mono/eglib/gunicode.c

   1 /*
   2  * gunicode.c: Some Unicode routines
   3  *
   4  * Author:
   5  *   Miguel de Icaza (miguel@novell.com)
   6  *
   7  * (C) 2006 Novell, Inc.
   8  *
   9  * utf8 validation code came from:
  10  *      libxml2-2.6.26 licensed under the MIT X11 license
  11  *
  12  * Authors credit in libxml's string.c:
  13  *   William Brack <wbrack@mmm.com.hk>
  14  *   daniel@veillard.com
  15  *
  16  * Permission is hereby granted, free of charge, to any person obtaining
  17  * a copy of this software and associated documentation files (the
  18  * "Software"), to deal in the Software without restriction, including
  19  * without limitation the rights to use, copy, modify, merge, publish,
  20  * distribute, sublicense, and/or sell copies of the Software, and to
  21  * permit persons to whom the Software is furnished to do so, subject to
  22  * the following conditions:
  23  *
  24  * The above copyright notice and this permission notice shall be
  25  * included in all copies or substantial portions of the Software.
  26  *
  27  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
  28  * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
  29  * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
  30  * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
  31  * LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
  32  * OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
  33  * WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
  34  *
  35  */
  36 #include <config.h>
  37 #include <stdio.h>
  38 #include <glib.h>
  39 #include <unicode-data.h>
  40 #include <errno.h>
  41
  42 #ifndef G_OS_WIN32
  43 #    ifdef HAVE_LOCALCHARSET_H
  44 #       include <localcharset.h>
  45 #    endif
  46 #endif
  47
  48 const char *my_charset;
  49
  50 /*
  51  * Character set conversion
  52  */
  53
  54 GUnicodeType
  55 g_unichar_type (gunichar c)
  56 {
  57         int i;
  58
  59         guint16 cp = (guint16) c;
  60         for (i = 0; i < unicode_category_ranges_count; i++) {
  61                 if (cp < unicode_category_ranges [i].start)
  62                         continue;
  63                 if (unicode_category_ranges [i].end <= cp)
  64                         continue;
  65                 return unicode_category [i] [cp - unicode_category_ranges [i].start];
  66         }
  67
  68         /*
  69         // 3400-4DB5: OtherLetter
  70         // 4E00-9FC3: OtherLetter
  71         // AC00-D7A3: OtherLetter
  72         // D800-DFFF: OtherSurrogate
  73         // E000-F8FF: OtherPrivateUse
  74         // 20000-2A6D6 OtherLetter
  75         // F0000-FFFFD OtherPrivateUse
  76         // 100000-10FFFD OtherPrivateUse
  77         */
  78         if (0x3400 <= cp && cp < 0x4DB5)
  79                 return G_UNICODE_OTHER_LETTER;
  80         if (0x4E00 <= cp && cp < 0x9FC3)
  81                 return G_UNICODE_OTHER_LETTER;
  82         if (0xAC00<= cp && cp < 0xD7A3)
  83                 return G_UNICODE_OTHER_LETTER;
  84         if (0xD800 <= cp && cp < 0xDFFF)
  85                 return G_UNICODE_SURROGATE;
  86         if (0xE000 <= cp && cp < 0xF8FF)
  87                 return G_UNICODE_PRIVATE_USE;
  88         /* since the argument is UTF-16, we cannot check beyond FFFF */
  89
  90         /* It should match any of above */
  91         return 0;
  92 }
  93
  94 GUnicodeBreakType
  95 g_unichar_break_type (gunichar c)
  96 {
  97         // MOONLIGHT_FIXME
  98         return G_UNICODE_BREAK_UNKNOWN;
  99 }
 100
 101 gunichar
 102 g_unichar_case (gunichar c, gboolean upper)
 103 {
 104         gint8 i, i2;
 105         guint32 cp = (guint32) c, v;
 106
 107         for (i = 0; i < simple_case_map_ranges_count; i++) {
 108                 if (cp < simple_case_map_ranges [i].start)
 109                         return c;
 110                 if (simple_case_map_ranges [i].end <= cp)
 111                         continue;
 112                 if (c < 0x10000) {
 113                         const guint16 *tab = upper ? simple_upper_case_mapping_lowarea [i] : simple_lower_case_mapping_lowarea [i];
 114                         v = tab [cp - simple_case_map_ranges [i].start];
 115                 } else {
 116                         const guint32 *tab;
 117                         i2 = (gint8)(i - (upper ? simple_upper_case_mapping_lowarea_table_count : simple_lower_case_mapping_lowarea_table_count));
 118                         tab = upper ? simple_upper_case_mapping_higharea [i2] : simple_lower_case_mapping_higharea [i2];
 119                         v = tab [cp - simple_case_map_ranges [i].start];
 120                 }
 121                 return v != 0 ? (gunichar) v : c;
 122         }
 123         return c;
 124 }
 125
 126 gunichar
 127 g_unichar_toupper (gunichar c)
 128 {
 129         return g_unichar_case (c, TRUE);
 130 }
 131
 132 gunichar
 133 g_unichar_tolower (gunichar c)
 134 {
 135         return g_unichar_case (c, FALSE);
 136 }
 137
 138 gunichar
 139 g_unichar_totitle (gunichar c)
 140 {
 141         guint8 i;
 142         guint32 cp;
 143
 144         cp = (guint32) c;
 145         for (i = 0; i < simple_titlecase_mapping_count; i++) {
 146                 if (simple_titlecase_mapping [i].codepoint == cp)
 147                         return simple_titlecase_mapping [i].title;
 148                 if (simple_titlecase_mapping [i].codepoint > cp)
 149                         /* it is ordered, hence no more match */
 150                         break;
 151         }
 152         return g_unichar_toupper (c);
 153 }
 154
 155 gboolean
 156 g_unichar_isxdigit (gunichar c)
 157 {
 158         return (g_unichar_xdigit_value (c) != -1);
 159
 160 }
 161
 162 gint
 163 g_unichar_xdigit_value (gunichar c)
 164 {
 165         if (c >= 0x30 && c <= 0x39) /*0-9*/
 166                 return (c - 0x30);
 167         if (c >= 0x41 && c <= 0x46) /*A-F*/
 168                 return (c - 0x37);
 169         if (c >= 0x61 && c <= 0x66) /*a-f*/
 170                 return (c - 0x57);
 171         return -1;
 172 }
 173
 174 gboolean
 175 g_unichar_isspace (gunichar c)
 176 {
 177         GUnicodeType type = g_unichar_type (c);
 178         if (type == G_UNICODE_LINE_SEPARATOR ||
 179             type == G_UNICODE_PARAGRAPH_SEPARATOR ||
 180             type == G_UNICODE_SPACE_SEPARATOR)
 181                 return TRUE;
 182
 183         return FALSE;
 184 }
 185
 186
 187 /*
 188  * This is broken, and assumes an UTF8 system, but will do for eglib's first user
 189  */
 190 gchar *
 191 g_filename_from_utf8 (const gchar *utf8string, gssize len, gsize *bytes_read, gsize *bytes_written, GError **error)
 192 {
 193         char *res;
 194
 195         if (len == -1)
 196                 len = strlen (utf8string);
 197
 198         res = g_malloc (len + 1);
 199         g_strlcpy (res, utf8string, len + 1);
 200         return res;
 201 }
 202
 203 #ifndef G_OS_WIN32
 204 static gboolean is_utf8;
 205
 206 gboolean
 207 g_get_charset (G_CONST_RETURN char **charset)
 208 {
 209         if (my_charset == NULL) {
 210                 /* These shouldn't be heap allocated */
 211 #if defined(HAVE_LOCALCHARSET_H)
 212                 my_charset = locale_charset ();
 213 #else
 214                 my_charset = "UTF-8";
 215 #endif
 216                 is_utf8 = strcmp (my_charset, "UTF-8") == 0;
 217         }
 218
 219         if (charset != NULL)
 220                 *charset = my_charset;
 221
 222         return is_utf8;
 223 }
 224 #endif /* G_OS_WIN32 */
 225
 226 gchar *
 227 g_locale_to_utf8 (const gchar *opsysstring, gssize len, gsize *bytes_read, gsize *bytes_written, GError **error)
 228 {
 229         g_get_charset (NULL);
 230
 231         return g_convert (opsysstring, len, "UTF-8", my_charset, bytes_read, bytes_written, error);
 232 }
 233
 234 gchar *
 235 g_locale_from_utf8 (const gchar *utf8string, gssize len, gsize *bytes_read, gsize *bytes_written, GError **error)
 236 {
 237         g_get_charset (NULL);
 238
 239         return g_convert (utf8string, len, my_charset, "UTF-8", bytes_read, bytes_written, error);
 240 }