Created
July 17, 2016 19:24
-
-
Save timvw/4ec727de9b76d9afc51298d9e68c4241 to your computer and use it in GitHub Desktop.
scala wrapper for hadoop remote iterator
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
case class RemoteIteratorWrapper[T](underlying: org.apache.hadoop.fs.RemoteIterator[T]) extends scala.collection.AbstractIterator[T] with scala.collection.Iterator[T] { | |
def hasNext = underlying.hasNext | |
def next() = underlying.next() | |
} | |
object Conversions { | |
implicit def remoteIterator2ScalaIterator[T](underlying: org.apache.hadoop.fs.RemoteIterator[T]) : scala.collection.Iterator[T] = RemoteIteratorWrapper[T](underlying) | |
} |
what about this:
import org.apache.hadoop.fs.RemoteIterator
/**
* Converts RemoteIterator from Hadoop to Scala Iterator that provides all the familiar functions such as map,
* filter, foreach, etc.
*
* @param underlying The RemoteIterator that needs to be wrapped
* @tparam T Items inside the iterator
* @return Standard Scala Iterator
*/
implicit def convertToScalaIterator[T](underlying: RemoteIterator[T]): Iterator[T] = {
case class wrapper(underlying: RemoteIterator[T]) extends Iterator[T] {
override def hasNext = underlying.hasNext
override def next = underlying.next
}
wrapper(underlying)
}
Here is a usage example:
val fs = FileSystem.get(spark.sparkContext.hadoopConfiguration)
val hdfsPath = new Path(basePath)
fs.mkdirs(hdfsPath)
import Conversions._
fs.listFiles(hdfsPath, true).foreach(x => println(s"found file ${x.getPath.toUri}"))
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
How to use it?