MapReduce wordcount

MapReduce wordcount 0 概述

mapreducer wordcount 案例
1 添加依赖
2 编写Mapper类
3 编写Reducer类
4 编写Driver驱动类

1 依赖

    4.0.0

    com
    MapReduceDemo
    1.0-SNAPSHOT
    
        
            org.apache.hadoop
            hadoop-client
            3.1.3
        
        
            junit
            junit
            4.12
        
        
            org.slf4j
            slf4j-log4j12
            1.7.30
        
    
    
        
            
                maven-compiler-plugin
                3.6.1
                
                    1.8
                    1.8
                
            
            
                maven-assembly-plugin
                
                    
                        jar-with-dependencies
                    
                
                
                    
                        make-assembly
                        package
                        
                            single
                        
                    
                
            
        
    

2 mapper

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.apache.hadoop.yarn.webapp.hamlet2.Hamlet;

import java.io.IOException;

public class WordCountMapper extends Mapper {
    private  Text text = new Text();
    private  IntWritable outv=new IntWritable(1);
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String[] words = line.split(" ");

        // 3 循环写入
        for (String word: words){

            text.set(word);
            context.write(text,outv);


        }
    }
}

3 reducer

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 {
    private  IntWritable outv=new IntWritable();
    @Override
    protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
        int sum=0;
        for (IntWritable value : values) {
            sum+=value.get();

        }
        outv.set(sum);
        context.write(key,outv);
    }
}

4 Driver

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.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import java.io.IOException;

public class WordCountDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        // 1 获取job
        Job job = Job.getInstance(new Configuration());
        //2 设置jar 包路径
        job.setJarByClass(WordCountDriver.class);
        //3  设置mapper and areducer
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        //4 set 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);
    }
}