diff options
author | Matei Zaharia <matei@databricks.com> | 2014-05-10 12:10:24 -0700 |
---|---|---|
committer | Patrick Wendell <pwendell@gmail.com> | 2014-05-10 12:10:24 -0700 |
commit | 7eefc9d2b3f6ebc0ecb5562da7323f1e06afbb35 (patch) | |
tree | 32a35b0898c5710cdbd73b56ef9dcb9914e1cf02 /examples/src/main | |
parent | 8e94d2721a9d3d36697e13f8cc6567ae8aeee78b (diff) | |
download | spark-7eefc9d2b3f6ebc0ecb5562da7323f1e06afbb35.tar.gz spark-7eefc9d2b3f6ebc0ecb5562da7323f1e06afbb35.tar.bz2 spark-7eefc9d2b3f6ebc0ecb5562da7323f1e06afbb35.zip |
SPARK-1708. Add a ClassTag on Serializer and things that depend on it
This pull request contains a rebased patch from @heathermiller (https://github.com/heathermiller/spark/pull/1) to add ClassTags on Serializer and types that depend on it (Broadcast and AccumulableCollection). Putting these in the public API signatures now will allow us to use Scala Pickling for serialization down the line without breaking binary compatibility.
One question remaining is whether we also want them on Accumulator -- Accumulator is passed as part of a bigger Task or TaskResult object via the closure serializer so it doesn't seem super useful to add the ClassTag there. Broadcast and AccumulableCollection in contrast were being serialized directly.
CC @rxin, @pwendell, @heathermiller
Author: Matei Zaharia <matei@databricks.com>
Closes #700 from mateiz/spark-1708 and squashes the following commits:
1a3d8b0 [Matei Zaharia] Use fake ClassTag in Java
3b449ed [Matei Zaharia] test fix
2209a27 [Matei Zaharia] Code style fixes
9d48830 [Matei Zaharia] Add a ClassTag on Serializer and things that depend on it
Diffstat (limited to 'examples/src/main')
-rw-r--r-- | examples/src/main/scala/org/apache/spark/examples/bagel/WikipediaPageRankStandalone.scala | 12 |
1 files changed, 7 insertions, 5 deletions
diff --git a/examples/src/main/scala/org/apache/spark/examples/bagel/WikipediaPageRankStandalone.scala b/examples/src/main/scala/org/apache/spark/examples/bagel/WikipediaPageRankStandalone.scala index a197dac87d..576a3e371b 100644 --- a/examples/src/main/scala/org/apache/spark/examples/bagel/WikipediaPageRankStandalone.scala +++ b/examples/src/main/scala/org/apache/spark/examples/bagel/WikipediaPageRankStandalone.scala @@ -28,6 +28,8 @@ import org.apache.spark.serializer.{DeserializationStream, SerializationStream, import org.apache.spark.SparkContext._ import org.apache.spark.rdd.RDD +import scala.reflect.ClassTag + object WikipediaPageRankStandalone { def main(args: Array[String]) { if (args.length < 4) { @@ -143,15 +145,15 @@ class WPRSerializer extends org.apache.spark.serializer.Serializer { } class WPRSerializerInstance extends SerializerInstance { - def serialize[T](t: T): ByteBuffer = { + def serialize[T: ClassTag](t: T): ByteBuffer = { throw new UnsupportedOperationException() } - def deserialize[T](bytes: ByteBuffer): T = { + def deserialize[T: ClassTag](bytes: ByteBuffer): T = { throw new UnsupportedOperationException() } - def deserialize[T](bytes: ByteBuffer, loader: ClassLoader): T = { + def deserialize[T: ClassTag](bytes: ByteBuffer, loader: ClassLoader): T = { throw new UnsupportedOperationException() } @@ -167,7 +169,7 @@ class WPRSerializerInstance extends SerializerInstance { class WPRSerializationStream(os: OutputStream) extends SerializationStream { val dos = new DataOutputStream(os) - def writeObject[T](t: T): SerializationStream = t match { + def writeObject[T: ClassTag](t: T): SerializationStream = t match { case (id: String, wrapper: ArrayBuffer[_]) => wrapper(0) match { case links: Array[String] => { dos.writeInt(0) // links @@ -200,7 +202,7 @@ class WPRSerializationStream(os: OutputStream) extends SerializationStream { class WPRDeserializationStream(is: InputStream) extends DeserializationStream { val dis = new DataInputStream(is) - def readObject[T](): T = { + def readObject[T: ClassTag](): T = { val typeId = dis.readInt() typeId match { case 0 => { |