include/dict.h

   1 /*
   2  * Copyright (C) 2004 Jesus Gimenez, Lluis Marquez and Senen Moya
   3  *
   4  * This library is free software; you can redistribute it and/or
   5  * modify it under the terms of the GNU Lesser General Public
   6  * License as published by the Free Software Foundation; either
   7  * version 2.1 of the License, or (at your option) any later version.
   8  *
   9  * This library is distributed in the hope that it will be useful,
  10  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  11  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  12  * Lesser General Public License for more details.
  13  *
  14  * You should have received a copy of the GNU Lesser General Public
  15  * License along with this library; if not, write to the Free Software
  16  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  17  */
  18
  19 #ifndef DICT_H
  20
  21 #include "list.h"
  22 #include "hash.h"
  23 #include <set>
  24 #include <string>
  25
  26 #define TAMTXT 100
  27
  28 struct infoDict
  29 {
  30   std::string pos;
  31   int  num;
  32 };
  33
  34 struct dataDict
  35 {
  36   std::string wrd;
  37   int  numWrd;
  38   int  numMaybe;
  39   simpleList<infoDict*> maybe;
  40 };
  41
  42 class  dictionary
  43 {
  44   public:
  45     dictionary(const std::string& name, const std::string& backup);
  46     dictionary(const std::string& name);
  47     dictionary(const std::string& name,int limInf, int limSup);
  48     ~dictionary();
  49
  50     void dictAddBackup(const std::string& name);
  51     void addBackupEntry(const std::string& token, const std::set<std::string>& tags);
  52
  53     dataDict* getElement(const std::string& key);
  54     std::string& getElementWord(dataDict*  ptr);
  55     int getElementNumWord(dataDict*  ptr);
  56     int getElementNumMaybe(dataDict*  ptr);
  57     simpleList<infoDict*>& getElementMaybe(dataDict*  ptr);
  58     infoDict* getMFT(dataDict* w);
  59     std::string getAmbiguityClass(dataDict*  w);
  60
  61     hash_t<infoDict*>* dictFindAmbP(int *numPOS);
  62     hash_t<infoDict*>* dictFindUnkP(int *numPOS);
  63     void dictRepairFromFile(const std::string& fileName);
  64     void dictRepairHeuristic(float dratio);
  65
  66     void dictCleanListInfoDict(simpleList< infoDict* >* l, int num);
  67
  68     void dictWrite(const std::string& outName);
  69
  70 private:
  71   void dictLoad(FILE *in);
  72   void dictCreate(FILE *f,int offset, int limit);
  73   void dictIncInfo(dataDict *elem, const std::string& pos);
  74
  75   int readInt(FILE *in);
  76   infoDict *readData(FILE *in);
  77
  78   hash_t<dataDict*> d;
  79 };
  80
  81 #define DICT_H
  82 #endif