File: ucs.cc

package info (click to toggle)
ocrad 0.17-4
  • links: PTS
  • area: main
  • in suites: squeeze
  • size: 624 kB
  • ctags: 687
  • sloc: cpp: 7,809; sh: 161; makefile: 149
file content (376 lines) | stat: -rw-r--r-- 10,373 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
/*  GNU Ocrad - Optical Character Recognition program
    Copyright (C) 2003, 2004, 2005, 2006, 2007 Antonio Diaz Diaz.

    This program is free software: you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation, either version 3 of the License, or
    (at your option) any later version.

    This program is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    GNU General Public License for more details.

    You should have received a copy of the GNU General Public License
    along with this program.  If not, see <http://www.gnu.org/licenses/>.
*/

#include <cctype>

#include "ucs.h"


int UCS::base_letter( const int code ) throw()
  {
  switch( code )
    {
    case CAGRAVE:
    case CAACUTE:
    case CACIRCU:
    case CATILDE:
    case CADIAER:
    case CARING : return 'A';
    case CCCEDI : return 'C';
    case CEGRAVE:
    case CEACUTE:
    case CECIRCU:
    case CEDIAER: return 'E';
    case CGBREVE: return 'G';
    case CIGRAVE:
    case CIACUTE:
    case CICIRCU:
    case CIDIAER:
    case CIDOT  : return 'I';
    case CNTILDE: return 'N';
    case COGRAVE:
    case COACUTE:
    case COCIRCU:
    case COTILDE:
    case CODIAER: return 'O';
    case CSCEDI : return 'S';
    case CUGRAVE:
    case CUACUTE:
    case CUCIRCU:
    case CUDIAER: return 'U';
    case CYACUTE: return 'Y';
    case SAGRAVE:
    case SAACUTE:
    case SACIRCU:
    case SATILDE:
    case SADIAER:
    case SARING : return 'a';
    case SCCEDI : return 'c';
    case SEGRAVE:
    case SEACUTE:
    case SECIRCU:
    case SEDIAER: return 'e';
    case SGBREVE: return 'g';
    case SIGRAVE:
    case SIACUTE:
    case SICIRCU:
    case SIDIAER:
    case SINODOT: return 'i';
    case SNTILDE: return 'n';
    case SOGRAVE:
    case SOACUTE:
    case SOCIRCU:
    case SOTILDE:
    case SODIAER: return 'o';
    case SSCEDI : return 's';
    case SUGRAVE:
    case SUACUTE:
    case SUCIRCU:
    case SUDIAER: return 'u';
    case SYACUTE:
    case SYDIAER: return 'y';
    default:      return 0;
    }
  }


int UCS::compose( const int letter, const int accent ) throw()
  {
  switch( letter )
    {
    case 'A': if( accent == '\'') return CAACUTE;
              if( accent == '`' ) return CAGRAVE;
              if( accent == '^' ) return CACIRCU;
              if( accent == ':' ) return CADIAER; break;
    case 'E': if( accent == '\'') return CEACUTE;
              if( accent == '`' ) return CEGRAVE;
              if( accent == '^' ) return CECIRCU;
              if( accent == ':' ) return CEDIAER; break;
    case 'G': return CGBREVE;
    case '[':
    case 'I': if( accent == '\'') return CIACUTE;
              if( accent == '`' ) return CIGRAVE;
              if( accent == '^' ) return CICIRCU;
              if( accent == ':' ) return CIDIAER; break;
    case 'N': if( accent != ':' ) return CNTILDE; break;
    case 'O': if( accent == '\'') return COACUTE;
              if( accent == '`' ) return COGRAVE;
              if( accent == '^' ) return COCIRCU;
              if( accent == ':' ) return CODIAER; break;
    case 'S': return CSCARON;
    case 'U':
    case 'V': if( accent == '\'') return CUACUTE;
              if( accent == '`' ) return CUGRAVE;
              if( accent == '^' ) return CUCIRCU;
              if( accent == ':' ) return CUDIAER; break;
    case 'Z': return CZCARON;
    case 'a': if( accent == '\'') return SAACUTE;
              if( accent == '`' ) return SAGRAVE;
              if( accent == '^' ) return SACIRCU;
              if( accent == ':' ) return SADIAER; break;
    case 'e': if( accent == '\'') return SEACUTE;
              if( accent == '`' ) return SEGRAVE;
              if( accent == '^' ) return SECIRCU;
              if( accent == ':' ) return SEDIAER; break;
    case '9':
    case 'g': return SGBREVE;
    case '|':
    case ']':
    case 'i':
    case 'l': if( accent == '\'') return SIACUTE;
              if( accent == '`' ) return SIGRAVE;
              if( accent == '^' ) return SICIRCU;
              if( accent == ':' ) return SIDIAER; break;
    case 'n': if( accent != ':' ) return SNTILDE; break;
    case 'o': if( accent == '\'') return SOACUTE;
              if( accent == '`' ) return SOGRAVE;
              if( accent == '^' ) return SOCIRCU;
              if( accent == ':' ) return SODIAER; break;
    case 's': return SSCARON;
    case 'u':
    case 'v': if( accent == '\'') return SUACUTE;
              if( accent == '`' ) return SUGRAVE;
              if( accent == '^' ) return SUCIRCU;
              if( accent == ':' ) return SUDIAER; break;
    case 'y': if( accent == '\'') return SYACUTE;
              if( accent == ':' ) return SYDIAER; break;
    case 'z': return SZCARON;
    }
  return 0;
  }


bool UCS::isalnum( const int code ) throw()
  {
  return ( UCS::isalpha( code ) || UCS::isdigit( code ) );
  }


bool UCS::isalpha( const int code ) throw()
  {
  return ( ( code < 128 && std::isalpha( code ) ) || base_letter( code ) );
  }


bool UCS::isdigit( const int code ) throw()
  {
  return ( code <= '9' && code >= '0' );
  }


bool UCS::islower( const int code ) throw()
  {
  if( code < 128 && std::islower( code ) ) return true;
  const int base = base_letter( code );
  return ( base && std::islower( base ) );
  }


bool UCS::islower_ambiguous( const int code ) throw()
  {
  if( islower_small_ambiguous( code ) ) return true;
  switch( code )
    {
    case 'k': case 'p': case SCCEDI:
    case SIGRAVE: case SIACUTE: case SICIRCU: case SIDIAER:
    case SOGRAVE: case SOACUTE: case SOCIRCU: case SOTILDE: case SODIAER:
    case SUGRAVE: case SUACUTE: case SUCIRCU: case SUDIAER:
    case  SSCEDI: case SSCARON: case SZCARON:
      return true;
    default : return false;
    }
  }


bool UCS::islower_small( const int code ) throw()
  {
  if( code >= 128 || !std::islower( code ) ) return false;
  switch( code )
    {
    case 'a': case 'c': case 'e': case 'm': case 'n': case 'o':
    case 'r': case 's': case 'u': case 'v': case 'w': case 'x':
    case 'z': return true;
    default : return false;
    }
  }


bool UCS::islower_small_ambiguous( const int code ) throw()
  {
  if( code >= 128 || !std::islower( code ) ) return false;
  switch( code )
    {
    case 'c': case 'o': case 's': case 'u': case 'v': case 'w':
    case 'x': case 'z': return true;
    default : return false;
    }
  }


bool UCS::isspace( const int code ) throw()
  {
  return ( code < 128 && std::isspace( code ) );
  }


bool UCS::isupper( const int code ) throw()
  {
  if( code < 128 && std::isupper( code ) ) return true;
  const int base = base_letter( code );
  return ( base && std::isupper( base ) );
  }


bool UCS::isvowel( int code ) throw()
  {
  if( code >= 128 ) code = base_letter( code );
  if( !code || !std::isalpha( code ) ) return false;
  code = std::tolower( code );
  return ( code == 'a' || code == 'e' || code == 'i' || code == 'o' || code == 'u' );
  }


char UCS::map_to_byte( const int code ) throw()
  {
  if( code < 0 ) return 0;
  if( code < 256 ) return code;
  switch( code )
    {
    case CGBREVE: return 0xD0;
    case SGBREVE: return 0xF0;
    case CIDOT  : return 0xDD;
    case SINODOT: return 0xFD;
    case CSCEDI : return 0xDE;
    case SSCEDI : return 0xFE;
    case CSCARON: return 0xA6;
    case SSCARON: return 0xA8;
    case CZCARON: return 0xB4;
    case SZCARON: return 0xB8;
    case EURO   : return 0xA4;
    default     : return 0;
    }
  }


char * UCS::ucs_to_utf8( const int code ) throw()
  {
  static char s[7];

  if( code < 0 || code > 0x7FFFFFFF ) { s[0] = 0; return s; } // invalid code
  if( code < 128 ) { s[0] = code; s[1] = 0; return s; }       // plain ascii
  int i;
  char mask;
  if( code < 0x800 ) { i = 2; mask = 0xC0; }		// 110X XXXX
  else if( code < 0x10000 ) { i = 3; mask = 0xE0; }	// 1110 XXXX
  else if( code < 0x200000 ) { i = 4; mask = 0xF0; }	// 1111 0XXX
  else if( code < 0x4000000 ) { i = 5; mask = 0xF8; }	// 1111 10XX
  else { i = 6; mask = 0xFC; }				// 1111 110X

  s[i] = 0; --i;
  int d = 0;
  for( ; i > 0; --i, d+=6 )
    s[i] = 0x80 | ( ( code >> d ) & 0x3F );		// 10XX XXXX
  s[0] = mask | ( code >> d );
  return s;
  }


int UCS::to_nearest_digit( const int code ) throw()
  {
  switch( code )
    {
    case 'O':
    case 'Q':
    case 'o':     return '0';
    case '|':
    case 'I':
    case 'L':
    case 'l':
    case SINODOT: return '1';
    case 'Z':
    case 'z':     return '2';
    case 'A':
    case 'q':     return '4';
    case 'S':
    case 's':     return '5';
    case 'G':
    case 'b':
    case SOACUTE: return '6';
    case 'J':
    case 'T':     return '7';
    case '&':
    case 'B':     return '8';
    case 'g':     return '9';
    default:      return code;
    }
  }


int UCS::to_nearest_letter( const int code ) throw()
  {
  switch( code )
    {
    case '0': return 'O';
    case '1': return 'l';
    case '2': return 'Z';
    case '4': return 'q';
    case '5': return 'S';
    case '6': return SOACUTE;
    case '7': return 'I';
    case '8': return 'B';
    case '9': return 'g';
    default:  return code;
    }
  }


int UCS::toupper( const int code ) throw()
  {
  if( code < 128 ) return std::toupper( code );
  switch( code )
    {
    case SAGRAVE: return CAGRAVE;
    case SAACUTE: return CAACUTE;
    case SACIRCU: return CACIRCU;
    case SATILDE: return CATILDE;
    case SADIAER: return CADIAER;
    case SARING : return CARING;
    case SCCEDI : return CCCEDI;
    case SEGRAVE: return CEGRAVE;
    case SEACUTE: return CEACUTE;
    case SECIRCU: return CECIRCU;
    case SEDIAER: return CEDIAER;
    case SGBREVE: return CGBREVE;
    case SIGRAVE: return CIGRAVE;
    case SIACUTE: return CIACUTE;
    case SICIRCU: return CICIRCU;
    case SIDIAER: return CIDIAER;
    case SNTILDE: return CNTILDE;
    case SOGRAVE: return COGRAVE;
    case SOACUTE: return COACUTE;
    case SOCIRCU: return COCIRCU;
    case SOTILDE: return COTILDE;
    case SODIAER: return CODIAER;
    case SSCEDI : return CSCEDI;
    case SUGRAVE: return CUGRAVE;
    case SUACUTE: return CUACUTE;
    case SUCIRCU: return CUCIRCU;
    case SUDIAER: return CUDIAER;
    case SYACUTE: return CYACUTE;
    default:      return code;
    }
  }