MapReduce （三部曲）

拿FileInputFormat实现类中的 KeyValueTextInputFormat来说

首先有个任务：需要你统计输入文件中每一行的第一个单词相同的次数

数据 ：

banzhang ni hao

xihuan hadoop banzhang

banzhang ni hao

xihuan hadoop banzhang

需要得到的结果：

banzhang 2

xihuan 2

这个任务的解决思路是

Map阶段： 1 先设置key 和 value 2 写出

Reduce阶段: 1 先汇总 2 写出

Driver阶段：

1 设置切割符 conf . set (KeyvalueLineRecordReader. EY_vALUE_SEPERATOR," " ) ;

2 设置输入格式 job.se tInputFormatClass(KeyValueTextInput）

Mapper类代码块

package com.atguigu.mapreduce.KeyValueTextInputFormat;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Mapper;

 

public class KVTextMapper extends Mapper{

​	

// 1 设置value

  LongWritable v = new LongWritable(1);  

  

​	@Override

​	protected void map(Text key, Text value, Context context)

​			throws IOException, InterruptedException {

 

// banzhang ni hao

​    

​    // 2 写出

​    context.write(key, v);  

​	}

}

Reducer类代码块

package com.atguigu.mapreduce.KeyValueTextInputFormat;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class KVTextReducer extends Reducer{
	
    LongWritable v = new LongWritable();  
    
	@Override
	protected void reduce(Text key, Iterable values,	Context context) throws IOException, InterruptedException {
		
		 long sum = 0L;  

		 // 1 汇总统计
        for (LongWritable value : values) {  
            sum += value.get();  
        }
         
        v.set(sum);  
         
        // 2 输出
        context.write(key, v);  
	}
}

Driver类代码块

package com.atguigu.mapreduce.keyvaleTextInputFormat;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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.input.KeyValueLineRecordReader;
import org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class KVTextDriver {

	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		
		Configuration conf = new Configuration();
		// 设置切割符
	conf.set(KeyValueLineRecordReader.KEY_VALUE_SEPERATOR, " ");
		// 1 获取job对象
		Job job = Job.getInstance(conf);
		
		// 2 设置jar包位置，关联mapper和reducer
		job.setJarByClass(KVTextDriver.class);
		job.setMapperClass(KVTextMapper.class);
job.setReducerClass(KVTextReducer.class);
				
		// 3 设置map输出kv类型
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(LongWritable.class);

		// 4 设置最终输出kv类型
		job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
		
		// 5 设置输入输出数据路径
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		
		// 设置输入格式
	job.setInputFormatClass(KeyValueTextInputFormat.class);
		
		// 6 设置输出数据路径
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		// 7 提交job
		job.waitForCompletion(true);
	}
}

以上即为MapReduce三部曲简单内容

刚学hadoop小白 不喜忽喷