Add comment explaining collectPartitions's use

robinkeunen · Dec 19, 2013 · 9cc3a6d · 9cc3a6d
1 parent d3234f9
commit 9cc3a6d
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala b/core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala
@@ -248,6 +248,8 @@ trait JavaRDDLike[T, This <: JavaRDDLike[T, This]] extends Serializable {
    * Return an array that contains all of the elements in a specific partition of this RDD.
    */
   def collectPartitions(partitionIds: Array[Int]): Array[JList[T]] = {
+    // This is useful for implementing `take` from other language frontends
+    // like Python where the data is serialized.
     import scala.collection.JavaConversions._
     val res = context.runJob(rdd, (it: Iterator[T]) => it.toArray, partitionIds, true)
     res.map(x => new java.util.ArrayList(x.toSeq)).toArray