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 Library 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  * Library General Public License for more details.
  15  *
  16  * You should have received a copy of the GNU Library 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 __GUNICODE_H__
  23 #define __GUNICODE_H__
  24
  25 #include <stdlib.h>      /* For size_t */
  26
  27 #ifdef __cplusplus
  28 extern "C"
  29 {
  30 #endif
  31
  32 typedef guint32 gunichar;
  33 typedef guint16 gunichar2;
  34
  35 /* These are the possible character classifications.  */
  36 typedef enum {
  37   G_UNICODE_CONTROL,
  38   G_UNICODE_FORMAT,
  39   G_UNICODE_UNASSIGNED,
  40   G_UNICODE_PRIVATE_USE,
  41   G_UNICODE_SURROGATE,
  42   G_UNICODE_LOWERCASE_LETTER,
  43   G_UNICODE_MODIFIER_LETTER,
  44   G_UNICODE_OTHER_LETTER,
  45   G_UNICODE_TITLECASE_LETTER,
  46   G_UNICODE_UPPERCASE_LETTER,
  47   G_UNICODE_COMBINING_MARK,
  48   G_UNICODE_ENCLOSING_MARK,
  49   G_UNICODE_NON_SPACING_MARK,
  50   G_UNICODE_DECIMAL_NUMBER,
  51   G_UNICODE_LETTER_NUMBER,
  52   G_UNICODE_OTHER_NUMBER,
  53   G_UNICODE_CONNECT_PUNCTUATION,
  54   G_UNICODE_DASH_PUNCTUATION,
  55   G_UNICODE_CLOSE_PUNCTUATION,
  56   G_UNICODE_FINAL_PUNCTUATION,
  57   G_UNICODE_INITIAL_PUNCTUATION,
  58   G_UNICODE_OTHER_PUNCTUATION,
  59   G_UNICODE_OPEN_PUNCTUATION,
  60   G_UNICODE_CURRENCY_SYMBOL,
  61   G_UNICODE_MODIFIER_SYMBOL,
  62   G_UNICODE_MATH_SYMBOL,
  63   G_UNICODE_OTHER_SYMBOL,
  64   G_UNICODE_LINE_SEPARATOR,
  65   G_UNICODE_PARAGRAPH_SEPARATOR,
  66   G_UNICODE_SPACE_SEPARATOR
  67 } GUnicodeType;
  68
  69 /* Returns TRUE if current locale uses UTF-8 charset.  If CHARSET is
  70  * not null, sets *CHARSET to the name of the current locale's
  71  * charset.  This value is statically allocated.
  72  */
  73 gboolean g_get_charset (char **charset);
  74
  75 /* These are all analogs of the <ctype.h> functions.
  76  */
  77 gboolean g_unichar_isalnum   (gunichar c);
  78 gboolean g_unichar_isalpha   (gunichar c);
  79 gboolean g_unichar_iscntrl   (gunichar c);
  80 gboolean g_unicphar_isdigit   (gunichar c);
  81 gboolean g_unichar_isgraph   (gunichar c);
  82 gboolean g_unichar_islower   (gunichar c);
  83 gboolean g_unichar_isprint   (gunichar c);
  84 gboolean g_unichar_ispunct   (gunichar c);
  85 gboolean g_unichar_isspace   (gunichar c);
  86 gboolean g_unichar_isupper   (gunichar c);
  87 gboolean g_unichar_isxdigit  (gunichar c);
  88 gboolean g_unichar_istitle   (gunichar c);
  89 gboolean g_unichar_isdefined (gunichar c);
  90 gboolean g_unichar_iswide    (gunichar c);
  91
  92 /* More <ctype.h> functions.  These convert between the three cases.
  93  * See the Unicode book to understand title case.  */
  94 gunichar g_unichar_toupper (gunichar c);
  95 gunichar g_unichar_tolower (gunichar c);
  96 gunichar g_unichar_totitle (gunichar c);
  97
  98 /* If C is a digit (according to `g_unichar_isdigit'), then return its
  99    numeric value.  Otherwise return -1.  */
 100 gint g_unichar_digit_value (gunichar c);
 101
 102 gint g_unichar_xdigit_value (gunichar c);
 103
 104 /* Return the Unicode character type of a given character.  */
 105 GUnicodeType g_unichar_type (gunichar c);
 106
 107
 108
 109 /* Compute canonical ordering of a string in-place.  This rearranges
 110    decomposed characters in the string according to their combining
 111    classes.  See the Unicode manual for more information.  */
 112 void g_unicode_canonical_ordering (gunichar *string,
 113                                    size_t   len);
 114
 115 /* Compute canonical decomposition of a character.  Returns g_malloc()d
 116    string of Unicode characters.  RESULT_LEN is set to the resulting
 117    length of the string.  */
 118 gunichar *g_unicode_canonical_decomposition (gunichar  ch,
 119                                              size_t   *result_len);
 120
 121 /* Array of skip-bytes-per-initial character
 122  */
 123 extern char g_utf8_skip[256];
 124
 125 #define g_utf8_next_char(p) (char *)((p) + g_utf8_skip[*(guchar *)(p)])
 126
 127 gunichar g_utf8_get_char          (const gchar *p);
 128 gchar *  g_utf8_offset_to_pointer  (const gchar *str,
 129                                     gint         offset);
 130 gint     g_utf8_pointer_to_offset (const gchar *str,
 131                                    const gchar *pos);
 132 gchar *  g_utf8_prev_char         (const gchar *p);
 133 gchar *  g_utf8_find_next_char    (const gchar *p,
 134                                    const gchar *bound);
 135 gchar *  g_utf8_find_prev_char    (const gchar *str,
 136                                    const gchar *p);
 137
 138 gint g_utf8_strlen (const gchar *p,
 139                     gint         max);
 140
 141 /* Copies n characters from src to dest */
 142 gchar *g_utf8_strncpy (gchar       *dest,
 143                        const gchar *src,
 144                        size_t       n);
 145
 146 /* Find the UTF-8 character corresponding to ch, in string p. These
 147    functions are equivalants to strchr and strrchr */
 148
 149 gchar *g_utf8_strchr  (const gchar *p,
 150                        gunichar     ch);
 151 gchar *g_utf8_strrchr (const gchar *p,
 152                        gunichar     ch);
 153
 154 gunichar2 *g_utf8_to_utf16 (const gchar     *str,
 155                             gint             len);
 156 gunichar * g_utf8_to_ucs4  (const gchar     *str,
 157                             gint             len);
 158 gunichar * g_utf16_to_ucs4 (const gunichar2 *str,
 159                             gint             len);
 160 gchar *    g_utf16_to_utf8 (const gunichar2 *str,
 161                             gint             len);
 162 gunichar * g_ucs4_to_utf16 (const gunichar  *str,
 163                             gint             len);
 164 gchar *    g_ucs4_to_utf8  (const gunichar  *str,
 165                             gint             len);
 166
 167 /* Convert a single character into UTF-8. outbuf must have at
 168  * least 6 bytes of space. Returns the number of bytes in the
 169  * result.
 170  */
 171 gint      g_unichar_to_utf8 (gunichar    c,
 172                              char       *outbuf);
 173
 174 #ifdef __cplusplus
 175 }
 176 #endif
 177
 178 #endif /* GUNICODE_H */