NellEdgeMapper.java

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.HashMap;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Mapper.Context;


public  class NellEdgeMapper extends Mapper <Object ,  Text, LongWritable, Text> {
	private HashMap<String, Long> VMap= new HashMap<String, Long>();
	@Override
	protected void setup(Context context) throws IOException,
			InterruptedException {
		// TODO Auto-generated method stub
		try{
            Path pt=new Path("hdfs:/user/nellout50/part-r-00000");
            FileSystem fs = FileSystem.get(new Configuration());
            BufferedReader br=new BufferedReader(new InputStreamReader(fs.open(pt)));
            String line;
            line=br.readLine();
            if(line==null)System.out.println("file is empty");
            while (line != null){
                    System.out.println(line);
                    String value=line.toString();
                    String[] strs = value.trim().split(":");
                    String label=strs[0];
                    long vid=Long.parseLong(strs[1]);
                    System.out.println("TEST1: label="+label+"  id  "+vid);
                    VMap.put(label,vid);
                    System.out.println("TEST2: label="+label+"  id  "+VMap.get(label));
                    line=br.readLine();
            }
    }catch(Exception e){
    }
		
	}

	@Override
	public void run(Context context) throws IOException, InterruptedException {
		// TODO Auto-generated method stub
		super.run(context);
	}

	@Override
	protected void map(Object key, Text value, Context context)
			throws IOException, InterruptedException {

		String line=value.toString();
		if(!line.startsWith("#")){
            
            String[] strs = line.trim().split("\\s+");
            	            
            String srcstring=strs[0];
            
            String[] srcsplit=srcstring.trim().split(":");
            String src=srcsplit[srcsplit.length - 1];
            
            String relationstr=strs[1];
            String[] relationsplit=relationstr.trim().split(":");	
            String relation=relationsplit[relationsplit.length -1];		
            		
            String deststring=strs[2];
            String[] destsplit=deststring.trim().split(":");
            String target=destsplit[destsplit.length - 1];
            
          /*  System.out.println("source : "+src+"  relation : "+relation+"  target : "+target);
            long srchash=Math.abs(hash(src));
            srchash=srchash%(1<<20);
            long targethash=Math.abs(hash(target));
            targethash=targethash%(1<<20);
           */
            String v="";
            if(VMap.get(src)==null){
            	System.out.println("TESTNULL :"+src);
            }
            if(VMap.get(target)==null){
            	System.out.println("TESTNULL :"+target);
            }
            long srcid=VMap.get(src);
            long tid=VMap.get(target);
            long relationhash=Math.abs(hash(src+relation+target));
            v=srcid+":"+tid+":"+relation;
            context.write(new LongWritable(relationhash), new Text(v));
            
		}
		
		
		
	}public static long hash(String string) {
		  long h = 1125899906842597L; // prime
		  int len = string.length();

		  for (int i = 0; i < len; i++) {
		    h = 31*h + string.charAt(i);
		  }
		  return h;
		}


}