FreeLing
4.0
|
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 _FEX_LEXICON 00030 #define _FEX_LEXICON 00031 00032 #include <map> 00033 #include <set> 00034 #include <string> 00035 00036 namespace freeling { 00037 00041 00042 class lex_entry { 00043 public: 00044 unsigned int code; 00045 unsigned int freq; 00046 lex_entry(unsigned int c, unsigned int f) {code=c; freq=f;}; 00047 }; 00048 00049 00053 00054 class fex_lexicon : std::map<std::wstring,lex_entry> { 00055 00056 private: 00057 unsigned int freq_sum; 00058 unsigned int next_code; 00059 std::set<unsigned int> known_codes; 00060 00061 public: 00063 fex_lexicon(); 00065 fex_lexicon(const std::wstring &); 00067 void clear_lexicon(); 00069 void add_occurrence(const std::wstring &); 00071 void save_lexicon(const std::wstring &, double) const; 00073 unsigned int get_code(const std::wstring &) const; 00075 unsigned int get_freq(const std::wstring &) const; 00077 bool contains_code(unsigned int) const; 00079 bool is_empty() const; 00080 }; 00081 00082 } // namespace 00083 00084 #endif