MapReduce单词统计

标签：output   format   res   count   数据   value   mapr   unit   test   

package com.sky.mr.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 org.junit.Test;

import java.io.IOException;

public class WordcountMapper extends Mapper<LongWritable,Text, Text, IntWritable> {
    //由于每读一行文本数据，就要调用一次map方法，为了避免多次创建对象，浪费内存资源，将Text,IntWritable对象创建在
    //map方法之外
   Text k = new Text();
   IntWritable v  = new IntWritable(1);
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //获取每一行的文本内容
        String line = value.toString();
        //按空格分割
        String[] words = line.split(" ");

        //转换数据格式，输出
        for ( String word: words) {
            k.set(word);
            context.write(k, v);
        }
    }
}

WordcountReducer类

package com.sky.mr.wordcount;

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

public class WordcountReducer extends Reducer<Text, IntWritable, Text,IntWritable> {
    IntWritable v  = new IntWritable();
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        //求每组相同key的总个数
        int sum = 0;
        for ( IntWritable count:values) {
            sum += count.get();
        }
        //输出
        v.set(sum);
        context.write(key, v);
    }
}

WordcountDriver类

package com.sky.mr.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;

public class WordcountDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //1、获取配置信息以及job对象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        //2、设置jar包路径
        job.setJarByClass(WordcountDriver.class);
        //3、关联自定义mapper和reducer类
        job.setMapperClass(WordcountMapper.class);
        job.setReducerClass(WordcountReducer.class);
        //4、设置Map输出key和value类型
         job.setMapOutputKeyClass(Text.class);
         job.setMapOutputValueClass(IntWritable.class);
        //5、设置最终结果key，value类型
         job.setOutputKeyClass(Text.class);
         job.setOutputValueClass(IntWritable.class);
        //6、设置文件输入输出路径
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        //7、将封装了MapReduce程序运行参数的job对象，提交到Yarn集群
        boolean result = job.waitForCompletion(true);
        System.exit(result?0:1);
    }
}

输入文件

import org apache hadoop io
import org apache hadoop io
import org apache hadoop
import java io IOException

输出文件

IOException 1
apache 3
hadoop 3
import 4
io 3
java 1
org 3

MapReduce单词统计

标签：output   format   res   count   数据   value   mapr   unit   test   

原文地址：https://blog.51cto.com/12721734/2449225