diff --git a/core/src/main/scala/spark/RDD.scala b/core/src/main/scala/spark/RDD.scala index 4d984591bd633260c2824144f5813c69ff7c59ca..17869fb31b69055b12f93e979756438737410495 100644 --- a/core/src/main/scala/spark/RDD.scala +++ b/core/src/main/scala/spark/RDD.scala @@ -188,7 +188,7 @@ abstract class RDD[T: ClassManifest](@transient sc: SparkContext) extends Serial map(x => (x, null)).reduceByKey((x, y) => x, numSplits).map(_._1) /** - * Return a sampled subset of this RDD. + * Return a sampled subset of this RDD. */ def sample(withReplacement: Boolean, fraction: Double, seed: Int): RDD[T] = new SampledRDD(this, withReplacement, fraction, seed) @@ -305,7 +305,7 @@ abstract class RDD[T: ClassManifest](@transient sc: SparkContext) extends Serial val results = sc.runJob(this, (iter: Iterator[T]) => iter.toArray) Array.concat(results: _*) } - + /** * Return an array that contains all of the elements in this RDD. */ @@ -471,7 +471,7 @@ abstract class RDD[T: ClassManifest](@transient sc: SparkContext) extends Serial } /** - * Save this RDD as a text file, using string representations of elements. + * Save this RDD as a text file, using string representations of elements. */ def saveAsTextFile(path: String) { this.map(x => (NullWritable.get(), new Text(x.toString))) @@ -479,7 +479,7 @@ abstract class RDD[T: ClassManifest](@transient sc: SparkContext) extends Serial } /** - * Save this RDD as a SequenceFile of serialized objects. + * Save this RDD as a SequenceFile of serialized objects. */ def saveAsObjectFile(path: String) { this.mapPartitions(iter => iter.grouped(10).map(_.toArray)) diff --git a/core/src/main/scala/spark/SparkContext.scala b/core/src/main/scala/spark/SparkContext.scala index 84fc541f82ef543f41d85cb8de91433f16bdd9a7..47e002201ba3d79986af6649f05e052ecc059745 100644 --- a/core/src/main/scala/spark/SparkContext.scala +++ b/core/src/main/scala/spark/SparkContext.scala @@ -54,15 +54,21 @@ import spark.storage.BlockManagerMaster * Main entry point for Spark functionality. A SparkContext represents the connection to a Spark * cluster, and can be used to create RDDs, accumulators and broadcast variables on that cluster. * + * @constructor Returns a new SparkContext. * @param master Cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]). * @param jobName A name for your job, to display on the cluster web UI - * @param sparkHome Location where Spark is instaled on cluster nodes + * @param sparkHome Location where Spark is installed on cluster nodes * @param jars Collection of JARs to send to the cluster. These can be paths on the local file * system or HDFS, HTTP, HTTPS, or FTP URLs. */ class SparkContext(master: String, jobName: String, val sparkHome: String, val jars: Seq[String]) extends Logging { + /** + * @constructor Returns a new SparkContext. + * @param master Cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]). + * @param jobName A name for your job, to display on the cluster web UI + */ def this(master: String, jobName: String) = this(master, jobName, null, Nil) // Ensure logging is initialized before we spawn any threads