* Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *     http://www.apache.org/licenses/LICENSE-2.0
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * See the License for the specific language governing permissions and
 * limitations under the License.

package org.apache.hadoop.tools;

import java.io.BufferedReader;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.ArrayList;
import java.util.EnumSet;
import java.util.HashSet;
import java.util.Iterator;
import java.util.LinkedList;
import java.util.List;
import java.util.Random;
import java.util.Stack;
import java.util.StringTokenizer;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileChecksum;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.FilterFileSystem;
import org.apache.hadoop.fs.FsShell;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.permission.FsPermission;
import org.apache.hadoop.hdfs.DFSClient;
import org.apache.hadoop.hdfs.DFSUtil;
import org.apache.hadoop.hdfs.DistributedFileSystem;
import org.apache.hadoop.hdfs.protocol.QuotaExceededException;
import org.apache.hadoop.hdfs.tools.FastCopy;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.ipc.RemoteException;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.FileSplit;
import org.apache.hadoop.mapred.InputFormat;
import org.apache.hadoop.mapred.InputSplit;
import org.apache.hadoop.mapred.InvalidInputException;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.RecordReader;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.RunningJob;
import org.apache.hadoop.mapred.SequenceFileRecordReader;
import org.apache.hadoop.security.AccessControlException;
import org.apache.hadoop.util.StringUtils;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

 * A Map-reduce program to recursively copy directories between
 * different file-systems.
public class DistCp implements Tool {
  public static final Log LOG = LogFactory.getLog(DistCp.class);

  private static final String NAME = "distcp";

  private static final String usage = NAME
    + " [OPTIONS] <srcurl>* <desturl>" +
    "\n\nOPTIONS:" +
    "\n-p[rbugp]              Preserve status" +
    "\n                       r: replication number" +
    "\n                       b: block size" +
    "\n                       u: user" + 
    "\n                       g: group" +
    "\n                       p: permission" +
    "\n                       t: modification and access times" +
    "\n                       -p alone is equivalent to -prbugpt" +
    "\n-i                     Ignore failures" +
    "\n-basedir <basedir>     Use <basedir> as the base directory when copying files from <srcurl>" +
    "\n-log <logdir>          Write logs to <logdir>" +
    "\n-m <num_maps>          Maximum number of simultaneous copies" +
    "\n-r <num_reducers>      Maximum number of reducers" +
    "\n-overwrite             Overwrite destination" +
    "\n-update                Overwrite if src size different from dst size" +
    "\n-skipcrccheck          Do not use CRC check to determine if src is " +
    "\n                       different from dest. Relevant only if -update" +
    "\n                       is specified" +
    "\n-copybychunk           Chop files in chunk and copy" +
    "\n-f <urilist_uri>       Use list at <urilist_uri> as src list" +
    "\n-filelimit <n>         Limit the total number of files to be <= n" +
    "\n-sizelimit <n>         Limit the total size to be <= n bytes" +
    "\n-delete                Delete the files existing in the dst but not in src" +
    "\n-mapredSslConf <f>     Filename of SSL configuration for mapper task" +
    "\n-usefastcopy           Use FastCopy (applicable to DFS only)" +
    "\n\nNOTE 1: if -overwrite or -update are set, each source URI is " +
    "\n      interpreted as an isomorphic update to an existing directory." +
    "\nFor example:" +
    "\nhadoop " + NAME + " -p -update \"hdfs://A:8020/user/foo/bar\" " +
    "\"hdfs://B:8020/user/foo/baz\"\n" +
    "\n     would update all descendants of 'baz' also in 'bar'; it would " +
    "\n     *not* update /user/foo/baz/bar" + 

    "\n\nNOTE 2: The parameter <n> in -filelimit and -sizelimit can be " +
    "\n     specified with symbolic representation.  For examples," +
    "\n       1230k = 1230 * 1024 = 1259520" +