Github user andrewor14 commented on a diff in the pull request:
https://github.com/apache/spark/pull/7403#discussion_r38458197
--- Diff: core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala
---
@@ -103,13 +105,46 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])
}
/**
- * Simplified version of combineByKey that hash-partitions the output
RDD.
+ * This method is here for backward compatibility. It
+ * does not provide combiner classtag information to
+ * the shuffle.
+ *
+ * @see [[combineByKeyWithClassTag]]
+ */
+ def combineByKey[C](createCombiner: V => C,
+ mergeValue: (C, V) => C,
+ mergeCombiners: (C, C) => C,
+ partitioner: Partitioner,
+ mapSideCombine: Boolean = true,
+ serializer: Serializer = null): RDD[(K, C)] = {
+ combineByKeyWithClassTag(createCombiner, mergeValue, mergeCombiners,
+ partitioner, mapSideCombine, serializer)(null)
+ }
+
+ /**
+ * This method is here for backward compatibility. It
+ * does not provide combiner classtag information to
+ * the shuffle.
+ *
+ * @see [[combineByKeyWithClassTag]]
*/
def combineByKey[C](createCombiner: V => C,
mergeValue: (C, V) => C,
mergeCombiners: (C, C) => C,
- numPartitions: Int): RDD[(K, C)] = self.withScope {
- combineByKey(createCombiner, mergeValue, mergeCombiners, new
HashPartitioner(numPartitions))
+ numPartitions: Int): RDD[(K, C)] = {
+ combineByKeyWithClassTag(createCombiner, mergeValue, mergeCombiners,
numPartitions)(null)
+ }
+
+ /**
+ * Simplified version of combineByKeyWithClassTag that hash-partitions
the output RDD.
+ */
+ def combineByKeyWithClassTag[C](createCombiner: V => C,
+ mergeValue: (C, V) => C,
+ mergeCombiners: (C, C) => C,
+ numPartitions: Int)
--- End diff --
style
---
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]
