Adding Java versions and associated tests

5 files changed, 55 insertions, 1 deletions

diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala b/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala
index f9b6ee351a..043cb183ba 100644
--- a/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala
+++ b/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala
@@ -94,6 +94,17 @@ class JavaDoubleRDD(val srdd: RDD[scala.Double]) extends JavaRDDLike[Double, Jav
     fromRDD(srdd.coalesce(numPartitions, shuffle))
 
   /**
+   * Return a new RDD that has exactly numPartitions partitions.
+   *
+   * Can increase or decrease the level of parallelism in this RDD. Internally, this uses
+   * a shuffle to redistribute data.
+   *
+   * If you are decreasing the number of partitions in this RDD, consider using `coalesce`,
+   * which can avoid performing a shuffle.
+   */
+  def repartition(numPartitions: Int): JavaDoubleRDD = fromRDD(srdd.repartition(numPartitions))
+
+  /**
    * Return an RDD with the elements from `this` that are not in `other`.
    * 
    * Uses `this` partitioner/partition size, because even if `other` is huge, the resulting
diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala b/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala
index 268f43b4e8..39f408b8c8 100644
--- a/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala
+++ b/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala
@@ -108,6 +108,17 @@ class JavaPairRDD[K, V](val rdd: RDD[(K, V)])(implicit val kManifest: ClassManif
     fromRDD(rdd.coalesce(numPartitions, shuffle))
 
   /**
+   * Return a new RDD that has exactly numPartitions partitions.
+   *
+   * Can increase or decrease the level of parallelism in this RDD. Internally, this uses
+   * a shuffle to redistribute data.
+   *
+   * If you are decreasing the number of partitions in this RDD, consider using `coalesce`,
+   * which can avoid performing a shuffle.
+   */
+  def repartition(numPartitions: Int): JavaPairRDD[K, V] = fromRDD(rdd.repartition(numPartitions))
+
+  /**
    * Return a sampled subset of this RDD.
    */
   def sample(withReplacement: Boolean, fraction: Double, seed: Int): JavaPairRDD[K, V] =
diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaRDD.scala b/core/src/main/scala/org/apache/spark/api/java/JavaRDD.scala
index 662990049b..3b359a8fd6 100644
--- a/core/src/main/scala/org/apache/spark/api/java/JavaRDD.scala
+++ b/core/src/main/scala/org/apache/spark/api/java/JavaRDD.scala
@@ -82,6 +82,17 @@ JavaRDDLike[T, JavaRDD[T]] {
     rdd.coalesce(numPartitions, shuffle)
 
   /**
+   * Return a new RDD that has exactly numPartitions partitions.
+   *
+   * Can increase or decrease the level of parallelism in this RDD. Internally, this uses
+   * a shuffle to redistribute data.
+   *
+   * If you are decreasing the number of partitions in this RDD, consider using `coalesce`,
+   * which can avoid performing a shuffle.
+   */
+  def repartition(numPartitions: Int): JavaRDD[T] = rdd.repartition(numPartitions)
+
+  /**
    * Return a sampled subset of this RDD.
    */
   def sample(withReplacement: Boolean, fraction: Double, seed: Int): JavaRDD[T] =
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 17bc2515f2..6e88be6f6a 100644
--- a/core/src/main/scala/org/apache/spark/rdd/RDD.scala
+++ b/core/src/main/scala/org/apache/spark/rdd/RDD.scala
@@ -268,7 +268,7 @@ abstract class RDD[T: ClassManifest](
   /**
    * Return a new RDD that has exactly numPartitions partitions.
    *
-   * Used to increase or decrease the level of parallelism in this RDD. This will use
+   * Can increase or decrease the level of parallelism in this RDD. Internally, this uses
    * a shuffle to redistribute data.
    *
    * If you are decreasing the number of partitions in this RDD, consider using `coalesce`,
diff --git a/core/src/test/scala/org/apache/spark/JavaAPISuite.java b/core/src/test/scala/org/apache/spark/JavaAPISuite.java
index 7b0bb89ab2..f38c607d65 100644
--- a/core/src/test/scala/org/apache/spark/JavaAPISuite.java
+++ b/core/src/test/scala/org/apache/spark/JavaAPISuite.java
@@ -473,6 +473,27 @@ public class JavaAPISuite implements Serializable {
   }
 
   @Test
+  public void repartition() {
+    // Shrinking number of partitions
+    JavaRDD<Integer> in1 = sc.parallelize(Arrays.asList(1,2,3,4,5,6,7,8), 2);
+    JavaRDD<Integer> repartitioned1 = in1.repartition(4);
+    List<List<Integer>> result1 = repartitioned1.glom().collect();
+    Assert.assertEquals(4, result1.size());
+    for (List<Integer> l: result1) {
+      Assert.assertTrue(l.size() > 0);
+    }
+
+    // Growing number of partitions
+    JavaRDD<Integer> in2 = sc.parallelize(Arrays.asList(1,2,3,4,5,6,7,8), 4);
+    JavaRDD<Integer> repartitioned2 = in2.repartition(2);
+    List<List<Integer>> result2 = repartitioned2.glom().collect();
+    Assert.assertEquals(2, result2.size());
+    for (List<Integer> l: result2) {
+      Assert.assertTrue(l.size() > 0);
+    }
+  }
+
+  @Test
   public void persist() {
     JavaDoubleRDD doubleRDD = sc.parallelizeDoubles(Arrays.asList(1.0, 1.0, 2.0, 3.0, 5.0, 8.0));
     doubleRDD = doubleRDD.persist(StorageLevel.DISK_ONLY());