Add isEmpty to Java, Python

Author: srowen

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

@@ -435,6 +435,12 @@ trait JavaRDDLike[T, This <: JavaRDDLike[T, This]] extends Serializable {
    */
   def first(): T = rdd.first()
 
+  /**
+   * @return true if and only if the RDD contains no elements at all. Note that an RDD
+   *         may be empty even when it has at least 1 partition.
+   */
+  def isEmpty(): Boolean = rdd.isEmpty()
+
   /**
    * Save this RDD as a text file, using string representations of elements.
    */

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

@@ -606,6 +606,13 @@ public void take() {
     rdd.takeSample(false, 2, 42);
   }
 
+  @Test
+  public void isEmpty() {
+    Assert.assertTrue(sc.emptyRDD().isEmpty());
+    Assert.assertTrue(sc.parallelize(new ArrayList<Integer>()).isEmpty());
+    Assert.assertFalse(sc.parallelize(Arrays.asList(1)).isEmpty());
+  }
+
   @Test
   public void cartesian() {
     JavaDoubleRDD doubleRDD = sc.parallelizeDoubles(Arrays.asList(1.0, 1.0, 2.0, 3.0, 5.0, 8.0));

python/pyspark/rdd.py

@@ -1130,6 +1130,18 @@ def first(self):
             return rs[0]
         raise ValueError("RDD is empty")
 
+    def isEmpty(self):
+        """
+        Returns true if and only if the RDD contains no elements at all. Note that an RDD
+        may be empty even when it has at least 1 partition.
+
+        >>> sc.parallelize([]).isEmpty()
+        True
+        >>> sc.parallelize([1]).isEmpty()
+        False
+        """
+        return self._jrdd.partitions().size() == 0 or len(self.take(1)) == 0
+
     def saveAsNewAPIHadoopDataset(self, conf, keyConverter=None, valueConverter=None):
         """
         Output a Python RDD of key-value pairs (of form C{RDD[(K, V)]}) to any Hadoop file