FreeLing  3.0
tagger.h
Go to the documentation of this file.
00001 
00002 //
00003 //    FreeLing - Open Source Language Analyzers
00004 //
00005 //    Copyright (C) 2004   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 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 //    General Public License for more details.
00017 //
00018 //    You should have received a copy of the GNU 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 _POS_TAGGER
00030 #define _POS_TAGGER
00031 
00032 #include <list> 
00033 #include "freeling/windll.h"
00034 #include "freeling/morfo/language.h"
00035 #include "freeling/morfo/processor.h"
00036 
00037 #define FORCE_NONE   0  // no selection forced
00038 #define FORCE_TAGGER 1  // force select after tagger
00039 #define FORCE_RETOK  2  // force select after retokenization
00040 
00046 
00047 class WINDLL POS_tagger : public processor {
00048 
00049  protected: 
00050   // remember whether retokenization is active
00051   bool retok;
00052   // remember whether the user asked to force only one tag per word
00053   unsigned int force;
00054   // retokenize words that may need it after tagging
00055   void retokenize(sentence &);
00056   // force the selection of only one Pos tag per word
00057   void force_select(sentence &);
00058 
00059  public:
00060   POS_tagger(bool,unsigned int);
00061   virtual ~POS_tagger() {};
00062 
00064   virtual void annotate(sentence &)=0;
00065 
00067   void analyze(sentence &);
00069   void analyze(std::list<sentence> &);
00071   sentence analyze(const sentence &);
00073   std::list<sentence> analyze(const std::list<sentence> &);
00074 };
00075 
00076 
00077 #endif