Linux server1.dn-server.com 4.18.0-553.89.1.lve.el8.x86_64 #1 SMP Wed Dec 10 13:58:50 UTC 2025 x86_64
LiteSpeed
Server IP : 195.201.204.189 & Your IP : 216.73.216.198
Domains :
Cant Read [ /etc/named.conf ]
User : beriska1
Terminal
Auto Root
Create File
Create Folder
Localroot Suggester
Backdoor Destroyer
Readme
/
opt /
alt /
alt-nodejs6 /
root /
usr /
include /
unicode /
Delete
Unzip
Name
Size
Permission
Date
Action
alphaindex.h
26.27
KB
-rw-r--r--
2019-12-13 16:03
appendable.h
8.43
KB
-rw-r--r--
2019-12-13 16:03
basictz.h
8.84
KB
-rw-r--r--
2019-12-13 16:03
brkiter.h
27.54
KB
-rw-r--r--
2019-12-13 16:03
bytestream.h
9.59
KB
-rw-r--r--
2019-12-13 16:03
bytestrie.h
19.26
KB
-rw-r--r--
2019-12-13 16:03
bytestriebuilder.h
7.1
KB
-rw-r--r--
2019-12-13 16:03
calendar.h
105.35
KB
-rw-r--r--
2019-12-13 16:03
caniter.h
7.35
KB
-rw-r--r--
2019-12-13 16:03
casemap.h
25.31
KB
-rw-r--r--
2019-12-13 16:03
char16ptr.h
7.29
KB
-rw-r--r--
2019-12-13 16:03
chariter.h
24
KB
-rw-r--r--
2019-12-13 16:03
choicfmt.h
23.85
KB
-rw-r--r--
2019-12-13 16:03
coleitr.h
13.7
KB
-rw-r--r--
2019-12-13 16:03
coll.h
55.61
KB
-rw-r--r--
2019-12-13 16:03
compactdecimalformat.h
16.58
KB
-rw-r--r--
2019-12-13 16:03
curramt.h
3.69
KB
-rw-r--r--
2019-12-13 16:03
currpinf.h
7.08
KB
-rw-r--r--
2019-12-13 16:03
currunit.h
3.49
KB
-rw-r--r--
2019-12-13 16:03
datefmt.h
40.18
KB
-rw-r--r--
2019-12-13 16:03
dbbi.h
1.11
KB
-rw-r--r--
2019-12-13 16:03
dcfmtsym.h
17.66
KB
-rw-r--r--
2019-12-13 16:03
decimfmt.h
89.73
KB
-rw-r--r--
2019-12-13 16:03
docmain.h
6.56
KB
-rw-r--r--
2019-12-13 16:03
dtfmtsym.h
37.64
KB
-rw-r--r--
2019-12-13 16:03
dtintrv.h
3.76
KB
-rw-r--r--
2019-12-13 16:03
dtitvfmt.h
42.87
KB
-rw-r--r--
2019-12-13 16:03
dtitvinf.h
18.46
KB
-rw-r--r--
2019-12-13 16:03
dtptngen.h
23.72
KB
-rw-r--r--
2019-12-13 16:03
dtrule.h
8.62
KB
-rw-r--r--
2019-12-13 16:03
edits.h
15.54
KB
-rw-r--r--
2019-12-13 16:03
enumset.h
2.05
KB
-rw-r--r--
2019-12-13 16:03
errorcode.h
4.78
KB
-rw-r--r--
2019-12-13 16:03
fieldpos.h
8.63
KB
-rw-r--r--
2019-12-13 16:03
filteredbrk.h
5.46
KB
-rw-r--r--
2019-12-13 16:03
fmtable.h
24.39
KB
-rw-r--r--
2019-12-13 16:03
format.h
12.44
KB
-rw-r--r--
2019-12-13 16:03
fpositer.h
3.14
KB
-rw-r--r--
2019-12-13 16:03
gender.h
3.18
KB
-rw-r--r--
2019-12-13 16:03
gregocal.h
31.57
KB
-rw-r--r--
2019-12-13 16:03
icudataver.h
1.03
KB
-rw-r--r--
2019-12-13 16:03
icuplug.h
11.86
KB
-rw-r--r--
2019-12-13 16:03
idna.h
12.63
KB
-rw-r--r--
2019-12-13 16:03
listformatter.h
4.98
KB
-rw-r--r--
2019-12-13 16:03
localpointer.h
16.88
KB
-rw-r--r--
2019-12-13 16:03
locdspnm.h
7.05
KB
-rw-r--r--
2019-12-13 16:03
locid.h
31.4
KB
-rw-r--r--
2019-12-13 16:03
measfmt.h
11.25
KB
-rw-r--r--
2019-12-13 16:03
measunit.h
37.74
KB
-rw-r--r--
2019-12-13 16:03
measure.h
4.26
KB
-rw-r--r--
2019-12-13 16:03
messagepattern.h
33.64
KB
-rw-r--r--
2019-12-13 16:03
msgfmt.h
43.16
KB
-rw-r--r--
2019-12-13 16:03
normalizer2.h
33.97
KB
-rw-r--r--
2019-12-13 16:03
normlzr.h
30.74
KB
-rw-r--r--
2019-12-13 16:03
nounit.h
2.6
KB
-rw-r--r--
2019-12-13 16:03
numberformatter.h
64.98
KB
-rw-r--r--
2019-12-13 16:03
numfmt.h
47.76
KB
-rw-r--r--
2019-12-13 16:03
numsys.h
6.73
KB
-rw-r--r--
2019-12-13 16:03
parseerr.h
3.08
KB
-rw-r--r--
2019-12-13 16:03
parsepos.h
5.45
KB
-rw-r--r--
2019-12-13 16:03
platform.h
27.19
KB
-rw-r--r--
2019-12-13 16:03
plurfmt.h
25.66
KB
-rw-r--r--
2019-12-13 16:03
plurrule.h
18.34
KB
-rw-r--r--
2019-12-13 16:03
ptypes.h
3.47
KB
-rw-r--r--
2019-12-13 16:03
putil.h
6.34
KB
-rw-r--r--
2019-12-13 16:03
rbbi.h
27.09
KB
-rw-r--r--
2019-12-13 16:03
rbnf.h
49.76
KB
-rw-r--r--
2019-12-13 16:03
rbtz.h
15.47
KB
-rw-r--r--
2019-12-13 16:03
regex.h
84.91
KB
-rw-r--r--
2019-12-13 16:03
region.h
9.12
KB
-rw-r--r--
2019-12-13 16:03
reldatefmt.h
14.3
KB
-rw-r--r--
2019-12-13 16:03
rep.h
9.5
KB
-rw-r--r--
2019-12-13 16:03
resbund.h
18.01
KB
-rw-r--r--
2019-12-13 16:03
schriter.h
6.26
KB
-rw-r--r--
2019-12-13 16:03
scientificnumberformatter.h
6.59
KB
-rw-r--r--
2019-12-13 16:03
search.h
22.21
KB
-rw-r--r--
2019-12-13 16:03
selfmt.h
14.24
KB
-rw-r--r--
2019-12-13 16:03
simpleformatter.h
11.43
KB
-rw-r--r--
2019-12-13 16:03
simpletz.h
45.24
KB
-rw-r--r--
2019-12-13 16:03
smpdtfmt.h
70.09
KB
-rw-r--r--
2019-12-13 16:03
sortkey.h
11.12
KB
-rw-r--r--
2019-12-13 16:03
std_string.h
1015
B
-rw-r--r--
2019-12-13 16:03
strenum.h
10.04
KB
-rw-r--r--
2019-12-13 16:03
stringoptions.h
5.89
KB
-rw-r--r--
2019-12-13 16:03
stringpiece.h
6.46
KB
-rw-r--r--
2019-12-13 16:03
stringtriebuilder.h
15.2
KB
-rw-r--r--
2019-12-13 16:03
stsearch.h
21.29
KB
-rw-r--r--
2019-12-13 16:03
symtable.h
4.21
KB
-rw-r--r--
2019-12-13 16:03
tblcoll.h
36.4
KB
-rw-r--r--
2019-12-13 16:03
timezone.h
40.83
KB
-rw-r--r--
2019-12-13 16:03
tmunit.h
3.29
KB
-rw-r--r--
2019-12-13 16:03
tmutamt.h
4.8
KB
-rw-r--r--
2019-12-13 16:03
tmutfmt.h
7.79
KB
-rw-r--r--
2019-12-13 16:03
translit.h
54.53
KB
-rw-r--r--
2019-12-13 16:03
tzfmt.h
42.81
KB
-rw-r--r--
2019-12-13 16:03
tznames.h
16.79
KB
-rw-r--r--
2019-12-13 16:03
tzrule.h
35.32
KB
-rw-r--r--
2019-12-13 16:03
tztrans.h
6.07
KB
-rw-r--r--
2019-12-13 16:03
ubidi.h
89.28
KB
-rw-r--r--
2019-12-13 16:03
ubiditransform.h
12.71
KB
-rw-r--r--
2019-12-13 16:03
ubrk.h
24.08
KB
-rw-r--r--
2019-12-13 16:03
ucal.h
54.56
KB
-rw-r--r--
2019-12-13 16:03
ucasemap.h
15.18
KB
-rw-r--r--
2019-12-13 16:03
ucat.h
5.36
KB
-rw-r--r--
2019-12-13 16:03
uchar.h
131.61
KB
-rw-r--r--
2019-12-13 16:03
ucharstrie.h
21.06
KB
-rw-r--r--
2019-12-13 16:03
ucharstriebuilder.h
7.14
KB
-rw-r--r--
2019-12-13 16:03
uchriter.h
13.14
KB
-rw-r--r--
2019-12-13 16:03
uclean.h
11.24
KB
-rw-r--r--
2019-12-13 16:03
ucnv.h
83.06
KB
-rw-r--r--
2019-12-13 16:03
ucnv_cb.h
6.59
KB
-rw-r--r--
2019-12-13 16:03
ucnv_err.h
20.98
KB
-rw-r--r--
2019-12-13 16:03
ucnvsel.h
6.14
KB
-rw-r--r--
2019-12-13 16:03
ucol.h
61.36
KB
-rw-r--r--
2019-12-13 16:03
ucoleitr.h
9.46
KB
-rw-r--r--
2019-12-13 16:03
uconfig.h
11.91
KB
-rw-r--r--
2019-12-13 16:03
ucsdet.h
14.67
KB
-rw-r--r--
2019-12-13 16:03
ucurr.h
15.15
KB
-rw-r--r--
2019-12-13 16:03
udat.h
60.13
KB
-rw-r--r--
2019-12-13 16:03
udata.h
15.53
KB
-rw-r--r--
2019-12-13 16:03
udateintervalformat.h
6.79
KB
-rw-r--r--
2019-12-13 16:03
udatpg.h
24.11
KB
-rw-r--r--
2019-12-13 16:03
udisplaycontext.h
5.89
KB
-rw-r--r--
2019-12-13 16:03
uenum.h
7.9
KB
-rw-r--r--
2019-12-13 16:03
ufieldpositer.h
4.36
KB
-rw-r--r--
2019-12-13 16:03
uformattable.h
10.94
KB
-rw-r--r--
2019-12-13 16:03
ugender.h
2
KB
-rw-r--r--
2019-12-13 16:03
uidna.h
33.37
KB
-rw-r--r--
2019-12-13 16:03
uiter.h
22.77
KB
-rw-r--r--
2019-12-13 16:03
uldnames.h
10.45
KB
-rw-r--r--
2019-12-13 16:03
ulistformatter.h
4.54
KB
-rw-r--r--
2019-12-13 16:03
uloc.h
50.75
KB
-rw-r--r--
2019-12-13 16:03
ulocdata.h
11.26
KB
-rw-r--r--
2019-12-13 16:03
umachine.h
13.1
KB
-rw-r--r--
2019-12-13 16:03
umisc.h
1.33
KB
-rw-r--r--
2019-12-13 16:03
umsg.h
24.23
KB
-rw-r--r--
2019-12-13 16:03
unifilt.h
3.63
KB
-rw-r--r--
2019-12-13 16:03
unifunct.h
3.98
KB
-rw-r--r--
2019-12-13 16:03
unimatch.h
6.04
KB
-rw-r--r--
2019-12-13 16:03
unirepl.h
3.32
KB
-rw-r--r--
2019-12-13 16:03
uniset.h
63.98
KB
-rw-r--r--
2019-12-13 16:03
unistr.h
175.58
KB
-rw-r--r--
2019-12-13 16:03
unorm.h
20.45
KB
-rw-r--r--
2019-12-13 16:03
unorm2.h
24.66
KB
-rw-r--r--
2019-12-13 16:03
unum.h
52.49
KB
-rw-r--r--
2019-12-13 16:03
unumsys.h
7.14
KB
-rw-r--r--
2019-12-13 16:03
uobject.h
10.72
KB
-rw-r--r--
2019-12-13 16:03
upluralrules.h
6.77
KB
-rw-r--r--
2019-12-13 16:03
uregex.h
72.05
KB
-rw-r--r--
2019-12-13 16:03
uregion.h
9.84
KB
-rw-r--r--
2019-12-13 16:03
ureldatefmt.h
12.22
KB
-rw-r--r--
2019-12-13 16:03
urename.h
124.49
KB
-rw-r--r--
2019-12-13 16:03
urep.h
5.38
KB
-rw-r--r--
2019-12-13 16:03
ures.h
36.52
KB
-rw-r--r--
2019-12-13 16:03
uscript.h
25.91
KB
-rw-r--r--
2019-12-13 16:03
usearch.h
38.14
KB
-rw-r--r--
2019-12-13 16:03
uset.h
39.91
KB
-rw-r--r--
2019-12-13 16:03
usetiter.h
9.49
KB
-rw-r--r--
2019-12-13 16:03
ushape.h
18
KB
-rw-r--r--
2019-12-13 16:03
uspoof.h
64.9
KB
-rw-r--r--
2019-12-13 16:03
usprep.h
8.13
KB
-rw-r--r--
2019-12-13 16:03
ustdio.h
38.54
KB
-rw-r--r--
2019-12-13 16:03
ustream.h
1.8
KB
-rw-r--r--
2019-12-13 16:03
ustring.h
72.52
KB
-rw-r--r--
2019-12-13 16:03
ustringtrie.h
3.15
KB
-rw-r--r--
2019-12-13 16:03
utext.h
58.11
KB
-rw-r--r--
2019-12-13 16:03
utf.h
7.86
KB
-rw-r--r--
2019-12-13 16:03
utf16.h
22.49
KB
-rw-r--r--
2019-12-13 16:03
utf32.h
763
B
-rw-r--r--
2019-12-13 16:03
utf8.h
28.16
KB
-rw-r--r--
2019-12-13 16:03
utf_old.h
43.78
KB
-rw-r--r--
2019-12-13 16:03
utmscale.h
13.78
KB
-rw-r--r--
2019-12-13 16:03
utrace.h
13.89
KB
-rw-r--r--
2019-12-13 16:03
utrans.h
25.53
KB
-rw-r--r--
2019-12-13 16:03
utypes.h
29.92
KB
-rw-r--r--
2019-12-13 16:03
uvernum.h
5.69
KB
-rw-r--r--
2019-12-13 16:03
uversion.h
6.4
KB
-rw-r--r--
2019-12-13 16:03
vtzone.h
20.17
KB
-rw-r--r--
2019-12-13 16:03
Save
Rename
// © 2016 and later: Unicode, Inc. and others. // License & terms of use: http://www.unicode.org/copyright.html /* ******************************************************************************* * * Copyright (C) 1999-2015, International Business Machines * Corporation and others. All Rights Reserved. * ******************************************************************************* * file name: utf8.h * encoding: UTF-8 * tab size: 8 (not used) * indentation:4 * * created on: 1999sep13 * created by: Markus W. Scherer */ /** * \file * \brief C API: 8-bit Unicode handling macros * * This file defines macros to deal with 8-bit Unicode (UTF-8) code units (bytes) and strings. * * For more information see utf.h and the ICU User Guide Strings chapter * (http://userguide.icu-project.org/strings). * * <em>Usage:</em> * ICU coding guidelines for if() statements should be followed when using these macros. * Compound statements (curly braces {}) must be used for if-else-while... * bodies and all macro statements should be terminated with semicolon. */ #ifndef __UTF8_H__ #define __UTF8_H__ #include "unicode/umachine.h" #ifndef __UTF_H__ # include "unicode/utf.h" #endif /* internal definitions ----------------------------------------------------- */ /** * Counts the trail bytes for a UTF-8 lead byte. * Returns 0 for 0..0xc1 as well as for 0xf5..0xff. * leadByte might be evaluated multiple times. * * This is internal since it is not meant to be called directly by external clients; * however it is called by public macros in this file and thus must remain stable. * * @param leadByte The first byte of a UTF-8 sequence. Must be 0..0xff. * @internal */ #define U8_COUNT_TRAIL_BYTES(leadByte) \ (U8_IS_LEAD(leadByte) ? \ ((uint8_t)(leadByte)>=0xe0)+((uint8_t)(leadByte)>=0xf0)+1 : 0) /** * Counts the trail bytes for a UTF-8 lead byte of a valid UTF-8 sequence. * Returns 0 for 0..0xc1. Undefined for 0xf5..0xff. * leadByte might be evaluated multiple times. * * This is internal since it is not meant to be called directly by external clients; * however it is called by public macros in this file and thus must remain stable. * * @param leadByte The first byte of a UTF-8 sequence. Must be 0..0xff. * @internal */ #define U8_COUNT_TRAIL_BYTES_UNSAFE(leadByte) \ (((uint8_t)(leadByte)>=0xc2)+((uint8_t)(leadByte)>=0xe0)+((uint8_t)(leadByte)>=0xf0)) /** * Mask a UTF-8 lead byte, leave only the lower bits that form part of the code point value. * * This is internal since it is not meant to be called directly by external clients; * however it is called by public macros in this file and thus must remain stable. * @internal */ #define U8_MASK_LEAD_BYTE(leadByte, countTrailBytes) ((leadByte)&=(1<<(6-(countTrailBytes)))-1) /** * Internal bit vector for 3-byte UTF-8 validity check, for use in U8_IS_VALID_LEAD3_AND_T1. * Each bit indicates whether one lead byte + first trail byte pair starts a valid sequence. * Lead byte E0..EF bits 3..0 are used as byte index, * first trail byte bits 7..5 are used as bit index into that byte. * @see U8_IS_VALID_LEAD3_AND_T1 * @internal */ #define U8_LEAD3_T1_BITS "\x20\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x10\x30\x30" /** * Internal 3-byte UTF-8 validity check. * Non-zero if lead byte E0..EF and first trail byte 00..FF start a valid sequence. * @internal */ #define U8_IS_VALID_LEAD3_AND_T1(lead, t1) (U8_LEAD3_T1_BITS[(lead)&0xf]&(1<<((uint8_t)(t1)>>5))) /** * Internal bit vector for 4-byte UTF-8 validity check, for use in U8_IS_VALID_LEAD4_AND_T1. * Each bit indicates whether one lead byte + first trail byte pair starts a valid sequence. * First trail byte bits 7..4 are used as byte index, * lead byte F0..F4 bits 2..0 are used as bit index into that byte. * @see U8_IS_VALID_LEAD4_AND_T1 * @internal */ #define U8_LEAD4_T1_BITS "\x00\x00\x00\x00\x00\x00\x00\x00\x1E\x0F\x0F\x0F\x00\x00\x00\x00" /** * Internal 4-byte UTF-8 validity check. * Non-zero if lead byte F0..F4 and first trail byte 00..FF start a valid sequence. * @internal */ #define U8_IS_VALID_LEAD4_AND_T1(lead, t1) (U8_LEAD4_T1_BITS[(uint8_t)(t1)>>4]&(1<<((lead)&7))) /** * Function for handling "next code point" with error-checking. * * This is internal since it is not meant to be called directly by external clients; * however it is U_STABLE (not U_INTERNAL) since it is called by public macros in this * file and thus must remain stable, and should not be hidden when other internal * functions are hidden (otherwise public macros would fail to compile). * @internal */ U_STABLE UChar32 U_EXPORT2 utf8_nextCharSafeBody(const uint8_t *s, int32_t *pi, int32_t length, UChar32 c, UBool strict); /** * Function for handling "append code point" with error-checking. * * This is internal since it is not meant to be called directly by external clients; * however it is U_STABLE (not U_INTERNAL) since it is called by public macros in this * file and thus must remain stable, and should not be hidden when other internal * functions are hidden (otherwise public macros would fail to compile). * @internal */ U_STABLE int32_t U_EXPORT2 utf8_appendCharSafeBody(uint8_t *s, int32_t i, int32_t length, UChar32 c, UBool *pIsError); /** * Function for handling "previous code point" with error-checking. * * This is internal since it is not meant to be called directly by external clients; * however it is U_STABLE (not U_INTERNAL) since it is called by public macros in this * file and thus must remain stable, and should not be hidden when other internal * functions are hidden (otherwise public macros would fail to compile). * @internal */ U_STABLE UChar32 U_EXPORT2 utf8_prevCharSafeBody(const uint8_t *s, int32_t start, int32_t *pi, UChar32 c, UBool strict); /** * Function for handling "skip backward one code point" with error-checking. * * This is internal since it is not meant to be called directly by external clients; * however it is U_STABLE (not U_INTERNAL) since it is called by public macros in this * file and thus must remain stable, and should not be hidden when other internal * functions are hidden (otherwise public macros would fail to compile). * @internal */ U_STABLE int32_t U_EXPORT2 utf8_back1SafeBody(const uint8_t *s, int32_t start, int32_t i); /* single-code point definitions -------------------------------------------- */ /** * Does this code unit (byte) encode a code point by itself (US-ASCII 0..0x7f)? * @param c 8-bit code unit (byte) * @return TRUE or FALSE * @stable ICU 2.4 */ #define U8_IS_SINGLE(c) (((c)&0x80)==0) /** * Is this code unit (byte) a UTF-8 lead byte? (0xC2..0xF4) * @param c 8-bit code unit (byte) * @return TRUE or FALSE * @stable ICU 2.4 */ #define U8_IS_LEAD(c) ((uint8_t)((c)-0xc2)<=0x32) // 0x32=0xf4-0xc2 /** * Is this code unit (byte) a UTF-8 trail byte? (0x80..0xBF) * @param c 8-bit code unit (byte) * @return TRUE or FALSE * @stable ICU 2.4 */ #define U8_IS_TRAIL(c) ((int8_t)(c)<-0x40) /** * How many code units (bytes) are used for the UTF-8 encoding * of this Unicode code point? * @param c 32-bit code point * @return 1..4, or 0 if c is a surrogate or not a Unicode code point * @stable ICU 2.4 */ #define U8_LENGTH(c) \ ((uint32_t)(c)<=0x7f ? 1 : \ ((uint32_t)(c)<=0x7ff ? 2 : \ ((uint32_t)(c)<=0xd7ff ? 3 : \ ((uint32_t)(c)<=0xdfff || (uint32_t)(c)>0x10ffff ? 0 : \ ((uint32_t)(c)<=0xffff ? 3 : 4)\ ) \ ) \ ) \ ) /** * The maximum number of UTF-8 code units (bytes) per Unicode code point (U+0000..U+10ffff). * @return 4 * @stable ICU 2.4 */ #define U8_MAX_LENGTH 4 /** * Get a code point from a string at a random-access offset, * without changing the offset. * The offset may point to either the lead byte or one of the trail bytes * for a code point, in which case the macro will read all of the bytes * for the code point. * The result is undefined if the offset points to an illegal UTF-8 * byte sequence. * Iteration through a string is more efficient with U8_NEXT_UNSAFE or U8_NEXT. * * @param s const uint8_t * string * @param i string offset * @param c output UChar32 variable * @see U8_GET * @stable ICU 2.4 */ #define U8_GET_UNSAFE(s, i, c) { \ int32_t _u8_get_unsafe_index=(int32_t)(i); \ U8_SET_CP_START_UNSAFE(s, _u8_get_unsafe_index); \ U8_NEXT_UNSAFE(s, _u8_get_unsafe_index, c); \ } /** * Get a code point from a string at a random-access offset, * without changing the offset. * The offset may point to either the lead byte or one of the trail bytes * for a code point, in which case the macro will read all of the bytes * for the code point. * * The length can be negative for a NUL-terminated string. * * If the offset points to an illegal UTF-8 byte sequence, then * c is set to a negative value. * Iteration through a string is more efficient with U8_NEXT_UNSAFE or U8_NEXT. * * @param s const uint8_t * string * @param start int32_t starting string offset * @param i int32_t string offset, must be start<=i<length * @param length int32_t string length * @param c output UChar32 variable, set to <0 in case of an error * @see U8_GET_UNSAFE * @stable ICU 2.4 */ #define U8_GET(s, start, i, length, c) { \ int32_t _u8_get_index=(i); \ U8_SET_CP_START(s, start, _u8_get_index); \ U8_NEXT(s, _u8_get_index, length, c); \ } /** * Get a code point from a string at a random-access offset, * without changing the offset. * The offset may point to either the lead byte or one of the trail bytes * for a code point, in which case the macro will read all of the bytes * for the code point. * * The length can be negative for a NUL-terminated string. * * If the offset points to an illegal UTF-8 byte sequence, then * c is set to U+FFFD. * Iteration through a string is more efficient with U8_NEXT_UNSAFE or U8_NEXT_OR_FFFD. * * This macro does not distinguish between a real U+FFFD in the text * and U+FFFD returned for an ill-formed sequence. * Use U8_GET() if that distinction is important. * * @param s const uint8_t * string * @param start int32_t starting string offset * @param i int32_t string offset, must be start<=i<length * @param length int32_t string length * @param c output UChar32 variable, set to U+FFFD in case of an error * @see U8_GET * @stable ICU 51 */ #define U8_GET_OR_FFFD(s, start, i, length, c) { \ int32_t _u8_get_index=(i); \ U8_SET_CP_START(s, start, _u8_get_index); \ U8_NEXT_OR_FFFD(s, _u8_get_index, length, c); \ } /* definitions with forward iteration --------------------------------------- */ /** * Get a code point from a string at a code point boundary offset, * and advance the offset to the next code point boundary. * (Post-incrementing forward iteration.) * "Unsafe" macro, assumes well-formed UTF-8. * * The offset may point to the lead byte of a multi-byte sequence, * in which case the macro will read the whole sequence. * The result is undefined if the offset points to a trail byte * or an illegal UTF-8 sequence. * * @param s const uint8_t * string * @param i string offset * @param c output UChar32 variable * @see U8_NEXT * @stable ICU 2.4 */ #define U8_NEXT_UNSAFE(s, i, c) { \ (c)=(uint8_t)(s)[(i)++]; \ if(!U8_IS_SINGLE(c)) { \ if((c)<0xe0) { \ (c)=(((c)&0x1f)<<6)|((s)[(i)++]&0x3f); \ } else if((c)<0xf0) { \ /* no need for (c&0xf) because the upper bits are truncated after <<12 in the cast to (UChar) */ \ (c)=(UChar)(((c)<<12)|(((s)[i]&0x3f)<<6)|((s)[(i)+1]&0x3f)); \ (i)+=2; \ } else { \ (c)=(((c)&7)<<18)|(((s)[i]&0x3f)<<12)|(((s)[(i)+1]&0x3f)<<6)|((s)[(i)+2]&0x3f); \ (i)+=3; \ } \ } \ } /** * Get a code point from a string at a code point boundary offset, * and advance the offset to the next code point boundary. * (Post-incrementing forward iteration.) * "Safe" macro, checks for illegal sequences and for string boundaries. * * The length can be negative for a NUL-terminated string. * * The offset may point to the lead byte of a multi-byte sequence, * in which case the macro will read the whole sequence. * If the offset points to a trail byte or an illegal UTF-8 sequence, then * c is set to a negative value. * * @param s const uint8_t * string * @param i int32_t string offset, must be i<length * @param length int32_t string length * @param c output UChar32 variable, set to <0 in case of an error * @see U8_NEXT_UNSAFE * @stable ICU 2.4 */ #define U8_NEXT(s, i, length, c) { \ (c)=(uint8_t)(s)[(i)++]; \ if(!U8_IS_SINGLE(c)) { \ uint8_t __t1, __t2; \ if( /* handle U+0800..U+FFFF inline */ \ (0xe0<=(c) && (c)<0xf0) && \ (((i)+1)<(length) || (length)<0) && \ U8_IS_VALID_LEAD3_AND_T1((c), __t1=(s)[i]) && \ (__t2=(s)[(i)+1]-0x80)<=0x3f) { \ (c)=(((c)&0xf)<<12)|((__t1&0x3f)<<6)|__t2; \ (i)+=2; \ } else if( /* handle U+0080..U+07FF inline */ \ ((c)<0xe0 && (c)>=0xc2) && \ ((i)!=(length)) && \ (__t1=(s)[i]-0x80)<=0x3f) { \ (c)=(((c)&0x1f)<<6)|__t1; \ ++(i); \ } else { \ /* function call for "complicated" and error cases */ \ (c)=utf8_nextCharSafeBody((const uint8_t *)s, &(i), (length), c, -1); \ } \ } \ } /** * Get a code point from a string at a code point boundary offset, * and advance the offset to the next code point boundary. * (Post-incrementing forward iteration.) * "Safe" macro, checks for illegal sequences and for string boundaries. * * The length can be negative for a NUL-terminated string. * * The offset may point to the lead byte of a multi-byte sequence, * in which case the macro will read the whole sequence. * If the offset points to a trail byte or an illegal UTF-8 sequence, then * c is set to U+FFFD. * * This macro does not distinguish between a real U+FFFD in the text * and U+FFFD returned for an ill-formed sequence. * Use U8_NEXT() if that distinction is important. * * @param s const uint8_t * string * @param i int32_t string offset, must be i<length * @param length int32_t string length * @param c output UChar32 variable, set to U+FFFD in case of an error * @see U8_NEXT * @stable ICU 51 */ #define U8_NEXT_OR_FFFD(s, i, length, c) { \ (c)=(uint8_t)(s)[(i)++]; \ if(!U8_IS_SINGLE(c)) { \ uint8_t __t1, __t2; \ if( /* handle U+0800..U+FFFF inline */ \ (0xe0<=(c) && (c)<0xf0) && \ (((i)+1)<(length) || (length)<0) && \ U8_IS_VALID_LEAD3_AND_T1((c), __t1=(s)[i]) && \ (__t2=(s)[(i)+1]-0x80)<=0x3f) { \ (c)=(((c)&0xf)<<12)|((__t1&0x3f)<<6)|__t2; \ (i)+=2; \ } else if( /* handle U+0080..U+07FF inline */ \ ((c)<0xe0 && (c)>=0xc2) && \ ((i)!=(length)) && \ (__t1=(s)[i]-0x80)<=0x3f) { \ (c)=(((c)&0x1f)<<6)|__t1; \ ++(i); \ } else { \ /* function call for "complicated" and error cases */ \ (c)=utf8_nextCharSafeBody((const uint8_t *)s, &(i), (length), c, -3); \ } \ } \ } /** * Append a code point to a string, overwriting 1 to 4 bytes. * The offset points to the current end of the string contents * and is advanced (post-increment). * "Unsafe" macro, assumes a valid code point and sufficient space in the string. * Otherwise, the result is undefined. * * @param s const uint8_t * string buffer * @param i string offset * @param c code point to append * @see U8_APPEND * @stable ICU 2.4 */ #define U8_APPEND_UNSAFE(s, i, c) { \ if((uint32_t)(c)<=0x7f) { \ (s)[(i)++]=(uint8_t)(c); \ } else { \ if((uint32_t)(c)<=0x7ff) { \ (s)[(i)++]=(uint8_t)(((c)>>6)|0xc0); \ } else { \ if((uint32_t)(c)<=0xffff) { \ (s)[(i)++]=(uint8_t)(((c)>>12)|0xe0); \ } else { \ (s)[(i)++]=(uint8_t)(((c)>>18)|0xf0); \ (s)[(i)++]=(uint8_t)((((c)>>12)&0x3f)|0x80); \ } \ (s)[(i)++]=(uint8_t)((((c)>>6)&0x3f)|0x80); \ } \ (s)[(i)++]=(uint8_t)(((c)&0x3f)|0x80); \ } \ } /** * Append a code point to a string, overwriting 1 to 4 bytes. * The offset points to the current end of the string contents * and is advanced (post-increment). * "Safe" macro, checks for a valid code point. * If a non-ASCII code point is written, checks for sufficient space in the string. * If the code point is not valid or trail bytes do not fit, * then isError is set to TRUE. * * @param s const uint8_t * string buffer * @param i int32_t string offset, must be i<capacity * @param capacity int32_t size of the string buffer * @param c UChar32 code point to append * @param isError output UBool set to TRUE if an error occurs, otherwise not modified * @see U8_APPEND_UNSAFE * @stable ICU 2.4 */ #define U8_APPEND(s, i, capacity, c, isError) { \ if((uint32_t)(c)<=0x7f) { \ (s)[(i)++]=(uint8_t)(c); \ } else if((uint32_t)(c)<=0x7ff && (i)+1<(capacity)) { \ (s)[(i)++]=(uint8_t)(((c)>>6)|0xc0); \ (s)[(i)++]=(uint8_t)(((c)&0x3f)|0x80); \ } else if((uint32_t)(c)<=0xd7ff && (i)+2<(capacity)) { \ (s)[(i)++]=(uint8_t)(((c)>>12)|0xe0); \ (s)[(i)++]=(uint8_t)((((c)>>6)&0x3f)|0x80); \ (s)[(i)++]=(uint8_t)(((c)&0x3f)|0x80); \ } else { \ (i)=utf8_appendCharSafeBody(s, (i), (capacity), c, &(isError)); \ } \ } /** * Advance the string offset from one code point boundary to the next. * (Post-incrementing iteration.) * "Unsafe" macro, assumes well-formed UTF-8. * * @param s const uint8_t * string * @param i string offset * @see U8_FWD_1 * @stable ICU 2.4 */ #define U8_FWD_1_UNSAFE(s, i) { \ (i)+=1+U8_COUNT_TRAIL_BYTES_UNSAFE((s)[i]); \ } /** * Advance the string offset from one code point boundary to the next. * (Post-incrementing iteration.) * "Safe" macro, checks for illegal sequences and for string boundaries. * * The length can be negative for a NUL-terminated string. * * @param s const uint8_t * string * @param i int32_t string offset, must be i<length * @param length int32_t string length * @see U8_FWD_1_UNSAFE * @stable ICU 2.4 */ #define U8_FWD_1(s, i, length) { \ uint8_t __b=(s)[(i)++]; \ if(U8_IS_LEAD(__b) && (i)!=(length)) { \ uint8_t __t1=(s)[i]; \ if((0xe0<=__b && __b<0xf0)) { \ if(U8_IS_VALID_LEAD3_AND_T1(__b, __t1) && \ ++(i)!=(length) && U8_IS_TRAIL((s)[i])) { \ ++(i); \ } \ } else if(__b<0xe0) { \ if(U8_IS_TRAIL(__t1)) { \ ++(i); \ } \ } else /* c>=0xf0 */ { \ if(U8_IS_VALID_LEAD4_AND_T1(__b, __t1) && \ ++(i)!=(length) && U8_IS_TRAIL((s)[i]) && \ ++(i)!=(length) && U8_IS_TRAIL((s)[i])) { \ ++(i); \ } \ } \ } \ } /** * Advance the string offset from one code point boundary to the n-th next one, * i.e., move forward by n code points. * (Post-incrementing iteration.) * "Unsafe" macro, assumes well-formed UTF-8. * * @param s const uint8_t * string * @param i string offset * @param n number of code points to skip * @see U8_FWD_N * @stable ICU 2.4 */ #define U8_FWD_N_UNSAFE(s, i, n) { \ int32_t __N=(n); \ while(__N>0) { \ U8_FWD_1_UNSAFE(s, i); \ --__N; \ } \ } /** * Advance the string offset from one code point boundary to the n-th next one, * i.e., move forward by n code points. * (Post-incrementing iteration.) * "Safe" macro, checks for illegal sequences and for string boundaries. * * The length can be negative for a NUL-terminated string. * * @param s const uint8_t * string * @param i int32_t string offset, must be i<length * @param length int32_t string length * @param n number of code points to skip * @see U8_FWD_N_UNSAFE * @stable ICU 2.4 */ #define U8_FWD_N(s, i, length, n) { \ int32_t __N=(n); \ while(__N>0 && ((i)<(length) || ((length)<0 && (s)[i]!=0))) { \ U8_FWD_1(s, i, length); \ --__N; \ } \ } /** * Adjust a random-access offset to a code point boundary * at the start of a code point. * If the offset points to a UTF-8 trail byte, * then the offset is moved backward to the corresponding lead byte. * Otherwise, it is not modified. * "Unsafe" macro, assumes well-formed UTF-8. * * @param s const uint8_t * string * @param i string offset * @see U8_SET_CP_START * @stable ICU 2.4 */ #define U8_SET_CP_START_UNSAFE(s, i) { \ while(U8_IS_TRAIL((s)[i])) { --(i); } \ } /** * Adjust a random-access offset to a code point boundary * at the start of a code point. * If the offset points to a UTF-8 trail byte, * then the offset is moved backward to the corresponding lead byte. * Otherwise, it is not modified. * "Safe" macro, checks for illegal sequences and for string boundaries. * * @param s const uint8_t * string * @param start int32_t starting string offset (usually 0) * @param i int32_t string offset, must be start<=i * @see U8_SET_CP_START_UNSAFE * @stable ICU 2.4 */ #define U8_SET_CP_START(s, start, i) { \ if(U8_IS_TRAIL((s)[(i)])) { \ (i)=utf8_back1SafeBody(s, start, (i)); \ } \ } /* definitions with backward iteration -------------------------------------- */ /** * Move the string offset from one code point boundary to the previous one * and get the code point between them. * (Pre-decrementing backward iteration.) * "Unsafe" macro, assumes well-formed UTF-8. * * The input offset may be the same as the string length. * If the offset is behind a multi-byte sequence, then the macro will read * the whole sequence. * If the offset is behind a lead byte, then that itself * will be returned as the code point. * The result is undefined if the offset is behind an illegal UTF-8 sequence. * * @param s const uint8_t * string * @param i string offset * @param c output UChar32 variable * @see U8_PREV * @stable ICU 2.4 */ #define U8_PREV_UNSAFE(s, i, c) { \ (c)=(uint8_t)(s)[--(i)]; \ if(U8_IS_TRAIL(c)) { \ uint8_t __b, __count=1, __shift=6; \ \ /* c is a trail byte */ \ (c)&=0x3f; \ for(;;) { \ __b=(s)[--(i)]; \ if(__b>=0xc0) { \ U8_MASK_LEAD_BYTE(__b, __count); \ (c)|=(UChar32)__b<<__shift; \ break; \ } else { \ (c)|=(UChar32)(__b&0x3f)<<__shift; \ ++__count; \ __shift+=6; \ } \ } \ } \ } /** * Move the string offset from one code point boundary to the previous one * and get the code point between them. * (Pre-decrementing backward iteration.) * "Safe" macro, checks for illegal sequences and for string boundaries. * * The input offset may be the same as the string length. * If the offset is behind a multi-byte sequence, then the macro will read * the whole sequence. * If the offset is behind a lead byte, then that itself * will be returned as the code point. * If the offset is behind an illegal UTF-8 sequence, then c is set to a negative value. * * @param s const uint8_t * string * @param start int32_t starting string offset (usually 0) * @param i int32_t string offset, must be start<i * @param c output UChar32 variable, set to <0 in case of an error * @see U8_PREV_UNSAFE * @stable ICU 2.4 */ #define U8_PREV(s, start, i, c) { \ (c)=(uint8_t)(s)[--(i)]; \ if(!U8_IS_SINGLE(c)) { \ (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -1); \ } \ } /** * Move the string offset from one code point boundary to the previous one * and get the code point between them. * (Pre-decrementing backward iteration.) * "Safe" macro, checks for illegal sequences and for string boundaries. * * The input offset may be the same as the string length. * If the offset is behind a multi-byte sequence, then the macro will read * the whole sequence. * If the offset is behind a lead byte, then that itself * will be returned as the code point. * If the offset is behind an illegal UTF-8 sequence, then c is set to U+FFFD. * * This macro does not distinguish between a real U+FFFD in the text * and U+FFFD returned for an ill-formed sequence. * Use U8_PREV() if that distinction is important. * * @param s const uint8_t * string * @param start int32_t starting string offset (usually 0) * @param i int32_t string offset, must be start<i * @param c output UChar32 variable, set to U+FFFD in case of an error * @see U8_PREV * @stable ICU 51 */ #define U8_PREV_OR_FFFD(s, start, i, c) { \ (c)=(uint8_t)(s)[--(i)]; \ if(!U8_IS_SINGLE(c)) { \ (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -3); \ } \ } /** * Move the string offset from one code point boundary to the previous one. * (Pre-decrementing backward iteration.) * The input offset may be the same as the string length. * "Unsafe" macro, assumes well-formed UTF-8. * * @param s const uint8_t * string * @param i string offset * @see U8_BACK_1 * @stable ICU 2.4 */ #define U8_BACK_1_UNSAFE(s, i) { \ while(U8_IS_TRAIL((s)[--(i)])) {} \ } /** * Move the string offset from one code point boundary to the previous one. * (Pre-decrementing backward iteration.) * The input offset may be the same as the string length. * "Safe" macro, checks for illegal sequences and for string boundaries. * * @param s const uint8_t * string * @param start int32_t starting string offset (usually 0) * @param i int32_t string offset, must be start<i * @see U8_BACK_1_UNSAFE * @stable ICU 2.4 */ #define U8_BACK_1(s, start, i) { \ if(U8_IS_TRAIL((s)[--(i)])) { \ (i)=utf8_back1SafeBody(s, start, (i)); \ } \ } /** * Move the string offset from one code point boundary to the n-th one before it, * i.e., move backward by n code points. * (Pre-decrementing backward iteration.) * The input offset may be the same as the string length. * "Unsafe" macro, assumes well-formed UTF-8. * * @param s const uint8_t * string * @param i string offset * @param n number of code points to skip * @see U8_BACK_N * @stable ICU 2.4 */ #define U8_BACK_N_UNSAFE(s, i, n) { \ int32_t __N=(n); \ while(__N>0) { \ U8_BACK_1_UNSAFE(s, i); \ --__N; \ } \ } /** * Move the string offset from one code point boundary to the n-th one before it, * i.e., move backward by n code points. * (Pre-decrementing backward iteration.) * The input offset may be the same as the string length. * "Safe" macro, checks for illegal sequences and for string boundaries. * * @param s const uint8_t * string * @param start int32_t index of the start of the string * @param i int32_t string offset, must be start<i * @param n number of code points to skip * @see U8_BACK_N_UNSAFE * @stable ICU 2.4 */ #define U8_BACK_N(s, start, i, n) { \ int32_t __N=(n); \ while(__N>0 && (i)>(start)) { \ U8_BACK_1(s, start, i); \ --__N; \ } \ } /** * Adjust a random-access offset to a code point boundary after a code point. * If the offset is behind a partial multi-byte sequence, * then the offset is incremented to behind the whole sequence. * Otherwise, it is not modified. * The input offset may be the same as the string length. * "Unsafe" macro, assumes well-formed UTF-8. * * @param s const uint8_t * string * @param i string offset * @see U8_SET_CP_LIMIT * @stable ICU 2.4 */ #define U8_SET_CP_LIMIT_UNSAFE(s, i) { \ U8_BACK_1_UNSAFE(s, i); \ U8_FWD_1_UNSAFE(s, i); \ } /** * Adjust a random-access offset to a code point boundary after a code point. * If the offset is behind a partial multi-byte sequence, * then the offset is incremented to behind the whole sequence. * Otherwise, it is not modified. * The input offset may be the same as the string length. * "Safe" macro, checks for illegal sequences and for string boundaries. * * The length can be negative for a NUL-terminated string. * * @param s const uint8_t * string * @param start int32_t starting string offset (usually 0) * @param i int32_t string offset, must be start<=i<=length * @param length int32_t string length * @see U8_SET_CP_LIMIT_UNSAFE * @stable ICU 2.4 */ #define U8_SET_CP_LIMIT(s, start, i, length) { \ if((start)<(i) && ((i)<(length) || (length)<0)) { \ U8_BACK_1(s, start, i); \ U8_FWD_1(s, i, length); \ } \ } #endif