refine comments

apache · Apr 3, 2014 · 7191be6 · 7191be6
1 parent 0af3faf
commit 7191be6
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 1 deletion.
diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala
@@ -394,6 +394,8 @@ class SparkContext(
    *   ...
    *   (a-hdfs-path/part-nnnnn, its content)
    * }}}
+   *
+   * @note Small files are perferred, large file is also allowable, but may cause bad performance.
    */
   def wholeTextFiles(path: String): RDD[(String, String)] = {
     newAPIHadoopFile(

diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala b/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala
@@ -167,7 +167,7 @@ class JavaSparkContext(val sc: SparkContext) extends JavaSparkContextVarargsWork
    *   hdfs://a-hdfs-path/part-nnnnn
    * }}}
    *
-   * Do `JavaPairRDD<String, String> rdd = context.wholeTextFiles("hdfs://a-hdfs-path")`,
+   * Do `JavaPairRDD<String, String> rdd = sparkContext.wholeTextFiles("hdfs://a-hdfs-path")`,
    *
    * <p> then `rdd` contains
    * {{{
@@ -176,6 +176,8 @@ class JavaSparkContext(val sc: SparkContext) extends JavaSparkContextVarargsWork
    *   ...
    *   (a-hdfs-path/part-nnnnn, its content)
    * }}}
+   *
+   * @note Small files are perferred, large file is also allowable, but may cause bad performance.
    */
   def wholeTextFiles(path: String): JavaPairRDD[String, String] =
     new JavaPairRDD(sc.wholeTextFiles(path))