hadoop经典案列（wordcount）源码解析

wordcount是hadoop最简单也是最经典的案例之一。假如我们要计算《You Have Only One Life》中每个单词出现的次数，其思路如下：

数据准备：

编码工可分为三个部分：map阶段、reduce阶段 以及主程序driver阶段

map阶段：

package com.yangmin.mapreduce.wordcount;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

/**
 * KEYIN:map阶段输入的key的类型：LongWritable
 * VALUEIN:map阶段输入value的类型：Text
 * KEYOUT:map阶段输出的key的类型：Text
 * VALUEOUT：map阶段输出的value的类型：IntWritable
 */
public class WordCountMapper extends Mapper<LongWritable,Text,Text,IntWritable> {
   private Text k = new Text();
   private IntWritable v = new IntWritable(1);

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // 1 获取一行
        String s = value.toString();

        // 2 切割
        String[] words = s.split(" ");

        // 3 输出
        for (String word : words) {
            k.set(word);
            context.write(k,v);
        }

    }
}

reduce 阶段：

package com.yangmin.mapreduce.wordcount;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

/**
 * KEYIN: reducer输入阶段的key类型：Text
 * VALUEIN:reduce输入阶段的value类型：IntWritable
 * KEYOUT:reduce输出阶段的key类型：Text
 * VALUEOUT:reduce输出阶段value类型：IntWritable
 */
public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
   private int sum = 0;
   private IntWritable v = new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        // 1 累加求和
        sum = 0;
        for (IntWritable count : values) {
            sum += count.get();
        }

        // 2 输出
        v.set(sum);
        context.write(key, v);
    }
}

driver阶段：

package com.yangmin.mapreduce.wordcount;

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;
import java.util.jar.JarEntry;

public class WordCountDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        // 1. 获取配置信息以及获取job对象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        // 2. 设置jar包路径
        job.setJarByClass(WordCountDriver.class);

        //3. 关联mapper和reducer
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        //4.设置map输出的kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        //5. 设置最终输出的kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //6.设置输出路径和输出路径
        FileInputFormat.setInputPaths(job, new Path("C:\\ZProject\\bigdata\\input\\inputword"));
        FileOutputFormat.setOutputPath(job, new Path("C:\\ZProject\\bigdata\\output\\output1"));

        //7.提交作业
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);

    }
}

结果：