大数据||MapReduce编程模板

标准模板代码

package com.lizh.hadoop.mapreduce;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import com.lizh.hadoop.mapreduce.WordCountMapReduce.WordCountMapper;
import com.lizh.hadoop.mapreduce.WordCountMapReduce.WordCountReduces;

public class MouldMapReduce extends Configured implements Tool{

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

        @Override
        protected void setup(Context context) throws IOException,
                InterruptedException {
            // TODO 读取数据前的一些初始化工作或者读取文件前的一些初始化工作
            super.setup(context);
        }
        

        @Override
        protected void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {
            // TODO 
            super.map(key, value, context);
        }


        @Override
        protected void cleanup(Context context) throws IOException,
                InterruptedException {
            // TODO Auto-generated method stub
            super.cleanup(context);
        }
        
    }
    
    
    public class MouldReduce extends Reducer<Text, IntWritable, Text,IntWritable>{

        @Override
        protected void setup(Context context)
                throws IOException, InterruptedException {
            // TODO  读取数据前的一些初始化工作或者读取文件前的一些初始化工作
            super.setup(context);
        }
        

        @Override
        protected void reduce(Text arg0, Iterable<IntWritable> arg1,Context arg2)
                throws IOException, InterruptedException {
            // TODO Auto-generated method stub
            super.reduce(arg0, arg1, arg2);
        }
        
        @Override
        protected void cleanup(
                org.apache.hadoop.mapreduce.Reducer.Context context)
                throws IOException, InterruptedException {
            // TODO Auto-generated method stub
            super.cleanup(context);
        }
        
    }
    
    private Job getJob(String[] args){
        Configuration configuration = this.getConf();
        Job job = null;
        try {
            job = Job.getInstance(configuration, this.getClass().getSimpleName());
            job.setJarByClass(this.getClass());
            
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
        
        return job;
    }
    
    public int run(String[] args) throws Exception {
        // TODO Auto-generated method stub
        //input-->map--reduce--output
    //getjob
        Job job = getJob(args);
        //setjob
        Path path = new Path(args[0]);
        FileInputFormat.addInputPath(job, path);
        
        // map
        job.setMapperClass(WordCountMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        
        // reduce
        job.setReducerClass(WordCountReduces.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        
        //output
        Path outputpath = new Path(args[1]);
        FileOutputFormat.setOutputPath(job, outputpath);
        
        // submit job
        boolean rv = job.waitForCompletion(true);//true的时候打印日志
        
        return rv ? 0:1;
    }
    
    public static void main(String[] args) throws Exception{
        Configuration conf = new Configuration();
        ToolRunner.run(conf, new MouldMapReduce(), args);
    }

}