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 Lesser General Public 00010 // License as published by the Free Software Foundation; either 00011 // version 2.1 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 // Lesser General Public License for more details. 00017 // 00018 // You should have received a copy of the GNU Lesser 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 _TOKENIZER 00030 #define _TOKENIZER 00031 00032 #include <set> 00033 #include <map> 00034 #include <vector> 00035 00036 #include "language.h" 00037 #include "regexp.h" 00038 00045 00046 class tokenizer { 00047 private: 00049 set<string> abrevs; 00051 vector<pair<string,RegEx> > rules; 00053 map<string,int> matches; 00054 00055 public: 00057 tokenizer(const string &); 00058 00060 list<word> tokenize(const string &); 00062 list<word> tokenize(const string &, int &); 00063 }; 00064 00065 #endif 00066 00067 00068 00069 00070 00071 00072 00073 00074