Parser.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 _PARSER_HPP
#define _PARSER_HPP

#include "TextHandler.hpp"
#include "WordSet.hpp"
namespace lemur
{
  namespace api
  {

    class Parser : public TextHandler {
    public:
      static const string category;
      static const string identifier;

      Parser();
      virtual ~Parser();

      virtual void parse(const string &filename);
  
      virtual void parseFile(const string &filename) = 0;

      virtual void parseBuffer(char * buf, int len) = 0;

      virtual void setAcroList(const lemur::utility::WordSet * acronyms);

      virtual void setAcroList(string filename);

      virtual long fileTell() const = 0;

      virtual long getDocBytePos() const { return docpos; }

      virtual const string getParseFile() const { return parsefile; }

    protected: 
      bool isAcronym(const char * word);
      void clearAcros();

      long docpos; 

      string parsefile;
    private:
      lemur::utility::WordSet * myacros;
      const lemur::utility::WordSet* borrowedacros;
    };
  }
}

#endif

---