MAPREDUCER(MR)java代码阶段

WCDRIVER

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 WCDriver  {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //创建JOB对象
        Job job = Job.getInstance(new Configuration());
        //设置参数
       //设置jar加载类型
        job.setJarByClass(WCDriver.class);
        //设置mapper和reducer类
        job.setMapperClass(WCMapper.class);
        job.setReducerClass(WCReducer.class);
        //设置MAPPER输出的key,value的类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //设置最终输出的KEY，value的类型(在这里指的是reduce输出的KEY，value)
        job.setOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //设置读取的数据的路径--如果指定的目录那马会将整个目录中所有的文件进行运算
        FileInputFormat.setInputPaths(job,new Path("D:\\lianxizhuanyong"));
        //设置输出的路劲---输出的路径必须不存在
        FileOutputFormat.setOutputPath(job,new Path("D:\\lianxizhuanyong3"));

        //提交参数
        job.waitForCompletion(true);
    }
}

 

WCREDUCER

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

import java.io.IOException;

public class WCReducer  extends Reducer<Text, IntWritable, Text,IntWritable> {
        //封装的value
         private   IntWritable  outvalue=    new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
     int sum=0;
       // 1.遍历所有的value
        for(IntWritable  value:values){
            //2.对所有valu进行累加
            int v = value.get();//将Intwritable转换成基本数据类型
                sum +=v;

        }
       //封装key value
        outvalue.set(sum);//将基本数据类型转换成Intweitrable(实际上是赋值)
        //写出去
        context.write(key,outvalue);
    }
}

WCMAPPE

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;

public class WCMapper  extends Mapper<LongWritable, Text,Text, IntWritable> {

     private  Text outkey = new Text();
     private  IntWritable outvalue = new IntWritable();
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //将value转换成字符串类型
        String line=value.toString();
        //对字符串进行切割
        String[] words = line.split(" ");
        for(String word:words){
            //封装KV

            outkey.set(word);
            outvalue.set(1);
            //写出去
            context.write(outkey,outvalue);


        }
    }
}