From 6471bfec736b033a94a96575255f2d4453082709 Mon Sep 17 00:00:00 2001
From: Stephen Haberman <stephen@exigencecorp.com>
Date: Mon, 9 Sep 2013 11:44:15 -0500
Subject: [PATCH] Reword 'evenly distributed' to 'distributed with a hash
partitioner.
---
core/src/main/scala/org/apache/spark/rdd/RDD.scala | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/core/src/main/scala/org/apache/spark/rdd/RDD.scala b/core/src/main/scala/org/apache/spark/rdd/RDD.scala
index 41a90f139e..1082cbae3e 100644
--- a/core/src/main/scala/org/apache/spark/rdd/RDD.scala
+++ b/core/src/main/scala/org/apache/spark/rdd/RDD.scala
@@ -282,8 +282,8 @@ abstract class RDD[T: ClassManifest](
* Note: With shuffle = true, you can actually coalesce to a larger number
* of partitions. This is useful if you have a small number of partitions,
* say 100, potentially with a few partitions being abnormally large. Calling
- * coalecse(1000, shuffle = true) will result in 1000 partitions with the
- * data evenly distributed into each partition.
+ * coalesce(1000, shuffle = true) will result in 1000 partitions with the
+ * data distributed using a hash partitioner.
*/
def coalesce(numPartitions: Int, shuffle: Boolean = false): RDD[T] = {
if (shuffle) {
--
GitLab