import java.io.*;
import java.util.*;

/**
 *  Description of the Class
 *
 * @author     dav
 * @created    July 4, 2004
 */
public class AnalyzeRefererLog {

  /**
   *  The main program for the AnalyzeRefererLog class
   *
   * @param  args  The command line arguments
   */
  public static void main(String[] args) {

    if (args.length < 1) {
      System.out.println("need the full path/name of the combined referal log as param");
      System.exit(0);
    }

    String log = args[0];

    HashMap map = new HashMap();

    try {
      File file = new File(log);
      BufferedReader in = new BufferedReader(new FileReader(file));

      String line = in.readLine();
      while (line != null) {

        String[] cols = line.split(" ");

        String post = cols[6]; // 7th column is the URL requested
        String referer = cols[10]; // 11th column is the referal URL
        //System.out.println(line);

        if (post.indexOf("archives") > -1 && post.indexOf("html") > -1) {
          if (!referer.equals("\"-\"")
               && !referer.equals("\"\"")
               && (referer.indexOf("google") == -1)
               && (referer.indexOf("search") == -1)
               && (referer.indexOf("altavista") == -1)
               && (referer.indexOf("msn.com") == -1)
              ) {

            //System.out.println("url: "+post);
            //System.out.println("  ref: "+referer);

            Set set = (Set) map.get(post);
            if (set == null) {
              set = new HashSet();
            }
            set.add(referer);
            map.put(post, set);
          }
        }
        line = in.readLine();
      }

      in.close();
    } catch (Exception e) {
      e.printStackTrace();
    }

    for (Iterator it = map.keySet().iterator(); it.hasNext(); ) {
      String post = (String) it.next();
      Set set = (Set) map.get(post);

      System.out.println("" + set.size() + " post: " + post);

      for (Iterator it2 = set.iterator(); it2.hasNext(); ) {
        System.out.println("  + " + it2.next());
      }
    }
  }
}