我没有彻底测试它,但这样的东西似乎工作:
import org.apache.spark.deploy.SparkHadoopUtil
import org.apache.hadoop.fs.{FileSystem, Path, LocatedFileStatus, RemoteIterator}
import java.net.URI
val path: String = ???
val hconf = SparkHadoopUtil.get.newConfiguration(sc.getConf)
val hdfs = FileSystem.get(hconf)
val iter = hdfs.listFiles(new Path(path), false)
def listFiles(iter: RemoteIterator[LocatedFileStatus]) = {
def go(iter: RemoteIterator[LocatedFileStatus], acc: List[URI]): List[URI] = {
if (iter.hasNext) {
val uri = iter.next.getPath.toUri
go(iter, uri :: acc)
} else {
acc
}
}
go(iter, List.empty[java.net.URI])
}
listFiles(iter).filter(_.toString.endsWith(".csv"))