Linux premium71.web-hosting.com 4.18.0-513.11.1.lve.el8.x86_64 #1 SMP Thu Jan 18 16:21:02 UTC 2024 x86_64
LiteSpeed
Server IP : 198.187.29.8 & Your IP : 18.223.172.149
Domains :
Cant Read [ /etc/named.conf ]
User : cleahvkv
Terminal
Auto Root
Create File
Create Folder
Localroot Suggester
Backdoor Destroyer
Readme
/
opt /
alt /
libicu65 /
usr /
include /
unicode /
Delete
Unzip
Name
Size
Permission
Date
Action
alphaindex.h
26.48
KB
-rw-r--r--
2022-02-08 16:22
appendable.h
8.49
KB
-rw-r--r--
2022-02-08 16:22
basictz.h
9.15
KB
-rw-r--r--
2022-02-08 16:22
brkiter.h
27.8
KB
-rw-r--r--
2022-02-08 16:22
bytestream.h
9.6
KB
-rw-r--r--
2022-02-08 16:22
bytestrie.h
20.77
KB
-rw-r--r--
2022-02-08 16:22
bytestriebuilder.h
7.08
KB
-rw-r--r--
2022-02-08 16:22
calendar.h
105.74
KB
-rw-r--r--
2022-02-08 16:22
caniter.h
7.43
KB
-rw-r--r--
2022-02-08 16:22
casemap.h
25.33
KB
-rw-r--r--
2022-02-08 16:22
char16ptr.h
7.22
KB
-rw-r--r--
2022-02-08 16:22
chariter.h
24.05
KB
-rw-r--r--
2022-02-08 16:22
choicfmt.h
23.91
KB
-rw-r--r--
2022-02-08 16:22
coleitr.h
13.76
KB
-rw-r--r--
2022-02-08 16:22
coll.h
56.23
KB
-rw-r--r--
2022-02-08 16:22
compactdecimalformat.h
6.88
KB
-rw-r--r--
2022-02-08 16:22
curramt.h
3.76
KB
-rw-r--r--
2022-02-08 16:22
currpinf.h
7.3
KB
-rw-r--r--
2022-02-08 16:22
currunit.h
4.05
KB
-rw-r--r--
2022-02-08 16:22
datefmt.h
40.67
KB
-rw-r--r--
2022-02-08 16:22
dbbi.h
1.19
KB
-rw-r--r--
2022-02-08 16:22
dcfmtsym.h
20.13
KB
-rw-r--r--
2022-02-08 16:22
decimfmt.h
87.38
KB
-rw-r--r--
2022-02-08 16:22
docmain.h
6.97
KB
-rw-r--r--
2022-02-08 16:22
dtfmtsym.h
37.7
KB
-rw-r--r--
2022-02-08 16:22
dtintrv.h
3.84
KB
-rw-r--r--
2022-02-08 16:22
dtitvfmt.h
46.63
KB
-rw-r--r--
2022-02-08 16:22
dtitvinf.h
18.51
KB
-rw-r--r--
2022-02-08 16:22
dtptngen.h
25.08
KB
-rw-r--r--
2022-02-08 16:22
dtrule.h
8.68
KB
-rw-r--r--
2022-02-08 16:22
edits.h
20.74
KB
-rw-r--r--
2022-02-08 16:22
enumset.h
2.08
KB
-rw-r--r--
2022-02-08 16:22
errorcode.h
4.84
KB
-rw-r--r--
2022-02-08 16:22
fieldpos.h
8.69
KB
-rw-r--r--
2022-02-08 16:22
filteredbrk.h
5.37
KB
-rw-r--r--
2022-02-08 16:22
fmtable.h
24.42
KB
-rw-r--r--
2022-02-08 16:22
format.h
12.5
KB
-rw-r--r--
2022-02-08 16:22
formattedvalue.h
10.27
KB
-rw-r--r--
2022-02-08 16:22
fpositer.h
3.04
KB
-rw-r--r--
2022-02-08 16:22
gender.h
3.33
KB
-rw-r--r--
2022-02-08 16:22
gregocal.h
31.71
KB
-rw-r--r--
2022-02-08 16:22
icudataver.h
1.03
KB
-rw-r--r--
2022-02-08 16:22
icuplug.h
11.88
KB
-rw-r--r--
2022-02-08 16:22
idna.h
12.7
KB
-rw-r--r--
2022-02-08 16:22
listformatter.h
9.47
KB
-rw-r--r--
2022-02-08 16:22
localebuilder.h
11.27
KB
-rw-r--r--
2022-02-08 16:22
localematcher.h
22.5
KB
-rw-r--r--
2022-02-08 16:22
localpointer.h
19.69
KB
-rw-r--r--
2022-02-08 16:22
locdspnm.h
7.12
KB
-rw-r--r--
2022-02-08 16:22
locid.h
47.4
KB
-rw-r--r--
2022-02-08 16:22
measfmt.h
11.33
KB
-rw-r--r--
2022-02-08 16:22
measunit.h
93.31
KB
-rw-r--r--
2022-02-08 16:22
measure.h
4.32
KB
-rw-r--r--
2022-02-08 16:22
messagepattern.h
33.71
KB
-rw-r--r--
2022-02-08 16:22
msgfmt.h
44.11
KB
-rw-r--r--
2022-02-08 16:22
normalizer2.h
34.03
KB
-rw-r--r--
2022-02-08 16:22
normlzr.h
30.94
KB
-rw-r--r--
2022-02-08 16:22
nounit.h
2.69
KB
-rw-r--r--
2022-02-08 16:22
numberformatter.h
86.31
KB
-rw-r--r--
2022-02-08 16:22
numberrangeformatter.h
30.14
KB
-rw-r--r--
2022-02-08 16:22
numfmt.h
49.81
KB
-rw-r--r--
2022-02-08 16:22
numsys.h
7.19
KB
-rw-r--r--
2022-02-08 16:22
parseerr.h
3.08
KB
-rw-r--r--
2022-02-08 16:22
parsepos.h
5.56
KB
-rw-r--r--
2022-02-08 16:22
platform.h
28.08
KB
-rw-r--r--
2022-02-08 16:22
plurfmt.h
25.2
KB
-rw-r--r--
2022-02-08 16:22
plurrule.h
18.39
KB
-rw-r--r--
2022-02-08 16:22
ptypes.h
3.49
KB
-rw-r--r--
2022-02-08 16:22
putil.h
6.33
KB
-rw-r--r--
2022-02-08 16:22
rbbi.h
26.58
KB
-rw-r--r--
2022-02-08 16:22
rbnf.h
48.73
KB
-rw-r--r--
2022-02-08 16:22
rbtz.h
15.6
KB
-rw-r--r--
2022-02-08 16:22
regex.h
84.36
KB
-rw-r--r--
2022-02-08 16:22
region.h
9.18
KB
-rw-r--r--
2022-02-08 16:22
reldatefmt.h
22.62
KB
-rw-r--r--
2022-02-08 16:22
rep.h
9.37
KB
-rw-r--r--
2022-02-08 16:22
resbund.h
18.07
KB
-rw-r--r--
2022-02-08 16:22
schriter.h
6.32
KB
-rw-r--r--
2022-02-08 16:22
scientificnumberformatter.h
6.4
KB
-rw-r--r--
2022-02-08 16:22
search.h
22.22
KB
-rw-r--r--
2022-02-08 16:22
selfmt.h
14.3
KB
-rw-r--r--
2022-02-08 16:22
simpleformatter.h
12.59
KB
-rw-r--r--
2022-02-08 16:22
simpletz.h
45.44
KB
-rw-r--r--
2022-02-08 16:22
smpdtfmt.h
70.97
KB
-rw-r--r--
2022-02-08 16:22
sortkey.h
11.18
KB
-rw-r--r--
2022-02-08 16:22
std_string.h
1.05
KB
-rw-r--r--
2022-02-08 16:22
strenum.h
9.92
KB
-rw-r--r--
2022-02-08 16:22
stringoptions.h
5.79
KB
-rw-r--r--
2022-02-08 16:22
stringpiece.h
7.38
KB
-rw-r--r--
2022-02-08 16:22
stringtriebuilder.h
15.33
KB
-rw-r--r--
2022-02-08 16:22
stsearch.h
21.3
KB
-rw-r--r--
2022-02-08 16:22
symtable.h
4.27
KB
-rw-r--r--
2022-02-08 16:22
tblcoll.h
36.61
KB
-rw-r--r--
2022-02-08 16:22
timezone.h
41.02
KB
-rw-r--r--
2022-02-08 16:22
tmunit.h
3.38
KB
-rw-r--r--
2022-02-08 16:22
tmutamt.h
4.9
KB
-rw-r--r--
2022-02-08 16:22
tmutfmt.h
7.85
KB
-rw-r--r--
2022-02-08 16:22
translit.h
65.82
KB
-rw-r--r--
2022-02-08 16:22
tzfmt.h
42.89
KB
-rw-r--r--
2022-02-08 16:22
tznames.h
16.85
KB
-rw-r--r--
2022-02-08 16:22
tzrule.h
35.37
KB
-rw-r--r--
2022-02-08 16:22
tztrans.h
6.12
KB
-rw-r--r--
2022-02-08 16:22
ubidi.h
89.56
KB
-rw-r--r--
2022-02-08 16:22
ubiditransform.h
12.65
KB
-rw-r--r--
2022-02-08 16:22
ubrk.h
23.97
KB
-rw-r--r--
2022-02-08 16:22
ucal.h
56.9
KB
-rw-r--r--
2022-02-08 16:22
ucasemap.h
15.18
KB
-rw-r--r--
2022-02-08 16:22
ucat.h
5.36
KB
-rw-r--r--
2022-02-08 16:22
uchar.h
140.56
KB
-rw-r--r--
2022-02-08 16:22
ucharstrie.h
22.58
KB
-rw-r--r--
2022-02-08 16:22
ucharstriebuilder.h
7.21
KB
-rw-r--r--
2022-02-08 16:22
uchriter.h
13.2
KB
-rw-r--r--
2022-02-08 16:22
uclean.h
11.21
KB
-rw-r--r--
2022-02-08 16:22
ucnv.h
83.09
KB
-rw-r--r--
2022-02-08 16:22
ucnv_cb.h
6.59
KB
-rw-r--r--
2022-02-08 16:22
ucnv_err.h
20.99
KB
-rw-r--r--
2022-02-08 16:22
ucnvsel.h
6.14
KB
-rw-r--r--
2022-02-08 16:22
ucol.h
61.46
KB
-rw-r--r--
2022-02-08 16:22
ucoleitr.h
9.46
KB
-rw-r--r--
2022-02-08 16:22
uconfig.h
12.07
KB
-rw-r--r--
2022-02-08 16:22
ucpmap.h
5.53
KB
-rw-r--r--
2022-02-08 16:22
ucptrie.h
22.46
KB
-rw-r--r--
2022-02-08 16:22
ucsdet.h
14.67
KB
-rw-r--r--
2022-02-08 16:22
ucurr.h
16.12
KB
-rw-r--r--
2022-02-08 16:22
udat.h
60.88
KB
-rw-r--r--
2022-02-08 16:22
udata.h
15.56
KB
-rw-r--r--
2022-02-08 16:22
udateintervalformat.h
10.03
KB
-rw-r--r--
2022-02-08 16:22
udatpg.h
26.01
KB
-rw-r--r--
2022-02-08 16:22
udisplaycontext.h
5.89
KB
-rw-r--r--
2022-02-08 16:22
uenum.h
7.78
KB
-rw-r--r--
2022-02-08 16:22
ufieldpositer.h
4.36
KB
-rw-r--r--
2022-02-08 16:22
uformattable.h
10.94
KB
-rw-r--r--
2022-02-08 16:22
uformattedvalue.h
12.14
KB
-rw-r--r--
2022-02-08 16:22
ugender.h
2
KB
-rw-r--r--
2022-02-08 16:22
uidna.h
33.37
KB
-rw-r--r--
2022-02-08 16:22
uiter.h
22.77
KB
-rw-r--r--
2022-02-08 16:22
uldnames.h
10.45
KB
-rw-r--r--
2022-02-08 16:22
ulistformatter.h
8.83
KB
-rw-r--r--
2022-02-08 16:22
uloc.h
52.54
KB
-rw-r--r--
2022-02-08 16:22
ulocdata.h
11.26
KB
-rw-r--r--
2022-02-08 16:22
umachine.h
14.53
KB
-rw-r--r--
2022-02-08 16:22
umisc.h
1.33
KB
-rw-r--r--
2022-02-08 16:22
umsg.h
24.23
KB
-rw-r--r--
2022-02-08 16:22
umutablecptrie.h
8.24
KB
-rw-r--r--
2022-02-08 16:22
unifilt.h
3.96
KB
-rw-r--r--
2022-02-08 16:22
unifunct.h
4.04
KB
-rw-r--r--
2022-02-08 16:22
unimatch.h
6.1
KB
-rw-r--r--
2022-02-08 16:22
unirepl.h
3.38
KB
-rw-r--r--
2022-02-08 16:22
uniset.h
64.9
KB
-rw-r--r--
2022-02-08 16:22
unistr.h
170.43
KB
-rw-r--r--
2022-02-08 16:22
unorm.h
20.52
KB
-rw-r--r--
2022-02-08 16:22
unorm2.h
24.66
KB
-rw-r--r--
2022-02-08 16:22
unum.h
53.62
KB
-rw-r--r--
2022-02-08 16:22
unumberformatter.h
25.36
KB
-rw-r--r--
2022-02-08 16:22
unumsys.h
7.21
KB
-rw-r--r--
2022-02-08 16:22
uobject.h
10.68
KB
-rw-r--r--
2022-02-08 16:22
upluralrules.h
7.88
KB
-rw-r--r--
2022-02-08 16:22
uregex.h
72.05
KB
-rw-r--r--
2022-02-08 16:22
uregion.h
9.84
KB
-rw-r--r--
2022-02-08 16:22
ureldatefmt.h
17.26
KB
-rw-r--r--
2022-02-08 16:22
urename.h
130.97
KB
-rw-r--r--
2022-02-08 16:22
urep.h
5.38
KB
-rw-r--r--
2022-02-08 16:22
ures.h
36.54
KB
-rw-r--r--
2022-02-08 16:22
uscript.h
26.87
KB
-rw-r--r--
2022-02-08 16:22
usearch.h
38.12
KB
-rw-r--r--
2022-02-08 16:22
uset.h
40
KB
-rw-r--r--
2022-02-08 16:22
usetiter.h
9.55
KB
-rw-r--r--
2022-02-08 16:22
ushape.h
18
KB
-rw-r--r--
2022-02-08 16:22
uspoof.h
65.9
KB
-rw-r--r--
2022-02-08 16:22
usprep.h
8.14
KB
-rw-r--r--
2022-02-08 16:22
ustdio.h
38.54
KB
-rw-r--r--
2022-02-08 16:22
ustream.h
1.89
KB
-rw-r--r--
2022-02-08 16:22
ustring.h
72.47
KB
-rw-r--r--
2022-02-08 16:22
ustringtrie.h
3.15
KB
-rw-r--r--
2022-02-08 16:22
utext.h
58.13
KB
-rw-r--r--
2022-02-08 16:22
utf.h
7.86
KB
-rw-r--r--
2022-02-08 16:22
utf16.h
23.32
KB
-rw-r--r--
2022-02-08 16:22
utf32.h
763
B
-rw-r--r--
2022-02-08 16:22
utf8.h
30.96
KB
-rw-r--r--
2022-02-08 16:22
utf_old.h
45.83
KB
-rw-r--r--
2022-02-08 16:22
utmscale.h
13.78
KB
-rw-r--r--
2022-02-08 16:22
utrace.h
15.73
KB
-rw-r--r--
2022-02-08 16:22
utrans.h
25.52
KB
-rw-r--r--
2022-02-08 16:22
utypes.h
30.74
KB
-rw-r--r--
2022-02-08 16:22
uvernum.h
6.67
KB
-rw-r--r--
2022-02-08 16:22
uversion.h
6
KB
-rw-r--r--
2022-02-08 16:22
vtzone.h
20.3
KB
-rw-r--r--
2022-02-08 16:22
Save
Rename
// © 2016 and later: Unicode, Inc. and others. // License & terms of use: http://www.unicode.org/copyright.html /* ********************************************************************** * Copyright (C) 2005-2013, International Business Machines * Corporation and others. All Rights Reserved. ********************************************************************** * file name: ucsdet.h * encoding: UTF-8 * indentation:4 * * created on: 2005Aug04 * created by: Andy Heninger * * ICU Character Set Detection, API for C * * Draft version 18 Oct 2005 * */ #ifndef __UCSDET_H #define __UCSDET_H #include "unicode/utypes.h" #if !UCONFIG_NO_CONVERSION #include "unicode/localpointer.h" #include "unicode/uenum.h" /** * \file * \brief C API: Charset Detection API * * This API provides a facility for detecting the * charset or encoding of character data in an unknown text format. * The input data can be from an array of bytes. * <p> * Character set detection is at best an imprecise operation. The detection * process will attempt to identify the charset that best matches the characteristics * of the byte data, but the process is partly statistical in nature, and * the results can not be guaranteed to always be correct. * <p> * For best accuracy in charset detection, the input data should be primarily * in a single language, and a minimum of a few hundred bytes worth of plain text * in the language are needed. The detection process will attempt to * ignore html or xml style markup that could otherwise obscure the content. * <p> * An alternative to the ICU Charset Detector is the * Compact Encoding Detector, https://github.com/google/compact_enc_det. * It often gives more accurate results, especially with short input samples. */ struct UCharsetDetector; /** * Structure representing a charset detector * @stable ICU 3.6 */ typedef struct UCharsetDetector UCharsetDetector; struct UCharsetMatch; /** * Opaque structure representing a match that was identified * from a charset detection operation. * @stable ICU 3.6 */ typedef struct UCharsetMatch UCharsetMatch; /** * Open a charset detector. * * @param status Any error conditions occurring during the open * operation are reported back in this variable. * @return the newly opened charset detector. * @stable ICU 3.6 */ U_STABLE UCharsetDetector * U_EXPORT2 ucsdet_open(UErrorCode *status); /** * Close a charset detector. All storage and any other resources * owned by this charset detector will be released. Failure to * close a charset detector when finished with it can result in * memory leaks in the application. * * @param ucsd The charset detector to be closed. * @stable ICU 3.6 */ U_STABLE void U_EXPORT2 ucsdet_close(UCharsetDetector *ucsd); #if U_SHOW_CPLUSPLUS_API U_NAMESPACE_BEGIN /** * \class LocalUCharsetDetectorPointer * "Smart pointer" class, closes a UCharsetDetector via ucsdet_close(). * For most methods see the LocalPointerBase base class. * * @see LocalPointerBase * @see LocalPointer * @stable ICU 4.4 */ U_DEFINE_LOCAL_OPEN_POINTER(LocalUCharsetDetectorPointer, UCharsetDetector, ucsdet_close); U_NAMESPACE_END #endif /** * Set the input byte data whose charset is to detected. * * Ownership of the input text byte array remains with the caller. * The input string must not be altered or deleted until the charset * detector is either closed or reset to refer to different input text. * * @param ucsd the charset detector to be used. * @param textIn the input text of unknown encoding. . * @param len the length of the input text, or -1 if the text * is NUL terminated. * @param status any error conditions are reported back in this variable. * * @stable ICU 3.6 */ U_STABLE void U_EXPORT2 ucsdet_setText(UCharsetDetector *ucsd, const char *textIn, int32_t len, UErrorCode *status); /** Set the declared encoding for charset detection. * The declared encoding of an input text is an encoding obtained * by the user from an http header or xml declaration or similar source that * can be provided as an additional hint to the charset detector. * * How and whether the declared encoding will be used during the * detection process is TBD. * * @param ucsd the charset detector to be used. * @param encoding an encoding for the current data obtained from * a header or declaration or other source outside * of the byte data itself. * @param length the length of the encoding name, or -1 if the name string * is NUL terminated. * @param status any error conditions are reported back in this variable. * * @stable ICU 3.6 */ U_STABLE void U_EXPORT2 ucsdet_setDeclaredEncoding(UCharsetDetector *ucsd, const char *encoding, int32_t length, UErrorCode *status); /** * Return the charset that best matches the supplied input data. * * Note though, that because the detection * only looks at the start of the input data, * there is a possibility that the returned charset will fail to handle * the full set of input data. * <p> * The returned UCharsetMatch object is owned by the UCharsetDetector. * It will remain valid until the detector input is reset, or until * the detector is closed. * <p> * The function will fail if * <ul> * <li>no charset appears to match the data.</li> * <li>no input text has been provided</li> * </ul> * * @param ucsd the charset detector to be used. * @param status any error conditions are reported back in this variable. * @return a UCharsetMatch representing the best matching charset, * or NULL if no charset matches the byte data. * * @stable ICU 3.6 */ U_STABLE const UCharsetMatch * U_EXPORT2 ucsdet_detect(UCharsetDetector *ucsd, UErrorCode *status); /** * Find all charset matches that appear to be consistent with the input, * returning an array of results. The results are ordered with the * best quality match first. * * Because the detection only looks at a limited amount of the * input byte data, some of the returned charsets may fail to handle * the all of input data. * <p> * The returned UCharsetMatch objects are owned by the UCharsetDetector. * They will remain valid until the detector is closed or modified * * <p> * Return an error if * <ul> * <li>no charsets appear to match the input data.</li> * <li>no input text has been provided</li> * </ul> * * @param ucsd the charset detector to be used. * @param matchesFound pointer to a variable that will be set to the * number of charsets identified that are consistent with * the input data. Output only. * @param status any error conditions are reported back in this variable. * @return A pointer to an array of pointers to UCharSetMatch objects. * This array, and the UCharSetMatch instances to which it refers, * are owned by the UCharsetDetector, and will remain valid until * the detector is closed or modified. * @stable ICU 3.6 */ U_STABLE const UCharsetMatch ** U_EXPORT2 ucsdet_detectAll(UCharsetDetector *ucsd, int32_t *matchesFound, UErrorCode *status); /** * Get the name of the charset represented by a UCharsetMatch. * * The storage for the returned name string is owned by the * UCharsetMatch, and will remain valid while the UCharsetMatch * is valid. * * The name returned is suitable for use with the ICU conversion APIs. * * @param ucsm The charset match object. * @param status Any error conditions are reported back in this variable. * @return The name of the matching charset. * * @stable ICU 3.6 */ U_STABLE const char * U_EXPORT2 ucsdet_getName(const UCharsetMatch *ucsm, UErrorCode *status); /** * Get a confidence number for the quality of the match of the byte * data with the charset. Confidence numbers range from zero to 100, * with 100 representing complete confidence and zero representing * no confidence. * * The confidence values are somewhat arbitrary. They define an * an ordering within the results for any single detection operation * but are not generally comparable between the results for different input. * * A confidence value of ten does have a general meaning - it is used * for charsets that can represent the input data, but for which there * is no other indication that suggests that the charset is the correct one. * Pure 7 bit ASCII data, for example, is compatible with a * great many charsets, most of which will appear as possible matches * with a confidence of 10. * * @param ucsm The charset match object. * @param status Any error conditions are reported back in this variable. * @return A confidence number for the charset match. * * @stable ICU 3.6 */ U_STABLE int32_t U_EXPORT2 ucsdet_getConfidence(const UCharsetMatch *ucsm, UErrorCode *status); /** * Get the RFC 3066 code for the language of the input data. * * The Charset Detection service is intended primarily for detecting * charsets, not language. For some, but not all, charsets, a language is * identified as a byproduct of the detection process, and that is what * is returned by this function. * * CAUTION: * 1. Language information is not available for input data encoded in * all charsets. In particular, no language is identified * for UTF-8 input data. * * 2. Closely related languages may sometimes be confused. * * If more accurate language detection is required, a linguistic * analysis package should be used. * * The storage for the returned name string is owned by the * UCharsetMatch, and will remain valid while the UCharsetMatch * is valid. * * @param ucsm The charset match object. * @param status Any error conditions are reported back in this variable. * @return The RFC 3066 code for the language of the input data, or * an empty string if the language could not be determined. * * @stable ICU 3.6 */ U_STABLE const char * U_EXPORT2 ucsdet_getLanguage(const UCharsetMatch *ucsm, UErrorCode *status); /** * Get the entire input text as a UChar string, placing it into * a caller-supplied buffer. A terminating * NUL character will be appended to the buffer if space is available. * * The number of UChars in the output string, not including the terminating * NUL, is returned. * * If the supplied buffer is smaller than required to hold the output, * the contents of the buffer are undefined. The full output string length * (in UChars) is returned as always, and can be used to allocate a buffer * of the correct size. * * * @param ucsm The charset match object. * @param buf A UChar buffer to be filled with the converted text data. * @param cap The capacity of the buffer in UChars. * @param status Any error conditions are reported back in this variable. * @return The number of UChars in the output string. * * @stable ICU 3.6 */ U_STABLE int32_t U_EXPORT2 ucsdet_getUChars(const UCharsetMatch *ucsm, UChar *buf, int32_t cap, UErrorCode *status); /** * Get an iterator over the set of all detectable charsets - * over the charsets that are known to the charset detection * service. * * The returned UEnumeration provides access to the names of * the charsets. * * <p> * The state of the Charset detector that is passed in does not * affect the result of this function, but requiring a valid, open * charset detector as a parameter insures that the charset detection * service has been safely initialized and that the required detection * data is available. * * <p> * <b>Note:</b> Multiple different charset encodings in a same family may use * a single shared name in this implementation. For example, this method returns * an array including "ISO-8859-1" (ISO Latin 1), but not including "windows-1252" * (Windows Latin 1). However, actual detection result could be "windows-1252" * when the input data matches Latin 1 code points with any points only available * in "windows-1252". * * @param ucsd a Charset detector. * @param status Any error conditions are reported back in this variable. * @return an iterator providing access to the detectable charset names. * @stable ICU 3.6 */ U_STABLE UEnumeration * U_EXPORT2 ucsdet_getAllDetectableCharsets(const UCharsetDetector *ucsd, UErrorCode *status); /** * Test whether input filtering is enabled for this charset detector. * Input filtering removes text that appears to be HTML or xml * markup from the input before applying the code page detection * heuristics. * * @param ucsd The charset detector to check. * @return TRUE if filtering is enabled. * @stable ICU 3.6 */ U_STABLE UBool U_EXPORT2 ucsdet_isInputFilterEnabled(const UCharsetDetector *ucsd); /** * Enable filtering of input text. If filtering is enabled, * text within angle brackets ("<" and ">") will be removed * before detection, which will remove most HTML or xml markup. * * @param ucsd the charset detector to be modified. * @param filter <code>true</code> to enable input text filtering. * @return The previous setting. * * @stable ICU 3.6 */ U_STABLE UBool U_EXPORT2 ucsdet_enableInputFilter(UCharsetDetector *ucsd, UBool filter); #ifndef U_HIDE_INTERNAL_API /** * Get an iterator over the set of detectable charsets - * over the charsets that are enabled by the specified charset detector. * * The returned UEnumeration provides access to the names of * the charsets. * * @param ucsd a Charset detector. * @param status Any error conditions are reported back in this variable. * @return an iterator providing access to the detectable charset names by * the specified charset detector. * @internal */ U_INTERNAL UEnumeration * U_EXPORT2 ucsdet_getDetectableCharsets(const UCharsetDetector *ucsd, UErrorCode *status); /** * Enable or disable individual charset encoding. * A name of charset encoding must be included in the names returned by * {@link #ucsdet_getAllDetectableCharsets()}. * * @param ucsd a Charset detector. * @param encoding encoding the name of charset encoding. * @param enabled <code>TRUE</code> to enable, or <code>FALSE</code> to disable the * charset encoding. * @param status receives the return status. When the name of charset encoding * is not supported, U_ILLEGAL_ARGUMENT_ERROR is set. * @internal */ U_INTERNAL void U_EXPORT2 ucsdet_setDetectableCharset(UCharsetDetector *ucsd, const char *encoding, UBool enabled, UErrorCode *status); #endif /* U_HIDE_INTERNAL_API */ #endif #endif /* __UCSDET_H */