Hadoop程序基础模板

输入文件格式为：X,Y，表示X引用Y；
本程序目的为将引用数据进行倒排，对于每一个专利找到引用他的那些专利

import java.io.IOException;
import java.util.Iterator;

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.Text;

import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.KeyValueTextInputFormat;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import com.google.inject.Key;
import com.sun.tracing.dtrace.ArgsAttributes;

public class MyJob extends Configured implements Tool {

    public static class MapClass extends MapReduceBase implements Mapper<Text, Text, Text, Text>{

        public void map(Text key,Text value,OutputCollector<Text, Text> output,Reporter reporter)throws IOException{

            output.collect(value, key);
        }
    }

    public static class Reduce extends MapReduceBase implements Reducer<Text, Text, Text, Text>{

        public void reduce(Text key,Iterator<Text> value,OutputCollector<Text, Text> output,Reporter reporter)throws IOException{

//          int sum=0;
//          while(value.hasNext()){
//              value.next();
//              sum++;
//          }
//          output.collect(key, new IntWritable(sum));
            String res="";
            while(value.hasNext()){
                if(res.length()>0)res+=",";
                res+=value.next().toString();
            }
            output.collect(key, new Text(res));
        }
    }
    @Override
    public int run(String[] arg0) throws Exception {
        // TODO Auto-generated method stub

        Configuration configuration=getConf();

        JobConf job=new JobConf(configuration,MyJob.class);

        FileInputFormat.setInputPaths(job, new Path(arg0[0]));
        FileOutputFormat.setOutputPath(job, new Path(arg0[1]));
        job.setJobName("InvertedIndex");
        job.setMapperClass(MapClass.class);
        job.setReducerClass(Reduce.class);
        job.setInputFormat(KeyValueTextInputFormat.class);
        job.setOutputFormat(TextOutputFormat.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        //job.setMapOutputValueClass(Text.class);

        job.set("key.value.separator.in.input.line",",");
        JobClient.runJob(job);
        return 0;
    }

    public static void main(String[] args) throws Exception{
        // TODO Auto-generated method stub
        //ToolRunner.run(conf, tool, args)
        int res=ToolRunner.run(new Configuration(), new MyJob(), args);
        System.exit(res);

    }

}