[大数据]Hadoop——MapReduce——wordcount

刚开始接触MapRecude还不是太理解只是知道了些大概的流程。暂时先记下当作笔记。
下面是依据java实现wordcount的代码：

WordCountMapper

package com.atguigu.mapreduce.wordcount2;

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;

/**
 * KEYIN,map阶段输入的key的类型：LongWritable
 * VALUEIN,map阶段输入value类型：Text
 * KEYOUT,map阶段输出的Key类型：Text
 * VALUEOUT，map阶段输出的value类型：IntWritable
 */
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    private Text outK = new Text();
    private IntWritable outV = new IntWritable(1);

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //1、获取一行
        //比如输入为：dlw dlw
        String line = value.toString();

        //2、切割
        //切割之后变为
        //dlw
        //dlw
        String[] words = line.split(" ");

        //3、循环写出
        for (String word : words) {
            //4、封装outK
            outK.set(word);
            //5、写出
            context.write(outK, outV);
        }
    }
}

WordCountReducer

package com.atguigu.mapreduce.wordcount2;

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

import java.io.IOException;

/**
 * KEYIN,reduce阶段输入的key的类型：Text
 * VALUEIN,reduce阶段输入value类型：LongWritable
 * KEYOUT,reduce阶段输出的Key类型：Text
 * VALUEOUT，reduce阶段输出的value类型：IntWritable
 */
public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    private IntWritable outV = new IntWritable();
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        //dlw,(1,1)
        //累加
        for (IntWritable value : values) {
            sum+=value.get();
        }
        outV.set(sum);
        //写出
        context.write(key,outV);
    }
}

WordCountDriver
课程中介绍到以下七步可当作模板。

package com.atguigu.mapreduce.wordcount2;

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, InterruptedException, ClassNotFoundException {

        //1、获取job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        //2、设置jar包路径
        job.setJarByClass(WordCountDriver.class);

        //3、关联mapper和reducer
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        //4、设置map输出的kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //5、设置最终输出的kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //6、设置输入路径和输出路径
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

        //7、提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result?0:1);
    }
}