Github user JoshRosen commented on a diff in the pull request:
https://github.com/apache/spark/pull/6971#discussion_r34746496
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
---
@@ -47,6 +47,45 @@ case class Md5(child: Expression) extends
UnaryExpression with ExpectsInputTypes
}
/**
+ * 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)) }
--- End diff --
The ordering of the map keys in `foreach` is not stable, so I think this
may lead to unstable hashcodes for identical maps.
---
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]
