MapReduce例子

//MapReduce 排序例子


import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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;

import java.io.IOException;

public class Sort {
    //12,3,4,5,6,
   /* 1 3
    2 4*/
   // map key

    public static class SortMap extends Mapper<Object,Text,IntWritable,IntWritable>{
        //
        private static IntWritable data=new IntWritable();
        @Override
        protected  void map(Object key,Text values,Context context) throws IOException, InterruptedException {
         //
            String line=values.toString();
            data.set(Integer.parseInt(line));
            context.write(data,new IntWritable(1));
        }
    }
    public static class SortReduce extends Reducer<IntWritable,IntWritable,IntWritable,IntWritable>{
        private static IntWritable linenum=new IntWritable(1);
        @Override
        protected void reduce(IntWritable key,Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
            for(IntWritable value:values){
                context.write(linenum,key);
                linenum= new IntWritable(value.get()+1);
            }
        }
    }
    public static int main(String[] args) throws Exception{
        Configuration conf =new Configuration();
        Job job=Job.getInstance(conf);
        job.setJarByClass(Sort.class);

        job.setMapperClass(SortMap.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        //
        job.setReducerClass(SortReduce.class);
        job.setOutputKeyClass(IntWritable.class);
        job.setMapOutputValueClass(IntWritable.class);
        //
        Path inPath =new Path(args[0]);

        FileInputFormat.addInputPath(job,inPath);

        Path outPath=new Path(args[1]);
        FileSystem fs =FileSystem.get(conf);
        if(fs.exists(outPath)){
            fs.delete(outPath,true);
        }
        FileOutputFormat.setOutputPath(job,outPath);

        boolean b = job.waitForCompletion(true);
        return b?1:0;
    }

}