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 ##### -->
38 <!-- ##### FUNCTION g_unichar_validate ##### -->
47 <!-- ##### FUNCTION g_unichar_isalnum ##### -->
56 <!-- ##### FUNCTION g_unichar_isalpha ##### -->
65 <!-- ##### FUNCTION g_unichar_iscntrl ##### -->
74 <!-- ##### FUNCTION g_unichar_isdigit ##### -->
83 <!-- ##### FUNCTION g_unichar_isgraph ##### -->
92 <!-- ##### FUNCTION g_unichar_islower ##### -->
101 <!-- ##### FUNCTION g_unichar_isprint ##### -->
110 <!-- ##### FUNCTION g_unichar_ispunct ##### -->
119 <!-- ##### FUNCTION g_unichar_isspace ##### -->
128 <!-- ##### FUNCTION g_unichar_isupper ##### -->
137 <!-- ##### FUNCTION g_unichar_isxdigit ##### -->
146 <!-- ##### FUNCTION g_unichar_istitle ##### -->
155 <!-- ##### FUNCTION g_unichar_isdefined ##### -->
164 <!-- ##### FUNCTION g_unichar_iswide ##### -->
173 <!-- ##### FUNCTION g_unichar_toupper ##### -->
182 <!-- ##### FUNCTION g_unichar_tolower ##### -->
191 <!-- ##### FUNCTION g_unichar_totitle ##### -->
200 <!-- ##### FUNCTION g_unichar_digit_value ##### -->
209 <!-- ##### FUNCTION g_unichar_xdigit_value ##### -->
218 <!-- ##### ENUM GUnicodeType ##### -->
220 These are the possible character classifications.
221 See <ulink url="http://www.unicode.org/Public/UNIDATA/UnicodeData.html"
222 >http://www.unicode.org/Public/UNIDATA/UnicodeData.html</ulink>.
227 @G_UNICODE_UNASSIGNED:
228 @G_UNICODE_PRIVATE_USE:
229 @G_UNICODE_SURROGATE:
230 @G_UNICODE_LOWERCASE_LETTER:
231 @G_UNICODE_MODIFIER_LETTER:
232 @G_UNICODE_OTHER_LETTER:
233 @G_UNICODE_TITLECASE_LETTER:
234 @G_UNICODE_UPPERCASE_LETTER:
235 @G_UNICODE_COMBINING_MARK:
236 @G_UNICODE_ENCLOSING_MARK:
237 @G_UNICODE_NON_SPACING_MARK:
238 @G_UNICODE_DECIMAL_NUMBER:
239 @G_UNICODE_LETTER_NUMBER:
240 @G_UNICODE_OTHER_NUMBER:
241 @G_UNICODE_CONNECT_PUNCTUATION:
242 @G_UNICODE_DASH_PUNCTUATION:
243 @G_UNICODE_CLOSE_PUNCTUATION:
244 @G_UNICODE_FINAL_PUNCTUATION:
245 @G_UNICODE_INITIAL_PUNCTUATION:
246 @G_UNICODE_OTHER_PUNCTUATION:
247 @G_UNICODE_OPEN_PUNCTUATION:
248 @G_UNICODE_CURRENCY_SYMBOL:
249 @G_UNICODE_MODIFIER_SYMBOL:
250 @G_UNICODE_MATH_SYMBOL:
251 @G_UNICODE_OTHER_SYMBOL:
252 @G_UNICODE_LINE_SEPARATOR:
253 @G_UNICODE_PARAGRAPH_SEPARATOR:
254 @G_UNICODE_SPACE_SEPARATOR:
256 <!-- ##### FUNCTION g_unichar_type ##### -->
265 <!-- ##### ENUM GUnicodeBreakType ##### -->
267 These are the possible line break classifications.
268 See <ulink url="http://www.unicode.org/unicode/reports/tr14/"
269 >http://www.unicode.org/unicode/reports/tr14/</ulink>.
272 @G_UNICODE_BREAK_MANDATORY:
273 @G_UNICODE_BREAK_CARRIAGE_RETURN:
274 @G_UNICODE_BREAK_LINE_FEED:
275 @G_UNICODE_BREAK_COMBINING_MARK:
276 @G_UNICODE_BREAK_SURROGATE:
277 @G_UNICODE_BREAK_ZERO_WIDTH_SPACE:
278 @G_UNICODE_BREAK_INSEPARABLE:
279 @G_UNICODE_BREAK_NON_BREAKING_GLUE:
280 @G_UNICODE_BREAK_CONTINGENT:
281 @G_UNICODE_BREAK_SPACE:
282 @G_UNICODE_BREAK_AFTER:
283 @G_UNICODE_BREAK_BEFORE:
284 @G_UNICODE_BREAK_BEFORE_AND_AFTER:
285 @G_UNICODE_BREAK_HYPHEN:
286 @G_UNICODE_BREAK_NON_STARTER:
287 @G_UNICODE_BREAK_OPEN_PUNCTUATION:
288 @G_UNICODE_BREAK_CLOSE_PUNCTUATION:
289 @G_UNICODE_BREAK_QUOTATION:
290 @G_UNICODE_BREAK_EXCLAMATION:
291 @G_UNICODE_BREAK_IDEOGRAPHIC:
292 @G_UNICODE_BREAK_NUMERIC:
293 @G_UNICODE_BREAK_INFIX_SEPARATOR:
294 @G_UNICODE_BREAK_SYMBOL:
295 @G_UNICODE_BREAK_ALPHABETIC:
296 @G_UNICODE_BREAK_PREFIX:
297 @G_UNICODE_BREAK_POSTFIX:
298 @G_UNICODE_BREAK_COMPLEX_CONTEXT:
299 @G_UNICODE_BREAK_AMBIGUOUS:
300 @G_UNICODE_BREAK_UNKNOWN:
302 <!-- ##### FUNCTION g_unichar_break_type ##### -->
311 <!-- ##### FUNCTION g_unicode_canonical_ordering ##### -->
320 <!-- ##### FUNCTION g_unicode_canonical_decomposition ##### -->
330 <!-- ##### MACRO g_utf8_next_char ##### -->
332 Skips to the next character in a UTF-8 string. The string must be
333 valid; this macro is as fast as possible, and has zero error-checking.
334 You would use this macro to iterate over a string character by
335 character. The macro returns the start of the next UTF-8 character.
336 Before using this macro, use g_utf8_validate() to validate strings
337 that may contain invalid UTF-8.
340 @p: Pointer to the start of a valid UTF-8 character.
343 <!-- ##### FUNCTION g_utf8_get_char ##### -->
352 <!-- ##### FUNCTION g_utf8_get_char_validated ##### -->
362 <!-- ##### FUNCTION g_utf8_offset_to_pointer ##### -->
372 <!-- ##### FUNCTION g_utf8_pointer_to_offset ##### -->
382 <!-- ##### FUNCTION g_utf8_prev_char ##### -->
391 <!-- ##### FUNCTION g_utf8_find_next_char ##### -->
399 <!-- # Unused Parameters # -->
403 <!-- ##### FUNCTION g_utf8_find_prev_char ##### -->
413 <!-- ##### FUNCTION g_utf8_strlen ##### -->
423 <!-- ##### FUNCTION g_utf8_strncpy ##### -->
434 <!-- ##### FUNCTION g_utf8_strchr ##### -->
443 <!-- # Unused Parameters # -->
447 <!-- ##### FUNCTION g_utf8_strrchr ##### -->
456 <!-- # Unused Parameters # -->
460 <!-- ##### FUNCTION g_utf8_validate ##### -->
469 <!-- # Unused Parameters # -->
473 <!-- ##### FUNCTION g_utf8_strup ##### -->
483 <!-- ##### FUNCTION g_utf8_strdown ##### -->
493 <!-- ##### FUNCTION g_utf8_casefold ##### -->
503 <!-- ##### FUNCTION g_utf8_normalize ##### -->
514 <!-- ##### ENUM GNormalizeMode ##### -->
519 @G_NORMALIZE_DEFAULT:
521 @G_NORMALIZE_DEFAULT_COMPOSE:
525 @G_NORMALIZE_ALL_COMPOSE:
528 <!-- ##### FUNCTION g_utf8_collate ##### -->
538 <!-- ##### FUNCTION g_utf8_collate_key ##### -->
548 <!-- ##### FUNCTION g_utf8_to_utf16 ##### -->
561 <!-- ##### FUNCTION g_utf8_to_ucs4 ##### -->
574 <!-- ##### FUNCTION g_utf8_to_ucs4_fast ##### -->
585 <!-- ##### FUNCTION g_utf16_to_ucs4 ##### -->
598 <!-- ##### FUNCTION g_utf16_to_utf8 ##### -->
611 <!-- ##### FUNCTION g_ucs4_to_utf16 ##### -->
624 <!-- ##### FUNCTION g_ucs4_to_utf8 ##### -->
637 <!-- ##### FUNCTION g_unichar_to_utf8 ##### -->