1/* gunicode.h - Unicode manipulation functions 2 * 3 * Copyright (C) 1999, 2000 Tom Tromey 4 * Copyright 2000, 2005 Red Hat, Inc. 5 * 6 * The Gnome Library is free software; you can redistribute it and/or 7 * modify it under the terms of the GNU Lesser General Public License as 8 * published by the Free Software Foundation; either version 2 of the 9 * License, or (at your option) any later version. 10 * 11 * The Gnome Library is distributed in the hope that it will be useful, 12 * but WITHOUT ANY WARRANTY; without even the implied warranty of 13 * 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 * License along with the Gnome Library; see the file COPYING.LIB. If not, 18 * write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330, 19 * Boston, MA 02111-1307, USA. 20 */ 21 22#if defined(G_DISABLE_SINGLE_INCLUDES) && !defined (__GLIB_H_INSIDE__) && !defined (GLIB_COMPILATION) 23#error "Only <glib.h> can be included directly." 24#endif 25 26#ifndef __G_UNICODE_H__ 27#define __G_UNICODE_H__ 28 29#include <glib/gerror.h> 30#include <glib/gtypes.h> 31 32G_BEGIN_DECLS 33 34typedef guint32 gunichar; 35typedef guint16 gunichar2; 36 37/* These are the possible character classifications. 38 * See http://www.unicode.org/Public/UNIDATA/UCD.html#General_Category_Values 39 */ 40typedef enum 41{ 42 G_UNICODE_CONTROL, 43 G_UNICODE_FORMAT, 44 G_UNICODE_UNASSIGNED, 45 G_UNICODE_PRIVATE_USE, 46 G_UNICODE_SURROGATE, 47 G_UNICODE_LOWERCASE_LETTER, 48 G_UNICODE_MODIFIER_LETTER, 49 G_UNICODE_OTHER_LETTER, 50 G_UNICODE_TITLECASE_LETTER, 51 G_UNICODE_UPPERCASE_LETTER, 52 G_UNICODE_COMBINING_MARK, 53 G_UNICODE_ENCLOSING_MARK, 54 G_UNICODE_NON_SPACING_MARK, 55 G_UNICODE_DECIMAL_NUMBER, 56 G_UNICODE_LETTER_NUMBER, 57 G_UNICODE_OTHER_NUMBER, 58 G_UNICODE_CONNECT_PUNCTUATION, 59 G_UNICODE_DASH_PUNCTUATION, 60 G_UNICODE_CLOSE_PUNCTUATION, 61 G_UNICODE_FINAL_PUNCTUATION, 62 G_UNICODE_INITIAL_PUNCTUATION, 63 G_UNICODE_OTHER_PUNCTUATION, 64 G_UNICODE_OPEN_PUNCTUATION, 65 G_UNICODE_CURRENCY_SYMBOL, 66 G_UNICODE_MODIFIER_SYMBOL, 67 G_UNICODE_MATH_SYMBOL, 68 G_UNICODE_OTHER_SYMBOL, 69 G_UNICODE_LINE_SEPARATOR, 70 G_UNICODE_PARAGRAPH_SEPARATOR, 71 G_UNICODE_SPACE_SEPARATOR 72} GUnicodeType; 73 74/* These are the possible line break classifications. 75 * Note that new types may be added in the future. 76 * Implementations may regard unknown values like G_UNICODE_BREAK_UNKNOWN 77 * See http://www.unicode.org/unicode/reports/tr14/ 78 */ 79typedef enum 80{ 81 G_UNICODE_BREAK_MANDATORY, 82 G_UNICODE_BREAK_CARRIAGE_RETURN, 83 G_UNICODE_BREAK_LINE_FEED, 84 G_UNICODE_BREAK_COMBINING_MARK, 85 G_UNICODE_BREAK_SURROGATE, 86 G_UNICODE_BREAK_ZERO_WIDTH_SPACE, 87 G_UNICODE_BREAK_INSEPARABLE, 88 G_UNICODE_BREAK_NON_BREAKING_GLUE, 89 G_UNICODE_BREAK_CONTINGENT, 90 G_UNICODE_BREAK_SPACE, 91 G_UNICODE_BREAK_AFTER, 92 G_UNICODE_BREAK_BEFORE, 93 G_UNICODE_BREAK_BEFORE_AND_AFTER, 94 G_UNICODE_BREAK_HYPHEN, 95 G_UNICODE_BREAK_NON_STARTER, 96 G_UNICODE_BREAK_OPEN_PUNCTUATION, 97 G_UNICODE_BREAK_CLOSE_PUNCTUATION, 98 G_UNICODE_BREAK_QUOTATION, 99 G_UNICODE_BREAK_EXCLAMATION, 100 G_UNICODE_BREAK_IDEOGRAPHIC, 101 G_UNICODE_BREAK_NUMERIC, 102 G_UNICODE_BREAK_INFIX_SEPARATOR, 103 G_UNICODE_BREAK_SYMBOL, 104 G_UNICODE_BREAK_ALPHABETIC, 105 G_UNICODE_BREAK_PREFIX, 106 G_UNICODE_BREAK_POSTFIX, 107 G_UNICODE_BREAK_COMPLEX_CONTEXT, 108 G_UNICODE_BREAK_AMBIGUOUS, 109 G_UNICODE_BREAK_UNKNOWN, 110 G_UNICODE_BREAK_NEXT_LINE, 111 G_UNICODE_BREAK_WORD_JOINER, 112 G_UNICODE_BREAK_HANGUL_L_JAMO, 113 G_UNICODE_BREAK_HANGUL_V_JAMO, 114 G_UNICODE_BREAK_HANGUL_T_JAMO, 115 G_UNICODE_BREAK_HANGUL_LV_SYLLABLE, 116 G_UNICODE_BREAK_HANGUL_LVT_SYLLABLE 117} GUnicodeBreakType; 118 119typedef enum 120{ /* ISO 15924 code */ 121 G_UNICODE_SCRIPT_INVALID_CODE = -1, 122 G_UNICODE_SCRIPT_COMMON = 0, /* Zyyy */ 123 G_UNICODE_SCRIPT_INHERITED, /* Qaai */ 124 G_UNICODE_SCRIPT_ARABIC, /* Arab */ 125 G_UNICODE_SCRIPT_ARMENIAN, /* Armn */ 126 G_UNICODE_SCRIPT_BENGALI, /* Beng */ 127 G_UNICODE_SCRIPT_BOPOMOFO, /* Bopo */ 128 G_UNICODE_SCRIPT_CHEROKEE, /* Cher */ 129 G_UNICODE_SCRIPT_COPTIC, /* Qaac */ 130 G_UNICODE_SCRIPT_CYRILLIC, /* Cyrl (Cyrs) */ 131 G_UNICODE_SCRIPT_DESERET, /* Dsrt */ 132 G_UNICODE_SCRIPT_DEVANAGARI, /* Deva */ 133 G_UNICODE_SCRIPT_ETHIOPIC, /* Ethi */ 134 G_UNICODE_SCRIPT_GEORGIAN, /* Geor (Geon, Geoa) */ 135 G_UNICODE_SCRIPT_GOTHIC, /* Goth */ 136 G_UNICODE_SCRIPT_GREEK, /* Grek */ 137 G_UNICODE_SCRIPT_GUJARATI, /* Gujr */ 138 G_UNICODE_SCRIPT_GURMUKHI, /* Guru */ 139 G_UNICODE_SCRIPT_HAN, /* Hani */ 140 G_UNICODE_SCRIPT_HANGUL, /* Hang */ 141 G_UNICODE_SCRIPT_HEBREW, /* Hebr */ 142 G_UNICODE_SCRIPT_HIRAGANA, /* Hira */ 143 G_UNICODE_SCRIPT_KANNADA, /* Knda */ 144 G_UNICODE_SCRIPT_KATAKANA, /* Kana */ 145 G_UNICODE_SCRIPT_KHMER, /* Khmr */ 146 G_UNICODE_SCRIPT_LAO, /* Laoo */ 147 G_UNICODE_SCRIPT_LATIN, /* Latn (Latf, Latg) */ 148 G_UNICODE_SCRIPT_MALAYALAM, /* Mlym */ 149 G_UNICODE_SCRIPT_MONGOLIAN, /* Mong */ 150 G_UNICODE_SCRIPT_MYANMAR, /* Mymr */ 151 G_UNICODE_SCRIPT_OGHAM, /* Ogam */ 152 G_UNICODE_SCRIPT_OLD_ITALIC, /* Ital */ 153 G_UNICODE_SCRIPT_ORIYA, /* Orya */ 154 G_UNICODE_SCRIPT_RUNIC, /* Runr */ 155 G_UNICODE_SCRIPT_SINHALA, /* Sinh */ 156 G_UNICODE_SCRIPT_SYRIAC, /* Syrc (Syrj, Syrn, Syre) */ 157 G_UNICODE_SCRIPT_TAMIL, /* Taml */ 158 G_UNICODE_SCRIPT_TELUGU, /* Telu */ 159 G_UNICODE_SCRIPT_THAANA, /* Thaa */ 160 G_UNICODE_SCRIPT_THAI, /* Thai */ 161 G_UNICODE_SCRIPT_TIBETAN, /* Tibt */ 162 G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL, /* Cans */ 163 G_UNICODE_SCRIPT_YI, /* Yiii */ 164 G_UNICODE_SCRIPT_TAGALOG, /* Tglg */ 165 G_UNICODE_SCRIPT_HANUNOO, /* Hano */ 166 G_UNICODE_SCRIPT_BUHID, /* Buhd */ 167 G_UNICODE_SCRIPT_TAGBANWA, /* Tagb */ 168 169 /* Unicode-4.0 additions */ 170 G_UNICODE_SCRIPT_BRAILLE, /* Brai */ 171 G_UNICODE_SCRIPT_CYPRIOT, /* Cprt */ 172 G_UNICODE_SCRIPT_LIMBU, /* Limb */ 173 G_UNICODE_SCRIPT_OSMANYA, /* Osma */ 174 G_UNICODE_SCRIPT_SHAVIAN, /* Shaw */ 175 G_UNICODE_SCRIPT_LINEAR_B, /* Linb */ 176 G_UNICODE_SCRIPT_TAI_LE, /* Tale */ 177 G_UNICODE_SCRIPT_UGARITIC, /* Ugar */ 178 179 /* Unicode-4.1 additions */ 180 G_UNICODE_SCRIPT_NEW_TAI_LUE, /* Talu */ 181 G_UNICODE_SCRIPT_BUGINESE, /* Bugi */ 182 G_UNICODE_SCRIPT_GLAGOLITIC, /* Glag */ 183 G_UNICODE_SCRIPT_TIFINAGH, /* Tfng */ 184 G_UNICODE_SCRIPT_SYLOTI_NAGRI, /* Sylo */ 185 G_UNICODE_SCRIPT_OLD_PERSIAN, /* Xpeo */ 186 G_UNICODE_SCRIPT_KHAROSHTHI, /* Khar */ 187 188 /* Unicode-5.0 additions */ 189 G_UNICODE_SCRIPT_UNKNOWN, /* Zzzz */ 190 G_UNICODE_SCRIPT_BALINESE, /* Bali */ 191 G_UNICODE_SCRIPT_CUNEIFORM, /* Xsux */ 192 G_UNICODE_SCRIPT_PHOENICIAN, /* Phnx */ 193 G_UNICODE_SCRIPT_PHAGS_PA, /* Phag */ 194 G_UNICODE_SCRIPT_NKO, /* Nkoo */ 195 196 /* Unicode-5.1 additions */ 197 G_UNICODE_SCRIPT_KAYAH_LI, /* Kali */ 198 G_UNICODE_SCRIPT_LEPCHA, /* Lepc */ 199 G_UNICODE_SCRIPT_REJANG, /* Rjng */ 200 G_UNICODE_SCRIPT_SUNDANESE, /* Sund */ 201 G_UNICODE_SCRIPT_SAURASHTRA, /* Saur */ 202 G_UNICODE_SCRIPT_CHAM, /* Cham */ 203 G_UNICODE_SCRIPT_OL_CHIKI, /* Olck */ 204 G_UNICODE_SCRIPT_VAI, /* Vaii */ 205 G_UNICODE_SCRIPT_CARIAN, /* Cari */ 206 G_UNICODE_SCRIPT_LYCIAN, /* Lyci */ 207 G_UNICODE_SCRIPT_LYDIAN /* Lydi */ 208} GUnicodeScript; 209 210/* Returns TRUE if current locale uses UTF-8 charset. If CHARSET is 211 * not null, sets *CHARSET to the name of the current locale's 212 * charset. This value is statically allocated, and should be copied 213 * in case the locale's charset will be changed later using setlocale() 214 * or in some other way. 215 */ 216gboolean g_get_charset (G_CONST_RETURN char **charset); 217 218/* These are all analogs of the <ctype.h> functions. 219 */ 220gboolean g_unichar_isalnum (gunichar c) G_GNUC_CONST; 221gboolean g_unichar_isalpha (gunichar c) G_GNUC_CONST; 222gboolean g_unichar_iscntrl (gunichar c) G_GNUC_CONST; 223gboolean g_unichar_isdigit (gunichar c) G_GNUC_CONST; 224gboolean g_unichar_isgraph (gunichar c) G_GNUC_CONST; 225gboolean g_unichar_islower (gunichar c) G_GNUC_CONST; 226gboolean g_unichar_isprint (gunichar c) G_GNUC_CONST; 227gboolean g_unichar_ispunct (gunichar c) G_GNUC_CONST; 228gboolean g_unichar_isspace (gunichar c) G_GNUC_CONST; 229gboolean g_unichar_isupper (gunichar c) G_GNUC_CONST; 230gboolean g_unichar_isxdigit (gunichar c) G_GNUC_CONST; 231gboolean g_unichar_istitle (gunichar c) G_GNUC_CONST; 232gboolean g_unichar_isdefined (gunichar c) G_GNUC_CONST; 233gboolean g_unichar_iswide (gunichar c) G_GNUC_CONST; 234gboolean g_unichar_iswide_cjk(gunichar c) G_GNUC_CONST; 235gboolean g_unichar_iszerowidth(gunichar c) G_GNUC_CONST; 236gboolean g_unichar_ismark (gunichar c) G_GNUC_CONST; 237 238/* More <ctype.h> functions. These convert between the three cases. 239 * See the Unicode book to understand title case. */ 240gunichar g_unichar_toupper (gunichar c) G_GNUC_CONST; 241gunichar g_unichar_tolower (gunichar c) G_GNUC_CONST; 242gunichar g_unichar_totitle (gunichar c) G_GNUC_CONST; 243 244/* If C is a digit (according to `g_unichar_isdigit'), then return its 245 numeric value. Otherwise return -1. */ 246gint g_unichar_digit_value (gunichar c) G_GNUC_CONST; 247 248gint g_unichar_xdigit_value (gunichar c) G_GNUC_CONST; 249 250/* Return the Unicode character type of a given character. */ 251GUnicodeType g_unichar_type (gunichar c) G_GNUC_CONST; 252 253/* Return the line break property for a given character */ 254GUnicodeBreakType g_unichar_break_type (gunichar c) G_GNUC_CONST; 255 256/* Returns the combining class for a given character */ 257gint g_unichar_combining_class (gunichar uc) G_GNUC_CONST; 258 259 260/* Compute canonical ordering of a string in-place. This rearranges 261 decomposed characters in the string according to their combining 262 classes. See the Unicode manual for more information. */ 263void g_unicode_canonical_ordering (gunichar *string, 264 gsize len); 265 266/* Compute canonical decomposition of a character. Returns g_malloc()d 267 string of Unicode characters. RESULT_LEN is set to the resulting 268 length of the string. */ 269gunichar *g_unicode_canonical_decomposition (gunichar ch, 270 gsize *result_len) G_GNUC_MALLOC; 271 272/* Array of skip-bytes-per-initial character. 273 */ 274GLIB_VAR const gchar * const g_utf8_skip; 275 276#define g_utf8_next_char(p) (char *)((p) + g_utf8_skip[*(const guchar *)(p)]) 277 278gunichar g_utf8_get_char (const gchar *p) G_GNUC_PURE; 279gunichar g_utf8_get_char_validated (const gchar *p, 280 gssize max_len) G_GNUC_PURE; 281 282gchar* g_utf8_offset_to_pointer (const gchar *str, 283 glong offset) G_GNUC_PURE; 284glong g_utf8_pointer_to_offset (const gchar *str, 285 const gchar *pos) G_GNUC_PURE; 286gchar* g_utf8_prev_char (const gchar *p) G_GNUC_PURE; 287gchar* g_utf8_find_next_char (const gchar *p, 288 const gchar *end) G_GNUC_PURE; 289gchar* g_utf8_find_prev_char (const gchar *str, 290 const gchar *p) G_GNUC_PURE; 291 292glong g_utf8_strlen (const gchar *p, 293 gssize max) G_GNUC_PURE; 294 295/* Copies n characters from src to dest */ 296gchar* g_utf8_strncpy (gchar *dest, 297 const gchar *src, 298 gsize n); 299 300/* Find the UTF-8 character corresponding to ch, in string p. These 301 functions are equivalants to strchr and strrchr */ 302gchar* g_utf8_strchr (const gchar *p, 303 gssize len, 304 gunichar c); 305gchar* g_utf8_strrchr (const gchar *p, 306 gssize len, 307 gunichar c); 308gchar* g_utf8_strreverse (const gchar *str, 309 gssize len); 310 311gunichar2 *g_utf8_to_utf16 (const gchar *str, 312 glong len, 313 glong *items_read, 314 glong *items_written, 315 GError **error) G_GNUC_MALLOC; 316gunichar * g_utf8_to_ucs4 (const gchar *str, 317 glong len, 318 glong *items_read, 319 glong *items_written, 320 GError **error) G_GNUC_MALLOC; 321gunichar * g_utf8_to_ucs4_fast (const gchar *str, 322 glong len, 323 glong *items_written) G_GNUC_MALLOC; 324gunichar * g_utf16_to_ucs4 (const gunichar2 *str, 325 glong len, 326 glong *items_read, 327 glong *items_written, 328 GError **error) G_GNUC_MALLOC; 329gchar* g_utf16_to_utf8 (const gunichar2 *str, 330 glong len, 331 glong *items_read, 332 glong *items_written, 333 GError **error) G_GNUC_MALLOC; 334gunichar2 *g_ucs4_to_utf16 (const gunichar *str, 335 glong len, 336 glong *items_read, 337 glong *items_written, 338 GError **error) G_GNUC_MALLOC; 339gchar* g_ucs4_to_utf8 (const gunichar *str, 340 glong len, 341 glong *items_read, 342 glong *items_written, 343 GError **error) G_GNUC_MALLOC; 344 345/* Convert a single character into UTF-8. outbuf must have at 346 * least 6 bytes of space. Returns the number of bytes in the 347 * result. 348 */ 349gint g_unichar_to_utf8 (gunichar c, 350 gchar *outbuf); 351 352/* Validate a UTF8 string, return TRUE if valid, put pointer to 353 * first invalid char in **end 354 */ 355 356gboolean g_utf8_validate (const gchar *str, 357 gssize max_len, 358 const gchar **end); 359 360/* Validate a Unicode character */ 361gboolean g_unichar_validate (gunichar ch) G_GNUC_CONST; 362 363gchar *g_utf8_strup (const gchar *str, 364 gssize len) G_GNUC_MALLOC; 365gchar *g_utf8_strdown (const gchar *str, 366 gssize len) G_GNUC_MALLOC; 367gchar *g_utf8_casefold (const gchar *str, 368 gssize len) G_GNUC_MALLOC; 369 370typedef enum { 371 G_NORMALIZE_DEFAULT, 372 G_NORMALIZE_NFD = G_NORMALIZE_DEFAULT, 373 G_NORMALIZE_DEFAULT_COMPOSE, 374 G_NORMALIZE_NFC = G_NORMALIZE_DEFAULT_COMPOSE, 375 G_NORMALIZE_ALL, 376 G_NORMALIZE_NFKD = G_NORMALIZE_ALL, 377 G_NORMALIZE_ALL_COMPOSE, 378 G_NORMALIZE_NFKC = G_NORMALIZE_ALL_COMPOSE 379} GNormalizeMode; 380 381gchar *g_utf8_normalize (const gchar *str, 382 gssize len, 383 GNormalizeMode mode) G_GNUC_MALLOC; 384 385gint g_utf8_collate (const gchar *str1, 386 const gchar *str2) G_GNUC_PURE; 387gchar *g_utf8_collate_key (const gchar *str, 388 gssize len) G_GNUC_MALLOC; 389gchar *g_utf8_collate_key_for_filename (const gchar *str, 390 gssize len) G_GNUC_MALLOC; 391 392gboolean g_unichar_get_mirror_char (gunichar ch, 393 gunichar *mirrored_ch); 394 395GUnicodeScript g_unichar_get_script (gunichar ch) G_GNUC_CONST; 396 397 398/* private */ 399 400gchar *_g_utf8_make_valid (const gchar *name); 401 402G_END_DECLS 403 404#endif /* __G_UNICODE_H__ */ 405