MapReduce的自定义排序

package com.mengyao.hadoop.mapreduce;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
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;

public class SortApp extends Configured implements Tool {

    static class Num2 implements WritableComparable<Num2> {

        private long c1;
        private long c2;
        
        public Num2(){
            
        }
        
        public Num2(long c1, long c2) {
            this.c1 = c1;
            this.c2 = c2;
        }

        @Override
        public void write(DataOutput out) throws IOException {
            out.writeLong(this.c1);
            out.writeLong(this.c2);
        }

        @Override
        public void readFields(DataInput in) throws IOException {
            this.c1 = in.readLong();
            this.c2 = in.readLong();
        }

        @Override
        public int compareTo(Num2 num2) {
            long min = this.c1 - num2.c1;
            if (min != 0) {
                return (int)min;
            }
            
            return (int)(this.c2 - num2.c2);
        }

        public void set(long c1, long c2) {
            this.c1 = c1;
            this.c2 = c2;
        }
        
    }
    
    static class SortMapper extends Mapper<LongWritable, Text, Num2, LongWritable> {
        
        private Num2 k = null;
        private LongWritable v = null;
        
        @Override
        protected void setup(Mapper<LongWritable, Text, Num2, LongWritable>.Context context)
                throws IOException, InterruptedException {
            k = new Num2();
            v = new LongWritable();
        }

        @Override
        protected void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {
            String[] fields = value.toString().split("\t");
            if (fields != null && fields.length == 2) {
                k.set(Long.parseLong(fields[0]), Long.parseLong(fields[1]));
                v.set(Long.parseLong(fields[0]));
                context.write(k, v);                
            }
        }
    }
    
    static class SortReducer extends Reducer<Num2, LongWritable, LongWritable, LongWritable> {
        @Override
        protected void reduce(Num2 key, Iterable<LongWritable> value, Context context)
                throws IOException, InterruptedException {
            context.write(new LongWritable(key.c1), new LongWritable(key.c2));
        }
    }
    
    @Override
    public int run(String[] args) throws Exception {
        Configuration conf = getConf();
        conf.set("mapreduce.job.jvm.numtasks", "-1");        
        conf.set("mapreduce.map.speculative", "false");        
        conf.set("mapreduce.reduce.speculative", "false");    
        conf.set("mapreduce.map.maxattempts", "4");            
        conf.set("mapreduce.reduce.maxattempts", "4");        
        conf.set("mapreduce.map.skip.maxrecords", "0");    
        Job job = Job.getInstance(conf, SortApp.class.getSimpleName());
        job.setJarByClass(SortApp.class);
        
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        
        job.setMapperClass(SortMapper.class);
        job.setMapOutputKeyClass(Num2.class);
        job.setMapOutputValueClass(LongWritable.class);
        
        job.setReducerClass(SortReducer.class);
        job.setOutputKeyClass(LongWritable.class);
        job.setOutputValueClass(LongWritable.class);
        
        return job.waitForCompletion(true)?0:1;
    }

    public static int createJob(String[] params) {
        Configuration conf = new Configuration();
        int status = 1;
        try {
            status = ToolRunner.run(conf, new SortApp(), params);
        } catch (Exception e) {
            e.printStackTrace();
            throw new RuntimeException(e);
        }
        
        return status;
    }
    
    public static void main(String[] args) throws Exception {
        args = new String[]{"/testdata/sortdata", "/job/mapreduce/"+SortApp.class.getSimpleName()+"_"+new SimpleDateFormat("yyyyMMddhhMMss").format(new Date())};
        if (args.length != 2) {
            System.err.println("Usage: "+SortApp.class.getSimpleName()+" <in> <out>");
            System.exit(2);
        } else {
            int status = createJob(args);
            System.exit(status);
        }
    }

}