1.环境
Jdk：1.6.0_10-rc2
Hadoop：hadoop-1.0.0.tar.gz
Eclipse 版本：3.4.0
Hadoop Eclipse 插件 ：hadoop-eclipse-plugin-1.0.0.jar
操作系统：Windows7 32位 旗舰版
2.Eclipse插件配置
2.1 把"hadoop-eclipse-plugin-1.0.0.jar"放到Eclipse的目录的"plugins"中(eclipse/plugins)，重新启动Eclipse生效
2.2 选择Elipse Window菜单下的"Preference"，配置"Hadoop Map/Reduce"选项，选择Hadoop的安装根目录
2.3 配置Hadoop Location
在配置Hadoop Location之前 确定hadoop 已启动起来
Eclipse 切换到“Map/Reduce Locations” 视图 ， 在"Map/Reduce Locations"视图右击 选择"New Hadoop Location"，
* Map/Reduce Master与mapred-site.xml配置文件对应
* DFS Mast 与core-site.xml配置对应创建完成后 ,切换到JavaEE视图 刷新右边的DFS Locations 就会看到dfs文件结构
可以在节点上右键 创建 删除目录做测试
3.运行wordCount例子程序
创建一个 Map/Reduce Project项目
创建成功后 WordCount报名对应(源码在hadoop\src\examples\org\apache\hadoop\examples目录下)
WordCount.java
package org.apache.hadoop.examples;import java.io.IOException;import java.net.URI;import java.util.StringTokenizer;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.FSDataInputStream;import org.apache.hadoop.fs.FileSystem;import org.apache.hadoop.fs.FileUtil;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.IOUtils;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 { 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 { private IntWritable result = new IntWritable(); public void reduce(Text key, Iterable 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 "); System.exit(2); } //删除输出目录 FileSystem fileSystem = FileSystem.get(URI.create(args[1]),conf); fileSystem.delete(new Path("/user/admin/output"), true); 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])); boolean flag = job.waitForCompletion(true); FSDataInputStream fDataInputStream = null; try { fDataInputStream = fileSystem.open(new Path("/user/admin/output/part-r-00000")); String line = null; while ((line = fDataInputStream.readLine()) != null) { System.out.println(line);; } } catch (Exception e) { e.printStackTrace(); } finally { IOUtils.closeStream(fDataInputStream); IOUtils.closeStream(fileSystem); } System.exit( flag ? 0 : 1); }} 运行例子
1.点击WordCount.java，右键-->Run As-->Run Configurations
2.在弹出的Run Configurations对话框中，点Java Application，右键-->New，这时会新建一个application名为WordCount 3.配置参数，点Arguments，在Program arguments中配置 /user/admin/input /user/admin/output 4.运行时可能会抛出java.lang.OutOfMemoryError: Java heap space异常 配置VM arguments(在Program arguments下) -Xms512m -Xmx512m -XX:PermSize=96m 
