Current Path: > > opt > alt > libicu65 > usr > > include > > unicode
Operation : Linux premium131.web-hosting.com 4.18.0-553.44.1.lve.el8.x86_64 #1 SMP Thu Mar 13 14:29:12 UTC 2025 x86_64 Software : Apache Server IP : 162.0.232.56 | Your IP: 216.73.216.111 Domains : 1034 Domain(s) Permission : [ 0755 ]
Name | Type | Size | Last Modified | Actions |
---|---|---|---|---|
alphaindex.h | File | 27118 bytes | February 08 2022 16:22:58. | |
appendable.h | File | 8694 bytes | February 08 2022 16:22:58. | |
basictz.h | File | 9365 bytes | February 08 2022 16:22:58. | |
brkiter.h | File | 28464 bytes | February 08 2022 16:22:58. | |
bytestream.h | File | 9829 bytes | February 08 2022 16:22:58. | |
bytestrie.h | File | 21266 bytes | February 08 2022 16:22:58. | |
bytestriebuilder.h | File | 7248 bytes | February 08 2022 16:22:58. | |
calendar.h | File | 108278 bytes | February 08 2022 16:22:58. | |
caniter.h | File | 7611 bytes | February 08 2022 16:22:58. | |
casemap.h | File | 25933 bytes | February 08 2022 16:22:58. | |
char16ptr.h | File | 7393 bytes | February 08 2022 16:22:58. | |
chariter.h | File | 24632 bytes | February 08 2022 16:22:58. | |
choicfmt.h | File | 24482 bytes | February 08 2022 16:22:58. | |
coleitr.h | File | 14094 bytes | February 08 2022 16:22:58. | |
coll.h | File | 57581 bytes | February 08 2022 16:22:58. | |
compactdecimalformat.h | File | 7047 bytes | February 08 2022 16:22:58. | |
curramt.h | File | 3851 bytes | February 08 2022 16:22:58. | |
currpinf.h | File | 7473 bytes | February 08 2022 16:22:58. | |
currunit.h | File | 4149 bytes | February 08 2022 16:22:58. | |
datefmt.h | File | 41641 bytes | February 08 2022 16:22:58. | |
dbbi.h | File | 1223 bytes | February 08 2022 16:22:58. | |
dcfmtsym.h | File | 20611 bytes | February 08 2022 16:22:59. | |
decimfmt.h | File | 89480 bytes | February 08 2022 16:22:59. | |
docmain.h | File | 7142 bytes | February 08 2022 16:22:58. | |
dtfmtsym.h | File | 38609 bytes | February 08 2022 16:22:59. | |
dtintrv.h | File | 3930 bytes | February 08 2022 16:22:58. | |
dtitvfmt.h | File | 47745 bytes | February 08 2022 16:22:59. | |
dtitvinf.h | File | 18959 bytes | February 08 2022 16:22:59. | |
dtptngen.h | File | 25684 bytes | February 08 2022 16:22:59. | |
dtrule.h | File | 8888 bytes | February 08 2022 16:22:59. | |
edits.h | File | 21237 bytes | February 08 2022 16:22:58. | |
enumset.h | File | 2130 bytes | February 08 2022 16:22:58. | |
errorcode.h | File | 4956 bytes | February 08 2022 16:22:58. | |
fieldpos.h | File | 8899 bytes | February 08 2022 16:22:59. | |
filteredbrk.h | File | 5501 bytes | February 08 2022 16:22:58. | |
fmtable.h | File | 25007 bytes | February 08 2022 16:22:59. | |
format.h | File | 12802 bytes | February 08 2022 16:22:59. | |
formattedvalue.h | File | 10521 bytes | February 08 2022 16:22:59. | |
fpositer.h | File | 3109 bytes | February 08 2022 16:22:59. | |
gender.h | File | 3408 bytes | February 08 2022 16:22:59. | |
gregocal.h | File | 32472 bytes | February 08 2022 16:22:59. | |
icudataver.h | File | 1051 bytes | February 08 2022 16:22:58. | |
icuplug.h | File | 12166 bytes | February 08 2022 16:22:58. | |
idna.h | File | 13000 bytes | February 08 2022 16:22:58. | |
listformatter.h | File | 9701 bytes | February 08 2022 16:22:59. | |
localebuilder.h | File | 11540 bytes | February 08 2022 16:22:58. | |
localematcher.h | File | 23043 bytes | February 08 2022 16:22:58. | |
localpointer.h | File | 20159 bytes | February 08 2022 16:22:58. | |
locdspnm.h | File | 7292 bytes | February 08 2022 16:22:58. | |
locid.h | File | 48536 bytes | February 08 2022 16:22:58. | |
measfmt.h | File | 11603 bytes | February 08 2022 16:22:59. | |
measunit.h | File | 95554 bytes | February 08 2022 16:22:59. | |
measure.h | File | 4423 bytes | February 08 2022 16:22:59. | |
messagepattern.h | File | 34521 bytes | February 08 2022 16:22:58. | |
msgfmt.h | File | 45168 bytes | February 08 2022 16:22:59. | |
normalizer2.h | File | 34851 bytes | February 08 2022 16:22:58. | |
normlzr.h | File | 31682 bytes | February 08 2022 16:22:58. | |
nounit.h | File | 2754 bytes | February 08 2022 16:22:59. | |
numberformatter.h | File | 88383 bytes | February 08 2022 16:22:59. | |
numberrangeformatter.h | File | 30865 bytes | February 08 2022 16:22:59. | |
numfmt.h | File | 51001 bytes | February 08 2022 16:22:59. | |
numsys.h | File | 7364 bytes | February 08 2022 16:22:59. | |
parseerr.h | File | 3155 bytes | February 08 2022 16:22:58. | |
parsepos.h | File | 5692 bytes | February 08 2022 16:22:58. | |
platform.h | File | 28752 bytes | February 08 2022 16:22:58. | |
plurfmt.h | File | 25800 bytes | February 08 2022 16:22:59. | |
plurrule.h | File | 18835 bytes | February 08 2022 16:22:59. | |
ptypes.h | File | 3577 bytes | February 08 2022 16:22:58. | |
putil.h | File | 6487 bytes | February 08 2022 16:22:58. | |
rbbi.h | File | 27218 bytes | February 08 2022 16:22:58. | |
rbnf.h | File | 49899 bytes | February 08 2022 16:22:59. | |
rbtz.h | File | 15979 bytes | February 08 2022 16:22:59. | |
regex.h | File | 86382 bytes | February 08 2022 16:22:59. | |
region.h | File | 9404 bytes | February 08 2022 16:22:59. | |
reldatefmt.h | File | 23159 bytes | February 08 2022 16:22:59. | |
rep.h | File | 9599 bytes | February 08 2022 16:22:58. | |
resbund.h | File | 18503 bytes | February 08 2022 16:22:58. | |
schriter.h | File | 6475 bytes | February 08 2022 16:22:58. | |
scientificnumberformatter.h | File | 6553 bytes | February 08 2022 16:22:59. | |
search.h | File | 22757 bytes | February 08 2022 16:22:59. | |
selfmt.h | File | 14643 bytes | February 08 2022 16:22:59. | |
simpleformatter.h | File | 12888 bytes | February 08 2022 16:22:58. | |
simpletz.h | File | 46527 bytes | February 08 2022 16:22:59. | |
smpdtfmt.h | File | 72670 bytes | February 08 2022 16:22:59. | |
sortkey.h | File | 11444 bytes | February 08 2022 16:22:59. | |
std_string.h | File | 1076 bytes | February 08 2022 16:22:58. | |
strenum.h | File | 10158 bytes | February 08 2022 16:22:58. | |
stringoptions.h | File | 5926 bytes | February 08 2022 16:22:58. | |
stringpiece.h | File | 7556 bytes | February 08 2022 16:22:58. | |
stringtriebuilder.h | File | 15698 bytes | February 08 2022 16:22:58. | |
stsearch.h | File | 21810 bytes | February 08 2022 16:22:59. | |
symtable.h | File | 4374 bytes | February 08 2022 16:22:58. | |
tblcoll.h | File | 37489 bytes | February 08 2022 16:22:59. | |
timezone.h | File | 42005 bytes | February 08 2022 16:22:59. | |
tmunit.h | File | 3461 bytes | February 08 2022 16:22:59. | |
tmutamt.h | File | 5015 bytes | February 08 2022 16:22:59. | |
tmutfmt.h | File | 8042 bytes | February 08 2022 16:22:59. | |
translit.h | File | 67400 bytes | February 08 2022 16:22:59. | |
tzfmt.h | File | 43916 bytes | February 08 2022 16:22:59. | |
tznames.h | File | 17252 bytes | February 08 2022 16:22:59. | |
tzrule.h | File | 36215 bytes | February 08 2022 16:22:59. | |
tztrans.h | File | 6271 bytes | February 08 2022 16:22:59. | |
ubidi.h | File | 91711 bytes | February 08 2022 16:22:58. | |
ubiditransform.h | File | 12950 bytes | February 08 2022 16:22:58. | |
ubrk.h | File | 24547 bytes | February 08 2022 16:22:58. | |
ucal.h | File | 58265 bytes | February 08 2022 16:22:59. | |
ucasemap.h | File | 15546 bytes | February 08 2022 16:22:58. | |
ucat.h | File | 5484 bytes | February 08 2022 16:22:58. | |
uchar.h | File | 143936 bytes | February 08 2022 16:22:58. | |
ucharstrie.h | File | 23120 bytes | February 08 2022 16:22:58. | |
ucharstriebuilder.h | File | 7378 bytes | February 08 2022 16:22:58. | |
uchriter.h | File | 13521 bytes | February 08 2022 16:22:58. | |
uclean.h | File | 11474 bytes | February 08 2022 16:22:58. | |
ucnv.h | File | 85085 bytes | February 08 2022 16:22:58. | |
ucnv_cb.h | File | 6748 bytes | February 08 2022 16:22:58. | |
ucnv_err.h | File | 21492 bytes | February 08 2022 16:22:58. | |
ucnvsel.h | File | 6283 bytes | February 08 2022 16:22:58. | |
ucol.h | File | 62939 bytes | February 08 2022 16:22:59. | |
ucoleitr.h | File | 9684 bytes | February 08 2022 16:22:59. | |
uconfig.h | File | 12356 bytes | February 08 2022 16:22:58. | |
ucpmap.h | File | 5663 bytes | February 08 2022 16:22:58. | |
ucptrie.h | File | 23002 bytes | February 08 2022 16:22:58. | |
ucsdet.h | File | 15018 bytes | February 08 2022 16:22:59. | |
ucurr.h | File | 16507 bytes | February 08 2022 16:22:58. | |
udat.h | File | 62342 bytes | February 08 2022 16:22:59. | |
udata.h | File | 15930 bytes | February 08 2022 16:22:58. | |
udateintervalformat.h | File | 10272 bytes | February 08 2022 16:22:59. | |
udatpg.h | File | 26639 bytes | February 08 2022 16:22:59. | |
udisplaycontext.h | File | 6029 bytes | February 08 2022 16:22:58. | |
uenum.h | File | 7970 bytes | February 08 2022 16:22:58. | |
ufieldpositer.h | File | 4461 bytes | February 08 2022 16:22:59. | |
uformattable.h | File | 11198 bytes | February 08 2022 16:22:59. | |
uformattedvalue.h | File | 12431 bytes | February 08 2022 16:22:59. | |
ugender.h | File | 2052 bytes | February 08 2022 16:22:59. | |
uidna.h | File | 34169 bytes | February 08 2022 16:22:58. | |
uiter.h | File | 23319 bytes | February 08 2022 16:22:58. | |
uldnames.h | File | 10702 bytes | February 08 2022 16:22:58. | |
ulistformatter.h | File | 9047 bytes | February 08 2022 16:22:59. | |
uloc.h | File | 53805 bytes | February 08 2022 16:22:58. | |
ulocdata.h | File | 11533 bytes | February 08 2022 16:22:59. | |
umachine.h | File | 14877 bytes | February 08 2022 16:22:58. | |
umisc.h | File | 1365 bytes | February 08 2022 16:22:58. | |
umsg.h | File | 24812 bytes | February 08 2022 16:22:59. | |
umutablecptrie.h | File | 8435 bytes | February 08 2022 16:22:58. | |
unifilt.h | File | 4055 bytes | February 08 2022 16:22:58. | |
unifunct.h | File | 4141 bytes | February 08 2022 16:22:58. | |
unimatch.h | File | 6244 bytes | February 08 2022 16:22:58. | |
unirepl.h | File | 3464 bytes | February 08 2022 16:22:59. | |
uniset.h | File | 66459 bytes | February 08 2022 16:22:58. | |
unistr.h | File | 174523 bytes | February 08 2022 16:22:58. | |
unorm.h | File | 21015 bytes | February 08 2022 16:22:58. | |
unorm2.h | File | 25254 bytes | February 08 2022 16:22:58. | |
unum.h | File | 54906 bytes | February 08 2022 16:22:59. | |
unumberformatter.h | File | 25972 bytes | February 08 2022 16:22:59. | |
unumsys.h | File | 7387 bytes | February 08 2022 16:22:59. | |
uobject.h | File | 10936 bytes | February 08 2022 16:22:58. | |
upluralrules.h | File | 8068 bytes | February 08 2022 16:22:59. | |
uregex.h | File | 73784 bytes | February 08 2022 16:22:59. | |
uregion.h | File | 10073 bytes | February 08 2022 16:22:59. | |
ureldatefmt.h | File | 17670 bytes | February 08 2022 16:22:59. | |
urename.h | File | 134109 bytes | February 08 2022 16:22:58. | |
urep.h | File | 5507 bytes | February 08 2022 16:22:58. | |
ures.h | File | 37415 bytes | February 08 2022 16:22:58. | |
uscript.h | File | 27510 bytes | February 08 2022 16:22:58. | |
usearch.h | File | 39039 bytes | February 08 2022 16:22:59. | |
uset.h | File | 40958 bytes | February 08 2022 16:22:58. | |
usetiter.h | File | 9781 bytes | February 08 2022 16:22:58. | |
ushape.h | File | 18432 bytes | February 08 2022 16:22:58. | |
uspoof.h | File | 67480 bytes | February 08 2022 16:22:59. | |
usprep.h | File | 8331 bytes | February 08 2022 16:22:58. | |
ustdio.h | File | 39469 bytes | February 08 2022 16:22:59. | |
ustream.h | File | 1934 bytes | February 08 2022 16:22:59. | |
ustring.h | File | 74211 bytes | February 08 2022 16:22:58. | |
ustringtrie.h | File | 3224 bytes | February 08 2022 16:22:58. | |
utext.h | File | 59527 bytes | February 08 2022 16:22:58. | |
utf.h | File | 8046 bytes | February 08 2022 16:22:58. | |
utf16.h | File | 23878 bytes | February 08 2022 16:22:58. | |
utf32.h | File | 763 bytes | February 08 2022 16:22:58. | |
utf8.h | File | 31700 bytes | February 08 2022 16:22:58. | |
utf_old.h | File | 46929 bytes | February 08 2022 16:22:58. | |
utmscale.h | File | 14113 bytes | February 08 2022 16:22:59. | |
utrace.h | File | 16112 bytes | February 08 2022 16:22:58. | |
utrans.h | File | 26130 bytes | February 08 2022 16:22:59. | |
utypes.h | File | 31481 bytes | February 08 2022 16:22:58. | |
uvernum.h | File | 6832 bytes | February 08 2022 16:22:58. | |
uversion.h | File | 6145 bytes | February 08 2022 16:22:58. | |
vtzone.h | File | 20784 bytes | February 08 2022 16:22:59. |
// © 2016 and later: Unicode, Inc. and others. // License & terms of use: http://www.unicode.org/copyright.html /* ******************************************************************************* * * Copyright (C) 2009-2015, International Business Machines * Corporation and others. All Rights Reserved. * ******************************************************************************* * file name: unorm2.h * encoding: UTF-8 * tab size: 8 (not used) * indentation:4 * * created on: 2009dec15 * created by: Markus W. Scherer */ #ifndef __UNORM2_H__ #define __UNORM2_H__ /** * \file * \brief C API: New API for Unicode Normalization. * * Unicode normalization functionality for standard Unicode normalization or * for using custom mapping tables. * All instances of UNormalizer2 are unmodifiable/immutable. * Instances returned by unorm2_getInstance() are singletons that must not be deleted by the caller. * For more details see the Normalizer2 C++ class. */ #include "unicode/utypes.h" #include "unicode/localpointer.h" #include "unicode/stringoptions.h" #include "unicode/uset.h" /** * Constants for normalization modes. * For details about standard Unicode normalization forms * and about the algorithms which are also used with custom mapping tables * see http://www.unicode.org/unicode/reports/tr15/ * @stable ICU 4.4 */ typedef enum { /** * Decomposition followed by composition. * Same as standard NFC when using an "nfc" instance. * Same as standard NFKC when using an "nfkc" instance. * For details about standard Unicode normalization forms * see http://www.unicode.org/unicode/reports/tr15/ * @stable ICU 4.4 */ UNORM2_COMPOSE, /** * Map, and reorder canonically. * Same as standard NFD when using an "nfc" instance. * Same as standard NFKD when using an "nfkc" instance. * For details about standard Unicode normalization forms * see http://www.unicode.org/unicode/reports/tr15/ * @stable ICU 4.4 */ UNORM2_DECOMPOSE, /** * "Fast C or D" form. * If a string is in this form, then further decomposition <i>without reordering</i> * would yield the same form as DECOMPOSE. * Text in "Fast C or D" form can be processed efficiently with data tables * that are "canonically closed", that is, that provide equivalent data for * equivalent text, without having to be fully normalized. * Not a standard Unicode normalization form. * Not a unique form: Different FCD strings can be canonically equivalent. * For details see http://www.unicode.org/notes/tn5/#FCD * @stable ICU 4.4 */ UNORM2_FCD, /** * Compose only contiguously. * Also known as "FCC" or "Fast C Contiguous". * The result will often but not always be in NFC. * The result will conform to FCD which is useful for processing. * Not a standard Unicode normalization form. * For details see http://www.unicode.org/notes/tn5/#FCC * @stable ICU 4.4 */ UNORM2_COMPOSE_CONTIGUOUS } UNormalization2Mode; /** * Result values for normalization quick check functions. * For details see http://www.unicode.org/reports/tr15/#Detecting_Normalization_Forms * @stable ICU 2.0 */ typedef enum UNormalizationCheckResult { /** * The input string is not in the normalization form. * @stable ICU 2.0 */ UNORM_NO, /** * The input string is in the normalization form. * @stable ICU 2.0 */ UNORM_YES, /** * The input string may or may not be in the normalization form. * This value is only returned for composition forms like NFC and FCC, * when a backward-combining character is found for which the surrounding text * would have to be analyzed further. * @stable ICU 2.0 */ UNORM_MAYBE } UNormalizationCheckResult; /** * Opaque C service object type for the new normalization API. * @stable ICU 4.4 */ struct UNormalizer2; typedef struct UNormalizer2 UNormalizer2; /**< C typedef for struct UNormalizer2. @stable ICU 4.4 */ #if !UCONFIG_NO_NORMALIZATION /** * Returns a UNormalizer2 instance for Unicode NFC normalization. * Same as unorm2_getInstance(NULL, "nfc", UNORM2_COMPOSE, pErrorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested Normalizer2, if successful * @stable ICU 49 */ U_STABLE const UNormalizer2 * U_EXPORT2 unorm2_getNFCInstance(UErrorCode *pErrorCode); /** * Returns a UNormalizer2 instance for Unicode NFD normalization. * Same as unorm2_getInstance(NULL, "nfc", UNORM2_DECOMPOSE, pErrorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested Normalizer2, if successful * @stable ICU 49 */ U_STABLE const UNormalizer2 * U_EXPORT2 unorm2_getNFDInstance(UErrorCode *pErrorCode); /** * Returns a UNormalizer2 instance for Unicode NFKC normalization. * Same as unorm2_getInstance(NULL, "nfkc", UNORM2_COMPOSE, pErrorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested Normalizer2, if successful * @stable ICU 49 */ U_STABLE const UNormalizer2 * U_EXPORT2 unorm2_getNFKCInstance(UErrorCode *pErrorCode); /** * Returns a UNormalizer2 instance for Unicode NFKD normalization. * Same as unorm2_getInstance(NULL, "nfkc", UNORM2_DECOMPOSE, pErrorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested Normalizer2, if successful * @stable ICU 49 */ U_STABLE const UNormalizer2 * U_EXPORT2 unorm2_getNFKDInstance(UErrorCode *pErrorCode); /** * Returns a UNormalizer2 instance for Unicode NFKC_Casefold normalization. * Same as unorm2_getInstance(NULL, "nfkc_cf", UNORM2_COMPOSE, pErrorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested Normalizer2, if successful * @stable ICU 49 */ U_STABLE const UNormalizer2 * U_EXPORT2 unorm2_getNFKCCasefoldInstance(UErrorCode *pErrorCode); /** * Returns a UNormalizer2 instance which uses the specified data file * (packageName/name similar to ucnv_openPackage() and ures_open()/ResourceBundle) * and which composes or decomposes text according to the specified mode. * Returns an unmodifiable singleton instance. Do not delete it. * * Use packageName=NULL for data files that are part of ICU's own data. * Use name="nfc" and UNORM2_COMPOSE/UNORM2_DECOMPOSE for Unicode standard NFC/NFD. * Use name="nfkc" and UNORM2_COMPOSE/UNORM2_DECOMPOSE for Unicode standard NFKC/NFKD. * Use name="nfkc_cf" and UNORM2_COMPOSE for Unicode standard NFKC_CF=NFKC_Casefold. * * @param packageName NULL for ICU built-in data, otherwise application data package name * @param name "nfc" or "nfkc" or "nfkc_cf" or name of custom data file * @param mode normalization mode (compose or decompose etc.) * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested UNormalizer2, if successful * @stable ICU 4.4 */ U_STABLE const UNormalizer2 * U_EXPORT2 unorm2_getInstance(const char *packageName, const char *name, UNormalization2Mode mode, UErrorCode *pErrorCode); /** * Constructs a filtered normalizer wrapping any UNormalizer2 instance * and a filter set. * Both are aliased and must not be modified or deleted while this object * is used. * The filter set should be frozen; otherwise the performance will suffer greatly. * @param norm2 wrapped UNormalizer2 instance * @param filterSet USet which determines the characters to be normalized * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested UNormalizer2, if successful * @stable ICU 4.4 */ U_STABLE UNormalizer2 * U_EXPORT2 unorm2_openFiltered(const UNormalizer2 *norm2, const USet *filterSet, UErrorCode *pErrorCode); /** * Closes a UNormalizer2 instance from unorm2_openFiltered(). * Do not close instances from unorm2_getInstance()! * @param norm2 UNormalizer2 instance to be closed * @stable ICU 4.4 */ U_STABLE void U_EXPORT2 unorm2_close(UNormalizer2 *norm2); #if U_SHOW_CPLUSPLUS_API U_NAMESPACE_BEGIN /** * \class LocalUNormalizer2Pointer * "Smart pointer" class, closes a UNormalizer2 via unorm2_close(). * For most methods see the LocalPointerBase base class. * * @see LocalPointerBase * @see LocalPointer * @stable ICU 4.4 */ U_DEFINE_LOCAL_OPEN_POINTER(LocalUNormalizer2Pointer, UNormalizer2, unorm2_close); U_NAMESPACE_END #endif /** * Writes the normalized form of the source string to the destination string * (replacing its contents) and returns the length of the destination string. * The source and destination strings must be different buffers. * @param norm2 UNormalizer2 instance * @param src source string * @param length length of the source string, or -1 if NUL-terminated * @param dest destination string; its contents is replaced with normalized src * @param capacity number of UChars that can be written to dest * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return dest * @stable ICU 4.4 */ U_STABLE int32_t U_EXPORT2 unorm2_normalize(const UNormalizer2 *norm2, const UChar *src, int32_t length, UChar *dest, int32_t capacity, UErrorCode *pErrorCode); /** * Appends the normalized form of the second string to the first string * (merging them at the boundary) and returns the length of the first string. * The result is normalized if the first string was normalized. * The first and second strings must be different buffers. * @param norm2 UNormalizer2 instance * @param first string, should be normalized * @param firstLength length of the first string, or -1 if NUL-terminated * @param firstCapacity number of UChars that can be written to first * @param second string, will be normalized * @param secondLength length of the source string, or -1 if NUL-terminated * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return first * @stable ICU 4.4 */ U_STABLE int32_t U_EXPORT2 unorm2_normalizeSecondAndAppend(const UNormalizer2 *norm2, UChar *first, int32_t firstLength, int32_t firstCapacity, const UChar *second, int32_t secondLength, UErrorCode *pErrorCode); /** * Appends the second string to the first string * (merging them at the boundary) and returns the length of the first string. * The result is normalized if both the strings were normalized. * The first and second strings must be different buffers. * @param norm2 UNormalizer2 instance * @param first string, should be normalized * @param firstLength length of the first string, or -1 if NUL-terminated * @param firstCapacity number of UChars that can be written to first * @param second string, should be normalized * @param secondLength length of the source string, or -1 if NUL-terminated * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return first * @stable ICU 4.4 */ U_STABLE int32_t U_EXPORT2 unorm2_append(const UNormalizer2 *norm2, UChar *first, int32_t firstLength, int32_t firstCapacity, const UChar *second, int32_t secondLength, UErrorCode *pErrorCode); /** * Gets the decomposition mapping of c. * Roughly equivalent to normalizing the String form of c * on a UNORM2_DECOMPOSE UNormalizer2 instance, but much faster, and except that this function * returns a negative value and does not write a string * if c does not have a decomposition mapping in this instance's data. * This function is independent of the mode of the UNormalizer2. * @param norm2 UNormalizer2 instance * @param c code point * @param decomposition String buffer which will be set to c's * decomposition mapping, if there is one. * @param capacity number of UChars that can be written to decomposition * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the non-negative length of c's decomposition, if there is one; otherwise a negative value * @stable ICU 4.6 */ U_STABLE int32_t U_EXPORT2 unorm2_getDecomposition(const UNormalizer2 *norm2, UChar32 c, UChar *decomposition, int32_t capacity, UErrorCode *pErrorCode); /** * Gets the raw decomposition mapping of c. * * This is similar to the unorm2_getDecomposition() function but returns the * raw decomposition mapping as specified in UnicodeData.txt or * (for custom data) in the mapping files processed by the gennorm2 tool. * By contrast, unorm2_getDecomposition() returns the processed, * recursively-decomposed version of this mapping. * * When used on a standard NFKC Normalizer2 instance, * unorm2_getRawDecomposition() returns the Unicode Decomposition_Mapping (dm) property. * * When used on a standard NFC Normalizer2 instance, * it returns the Decomposition_Mapping only if the Decomposition_Type (dt) is Canonical (Can); * in this case, the result contains either one or two code points (=1..4 UChars). * * This function is independent of the mode of the UNormalizer2. * @param norm2 UNormalizer2 instance * @param c code point * @param decomposition String buffer which will be set to c's * raw decomposition mapping, if there is one. * @param capacity number of UChars that can be written to decomposition * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the non-negative length of c's raw decomposition, if there is one; otherwise a negative value * @stable ICU 49 */ U_STABLE int32_t U_EXPORT2 unorm2_getRawDecomposition(const UNormalizer2 *norm2, UChar32 c, UChar *decomposition, int32_t capacity, UErrorCode *pErrorCode); /** * Performs pairwise composition of a & b and returns the composite if there is one. * * Returns a composite code point c only if c has a two-way mapping to a+b. * In standard Unicode normalization, this means that * c has a canonical decomposition to a+b * and c does not have the Full_Composition_Exclusion property. * * This function is independent of the mode of the UNormalizer2. * @param norm2 UNormalizer2 instance * @param a A (normalization starter) code point. * @param b Another code point. * @return The non-negative composite code point if there is one; otherwise a negative value. * @stable ICU 49 */ U_STABLE UChar32 U_EXPORT2 unorm2_composePair(const UNormalizer2 *norm2, UChar32 a, UChar32 b); /** * Gets the combining class of c. * The default implementation returns 0 * but all standard implementations return the Unicode Canonical_Combining_Class value. * @param norm2 UNormalizer2 instance * @param c code point * @return c's combining class * @stable ICU 49 */ U_STABLE uint8_t U_EXPORT2 unorm2_getCombiningClass(const UNormalizer2 *norm2, UChar32 c); /** * Tests if the string is normalized. * Internally, in cases where the quickCheck() method would return "maybe" * (which is only possible for the two COMPOSE modes) this method * resolves to "yes" or "no" to provide a definitive result, * at the cost of doing more work in those cases. * @param norm2 UNormalizer2 instance * @param s input string * @param length length of the string, or -1 if NUL-terminated * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return TRUE if s is normalized * @stable ICU 4.4 */ U_STABLE UBool U_EXPORT2 unorm2_isNormalized(const UNormalizer2 *norm2, const UChar *s, int32_t length, UErrorCode *pErrorCode); /** * Tests if the string is normalized. * For the two COMPOSE modes, the result could be "maybe" in cases that * would take a little more work to resolve definitively. * Use spanQuickCheckYes() and normalizeSecondAndAppend() for a faster * combination of quick check + normalization, to avoid * re-checking the "yes" prefix. * @param norm2 UNormalizer2 instance * @param s input string * @param length length of the string, or -1 if NUL-terminated * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return UNormalizationCheckResult * @stable ICU 4.4 */ U_STABLE UNormalizationCheckResult U_EXPORT2 unorm2_quickCheck(const UNormalizer2 *norm2, const UChar *s, int32_t length, UErrorCode *pErrorCode); /** * Returns the end of the normalized substring of the input string. * In other words, with <code>end=spanQuickCheckYes(s, ec);</code> * the substring <code>UnicodeString(s, 0, end)</code> * will pass the quick check with a "yes" result. * * The returned end index is usually one or more characters before the * "no" or "maybe" character: The end index is at a normalization boundary. * (See the class documentation for more about normalization boundaries.) * * When the goal is a normalized string and most input strings are expected * to be normalized already, then call this method, * and if it returns a prefix shorter than the input string, * copy that prefix and use normalizeSecondAndAppend() for the remainder. * @param norm2 UNormalizer2 instance * @param s input string * @param length length of the string, or -1 if NUL-terminated * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return "yes" span end index * @stable ICU 4.4 */ U_STABLE int32_t U_EXPORT2 unorm2_spanQuickCheckYes(const UNormalizer2 *norm2, const UChar *s, int32_t length, UErrorCode *pErrorCode); /** * Tests if the character always has a normalization boundary before it, * regardless of context. * For details see the Normalizer2 base class documentation. * @param norm2 UNormalizer2 instance * @param c character to test * @return TRUE if c has a normalization boundary before it * @stable ICU 4.4 */ U_STABLE UBool U_EXPORT2 unorm2_hasBoundaryBefore(const UNormalizer2 *norm2, UChar32 c); /** * Tests if the character always has a normalization boundary after it, * regardless of context. * For details see the Normalizer2 base class documentation. * @param norm2 UNormalizer2 instance * @param c character to test * @return TRUE if c has a normalization boundary after it * @stable ICU 4.4 */ U_STABLE UBool U_EXPORT2 unorm2_hasBoundaryAfter(const UNormalizer2 *norm2, UChar32 c); /** * Tests if the character is normalization-inert. * For details see the Normalizer2 base class documentation. * @param norm2 UNormalizer2 instance * @param c character to test * @return TRUE if c is normalization-inert * @stable ICU 4.4 */ U_STABLE UBool U_EXPORT2 unorm2_isInert(const UNormalizer2 *norm2, UChar32 c); /** * Compares two strings for canonical equivalence. * Further options include case-insensitive comparison and * code point order (as opposed to code unit order). * * Canonical equivalence between two strings is defined as their normalized * forms (NFD or NFC) being identical. * This function compares strings incrementally instead of normalizing * (and optionally case-folding) both strings entirely, * improving performance significantly. * * Bulk normalization is only necessary if the strings do not fulfill the FCD * conditions. Only in this case, and only if the strings are relatively long, * is memory allocated temporarily. * For FCD strings and short non-FCD strings there is no memory allocation. * * Semantically, this is equivalent to * strcmp[CodePointOrder](NFD(foldCase(NFD(s1))), NFD(foldCase(NFD(s2)))) * where code point order and foldCase are all optional. * * UAX 21 2.5 Caseless Matching specifies that for a canonical caseless match * the case folding must be performed first, then the normalization. * * @param s1 First source string. * @param length1 Length of first source string, or -1 if NUL-terminated. * * @param s2 Second source string. * @param length2 Length of second source string, or -1 if NUL-terminated. * * @param options A bit set of options: * - U_FOLD_CASE_DEFAULT or 0 is used for default options: * Case-sensitive comparison in code unit order, and the input strings * are quick-checked for FCD. * * - UNORM_INPUT_IS_FCD * Set if the caller knows that both s1 and s2 fulfill the FCD conditions. * If not set, the function will quickCheck for FCD * and normalize if necessary. * * - U_COMPARE_CODE_POINT_ORDER * Set to choose code point order instead of code unit order * (see u_strCompare for details). * * - U_COMPARE_IGNORE_CASE * Set to compare strings case-insensitively using case folding, * instead of case-sensitively. * If set, then the following case folding options are used. * * - Options as used with case-insensitive comparisons, currently: * * - U_FOLD_CASE_EXCLUDE_SPECIAL_I * (see u_strCaseCompare for details) * * - regular normalization options shifted left by UNORM_COMPARE_NORM_OPTIONS_SHIFT * * @param pErrorCode ICU error code in/out parameter. * Must fulfill U_SUCCESS before the function call. * @return <0 or 0 or >0 as usual for string comparisons * * @see unorm_normalize * @see UNORM_FCD * @see u_strCompare * @see u_strCaseCompare * * @stable ICU 2.2 */ U_STABLE int32_t U_EXPORT2 unorm_compare(const UChar *s1, int32_t length1, const UChar *s2, int32_t length2, uint32_t options, UErrorCode *pErrorCode); #endif /* !UCONFIG_NO_NORMALIZATION */ #endif /* __UNORM2_H__ */
SILENT KILLER Tool