mr相关代码

jobmain

package com.naixue.sort;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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;

/**
 * @author LIAO
 * @create 2020-07-26 20:38
 * 排序的主类，将map和reducer串联起来
 */
public class JobMain {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        Configuration configuration = new Configuration();
        //一、初始化一个job
        Job job = Job.getInstance(configuration, "sort");

        //二、设置job的相关信息  8个小步骤
        //1、设置输入的路径，让程序找到源文件
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new Path("D://input/test3.txt"));

        //2、设置Mapper类，并设置k2 v2
        job.setMapperClass(SortMapper.class);
        job.setMapOutputKeyClass(MySortBean.class);
        job.setMapOutputValueClass(NullWritable.class);

        //3 4 5 6

        //7、设置Reducer类，并设置k3 v3
        job.setReducerClass(SortReducer.class);
        job.setOutputKeyClass(MySortBean.class);
        job.setOutputValueClass(NullWritable.class);

        //8、设置输出的路径
        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job,new Path("D://wordoutsort"));

        //三、等待完成
        boolean b = job.waitForCompletion(true);
        System.out.println(b);
        System.exit(b ? 0 : 1);
    }
}

mybean

package com.naixue.sort;

import org.apache.hadoop.io.WritableComparable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

/**
 * @author LIAO
 * @create 2020-07-26 20:16
 * 排序的实例化对象
 */
public class MySortBean implements WritableComparable<MySortBean> {

    private String word;
    private int num;

    public String getWord() {
        return word;
    }

    public void setWord(String word) {
        this.word = word;
    }

    public int getNum() {
        return num;
    }

    public void setNum(int num) {
        this.num = num;
    }

    @Override
    public String toString() {
        return "MySortBean{" +
                "word='" + word + '\'' +
                ", num=" + num +
                '}';
    }

    /**
     * 比较器，按照我们自己指定的规则进行排序
     * 排序规则：
     *      要求第一列按照字典顺序进行排列，第一列相同的时候, 第二列按照升序进行排列。
     * @param o
     * @return
     */
    @Override
    public int compareTo(MySortBean o) {
        //1、先对第一列进行排序 word
        int result = this.word.compareTo(o.word);

        //2、第一列相同的时候，num排序
        if (result == 0){
            return this.num - o.num;
        }
        return result;
    }

    //实现序列化
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeUTF(word);
        out.writeInt(num);
    }

    //实现反序列化
    @Override
    public void readFields(DataInput in) throws IOException {
        this.word = in.readUTF();
        this.num = in.readInt();
    }
}

sortmapper

package com.naixue.sort;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

/**
 * @author LIAO
 * @create 2020-07-26 20:26
 * Mapper<KEYIN, VALUEIN, KEYOUT, VALUEOUT>
 *     KEYIN:文本偏移量
 *     VALUEIN：一行的文本
 *     KEYOUT：MySortBean
 *     VALUEOUT：NullWritable
 */
public class SortMapper extends Mapper<LongWritable,Text,MySortBean,NullWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //1、拆分，将一行文本进行拆分
        String[] split = value.toString().split(" ");

        //2、将相应的值给写入到MySortBean对象中
        MySortBean mySortBean = new MySortBean();
        mySortBean.setWord(split[0]);
        mySortBean.setNum(Integer.parseInt(split[1]));

        //3、写入到上下文
        context.write(mySortBean,NullWritable.get());
    }
}

sortreducer

package com.naixue.sort;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

/**
 * @author LIAO
 * @create 2020-07-26 20:26
 * Mapper<KEYIN, VALUEIN, KEYOUT, VALUEOUT>
 *     KEYIN:文本偏移量
 *     VALUEIN：一行的文本
 *     KEYOUT：MySortBean
 *     VALUEOUT：NullWritable
 */
public class SortMapper extends Mapper<LongWritable,Text,MySortBean,NullWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //1、拆分，将一行文本进行拆分
        String[] split = value.toString().split(" ");

        //2、将相应的值给写入到MySortBean对象中
        MySortBean mySortBean = new MySortBean();
        mySortBean.setWord(split[0]);
        mySortBean.setNum(Integer.parseInt(split[1]));

        //3、写入到上下文
        context.write(mySortBean,NullWritable.get());
    }
}