package com.jss.hadoop.mapreduce.test;

import java.io.IOException;

import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.IntWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Job;

import org.apache.hadoop.mapreduce.Mapper;

import org.apache.hadoop.mapreduce.Reducer;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount {

  public static class TokenizerMapper 

       extends Mapper<Object, Text, Text, IntWritable>{

    private final static IntWritable one = new IntWritable(1);

    private Text word = new Text();

    public void map(Object key, Text value, Context context

                    ) throws IOException, InterruptedException {

      StringTokenizer itr = new StringTokenizer(value.toString());

      while (itr.hasMoreTokens()) {

        word.set(itr.nextToken());

        context.write(word, one);

      }

    }

  }

  public static class IntSumReducer 

       extends Reducer<Text,IntWritable,Text,IntWritable> {

    private IntWritable result = new IntWritable();

    public void reduce(Text key, Iterable<IntWritable> values, 

                       Context context

                       ) throws IOException, InterruptedException {

      int sum = 0;

      for (IntWritable val : values) {

        sum += val.get();

      }

      result.set(sum);

      context.write(key, result);

    }

  }

  public static void main(String[] args) throws Exception {

    Configuration conf = new Configuration();

    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    if (otherArgs.length != 2) {

      System.err.println("Usage: wordcount <in> <out>");

      System.exit(2);

    }

    Job job = new Job(conf, "word count");

    job.setJarByClass(WordCount.class);

    job.setMapperClass(TokenizerMapper.class);

    job.setCombinerClass(IntSumReducer.class);

    job.setReducerClass(IntSumReducer.class);

    job.setOutputKeyClass(Text.class);

    job.setOutputValueClass(IntWritable.class);

    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));

    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

    System.exit(job.waitForCompletion(true) ? 0 : 1);

  }

$ more /data/developer/workspace/FirstHadoopProject/src/com/jss/hadoop/hdfs/test/FileOper.java 

package com.jss.hadoop.hdfs.test;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.FSDataOutputStream;

import org.apache.hadoop.fs.FSDataInputStream;

import org.apache.hadoop.fs.FileStatus;

import org.apache.hadoop.fs.FileSystem;

import org.apache.hadoop.fs.Path;

public class FileOper {

        public static void main(String[] args) throws Exception {

                if (args.length < 1) {

                        System.out.println("Must define parameters!");

                } else {

                        Configuration conf = new Configuration();

                        conf.set("fs.default.name", args[0]);

                        FileOper.listHDFSFiles(conf); // 显示目录结构

                        //FileOper.uploadLocal2HDFS(conf, args[1], args[2]); // 上传文件

                        //FileOper.createHDFSFile(conf, args[1], args[2]); // 创建文件

                        //FileOper.deleteHDFSFile(conf, args[1]); // 删除文件

                        //FileOper.readHDFSFile(conf, args[1]); // 读取文件

                        //FileOper.makeHDFSDirectory(conf, args[1]); // 创建目录

                        //FileOper.removeHDFSDirectory(conf, args[1]); // 删除目录

                }

        }

        public static void listHDFSFiles(Configuration conf) throws IOException {

                FileSystem fs = FileSystem.get(conf);

                FileStatus files[] = fs.listStatus(new Path("/"));

                for (FileStatus file : files) {

                        System.out.println(file.getPath());

                }

        }

        public static void uploadLocal2HDFS(Configuration conf, String s, String d)

                        throws IOException {

                FileSystem fs = FileSystem.get(conf);

                Path src = new Path(s);

                Path dst = new Path(d);

                fs.copyFromLocalFile(src, dst);

                fs.close();

                System.out.println("Upload to " + conf.get("fs.default.name"));

        }

        public static void createHDFSFile(Configuration conf, String createFilePath,

                        String content) throws IOException {

                FileSystem fs = FileSystem.get(conf);

                FSDataOutputStream fsos = fs.create(new Path(createFilePath));

                fsos.write(content.getBytes("UTF-8"));

                fsos.close();

                fs.close();

                System.out.println("Succeeded created file " + createFilePath);

        }

        public static boolean deleteHDFSFile(Configuration conf, String dst)

                        throws IOException {

                FileSystem fs = FileSystem.get(conf);

                Path path = new Path(dst);

                boolean isDeleted = fs.delete(path, true);

                fs.close();

                return isDeleted;

        }

        public static byte[] readHDFSFile(Configuration conf, String dst)

                        throws Exception {

                FileSystem fs = FileSystem.get(conf);

                Path path = new Path(dst);

                if (fs.exists(path)) {

                        FSDataInputStream is = fs.open(path);

                        // get the file info to create the buffer

                        FileStatus stat = fs.getFileStatus(path);

                        // create the buffer

                        byte[] buffer = new byte[Integer.parseInt(String.valueOf(stat

                                        .getLen()))];

                        is.readFully(0, buffer);

                        is.close();

                        fs.close();

                        return buffer;

                } else {

                        throw new Exception("the file is not found .");

                }

        }

        public static void makeHDFSDirectory(Configuration conf, String dst)

                        throws IOException {

                FileSystem fs = FileSystem.get(conf);

                fs.mkdirs(new Path(dst));

                fs.close();

                System.out.println("Succeeded created directory " + dst);

        }

        public static void removeHDFSDirectory(Configuration conf, String dst)

                        throws IOException {

                FileSystem fs = FileSystem.get(conf);

                fs.delete(new Path(dst), true);

                fs.close();

                System.out.println("Succeeded remove directory " + dst);

        }