gunicode.h

00001 /* gunicode.h - Unicode manipulation functions
00002  *
00003  *  Copyright (C) 1999, 2000 Tom Tromey
00004  *  Copyright 2000, 2005 Red Hat, Inc.
00005  * Portions copyright (c) 2006 Nokia Corporation.  All rights reserved.
00006  *
00007  * The Gnome Library is free software; you can redistribute it and/or
00008  * modify it under the terms of the GNU Lesser General Public License as
00009  * published by the Free Software Foundation; either version 2 of the
00010  * License, or (at your option) any later version.
00011  *
00012  * The Gnome Library is distributed in the hope that it will be useful,
00013  * but WITHOUT ANY WARRANTY; without even the implied warranty of
00014  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
00015  * Lesser General Public License for more details.
00016  *
00017  * You should have received a copy of the GNU Lesser General Public
00018  * License along with the Gnome Library; see the file COPYING.LIB.  If not,
00019  * write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
00020  *   Boston, MA 02111-1307, USA.
00021  */
00022 
00023 #ifndef __G_UNICODE_H__
00024 #define __G_UNICODE_H__
00025 
00026 #include <_ansi.h>
00027 #include <glib/gerror.h>
00028 #include <glib/gtypes.h>
00029 
00030 G_BEGIN_DECLS
00031 
00032 typedef guint32 gunichar;
00033 typedef guint16 gunichar2;
00034 
00035 /* These are the possible character classifications.
00036  * See http://www.unicode.org/Public/UNIDATA/UCD.html#General_Category_Values
00037  */
00038 typedef enum
00039 {
00040   G_UNICODE_CONTROL,
00041   G_UNICODE_FORMAT,
00042   G_UNICODE_UNASSIGNED,
00043   G_UNICODE_PRIVATE_USE,
00044   G_UNICODE_SURROGATE,
00045   G_UNICODE_LOWERCASE_LETTER,
00046   G_UNICODE_MODIFIER_LETTER,
00047   G_UNICODE_OTHER_LETTER,
00048   G_UNICODE_TITLECASE_LETTER,
00049   G_UNICODE_UPPERCASE_LETTER,
00050   G_UNICODE_COMBINING_MARK,
00051   G_UNICODE_ENCLOSING_MARK,
00052   G_UNICODE_NON_SPACING_MARK,
00053   G_UNICODE_DECIMAL_NUMBER,
00054   G_UNICODE_LETTER_NUMBER,
00055   G_UNICODE_OTHER_NUMBER,
00056   G_UNICODE_CONNECT_PUNCTUATION,
00057   G_UNICODE_DASH_PUNCTUATION,
00058   G_UNICODE_CLOSE_PUNCTUATION,
00059   G_UNICODE_FINAL_PUNCTUATION,
00060   G_UNICODE_INITIAL_PUNCTUATION,
00061   G_UNICODE_OTHER_PUNCTUATION,
00062   G_UNICODE_OPEN_PUNCTUATION,
00063   G_UNICODE_CURRENCY_SYMBOL,
00064   G_UNICODE_MODIFIER_SYMBOL,
00065   G_UNICODE_MATH_SYMBOL,
00066   G_UNICODE_OTHER_SYMBOL,
00067   G_UNICODE_LINE_SEPARATOR,
00068   G_UNICODE_PARAGRAPH_SEPARATOR,
00069   G_UNICODE_SPACE_SEPARATOR
00070 } GUnicodeType;
00071 
00072 /* These are the possible line break classifications.
00073  * Note that new types may be added in the future.
00074  * Implementations may regard unknown values like G_UNICODE_BREAK_UNKNOWN
00075  * See http://www.unicode.org/unicode/reports/tr14/
00076  */
00077 typedef enum
00078 {
00079   G_UNICODE_BREAK_MANDATORY,
00080   G_UNICODE_BREAK_CARRIAGE_RETURN,
00081   G_UNICODE_BREAK_LINE_FEED,
00082   G_UNICODE_BREAK_COMBINING_MARK,
00083   G_UNICODE_BREAK_SURROGATE,
00084   G_UNICODE_BREAK_ZERO_WIDTH_SPACE,
00085   G_UNICODE_BREAK_INSEPARABLE,
00086   G_UNICODE_BREAK_NON_BREAKING_GLUE,
00087   G_UNICODE_BREAK_CONTINGENT,
00088   G_UNICODE_BREAK_SPACE,
00089   G_UNICODE_BREAK_AFTER,
00090   G_UNICODE_BREAK_BEFORE,
00091   G_UNICODE_BREAK_BEFORE_AND_AFTER,
00092   G_UNICODE_BREAK_HYPHEN,
00093   G_UNICODE_BREAK_NON_STARTER,
00094   G_UNICODE_BREAK_OPEN_PUNCTUATION,
00095   G_UNICODE_BREAK_CLOSE_PUNCTUATION,
00096   G_UNICODE_BREAK_QUOTATION,
00097   G_UNICODE_BREAK_EXCLAMATION,
00098   G_UNICODE_BREAK_IDEOGRAPHIC,
00099   G_UNICODE_BREAK_NUMERIC,
00100   G_UNICODE_BREAK_INFIX_SEPARATOR,
00101   G_UNICODE_BREAK_SYMBOL,
00102   G_UNICODE_BREAK_ALPHABETIC,
00103   G_UNICODE_BREAK_PREFIX,
00104   G_UNICODE_BREAK_POSTFIX,
00105   G_UNICODE_BREAK_COMPLEX_CONTEXT,
00106   G_UNICODE_BREAK_AMBIGUOUS,
00107   G_UNICODE_BREAK_UNKNOWN,
00108   G_UNICODE_BREAK_NEXT_LINE,
00109   G_UNICODE_BREAK_WORD_JOINER,
00110   G_UNICODE_BREAK_HANGUL_L_JAMO,
00111   G_UNICODE_BREAK_HANGUL_V_JAMO,
00112   G_UNICODE_BREAK_HANGUL_T_JAMO,
00113   G_UNICODE_BREAK_HANGUL_LV_SYLLABLE,
00114   G_UNICODE_BREAK_HANGUL_LVT_SYLLABLE
00115 } GUnicodeBreakType;
00116 
00117 /* Returns TRUE if current locale uses UTF-8 charset.  If CHARSET is
00118  * not null, sets *CHARSET to the name of the current locale's
00119  * charset.  This value is statically allocated, and should be copied
00120  * in case the locale's charset will be changed later using setlocale()
00121  * or in some other way.
00122  */
00123 IMPORT_C gboolean g_get_charset (G_CONST_RETURN char **charset);
00124 
00125 /* These are all analogs of the <ctype.h> functions.
00126  */
00127 IMPORT_C gboolean g_unichar_isalnum   (gunichar c) G_GNUC_CONST;
00128 IMPORT_C gboolean g_unichar_isalpha   (gunichar c) G_GNUC_CONST;
00129 IMPORT_C gboolean g_unichar_iscntrl   (gunichar c) G_GNUC_CONST;
00130 IMPORT_C gboolean g_unichar_isdigit   (gunichar c) G_GNUC_CONST;
00131 IMPORT_C gboolean g_unichar_isgraph   (gunichar c) G_GNUC_CONST;
00132 IMPORT_C gboolean g_unichar_islower   (gunichar c) G_GNUC_CONST;
00133 IMPORT_C gboolean g_unichar_isprint   (gunichar c) G_GNUC_CONST;
00134 IMPORT_C gboolean g_unichar_ispunct   (gunichar c) G_GNUC_CONST;
00135 IMPORT_C gboolean g_unichar_isspace   (gunichar c) G_GNUC_CONST;
00136 IMPORT_C gboolean g_unichar_isupper   (gunichar c) G_GNUC_CONST;
00137 IMPORT_C gboolean g_unichar_isxdigit  (gunichar c) G_GNUC_CONST;
00138 IMPORT_C gboolean g_unichar_istitle   (gunichar c) G_GNUC_CONST;
00139 IMPORT_C gboolean g_unichar_isdefined (gunichar c) G_GNUC_CONST;
00140 IMPORT_C gboolean g_unichar_iswide    (gunichar c) G_GNUC_CONST;
00141 
00142 /* More <ctype.h> functions.  These convert between the three cases.
00143  * See the Unicode book to understand title case.  */
00144 IMPORT_C gunichar g_unichar_toupper (gunichar c) G_GNUC_CONST;
00145 IMPORT_C gunichar g_unichar_tolower (gunichar c) G_GNUC_CONST;
00146 IMPORT_C gunichar g_unichar_totitle (gunichar c) G_GNUC_CONST;
00147 
00148 /* If C is a digit (according to `g_unichar_isdigit'), then return its
00149    numeric value.  Otherwise return -1.  */
00150 IMPORT_C gint g_unichar_digit_value (gunichar c) G_GNUC_CONST;
00151 
00152 IMPORT_C gint g_unichar_xdigit_value (gunichar c) G_GNUC_CONST;
00153 
00154 /* Return the Unicode character type of a given character.  */
00155 IMPORT_C GUnicodeType g_unichar_type (gunichar c) G_GNUC_CONST;
00156 
00157 /* Return the line break property for a given character */
00158 IMPORT_C GUnicodeBreakType g_unichar_break_type (gunichar c) G_GNUC_CONST;
00159 
00160 
00161 /* Compute canonical ordering of a string in-place.  This rearranges
00162    decomposed characters in the string according to their combining
00163    classes.  See the Unicode manual for more information.  */
00164 IMPORT_C void g_unicode_canonical_ordering (gunichar *string,
00165                                    gsize     len);
00166 
00167 /* Compute canonical decomposition of a character.  Returns g_malloc()d
00168    string of Unicode characters.  RESULT_LEN is set to the resulting
00169    length of the string.  */
00170 IMPORT_C gunichar *g_unicode_canonical_decomposition (gunichar  ch,
00171                                              gsize    *result_len) G_GNUC_MALLOC;
00172 
00173 /* Array of skip-bytes-per-initial character.
00174  */
00175 #ifdef SYMBIAN
00176 IMPORT_C const gchar * const * _g_utf8_skip();
00177 #endif /* SYMBIAN */
00178 GLIB_VAR const gchar * const g_utf8_skip;
00179 
00180 #define g_utf8_next_char(p) (char *)((p) + g_utf8_skip[*(guchar *)(p)])
00181 
00182 IMPORT_C gunichar g_utf8_get_char           (const gchar  *p);
00183 IMPORT_C gunichar g_utf8_get_char_validated (const  gchar *p,
00184                                     gssize        max_len);
00185 
00186 IMPORT_C gchar*   g_utf8_offset_to_pointer (const gchar *str,
00187                                    glong        offset);  
00188 IMPORT_C glong    g_utf8_pointer_to_offset (const gchar *str,      
00189                                    const gchar *pos);
00190 IMPORT_C gchar*   g_utf8_prev_char         (const gchar *p);
00191 IMPORT_C gchar*   g_utf8_find_next_char    (const gchar *p,
00192                                    const gchar *end);
00193 IMPORT_C gchar*   g_utf8_find_prev_char    (const gchar *str,
00194                                    const gchar *p);
00195 
00196 IMPORT_C glong g_utf8_strlen (const gchar *p,  
00197                      gssize       max);        
00198 
00199 /* Copies n characters from src to dest */
00200 IMPORT_C gchar* g_utf8_strncpy (gchar       *dest,
00201                        const gchar *src,
00202                        gsize        n);
00203 
00204 /* Find the UTF-8 character corresponding to ch, in string p. These
00205    functions are equivalants to strchr and strrchr */
00206 IMPORT_C gchar* g_utf8_strchr  (const gchar *p,
00207                        gssize       len,
00208                        gunichar     c);
00209 IMPORT_C gchar* g_utf8_strrchr (const gchar *p,
00210                        gssize       len,
00211                        gunichar     c);
00212 IMPORT_C gchar* g_utf8_strreverse (const gchar *str,
00213                           gssize len);
00214 
00215 IMPORT_C gunichar2 *g_utf8_to_utf16     (const gchar      *str,
00216                                 glong             len,            
00217                                 glong            *items_read,     
00218                                 glong            *items_written,  
00219                                 GError          **error) G_GNUC_MALLOC;
00220 IMPORT_C gunichar * g_utf8_to_ucs4      (const gchar      *str,
00221                                 glong             len,            
00222                                 glong            *items_read,     
00223                                 glong            *items_written,  
00224                                 GError          **error) G_GNUC_MALLOC;
00225 IMPORT_C gunichar * g_utf8_to_ucs4_fast (const gchar      *str,
00226                                 glong             len,            
00227                                 glong            *items_written) G_GNUC_MALLOC; 
00228 IMPORT_C gunichar * g_utf16_to_ucs4     (const gunichar2  *str,
00229                                 glong             len,            
00230                                 glong            *items_read,     
00231                                 glong            *items_written,  
00232                                 GError          **error) G_GNUC_MALLOC;
00233 IMPORT_C gchar*     g_utf16_to_utf8     (const gunichar2  *str,
00234                                 glong             len,            
00235                                 glong            *items_read,     
00236                                 glong            *items_written,  
00237                                 GError          **error) G_GNUC_MALLOC;
00238 IMPORT_C gunichar2 *g_ucs4_to_utf16     (const gunichar   *str,
00239                                 glong             len,            
00240                                 glong            *items_read,     
00241                                 glong            *items_written,  
00242                                 GError          **error) G_GNUC_MALLOC;
00243 IMPORT_C gchar*     g_ucs4_to_utf8      (const gunichar   *str,
00244                                 glong             len,            
00245                                 glong            *items_read,     
00246                                 glong            *items_written,  
00247                                 GError          **error) G_GNUC_MALLOC;
00248 
00249 /* Convert a single character into UTF-8. outbuf must have at
00250  * least 6 bytes of space. Returns the number of bytes in the
00251  * result.
00252  */
00253 IMPORT_C gint      g_unichar_to_utf8 (gunichar    c,
00254                              gchar      *outbuf);
00255 
00256 /* Validate a UTF8 string, return TRUE if valid, put pointer to
00257  * first invalid char in **end
00258  */
00259 
00260 IMPORT_C gboolean g_utf8_validate (const gchar  *str,
00261                           gssize        max_len,  
00262                           const gchar **end);
00263 
00264 /* Validate a Unicode character */
00265 IMPORT_C gboolean g_unichar_validate (gunichar ch);
00266 
00267 IMPORT_C gchar *g_utf8_strup   (const gchar *str,
00268                        gssize       len) G_GNUC_MALLOC;
00269 IMPORT_C gchar *g_utf8_strdown (const gchar *str,
00270                        gssize       len) G_GNUC_MALLOC;
00271 IMPORT_C gchar *g_utf8_casefold (const gchar *str,
00272                         gssize       len) G_GNUC_MALLOC;
00273 
00274 typedef enum {
00275   G_NORMALIZE_DEFAULT,
00276   G_NORMALIZE_NFD = G_NORMALIZE_DEFAULT,
00277   G_NORMALIZE_DEFAULT_COMPOSE,
00278   G_NORMALIZE_NFC = G_NORMALIZE_DEFAULT_COMPOSE,
00279   G_NORMALIZE_ALL,
00280   G_NORMALIZE_NFKD = G_NORMALIZE_ALL,
00281   G_NORMALIZE_ALL_COMPOSE,
00282   G_NORMALIZE_NFKC = G_NORMALIZE_ALL_COMPOSE
00283 } GNormalizeMode;
00284 
00285 IMPORT_C gchar *g_utf8_normalize (const gchar   *str,
00286                          gssize         len,
00287                          GNormalizeMode mode) G_GNUC_MALLOC;
00288 
00289 IMPORT_C gint   g_utf8_collate     (const gchar *str1,
00290                            const gchar *str2);
00291 IMPORT_C gchar *g_utf8_collate_key (const gchar *str,
00292                            gssize       len) G_GNUC_MALLOC;
00293 IMPORT_C gchar *g_utf8_collate_key_for_filename (const gchar *str,
00294                                         gssize       len) G_GNUC_MALLOC;
00295 
00296 IMPORT_C gboolean g_unichar_get_mirror_char (gunichar ch,
00297                                     gunichar *mirrored_ch);
00298 
00299 G_END_DECLS
00300 
00301 #endif /* __G_UNICODE_H__ */