NellVertexMapper.java

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;



public class NellVertexMapper extends Mapper <Object ,  Text, LongWritable, Text>{

	@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);
            if(srchash<0 || targethash <0){
            	System.out.println("TESTNEGATIVEMapper");
            }
            context.write(new LongWritable(srchash), new Text(src));
            context.write(new LongWritable(targethash), new Text(target));
		}
            
		// TODO Auto-generated method stub
	}
	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;
		}
	public static void main(String[] args){
		String test ="jkds";
		System.out.println(hash(test));
	}
}