MapReduce-WordCount案例

有上一篇讲解了MapReduce运行原理后,相信大家能理解了,本篇以wordcount为案例了解下MapReduce编程的乐趣...

1 MR参考代码

1 .1Mapper代码

package com.mr.cf.wordcount;

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

public class WordCountMap extends Mapper<LongWritable, Text, Text, IntWritable> {
    protected void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {
        String[] words = value.toString().split(" ");
        for (String word : words) {
            // 每个单词出现１次，作为中间结果输出
            context.write(new Text(word), new IntWritable(1));
        }
    }
}

1.2 Reducer代码

package com.mr.cf.wordcount;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class WordCountReduce extends Reducer<Text, IntWritable, Text, IntWritable> {
    /*
        key: hello
        value: List(1, 1, ...)
    */
    protected void reduce(Text key, Iterable<IntWritable> values,
                          Context context) throws IOException, InterruptedException {
        int sum = 0;

        for (IntWritable count : values) {
            sum = sum + count.get();
        }
        // 输出最终结果
        context.write(key, new IntWritable(sum));
    }
}

1.3 Main程序入口

package com.mr.cf.wordcount;

import java.io.IOException;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

public class WordCountMain {
    public static void main(String[] args) throws IOException,
            ClassNotFoundException, InterruptedException {
        //判断输入参数是否够
        if (args.length != 2 || args == null) {
            System.out.println("please input Path!");
            System.exit(0);
        }

        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration, WordCountMain.class.getSimpleName());

        // 打jar包
        job.setJarByClass(WordCountMain.class);

        // 通过job设置输入/输出格式
        //job.setInputFormatClass(TextInputFormat.class);
        //job.setOutputFormatClass(TextOutputFormat.class);

        // 设置输入/输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        // 设置处理Map/Reduce阶段的类
        job.setMapperClass(WordCountMap.class);
        job.setReducerClass(WordCountReduce.class);
        //如果map、reduce的输出的kv对类型一致，直接设置reduce的输出的kv对就行；如果不一样，需要分别设置map, reduce的输出的kv类型
        //job.setMapOutputKeyClass(.class)
        // 设置最终输出key/value的类型m
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        // 提交作业
        job.waitForCompletion(true);
    }
}

集群方式运行 

用maven将项目打包 ,用hadoop jar命令行运行mr程序

]$ hadoop jar com.mr.cf-1.0-SNAPSHOT.jar com.mr.cf.wordcount.WordCountMain /a.txt /wordcount 

  HDFS查看结果

hdfs dfs -ls /wordcount