glib/gunicode.h

   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
  32 G_BEGIN_DECLS
  33
  34 typedef guint32 gunichar;
  35 typedef guint16 gunichar2;
  36
  37 /* These are the possible character classifications.
  38  * See http://www.unicode.org/Public/UNIDATA/UCD.html#General_Category_Values
  39  */
  40 typedef 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  */
  79 typedef 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
 119 typedef 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
 209   /* Unicode-5.2 additions */
 210   G_UNICODE_SCRIPT_AVESTAN,                /* Avestan */
 211   G_UNICODE_SCRIPT_BAMUM,                  /* Bamum */
 212   G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS,   /* Egyptian Hieroglyphs */
 213   G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC,       /* Imperial Aramaic */
 214   G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI,  /* Inscriptional Pahlavi */
 215   G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN, /* Inscriptional Parthian */
 216   G_UNICODE_SCRIPT_JAVANESE,               /* Javanese */
 217   G_UNICODE_SCRIPT_KAITHI,                 /* Kaithi */
 218   G_UNICODE_SCRIPT_LISU,                   /* Lisu */
 219   G_UNICODE_SCRIPT_MEETEI_MAYEK,           /* Meetei Mayek */
 220   G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN,      /* Old South Arabian */
 221   G_UNICODE_SCRIPT_OLD_TURKISH,            /* Old Turkish */
 222   G_UNICODE_SCRIPT_SAMARITAN,              /* Samaritan */
 223   G_UNICODE_SCRIPT_TAI_THAM,               /* Tai Tham */
 224   G_UNICODE_SCRIPT_TAI_VIET                /* Tai Viet */
 225 } GUnicodeScript;
 226
 227 /* Returns TRUE if current locale uses UTF-8 charset.  If CHARSET is
 228  * not null, sets *CHARSET to the name of the current locale's
 229  * charset.  This value is statically allocated, and should be copied
 230  * in case the locale's charset will be changed later using setlocale()
 231  * or in some other way.
 232  */
 233 gboolean g_get_charset (G_CONST_RETURN char **charset);
 234
 235 /* These are all analogs of the <ctype.h> functions.
 236  */
 237 gboolean g_unichar_isalnum   (gunichar c) G_GNUC_CONST;
 238 gboolean g_unichar_isalpha   (gunichar c) G_GNUC_CONST;
 239 gboolean g_unichar_iscntrl   (gunichar c) G_GNUC_CONST;
 240 gboolean g_unichar_isdigit   (gunichar c) G_GNUC_CONST;
 241 gboolean g_unichar_isgraph   (gunichar c) G_GNUC_CONST;
 242 gboolean g_unichar_islower   (gunichar c) G_GNUC_CONST;
 243 gboolean g_unichar_isprint   (gunichar c) G_GNUC_CONST;
 244 gboolean g_unichar_ispunct   (gunichar c) G_GNUC_CONST;
 245 gboolean g_unichar_isspace   (gunichar c) G_GNUC_CONST;
 246 gboolean g_unichar_isupper   (gunichar c) G_GNUC_CONST;
 247 gboolean g_unichar_isxdigit  (gunichar c) G_GNUC_CONST;
 248 gboolean g_unichar_istitle   (gunichar c) G_GNUC_CONST;
 249 gboolean g_unichar_isdefined (gunichar c) G_GNUC_CONST;
 250 gboolean g_unichar_iswide    (gunichar c) G_GNUC_CONST;
 251 gboolean g_unichar_iswide_cjk(gunichar c) G_GNUC_CONST;
 252 gboolean g_unichar_iszerowidth(gunichar c) G_GNUC_CONST;
 253 gboolean g_unichar_ismark    (gunichar c) G_GNUC_CONST;
 254
 255 /* More <ctype.h> functions.  These convert between the three cases.
 256  * See the Unicode book to understand title case.  */
 257 gunichar g_unichar_toupper (gunichar c) G_GNUC_CONST;
 258 gunichar g_unichar_tolower (gunichar c) G_GNUC_CONST;
 259 gunichar g_unichar_totitle (gunichar c) G_GNUC_CONST;
 260
 261 /* If C is a digit (according to `g_unichar_isdigit'), then return its
 262    numeric value.  Otherwise return -1.  */
 263 gint g_unichar_digit_value (gunichar c) G_GNUC_CONST;
 264
 265 gint g_unichar_xdigit_value (gunichar c) G_GNUC_CONST;
 266
 267 /* Return the Unicode character type of a given character.  */
 268 GUnicodeType g_unichar_type (gunichar c) G_GNUC_CONST;
 269
 270 /* Return the line break property for a given character */
 271 GUnicodeBreakType g_unichar_break_type (gunichar c) G_GNUC_CONST;
 272
 273 /* Returns the combining class for a given character */
 274 gint g_unichar_combining_class (gunichar uc) G_GNUC_CONST;
 275
 276
 277 /* Compute canonical ordering of a string in-place.  This rearranges
 278    decomposed characters in the string according to their combining
 279    classes.  See the Unicode manual for more information.  */
 280 void g_unicode_canonical_ordering (gunichar *string,
 281                                    gsize     len);
 282
 283 /* Compute canonical decomposition of a character.  Returns g_malloc()d
 284    string of Unicode characters.  RESULT_LEN is set to the resulting
 285    length of the string.  */
 286 gunichar *g_unicode_canonical_decomposition (gunichar  ch,
 287                                              gsize    *result_len) G_GNUC_MALLOC;
 288
 289 /* Array of skip-bytes-per-initial character.
 290  */
 291 GLIB_VAR const gchar * const g_utf8_skip;
 292
 293 #define g_utf8_next_char(p) (char *)((p) + g_utf8_skip[*(const guchar *)(p)])
 294
 295 gunichar g_utf8_get_char           (const gchar  *p) G_GNUC_PURE;
 296 gunichar g_utf8_get_char_validated (const  gchar *p,
 297                                     gssize        max_len) G_GNUC_PURE;
 298
 299 gchar*   g_utf8_offset_to_pointer (const gchar *str,
 300                                    glong        offset) G_GNUC_PURE;
 301 glong    g_utf8_pointer_to_offset (const gchar *str,
 302                                    const gchar *pos) G_GNUC_PURE;
 303 gchar*   g_utf8_prev_char         (const gchar *p) G_GNUC_PURE;
 304 gchar*   g_utf8_find_next_char    (const gchar *p,
 305                                    const gchar *end) G_GNUC_PURE;
 306 gchar*   g_utf8_find_prev_char    (const gchar *str,
 307                                    const gchar *p) G_GNUC_PURE;
 308
 309 glong g_utf8_strlen (const gchar *p,
 310                      gssize       max) G_GNUC_PURE;
 311
 312 /* Copies n characters from src to dest */
 313 gchar* g_utf8_strncpy (gchar       *dest,
 314                        const gchar *src,
 315                        gsize        n);
 316
 317 /* Find the UTF-8 character corresponding to ch, in string p. These
 318    functions are equivalants to strchr and strrchr */
 319 gchar* g_utf8_strchr  (const gchar *p,
 320                        gssize       len,
 321                        gunichar     c);
 322 gchar* g_utf8_strrchr (const gchar *p,
 323                        gssize       len,
 324                        gunichar     c);
 325 gchar* g_utf8_strreverse (const gchar *str,
 326                           gssize len);
 327
 328 gunichar2 *g_utf8_to_utf16     (const gchar      *str,
 329                                 glong             len,
 330                                 glong            *items_read,
 331                                 glong            *items_written,
 332                                 GError          **error) G_GNUC_MALLOC;
 333 gunichar * g_utf8_to_ucs4      (const gchar      *str,
 334                                 glong             len,
 335                                 glong            *items_read,
 336                                 glong            *items_written,
 337                                 GError          **error) G_GNUC_MALLOC;
 338 gunichar * g_utf8_to_ucs4_fast (const gchar      *str,
 339                                 glong             len,
 340                                 glong            *items_written) G_GNUC_MALLOC;
 341 gunichar * g_utf16_to_ucs4     (const gunichar2  *str,
 342                                 glong             len,
 343                                 glong            *items_read,
 344                                 glong            *items_written,
 345                                 GError          **error) G_GNUC_MALLOC;
 346 gchar*     g_utf16_to_utf8     (const gunichar2  *str,
 347                                 glong             len,
 348                                 glong            *items_read,
 349                                 glong            *items_written,
 350                                 GError          **error) G_GNUC_MALLOC;
 351 gunichar2 *g_ucs4_to_utf16     (const gunichar   *str,
 352                                 glong             len,
 353                                 glong            *items_read,
 354                                 glong            *items_written,
 355                                 GError          **error) G_GNUC_MALLOC;
 356 gchar*     g_ucs4_to_utf8      (const gunichar   *str,
 357                                 glong             len,
 358                                 glong            *items_read,
 359                                 glong            *items_written,
 360                                 GError          **error) G_GNUC_MALLOC;
 361
 362 /* Convert a single character into UTF-8. outbuf must have at
 363  * least 6 bytes of space. Returns the number of bytes in the
 364  * result.
 365  */
 366 gint      g_unichar_to_utf8 (gunichar    c,
 367                              gchar      *outbuf);
 368
 369 /* Validate a UTF8 string, return TRUE if valid, put pointer to
 370  * first invalid char in **end
 371  */
 372
 373 gboolean g_utf8_validate (const gchar  *str,
 374                           gssize        max_len,
 375                           const gchar **end);
 376
 377 /* Validate a Unicode character */
 378 gboolean g_unichar_validate (gunichar ch) G_GNUC_CONST;
 379
 380 gchar *g_utf8_strup   (const gchar *str,
 381                        gssize       len) G_GNUC_MALLOC;
 382 gchar *g_utf8_strdown (const gchar *str,
 383                        gssize       len) G_GNUC_MALLOC;
 384 gchar *g_utf8_casefold (const gchar *str,
 385                         gssize       len) G_GNUC_MALLOC;
 386
 387 typedef enum {
 388   G_NORMALIZE_DEFAULT,
 389   G_NORMALIZE_NFD = G_NORMALIZE_DEFAULT,
 390   G_NORMALIZE_DEFAULT_COMPOSE,
 391   G_NORMALIZE_NFC = G_NORMALIZE_DEFAULT_COMPOSE,
 392   G_NORMALIZE_ALL,
 393   G_NORMALIZE_NFKD = G_NORMALIZE_ALL,
 394   G_NORMALIZE_ALL_COMPOSE,
 395   G_NORMALIZE_NFKC = G_NORMALIZE_ALL_COMPOSE
 396 } GNormalizeMode;
 397
 398 gchar *g_utf8_normalize (const gchar   *str,
 399                          gssize         len,
 400                          GNormalizeMode mode) G_GNUC_MALLOC;
 401
 402 gint   g_utf8_collate     (const gchar *str1,
 403                            const gchar *str2) G_GNUC_PURE;
 404 gchar *g_utf8_collate_key (const gchar *str,
 405                            gssize       len) G_GNUC_MALLOC;
 406 gchar *g_utf8_collate_key_for_filename (const gchar *str,
 407                                         gssize       len) G_GNUC_MALLOC;
 408
 409 gboolean g_unichar_get_mirror_char (gunichar ch,
 410                                     gunichar *mirrored_ch);
 411
 412 GUnicodeScript g_unichar_get_script (gunichar ch) G_GNUC_CONST;
 413
 414
 415 /* private */
 416
 417 gchar *_g_utf8_make_valid (const gchar *name);
 418
 419 G_END_DECLS
 420
 421 #endif /* __G_UNICODE_H__ */