guniprop.c 31 KB
Newer Older
1 2 3 4 5 6
/* guniprop.c - Unicode character properties.
 *
 * Copyright (C) 1999 Tom Tromey
 * Copyright (C) 2000 Red Hat, Inc.
 *
 * This library is free software; you can redistribute it and/or
7
 * modify it under the terms of the GNU Lesser General Public
8 9 10 11 12 13
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This library 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
14
 * Lesser General Public License for more details.
15
 *
16
 * You should have received a copy of the GNU Lesser General Public
17 18 19 20 21
 * License along with this library; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 02111-1307, USA.
 */

22
#include "config.h"
23

Behdad Esfahbod's avatar
Behdad Esfahbod committed
24
#include <stdlib.h>
25
#include <stddef.h>
26 27
#include <string.h>
#include <locale.h>
28

29 30
#include "glib.h"
#include "gunichartables.h"
31
#include "gmirroringtable.h"
32
#include "gunicodeprivate.h"
33
#include "galias.h"
34

35 36 37
#define ATTR_TABLE(Page) (((Page) <= G_UNICODE_LAST_PAGE_PART1) \
                          ? attr_table_part1[Page] \
                          : attr_table_part2[(Page) - 0xe00])
38

39
#define ATTTABLE(Page, Char) \
40
  ((ATTR_TABLE(Page) == G_UNICODE_MAX_TABLE_INDEX) ? 0 : (attr_data[ATTR_TABLE(Page)][Char]))
41

42 43 44 45
#define TTYPE_PART1(Page, Char) \
  ((type_table_part1[Page] >= G_UNICODE_MAX_TABLE_INDEX) \
   ? (type_table_part1[Page] - G_UNICODE_MAX_TABLE_INDEX) \
   : (type_data[type_table_part1[Page]][Char]))
46

47 48 49 50 51 52 53 54 55 56 57
#define TTYPE_PART2(Page, Char) \
  ((type_table_part2[Page] >= G_UNICODE_MAX_TABLE_INDEX) \
   ? (type_table_part2[Page] - G_UNICODE_MAX_TABLE_INDEX) \
   : (type_data[type_table_part2[Page]][Char]))

#define TYPE(Char) \
  (((Char) <= G_UNICODE_LAST_CHAR_PART1) \
   ? TTYPE_PART1 ((Char) >> 8, (Char) & 0xff) \
   : (((Char) >= 0xe0000 && (Char) <= G_UNICODE_LAST_CHAR) \
      ? TTYPE_PART2 (((Char) - 0xe0000) >> 8, (Char) & 0xff) \
      : G_UNICODE_UNASSIGNED))
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
#define IS(Type, Class)	(((guint)1 << (Type)) & (Class))
#define OR(Type, Rest)	(((guint)1 << (Type)) | (Rest))



#define ISDIGIT(Type)	IS ((Type),				\
			    OR (G_UNICODE_DECIMAL_NUMBER,	\
			    OR (G_UNICODE_LETTER_NUMBER,	\
			    OR (G_UNICODE_OTHER_NUMBER,		0))))

#define ISALPHA(Type)	IS ((Type),				\
			    OR (G_UNICODE_LOWERCASE_LETTER,	\
			    OR (G_UNICODE_UPPERCASE_LETTER,	\
			    OR (G_UNICODE_TITLECASE_LETTER,	\
			    OR (G_UNICODE_MODIFIER_LETTER,	\
			    OR (G_UNICODE_OTHER_LETTER,		0))))))

#define ISALDIGIT(Type)	IS ((Type),				\
			    OR (G_UNICODE_DECIMAL_NUMBER,	\
			    OR (G_UNICODE_LETTER_NUMBER,	\
			    OR (G_UNICODE_OTHER_NUMBER,		\
			    OR (G_UNICODE_LOWERCASE_LETTER,	\
			    OR (G_UNICODE_UPPERCASE_LETTER,	\
			    OR (G_UNICODE_TITLECASE_LETTER,	\
			    OR (G_UNICODE_MODIFIER_LETTER,	\
			    OR (G_UNICODE_OTHER_LETTER,		0)))))))))

#define ISMARK(Type)	IS ((Type),				\
			    OR (G_UNICODE_NON_SPACING_MARK,	\
			    OR (G_UNICODE_COMBINING_MARK,	\
			    OR (G_UNICODE_ENCLOSING_MARK,	0))))
91

Havoc Pennington's avatar
docs  
Havoc Pennington committed
92 93 94 95 96 97 98 99 100 101
/**
 * g_unichar_isalnum:
 * @c: a Unicode character
 * 
 * Determines whether a character is alphanumeric.
 * Given some UTF-8 text, obtain a character value
 * with g_utf8_get_char().
 * 
 * Return value: %TRUE if @c is an alphanumeric character
 **/
102 103 104
gboolean
g_unichar_isalnum (gunichar c)
{
105
  return ISALDIGIT (TYPE (c)) ? TRUE : FALSE;
106 107
}

Havoc Pennington's avatar
docs  
Havoc Pennington committed
108 109 110 111 112 113 114 115 116 117
/**
 * g_unichar_isalpha:
 * @c: a Unicode character
 * 
 * Determines whether a character is alphabetic (i.e. a letter).
 * Given some UTF-8 text, obtain a character value with
 * g_utf8_get_char().
 * 
 * Return value: %TRUE if @c is an alphabetic character
 **/
118 119 120
gboolean
g_unichar_isalpha (gunichar c)
{
121
  return ISALPHA (TYPE (c)) ? TRUE : FALSE;
122 123
}

Havoc Pennington's avatar
docs  
Havoc Pennington committed
124 125 126 127 128 129 130 131 132 133 134

/**
 * g_unichar_iscntrl:
 * @c: a Unicode character
 * 
 * Determines whether a character is a control character.
 * Given some UTF-8 text, obtain a character value with
 * g_utf8_get_char().
 * 
 * Return value: %TRUE if @c is a control character
 **/
135 136 137 138 139 140
gboolean
g_unichar_iscntrl (gunichar c)
{
  return TYPE (c) == G_UNICODE_CONTROL;
}

Havoc Pennington's avatar
docs  
Havoc Pennington committed
141 142 143 144 145 146 147 148 149 150
/**
 * g_unichar_isdigit:
 * @c: a Unicode character
 * 
 * Determines whether a character is numeric (i.e. a digit).  This
 * covers ASCII 0-9 and also digits in other languages/scripts.  Given
 * some UTF-8 text, obtain a character value with g_utf8_get_char().
 * 
 * Return value: %TRUE if @c is a digit
 **/
151 152 153 154 155 156
gboolean
g_unichar_isdigit (gunichar c)
{
  return TYPE (c) == G_UNICODE_DECIMAL_NUMBER;
}

Havoc Pennington's avatar
docs  
Havoc Pennington committed
157 158 159 160 161 162 163 164 165 166 167 168 169

/**
 * g_unichar_isgraph:
 * @c: a Unicode character
 * 
 * Determines whether a character is printable and not a space
 * (returns %FALSE for control characters, format characters, and
 * spaces). g_unichar_isprint() is similar, but returns %TRUE for
 * spaces. Given some UTF-8 text, obtain a character value with
 * g_utf8_get_char().
 * 
 * Return value: %TRUE if @c is printable unless it's a space
 **/
170 171 172
gboolean
g_unichar_isgraph (gunichar c)
{
173 174 175 176 177 178 179 180
  return !IS (TYPE(c),
	      OR (G_UNICODE_CONTROL,
	      OR (G_UNICODE_FORMAT,
	      OR (G_UNICODE_UNASSIGNED,
	      OR (G_UNICODE_PRIVATE_USE,
	      OR (G_UNICODE_SURROGATE,
	      OR (G_UNICODE_SPACE_SEPARATOR,
	     0)))))));
181 182
}

Havoc Pennington's avatar
docs  
Havoc Pennington committed
183 184 185 186 187 188 189 190 191 192
/**
 * g_unichar_islower:
 * @c: a Unicode character
 * 
 * Determines whether a character is a lowercase letter.
 * Given some UTF-8 text, obtain a character value with
 * g_utf8_get_char().
 * 
 * Return value: %TRUE if @c is a lowercase letter
 **/
193 194 195 196 197 198
gboolean
g_unichar_islower (gunichar c)
{
  return TYPE (c) == G_UNICODE_LOWERCASE_LETTER;
}

Havoc Pennington's avatar
docs  
Havoc Pennington committed
199 200 201 202 203 204 205 206 207 208 209 210

/**
 * g_unichar_isprint:
 * @c: a Unicode character
 * 
 * Determines whether a character is printable.
 * Unlike g_unichar_isgraph(), returns %TRUE for spaces.
 * Given some UTF-8 text, obtain a character value with
 * g_utf8_get_char().
 * 
 * Return value: %TRUE if @c is printable
 **/
211 212 213
gboolean
g_unichar_isprint (gunichar c)
{
214 215 216 217 218 219 220
  return !IS (TYPE(c),
	      OR (G_UNICODE_CONTROL,
	      OR (G_UNICODE_FORMAT,
	      OR (G_UNICODE_UNASSIGNED,
	      OR (G_UNICODE_PRIVATE_USE,
	      OR (G_UNICODE_SURROGATE,
	     0))))));
221 222
}

Havoc Pennington's avatar
docs  
Havoc Pennington committed
223 224 225 226
/**
 * g_unichar_ispunct:
 * @c: a Unicode character
 * 
227
 * Determines whether a character is punctuation or a symbol.
Havoc Pennington's avatar
docs  
Havoc Pennington committed
228 229 230
 * Given some UTF-8 text, obtain a character value with
 * g_utf8_get_char().
 * 
231
 * Return value: %TRUE if @c is a punctuation or symbol character
Havoc Pennington's avatar
docs  
Havoc Pennington committed
232
 **/
233 234 235
gboolean
g_unichar_ispunct (gunichar c)
{
236 237 238 239 240 241 242 243 244 245 246 247 248
  return IS (TYPE(c),
	     OR (G_UNICODE_CONNECT_PUNCTUATION,
	     OR (G_UNICODE_DASH_PUNCTUATION,
	     OR (G_UNICODE_CLOSE_PUNCTUATION,
	     OR (G_UNICODE_FINAL_PUNCTUATION,
	     OR (G_UNICODE_INITIAL_PUNCTUATION,
	     OR (G_UNICODE_OTHER_PUNCTUATION,
	     OR (G_UNICODE_OPEN_PUNCTUATION,
	     OR (G_UNICODE_CURRENCY_SYMBOL,
	     OR (G_UNICODE_MODIFIER_SYMBOL,
	     OR (G_UNICODE_MATH_SYMBOL,
	     OR (G_UNICODE_OTHER_SYMBOL,
	    0)))))))))))) ? TRUE : FALSE;
249 250
}

Havoc Pennington's avatar
docs  
Havoc Pennington committed
251 252 253 254 255 256 257 258 259 260 261 262
/**
 * g_unichar_isspace:
 * @c: a Unicode character
 * 
 * Determines whether a character is a space, tab, or line separator
 * (newline, carriage return, etc.).  Given some UTF-8 text, obtain a
 * character value with g_utf8_get_char().
 *
 * (Note: don't use this to do word breaking; you have to use
 * Pango or equivalent to get word breaking right, the algorithm
 * is fairly complex.)
 *  
263
 * Return value: %TRUE if @c is a space character
Havoc Pennington's avatar
docs  
Havoc Pennington committed
264
 **/
265 266 267
gboolean
g_unichar_isspace (gunichar c)
{
268
  switch (c)
Havoc Pennington's avatar
Havoc Pennington committed
269
    {
270 271 272 273 274 275 276 277 278 279
      /* special-case these since Unicode thinks they are not spaces */
    case '\t':
    case '\n':
    case '\r':
    case '\f':
      return TRUE;
      break;
      
    default:
      {
280 281 282 283 284
	return IS (TYPE(c),
	           OR (G_UNICODE_SPACE_SEPARATOR,
	           OR (G_UNICODE_LINE_SEPARATOR,
                   OR (G_UNICODE_PARAGRAPH_SEPARATOR,
		  0)))) ? TRUE : FALSE;
285 286
      }
      break;
Havoc Pennington's avatar
Havoc Pennington committed
287
    }
288 289 290 291
}

/**
 * g_unichar_isupper:
292
 * @c: a Unicode character
293 294 295
 * 
 * Determines if a character is uppercase.
 * 
296
 * Return value: %TRUE if @c is an uppercase character
297 298 299 300 301 302 303 304 305
 **/
gboolean
g_unichar_isupper (gunichar c)
{
  return TYPE (c) == G_UNICODE_UPPERCASE_LETTER;
}

/**
 * g_unichar_istitle:
306
 * @c: a Unicode character
307 308 309 310 311 312
 * 
 * Determines if a character is titlecase. Some characters in
 * Unicode which are composites, such as the DZ digraph
 * have three case variants instead of just two. The titlecase
 * form is used at the beginning of a word where only the
 * first letter is capitalized. The titlecase form of the DZ
313
 * digraph is U+01F2 LATIN CAPITAL LETTTER D WITH SMALL LETTER Z.
314
 * 
315
 * Return value: %TRUE if the character is titlecase
316 317 318 319 320
 **/
gboolean
g_unichar_istitle (gunichar c)
{
  unsigned int i;
321
  for (i = 0; i < G_N_ELEMENTS (title_table); ++i)
322
    if (title_table[i][0] == c)
323 324
      return TRUE;
  return FALSE;
325 326 327 328
}

/**
 * g_unichar_isxdigit:
329
 * @c: a Unicode character.
330
 * 
331
 * Determines if a character is a hexidecimal digit.
332
 * 
333
 * Return value: %TRUE if the character is a hexadecimal digit
334 335 336 337 338 339
 **/
gboolean
g_unichar_isxdigit (gunichar c)
{
  return ((c >= 'a' && c <= 'f')
	  || (c >= 'A' && c <= 'F')
340
	  || ISDIGIT (TYPE (c)));
341 342 343 344
}

/**
 * g_unichar_isdefined:
345
 * @c: a Unicode character
346 347
 * 
 * Determines if a given character is assigned in the Unicode
Havoc Pennington's avatar
docs  
Havoc Pennington committed
348
 * standard.
349
 *
350
 * Return value: %TRUE if the character has an assigned value
351 352 353 354
 **/
gboolean
g_unichar_isdefined (gunichar c)
{
355
  return TYPE (c) != G_UNICODE_UNASSIGNED;
356 357 358 359
}

/**
 * g_unichar_iswide:
360
 * @c: a Unicode character
361 362 363 364
 * 
 * Determines if a character is typically rendered in a double-width
 * cell.
 * 
365
 * Return value: %TRUE if the character is wide
366 367 368 369 370 371
 **/
/* This function stolen from Markus Kuhn <Markus.Kuhn@cl.cam.ac.uk>.  */
gboolean
g_unichar_iswide (gunichar c)
{
  if (c < 0x1100)
372
    return FALSE;
373

374 375 376 377 378 379 380 381 382 383 384
  return (c <= 0x115f  /* Hangul Jamo init. consonants */ 
          || c == 0x2329 || c == 0x232a     /* angle brackets */
          || (c >= 0x2e80 && c <= 0xa4cf && (c < 0x302a || c > 0x302f) 
              && c != 0x303f && c != 0x3099 && c!= 0x309a) /* CJK ... Yi */
          || (c >= 0xac00 && c <= 0xd7a3)   /* Hangul Syllables */
          || (c >= 0xf900 && c <= 0xfaff)   /* CJK Compatibility Ideographs */
          || (c >= 0xfe30 && c <= 0xfe6f)   /* CJK Compatibility Forms */
          || (c >= 0xff00 && c <= 0xff60)   /* Fullwidth Forms */
          || (c >= 0xffe0 && c <= 0xffe6)   /* Fullwidth Forms */
          || (c >= 0x20000 && c <= 0x2fffd) /* CJK extra stuff */
          || (c >= 0x30000 && c <= 0x3fffd));
385 386
}

387 388 389 390 391 392

struct Interval
{
  gunichar start, end;
};

Matthias Clasen's avatar
2.11.0  
Matthias Clasen committed
393
static int
394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415
interval_compare (const void *key, const void *elt)
{
  gunichar c = GPOINTER_TO_UINT (key);
  struct Interval *interval = elt;

  if (c < interval->start)
    return -1;
  if (c > interval->end)
    return +1;

  return 0;
}

/**
 * g_unichar_iswide_cjk:
 * @c: a Unicode character
 * 
 * Determines if a character is typically rendered in a double-width
 * cell under legacy East Asian locales.  If a character is wide according to
 * g_unichar_iswide(), then it is also reported wide with this function, but
 * the converse is not necessarily true.  See the
 * <ulink url="http://www.unicode.org/reports/tr11/">Unicode Standard
Matthias Clasen's avatar
Matthias Clasen committed
416
 * Annex #11</ulink> for details.
417 418
 * 
 * Return value: %TRUE if the character is wide in legacy East Asian locales
Matthias Clasen's avatar
Matthias Clasen committed
419 420 421
 *
 * Since: 2.12
 */
422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493
/* This function stolen from Markus Kuhn <Markus.Kuhn@cl.cam.ac.uk>.  */
gboolean
g_unichar_iswide_cjk (gunichar c)
{
  /* sorted list of non-overlapping intervals of East Asian Ambiguous
   * characters, generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" */
  static const struct Interval ambiguous[] = {
    { 0x00A1, 0x00A1 }, { 0x00A4, 0x00A4 }, { 0x00A7, 0x00A8 },
    { 0x00AA, 0x00AA }, { 0x00AE, 0x00AE }, { 0x00B0, 0x00B4 },
    { 0x00B6, 0x00BA }, { 0x00BC, 0x00BF }, { 0x00C6, 0x00C6 },
    { 0x00D0, 0x00D0 }, { 0x00D7, 0x00D8 }, { 0x00DE, 0x00E1 },
    { 0x00E6, 0x00E6 }, { 0x00E8, 0x00EA }, { 0x00EC, 0x00ED },
    { 0x00F0, 0x00F0 }, { 0x00F2, 0x00F3 }, { 0x00F7, 0x00FA },
    { 0x00FC, 0x00FC }, { 0x00FE, 0x00FE }, { 0x0101, 0x0101 },
    { 0x0111, 0x0111 }, { 0x0113, 0x0113 }, { 0x011B, 0x011B },
    { 0x0126, 0x0127 }, { 0x012B, 0x012B }, { 0x0131, 0x0133 },
    { 0x0138, 0x0138 }, { 0x013F, 0x0142 }, { 0x0144, 0x0144 },
    { 0x0148, 0x014B }, { 0x014D, 0x014D }, { 0x0152, 0x0153 },
    { 0x0166, 0x0167 }, { 0x016B, 0x016B }, { 0x01CE, 0x01CE },
    { 0x01D0, 0x01D0 }, { 0x01D2, 0x01D2 }, { 0x01D4, 0x01D4 },
    { 0x01D6, 0x01D6 }, { 0x01D8, 0x01D8 }, { 0x01DA, 0x01DA },
    { 0x01DC, 0x01DC }, { 0x0251, 0x0251 }, { 0x0261, 0x0261 },
    { 0x02C4, 0x02C4 }, { 0x02C7, 0x02C7 }, { 0x02C9, 0x02CB },
    { 0x02CD, 0x02CD }, { 0x02D0, 0x02D0 }, { 0x02D8, 0x02DB },
    { 0x02DD, 0x02DD }, { 0x02DF, 0x02DF }, { 0x0391, 0x03A1 },
    { 0x03A3, 0x03A9 }, { 0x03B1, 0x03C1 }, { 0x03C3, 0x03C9 },
    { 0x0401, 0x0401 }, { 0x0410, 0x044F }, { 0x0451, 0x0451 },
    { 0x2010, 0x2010 }, { 0x2013, 0x2016 }, { 0x2018, 0x2019 },
    { 0x201C, 0x201D }, { 0x2020, 0x2022 }, { 0x2024, 0x2027 },
    { 0x2030, 0x2030 }, { 0x2032, 0x2033 }, { 0x2035, 0x2035 },
    { 0x203B, 0x203B }, { 0x203E, 0x203E }, { 0x2074, 0x2074 },
    { 0x207F, 0x207F }, { 0x2081, 0x2084 }, { 0x20AC, 0x20AC },
    { 0x2103, 0x2103 }, { 0x2105, 0x2105 }, { 0x2109, 0x2109 },
    { 0x2113, 0x2113 }, { 0x2116, 0x2116 }, { 0x2121, 0x2122 },
    { 0x2126, 0x2126 }, { 0x212B, 0x212B }, { 0x2153, 0x2154 },
    { 0x215B, 0x215E }, { 0x2160, 0x216B }, { 0x2170, 0x2179 },
    { 0x2190, 0x2199 }, { 0x21B8, 0x21B9 }, { 0x21D2, 0x21D2 },
    { 0x21D4, 0x21D4 }, { 0x21E7, 0x21E7 }, { 0x2200, 0x2200 },
    { 0x2202, 0x2203 }, { 0x2207, 0x2208 }, { 0x220B, 0x220B },
    { 0x220F, 0x220F }, { 0x2211, 0x2211 }, { 0x2215, 0x2215 },
    { 0x221A, 0x221A }, { 0x221D, 0x2220 }, { 0x2223, 0x2223 },
    { 0x2225, 0x2225 }, { 0x2227, 0x222C }, { 0x222E, 0x222E },
    { 0x2234, 0x2237 }, { 0x223C, 0x223D }, { 0x2248, 0x2248 },
    { 0x224C, 0x224C }, { 0x2252, 0x2252 }, { 0x2260, 0x2261 },
    { 0x2264, 0x2267 }, { 0x226A, 0x226B }, { 0x226E, 0x226F },
    { 0x2282, 0x2283 }, { 0x2286, 0x2287 }, { 0x2295, 0x2295 },
    { 0x2299, 0x2299 }, { 0x22A5, 0x22A5 }, { 0x22BF, 0x22BF },
    { 0x2312, 0x2312 }, { 0x2460, 0x24E9 }, { 0x24EB, 0x254B },
    { 0x2550, 0x2573 }, { 0x2580, 0x258F }, { 0x2592, 0x2595 },
    { 0x25A0, 0x25A1 }, { 0x25A3, 0x25A9 }, { 0x25B2, 0x25B3 },
    { 0x25B6, 0x25B7 }, { 0x25BC, 0x25BD }, { 0x25C0, 0x25C1 },
    { 0x25C6, 0x25C8 }, { 0x25CB, 0x25CB }, { 0x25CE, 0x25D1 },
    { 0x25E2, 0x25E5 }, { 0x25EF, 0x25EF }, { 0x2605, 0x2606 },
    { 0x2609, 0x2609 }, { 0x260E, 0x260F }, { 0x2614, 0x2615 },
    { 0x261C, 0x261C }, { 0x261E, 0x261E }, { 0x2640, 0x2640 },
    { 0x2642, 0x2642 }, { 0x2660, 0x2661 }, { 0x2663, 0x2665 },
    { 0x2667, 0x266A }, { 0x266C, 0x266D }, { 0x266F, 0x266F },
    { 0x273D, 0x273D }, { 0x2776, 0x277F }, { 0xE000, 0xF8FF },
    { 0xFFFD, 0xFFFD }, { 0xF0000, 0xFFFFD }, { 0x100000, 0x10FFFD }
  };

  if (g_unichar_iswide (c))
    return TRUE;

  if (bsearch (GUINT_TO_POINTER (c), ambiguous, G_N_ELEMENTS (ambiguous), sizeof ambiguous[0],
	       interval_compare))
    return TRUE;

  return FALSE;
}


494 495
/**
 * g_unichar_toupper:
496
 * @c: a Unicode character
497
 * 
498
 * Converts a character to uppercase.
499 500 501
 * 
 * Return value: the result of converting @c to uppercase.
 *               If @c is not an lowercase or titlecase character,
502
 *               or has no upper case equivalent @c is returned unchanged.
503 504 505 506 507 508
 **/
gunichar
g_unichar_toupper (gunichar c)
{
  int t = TYPE (c);
  if (t == G_UNICODE_LOWERCASE_LETTER)
509 510
    {
      gunichar val = ATTTABLE (c >> 8, c & 0xff);
511
      if (val >= 0x1000000)
512
	{
513
	  const gchar *p = special_case_table + val - 0x1000000;
514
	  return g_utf8_get_char (p);
515 516
	}
      else
517
	return val ? val : c;
518
    }
519 520 521
  else if (t == G_UNICODE_TITLECASE_LETTER)
    {
      unsigned int i;
522
      for (i = 0; i < G_N_ELEMENTS (title_table); ++i)
523 524 525 526 527 528 529 530 531 532
	{
	  if (title_table[i][0] == c)
	    return title_table[i][1];
	}
    }
  return c;
}

/**
 * g_unichar_tolower:
533
 * @c: a Unicode character.
534
 * 
535
 * Converts a character to lower case.
536
 * 
Owen Taylor's avatar
Owen Taylor committed
537
 * Return value: the result of converting @c to lower case.
538
 *               If @c is not an upperlower or titlecase character,
539
 *               or has no lowercase equivalent @c is returned unchanged.
540 541 542 543 544 545
 **/
gunichar
g_unichar_tolower (gunichar c)
{
  int t = TYPE (c);
  if (t == G_UNICODE_UPPERCASE_LETTER)
546 547
    {
      gunichar val = ATTTABLE (c >> 8, c & 0xff);
548
      if (val >= 0x1000000)
549
	{
550
	  const gchar *p = special_case_table + val - 0x1000000;
551
	  return g_utf8_get_char (p);
552 553
	}
      else
554
	return val ? val : c;
555
    }
556 557 558
  else if (t == G_UNICODE_TITLECASE_LETTER)
    {
      unsigned int i;
559
      for (i = 0; i < G_N_ELEMENTS (title_table); ++i)
560 561 562 563 564 565 566 567 568 569
	{
	  if (title_table[i][0] == c)
	    return title_table[i][2];
	}
    }
  return c;
}

/**
 * g_unichar_totitle:
570
 * @c: a Unicode character
571
 * 
572
 * Converts a character to the titlecase.
573 574 575 576 577 578 579 580 581
 * 
 * Return value: the result of converting @c to titlecase.
 *               If @c is not an uppercase or lowercase character,
 *               @c is returned unchanged.
 **/
gunichar
g_unichar_totitle (gunichar c)
{
  unsigned int i;
582
  for (i = 0; i < G_N_ELEMENTS (title_table); ++i)
583 584 585 586 587 588 589 590 591 592 593
    {
      if (title_table[i][0] == c || title_table[i][1] == c
	  || title_table[i][2] == c)
	return title_table[i][0];
    }
  return (TYPE (c) == G_UNICODE_LOWERCASE_LETTER
	  ? ATTTABLE (c >> 8, c & 0xff)
	  : c);
}

/**
Havoc Pennington's avatar
docs  
Havoc Pennington committed
594
 * g_unichar_digit_value:
595
 * @c: a Unicode character
596 597
 *
 * Determines the numeric value of a character as a decimal
598
 * digit.
599 600
 *
 * Return value: If @c is a decimal digit (according to
601
 * g_unichar_isdigit()), its numeric value. Otherwise, -1.
602 603 604 605 606 607 608 609 610 611 612
 **/
int
g_unichar_digit_value (gunichar c)
{
  if (TYPE (c) == G_UNICODE_DECIMAL_NUMBER)
    return ATTTABLE (c >> 8, c & 0xff);
  return -1;
}

/**
 * g_unichar_xdigit_value:
613
 * @c: a Unicode character
614 615
 *
 * Determines the numeric value of a character as a hexidecimal
616
 * digit.
617 618
 *
 * Return value: If @c is a hex digit (according to
619
 * g_unichar_isxdigit()), its numeric value. Otherwise, -1.
620 621 622 623 624
 **/
int
g_unichar_xdigit_value (gunichar c)
{
  if (c >= 'A' && c <= 'F')
625
    return c - 'A' + 10;
626
  if (c >= 'a' && c <= 'f')
627
    return c - 'a' + 10;
628 629 630 631 632 633 634
  if (TYPE (c) == G_UNICODE_DECIMAL_NUMBER)
    return ATTTABLE (c >> 8, c & 0xff);
  return -1;
}

/**
 * g_unichar_type:
635
 * @c: a Unicode character
636
 * 
637
 * Classifies a Unicode character by type.
638
 * 
Havoc Pennington's avatar
docs  
Havoc Pennington committed
639
 * Return value: the type of the character.
640 641 642 643 644 645
 **/
GUnicodeType
g_unichar_type (gunichar c)
{
  return TYPE (c);
}
646 647 648 649 650 651 652 653 654 655 656 657 658 659

/*
 * Case mapping functions
 */

typedef enum {
  LOCALE_NORMAL,
  LOCALE_TURKIC,
  LOCALE_LITHUANIAN
} LocaleType;

static LocaleType
get_locale_type (void)
{
660 661 662 663 664 665 666 667
#ifdef G_OS_WIN32
  char *tem = g_win32_getlocale ();
  char locale[2];

  locale[0] = tem[0];
  locale[1] = tem[1];
  g_free (tem);
#else
668
  const char *locale = setlocale (LC_CTYPE, NULL);
669
#endif
670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689

  switch (locale[0])
    {
   case 'a':
      if (locale[1] == 'z')
	return LOCALE_TURKIC;
      break;
    case 'l':
      if (locale[1] == 't')
	return LOCALE_LITHUANIAN;
      break;
    case 't':
      if (locale[1] == 'r')
	return LOCALE_TURKIC;
      break;
    }

  return LOCALE_NORMAL;
}

690
static gint
691 692 693 694 695
output_marks (const char **p_inout,
	      char        *out_buffer,
	      gboolean     remove_dot)
{
  const char *p = *p_inout;
696
  gint len = 0;
697 698 699 700 701
  
  while (*p)
    {
      gunichar c = g_utf8_get_char (p);
      
702
      if (ISMARK (TYPE (c)))
703 704
	{
	  if (!remove_dot || c != 0x307 /* COMBINING DOT ABOVE */)
705
	    len += g_unichar_to_utf8 (c, out_buffer ? out_buffer + len : NULL);
706 707 708 709 710 711 712 713 714 715
	  p = g_utf8_next_char (p);
	}
      else
	break;
    }

  *p_inout = p;
  return len;
}

716
static gint
717
output_special_case (gchar *out_buffer,
718
		     int    offset,
719 720 721
		     int    type,
		     int    which)
{
722
  const gchar *p = special_case_table + offset;
723
  gint len;
724 725

  if (type != G_UNICODE_TITLECASE_LETTER)
726
    p = g_utf8_next_char (p);
727 728

  if (which == 1)
729
    p += strlen (p) + 1;
730

731 732 733
  len = strlen (p);
  if (out_buffer)
    memcpy (out_buffer, p, len);
734 735 736 737 738 739

  return len;
}

static gsize
real_toupper (const gchar *str,
740
	      gssize       max_len,
741 742 743 744 745 746 747 748
	      gchar       *out_buffer,
	      LocaleType   locale_type)
{
  const gchar *p = str;
  const char *last = NULL;
  gsize len = 0;
  gboolean last_was_i = FALSE;

749
  while ((max_len < 0 || p < str + max_len) && *p)
750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780
    {
      gunichar c = g_utf8_get_char (p);
      int t = TYPE (c);
      gunichar val;

      last = p;
      p = g_utf8_next_char (p);

      if (locale_type == LOCALE_LITHUANIAN)
	{
	  if (c == 'i')
	    last_was_i = TRUE;
	  else 
	    {
	      if (last_was_i)
		{
		  /* Nasty, need to remove any dot above. Though
		   * I think only E WITH DOT ABOVE occurs in practice
		   * which could simplify this considerably.
		   */
		  gsize decomp_len, i;
		  gunichar *decomp;

		  decomp = g_unicode_canonical_decomposition (c, &decomp_len);
		  for (i=0; i < decomp_len; i++)
		    {
		      if (decomp[i] != 0x307 /* COMBINING DOT ABOVE */)
			len += g_unichar_to_utf8 (g_unichar_toupper (decomp[i]), out_buffer ? out_buffer + len : NULL);
		    }
		  g_free (decomp);
		  
781
		  len += output_marks (&p, out_buffer ? out_buffer + len : NULL, TRUE);
782 783 784 785

		  continue;
		}

786
	      if (!ISMARK (t))
787 788 789 790 791 792 793 794 795 796 797 798 799 800
		last_was_i = FALSE;
	    }
	}
      
      if (locale_type == LOCALE_TURKIC && c == 'i')
	{
	  /* i => LATIN CAPITAL LETTER I WITH DOT ABOVE */
	  len += g_unichar_to_utf8 (0x130, out_buffer ? out_buffer + len : NULL); 
	}
      else if (c == 0x0345)	/* COMBINING GREEK YPOGEGRAMMENI */
	{
	  /* Nasty, need to move it after other combining marks .. this would go away if
	   * we normalized first.
	   */
801
	  len += output_marks (&p, out_buffer ? out_buffer + len : NULL, FALSE);
802 803 804 805

	  /* And output as GREEK CAPITAL LETTER IOTA */
	  len += g_unichar_to_utf8 (0x399, out_buffer ? out_buffer + len : NULL); 	  
	}
806 807 808 809
      else if (IS (t,
		   OR (G_UNICODE_LOWERCASE_LETTER,
		   OR (G_UNICODE_TITLECASE_LETTER,
		  0))))
810 811 812
	{
	  val = ATTTABLE (c >> 8, c & 0xff);

813
	  if (val >= 0x1000000)
814
	    {
815
	      len += output_special_case (out_buffer ? out_buffer + len : NULL, val - 0x1000000, t,
816 817 818 819 820 821 822 823 824 825
					  t == G_UNICODE_LOWERCASE_LETTER ? 0 : 1);
	    }
	  else
	    {
	      if (t == G_UNICODE_TITLECASE_LETTER)
		{
		  unsigned int i;
		  for (i = 0; i < G_N_ELEMENTS (title_table); ++i)
		    {
		      if (title_table[i][0] == c)
826 827 828 829
			{
			  val = title_table[i][1];
			  break;
			}
830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851
		    }
		}

	      len += g_unichar_to_utf8 (val, out_buffer ? out_buffer + len : NULL);
	    }
	}
      else
	{
	  gsize char_len = g_utf8_skip[*(guchar *)last];

	  if (out_buffer)
	    memcpy (out_buffer + len, last, char_len);

	  len += char_len;
	}

    }

  return len;
}

/**
852 853 854
 * g_utf8_strup:
 * @str: a UTF-8 encoded string
 * @len: length of @str, in bytes, or -1 if @str is nul-terminated.
855 856 857 858 859 860 861 862 863 864 865
 * 
 * Converts all Unicode characters in the string that have a case
 * to uppercase. The exact manner that this is done depends
 * on the current locale, and may result in the number of
 * characters in the string increasing. (For instance, the
 * German ess-zet will be changed to SS.)
 * 
 * Return value: a newly allocated string, with all characters
 *    converted to uppercase.  
 **/
gchar *
866 867
g_utf8_strup (const gchar *str,
	      gssize       len)
868
{
869
  gsize result_len;
870 871 872 873 874 875 876 877 878 879
  LocaleType locale_type;
  gchar *result;

  g_return_val_if_fail (str != NULL, NULL);

  locale_type = get_locale_type ();
  
  /*
   * We use a two pass approach to keep memory management simple
   */
880 881
  result_len = real_toupper (str, len, NULL, locale_type);
  result = g_malloc (result_len + 1);
882
  real_toupper (str, len, result, locale_type);
883
  result[result_len] = '\0';
884 885 886 887

  return result;
}

888 889 890
/* traverses the string checking for characters with combining class == 230
 * until a base character is found */
static gboolean
891
has_more_above (const gchar *str)
892
{
893
  const gchar *p = str;
894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909
  gint combining_class;

  while (*p)
    {
      combining_class = _g_unichar_combining_class (g_utf8_get_char (p));
      if (combining_class == 230)
        return TRUE;
      else if (combining_class == 0)
        break;

      p = g_utf8_next_char (p);
    }

  return FALSE;
}

910 911
static gsize
real_tolower (const gchar *str,
912
	      gssize       max_len,
913 914 915 916 917 918 919
	      gchar       *out_buffer,
	      LocaleType   locale_type)
{
  const gchar *p = str;
  const char *last = NULL;
  gsize len = 0;

920
  while ((max_len < 0 || p < str + max_len) && *p)
921 922 923 924 925 926 927 928 929 930
    {
      gunichar c = g_utf8_get_char (p);
      int t = TYPE (c);
      gunichar val;

      last = p;
      p = g_utf8_next_char (p);

      if (locale_type == LOCALE_TURKIC && c == 'I')
	{
931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970
          if (g_utf8_get_char (p) == 0x0307)
            {
              /* I + COMBINING DOT ABOVE => i (U+0069) */
              len += g_unichar_to_utf8 (0x0069, out_buffer ? out_buffer + len : NULL); 
              p = g_utf8_next_char (p);
            }
          else
            {
              /* I => LATIN SMALL LETTER DOTLESS I */
              len += g_unichar_to_utf8 (0x131, out_buffer ? out_buffer + len : NULL); 
            }
        }
      /* Introduce an explicit dot above when lowercasing capital I's and J's
       * whenever there are more accents above. [SpecialCasing.txt] */
      else if (locale_type == LOCALE_LITHUANIAN && 
               (c == 0x00cc || c == 0x00cd || c == 0x0128))
        {
          len += g_unichar_to_utf8 (0x0069, out_buffer ? out_buffer + len : NULL); 
          len += g_unichar_to_utf8 (0x0307, out_buffer ? out_buffer + len : NULL); 

          switch (c)
            {
            case 0x00cc: 
              len += g_unichar_to_utf8 (0x0300, out_buffer ? out_buffer + len : NULL); 
              break;
            case 0x00cd: 
              len += g_unichar_to_utf8 (0x0301, out_buffer ? out_buffer + len : NULL); 
              break;
            case 0x0128: 
              len += g_unichar_to_utf8 (0x0303, out_buffer ? out_buffer + len : NULL); 
              break;
            }
        }
      else if (locale_type == LOCALE_LITHUANIAN && 
               (c == 'I' || c == 'J' || c == 0x012e) && 
               has_more_above (p))
        {
          len += g_unichar_to_utf8 (g_unichar_tolower (c), out_buffer ? out_buffer + len : NULL); 
          len += g_unichar_to_utf8 (0x0307, out_buffer ? out_buffer + len : NULL); 
        }
971 972
      else if (c == 0x03A3)	/* GREEK CAPITAL LETTER SIGMA */
	{
973 974 975 976 977 978 979 980 981 982 983
	  if ((max_len < 0 || p < str + max_len) && *p)
	    {
	      gunichar next_c = g_utf8_get_char (p);
	      int next_type = TYPE(next_c);

	      /* SIGMA mapps differently depending on whether it is
	       * final or not. The following simplified test would
	       * fail in the case of combining marks following the
	       * sigma, but I don't think that occurs in real text.
	       * The test here matches that in ICU.
	       */
984
	      if (ISALPHA (next_type)) /* Lu,Ll,Lt,Lm,Lo */
985 986 987 988
		val = 0x3c3;	/* GREEK SMALL SIGMA */
	      else
		val = 0x3c2;	/* GREEK SMALL FINAL SIGMA */
	    }
989 990 991 992 993
	  else
	    val = 0x3c2;	/* GREEK SMALL FINAL SIGMA */

	  len += g_unichar_to_utf8 (val, out_buffer ? out_buffer + len : NULL);
	}
994 995 996 997
      else if (IS (t,
		   OR (G_UNICODE_UPPERCASE_LETTER,
		   OR (G_UNICODE_TITLECASE_LETTER,
		  0))))
998 999 1000
	{
	  val = ATTTABLE (c >> 8, c & 0xff);

1001
	  if (val >= 0x1000000)
1002
	    {
1003
	      len += output_special_case (out_buffer ? out_buffer + len : NULL, val - 0x1000000, t, 0);
1004 1005 1006 1007 1008 1009 1010 1011 1012
	    }
	  else
	    {
	      if (t == G_UNICODE_TITLECASE_LETTER)
		{
		  unsigned int i;
		  for (i = 0; i < G_N_ELEMENTS (title_table); ++i)
		    {
		      if (title_table[i][0] == c)
1013 1014 1015 1016
			{
			  val = title_table[i][2];
			  break;
			}
1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038
		    }
		}

	      len += g_unichar_to_utf8 (val, out_buffer ? out_buffer + len : NULL);
	    }
	}
      else
	{
	  gsize char_len = g_utf8_skip[*(guchar *)last];

	  if (out_buffer)
	    memcpy (out_buffer + len, last, char_len);

	  len += char_len;
	}

    }

  return len;
}

/**
1039 1040 1041
 * g_utf8_strdown:
 * @str: a UTF-8 encoded string
 * @len: length of @str, in bytes, or -1 if @str is nul-terminated.
1042 1043 1044 1045 1046 1047 1048 1049 1050 1051
 * 
 * Converts all Unicode characters in the string that have a case
 * to lowercase. The exact manner that this is done depends
 * on the current locale, and may result in the number of
 * characters in the string changing.
 * 
 * Return value: a newly allocated string, with all characters
 *    converted to lowercase.  
 **/
gchar *
1052 1053
g_utf8_strdown (const gchar *str,
		gssize       len)
1054
{
1055
  gsize result_len;
1056 1057 1058 1059 1060 1061 1062 1063 1064 1065
  LocaleType locale_type;
  gchar *result;

  g_return_val_if_fail (str != NULL, NULL);

  locale_type = get_locale_type ();
  
  /*
   * We use a two pass approach to keep memory management simple
   */
1066 1067
  result_len = real_tolower (str, len, NULL, locale_type);
  result = g_malloc (result_len + 1);
1068
  real_tolower (str, len, result, locale_type);
1069
  result[result_len] = '\0';
1070 1071 1072 1073 1074 1075 1076

  return result;
}

/**
 * g_utf8_casefold:
 * @str: a UTF-8 encoded string
1077
 * @len: length of @str, in bytes, or -1 if @str is nul-terminated.
1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094
 * 
 * Converts a string into a form that is independent of case. The
 * result will not correspond to any particular case, but can be
 * compared for equality or ordered with the results of calling
 * g_utf8_casefold() on other strings.
 * 
 * Note that calling g_utf8_casefold() followed by g_utf8_collate() is
 * only an approximation to the correct linguistic case insensitive
 * ordering, though it is a fairly good one. Getting this exactly
 * right would require a more sophisticated collation function that
 * takes case sensitivity into account. GLib does not currently
 * provide such a function.
 * 
 * Return value: a newly allocated string, that is a
 *   case independent form of @str.
 **/
gchar *
1095 1096
g_utf8_casefold (const gchar *str,
		 gssize       len)
1097
{
Matthias Clasen's avatar
Matthias Clasen committed
1098
  GString *result;
1099 1100
  const char *p;

1101 1102
  g_return_val_if_fail (str != NULL, NULL);

Matthias Clasen's avatar
Matthias Clasen committed
1103
  result = g_string_new (NULL);
1104
  p = str;
1105
  while ((len < 0 || p < str + len) && *p)
1106 1107 1108 1109 1110 1111 1112
    {
      gunichar ch = g_utf8_get_char (p);

      int start = 0;
      int end = G_N_ELEMENTS (casefold_table);

      if (ch >= casefold_table[start].ch &&
1113
          ch <= casefold_table[end - 1].ch)
1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131
	{
	  while (TRUE)
	    {
	      int half = (start + end) / 2;
	      if (ch == casefold_table[half].ch)
		{
		  g_string_append (result, casefold_table[half].data);
		  goto next;
		}
	      else if (half == start)
		break;
	      else if (ch > casefold_table[half].ch)
		start = half;
	      else
		end = half;
	    }
	}

1132
      g_string_append_unichar (result, g_unichar_tolower (ch));
1133 1134 1135 1136 1137 1138 1139
      
    next:
      p = g_utf8_next_char (p);
    }

  return g_string_free (result, FALSE); 
}
1140 1141 1142

/**
 * g_unichar_get_mirror_char:
1143
 * @ch: a Unicode character
1144 1145 1146 1147 1148 1149 1150 1151 1152
 * @mirrored_ch: location to store the mirrored character
 * 
 * In Unicode, some characters are <firstterm>mirrored</firstterm>. This
 * means that their images are mirrored horizontally in text that is laid
 * out from right to left. For instance, "(" would become its mirror image,
 * ")", in right-to-left text.
 *
 * If @ch has the Unicode mirrored property and there is another unicode
 * character that typically has a glyph that is the mirror image of @ch's
1153 1154
 * glyph and @mirrored_ch is set, it puts that character in the address
 * pointed to by @mirrored_ch.  Otherwise the original character is put.
1155
 *
1156
 * Return value: %TRUE if @ch has a mirrored character, %FALSE otherwise
1157 1158
 *
 * Since: 2.4
1159 1160 1161 1162 1163 1164
 **/
gboolean
g_unichar_get_mirror_char (gunichar ch,
                           gunichar *mirrored_ch)
{
  gboolean found;
1165
  gunichar mirrored;
1166

1167
  mirrored = GLIB_GET_MIRRORING(ch);
1168

1169
  found = ch != mirrored;
1170
  if (mirrored_ch)
1171
    *mirrored_ch = mirrored;
1172 1173 1174 1175

  return found;

}
1176 1177 1178

#define __G_UNIPROP_C__
#include "galiasdef.c"