OXIESEC PANEL
- Current Dir:
/
/
usr
/
include
/
unicode
Server IP: 139.59.38.164
Upload:
Create Dir:
Name
Size
Modified
Perms
📁
..
-
10/28/2024 06:50:42 AM
rwxr-xr-x
📄
alphaindex.h
26.27 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
appendable.h
8.43 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
basictz.h
8.84 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
brkiter.h
27.54 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
bytestream.h
9.59 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
bytestrie.h
19.26 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
bytestriebuilder.h
7.1 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
calendar.h
105.35 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
caniter.h
7.35 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
casemap.h
25.31 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
char16ptr.h
7.29 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
chariter.h
24 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
choicfmt.h
23.85 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
coleitr.h
13.7 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
coll.h
55.61 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
compactdecimalformat.h
16.58 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
curramt.h
3.69 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
currpinf.h
7.08 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
currunit.h
3.49 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
datefmt.h
40.18 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
dbbi.h
1.11 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
dcfmtsym.h
17.66 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
decimfmt.h
89.73 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
docmain.h
6.56 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
dtfmtsym.h
37.64 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
dtintrv.h
3.76 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
dtitvfmt.h
42.87 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
dtitvinf.h
18.46 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
dtptngen.h
23.72 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
dtrule.h
8.62 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
edits.h
15.54 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
enumset.h
2.05 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
errorcode.h
4.78 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
fieldpos.h
8.63 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
filteredbrk.h
5.46 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
fmtable.h
24.39 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
format.h
12.44 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
fpositer.h
3.14 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
gender.h
3.18 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
gregocal.h
31.57 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
icudataver.h
1.03 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
icuplug.h
11.86 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
idna.h
12.63 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
listformatter.h
4.98 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
localpointer.h
18.19 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
locdspnm.h
7.05 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
locid.h
31.4 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
measfmt.h
11.25 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
measunit.h
37.74 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
measure.h
4.26 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
messagepattern.h
33.64 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
msgfmt.h
43.16 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
normalizer2.h
33.97 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
normlzr.h
30.74 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
nounit.h
2.6 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
numberformatter.h
64.98 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
numfmt.h
47.76 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
numsys.h
6.73 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
parseerr.h
3.08 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
parsepos.h
5.45 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
platform.h
27.71 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
plurfmt.h
25.66 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
plurrule.h
18.34 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ptypes.h
3.47 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
putil.h
6.34 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
rbbi.h
27.09 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
rbnf.h
49.76 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
rbtz.h
15.47 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
regex.h
84.91 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
region.h
9.12 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
reldatefmt.h
14.3 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
rep.h
9.5 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
resbund.h
18.01 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
schriter.h
6.26 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
scientificnumberformatter.h
6.59 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
search.h
22.21 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
selfmt.h
14.24 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
simpleformatter.h
11.43 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
simpletz.h
45.24 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
smpdtfmt.h
70.09 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
sortkey.h
11.12 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
std_string.h
1015 bytes
10/19/2021 07:44:28 PM
rw-r--r--
📄
strenum.h
10.04 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
stringoptions.h
5.89 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
stringpiece.h
6.46 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
stringtriebuilder.h
15.2 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
stsearch.h
21.29 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
symtable.h
4.21 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
tblcoll.h
36.4 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
timezone.h
40.83 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
tmunit.h
3.29 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
tmutamt.h
4.8 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
tmutfmt.h
7.79 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
translit.h
54.53 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
tzfmt.h
42.81 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
tznames.h
16.79 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
tzrule.h
35.32 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
tztrans.h
6.07 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ubidi.h
89.28 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ubiditransform.h
12.71 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ubrk.h
24.08 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ucal.h
54.56 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ucasemap.h
15.18 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ucat.h
5.36 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uchar.h
131.61 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ucharstrie.h
21.06 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ucharstriebuilder.h
7.14 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uchriter.h
13.14 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uclean.h
11.24 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ucnv.h
83.06 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ucnv_cb.h
6.59 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ucnv_err.h
20.98 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ucnvsel.h
6.14 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ucol.h
61.36 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ucoleitr.h
9.46 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uconfig.h
11.91 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ucsdet.h
14.67 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ucurr.h
15.15 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
udat.h
60.13 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
udata.h
15.53 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
udateintervalformat.h
6.79 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
udatpg.h
24.11 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
udisplaycontext.h
5.89 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uenum.h
7.9 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ufieldpositer.h
4.36 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uformattable.h
10.94 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ugender.h
2 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uidna.h
33.37 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uiter.h
22.77 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uldnames.h
10.45 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ulistformatter.h
4.54 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uloc.h
50.75 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ulocdata.h
11.26 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
umachine.h
13.1 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
umisc.h
1.33 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
umsg.h
24.23 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
unifilt.h
3.63 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
unifunct.h
3.98 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
unimatch.h
6.04 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
unirepl.h
3.32 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uniset.h
63.98 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
unistr.h
175.65 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
unorm.h
20.45 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
unorm2.h
24.66 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
unum.h
52.49 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
unumsys.h
7.14 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uobject.h
10.72 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
upluralrules.h
6.77 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uregex.h
72.05 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uregion.h
9.84 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ureldatefmt.h
12.22 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
urename.h
124.49 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
urep.h
5.38 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ures.h
36.52 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uscript.h
25.91 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
usearch.h
38.14 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uset.h
39.91 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
usetiter.h
9.49 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ushape.h
18 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uspoof.h
64.9 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
usprep.h
8.13 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ustdio.h
38.54 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ustream.h
1.8 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ustring.h
72.52 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
ustringtrie.h
3.15 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
utext.h
58.11 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
utf.h
7.86 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
utf16.h
22.49 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
utf32.h
763 bytes
10/19/2021 07:44:28 PM
rw-r--r--
📄
utf8.h
28.16 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
utf_old.h
43.78 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
utmscale.h
13.78 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
utrace.h
13.89 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
utrans.h
25.53 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
utypes.h
29.92 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uvernum.h
5.69 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
uversion.h
6.4 KB
10/19/2021 07:44:28 PM
rw-r--r--
📄
vtzone.h
20.17 KB
10/19/2021 07:44:28 PM
rw-r--r--
Editing: normalizer2.h
Close
// © 2016 and later: Unicode, Inc. and others. // License & terms of use: http://www.unicode.org/copyright.html /* ******************************************************************************* * * Copyright (C) 2009-2013, International Business Machines * Corporation and others. All Rights Reserved. * ******************************************************************************* * file name: normalizer2.h * encoding: UTF-8 * tab size: 8 (not used) * indentation:4 * * created on: 2009nov22 * created by: Markus W. Scherer */ #ifndef __NORMALIZER2_H__ #define __NORMALIZER2_H__ /** * \file * \brief C++ API: New API for Unicode Normalization. */ #include "unicode/utypes.h" #if !UCONFIG_NO_NORMALIZATION #include "unicode/stringpiece.h" #include "unicode/uniset.h" #include "unicode/unistr.h" #include "unicode/unorm2.h" U_NAMESPACE_BEGIN class ByteSink; /** * Unicode normalization functionality for standard Unicode normalization or * for using custom mapping tables. * All instances of this class are unmodifiable/immutable. * Instances returned by getInstance() are singletons that must not be deleted by the caller. * The Normalizer2 class is not intended for public subclassing. * * The primary functions are to produce a normalized string and to detect whether * a string is already normalized. * The most commonly used normalization forms are those defined in * http://www.unicode.org/unicode/reports/tr15/ * However, this API supports additional normalization forms for specialized purposes. * For example, NFKC_Casefold is provided via getInstance("nfkc_cf", COMPOSE) * and can be used in implementations of UTS #46. * * Not only are the standard compose and decompose modes supplied, * but additional modes are provided as documented in the Mode enum. * * Some of the functions in this class identify normalization boundaries. * At a normalization boundary, the portions of the string * before it and starting from it do not interact and can be handled independently. * * The spanQuickCheckYes() stops at a normalization boundary. * When the goal is a normalized string, then the text before the boundary * can be copied, and the remainder can be processed with normalizeSecondAndAppend(). * * The hasBoundaryBefore(), hasBoundaryAfter() and isInert() functions test whether * a character is guaranteed to be at a normalization boundary, * regardless of context. * This is used for moving from one normalization boundary to the next * or preceding boundary, and for performing iterative normalization. * * Iterative normalization is useful when only a small portion of a * longer string needs to be processed. * For example, in ICU, iterative normalization is used by the NormalizationTransliterator * (to avoid replacing already-normalized text) and ucol_nextSortKeyPart() * (to process only the substring for which sort key bytes are computed). * * The set of normalization boundaries returned by these functions may not be * complete: There may be more boundaries that could be returned. * Different functions may return different boundaries. * @stable ICU 4.4 */ class U_COMMON_API Normalizer2 : public UObject { public: /** * Destructor. * @stable ICU 4.4 */ ~Normalizer2(); /** * Returns a Normalizer2 instance for Unicode NFC normalization. * Same as getInstance(NULL, "nfc", UNORM2_COMPOSE, errorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param errorCode 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 */ static const Normalizer2 * getNFCInstance(UErrorCode &errorCode); /** * Returns a Normalizer2 instance for Unicode NFD normalization. * Same as getInstance(NULL, "nfc", UNORM2_DECOMPOSE, errorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param errorCode 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 */ static const Normalizer2 * getNFDInstance(UErrorCode &errorCode); /** * Returns a Normalizer2 instance for Unicode NFKC normalization. * Same as getInstance(NULL, "nfkc", UNORM2_COMPOSE, errorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param errorCode 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 */ static const Normalizer2 * getNFKCInstance(UErrorCode &errorCode); /** * Returns a Normalizer2 instance for Unicode NFKD normalization. * Same as getInstance(NULL, "nfkc", UNORM2_DECOMPOSE, errorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param errorCode 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 */ static const Normalizer2 * getNFKDInstance(UErrorCode &errorCode); /** * Returns a Normalizer2 instance for Unicode NFKC_Casefold normalization. * Same as getInstance(NULL, "nfkc_cf", UNORM2_COMPOSE, errorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param errorCode 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 */ static const Normalizer2 * getNFKCCasefoldInstance(UErrorCode &errorCode); /** * Returns a Normalizer2 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 errorCode 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 4.4 */ static const Normalizer2 * getInstance(const char *packageName, const char *name, UNormalization2Mode mode, UErrorCode &errorCode); /** * Returns the normalized form of the source string. * @param src source string * @param errorCode 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 normalized src * @stable ICU 4.4 */ UnicodeString normalize(const UnicodeString &src, UErrorCode &errorCode) const { UnicodeString result; normalize(src, result, errorCode); return result; } /** * Writes the normalized form of the source string to the destination string * (replacing its contents) and returns the destination string. * The source and destination strings must be different objects. * @param src source string * @param dest destination string; its contents is replaced with normalized src * @param errorCode 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 */ virtual UnicodeString & normalize(const UnicodeString &src, UnicodeString &dest, UErrorCode &errorCode) const = 0; /** * Normalizes a UTF-8 string and optionally records how source substrings * relate to changed and unchanged result substrings. * * Currently implemented completely only for "compose" modes, * such as for NFC, NFKC, and NFKC_Casefold * (UNORM2_COMPOSE and UNORM2_COMPOSE_CONTIGUOUS). * Otherwise currently converts to & from UTF-16 and does not support edits. * * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT and U_EDITS_NO_RESET. * @param src Source UTF-8 string. * @param sink A ByteSink to which the normalized UTF-8 result string is written. * sink.Flush() is called at the end. * @param edits Records edits for index mapping, working with styled text, * and getting only changes (if any). * The Edits contents is undefined if any error occurs. * This function calls edits->reset() first unless * options includes U_EDITS_NO_RESET. edits can be nullptr. * @param errorCode 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.) * @draft ICU 60 */ virtual void normalizeUTF8(uint32_t options, StringPiece src, ByteSink &sink, Edits *edits, UErrorCode &errorCode) const; /** * Appends the normalized form of the second string to the first string * (merging them at the boundary) and returns the first string. * The result is normalized if the first string was normalized. * The first and second strings must be different objects. * @param first string, should be normalized * @param second string, will be normalized * @param errorCode 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 */ virtual UnicodeString & normalizeSecondAndAppend(UnicodeString &first, const UnicodeString &second, UErrorCode &errorCode) const = 0; /** * Appends the second string to the first string * (merging them at the boundary) and returns the first string. * The result is normalized if both the strings were normalized. * The first and second strings must be different objects. * @param first string, should be normalized * @param second string, should be normalized * @param errorCode 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 */ virtual UnicodeString & append(UnicodeString &first, const UnicodeString &second, UErrorCode &errorCode) const = 0; /** * Gets the decomposition mapping of c. * Roughly equivalent to normalizing the String form of c * on a UNORM2_DECOMPOSE Normalizer2 instance, but much faster, and except that this function * returns FALSE 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 Normalizer2. * @param c code point * @param decomposition String object which will be set to c's * decomposition mapping, if there is one. * @return TRUE if c has a decomposition, otherwise FALSE * @stable ICU 4.6 */ virtual UBool getDecomposition(UChar32 c, UnicodeString &decomposition) const = 0; /** * Gets the raw decomposition mapping of c. * * This is similar to the getDecomposition() method 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, getDecomposition() returns the processed, * recursively-decomposed version of this mapping. * * When used on a standard NFKC Normalizer2 instance, * 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 char16_ts). * * This function is independent of the mode of the Normalizer2. * The default implementation returns FALSE. * @param c code point * @param decomposition String object which will be set to c's * raw decomposition mapping, if there is one. * @return TRUE if c has a decomposition, otherwise FALSE * @stable ICU 49 */ virtual UBool getRawDecomposition(UChar32 c, UnicodeString &decomposition) const; /** * 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 Normalizer2. * The default implementation returns a negative value. * @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 */ virtual UChar32 composePair(UChar32 a, UChar32 b) const; /** * Gets the combining class of c. * The default implementation returns 0 * but all standard implementations return the Unicode Canonical_Combining_Class value. * @param c code point * @return c's combining class * @stable ICU 49 */ virtual uint8_t getCombiningClass(UChar32 c) const; /** * 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 s input string * @param errorCode 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 */ virtual UBool isNormalized(const UnicodeString &s, UErrorCode &errorCode) const = 0; /** * Tests if the UTF-8 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. * * This works for all normalization modes, * but it is currently optimized for UTF-8 only for "compose" modes, * such as for NFC, NFKC, and NFKC_Casefold * (UNORM2_COMPOSE and UNORM2_COMPOSE_CONTIGUOUS). * For other modes it currently converts to UTF-16 and calls isNormalized(). * * @param s UTF-8 input string * @param errorCode 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 * @draft ICU 60 */ virtual UBool isNormalizedUTF8(StringPiece s, UErrorCode &errorCode) const; /** * 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 s input string * @param errorCode 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 */ virtual UNormalizationCheckResult quickCheck(const UnicodeString &s, UErrorCode &errorCode) const = 0; /** * 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 s input string * @param errorCode 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 */ virtual int32_t spanQuickCheckYes(const UnicodeString &s, UErrorCode &errorCode) const = 0; /** * Tests if the character always has a normalization boundary before it, * regardless of context. * If true, then the character does not normalization-interact with * preceding characters. * In other words, a string containing this character can be normalized * by processing portions before this character and starting from this * character independently. * This is used for iterative normalization. See the class documentation for details. * @param c character to test * @return TRUE if c has a normalization boundary before it * @stable ICU 4.4 */ virtual UBool hasBoundaryBefore(UChar32 c) const = 0; /** * Tests if the character always has a normalization boundary after it, * regardless of context. * If true, then the character does not normalization-interact with * following characters. * In other words, a string containing this character can be normalized * by processing portions up to this character and after this * character independently. * This is used for iterative normalization. See the class documentation for details. * Note that this operation may be significantly slower than hasBoundaryBefore(). * @param c character to test * @return TRUE if c has a normalization boundary after it * @stable ICU 4.4 */ virtual UBool hasBoundaryAfter(UChar32 c) const = 0; /** * Tests if the character is normalization-inert. * If true, then the character does not change, nor normalization-interact with * preceding or following characters. * In other words, a string containing this character can be normalized * by processing portions before this character and after this * character independently. * This is used for iterative normalization. See the class documentation for details. * Note that this operation may be significantly slower than hasBoundaryBefore(). * @param c character to test * @return TRUE if c is normalization-inert * @stable ICU 4.4 */ virtual UBool isInert(UChar32 c) const = 0; }; /** * Normalization filtered by a UnicodeSet. * Normalizes portions of the text contained in the filter set and leaves * portions not contained in the filter set unchanged. * Filtering is done via UnicodeSet::span(..., USET_SPAN_SIMPLE). * Not-in-the-filter text is treated as "is normalized" and "quick check yes". * This class implements all of (and only) the Normalizer2 API. * An instance of this class is unmodifiable/immutable but is constructed and * must be destructed by the owner. * @stable ICU 4.4 */ class U_COMMON_API FilteredNormalizer2 : public Normalizer2 { public: /** * Constructs a filtered normalizer wrapping any Normalizer2 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 n2 wrapped Normalizer2 instance * @param filterSet UnicodeSet which determines the characters to be normalized * @stable ICU 4.4 */ FilteredNormalizer2(const Normalizer2 &n2, const UnicodeSet &filterSet) : norm2(n2), set(filterSet) {} /** * Destructor. * @stable ICU 4.4 */ ~FilteredNormalizer2(); /** * Writes the normalized form of the source string to the destination string * (replacing its contents) and returns the destination string. * The source and destination strings must be different objects. * @param src source string * @param dest destination string; its contents is replaced with normalized src * @param errorCode 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 */ virtual UnicodeString & normalize(const UnicodeString &src, UnicodeString &dest, UErrorCode &errorCode) const U_OVERRIDE; /** * Normalizes a UTF-8 string and optionally records how source substrings * relate to changed and unchanged result substrings. * * Currently implemented completely only for "compose" modes, * such as for NFC, NFKC, and NFKC_Casefold * (UNORM2_COMPOSE and UNORM2_COMPOSE_CONTIGUOUS). * Otherwise currently converts to & from UTF-16 and does not support edits. * * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT and U_EDITS_NO_RESET. * @param src Source UTF-8 string. * @param sink A ByteSink to which the normalized UTF-8 result string is written. * sink.Flush() is called at the end. * @param edits Records edits for index mapping, working with styled text, * and getting only changes (if any). * The Edits contents is undefined if any error occurs. * This function calls edits->reset() first unless * options includes U_EDITS_NO_RESET. edits can be nullptr. * @param errorCode 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.) * @draft ICU 60 */ virtual void normalizeUTF8(uint32_t options, StringPiece src, ByteSink &sink, Edits *edits, UErrorCode &errorCode) const U_OVERRIDE; /** * Appends the normalized form of the second string to the first string * (merging them at the boundary) and returns the first string. * The result is normalized if the first string was normalized. * The first and second strings must be different objects. * @param first string, should be normalized * @param second string, will be normalized * @param errorCode 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 */ virtual UnicodeString & normalizeSecondAndAppend(UnicodeString &first, const UnicodeString &second, UErrorCode &errorCode) const U_OVERRIDE; /** * Appends the second string to the first string * (merging them at the boundary) and returns the first string. * The result is normalized if both the strings were normalized. * The first and second strings must be different objects. * @param first string, should be normalized * @param second string, should be normalized * @param errorCode 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 */ virtual UnicodeString & append(UnicodeString &first, const UnicodeString &second, UErrorCode &errorCode) const U_OVERRIDE; /** * Gets the decomposition mapping of c. * For details see the base class documentation. * * This function is independent of the mode of the Normalizer2. * @param c code point * @param decomposition String object which will be set to c's * decomposition mapping, if there is one. * @return TRUE if c has a decomposition, otherwise FALSE * @stable ICU 4.6 */ virtual UBool getDecomposition(UChar32 c, UnicodeString &decomposition) const U_OVERRIDE; /** * Gets the raw decomposition mapping of c. * For details see the base class documentation. * * This function is independent of the mode of the Normalizer2. * @param c code point * @param decomposition String object which will be set to c's * raw decomposition mapping, if there is one. * @return TRUE if c has a decomposition, otherwise FALSE * @stable ICU 49 */ virtual UBool getRawDecomposition(UChar32 c, UnicodeString &decomposition) const U_OVERRIDE; /** * Performs pairwise composition of a & b and returns the composite if there is one. * For details see the base class documentation. * * This function is independent of the mode of the Normalizer2. * @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 */ virtual UChar32 composePair(UChar32 a, UChar32 b) const U_OVERRIDE; /** * Gets the combining class of c. * The default implementation returns 0 * but all standard implementations return the Unicode Canonical_Combining_Class value. * @param c code point * @return c's combining class * @stable ICU 49 */ virtual uint8_t getCombiningClass(UChar32 c) const U_OVERRIDE; /** * Tests if the string is normalized. * For details see the Normalizer2 base class documentation. * @param s input string * @param errorCode 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 */ virtual UBool isNormalized(const UnicodeString &s, UErrorCode &errorCode) const U_OVERRIDE; /** * Tests if the UTF-8 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. * * This works for all normalization modes, * but it is currently optimized for UTF-8 only for "compose" modes, * such as for NFC, NFKC, and NFKC_Casefold * (UNORM2_COMPOSE and UNORM2_COMPOSE_CONTIGUOUS). * For other modes it currently converts to UTF-16 and calls isNormalized(). * * @param s UTF-8 input string * @param errorCode 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 * @draft ICU 60 */ virtual UBool isNormalizedUTF8(StringPiece s, UErrorCode &errorCode) const U_OVERRIDE; /** * Tests if the string is normalized. * For details see the Normalizer2 base class documentation. * @param s input string * @param errorCode 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 */ virtual UNormalizationCheckResult quickCheck(const UnicodeString &s, UErrorCode &errorCode) const U_OVERRIDE; /** * Returns the end of the normalized substring of the input string. * For details see the Normalizer2 base class documentation. * @param s input string * @param errorCode 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 */ virtual int32_t spanQuickCheckYes(const UnicodeString &s, UErrorCode &errorCode) const U_OVERRIDE; /** * Tests if the character always has a normalization boundary before it, * regardless of context. * For details see the Normalizer2 base class documentation. * @param c character to test * @return TRUE if c has a normalization boundary before it * @stable ICU 4.4 */ virtual UBool hasBoundaryBefore(UChar32 c) const U_OVERRIDE; /** * Tests if the character always has a normalization boundary after it, * regardless of context. * For details see the Normalizer2 base class documentation. * @param c character to test * @return TRUE if c has a normalization boundary after it * @stable ICU 4.4 */ virtual UBool hasBoundaryAfter(UChar32 c) const U_OVERRIDE; /** * Tests if the character is normalization-inert. * For details see the Normalizer2 base class documentation. * @param c character to test * @return TRUE if c is normalization-inert * @stable ICU 4.4 */ virtual UBool isInert(UChar32 c) const U_OVERRIDE; private: UnicodeString & normalize(const UnicodeString &src, UnicodeString &dest, USetSpanCondition spanCondition, UErrorCode &errorCode) const; void normalizeUTF8(uint32_t options, const char *src, int32_t length, ByteSink &sink, Edits *edits, USetSpanCondition spanCondition, UErrorCode &errorCode) const; UnicodeString & normalizeSecondAndAppend(UnicodeString &first, const UnicodeString &second, UBool doNormalize, UErrorCode &errorCode) const; const Normalizer2 &norm2; const UnicodeSet &set; }; U_NAMESPACE_END #endif // !UCONFIG_NO_NORMALIZATION #endif // __NORMALIZER2_H__