Java API操作Hdfs的示例详解

  
  public abstract FileStatus[] listStatus(Path f) throws FileNotFoundException, 
                                                         IOException;

@InterfaceAudience.Public
@InterfaceStability.Stable
public class FileStatus implements Writable, Comparable {

  private Path path;
  private long length;
  private boolean isdir;
  private short block_replication;
  private long blocksize;
  private long modification_time;
  private long access_time;
  private FsPermission permission;
  private String owner;
  private String group;
  private Path symlink;
  ....

import org.apache.hadoop.fs.{FileStatus, FileSystem, Path}
import org.apache.spark.sql.SparkSession
import org.apache.spark.{SparkConf, SparkContext}
import org.slf4j.LoggerFactory

object hdfsOperation {
	
	val logger = LoggerFactory.getLogger(this.getClass)
	
	def tree(sc: SparkContext, path: String) : Unit = {
		val fs = FileSystem.get(sc.hadoopConfiguration)
		val fsPath = new Path(path)
		val status = fs.listStatus(fsPath)
		for(filestatus:FileStatus <- status) {
			logger.error("getPermission is: {}", filestatus.getPermission)
			logger.error("getOwner is: {}", filestatus.getOwner)
			logger.error("getGroup is: {}", filestatus.getGroup)
			logger.error("getLen is: {}", filestatus.getLen)
			logger.error("getModificationTime is: {}", filestatus.getModificationTime)
			logger.error("getReplication is: {}", filestatus.getReplication)
			logger.error("getBlockSize is: {}", filestatus.getBlockSize)
			if (filestatus.isDirectory) {
				val dirpath = filestatus.getPath.toString
				logger.error("文件夹名字为: {}", dirpath)
				tree(sc, dirpath)
			} else {
				val fullname = filestatus.getPath.toString
				val filename = filestatus.getPath.getName
				logger.error("全部文件名为: {}", fullname)
				logger.error("文件名为: {}", filename)
			}
		}
	}
}

	def findFiles(sc: SparkContext, path: String) = {
		val fs = FileSystem.get(sc.hadoopConfiguration)
		val fsPath = new Path(path)
		val files = fs.listFiles(fsPath, true)
		while(files.hasNext) {
			val filestatus = files.next()
			val fullname = filestatus.getPath.toString
			val filename = filestatus.getPath.getName
			logger.error("全部文件名为: {}", fullname)
			logger.error("文件名为: {}", filename)
			logger.error("文件大小为: {}", filestatus.getLen)
		}
	}

  
  public RemoteIterator<LocatedFileStatus> listFiles(
      final Path f, final boolean recursive)
  throws FileNotFoundException, IOException {
  ...

	def mkdirToHdfs(sc: SparkContext, path: String) = {
		val fs = FileSystem.get(sc.hadoopConfiguration)
		val result = fs.mkdirs(new Path(path))
		if (result) {
			logger.error("mkdirs already success!")
		} else {
			logger.error("mkdirs had failed!")
		}
	}

	def deleteOnHdfs(sc: SparkContext, path: String) = {
		val fs = FileSystem.get(sc.hadoopConfiguration)
		val result = fs.delete(new Path(path), true)
		if (result) {
			logger.error("delete already success!")
		} else {
			logger.error("delete had failed!")
		}
	}

	def uploadToHdfs(sc: SparkContext, localPath: String, hdfsPath: String): Unit = {
		val fs = FileSystem.get(sc.hadoopConfiguration)
		fs.copyFromLocalFile(new Path(localPath), new Path(hdfsPath))
		fs.close()
	}

	def downloadFromHdfs(sc: SparkContext, localPath: String, hdfsPath: String) = {
		val fs = FileSystem.get(sc.hadoopConfiguration)
		fs.copyToLocalFile(new Path(hdfsPath), new Path(localPath))
		fs.close()
	}