---

InvPushIndex.hpp

Go to the documentation of this file.

/*==========================================================================
 * Copyright (c) 2001 Carnegie Mellon University.  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
 *
 *==========================================================================
*/


#ifndef _INVPUSHINDEX_HPP
#define _INVPUSHINDEX_HPP


/*
 * NAME DATE - COMMENTS
 * tnt 01/02 - created
 ======================================================================*/
#include "common_headers.hpp"
#include "PushIndex.hpp"
#include "MemCache.hpp"
#include "InvFPTypes.hpp"
#include "InvDocList.hpp"
#include "InvFPTerm.hpp"
#include "InvIndexMerge.hpp"


typedef map<string, InvDocList*, less<string> > TABLE_T;

class InvPushIndex : public PushIndex {
public:
  InvPushIndex(){ };
  InvPushIndex(const string &prefix, int cachesize=128000000, long maxfilesize=2100000000, DOCID_T startdocid=1);
  ~InvPushIndex();

  void setName(const string &prefix);

  bool beginDoc(const DocumentProps* dp);

  bool addTerm(const Term& t);

  void endDoc(const DocumentProps* dp);

  virtual void endDoc(const DocumentProps* dp, const string &mgr);

  void endCollection(const CollectionProps* cp);

  void setDocManager(const string &mgrID);

protected:
  void writeTOC(int numinv);
  void writeDocIDs();
  void writeCache();
  void lastWriteCache();
  void writeDTIDs();
  void writeDocMgrIDs();
  int docMgrID(const string &mgr);
  virtual void doendDoc(const DocumentProps* dp, int mgrid);

  long maxfile; 
  MemCache* cache; 
  vector<EXDOCID_T> docIDs; 
  vector<TERM_T> termIDs; 
  vector<string> tempfiles; 
  vector<string> dtfiles; 
  vector<string> docmgrs;  // the list of doc managers we have (index = id)

  FILE* writetlookup; 
  ofstream writetlist; 

  COUNT_T tcount;    
  COUNT_T tidcount ; 
  COUNT_T dtidcount; 
  string name;    
  TABLE_T wordtable; 
  map<TERMID_T, COUNT_T> termlist; 
  int* membuf; 
  int membufsize;  // how much memory we have
  int curdocmgr; // the current docmanager to use
};

#endif

---