Linux vps-61133.fhnet.fr 4.9.0-19-amd64 #1 SMP Debian 4.9.320-2 (2022-06-30) x86_64
Apache/2.4.25 (Debian)
Server IP : 93.113.207.21 & Your IP : 216.73.216.35
Domains :
Cant Read [ /etc/named.conf ]
User : www-data
Terminal
Auto Root
Create File
Create Folder
Localroot Suggester
Backdoor Destroyer
Readme
/
usr /
include /
unicode /
Delete
Unzip
Name
Size
Permission
Date
Action
alphaindex.h
26.13
KB
-rw-r--r--
2021-10-12 12:29
appendable.h
8.25
KB
-rw-r--r--
2021-10-12 12:29
basictz.h
8.73
KB
-rw-r--r--
2021-10-12 12:29
brkiter.h
27.31
KB
-rw-r--r--
2021-10-12 12:29
bytestream.h
9.16
KB
-rw-r--r--
2021-10-12 12:29
bytestrie.h
19.19
KB
-rw-r--r--
2021-10-12 12:29
bytestriebuilder.h
7.06
KB
-rw-r--r--
2021-10-12 12:29
calendar.h
105.26
KB
-rw-r--r--
2021-10-12 12:29
caniter.h
7.24
KB
-rw-r--r--
2021-10-12 12:29
chariter.h
23.71
KB
-rw-r--r--
2021-10-12 12:29
choicfmt.h
23.74
KB
-rw-r--r--
2021-10-12 12:29
coleitr.h
13.57
KB
-rw-r--r--
2021-10-12 12:29
coll.h
55.46
KB
-rw-r--r--
2021-10-12 12:29
compactdecimalformat.h
16.56
KB
-rw-r--r--
2021-10-12 12:29
curramt.h
3.57
KB
-rw-r--r--
2021-10-12 12:29
currpinf.h
6.97
KB
-rw-r--r--
2021-10-12 12:29
currunit.h
2.81
KB
-rw-r--r--
2021-10-12 12:29
datefmt.h
40.07
KB
-rw-r--r--
2021-10-12 12:29
dbbi.h
1020
B
-rw-r--r--
2021-10-12 12:29
dcfmtsym.h
16.46
KB
-rw-r--r--
2021-10-12 12:29
decimfmt.h
90.45
KB
-rw-r--r--
2021-10-12 12:29
docmain.h
6.28
KB
-rw-r--r--
2021-10-12 12:29
dtfmtsym.h
37.05
KB
-rw-r--r--
2021-10-12 12:29
dtintrv.h
3.65
KB
-rw-r--r--
2021-10-12 12:29
dtitvfmt.h
42.76
KB
-rw-r--r--
2021-10-12 12:29
dtitvinf.h
18.34
KB
-rw-r--r--
2021-10-12 12:29
dtptngen.h
23.18
KB
-rw-r--r--
2021-10-12 12:29
dtrule.h
8.51
KB
-rw-r--r--
2021-10-12 12:29
enumset.h
1.94
KB
-rw-r--r--
2021-10-12 12:29
errorcode.h
4.67
KB
-rw-r--r--
2021-10-12 12:29
fieldpos.h
8.51
KB
-rw-r--r--
2021-10-12 12:29
filteredbrk.h
4.22
KB
-rw-r--r--
2021-10-12 12:29
fmtable.h
24.29
KB
-rw-r--r--
2021-10-12 12:29
format.h
12.33
KB
-rw-r--r--
2021-10-12 12:29
fpositer.h
2.87
KB
-rw-r--r--
2021-10-12 12:29
gender.h
3.07
KB
-rw-r--r--
2021-10-12 12:29
gregocal.h
31.46
KB
-rw-r--r--
2021-10-12 12:29
icudataver.h
938
B
-rw-r--r--
2021-10-12 12:29
icuplug.h
11.58
KB
-rw-r--r--
2021-10-12 12:29
idna.h
12.55
KB
-rw-r--r--
2021-10-12 12:29
listformatter.h
4.73
KB
-rw-r--r--
2021-10-12 12:29
localpointer.h
18.17
KB
-rw-r--r--
2021-10-12 12:29
locdspnm.h
6.92
KB
-rw-r--r--
2021-10-12 12:29
locid.h
31.3
KB
-rw-r--r--
2021-10-12 12:29
measfmt.h
10.43
KB
-rw-r--r--
2021-10-12 12:29
measunit.h
37.64
KB
-rw-r--r--
2021-10-12 12:29
measure.h
4.15
KB
-rw-r--r--
2021-10-12 12:29
messagepattern.h
33.53
KB
-rw-r--r--
2021-10-12 12:29
msgfmt.h
43.05
KB
-rw-r--r--
2021-10-12 12:29
normalizer2.h
28.17
KB
-rw-r--r--
2021-10-12 12:29
normlzr.h
30.65
KB
-rw-r--r--
2021-10-12 12:29
numfmt.h
45.85
KB
-rw-r--r--
2021-10-12 12:29
numsys.h
6.62
KB
-rw-r--r--
2021-10-12 12:29
parseerr.h
2.97
KB
-rw-r--r--
2021-10-12 12:29
parsepos.h
5.34
KB
-rw-r--r--
2021-10-12 12:29
platform.h
26.96
KB
-rw-r--r--
2021-10-12 12:29
plurfmt.h
25.55
KB
-rw-r--r--
2021-10-12 12:29
plurrule.h
17.16
KB
-rw-r--r--
2021-10-12 12:29
ptypes.h
3.36
KB
-rw-r--r--
2021-10-12 12:29
putil.h
6.23
KB
-rw-r--r--
2021-10-12 12:29
rbbi.h
29.2
KB
-rw-r--r--
2021-10-12 12:29
rbnf.h
46.66
KB
-rw-r--r--
2021-10-12 12:29
rbtz.h
15.36
KB
-rw-r--r--
2021-10-12 12:29
regex.h
84.75
KB
-rw-r--r--
2021-10-12 12:29
region.h
9
KB
-rw-r--r--
2021-10-12 12:29
reldatefmt.h
13.73
KB
-rw-r--r--
2021-10-12 12:29
rep.h
9.38
KB
-rw-r--r--
2021-10-12 12:29
resbund.h
17.89
KB
-rw-r--r--
2021-10-12 12:29
schriter.h
6.15
KB
-rw-r--r--
2021-10-12 12:29
scientificnumberformatter.h
6.48
KB
-rw-r--r--
2021-10-12 12:29
search.h
22.1
KB
-rw-r--r--
2021-10-12 12:29
selfmt.h
14.13
KB
-rw-r--r--
2021-10-12 12:29
simpleformatter.h
11.14
KB
-rw-r--r--
2021-10-12 12:29
simpletz.h
45.13
KB
-rw-r--r--
2021-10-12 12:29
smpdtfmt.h
69.24
KB
-rw-r--r--
2021-10-12 12:29
sortkey.h
11.01
KB
-rw-r--r--
2021-10-12 12:29
std_string.h
905
B
-rw-r--r--
2021-10-12 12:29
strenum.h
9.92
KB
-rw-r--r--
2021-10-12 12:29
stringpiece.h
6.38
KB
-rw-r--r--
2021-10-12 12:29
stringtriebuilder.h
14.56
KB
-rw-r--r--
2021-10-12 12:29
stsearch.h
21.18
KB
-rw-r--r--
2021-10-12 12:29
symtable.h
4.1
KB
-rw-r--r--
2021-10-12 12:29
tblcoll.h
36.24
KB
-rw-r--r--
2021-10-12 12:29
timezone.h
40.71
KB
-rw-r--r--
2021-10-12 12:29
tmunit.h
2.94
KB
-rw-r--r--
2021-10-12 12:29
tmutamt.h
4.69
KB
-rw-r--r--
2021-10-12 12:29
tmutfmt.h
7.61
KB
-rw-r--r--
2021-10-12 12:29
translit.h
54.41
KB
-rw-r--r--
2021-10-12 12:29
tzfmt.h
42.69
KB
-rw-r--r--
2021-10-12 12:29
tznames.h
16.25
KB
-rw-r--r--
2021-10-12 12:29
tzrule.h
35.21
KB
-rw-r--r--
2021-10-12 12:29
tztrans.h
5.96
KB
-rw-r--r--
2021-10-12 12:29
ubidi.h
88.57
KB
-rw-r--r--
2021-10-12 12:29
ubrk.h
20.05
KB
-rw-r--r--
2021-10-12 12:29
ucal.h
54.18
KB
-rw-r--r--
2021-10-12 12:29
ucasemap.h
16.45
KB
-rw-r--r--
2021-10-12 12:29
ucat.h
5.25
KB
-rw-r--r--
2021-10-12 12:29
uchar.h
122.74
KB
-rw-r--r--
2021-10-12 12:29
ucharstrie.h
20.8
KB
-rw-r--r--
2021-10-12 12:29
ucharstriebuilder.h
7.01
KB
-rw-r--r--
2021-10-12 12:29
uchriter.h
12.82
KB
-rw-r--r--
2021-10-12 12:29
uclean.h
11.03
KB
-rw-r--r--
2021-10-12 12:29
ucnv.h
82.81
KB
-rw-r--r--
2021-10-12 12:29
ucnv_cb.h
6.48
KB
-rw-r--r--
2021-10-12 12:29
ucnv_err.h
20.87
KB
-rw-r--r--
2021-10-12 12:29
ucnvsel.h
6.03
KB
-rw-r--r--
2021-10-12 12:29
ucol.h
60.51
KB
-rw-r--r--
2021-10-12 12:29
ucoleitr.h
9.34
KB
-rw-r--r--
2021-10-12 12:29
uconfig.h
11.76
KB
-rw-r--r--
2021-10-12 12:29
ucsdet.h
14.35
KB
-rw-r--r--
2021-10-12 12:29
ucurr.h
14.92
KB
-rw-r--r--
2021-10-12 12:29
udat.h
59.91
KB
-rw-r--r--
2021-10-12 12:29
udata.h
15.28
KB
-rw-r--r--
2021-10-12 12:29
udateintervalformat.h
6.68
KB
-rw-r--r--
2021-10-12 12:29
udatpg.h
23.5
KB
-rw-r--r--
2021-10-12 12:29
udisplaycontext.h
4.87
KB
-rw-r--r--
2021-10-12 12:29
uenum.h
7.76
KB
-rw-r--r--
2021-10-12 12:29
ufieldpositer.h
4.24
KB
-rw-r--r--
2021-10-12 12:29
uformattable.h
10.65
KB
-rw-r--r--
2021-10-12 12:29
ugender.h
1.89
KB
-rw-r--r--
2021-10-12 12:29
uidna.h
33.26
KB
-rw-r--r--
2021-10-12 12:29
uiter.h
22.67
KB
-rw-r--r--
2021-10-12 12:29
uldnames.h
10.34
KB
-rw-r--r--
2021-10-12 12:29
ulistformatter.h
4.43
KB
-rw-r--r--
2021-10-12 12:29
uloc.h
49.78
KB
-rw-r--r--
2021-10-12 12:29
ulocdata.h
10.57
KB
-rw-r--r--
2021-10-12 12:29
umachine.h
10.94
KB
-rw-r--r--
2021-10-12 12:29
umisc.h
1.23
KB
-rw-r--r--
2021-10-12 12:29
umsg.h
24.12
KB
-rw-r--r--
2021-10-12 12:29
unifilt.h
3.52
KB
-rw-r--r--
2021-10-12 12:29
unifunct.h
3.87
KB
-rw-r--r--
2021-10-12 12:29
unimatch.h
5.93
KB
-rw-r--r--
2021-10-12 12:29
unirepl.h
3.21
KB
-rw-r--r--
2021-10-12 12:29
uniset.h
63.86
KB
-rw-r--r--
2021-10-12 12:29
unistr.h
170.03
KB
-rw-r--r--
2021-10-12 12:29
unorm.h
20.18
KB
-rw-r--r--
2021-10-12 12:29
unorm2.h
25.11
KB
-rw-r--r--
2021-10-12 12:29
unum.h
49.13
KB
-rw-r--r--
2021-10-12 12:29
unumsys.h
7.03
KB
-rw-r--r--
2021-10-12 12:29
uobject.h
10.61
KB
-rw-r--r--
2021-10-12 12:29
upluralrules.h
4.47
KB
-rw-r--r--
2021-10-12 12:29
uregex.h
71.95
KB
-rw-r--r--
2021-10-12 12:29
uregion.h
9.58
KB
-rw-r--r--
2021-10-12 12:29
ureldatefmt.h
11.85
KB
-rw-r--r--
2021-10-12 12:29
urename.h
123.32
KB
-rw-r--r--
2021-10-12 12:29
urep.h
5.27
KB
-rw-r--r--
2021-10-12 12:29
ures.h
36.25
KB
-rw-r--r--
2021-10-12 12:29
uscript.h
25.24
KB
-rw-r--r--
2021-10-12 12:29
usearch.h
37.71
KB
-rw-r--r--
2021-10-12 12:29
uset.h
39.67
KB
-rw-r--r--
2021-10-12 12:29
usetiter.h
9.38
KB
-rw-r--r--
2021-10-12 12:29
ushape.h
17.89
KB
-rw-r--r--
2021-10-12 12:29
uspoof.h
45.43
KB
-rw-r--r--
2021-10-12 12:29
usprep.h
8.02
KB
-rw-r--r--
2021-10-12 12:29
ustdio.h
38.43
KB
-rw-r--r--
2021-10-12 12:29
ustream.h
1.8
KB
-rw-r--r--
2021-10-12 12:29
ustring.h
72.69
KB
-rw-r--r--
2021-10-12 12:29
ustringtrie.h
3.04
KB
-rw-r--r--
2021-10-12 12:29
utext.h
57.97
KB
-rw-r--r--
2021-10-12 12:29
utf.h
7.64
KB
-rw-r--r--
2021-10-12 12:29
utf16.h
18.63
KB
-rw-r--r--
2021-10-12 12:29
utf32.h
653
B
-rw-r--r--
2021-10-12 12:29
utf8.h
27.62
KB
-rw-r--r--
2021-10-12 12:29
utf_old.h
42.5
KB
-rw-r--r--
2021-10-12 12:29
utmscale.h
13.37
KB
-rw-r--r--
2021-10-12 12:29
utrace.h
13.09
KB
-rw-r--r--
2021-10-12 12:29
utrans.h
25.42
KB
-rw-r--r--
2021-10-12 12:29
utypes.h
31.05
KB
-rw-r--r--
2021-10-12 12:29
uvernum.h
5.62
KB
-rw-r--r--
2021-10-12 12:29
uversion.h
6.29
KB
-rw-r--r--
2021-10-12 12:29
vtzone.h
20.06
KB
-rw-r--r--
2021-10-12 12:29
Save
Rename
/* ******************************************************************************* * * Copyright (C) 2009-2013, International Business Machines * Corporation and others. All Rights Reserved. * ******************************************************************************* * file name: normalizer2.h * encoding: US-ASCII * 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/uniset.h" #include "unicode/unistr.h" #include "unicode/unorm2.h" U_NAMESPACE_BEGIN /** * 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; /** * 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 UChars). * * 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 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; /** * 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; /** * 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; /** * 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; /** * 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; /** * 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; /** * 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. * 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; /** * 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; /** * 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; /** * 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; /** * 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; /** * 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; private: UnicodeString & normalize(const UnicodeString &src, UnicodeString &dest, 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__