Hadoop的WordCount代码解析

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;

import java.io.IOException;
import java.util.StringTokenizer;

@SuppressWarnings("deprecation")
public class WordCount {

    //在map阶段接收输入的<key, value>(key是当前输入的行号，value是对应的内容)，
    //然后对内容进行切词，每切下一个词就将其组织成<word,1>的形式输出（输出即写到context中）
    //设置map的输入类型为<Object, Text>
    //输出类型为<Text, IntWritable>
    public static class TokenizerMapper extends	Mapper<Object, Text, Text, IntWritable> {
        //one表示单词出现1次
        private final static IntWritable one = new IntWritable(1);
        //word存储切下的单词
        private Text word = new Text();

        @Override
        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            //参数key表示的是行号，下面并没有用到key
            StringTokenizer itr = new StringTokenizer(value.toString()); //对输入的行进行切词
            while (itr.hasMoreTokens()) { //切下单词，存入word
                word.set(itr.nextToken());
                context.write(word, one);
            }
        }
    }

    //Reducer是对相同key下的所有value进行处理.
    //在reduce阶段，TaskTracker会接收到<word,{1,1,1,1}>形式的数据，也就是特定单词出现次数的情况
    //设置reduce的输入数据类型为<Text, IntWritable>
    //输出数据类型为<Text, IntWritable>
    public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        //result记录单词的个数
        private IntWritable result = new IntWritable();

        @Override
        public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            //对获取的<key, value-list>计算value的和
            for (IntWritable val : values) {
                sum += val.get();
            }
            //将频数设置到result中
            result.set(sum);
            //收集结果
            context.write(key, result);
        }
    }

    public static void main(String[] args) throws Exception {
        //args=hdfs://192.168.22.156:9000/input/file1 hdfs://192.168.22.156:9000/output/wordnum
        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);
        }
        //配置作业名
        Job job = new Job(conf, "word count");
        //配置作业各个类
        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);
    }
}

全文完。转载请注明出处：http://blog.csdn.net/ghuil/article/details/45586699