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 : 3.141.244.88
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) 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) UPRV_BLOCK_MACRO_BEGIN { \ 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); \ } UPRV_BLOCK_MACRO_END /** * 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) UPRV_BLOCK_MACRO_BEGIN { \ int32_t _u8_get_index=(i); \ U8_SET_CP_START(s, start, _u8_get_index); \ U8_NEXT(s, _u8_get_index, length, c); \ } UPRV_BLOCK_MACRO_END /** * 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) UPRV_BLOCK_MACRO_BEGIN { \ 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); \ } UPRV_BLOCK_MACRO_END /* 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) UPRV_BLOCK_MACRO_BEGIN { \ (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; \ } \ } \ } UPRV_BLOCK_MACRO_END /** * 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) U8_INTERNAL_NEXT_OR_SUB(s, i, length, c, U_SENTINEL) /** * 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) U8_INTERNAL_NEXT_OR_SUB(s, i, length, c, 0xfffd) /** @internal */ #define U8_INTERNAL_NEXT_OR_SUB(s, i, length, c, sub) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(uint8_t)(s)[(i)++]; \ if(!U8_IS_SINGLE(c)) { \ uint8_t __t = 0; \ if((i)!=(length) && \ /* fetch/validate/assemble all but last trail byte */ \ ((c)>=0xe0 ? \ ((c)<0xf0 ? /* U+0800..U+FFFF except surrogates */ \ U8_LEAD3_T1_BITS[(c)&=0xf]&(1<<((__t=(s)[i])>>5)) && \ (__t&=0x3f, 1) \ : /* U+10000..U+10FFFF */ \ ((c)-=0xf0)<=4 && \ U8_LEAD4_T1_BITS[(__t=(s)[i])>>4]&(1<<(c)) && \ ((c)=((c)<<6)|(__t&0x3f), ++(i)!=(length)) && \ (__t=(s)[i]-0x80)<=0x3f) && \ /* valid second-to-last trail byte */ \ ((c)=((c)<<6)|__t, ++(i)!=(length)) \ : /* U+0080..U+07FF */ \ (c)>=0xc2 && ((c)&=0x1f, 1)) && \ /* last trail byte */ \ (__t=(s)[i]-0x80)<=0x3f && \ ((c)=((c)<<6)|__t, ++(i), 1)) { \ } else { \ (c)=(sub); /* ill-formed*/ \ } \ } \ } UPRV_BLOCK_MACRO_END /** * 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) UPRV_BLOCK_MACRO_BEGIN { \ uint32_t __uc=(c); \ if(__uc<=0x7f) { \ (s)[(i)++]=(uint8_t)__uc; \ } else { \ if(__uc<=0x7ff) { \ (s)[(i)++]=(uint8_t)((__uc>>6)|0xc0); \ } else { \ if(__uc<=0xffff) { \ (s)[(i)++]=(uint8_t)((__uc>>12)|0xe0); \ } else { \ (s)[(i)++]=(uint8_t)((__uc>>18)|0xf0); \ (s)[(i)++]=(uint8_t)(((__uc>>12)&0x3f)|0x80); \ } \ (s)[(i)++]=(uint8_t)(((__uc>>6)&0x3f)|0x80); \ } \ (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \ } \ } UPRV_BLOCK_MACRO_END /** * 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) UPRV_BLOCK_MACRO_BEGIN { \ uint32_t __uc=(c); \ if(__uc<=0x7f) { \ (s)[(i)++]=(uint8_t)__uc; \ } else if(__uc<=0x7ff && (i)+1<(capacity)) { \ (s)[(i)++]=(uint8_t)((__uc>>6)|0xc0); \ (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \ } else if((__uc<=0xd7ff || (0xe000<=__uc && __uc<=0xffff)) && (i)+2<(capacity)) { \ (s)[(i)++]=(uint8_t)((__uc>>12)|0xe0); \ (s)[(i)++]=(uint8_t)(((__uc>>6)&0x3f)|0x80); \ (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \ } else if(0xffff<__uc && __uc<=0x10ffff && (i)+3<(capacity)) { \ (s)[(i)++]=(uint8_t)((__uc>>18)|0xf0); \ (s)[(i)++]=(uint8_t)(((__uc>>12)&0x3f)|0x80); \ (s)[(i)++]=(uint8_t)(((__uc>>6)&0x3f)|0x80); \ (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \ } else { \ (isError)=TRUE; \ } \ } UPRV_BLOCK_MACRO_END /** * 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) UPRV_BLOCK_MACRO_BEGIN { \ (i)+=1+U8_COUNT_TRAIL_BYTES_UNSAFE((s)[i]); \ } UPRV_BLOCK_MACRO_END /** * 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) UPRV_BLOCK_MACRO_BEGIN { \ 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); \ } \ } \ } \ } UPRV_BLOCK_MACRO_END /** * 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) UPRV_BLOCK_MACRO_BEGIN { \ int32_t __N=(n); \ while(__N>0) { \ U8_FWD_1_UNSAFE(s, i); \ --__N; \ } \ } UPRV_BLOCK_MACRO_END /** * 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) UPRV_BLOCK_MACRO_BEGIN { \ int32_t __N=(n); \ while(__N>0 && ((i)<(length) || ((length)<0 && (s)[i]!=0))) { \ U8_FWD_1(s, i, length); \ --__N; \ } \ } UPRV_BLOCK_MACRO_END /** * 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) UPRV_BLOCK_MACRO_BEGIN { \ while(U8_IS_TRAIL((s)[i])) { --(i); } \ } UPRV_BLOCK_MACRO_END /** * 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. * Unlike U8_TRUNCATE_IF_INCOMPLETE(), this macro always reads s[i]. * * @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 * @see U8_TRUNCATE_IF_INCOMPLETE * @stable ICU 2.4 */ #define U8_SET_CP_START(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \ if(U8_IS_TRAIL((s)[(i)])) { \ (i)=utf8_back1SafeBody(s, start, (i)); \ } \ } UPRV_BLOCK_MACRO_END /** * If the string ends with a UTF-8 byte sequence that is valid so far * but incomplete, then reduce the length of the string to end before * the lead byte of that incomplete sequence. * For example, if the string ends with E1 80, the length is reduced by 2. * * In all other cases (the string ends with a complete sequence, or it is not * possible for any further trail byte to extend the trailing sequence) * the length remains unchanged. * * Useful for processing text split across multiple buffers * (save the incomplete sequence for later) * and for optimizing iteration * (check for string length only once per character). * * "Safe" macro, checks for illegal sequences and for string boundaries. * Unlike U8_SET_CP_START(), this macro never reads s[length]. * * (In UTF-16, simply check for U16_IS_LEAD(last code unit).) * * @param s const uint8_t * string * @param start int32_t starting string offset (usually 0) * @param length int32_t string length (usually start<=length) * @see U8_SET_CP_START * @stable ICU 61 */ #define U8_TRUNCATE_IF_INCOMPLETE(s, start, length) UPRV_BLOCK_MACRO_BEGIN { \ if((length)>(start)) { \ uint8_t __b1=s[(length)-1]; \ if(U8_IS_SINGLE(__b1)) { \ /* common ASCII character */ \ } else if(U8_IS_LEAD(__b1)) { \ --(length); \ } else if(U8_IS_TRAIL(__b1) && ((length)-2)>=(start)) { \ uint8_t __b2=s[(length)-2]; \ if(0xe0<=__b2 && __b2<=0xf4) { \ if(__b2<0xf0 ? U8_IS_VALID_LEAD3_AND_T1(__b2, __b1) : \ U8_IS_VALID_LEAD4_AND_T1(__b2, __b1)) { \ (length)-=2; \ } \ } else if(U8_IS_TRAIL(__b2) && ((length)-3)>=(start)) { \ uint8_t __b3=s[(length)-3]; \ if(0xf0<=__b3 && __b3<=0xf4 && U8_IS_VALID_LEAD4_AND_T1(__b3, __b2)) { \ (length)-=3; \ } \ } \ } \ } \ } UPRV_BLOCK_MACRO_END /* 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) UPRV_BLOCK_MACRO_BEGIN { \ (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; \ } \ } \ } \ } UPRV_BLOCK_MACRO_END /** * 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) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(uint8_t)(s)[--(i)]; \ if(!U8_IS_SINGLE(c)) { \ (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -1); \ } \ } UPRV_BLOCK_MACRO_END /** * 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) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(uint8_t)(s)[--(i)]; \ if(!U8_IS_SINGLE(c)) { \ (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -3); \ } \ } UPRV_BLOCK_MACRO_END /** * 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) UPRV_BLOCK_MACRO_BEGIN { \ while(U8_IS_TRAIL((s)[--(i)])) {} \ } UPRV_BLOCK_MACRO_END /** * 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) UPRV_BLOCK_MACRO_BEGIN { \ if(U8_IS_TRAIL((s)[--(i)])) { \ (i)=utf8_back1SafeBody(s, start, (i)); \ } \ } UPRV_BLOCK_MACRO_END /** * 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) UPRV_BLOCK_MACRO_BEGIN { \ int32_t __N=(n); \ while(__N>0) { \ U8_BACK_1_UNSAFE(s, i); \ --__N; \ } \ } UPRV_BLOCK_MACRO_END /** * 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) UPRV_BLOCK_MACRO_BEGIN { \ int32_t __N=(n); \ while(__N>0 && (i)>(start)) { \ U8_BACK_1(s, start, i); \ --__N; \ } \ } UPRV_BLOCK_MACRO_END /** * 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) UPRV_BLOCK_MACRO_BEGIN { \ U8_BACK_1_UNSAFE(s, i); \ U8_FWD_1_UNSAFE(s, i); \ } UPRV_BLOCK_MACRO_END /** * 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) UPRV_BLOCK_MACRO_BEGIN { \ if((start)<(i) && ((i)<(length) || (length)<0)) { \ U8_BACK_1(s, start, i); \ U8_FWD_1(s, i, length); \ } \ } UPRV_BLOCK_MACRO_END #endif