package com.littlepage.wc;

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.TextInputFormat;

import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

import java.io.IOException;

public class MyWordCount {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        //1.读取配置

        Configuration conf=new Configuration(true);

        //设定本地环境运行，不进行集群运行

//        conf.set("mapreduce.framework.name","local");

        //设定异构平台

//        conf.set("mapreduce.app-submission.cross-platform","true");

        //2.设定Job

        Job job=Job.getInstance(conf);

        //3.设定Job执行的类

        job.setJarByClass(MyWordCount.class);

        //4.设定JobName

        job.setJobName("SteveYu's word count");

        //5.设定输入path

        Path infile=new Path("/data/wc/input");

        TextInputFormat.addInputPath(job,infile);

        //6.设定输出path

        Path outfile=new Path("/data/wc/loveloveOutput");

        if(outfile.getFileSystem(conf).exists(outfile)) outfile.getFileSystem(conf).delete(outfile,true);

        TextOutputFormat.setOutputPath(job,outfile);

        //7.设定MapperClass和ReduceClass

        job.setMapperClass(WordCountMapper.class);

        job.setReducerClass(WordCountReducer.class);

        //8.设定输出的Key，Value格式

        job.setOutputKeyClass(Text.class);

        job.setOutputValueClass(IntWritable.class);

        //9.等待程序完成

        job.waitForCompletion(true);

    }

}

package com.littlepage.wc;

import org.apache.hadoop.io.IntWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

import java.util.StringTokenizer;

public class WordCountMapper extends Mapper<Object,Text,Text,IntWritable> {

    private final static IntWritable one=new IntWritable();

    private Text word=new Text();

    @Override

    protected void map(Object key, Text value, Context context) throws IOException, InterruptedException {

        StringTokenizer itr=new StringTokenizer(value.toString());

        while(itr.hasMoreTokens()){

            word.set(itr.nextToken());

            context.write(word,one);

        }

    }

}

package com.littlepage.wc;

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> {

    private IntWritable result=new IntWritable();

    //相同的key为一组 ，这一组数据调用一次reduce

    //hello 1

    @Override

    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {

        int sum=;

        for (IntWritable val:values) {

            sum+=val.get();

        }

        result.set(sum);

        context.write(key,result);

    }

}