windows中eclipse调试hadoop

　　下载eclipse：https://www.eclipse.org/downloads/eclipse-packages

　　下载hadoop eclipse插件：https://github.com/winghc/hadoop2x-eclipse-plugin/tree/master/release/hadoop-eclipse-plugin-2.6.0.jar

　　下载hadoop：http://mirror.bit.edu.cn/apache/hadoop/common/hadoop-2.7.1/hadoop-2.7.1.tar.gz

　　下载hadoop2.7.1的window下编译好的bin目录：http://url.cn/4EO196a

　　 1、配置hadoop环境变量

　　　　将下载的hadoop-2.7.1.tar.gz进行解压，复制解压路径，配置到系统环境变量中

　　　　解压下载hadoop windowsbin目录包

　　　　将解压出来的内容复制到hadoop-2.7.1\bin 目录中，再将hadoop.dll文件复制到C:\Windows\System32中，然后重启机器；

　　2、配置eclipse

　　　　打开eclipse ，选择window/Peferences设置hadoop安装路径

　　　　在eclipse中的MapReduce面板右击新建hadoop localtion

　　　在弹窗的面板中输入hadoop服务器的DFS Master ip和端口

　　　注意由于本机使用的是administrator的用户，所以访问服务器的DFS可能会有权限问题，可master服务器的hadoop/etc/hadoop/hdfs-site.xml 中添加如下配置

<property>
<name>dfs.permissions</name>
<value>false</value> 
</property>

　　　完成后可在Project Exploer中看到如下界面

　　3、新建hadoop项目

　　　　WordCount.java代码

package com.apache.hadoop.examples;

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();
  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(args[0]));
  FileOutputFormat.setOutputPath(job, new Path(args[1]));
  System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}