Merge pull request #437 from mridulm/master

Minor api usability changes

- Expose checkpoint directory - since it is autogenerated now
- null check for jars
- Expose SparkHadoopUtil : so that configuration creation is abstracted even from user code to avoid duplication of functionality already in spark.

core/src/main/scala/org/apache/spark/SparkContext.scala

@@ -956,6 +956,8 @@ class SparkContext(
     }
   }
 
+  def getCheckpointDir = checkpointDir
+
   /** Default level of parallelism to use when not given by user (e.g. parallelize and makeRDD). */
   def defaultParallelism: Int = taskScheduler.defaultParallelism
 
@@ -1125,7 +1127,7 @@ object SparkContext {
     if (sparkHome != null) {
       res.setSparkHome(sparkHome)
     }
-    if (!jars.isEmpty) {
+    if (jars != null && !jars.isEmpty) {
       res.setJars(jars)
     }
     res.setExecutorEnv(environment.toSeq)

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

@@ -513,6 +513,8 @@ class JavaSparkContext(val sc: SparkContext) extends JavaSparkContextVarargsWork
     sc.setCheckpointDir(dir)
   }
 
+  def getCheckpointDir = JavaUtils.optionToOptional(sc.getCheckpointDir)
+
   protected def checkpointFile[T](path: String): JavaRDD[T] = {
     implicit val cm: ClassTag[T] =
       implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]]

core/src/main/scala/org/apache/spark/deploy/SparkHadoopUtil.scala

@@ -28,7 +28,6 @@ import org.apache.spark.{SparkContext, SparkException}
 /**
  * Contains util methods to interact with Hadoop from Spark.
  */
-private[spark]
 class SparkHadoopUtil {
   val conf = newConfiguration()
   UserGroupInformation.setConfiguration(conf)