hadoop实战之排序Sort源码

Sort：

package com.test.sorted;

import java.io.IOException;
import java.util.StringTokenizer;

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.Mapper;
import org.apache.hadoop.mapreduce.Partitioner;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class Sorted {
	public static class TokenizerMapper extends Mapper<Object, Text, IntWritable, IntWritable> {
		private static IntWritable data = new IntWritable();

		public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
			String str = value.toString().trim();

			data.set(Integer.parseInt(str));
			context.write(data, new IntWritable(1));
		}
	}

	public static class TokenizerReducer extends Reducer<IntWritable, IntWritable, IntWritable, IntWritable> {
		private static IntWritable linenum = new IntWritable(0);

		public void reduce(IntWritable key, Iterable<IntWritable> values, Context context)
				throws IOException, InterruptedException {
			for (IntWritable val : values) {
				context.write(linenum, key);
				linenum =new IntWritable(linenum.get() + 1);
			}
			// context.write(key,new Text(""));
		}

	}

public static class Partition extends Partitioner<IntWritable,IntWritable>{

	@Override
	public int getPartition(IntWritable key, IntWritable value, int partition) {
		int max=65535;
		int fenshu=max/partition+1;
		int keynum=key.get();
		for(int i=1;i<=partition;i++)
		{
			if(i*fenshu>keynum&&(i-1)*fenshu<keynum)
				return i-1;
		}
		
		return partition-1;
	}

}

public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();
		Job job = Job.getInstance(conf, "sort");
		// Job job=new Job(conf,"word count");
		job.setJarByClass(Sorted.class);
		job.setMapperClass(TokenizerMapper.class);
		// job.setCombinerClass(TokenizerReducer.class);
		job.setReducerClass(TokenizerReducer.class);
		job.setPartitionerClass(Partition.class);
		job.setOutputKeyClass(IntWritable.class);
		job.setOutputValueClass(IntWritable.class);
		FileInputFormat.addInputPath(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		System.exit(job.waitForCompletion(true) ? 0 : 1);

	}

}

源码出自：《hadoop实战》