新版API WordCount 小例 及如何导入jar包

WordCount：

简单解析wordcount小例子的代码，对应于新版的API进行处理。

import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.examples.WordCount.TokenizerMapper;
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;

public class WordCount {

	/**
	 * @param 
	 * @XD 2014-8-16
	 */
	public static class TokenzierMapper extends Mapper<Object,Text,Text,IntWritable>{
		//对于切下的单词赋予出现频数1
		private final static IntWritable one = new IntWritable(1);
		
		//存储切下的单词
		private Text word = new Text();
		
		public void map(Object key,Text value,Context context) throws IOException, InterruptedException{
			//StringTokenizer 对输入单词进行切分
			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>{
		//存取对应单词总频数
		private IntWritable result = new IntWritable();
		
		public  void reduce(Text key,Iterable<IntWritable> values,Context context) throws IOException, InterruptedException{
			//计算频数
			int sum = 0;
			for(IntWritable value:values){
				sum+=value.get();
			}
			result.set(sum);
			//写入输出
			context.write(key, result);
		}
	}
	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		// TODO Auto-generated method stub
		//初始化配置
		Configuration conf = new Configuration();
		Job job = new Job(conf,"word count");
		job.setJarByClass(WordCount.class);
		
		//设置map，combine，reduce处理
		job.setMapperClass(TokenizerMapper.class);
		job.setReducerClass(IntSumReducer.class);
		job.setCombinerClass(IntSumReducer.class);
		
		//设置输出格式处理类
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		//设置输入输出路径
		FileInputFormat.addInputPath(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		job.waitForCompletion(true);
		
		System.out.println("任务名称: "+job.getJobName());
		System.out.println("任务成功: "+(job.isSuccessful()?"Yes":"No"));
		
	}
}

在eclipse中实现此过程，需要先导入自己hadoop安装目录下面的jar包，eclipse导入jar如下：

1.右击工程的根目录，点击Properties进入Properties。或者选中工程根目录，按Alt-Enter即可。

2.在Properties页面中选中Java Build Path，选中Libraries标签，点击Add External JARs。

3.找到需要添加的jar包，确定即可。