Non penso che sia disponibile in Spark di default ma è facile da implementare con ReceiverInputDStream.
import org.apache.spark.storage.StorageLevel
import org.apache.spark.streaming.StreamingContext
import org.apache.spark.streaming.dstream.ReceiverInputDStream
import org.apache.spark.streaming.receiver.Receiver
class InfiniteStreamInputDStream[T](
@transient ssc_ : StreamingContext,
stream: Stream[T],
storageLevel: StorageLevel
) extends ReceiverInputDStream[T](ssc_) {
override def getReceiver(): Receiver[T] = {
new InfiniteStreamReceiver(stream, storageLevel)
}
}
class InfiniteStreamReceiver[T](stream: Stream[T], storageLevel: StorageLevel) extends Receiver[T](storageLevel) {
// Stateful iterator
private val streamIterator = stream.iterator
private class ReadAndStore extends Runnable {
def run(): Unit = {
while (streamIterator.hasNext) {
val next = streamIterator.next()
store(next)
}
}
}
override def onStart(): Unit = {
new Thread(new ReadAndStore).run()
}
override def onStop(): Unit = { }
}
fonte
2015-01-02 16:30:05