/usr/include/unicode
NameSizeModeActions
basictz.h89130644editdlrm
bms.h86640644editdlrm
bmsearch.h73160644editdlrm
brkiter.h230010644editdlrm
bytestream.h85310644editdlrm
calendar.h906590644editdlrm
caniter.h72880644editdlrm
chariter.h241860644editdlrm
choicfmt.h295280644editdlrm
coleitr.h129900644editdlrm
coll.h484680644editdlrm
colldata.h119570644editdlrm
curramt.h36590644editdlrm
currpinf.h70610644editdlrm
currunit.h30570644editdlrm
datefmt.h279460644editdlrm
dbbi.h9660644editdlrm
dcfmtsym.h140400644editdlrm
decimfmt.h886120644editdlrm
docmain.h60030644editdlrm
dtfmtsym.h261450644editdlrm
dtintrv.h37340644editdlrm
dtitvfmt.h397000644editdlrm
dtitvinf.h187040644editdlrm
dtptngen.h173030644editdlrm
dtrule.h87180644editdlrm
errorcode.h43610644editdlrm
fieldpos.h87130644editdlrm
fmtable.h187940644editdlrm
format.h120830644editdlrm
gregocal.h337970644editdlrm
locid.h302410644editdlrm
measfmt.h18970644editdlrm
measunit.h16350644editdlrm
measure.h33210644editdlrm
msgfmt.h394350644editdlrm
normlzr.h303370644editdlrm
numfmt.h339870644editdlrm
numsys.h50040644editdlrm
parseerr.h30440644editdlrm
parsepos.h54680644editdlrm
platform.h99610644editdlrm
plurfmt.h230790644editdlrm
plurrule.h99010644editdlrm
ppalmos.h69920644editdlrm
putil.h66860644editdlrm
pwin32.h86680644editdlrm
rbbi.h269930644editdlrm
rbnf.h456810644editdlrm
rbtz.h156950644editdlrm
regex.h523160644editdlrm
rep.h95590644editdlrm
resbund.h181300644editdlrm
schriter.h62930644editdlrm
search.h223570644editdlrm
simpletz.h461790644editdlrm
smpdtfmt.h483250644editdlrm
sortkey.h111110644editdlrm
std_string.h17690644editdlrm
strenum.h98880644editdlrm
stringpiece.h54840644editdlrm
stsearch.h222870644editdlrm
symtable.h41990644editdlrm
tblcoll.h381990644editdlrm
timezone.h345840644editdlrm
tmunit.h34540644editdlrm
tmutamt.h47870644editdlrm
tmutfmt.h86690644editdlrm
translit.h547800644editdlrm
tzrule.h360570644editdlrm
tztrans.h61010644editdlrm
ubidi.h830920644editdlrm
ubrk.h176880644editdlrm
ucal.h401770644editdlrm
ucasemap.h164200644editdlrm
ucat.h53710644editdlrm
uchar.h1110620644editdlrm
uchriter.h131320644editdlrm
uclean.h118550644editdlrm
ucnv.h831110644editdlrm
ucnvsel.h56300644editdlrm
ucnv_cb.h66350644editdlrm
ucnv_err.h213750644editdlrm
ucol.h488260644editdlrm
ucoleitr.h123560644editdlrm
uconfig.h60350644editdlrm
ucsdet.h124640644editdlrm
ucurr.h115720644editdlrm
udat.h344960644editdlrm
udata.h142650644editdlrm
udatpg.h187150644editdlrm
udeprctd.h22840644editdlrm
udraft.h76000644editdlrm
uenum.h57960644editdlrm
uidna.h159180644editdlrm
uintrnal.h157520644editdlrm
uiter.h232340644editdlrm
uloc.h445480644editdlrm
ulocdata.h97390644editdlrm
umachine.h113600644editdlrm
umisc.h12550644editdlrm
umsg.h260760644editdlrm
unifilt.h37700644editdlrm
unifunct.h39660644editdlrm
unimatch.h60710644editdlrm
unirepl.h32900644editdlrm
uniset.h617710644editdlrm
unistr.h1613210644editdlrm
unorm.h236210644editdlrm
unum.h321450644editdlrm
uobject.h113930644editdlrm
uobslete.h8520644editdlrm
uregex.h439480644editdlrm
urename.h925380644editdlrm
urep.h53940644editdlrm
ures.h363480644editdlrm
uscript.h113600644editdlrm
usearch.h342230644editdlrm
uset.h398680644editdlrm
usetiter.h96060644editdlrm
ushape.h179070644editdlrm
uspoof.h387520644editdlrm
usprep.h77500644editdlrm
ustdio.h353330644editdlrm
ustream.h18910644editdlrm
ustring.h693830644editdlrm
usystem.h19250644editdlrm
utext.h583940644editdlrm
utf.h82730644editdlrm
utf8.h205120644editdlrm
utf16.h187760644editdlrm
utf32.h6530644editdlrm
utf_old.h436460644editdlrm
utmscale.h136890644editdlrm
utrace.h133550644editdlrm
utrans.h231290644editdlrm
utypes.h345130644editdlrm
uversion.h109020644editdlrm
vtzone.h200480644editdlrm
Edit: /usr/include/unicode/ucasemap.h (16420B)
/* ******************************************************************************* * * Copyright (C) 2005-2009, International Business Machines * Corporation and others. All Rights Reserved. * ******************************************************************************* * file name: ucasemap.h * encoding: US-ASCII * tab size: 8 (not used) * indentation:4 * * created on: 2005may06 * created by: Markus W. Scherer * * Case mapping service object and functions using it. */ #ifndef __UCASEMAP_H__ #define __UCASEMAP_H__ #include "unicode/utypes.h" #include "unicode/ustring.h" /** * \file * \brief C API: Unicode case mapping functions using a UCaseMap service object. * * The service object takes care of memory allocations, data loading, and setup * for the attributes, as usual. * * Currently, the functionality provided here does not overlap with uchar.h * and ustring.h, except for ucasemap_toTitle(). * * ucasemap_utf8XYZ() functions operate directly on UTF-8 strings. */ /** * UCaseMap is an opaque service object for newer ICU case mapping functions. * Older functions did not use a service object. * @stable ICU 3.4 */ struct UCaseMap; typedef struct UCaseMap UCaseMap; /**< C typedef for struct UCaseMap. @stable ICU 3.4 */ /** * Open a UCaseMap service object for a locale and a set of options. * The locale ID and options are preprocessed so that functions using the * service object need not process them in each call. * * @param locale ICU locale ID, used for language-dependent * upper-/lower-/title-casing according to the Unicode standard. * Usual semantics: ""=root, NULL=default locale, etc. * @param options Options bit set, used for case folding and string comparisons. * Same flags as for u_foldCase(), u_strFoldCase(), * u_strCaseCompare(), etc. * Use 0 or U_FOLD_CASE_DEFAULT for default behavior. * @param pErrorCode Must be a valid pointer to an error code value, * which must not indicate a failure before the function call. * @return Pointer to a UCaseMap service object, if successful. * * @see U_FOLD_CASE_DEFAULT * @see U_FOLD_CASE_EXCLUDE_SPECIAL_I * @see U_TITLECASE_NO_LOWERCASE * @see U_TITLECASE_NO_BREAK_ADJUSTMENT * @stable ICU 3.4 */ U_STABLE UCaseMap * U_EXPORT2 ucasemap_open(const char *locale, uint32_t options, UErrorCode *pErrorCode); /** * Close a UCaseMap service object. * @param csm Object to be closed. * @stable ICU 3.4 */ U_STABLE void U_EXPORT2 ucasemap_close(UCaseMap *csm); /** * Get the locale ID that is used for language-dependent case mappings. * @param csm UCaseMap service object. * @return locale ID * @stable ICU 3.4 */ U_STABLE const char * U_EXPORT2 ucasemap_getLocale(const UCaseMap *csm); /** * Get the options bit set that is used for case folding and string comparisons. * @param csm UCaseMap service object. * @return options bit set * @stable ICU 3.4 */ U_STABLE uint32_t U_EXPORT2 ucasemap_getOptions(const UCaseMap *csm); /** * Set the locale ID that is used for language-dependent case mappings. * * @param csm UCaseMap service object. * @param locale Locale ID, see ucasemap_open(). * @param pErrorCode Must be a valid pointer to an error code value, * which must not indicate a failure before the function call. * * @see ucasemap_open * @stable ICU 3.4 */ U_STABLE void U_EXPORT2 ucasemap_setLocale(UCaseMap *csm, const char *locale, UErrorCode *pErrorCode); /** * Set the options bit set that is used for case folding and string comparisons. * * @param csm UCaseMap service object. * @param options Options bit set, see ucasemap_open(). * @param pErrorCode Must be a valid pointer to an error code value, * which must not indicate a failure before the function call. * * @see ucasemap_open * @stable ICU 3.4 */ U_STABLE void U_EXPORT2 ucasemap_setOptions(UCaseMap *csm, uint32_t options, UErrorCode *pErrorCode); /** * Do not lowercase non-initial parts of words when titlecasing. * Option bit for titlecasing APIs that take an options bit set. * * By default, titlecasing will titlecase the first cased character * of a word and lowercase all other characters. * With this option, the other characters will not be modified. * * @see ucasemap_setOptions * @see ucasemap_toTitle * @see ucasemap_utf8ToTitle * @see UnicodeString::toTitle * @stable ICU 3.8 */ #define U_TITLECASE_NO_LOWERCASE 0x100 /** * Do not adjust the titlecasing indexes from BreakIterator::next() indexes; * titlecase exactly the characters at breaks from the iterator. * Option bit for titlecasing APIs that take an options bit set. * * By default, titlecasing will take each break iterator index, * adjust it by looking for the next cased character, and titlecase that one. * Other characters are lowercased. * * This follows Unicode 4 & 5 section 3.13 Default Case Operations: * * R3 toTitlecase(X): Find the word boundaries based on Unicode Standard Annex * #29, "Text Boundaries." Between each pair of word boundaries, find the first * cased character F. If F exists, map F to default_title(F); then map each * subsequent character C to default_lower(C). * * @see ucasemap_setOptions * @see ucasemap_toTitle * @see ucasemap_utf8ToTitle * @see UnicodeString::toTitle * @see U_TITLECASE_NO_LOWERCASE * @stable ICU 3.8 */ #define U_TITLECASE_NO_BREAK_ADJUSTMENT 0x200 #if !UCONFIG_NO_BREAK_ITERATION /** * Get the break iterator that is used for titlecasing. * Do not modify the returned break iterator. * @param csm UCaseMap service object. * @return titlecasing break iterator * @stable ICU 3.8 */ U_DRAFT const UBreakIterator * U_EXPORT2 ucasemap_getBreakIterator(const UCaseMap *csm); /** * Set the break iterator that is used for titlecasing. * The UCaseMap service object releases a previously set break iterator * and "adopts" this new one, taking ownership of it. * It will be released in a subsequent call to ucasemap_setBreakIterator() * or ucasemap_close(). * * Break iterator operations are not thread-safe. Therefore, titlecasing * functions use non-const UCaseMap objects. It is not possible to titlecase * strings concurrently using the same UCaseMap. * * @param csm UCaseMap service object. * @param iterToAdopt Break iterator to be adopted for titlecasing. * @param pErrorCode Must be a valid pointer to an error code value, * which must not indicate a failure before the function call. * * @see ucasemap_toTitle * @see ucasemap_utf8ToTitle * @stable ICU 3.8 */ U_DRAFT void U_EXPORT2 ucasemap_setBreakIterator(UCaseMap *csm, UBreakIterator *iterToAdopt, UErrorCode *pErrorCode); /** * Titlecase a UTF-16 string. This function is almost a duplicate of u_strToTitle(), * except that it takes ucasemap_setOptions() into account and has performance * advantages from being able to use a UCaseMap object for multiple case mapping * operations, saving setup time. * * Casing is locale-dependent and context-sensitive. * Titlecasing uses a break iterator to find the first characters of words * that are to be titlecased. It titlecases those characters and lowercases * all others. (This can be modified with ucasemap_setOptions().) * * Note: This function takes a non-const UCaseMap pointer because it will * open a default break iterator if no break iterator was set yet, * and effectively call ucasemap_setBreakIterator(); * also because the break iterator is stateful and will be modified during * the iteration. * * The titlecase break iterator can be provided to customize for arbitrary * styles, using rules and dictionaries beyond the standard iterators. * The standard titlecase iterator for the root locale implements the * algorithm of Unicode TR 21. * * This function uses only the setUText(), first(), next() and close() methods of the * provided break iterator. * * The result may be longer or shorter than the original. * The source string and the destination buffer must not overlap. * * @param csm UCaseMap service object. This pointer is non-const! * See the note above for details. * @param dest A buffer for the result string. The result will be NUL-terminated if * the buffer is large enough. * The contents is undefined in case of failure. * @param destCapacity The size of the buffer (number of bytes). If it is 0, then * dest may be NULL and the function will only return the length of the result * without writing any of the result string. * @param src The original string. * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. * @param pErrorCode Must be a valid pointer to an error code value, * which must not indicate a failure before the function call. * @return The length of the result string, if successful - or in case of a buffer overflow, * in which case it will be greater than destCapacity. * * @see u_strToTitle * @stable ICU 3.8 */ U_DRAFT int32_t U_EXPORT2 ucasemap_toTitle(UCaseMap *csm, UChar *dest, int32_t destCapacity, const UChar *src, int32_t srcLength, UErrorCode *pErrorCode); #endif /** * Lowercase the characters in a UTF-8 string. * Casing is locale-dependent and context-sensitive. * The result may be longer or shorter than the original. * The source string and the destination buffer must not overlap. * * @param csm UCaseMap service object. * @param dest A buffer for the result string. The result will be NUL-terminated if * the buffer is large enough. * The contents is undefined in case of failure. * @param destCapacity The size of the buffer (number of bytes). If it is 0, then * dest may be NULL and the function will only return the length of the result * without writing any of the result string. * @param src The original string. * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. * @param pErrorCode Must be a valid pointer to an error code value, * which must not indicate a failure before the function call. * @return The length of the result string, if successful - or in case of a buffer overflow, * in which case it will be greater than destCapacity. * * @see u_strToLower * @stable ICU 3.4 */ U_STABLE int32_t U_EXPORT2 ucasemap_utf8ToLower(const UCaseMap *csm, char *dest, int32_t destCapacity, const char *src, int32_t srcLength, UErrorCode *pErrorCode); /** * Uppercase the characters in a UTF-8 string. * Casing is locale-dependent and context-sensitive. * The result may be longer or shorter than the original. * The source string and the destination buffer must not overlap. * * @param csm UCaseMap service object. * @param dest A buffer for the result string. The result will be NUL-terminated if * the buffer is large enough. * The contents is undefined in case of failure. * @param destCapacity The size of the buffer (number of bytes). If it is 0, then * dest may be NULL and the function will only return the length of the result * without writing any of the result string. * @param src The original string. * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. * @param pErrorCode Must be a valid pointer to an error code value, * which must not indicate a failure before the function call. * @return The length of the result string, if successful - or in case of a buffer overflow, * in which case it will be greater than destCapacity. * * @see u_strToUpper * @stable ICU 3.4 */ U_STABLE int32_t U_EXPORT2 ucasemap_utf8ToUpper(const UCaseMap *csm, char *dest, int32_t destCapacity, const char *src, int32_t srcLength, UErrorCode *pErrorCode); #if !UCONFIG_NO_BREAK_ITERATION /** * Titlecase a UTF-8 string. * Casing is locale-dependent and context-sensitive. * Titlecasing uses a break iterator to find the first characters of words * that are to be titlecased. It titlecases those characters and lowercases * all others. (This can be modified with ucasemap_setOptions().) * * Note: This function takes a non-const UCaseMap pointer because it will * open a default break iterator if no break iterator was set yet, * and effectively call ucasemap_setBreakIterator(); * also because the break iterator is stateful and will be modified during * the iteration. * * The titlecase break iterator can be provided to customize for arbitrary * styles, using rules and dictionaries beyond the standard iterators. * The standard titlecase iterator for the root locale implements the * algorithm of Unicode TR 21. * * This function uses only the setUText(), first(), next() and close() methods of the * provided break iterator. * * The result may be longer or shorter than the original. * The source string and the destination buffer must not overlap. * * @param csm UCaseMap service object. This pointer is non-const! * See the note above for details. * @param dest A buffer for the result string. The result will be NUL-terminated if * the buffer is large enough. * The contents is undefined in case of failure. * @param destCapacity The size of the buffer (number of bytes). If it is 0, then * dest may be NULL and the function will only return the length of the result * without writing any of the result string. * @param src The original string. * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. * @param pErrorCode Must be a valid pointer to an error code value, * which must not indicate a failure before the function call. * @return The length of the result string, if successful - or in case of a buffer overflow, * in which case it will be greater than destCapacity. * * @see u_strToTitle * @see U_TITLECASE_NO_LOWERCASE * @see U_TITLECASE_NO_BREAK_ADJUSTMENT * @stable ICU 3.8 */ U_DRAFT int32_t U_EXPORT2 ucasemap_utf8ToTitle(UCaseMap *csm, char *dest, int32_t destCapacity, const char *src, int32_t srcLength, UErrorCode *pErrorCode); #endif /** * Case-fold the characters in a UTF-8 string. * Case-folding is locale-independent and not context-sensitive, * but there is an option for whether to include or exclude mappings for dotted I * and dotless i that are marked with 'I' in CaseFolding.txt. * The result may be longer or shorter than the original. * The source string and the destination buffer must not overlap. * * @param csm UCaseMap service object. * @param dest A buffer for the result string. The result will be NUL-terminated if * the buffer is large enough. * The contents is undefined in case of failure. * @param destCapacity The size of the buffer (number of bytes). If it is 0, then * dest may be NULL and the function will only return the length of the result * without writing any of the result string. * @param src The original string. * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. * @param pErrorCode Must be a valid pointer to an error code value, * which must not indicate a failure before the function call. * @return The length of the result string, if successful - or in case of a buffer overflow, * in which case it will be greater than destCapacity. * * @see u_strFoldCase * @see ucasemap_setOptions * @see U_FOLD_CASE_DEFAULT * @see U_FOLD_CASE_EXCLUDE_SPECIAL_I * @stable ICU 3.8 */ U_DRAFT int32_t U_EXPORT2 ucasemap_utf8FoldCase(const UCaseMap *csm, char *dest, int32_t destCapacity, const char *src, int32_t srcLength, UErrorCode *pErrorCode); #endif