FlatFileClusterDB.hpp

Go to the documentation of this file.

/*==========================================================================
 * Copyright (c) 2002 University of Massachusetts.  All Rights Reserved.
 *
 * Use of the Lemur Toolkit for Language Modeling and Information Retrieval
 * is subject to the terms of the software license set forth in the LICENSE
 * file included with this software, and also available at
 * http://www.lemurproject.org/license.html
 *
 *==========================================================================
 */

// Peter Amstutz
// init: 12/17/2002
#ifndef _FLATFILECLUSTERDB_HPP
#define _FLATFILECLUSTERDB_HPP

#include "ClusterDB.hpp"
#include "IndexedReal.hpp"
#include <string>
namespace lemur 
{
  namespace cluster
  {
    class FlatFileClusterDB : public lemur::api::ClusterDB {

    public:
      FlatFileClusterDB(const lemur::api::Index *ind, 
                        const string &name,                
                        double threshold = 0.25,
                        enum ClusterParam::simTypes simType = ClusterParam::COS,
                        enum ClusterParam::clusterTypes 
                        clusterType = ClusterParam::CENTROID,
                        enum ClusterParam::docModes docMode = ClusterParam::DMAX);

      virtual ~FlatFileClusterDB();

      virtual vector<Cluster*> getDocCluster(lemur::api::DOCID_T docId) const;

      virtual int countClusters() const {return clusterCount - 1;}

      virtual int maxID() const{return clusterIdCounter - 1;}

      virtual Cluster *getCluster(int clusterId) const;

      virtual vector<int> getDocClusterId(lemur::api::DOCID_T docId) const;

      virtual int addToCluster(lemur::api::DOCID_T docId, int clusterId, 
                               double score);

      virtual int addToCluster(lemur::api::DOCID_T docId, Cluster *cluster, 
                               double score);

      virtual int removeFromCluster(lemur::api::DOCID_T docId, int clusterID);

      virtual int deleteCluster(int clusterID);

      virtual int deleteCluster(Cluster * cluster);

      virtual vector<int> splitCluster(int cid, int num = 2);

      virtual int mergeClusters(int cid1, int cid2);

    protected:
      virtual Cluster * newCluster();

    private:
      int clusterCount;
      int clusterIdCounter;
      string clusterDB;
      int *doc2cluster;
      void readClusterDB();
      void writeClusterDB();
      void init(const string &name);
    };
  }
}

#endif

---