Renamed the method.

Author: rxin

core/src/main/scala/org/apache/spark/util/random/SamplingUtils.scala

@@ -22,13 +22,13 @@ import scala.reflect.ClassTag
 private[spark] object SamplingUtils {
 
   /**
-   * Reservoir Sampling implementation.
+   * Reservoir sampling implementation that also returns the input size.
    *
    * @param input input size
    * @param k reservoir size
    * @return (samples, input size)
    */
-  def reservoirSample[T: ClassTag](input: Iterator[T], k: Int): (Array[T], Int) = {
+  def reservoirSampleAndCount[T: ClassTag](input: Iterator[T], k: Int): (Array[T], Int) = {
     val reservoir = new Array[T](k)
     // Put the first k elements in the reservoir.
     var i = 0

core/src/test/scala/org/apache/spark/util/random/SamplingUtilsSuite.scala

@@ -24,21 +24,21 @@ import org.scalatest.FunSuite
 
 class SamplingUtilsSuite extends FunSuite {
 
-  test("reservoirSample") {
+  test("reservoirSampleAndCount") {
     val input = Seq.fill(100)(Random.nextInt())
 
     // input size < k
-    val (sample1, count1) = SamplingUtils.reservoirSample(input.iterator, 150)
+    val (sample1, count1) = SamplingUtils.reservoirSampleAndCount(input.iterator, 150)
     assert(count1 === 100)
     assert(input === sample1.toSeq)
 
     // input size == k
-    val (sample2, count2) = SamplingUtils.reservoirSample(input.iterator, 100)
+    val (sample2, count2) = SamplingUtils.reservoirSampleAndCount(input.iterator, 100)
     assert(count2 === 100)
     assert(input === sample2.toSeq)
 
     // input size > k
-    val (sample3, count3) = SamplingUtils.reservoirSample(input.iterator, 10)
+    val (sample3, count3) = SamplingUtils.reservoirSampleAndCount(input.iterator, 10)
     assert(count3 === 100)
     assert(sample3.length === 10)
   }