SPARK-1509: add zipWithIndex zipWithUniqueId methods to java api

core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala

@@ -18,7 +18,7 @@
 package org.apache.spark.api.java
 
 import java.util.{Comparator, List => JList, Iterator => JIterator}
-import java.lang.{Iterable => JIterable}
+import java.lang.{Iterable => JIterable, Long => JLong}
 
 import scala.collection.JavaConversions._
 import scala.reflect.ClassTag
@@ -264,6 +264,26 @@ trait JavaRDDLike[T, This <: JavaRDDLike[T, This]] extends Serializable {
       rdd.zipPartitions(other.rdd)(fn)(other.classTag, fakeClassTag[V]))(fakeClassTag[V])
   }
 
+  /**
+   * Zips this RDD with generated unique Long ids. Items in the kth partition will get ids k, n+k,
+   * 2*n+k, ..., where n is the number of partitions. So there may exist gaps, but this method
+   * won't trigger a spark job, which is different from [[org.apache.spark.rdd.RDD#zipWithIndex]].
+   */
+  def zipWithUniqueId(): JavaPairRDD[T, JLong] = {
+    JavaPairRDD.fromRDD(rdd.zipWithUniqueId()).asInstanceOf[JavaPairRDD[T, JLong]]
+  }
+
+  /**
+   * Zips this RDD with its element indices. The ordering is first based on the partition index
+   * and then the ordering of items within each partition. So the first item in the first
+   * partition gets index 0, and the last item in the last partition receives the largest index.
+   * This is similar to Scala's zipWithIndex but it uses Long instead of Int as the index type.
+   * This method needs to trigger a spark job when this RDD contains more than one partitions.
+   */
+  def zipWithIndex(): JavaPairRDD[T, JLong] = {
+    JavaPairRDD.fromRDD(rdd.zipWithIndex()).asInstanceOf[JavaPairRDD[T, JLong]]
+  }
+
   // Actions (launch a job to return a value to the user program)
 
   /**

core/src/test/java/org/apache/spark/JavaAPISuite.java

@@ -182,13 +182,30 @@ public void call(String s) {
     Assert.assertEquals(2, foreachCalls);
   }
 
-    @Test
-    public void toLocalIterator() {
-        List<Integer> correct = Arrays.asList(1, 2, 3, 4);
-        JavaRDD<Integer> rdd = sc.parallelize(correct);
-        List<Integer> result = Lists.newArrayList(rdd.toLocalIterator());
-        Assert.assertTrue(correct.equals(result));
-    }
+  @Test
+  public void toLocalIterator() {
+    List<Integer> correct = Arrays.asList(1, 2, 3, 4);
+    JavaRDD<Integer> rdd = sc.parallelize(correct);
+    List<Integer> result = Lists.newArrayList(rdd.toLocalIterator());
+    Assert.assertTrue(correct.equals(result));
+  }
+
+  @Test
+  public void zipWithUniqueId() {
+    List<Integer> dataArray = Arrays.asList(1, 2, 3, 4);
+    JavaPairRDD<Integer, Long> zip = sc.parallelize(dataArray).zipWithUniqueId();
+    JavaRDD<Long> indexes = zip.values();
+    Assert.assertTrue(new HashSet<Long>(indexes.collect()).size() == 4);
+  }
+
+  @Test
+  public void zipWithIndex() {
+    List<Integer> dataArray = Arrays.asList(1, 2, 3, 4);
+    JavaPairRDD<Integer, Long> zip = sc.parallelize(dataArray).zipWithIndex();
+    JavaRDD<Long> indexes = zip.values();
+    List<Long> correctIndexes = Arrays.asList(0L, 1L, 2L, 3L);
+    Assert.assertTrue(indexes.collect().equals(correctIndexes));
+  }
 
   @SuppressWarnings("unchecked")
   @Test