MapReduce單詞統(tǒng)計

WordcountMapper類

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> {
    //由于每讀一行文本數(shù)據(jù)，就要調用一次map方法，為了避免多次創(chuàng)建對象，浪費內(nèi)存資源，將Text,IntWritable對象創(chuàng)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 {
        //獲取每一行的文本內(nèi)容
        String line = value.toString();
        //按空格分割
        String[] words = line.split(" ");

        //轉換數(shù)據(jù)格式，輸出
        for ( String word: words) {
            k.set(word);
            context.write(k, v);
        }
    }
}

WordcountReducer類

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 {
        //求每組相同key的總個數(shù)
        int sum = 0;
        for ( IntWritable count:values) {
            sum += count.get();
        }
        //輸出
        v.set(sum);
        context.write(key, v);
    }
}

WordcountDriver類

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、獲取配置信息以及job對象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        //2、設置jar包路徑
        job.setJarByClass(WordcountDriver.class);
        //3、關聯(lián)自定義mapper和reducer類
        job.setMapperClass(WordcountMapper.class);
        job.setReducerClass(WordcountReducer.class);
        //4、設置Map輸出key和value類型
         job.setMapOutputKeyClass(Text.class);
         job.setMapOutputValueClass(IntWritable.class);
        //5、設置最終結果key，value類型
         job.setOutputKeyClass(Text.class);
         job.setOutputValueClass(IntWritable.class);
        //6、設置文件輸入輸出路徑
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        //7、將封裝了MapReduce程序運行參數(shù)的job對象，提交到Yarn集群
        boolean result = job.waitForCompletion(true);
        System.exit(result?0:1);
    }
}

輸入文件

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

輸出文件

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