1 <!-- ##### SECTION Title ##### -->
4 <!-- ##### SECTION Short_Description ##### -->
7 <!-- ##### SECTION Long_Description ##### -->
12 <!-- ##### SECTION See_Also ##### -->
17 <!-- ##### TYPEDEF gunichar ##### -->
19 A type which can hold any UCS-4 character code.
23 <!-- ##### TYPEDEF gunichar2 ##### -->
25 A type which can hold any UTF-16 character code.
29 <!-- ##### FUNCTION g_get_charset ##### -->
35 <!-- # Unused Parameters # -->
39 <!-- ##### FUNCTION g_unichar_validate ##### -->
48 <!-- ##### FUNCTION g_unichar_isalnum ##### -->
57 <!-- ##### FUNCTION g_unichar_isalpha ##### -->
66 <!-- ##### FUNCTION g_unichar_iscntrl ##### -->
75 <!-- ##### FUNCTION g_unichar_isdigit ##### -->
84 <!-- ##### FUNCTION g_unichar_isgraph ##### -->
93 <!-- ##### FUNCTION g_unichar_islower ##### -->
102 <!-- ##### FUNCTION g_unichar_isprint ##### -->
111 <!-- ##### FUNCTION g_unichar_ispunct ##### -->
120 <!-- ##### FUNCTION g_unichar_isspace ##### -->
129 <!-- ##### FUNCTION g_unichar_isupper ##### -->
138 <!-- ##### FUNCTION g_unichar_isxdigit ##### -->
147 <!-- ##### FUNCTION g_unichar_istitle ##### -->
156 <!-- ##### FUNCTION g_unichar_isdefined ##### -->
165 <!-- ##### FUNCTION g_unichar_iswide ##### -->
174 <!-- ##### FUNCTION g_unichar_toupper ##### -->
183 <!-- ##### FUNCTION g_unichar_tolower ##### -->
192 <!-- ##### FUNCTION g_unichar_totitle ##### -->
201 <!-- ##### FUNCTION g_unichar_digit_value ##### -->
210 <!-- ##### FUNCTION g_unichar_xdigit_value ##### -->
219 <!-- ##### ENUM GUnicodeType ##### -->
221 These are the possible character classifications.
222 See <ulink url="http://www.unicode.org/Public/UNIDATA/UnicodeData.html"
223 >http://www.unicode.org/Public/UNIDATA/UnicodeData.html</ulink>.
228 @G_UNICODE_UNASSIGNED:
229 @G_UNICODE_PRIVATE_USE:
230 @G_UNICODE_SURROGATE:
231 @G_UNICODE_LOWERCASE_LETTER:
232 @G_UNICODE_MODIFIER_LETTER:
233 @G_UNICODE_OTHER_LETTER:
234 @G_UNICODE_TITLECASE_LETTER:
235 @G_UNICODE_UPPERCASE_LETTER:
236 @G_UNICODE_COMBINING_MARK:
237 @G_UNICODE_ENCLOSING_MARK:
238 @G_UNICODE_NON_SPACING_MARK:
239 @G_UNICODE_DECIMAL_NUMBER:
240 @G_UNICODE_LETTER_NUMBER:
241 @G_UNICODE_OTHER_NUMBER:
242 @G_UNICODE_CONNECT_PUNCTUATION:
243 @G_UNICODE_DASH_PUNCTUATION:
244 @G_UNICODE_CLOSE_PUNCTUATION:
245 @G_UNICODE_FINAL_PUNCTUATION:
246 @G_UNICODE_INITIAL_PUNCTUATION:
247 @G_UNICODE_OTHER_PUNCTUATION:
248 @G_UNICODE_OPEN_PUNCTUATION:
249 @G_UNICODE_CURRENCY_SYMBOL:
250 @G_UNICODE_MODIFIER_SYMBOL:
251 @G_UNICODE_MATH_SYMBOL:
252 @G_UNICODE_OTHER_SYMBOL:
253 @G_UNICODE_LINE_SEPARATOR:
254 @G_UNICODE_PARAGRAPH_SEPARATOR:
255 @G_UNICODE_SPACE_SEPARATOR:
257 <!-- ##### FUNCTION g_unichar_type ##### -->
266 <!-- ##### ENUM GUnicodeBreakType ##### -->
268 These are the possible line break classifications.
269 See <ulink url="http://www.unicode.org/unicode/reports/tr14/"
270 >http://www.unicode.org/unicode/reports/tr14/</ulink>.
273 @G_UNICODE_BREAK_MANDATORY:
274 @G_UNICODE_BREAK_CARRIAGE_RETURN:
275 @G_UNICODE_BREAK_LINE_FEED:
276 @G_UNICODE_BREAK_COMBINING_MARK:
277 @G_UNICODE_BREAK_SURROGATE:
278 @G_UNICODE_BREAK_ZERO_WIDTH_SPACE:
279 @G_UNICODE_BREAK_INSEPARABLE:
280 @G_UNICODE_BREAK_NON_BREAKING_GLUE:
281 @G_UNICODE_BREAK_CONTINGENT:
282 @G_UNICODE_BREAK_SPACE:
283 @G_UNICODE_BREAK_AFTER:
284 @G_UNICODE_BREAK_BEFORE:
285 @G_UNICODE_BREAK_BEFORE_AND_AFTER:
286 @G_UNICODE_BREAK_HYPHEN:
287 @G_UNICODE_BREAK_NON_STARTER:
288 @G_UNICODE_BREAK_OPEN_PUNCTUATION:
289 @G_UNICODE_BREAK_CLOSE_PUNCTUATION:
290 @G_UNICODE_BREAK_QUOTATION:
291 @G_UNICODE_BREAK_EXCLAMATION:
292 @G_UNICODE_BREAK_IDEOGRAPHIC:
293 @G_UNICODE_BREAK_NUMERIC:
294 @G_UNICODE_BREAK_INFIX_SEPARATOR:
295 @G_UNICODE_BREAK_SYMBOL:
296 @G_UNICODE_BREAK_ALPHABETIC:
297 @G_UNICODE_BREAK_PREFIX:
298 @G_UNICODE_BREAK_POSTFIX:
299 @G_UNICODE_BREAK_COMPLEX_CONTEXT:
300 @G_UNICODE_BREAK_AMBIGUOUS:
301 @G_UNICODE_BREAK_UNKNOWN:
303 <!-- ##### FUNCTION g_unichar_break_type ##### -->
312 <!-- ##### FUNCTION g_unicode_canonical_ordering ##### -->
321 <!-- ##### FUNCTION g_unicode_canonical_decomposition ##### -->
331 <!-- ##### MACRO g_utf8_next_char ##### -->
333 Skips to the next character in a UTF-8 string. The string must be
334 valid; this macro is as fast as possible, and has zero error-checking.
335 You would use this macro to iterate over a string character by
336 character. The macro returns the start of the next UTF-8 character.
337 Before using this macro, use g_utf8_validate() to validate strings
338 that may contain invalid UTF-8.
341 @p: Pointer to the start of a valid UTF-8 character.
344 <!-- ##### FUNCTION g_utf8_get_char ##### -->
353 <!-- ##### FUNCTION g_utf8_get_char_validated ##### -->
363 <!-- ##### FUNCTION g_utf8_offset_to_pointer ##### -->
373 <!-- ##### FUNCTION g_utf8_pointer_to_offset ##### -->
383 <!-- ##### FUNCTION g_utf8_prev_char ##### -->
392 <!-- ##### FUNCTION g_utf8_find_next_char ##### -->
400 <!-- # Unused Parameters # -->
404 <!-- ##### FUNCTION g_utf8_find_prev_char ##### -->
414 <!-- ##### FUNCTION g_utf8_strlen ##### -->
424 <!-- ##### FUNCTION g_utf8_strncpy ##### -->
435 <!-- ##### FUNCTION g_utf8_strchr ##### -->
444 <!-- # Unused Parameters # -->
448 <!-- ##### FUNCTION g_utf8_strrchr ##### -->
457 <!-- # Unused Parameters # -->
461 <!-- ##### FUNCTION g_utf8_validate ##### -->
470 <!-- # Unused Parameters # -->
474 <!-- ##### FUNCTION g_utf8_strup ##### -->
484 <!-- ##### FUNCTION g_utf8_strdown ##### -->
494 <!-- ##### FUNCTION g_utf8_casefold ##### -->
504 <!-- ##### FUNCTION g_utf8_normalize ##### -->
515 <!-- ##### ENUM GNormalizeMode ##### -->
520 @G_NORMALIZE_DEFAULT:
522 @G_NORMALIZE_DEFAULT_COMPOSE:
526 @G_NORMALIZE_ALL_COMPOSE:
529 <!-- ##### FUNCTION g_utf8_collate ##### -->
539 <!-- ##### FUNCTION g_utf8_collate_key ##### -->
549 <!-- ##### FUNCTION g_utf8_to_utf16 ##### -->
562 <!-- ##### FUNCTION g_utf8_to_ucs4 ##### -->
575 <!-- ##### FUNCTION g_utf8_to_ucs4_fast ##### -->
586 <!-- ##### FUNCTION g_utf16_to_ucs4 ##### -->
599 <!-- ##### FUNCTION g_utf16_to_utf8 ##### -->
612 <!-- ##### FUNCTION g_ucs4_to_utf16 ##### -->
625 <!-- ##### FUNCTION g_ucs4_to_utf8 ##### -->
638 <!-- ##### FUNCTION g_unichar_to_utf8 ##### -->