hadoop-WordCount程序

package com.zhangdan.wordcount;

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.LongWritable;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;



public class WordCount {
    public static class WordCountMap extends Mapper<LongWritable, Text, Text, IntWritable> {
        private final IntWritable one = new IntWritable(1);
        private Text word = new Text();
        public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString();
            StringTokenizer token = new StringTokenizer(line);
            while (token.hasMoreTokens()) {  //hasMoreTokens方法：测试此 tokenizer 的字符串中是否还有更多的可用标记。
                /**
                 * set方法：Set to contain the contents of a string.
                 * nextToken方法：返回此 string tokenizer 的下一个标记。
                 */
                word.set(token.nextToken());  
                context.write(word, one);//返回的是单词及次数
            }
        }
    }

    public static class WordCountReduce extends Reducer<Text, IntWritable, Text, IntWritable> {
        public void reduce(Text key, Iterable<IntWritable> values, Context context)
                throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
                //System.out.println(key+"  "+val);
            }
            context.write(key, new IntWritable(sum));
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        //1.创建Job
        Job job = new Job(conf);
        //2.设置Job运行的类
        job.setJarByClass(WordCount.class);
        //3.设置job名称
        job.setJobName("wordcount");
        job.setOutputValueClass(IntWritable.class);

        //设置Mapper和Reducer类
        job.setMapperClass(WordCountMap.class);
        //job.setCombinerClass(WordCountReduce.class);  这一步要特别说明下，因为这里没需要combine过程，因此不需要这个过程
        job.setReducerClass(WordCountReduce.class);
         
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);
        
        //设置输入文件目录和输出文件目录
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        //提交运行作业，等待运行结果
        job.waitForCompletion(true);
    }

}