DocOffsetParser.hpp

Go to the documentation of this file.

/*==========================================================================
 * Copyright (c) 2002-2003 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
 *
 *==========================================================================
 */

#ifndef _DOCOFFSETPARSER_HPP
#define _DOCOFFSETPARSER_HPP
#include "Parser.hpp"
#include "Match.hpp"
namespace lemur
{
  namespace parse 
  {
    
    class DocOffsetParser : public lemur::api::TextHandler {

    public:
      DocOffsetParser(lemur::api::Parser *parser) : p(parser) { 
        p->setTextHandler(this);
      }
  
      virtual ~DocOffsetParser(){}

      virtual char *handleWord(char * word) {
        if (word != NULL) {
          int end = p->fileTell() - 1;
          int start = (end - strlen(word)) + 1;
          Match m;
          m.start = start;
          m.end = end;    
          offsets.push_back(m);
        }
        return word;
      }
      virtual void parseString(char *buffer) {
        offsets.clear();
        p->parseBuffer(buffer, strlen(buffer));
      }
      vector <Match> getOffsets() { return offsets; }
    private:
      vector <Match> offsets;
      lemur::api::Parser *p;
    };
  }
}

#endif

---