --
That's required a recursive revisting all of its elements for the complex
data type, code gen here probably be difficult (not easy to maintain compare to
the performance gain).
---
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]
