gunicode.h

   1 /* gunicode.h - Unicode manipulation functions
   2  *
   3  *  Copyright (C) 1999, 2000 Tom Tromey
   4  *  Copyright 2000 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 #ifndef __G_UNICODE_H__
  23 #define __G_UNICODE_H__
  24
  25 #include <stddef.h>      /* For size_t */
  26 #include <gtypes.h>
  27
  28 G_BEGIN_DECLS
  29
  30 typedef guint32 gunichar;
  31 typedef guint16 gunichar2;
  32
  33 /* These are the possible character classifications.
  34  * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html
  35  */
  36 typedef enum
  37 {
  38   G_UNICODE_CONTROL,
  39   G_UNICODE_FORMAT,
  40   G_UNICODE_UNASSIGNED,
  41   G_UNICODE_PRIVATE_USE,
  42   G_UNICODE_SURROGATE,
  43   G_UNICODE_LOWERCASE_LETTER,
  44   G_UNICODE_MODIFIER_LETTER,
  45   G_UNICODE_OTHER_LETTER,
  46   G_UNICODE_TITLECASE_LETTER,
  47   G_UNICODE_UPPERCASE_LETTER,
  48   G_UNICODE_COMBINING_MARK,
  49   G_UNICODE_ENCLOSING_MARK,
  50   G_UNICODE_NON_SPACING_MARK,
  51   G_UNICODE_DECIMAL_NUMBER,
  52   G_UNICODE_LETTER_NUMBER,
  53   G_UNICODE_OTHER_NUMBER,
  54   G_UNICODE_CONNECT_PUNCTUATION,
  55   G_UNICODE_DASH_PUNCTUATION,
  56   G_UNICODE_CLOSE_PUNCTUATION,
  57   G_UNICODE_FINAL_PUNCTUATION,
  58   G_UNICODE_INITIAL_PUNCTUATION,
  59   G_UNICODE_OTHER_PUNCTUATION,
  60   G_UNICODE_OPEN_PUNCTUATION,
  61   G_UNICODE_CURRENCY_SYMBOL,
  62   G_UNICODE_MODIFIER_SYMBOL,
  63   G_UNICODE_MATH_SYMBOL,
  64   G_UNICODE_OTHER_SYMBOL,
  65   G_UNICODE_LINE_SEPARATOR,
  66   G_UNICODE_PARAGRAPH_SEPARATOR,
  67   G_UNICODE_SPACE_SEPARATOR
  68 } GUnicodeType;
  69
  70 /* These are the possible line break classifications.
  71  * See http://www.unicode.org/unicode/reports/tr14/
  72  */
  73 typedef enum
  74 {
  75   G_UNICODE_BREAK_MANDATORY,
  76   G_UNICODE_BREAK_CARRIAGE_RETURN,
  77   G_UNICODE_BREAK_LINE_FEED,
  78   G_UNICODE_BREAK_COMBINING_MARK,
  79   G_UNICODE_BREAK_SURROGATE,
  80   G_UNICODE_BREAK_ZERO_WIDTH_SPACE,
  81   G_UNICODE_BREAK_INSEPARABLE,
  82   G_UNICODE_BREAK_NON_BREAKING_GLUE,
  83   G_UNICODE_BREAK_CONTINGENT,
  84   G_UNICODE_BREAK_SPACE,
  85   G_UNICODE_BREAK_AFTER,
  86   G_UNICODE_BREAK_BEFORE,
  87   G_UNICODE_BREAK_BEFORE_AND_AFTER,
  88   G_UNICODE_BREAK_HYPHEN,
  89   G_UNICODE_BREAK_NON_STARTER,
  90   G_UNICODE_BREAK_OPEN_PUNCTUATION,
  91   G_UNICODE_BREAK_CLOSE_PUNCTUATION,
  92   G_UNICODE_BREAK_QUOTATION,
  93   G_UNICODE_BREAK_EXCLAMATION,
  94   G_UNICODE_BREAK_IDEOGRAPHIC,
  95   G_UNICODE_BREAK_NUMERIC,
  96   G_UNICODE_BREAK_INFIX_SEPARATOR,
  97   G_UNICODE_BREAK_SYMBOL,
  98   G_UNICODE_BREAK_ALPHABETIC,
  99   G_UNICODE_BREAK_PREFIX,
 100   G_UNICODE_BREAK_POSTFIX,
 101   G_UNICODE_BREAK_COMPLEX_CONTEXT,
 102   G_UNICODE_BREAK_AMBIGUOUS,
 103   G_UNICODE_BREAK_UNKNOWN
 104 } GUnicodeBreakType;
 105
 106 /* Returns TRUE if current locale uses UTF-8 charset.  If CHARSET is
 107  * not null, sets *CHARSET to the name of the current locale's
 108  * charset.  This value is statically allocated, and should be copied
 109  * in case the locale's charset will be changed later using setlocale()
 110  * or in some other way.
 111  */
 112 gboolean g_get_charset (char **charset);
 113
 114 /* These are all analogs of the <ctype.h> functions.
 115  */
 116 gboolean g_unichar_isalnum   (gunichar c) G_GNUC_CONST;
 117 gboolean g_unichar_isalpha   (gunichar c) G_GNUC_CONST;
 118 gboolean g_unichar_iscntrl   (gunichar c) G_GNUC_CONST;
 119 gboolean g_unichar_isdigit   (gunichar c) G_GNUC_CONST;
 120 gboolean g_unichar_isgraph   (gunichar c) G_GNUC_CONST;
 121 gboolean g_unichar_islower   (gunichar c) G_GNUC_CONST;
 122 gboolean g_unichar_isprint   (gunichar c) G_GNUC_CONST;
 123 gboolean g_unichar_ispunct   (gunichar c) G_GNUC_CONST;
 124 gboolean g_unichar_isspace   (gunichar c) G_GNUC_CONST;
 125 gboolean g_unichar_isupper   (gunichar c) G_GNUC_CONST;
 126 gboolean g_unichar_isxdigit  (gunichar c) G_GNUC_CONST;
 127 gboolean g_unichar_istitle   (gunichar c) G_GNUC_CONST;
 128 gboolean g_unichar_isdefined (gunichar c) G_GNUC_CONST;
 129 gboolean g_unichar_iswide    (gunichar c) G_GNUC_CONST;
 130
 131 /* More <ctype.h> functions.  These convert between the three cases.
 132  * See the Unicode book to understand title case.  */
 133 gunichar g_unichar_toupper (gunichar c) G_GNUC_CONST;
 134 gunichar g_unichar_tolower (gunichar c) G_GNUC_CONST;
 135 gunichar g_unichar_totitle (gunichar c) G_GNUC_CONST;
 136
 137 /* If C is a digit (according to `g_unichar_isdigit'), then return its
 138    numeric value.  Otherwise return -1.  */
 139 gint g_unichar_digit_value (gunichar c) G_GNUC_CONST;
 140
 141 gint g_unichar_xdigit_value (gunichar c) G_GNUC_CONST;
 142
 143 /* Return the Unicode character type of a given character.  */
 144 GUnicodeType g_unichar_type (gunichar c) G_GNUC_CONST;
 145
 146 /* Return the line break property for a given character */
 147 GUnicodeBreakType g_unichar_break_type (gunichar c) G_GNUC_CONST;
 148
 149
 150 /* Compute canonical ordering of a string in-place.  This rearranges
 151    decomposed characters in the string according to their combining
 152    classes.  See the Unicode manual for more information.  */
 153 void g_unicode_canonical_ordering (gunichar *string,
 154                                    size_t   len);
 155
 156 /* Compute canonical decomposition of a character.  Returns g_malloc()d
 157    string of Unicode characters.  RESULT_LEN is set to the resulting
 158    length of the string.  */
 159 gunichar *g_unicode_canonical_decomposition (gunichar  ch,
 160                                              size_t   *result_len);
 161
 162 /* Array of skip-bytes-per-initial character.
 163  * We prefix variable declarations so they can
 164  * properly get exported in windows dlls.
 165  */
 166 #ifndef GLIB_VAR
 167 #  ifdef G_OS_WIN32
 168 #    ifdef GLIB_COMPILATION
 169 #      define GLIB_VAR __declspec(dllexport)
 170 #    else /* !GLIB_COMPILATION */
 171 #      define GLIB_VAR extern __declspec(dllimport)
 172 #    endif /* !GLIB_COMPILATION */
 173 #  else /* !G_OS_WIN32 */
 174 #    define GLIB_VAR extern
 175 #  endif /* !G_OS_WIN32 */
 176 #endif /* !GLIB_VAR */
 177
 178 GLIB_VAR char g_utf8_skip[256];
 179
 180 #define g_utf8_next_char(p) (char *)((p) + g_utf8_skip[*(guchar *)(p)])
 181
 182 gunichar g_utf8_get_char          (const gchar *p);
 183 gchar *  g_utf8_offset_to_pointer  (const gchar *str,
 184                                     gint         offset);
 185 gint     g_utf8_pointer_to_offset (const gchar *str,
 186                                    const gchar *pos);
 187 gchar *  g_utf8_prev_char         (const gchar *p);
 188 gchar *  g_utf8_find_next_char    (const gchar *p,
 189                                    const gchar *end);
 190 gchar *  g_utf8_find_prev_char    (const gchar *str,
 191                                    const gchar *p);
 192
 193 gint g_utf8_strlen (const gchar *p,
 194                     gint         max);
 195
 196 /* Copies n characters from src to dest */
 197 gchar *g_utf8_strncpy (gchar       *dest,
 198                        const gchar *src,
 199                        size_t       n);
 200
 201 /* Find the UTF-8 character corresponding to ch, in string p. These
 202    functions are equivalants to strchr and strrchr */
 203
 204 gchar *g_utf8_strchr  (const gchar *p,
 205                        gunichar     c);
 206 gchar *g_utf8_strrchr (const gchar *p,
 207                        gunichar     c);
 208
 209 gunichar2 *g_utf8_to_utf16 (const gchar     *str,
 210                             gint             len);
 211 gunichar * g_utf8_to_ucs4  (const gchar     *str,
 212                             gint             len);
 213 gunichar * g_utf16_to_ucs4 (const gunichar2 *str,
 214                             gint             len);
 215 gchar *    g_utf16_to_utf8 (const gunichar2 *str,
 216                             gint             len);
 217 gunichar * g_ucs4_to_utf16 (const gunichar  *str,
 218                             gint             len);
 219 gchar *    g_ucs4_to_utf8  (const gunichar  *str,
 220                             gint             len);
 221
 222 /* Convert a single character into UTF-8. outbuf must have at
 223  * least 6 bytes of space. Returns the number of bytes in the
 224  * result.
 225  */
 226 gint      g_unichar_to_utf8 (gunichar    c,
 227                              char       *outbuf);
 228
 229 /* Validate a UTF8 string, return TRUE if valid, put pointer to
 230  * first invalid char in **end
 231  */
 232
 233 gboolean g_utf8_validate (const gchar  *str,
 234                           gint          max_len,
 235                           const gchar **end);
 236
 237 G_END_DECLS
 238
 239 #endif /* __G_UNICODE_H__ */