lttoolbox-unicode/lttoolbox/pattern_list.h

   1 /*
   2  * Copyright (C) 2005 Universitat d'Alacant / Universidad de Alicante
   3  *
   4  * This program is free software; you can redistribute it and/or
   5  * modify it under the terms of the GNU General Public License as
   6  * published by the Free Software Foundation; either version 2 of the
   7  * License, or (at your option) any later version.
   8  *
   9  * This program is distributed in the hope that it will be useful, but
  10  * WITHOUT ANY WARRANTY; without even the implied warranty of
  11  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  12  * General Public License for more details.
  13  *
  14  * You should have received a copy of the GNU General Public License
  15  * along with this program; if not, write to the Free Software
  16  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
  17  * 02111-1307, USA.
  18  */
  19 #ifndef _PATTERNLIST_
  20 #define _PATTERNLIST_
  21
  22 #include <lttoolbox/alphabet.h>
  23 #include <lttoolbox/match_exe.h>
  24 #include <lttoolbox/transducer.h>
  25
  26 #include <list>
  27 #include <map>
  28 #include <string>
  29 #include <vector>
  30
  31 using namespace std;
  32
  33 typedef multimap<int, vector<int> > PatternStore;
  34 typedef pair<PatternStore::iterator, PatternStore::iterator> PatternRange;
  35
  36 class PatternList
  37 {
  38 private:
  39   Alphabet alphabet;
  40   PatternStore patterns;
  41   bool sequence;
  42   list<vector<int> > sequence_data;
  43   Transducer transducer;
  44   map<int, int> final_type;
  45   int sequence_id;
  46
  47   void copy(PatternList const &o);
  48   void destroy();
  49   void insertOutOfSequence(wstring const &lemma, wstring const &tags,
  50                            vector<int> &result);
  51   void insertIntoSequence(int const id, wstring const &lemma,
  52                           wstring const &tags);
  53
  54   static int tagCount(wstring const &tags);
  55   static wstring tagAt(wstring const &tags, int const index);
  56
  57 public:
  58   /**
  59    * This symbol stands for any char
  60    */
  61   static wstring const ANY_CHAR;
  62
  63   /**
  64    * This symbol stands for any tag
  65    */
  66   static wstring const ANY_TAG;
  67
  68   /**
  69    * This symbol marks a word queue
  70    */
  71   static wstring const QUEUE;
  72
  73   /**
  74    * Constructor
  75    */
  76   PatternList();
  77
  78   /**
  79    * Destructor
  80    */
  81   ~PatternList();
  82
  83   /**
  84    * Copy constructor
  85    */
  86   PatternList(PatternList const &o);
  87
  88   /**
  89    * Assignment operator
  90    * @param o the object to be assigned
  91    */
  92   PatternList & operator =(PatternList const &o);
  93
  94   /**
  95    * Marks the start of a multiple word sequence
  96    */
  97   void beginSequence();
  98
  99   /**
 100    * Ends the multiple word sequence
 101    */
 102   void endSequence();
 103
 104   /**
 105    * Insertion method
 106    * @param id
 107    * @param lemma
 108    * @param tags
 109    */
 110   void insert(int const id, wstring const &lemma, wstring const &tags);
 111
 112   /**
 113    * Insertion method
 114    * @param id
 115    * @param otherid
 116    */
 117   void insert(int const id, int const otherid);
 118
 119   /**
 120    * Get the PatternStore
 121    * @returns a PatternStore object
 122    */
 123   PatternStore const & getPatterns();
 124
 125   /**
 126    * Build the FSM
 127    */
 128   void buildTransducer();
 129
 130   /**
 131    * Read PatternList from a file
 132    * @param input the input stream
 133    */
 134   void read(FILE *input);
 135
 136   /**
 137    * Write PatternList to a file
 138    * @param output the output stream
 139    */
 140   void write(FILE *output);
 141
 142   /**
 143    * Create a new MatchExe from PatternList, must be freed with 'delete'
 144    * @return the new MatchExe object
 145    */
 146   MatchExe * newMatchExe();
 147
 148   /**
 149    * Get the alphabet of this PatternList object
 150    * @return the alphabet
 151    */
 152   Alphabet & getAlphabet();
 153 };
 154
 155 #endif