FreeLing  4.0
lexer.h
Go to the documentation of this file.
00001 
00002 //
00003 //    FreeLing - Open Source Language Analyzers
00004 //
00005 //    Copyright (C) 2014   TALP Research Center
00006 //                         Universitat Politecnica de Catalunya
00007 //
00008 //    This library is free software; you can redistribute it and/or
00009 //    modify it under the terms of the GNU Affero General Public
00010 //    License as published by the Free Software Foundation; either
00011 //    version 3 of the License, or (at your option) any later version.
00012 //
00013 //    This library is distributed in the hope that it will be useful,
00014 //    but WITHOUT ANY WARRANTY; without even the implied warranty of
00015 //    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
00016 //    Affero General Public License for more details.
00017 //
00018 //    You should have received a copy of the GNU Affero General Public
00019 //    License along with this library; if not, write to the Free Software
00020 //    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
00021 //
00022 //    contact: Lluis Padro (padro@lsi.upc.es)
00023 //             TALP Research Center
00024 //             despatx C6.212 - Campus Nord UPC
00025 //             08034 Barcelona.  SPAIN
00026 //
00028 
00029 #ifndef _LEXER_H
00030 #define _LEXER_H
00031 
00032 #include <vector>
00033 #include "freeling/regexp.h"
00034 
00035 namespace freeling {
00036 
00041 
00042   class lexer {
00043   private:  
00045     std::vector<std::pair<freeling::regexp,int> > rules;
00046 
00048     std::wstring buffer;
00049     std::wstring::const_iterator beg, end;
00050     size_t line;
00051 
00053     std::wstring text;
00054     std::vector<std::wstring> rem;   
00055 
00056   public:
00058     lexer(const std::vector<std::pair<freeling::regexp,int> > &);    
00060     int getToken(std::wistream &);
00062     std::wstring getText();
00064     size_t lineno();
00065   };
00066 
00067 } // namespace
00068 
00069 #endif