From ada384b785c663392a0b69fad5bfe7a0a0584ee0 Mon Sep 17 00:00:00 2001
From: Sean Owen <sowen@cloudera.com>
Date: Tue, 30 Jun 2015 10:07:26 -0700
Subject: [PATCH] [SPARK-8437] [DOCS] Corrected: Using directory path without
 wildcard for filename slow for large number of files with wholeTextFiles and
 binaryFiles

Note that 'dir/*' can be more efficient in some Hadoop FS implementations that 'dir/' (now fixed scaladoc by using HTML entity for *)

Author: Sean Owen <sowen@cloudera.com>

Closes #7126 from srowen/SPARK-8437.2 and squashes the following commits:

7bb45da [Sean Owen] Note that 'dir/*' can be more efficient in some Hadoop FS implementations that 'dir/' (now fixed scaladoc by using HTML entity for *)
---
 core/src/main/scala/org/apache/spark/SparkContext.scala | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala
index b3c3bf3746..0e5a86f44e 100644
--- a/core/src/main/scala/org/apache/spark/SparkContext.scala
+++ b/core/src/main/scala/org/apache/spark/SparkContext.scala
@@ -831,7 +831,8 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli
    * }}}
    *
    * @note Small files are preferred, large file is also allowable, but may cause bad performance.
-   *
+   * @note On some filesystems, `.../path/&#42;` can be a more efficient way to read all files
+   *       in a directory rather than `.../path/` or `.../path`
    * @param minPartitions A suggestion value of the minimal splitting number for input data.
    */
   def wholeTextFiles(
@@ -878,9 +879,10 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli
    *   (a-hdfs-path/part-nnnnn, its content)
    * }}}
    *
-   * @param minPartitions A suggestion value of the minimal splitting number for input data.
-   *
    * @note Small files are preferred; very large files may cause bad performance.
+   * @note On some filesystems, `.../path/&#42;` can be a more efficient way to read all files
+   *       in a directory rather than `.../path/` or `.../path`
+   * @param minPartitions A suggestion value of the minimal splitting number for input data.
    */
   @Experimental
   def binaryFiles(
-- 
GitLab