From 8fbd5380b7f36842297f624bad3a2513f7eca47b Mon Sep 17 00:00:00 2001 From: Josh Rosen Date: Sun, 3 Feb 2013 06:44:49 +0000 Subject: Fetch fewer objects in PySpark's take() method. --- core/src/main/scala/spark/api/python/PythonRDD.scala | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'core') diff --git a/core/src/main/scala/spark/api/python/PythonRDD.scala b/core/src/main/scala/spark/api/python/PythonRDD.scala index 39758e94f4..ab8351e55e 100644 --- a/core/src/main/scala/spark/api/python/PythonRDD.scala +++ b/core/src/main/scala/spark/api/python/PythonRDD.scala @@ -238,6 +238,11 @@ private[spark] object PythonRDD { } def writeIteratorToPickleFile[T](items: java.util.Iterator[T], filename: String) { + import scala.collection.JavaConverters._ + writeIteratorToPickleFile(items.asScala, filename) + } + + def writeIteratorToPickleFile[T](items: Iterator[T], filename: String) { val file = new DataOutputStream(new FileOutputStream(filename)) for (item <- items) { writeAsPickle(item, file) @@ -245,8 +250,10 @@ private[spark] object PythonRDD { file.close() } - def takePartition[T](rdd: RDD[T], partition: Int): java.util.Iterator[T] = - rdd.context.runJob(rdd, ((x: Iterator[T]) => x), Seq(partition), true).head + def takePartition[T](rdd: RDD[T], partition: Int): Iterator[T] = { + implicit val cm : ClassManifest[T] = rdd.elementClassManifest + rdd.context.runJob(rdd, ((x: Iterator[T]) => x.toArray), Seq(partition), true).head.iterator + } } private object Pickle { -- cgit v1.2.3