Linux vps-61133.fhnet.fr 4.9.0-19-amd64 #1 SMP Debian 4.9.320-2 (2022-06-30) x86_64
Apache/2.4.25 (Debian)
Server IP : 93.113.207.21 & Your IP : 216.73.216.35
Domains :
Cant Read [ /etc/named.conf ]
User : www-data
Terminal
Auto Root
Create File
Create Folder
Localroot Suggester
Backdoor Destroyer
Readme
/
usr /
include /
unicode /
Delete
Unzip
Name
Size
Permission
Date
Action
alphaindex.h
26.13
KB
-rw-r--r--
2021-10-12 12:29
appendable.h
8.25
KB
-rw-r--r--
2021-10-12 12:29
basictz.h
8.73
KB
-rw-r--r--
2021-10-12 12:29
brkiter.h
27.31
KB
-rw-r--r--
2021-10-12 12:29
bytestream.h
9.16
KB
-rw-r--r--
2021-10-12 12:29
bytestrie.h
19.19
KB
-rw-r--r--
2021-10-12 12:29
bytestriebuilder.h
7.06
KB
-rw-r--r--
2021-10-12 12:29
calendar.h
105.26
KB
-rw-r--r--
2021-10-12 12:29
caniter.h
7.24
KB
-rw-r--r--
2021-10-12 12:29
chariter.h
23.71
KB
-rw-r--r--
2021-10-12 12:29
choicfmt.h
23.74
KB
-rw-r--r--
2021-10-12 12:29
coleitr.h
13.57
KB
-rw-r--r--
2021-10-12 12:29
coll.h
55.46
KB
-rw-r--r--
2021-10-12 12:29
compactdecimalformat.h
16.56
KB
-rw-r--r--
2021-10-12 12:29
curramt.h
3.57
KB
-rw-r--r--
2021-10-12 12:29
currpinf.h
6.97
KB
-rw-r--r--
2021-10-12 12:29
currunit.h
2.81
KB
-rw-r--r--
2021-10-12 12:29
datefmt.h
40.07
KB
-rw-r--r--
2021-10-12 12:29
dbbi.h
1020
B
-rw-r--r--
2021-10-12 12:29
dcfmtsym.h
16.46
KB
-rw-r--r--
2021-10-12 12:29
decimfmt.h
90.45
KB
-rw-r--r--
2021-10-12 12:29
docmain.h
6.28
KB
-rw-r--r--
2021-10-12 12:29
dtfmtsym.h
37.05
KB
-rw-r--r--
2021-10-12 12:29
dtintrv.h
3.65
KB
-rw-r--r--
2021-10-12 12:29
dtitvfmt.h
42.76
KB
-rw-r--r--
2021-10-12 12:29
dtitvinf.h
18.34
KB
-rw-r--r--
2021-10-12 12:29
dtptngen.h
23.18
KB
-rw-r--r--
2021-10-12 12:29
dtrule.h
8.51
KB
-rw-r--r--
2021-10-12 12:29
enumset.h
1.94
KB
-rw-r--r--
2021-10-12 12:29
errorcode.h
4.67
KB
-rw-r--r--
2021-10-12 12:29
fieldpos.h
8.51
KB
-rw-r--r--
2021-10-12 12:29
filteredbrk.h
4.22
KB
-rw-r--r--
2021-10-12 12:29
fmtable.h
24.29
KB
-rw-r--r--
2021-10-12 12:29
format.h
12.33
KB
-rw-r--r--
2021-10-12 12:29
fpositer.h
2.87
KB
-rw-r--r--
2021-10-12 12:29
gender.h
3.07
KB
-rw-r--r--
2021-10-12 12:29
gregocal.h
31.46
KB
-rw-r--r--
2021-10-12 12:29
icudataver.h
938
B
-rw-r--r--
2021-10-12 12:29
icuplug.h
11.58
KB
-rw-r--r--
2021-10-12 12:29
idna.h
12.55
KB
-rw-r--r--
2021-10-12 12:29
listformatter.h
4.73
KB
-rw-r--r--
2021-10-12 12:29
localpointer.h
18.17
KB
-rw-r--r--
2021-10-12 12:29
locdspnm.h
6.92
KB
-rw-r--r--
2021-10-12 12:29
locid.h
31.3
KB
-rw-r--r--
2021-10-12 12:29
measfmt.h
10.43
KB
-rw-r--r--
2021-10-12 12:29
measunit.h
37.64
KB
-rw-r--r--
2021-10-12 12:29
measure.h
4.15
KB
-rw-r--r--
2021-10-12 12:29
messagepattern.h
33.53
KB
-rw-r--r--
2021-10-12 12:29
msgfmt.h
43.05
KB
-rw-r--r--
2021-10-12 12:29
normalizer2.h
28.17
KB
-rw-r--r--
2021-10-12 12:29
normlzr.h
30.65
KB
-rw-r--r--
2021-10-12 12:29
numfmt.h
45.85
KB
-rw-r--r--
2021-10-12 12:29
numsys.h
6.62
KB
-rw-r--r--
2021-10-12 12:29
parseerr.h
2.97
KB
-rw-r--r--
2021-10-12 12:29
parsepos.h
5.34
KB
-rw-r--r--
2021-10-12 12:29
platform.h
26.96
KB
-rw-r--r--
2021-10-12 12:29
plurfmt.h
25.55
KB
-rw-r--r--
2021-10-12 12:29
plurrule.h
17.16
KB
-rw-r--r--
2021-10-12 12:29
ptypes.h
3.36
KB
-rw-r--r--
2021-10-12 12:29
putil.h
6.23
KB
-rw-r--r--
2021-10-12 12:29
rbbi.h
29.2
KB
-rw-r--r--
2021-10-12 12:29
rbnf.h
46.66
KB
-rw-r--r--
2021-10-12 12:29
rbtz.h
15.36
KB
-rw-r--r--
2021-10-12 12:29
regex.h
84.75
KB
-rw-r--r--
2021-10-12 12:29
region.h
9
KB
-rw-r--r--
2021-10-12 12:29
reldatefmt.h
13.73
KB
-rw-r--r--
2021-10-12 12:29
rep.h
9.38
KB
-rw-r--r--
2021-10-12 12:29
resbund.h
17.89
KB
-rw-r--r--
2021-10-12 12:29
schriter.h
6.15
KB
-rw-r--r--
2021-10-12 12:29
scientificnumberformatter.h
6.48
KB
-rw-r--r--
2021-10-12 12:29
search.h
22.1
KB
-rw-r--r--
2021-10-12 12:29
selfmt.h
14.13
KB
-rw-r--r--
2021-10-12 12:29
simpleformatter.h
11.14
KB
-rw-r--r--
2021-10-12 12:29
simpletz.h
45.13
KB
-rw-r--r--
2021-10-12 12:29
smpdtfmt.h
69.24
KB
-rw-r--r--
2021-10-12 12:29
sortkey.h
11.01
KB
-rw-r--r--
2021-10-12 12:29
std_string.h
905
B
-rw-r--r--
2021-10-12 12:29
strenum.h
9.92
KB
-rw-r--r--
2021-10-12 12:29
stringpiece.h
6.38
KB
-rw-r--r--
2021-10-12 12:29
stringtriebuilder.h
14.56
KB
-rw-r--r--
2021-10-12 12:29
stsearch.h
21.18
KB
-rw-r--r--
2021-10-12 12:29
symtable.h
4.1
KB
-rw-r--r--
2021-10-12 12:29
tblcoll.h
36.24
KB
-rw-r--r--
2021-10-12 12:29
timezone.h
40.71
KB
-rw-r--r--
2021-10-12 12:29
tmunit.h
2.94
KB
-rw-r--r--
2021-10-12 12:29
tmutamt.h
4.69
KB
-rw-r--r--
2021-10-12 12:29
tmutfmt.h
7.61
KB
-rw-r--r--
2021-10-12 12:29
translit.h
54.41
KB
-rw-r--r--
2021-10-12 12:29
tzfmt.h
42.69
KB
-rw-r--r--
2021-10-12 12:29
tznames.h
16.25
KB
-rw-r--r--
2021-10-12 12:29
tzrule.h
35.21
KB
-rw-r--r--
2021-10-12 12:29
tztrans.h
5.96
KB
-rw-r--r--
2021-10-12 12:29
ubidi.h
88.57
KB
-rw-r--r--
2021-10-12 12:29
ubrk.h
20.05
KB
-rw-r--r--
2021-10-12 12:29
ucal.h
54.18
KB
-rw-r--r--
2021-10-12 12:29
ucasemap.h
16.45
KB
-rw-r--r--
2021-10-12 12:29
ucat.h
5.25
KB
-rw-r--r--
2021-10-12 12:29
uchar.h
122.74
KB
-rw-r--r--
2021-10-12 12:29
ucharstrie.h
20.8
KB
-rw-r--r--
2021-10-12 12:29
ucharstriebuilder.h
7.01
KB
-rw-r--r--
2021-10-12 12:29
uchriter.h
12.82
KB
-rw-r--r--
2021-10-12 12:29
uclean.h
11.03
KB
-rw-r--r--
2021-10-12 12:29
ucnv.h
82.81
KB
-rw-r--r--
2021-10-12 12:29
ucnv_cb.h
6.48
KB
-rw-r--r--
2021-10-12 12:29
ucnv_err.h
20.87
KB
-rw-r--r--
2021-10-12 12:29
ucnvsel.h
6.03
KB
-rw-r--r--
2021-10-12 12:29
ucol.h
60.51
KB
-rw-r--r--
2021-10-12 12:29
ucoleitr.h
9.34
KB
-rw-r--r--
2021-10-12 12:29
uconfig.h
11.76
KB
-rw-r--r--
2021-10-12 12:29
ucsdet.h
14.35
KB
-rw-r--r--
2021-10-12 12:29
ucurr.h
14.92
KB
-rw-r--r--
2021-10-12 12:29
udat.h
59.91
KB
-rw-r--r--
2021-10-12 12:29
udata.h
15.28
KB
-rw-r--r--
2021-10-12 12:29
udateintervalformat.h
6.68
KB
-rw-r--r--
2021-10-12 12:29
udatpg.h
23.5
KB
-rw-r--r--
2021-10-12 12:29
udisplaycontext.h
4.87
KB
-rw-r--r--
2021-10-12 12:29
uenum.h
7.76
KB
-rw-r--r--
2021-10-12 12:29
ufieldpositer.h
4.24
KB
-rw-r--r--
2021-10-12 12:29
uformattable.h
10.65
KB
-rw-r--r--
2021-10-12 12:29
ugender.h
1.89
KB
-rw-r--r--
2021-10-12 12:29
uidna.h
33.26
KB
-rw-r--r--
2021-10-12 12:29
uiter.h
22.67
KB
-rw-r--r--
2021-10-12 12:29
uldnames.h
10.34
KB
-rw-r--r--
2021-10-12 12:29
ulistformatter.h
4.43
KB
-rw-r--r--
2021-10-12 12:29
uloc.h
49.78
KB
-rw-r--r--
2021-10-12 12:29
ulocdata.h
10.57
KB
-rw-r--r--
2021-10-12 12:29
umachine.h
10.94
KB
-rw-r--r--
2021-10-12 12:29
umisc.h
1.23
KB
-rw-r--r--
2021-10-12 12:29
umsg.h
24.12
KB
-rw-r--r--
2021-10-12 12:29
unifilt.h
3.52
KB
-rw-r--r--
2021-10-12 12:29
unifunct.h
3.87
KB
-rw-r--r--
2021-10-12 12:29
unimatch.h
5.93
KB
-rw-r--r--
2021-10-12 12:29
unirepl.h
3.21
KB
-rw-r--r--
2021-10-12 12:29
uniset.h
63.86
KB
-rw-r--r--
2021-10-12 12:29
unistr.h
170.03
KB
-rw-r--r--
2021-10-12 12:29
unorm.h
20.18
KB
-rw-r--r--
2021-10-12 12:29
unorm2.h
25.11
KB
-rw-r--r--
2021-10-12 12:29
unum.h
49.13
KB
-rw-r--r--
2021-10-12 12:29
unumsys.h
7.03
KB
-rw-r--r--
2021-10-12 12:29
uobject.h
10.61
KB
-rw-r--r--
2021-10-12 12:29
upluralrules.h
4.47
KB
-rw-r--r--
2021-10-12 12:29
uregex.h
71.95
KB
-rw-r--r--
2021-10-12 12:29
uregion.h
9.58
KB
-rw-r--r--
2021-10-12 12:29
ureldatefmt.h
11.85
KB
-rw-r--r--
2021-10-12 12:29
urename.h
123.32
KB
-rw-r--r--
2021-10-12 12:29
urep.h
5.27
KB
-rw-r--r--
2021-10-12 12:29
ures.h
36.25
KB
-rw-r--r--
2021-10-12 12:29
uscript.h
25.24
KB
-rw-r--r--
2021-10-12 12:29
usearch.h
37.71
KB
-rw-r--r--
2021-10-12 12:29
uset.h
39.67
KB
-rw-r--r--
2021-10-12 12:29
usetiter.h
9.38
KB
-rw-r--r--
2021-10-12 12:29
ushape.h
17.89
KB
-rw-r--r--
2021-10-12 12:29
uspoof.h
45.43
KB
-rw-r--r--
2021-10-12 12:29
usprep.h
8.02
KB
-rw-r--r--
2021-10-12 12:29
ustdio.h
38.43
KB
-rw-r--r--
2021-10-12 12:29
ustream.h
1.8
KB
-rw-r--r--
2021-10-12 12:29
ustring.h
72.69
KB
-rw-r--r--
2021-10-12 12:29
ustringtrie.h
3.04
KB
-rw-r--r--
2021-10-12 12:29
utext.h
57.97
KB
-rw-r--r--
2021-10-12 12:29
utf.h
7.64
KB
-rw-r--r--
2021-10-12 12:29
utf16.h
18.63
KB
-rw-r--r--
2021-10-12 12:29
utf32.h
653
B
-rw-r--r--
2021-10-12 12:29
utf8.h
27.62
KB
-rw-r--r--
2021-10-12 12:29
utf_old.h
42.5
KB
-rw-r--r--
2021-10-12 12:29
utmscale.h
13.37
KB
-rw-r--r--
2021-10-12 12:29
utrace.h
13.09
KB
-rw-r--r--
2021-10-12 12:29
utrans.h
25.42
KB
-rw-r--r--
2021-10-12 12:29
utypes.h
31.05
KB
-rw-r--r--
2021-10-12 12:29
uvernum.h
5.62
KB
-rw-r--r--
2021-10-12 12:29
uversion.h
6.29
KB
-rw-r--r--
2021-10-12 12:29
vtzone.h
20.06
KB
-rw-r--r--
2021-10-12 12:29
Save
Rename
/* ******************************************************************************* * * Copyright (C) 1999-2015, International Business Machines * Corporation and others. All Rights Reserved. * ******************************************************************************* * file name: utf8.h * encoding: US-ASCII * 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 ----------------------------------------------------- */ /** * \var utf8_countTrailBytes * Internal array with numbers of trail bytes for any given byte used in * lead byte position. * * 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, * and should not be hidden when other internal functions are hidden (otherwise * public macros would fail to compile). * @internal */ #ifdef U_UTF8_IMPL U_EXPORT const uint8_t #elif defined(U_STATIC_IMPLEMENTATION) || defined(U_COMMON_IMPLEMENTATION) U_CFUNC const uint8_t #else U_CFUNC U_IMPORT const uint8_t /* U_IMPORT2? */ /*U_IMPORT*/ #endif utf8_countTrailBytes[256]; /** * Counts the trail bytes for a UTF-8 lead byte. * Returns 0 for 0..0xbf as well as for 0xfe and 0xff. * * 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. * * Note: Beginning with ICU 50, the implementation uses a multi-condition expression * which was shown in 2012 (on x86-64) to compile to fast, branch-free code. * leadByte is evaluated multiple times. * * The pre-ICU 50 implementation used the exported array utf8_countTrailBytes: * #define U8_COUNT_TRAIL_BYTES(leadByte) (utf8_countTrailBytes[leadByte]) * leadByte was evaluated exactly once. * * @param leadByte The first byte of a UTF-8 sequence. Must be 0..0xff. * @internal */ #define U8_COUNT_TRAIL_BYTES(leadByte) \ ((uint8_t)(leadByte)<0xf0 ? \ ((uint8_t)(leadByte)>=0xc0)+((uint8_t)(leadByte)>=0xe0) : \ (uint8_t)(leadByte)<0xfe ? 3+((uint8_t)(leadByte)>=0xf8)+((uint8_t)(leadByte)>=0xfc) : 0) /** * Counts the trail bytes for a UTF-8 lead byte of a valid UTF-8 sequence. * The maximum supported lead byte is 0xf4 corresponding to U+10FFFF. * 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) \ (((leadByte)>=0xc0)+((leadByte)>=0xe0)+((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) /** * 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? * @param c 8-bit code unit (byte) * @return TRUE or FALSE * @stable ICU 2.4 */ #define U8_IS_LEAD(c) ((uint8_t)((c)-0xc0)<0x3e) /** * Is this code unit (byte) a UTF-8 trail byte? * @param c 8-bit code unit (byte) * @return TRUE or FALSE * @stable ICU 2.4 */ #define U8_IS_TRAIL(c) (((c)&0xc0)==0x80) /** * 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((c)>=0x80) { \ 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((c)>=0x80) { \ uint8_t __t1, __t2; \ if( /* handle U+1000..U+CFFF inline */ \ (0xe0<(c) && (c)<=0xec) && \ (((i)+1)<(length) || (length)<0) && \ (__t1=(uint8_t)((s)[i]-0x80))<=0x3f && \ (__t2=(uint8_t)((s)[(i)+1]-0x80))<= 0x3f \ ) { \ /* no need for (c&0xf) because the upper bits are truncated after <<12 in the cast to (UChar) */ \ (c)=(UChar)(((c)<<12)|(__t1<<6)|__t2); \ (i)+=2; \ } else if( /* handle U+0080..U+07FF inline */ \ ((c)<0xe0 && (c)>=0xc2) && \ ((i)!=(length)) && \ (__t1=(uint8_t)((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((c)>=0x80) { \ uint8_t __t1, __t2; \ if( /* handle U+1000..U+CFFF inline */ \ (0xe0<(c) && (c)<=0xec) && \ (((i)+1)<(length) || (length)<0) && \ (__t1=(uint8_t)((s)[i]-0x80))<=0x3f && \ (__t2=(uint8_t)((s)[(i)+1]-0x80))<= 0x3f \ ) { \ /* no need for (c&0xf) because the upper bits are truncated after <<12 in the cast to (UChar) */ \ (c)=(UChar)(((c)<<12)|(__t1<<6)|__t2); \ (i)+=2; \ } else if( /* handle U+0080..U+07FF inline */ \ ((c)<0xe0 && (c)>=0xc2) && \ ((i)!=(length)) && \ (__t1=(uint8_t)((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((uint8_t)(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=(uint8_t)(s)[(i)++]; \ if(U8_IS_LEAD(__b)) { \ uint8_t __count=U8_COUNT_TRAIL_BYTES(__b); \ if((i)+__count>(length) && (length)>=0) { \ __count=(uint8_t)((length)-(i)); \ } \ while(__count>0 && U8_IS_TRAIL((s)[i])) { \ ++(i); \ --__count; \ } \ } \ } /** * 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=(uint8_t)(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((c)>=0x80) { \ (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((c)>=0x80) { \ (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