hadoop学习4

利用mapreduce进行排序

import java.io.IOException;

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

public class Sort {

    public static class Map extends Mapper<Object,Text,IntWritable,IntWritable>{
        private static IntWritable data = new IntWritable();
        @Override
        protected void map(Object key, Text value, Mapper<Object, Text, IntWritable, IntWritable>.Context context)
                throws IOException, InterruptedException {
            String line = value.toString();
            data.set(Integer.parseInt(line));
            context.write(data, new IntWritable(1));
        }
    }

    public static class Reduce extends Reducer<IntWritable, IntWritable, IntWritable, IntWritable>{

        private static IntWritable lineSum = new IntWritable(1);

        @Override
        protected void reduce(IntWritable key, Iterable<IntWritable> values,
                Reducer<IntWritable, IntWritable, IntWritable, IntWritable>.Context context)
                throws IOException, InterruptedException {
            for(IntWritable value : values){
                context.write(lineSum,key);
                lineSum = new IntWritable(lineSum.get() + 1);
            }
        }
    }

    public static void main(String[] args) throws Exception{
        Configuration conf = new Configuration();
        Job job = new Job(conf,"sort");

        job.setOutputKeyClass(IntWritable.class);
        job.setOutputValueClass(IntWritable.class);

        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);

        FileInputFormat.setInputPaths(job,new Path("hdfs://node1:9000/afan/input"));
        FileOutputFormat.setOutputPath(job,new Path("hdfs://node1:9000/afan/output"));

        boolean ret = job.waitForCompletion(true);
        System.exit(ret? 0:1);

    }

}