OXIESEC PANEL
- Current Dir:
/
/
opt
/
alt
/
libicu71
/
usr
/
include
/
unicode
Server IP: 2a02:4780:11:1594:0:ef5:22d7:a
Upload:
Create Dir:
Name
Size
Modified
Perms
📁
..
-
05/14/2024 03:54:45 PM
rwxr-xr-x
📄
alphaindex.h
26.52 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
appendable.h
8.53 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
basictz.h
9.86 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
brkiter.h
27.81 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
bytestream.h
10.75 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
bytestrie.h
20.77 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
bytestriebuilder.h
7.46 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
calendar.h
105.88 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
caniter.h
7.44 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
casemap.h
25.33 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
char16ptr.h
7.22 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
chariter.h
24.06 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
choicfmt.h
23.97 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
coleitr.h
13.77 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
coll.h
56.26 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
compactdecimalformat.h
6.88 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
curramt.h
3.78 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
currpinf.h
7.3 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
currunit.h
4.02 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
datefmt.h
40.71 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
dbbi.h
1.19 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
dcfmtsym.h
20.61 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
decimfmt.h
87.57 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
docmain.h
7.21 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
dtfmtsym.h
38.21 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
dtintrv.h
3.84 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
dtitvfmt.h
49.27 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
dtitvinf.h
18.63 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
dtptngen.h
28.84 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
dtrule.h
8.69 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
edits.h
20.74 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
enumset.h
2.08 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
errorcode.h
4.84 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
fieldpos.h
8.7 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
filteredbrk.h
5.37 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
fmtable.h
24.43 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
format.h
12.5 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
formattedvalue.h
9.75 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
fpositer.h
3.03 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
gender.h
3.33 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
gregocal.h
31.88 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
icudataver.h
1.02 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
icuplug.h
11.83 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
idna.h
12.7 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
listformatter.h
8.79 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
localebuilder.h
11.08 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
localematcher.h
26.84 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
localpointer.h
19.36 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
locdspnm.h
7.12 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
locid.h
47.66 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
measfmt.h
11.42 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
measunit.h
104.97 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
measure.h
4.33 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
messagepattern.h
33.71 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
msgfmt.h
44.22 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
normalizer2.h
33.66 KB
12/01/2022 11:12:32 AM
rw-r--r--
📄
normlzr.h
30.95 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
nounit.h
2.25 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
numberformatter.h
94.15 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
numberrangeformatter.h
25.19 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
numfmt.h
49.84 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
numsys.h
7.33 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
parseerr.h
3.08 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
parsepos.h
5.57 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
platform.h
28.09 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
plurfmt.h
25.24 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
plurrule.h
20.82 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ptypes.h
3.49 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
putil.h
6.32 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
rbbi.h
28.64 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
rbnf.h
48.85 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
rbtz.h
15.77 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
regex.h
84.36 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
region.h
9.18 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
reldatefmt.h
22.22 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
rep.h
9.37 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
resbund.h
18.08 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
schriter.h
6.36 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
scientificnumberformatter.h
6.43 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
search.h
22.22 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
selfmt.h
14.34 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
simpleformatter.h
12.59 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
simpletz.h
45.64 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
smpdtfmt.h
71.07 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
sortkey.h
11.18 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
std_string.h
1.05 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
strenum.h
9.92 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
stringoptions.h
5.79 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
stringpiece.h
10.05 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
stringtriebuilder.h
15.47 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
stsearch.h
21.41 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
symtable.h
4.27 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
tblcoll.h
36.92 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
timezone.h
43.81 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
tmunit.h
3.4 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
tmutamt.h
4.91 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
tmutfmt.h
7.42 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
translit.h
65.82 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
tzfmt.h
42.93 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
tznames.h
16.85 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
tzrule.h
35.6 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
tztrans.h
6.13 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ubidi.h
89.61 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ubiditransform.h
12.7 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ubrk.h
24.43 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ucal.h
60.68 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ucasemap.h
15.21 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ucat.h
5.35 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uchar.h
144.64 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ucharstrie.h
22.53 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ucharstriebuilder.h
7.47 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uchriter.h
13.42 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uclean.h
11.2 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ucnv.h
83.46 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ucnv_cb.h
6.58 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ucnv_err.h
20.98 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ucnvsel.h
6.19 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ucol.h
61.95 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ucoleitr.h
9.82 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uconfig.h
12.07 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ucpmap.h
5.53 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ucptrie.h
22.5 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ucsdet.h
14.69 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ucurr.h
16.72 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
udat.h
62.4 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
udata.h
15.63 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
udateintervalformat.h
11.93 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
udatpg.h
30.18 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
udisplaycontext.h
5.94 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uenum.h
7.79 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ufieldpositer.h
4.41 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uformattable.h
10.97 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uformattedvalue.h
12.3 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ugender.h
2.06 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uidna.h
33.43 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uiter.h
22.75 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uldnames.h
10.48 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ulistformatter.h
10.78 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uloc.h
54.63 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ulocdata.h
11.3 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
umachine.h
16.05 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
umisc.h
1.33 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
umsg.h
24.25 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
umutablecptrie.h
8.29 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
unifilt.h
4 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
unifunct.h
4.05 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
unimatch.h
6.1 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
unirepl.h
3.38 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uniset.h
66.46 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
unistr.h
170.53 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
unorm.h
20.55 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
unorm2.h
24.68 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
unounclass.h
735 bytes
12/01/2022 11:12:33 AM
rw-r--r--
📄
unum.h
55.31 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
unumberformatter.h
30.28 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
unumberrangeformatter.h
15.37 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
unumsys.h
7.26 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uobject.h
10.68 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
upluralrules.h
8.79 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uregex.h
71.99 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uregion.h
9.81 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ureldatefmt.h
17.04 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
urename.h
135 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
urep.h
5.38 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ures.h
36.54 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uscript.h
27.63 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
usearch.h
39.21 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uset.h
44.29 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
usetiter.h
9.68 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ushape.h
18 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uspoof.h
65.84 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
usprep.h
8.19 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ustdio.h
38.56 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ustream.h
1.89 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ustring.h
72.36 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
ustringtrie.h
3.15 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
utext.h
58.08 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
utf.h
7.87 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
utf16.h
23.35 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
utf32.h
763 bytes
12/01/2022 11:12:33 AM
rw-r--r--
📄
utf8.h
30.83 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
utf_old.h
45.83 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
utmscale.h
13.78 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
utrace.h
17.18 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
utrans.h
25.54 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
utypes.h
31.06 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uvernum.h
6.68 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
uversion.h
5.99 KB
12/01/2022 11:12:33 AM
rw-r--r--
📄
vtzone.h
20.74 KB
12/01/2022 11:12:33 AM
rw-r--r--
Editing: utf.h
Close
// © 2016 and later: Unicode, Inc. and others. // License & terms of use: http://www.unicode.org/copyright.html /* ******************************************************************************* * * Copyright (C) 1999-2011, International Business Machines * Corporation and others. All Rights Reserved. * ******************************************************************************* * file name: utf.h * encoding: UTF-8 * tab size: 8 (not used) * indentation:4 * * created on: 1999sep09 * created by: Markus W. Scherer */ /** * \file * \brief C API: Code point macros * * This file defines macros for checking whether a code point is * a surrogate or a non-character etc. * * If U_NO_DEFAULT_INCLUDE_UTF_HEADERS is 0 then utf.h is included by utypes.h * and itself includes utf8.h and utf16.h after some * common definitions. * If U_NO_DEFAULT_INCLUDE_UTF_HEADERS is 1 then each of these headers must be * included explicitly if their definitions are used. * * utf8.h and utf16.h define macros for efficiently getting code points * in and out of UTF-8/16 strings. * utf16.h macros have "U16_" prefixes. * utf8.h defines similar macros with "U8_" prefixes for UTF-8 string handling. * * ICU mostly processes 16-bit Unicode strings. * Most of the time, such strings are well-formed UTF-16. * Single, unpaired surrogates must be handled as well, and are treated in ICU * like regular code points where possible. * (Pairs of surrogate code points are indistinguishable from supplementary * code points encoded as pairs of supplementary code units.) * * In fact, almost all Unicode code points in normal text (>99%) * are on the BMP (<=U+ffff) and even <=U+d7ff. * ICU functions handle supplementary code points (U+10000..U+10ffff) * but are optimized for the much more frequently occurring BMP code points. * * umachine.h defines UChar to be an unsigned 16-bit integer. * Since ICU 59, ICU uses char16_t in C++, UChar only in C, * and defines UChar=char16_t by default. See the UChar API docs for details. * * UChar32 is defined to be a signed 32-bit integer (int32_t), large enough for a 21-bit * Unicode code point (Unicode scalar value, 0..0x10ffff) and U_SENTINEL (-1). * Before ICU 2.4, the definition of UChar32 was similarly platform-dependent as * the definition of UChar. For details see the documentation for UChar32 itself. * * utf.h defines a small number of C macros for single Unicode code points. * These are simple checks for surrogates and non-characters. * For actual Unicode character properties see uchar.h. * * By default, string operations must be done with error checking in case * a string is not well-formed UTF-16 or UTF-8. * * The U16_ macros detect if a surrogate code unit is unpaired * (lead unit without trail unit or vice versa) and just return the unit itself * as the code point. * * The U8_ macros detect illegal byte sequences and return a negative value. * Starting with ICU 60, the observable length of a single illegal byte sequence * skipped by one of these macros follows the Unicode 6+ recommendation * which is consistent with the W3C Encoding Standard. * * There are ..._OR_FFFD versions of both U16_ and U8_ macros * that return U+FFFD for illegal code unit sequences. * * The regular "safe" macros require that the initial, passed-in string index * is within bounds. They only check the index when they read more than one * code unit. This is usually done with code similar to the following loop: * <pre>while(i<length) { * U16_NEXT(s, i, length, c); * // use c * }</pre> * * When it is safe to assume that text is well-formed UTF-16 * (does not contain single, unpaired surrogates), then one can use * U16_..._UNSAFE macros. * These do not check for proper code unit sequences or truncated text and may * yield wrong results or even cause a crash if they are used with "malformed" * text. * In practice, U16_..._UNSAFE macros will produce slightly less code but * should not be faster because the processing is only different when a * surrogate code unit is detected, which will be rare. * * Similarly for UTF-8, there are "safe" macros without a suffix, * and U8_..._UNSAFE versions. * The performance differences are much larger here because UTF-8 provides so * many opportunities for malformed sequences. * The unsafe UTF-8 macros are entirely implemented inside the macro definitions * and are fast, while the safe UTF-8 macros call functions for some complicated cases. * * Unlike with UTF-16, malformed sequences cannot be expressed with distinct * code point values (0..U+10ffff). They are indicated with negative values instead. * * For more information see the ICU User Guide Strings chapter * (https://unicode-org.github.io/icu/userguide/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. * * @stable ICU 2.4 */ #ifndef __UTF_H__ #define __UTF_H__ #include "unicode/umachine.h" /* include the utfXX.h after the following definitions */ /* single-code point definitions -------------------------------------------- */ /** * Is this code point a Unicode noncharacter? * @param c 32-bit code point * @return true or false * @stable ICU 2.4 */ #define U_IS_UNICODE_NONCHAR(c) \ ((c)>=0xfdd0 && \ ((c)<=0xfdef || ((c)&0xfffe)==0xfffe) && (c)<=0x10ffff) /** * Is c a Unicode code point value (0..U+10ffff) * that can be assigned a character? * * Code points that are not characters include: * - single surrogate code points (U+d800..U+dfff, 2048 code points) * - the last two code points on each plane (U+__fffe and U+__ffff, 34 code points) * - U+fdd0..U+fdef (new with Unicode 3.1, 32 code points) * - the highest Unicode code point value is U+10ffff * * This means that all code points below U+d800 are character code points, * and that boundary is tested first for performance. * * @param c 32-bit code point * @return true or false * @stable ICU 2.4 */ #define U_IS_UNICODE_CHAR(c) \ ((uint32_t)(c)<0xd800 || \ (0xdfff<(c) && (c)<=0x10ffff && !U_IS_UNICODE_NONCHAR(c))) /** * Is this code point a BMP code point (U+0000..U+ffff)? * @param c 32-bit code point * @return true or false * @stable ICU 2.8 */ #define U_IS_BMP(c) ((uint32_t)(c)<=0xffff) /** * Is this code point a supplementary code point (U+10000..U+10ffff)? * @param c 32-bit code point * @return true or false * @stable ICU 2.8 */ #define U_IS_SUPPLEMENTARY(c) ((uint32_t)((c)-0x10000)<=0xfffff) /** * Is this code point a lead surrogate (U+d800..U+dbff)? * @param c 32-bit code point * @return true or false * @stable ICU 2.4 */ #define U_IS_LEAD(c) (((c)&0xfffffc00)==0xd800) /** * Is this code point a trail surrogate (U+dc00..U+dfff)? * @param c 32-bit code point * @return true or false * @stable ICU 2.4 */ #define U_IS_TRAIL(c) (((c)&0xfffffc00)==0xdc00) /** * Is this code point a surrogate (U+d800..U+dfff)? * @param c 32-bit code point * @return true or false * @stable ICU 2.4 */ #define U_IS_SURROGATE(c) (((c)&0xfffff800)==0xd800) /** * Assuming c is a surrogate code point (U_IS_SURROGATE(c)), * is it a lead surrogate? * @param c 32-bit code point * @return true or false * @stable ICU 2.4 */ #define U_IS_SURROGATE_LEAD(c) (((c)&0x400)==0) /** * Assuming c is a surrogate code point (U_IS_SURROGATE(c)), * is it a trail surrogate? * @param c 32-bit code point * @return true or false * @stable ICU 4.2 */ #define U_IS_SURROGATE_TRAIL(c) (((c)&0x400)!=0) /* include the utfXX.h ------------------------------------------------------ */ #if !U_NO_DEFAULT_INCLUDE_UTF_HEADERS #include "unicode/utf8.h" #include "unicode/utf16.h" /* utf_old.h contains deprecated, pre-ICU 2.4 definitions */ #include "unicode/utf_old.h" #endif /* !U_NO_DEFAULT_INCLUDE_UTF_HEADERS */ #endif /* __UTF_H__ */