Repository: incubator-spark Updated Branches: refs/heads/master 9e63f80e7 -> 3fede4831
Super minor: Add require for mergeCombiners in combineByKey We changed the behavior in 0.9.0 from requiring that mergeCombiners be null when mapSideCombine was false to requiring that mergeCombiners *never* be null, for external sorting. This patch adds a require() to make this behavior change explicitly messaged rather than resulting in a NPE. Author: Aaron Davidson <aa...@databricks.com> Closes #623 from aarondav/master and squashes the following commits: 520b80c [Aaron Davidson] Super minor: Add require for mergeCombiners in combineByKey Project: http://git-wip-us.apache.org/repos/asf/incubator-spark/repo Commit: http://git-wip-us.apache.org/repos/asf/incubator-spark/commit/3fede483 Tree: http://git-wip-us.apache.org/repos/asf/incubator-spark/tree/3fede483 Diff: http://git-wip-us.apache.org/repos/asf/incubator-spark/diff/3fede483 Branch: refs/heads/master Commit: 3fede4831eeb7d36d4f8fa4aaa02ad0cc8b4b09e Parents: 9e63f80 Author: Aaron Davidson <aa...@databricks.com> Authored: Thu Feb 20 16:46:13 2014 -0800 Committer: Patrick Wendell <pwend...@gmail.com> Committed: Thu Feb 20 16:46:13 2014 -0800 ---------------------------------------------------------------------- core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala | 1 + 1 file changed, 1 insertion(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/incubator-spark/blob/3fede483/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala ---------------------------------------------------------------------- diff --git a/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala b/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala index 15bec39..39c3a49 100644 --- a/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala +++ b/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala @@ -77,6 +77,7 @@ class PairRDDFunctions[K: ClassTag, V: ClassTag](self: RDD[(K, V)]) partitioner: Partitioner, mapSideCombine: Boolean = true, serializerClass: String = null): RDD[(K, C)] = { + require(mergeCombiners != null, "mergeCombiners must be defined") // required as of Spark 0.9.0 if (getKeyClass().isArray) { if (mapSideCombine) { throw new SparkException("Cannot use map-side combining with array keys.")
