FM / unicode

/opt/alt/libicu/usr/include/unicode

Name	Size	Mode	Actions
alphaindex.h	27056	0644	edit dl rm
appendable.h	8632	0644	edit dl rm
basictz.h	9055	0644	edit dl rm
brkiter.h	28195	0644	edit dl rm
bytestream.h	9767	0644	edit dl rm
bytestrie.h	19718	0644	edit dl rm
bytestriebuilder.h	7186	0644	edit dl rm
calendar.h	107581	0644	edit dl rm
caniter.h	7550	0644	edit dl rm
casemap.h	25871	0644	edit dl rm
char16ptr.h	7331	0644	edit dl rm
chariter.h	24573	0644	edit dl rm
choicfmt.h	24418	0644	edit dl rm
coleitr.h	14033	0644	edit dl rm
coll.h	56928	0644	edit dl rm
compactdecimalformat.h	6971	0644	edit dl rm
curramt.h	3782	0644	edit dl rm
currpinf.h	7412	0644	edit dl rm
currunit.h	3606	0644	edit dl rm
datefmt.h	41334	0644	edit dl rm
dbbi.h	1133	0644	edit dl rm
dcfmtsym.h	20584	0644	edit dl rm
decimfmt.h	88478	0644	edit dl rm
docmain.h	6878	0644	edit dl rm
dtfmtsym.h	38548	0644	edit dl rm
dtintrv.h	3848	0644	edit dl rm
dtitvfmt.h	43898	0644	edit dl rm
dtitvinf.h	18903	0644	edit dl rm
dtptngen.h	25626	0644	edit dl rm
dtrule.h	8831	0644	edit dl rm
edits.h	21169	0644	edit dl rm
enumset.h	2130	0644	edit dl rm
errorcode.h	4894	0644	edit dl rm
fieldpos.h	8838	0644	edit dl rm
filteredbrk.h	5364	0644	edit dl rm
fmtable.h	24946	0644	edit dl rm
format.h	12741	0644	edit dl rm
fpositer.h	3047	0644	edit dl rm
gender.h	3347	0644	edit dl rm
gregocal.h	32331	0644	edit dl rm
icudataver.h	1051	0644	edit dl rm
icuplug.h	12166	0644	edit dl rm
idna.h	12938	0644	edit dl rm
listformatter.h	6331	0644	edit dl rm
localpointer.h	17284	0644	edit dl rm
locdspnm.h	7224	0644	edit dl rm
locid.h	46001	0644	edit dl rm
measfmt.h	12298	0644	edit dl rm
measunit.h	39427	0644	edit dl rm
measure.h	4361	0644	edit dl rm
messagepattern.h	34460	0644	edit dl rm
msgfmt.h	44398	0644	edit dl rm
normalizer2.h	34789	0644	edit dl rm
normlzr.h	31476	0644	edit dl rm
nounit.h	2693	0644	edit dl rm
numberformatter.h	89164	0644	edit dl rm
numberrangeformatter.h	29430	0644	edit dl rm
numfmt.h	50322	0644	edit dl rm
numsys.h	6895	0644	edit dl rm
parseerr.h	3155	0644	edit dl rm
parsepos.h	5581	0644	edit dl rm
platform.h	27754	0644	edit dl rm
plurfmt.h	25786	0644	edit dl rm
plurrule.h	17834	0644	edit dl rm
ptypes.h	3577	0644	edit dl rm
putil.h	6487	0644	edit dl rm
rbbi.h	27047	0644	edit dl rm
rbnf.h	50984	0644	edit dl rm
rbtz.h	15838	0644	edit dl rm
regex.h	86943	0644	edit dl rm
region.h	9342	0644	edit dl rm
reldatefmt.h	14812	0644	edit dl rm
rep.h	9726	0644	edit dl rm
resbund.h	18440	0644	edit dl rm
schriter.h	6410	0644	edit dl rm
scientificnumberformatter.h	6474	0644	edit dl rm
search.h	22742	0644	edit dl rm
selfmt.h	14579	0644	edit dl rm
simpleformatter.h	11701	0644	edit dl rm
simpletz.h	46389	0644	edit dl rm
smpdtfmt.h	72442	0644	edit dl rm
sortkey.h	11383	0644	edit dl rm
std_string.h	1015	0644	edit dl rm
strenum.h	10279	0644	edit dl rm
stringoptions.h	5926	0644	edit dl rm
stringpiece.h	6610	0644	edit dl rm
stringtriebuilder.h	15636	0644	edit dl rm
stsearch.h	21801	0644	edit dl rm
symtable.h	4312	0644	edit dl rm
tblcoll.h	37272	0644	edit dl rm
timezone.h	41862	0644	edit dl rm
tmunit.h	3371	0644	edit dl rm
tmutamt.h	4918	0644	edit dl rm
tmutfmt.h	7977	0644	edit dl rm
translit.h	67339	0644	edit dl rm
tzfmt.h	43846	0644	edit dl rm
tznames.h	17190	0644	edit dl rm
tzrule.h	36170	0644	edit dl rm
tztrans.h	6214	0644	edit dl rm
ubidi.h	91711	0644	edit dl rm
ubiditransform.h	12950	0644	edit dl rm
ubrk.h	24547	0644	edit dl rm
ucal.h	56526	0644	edit dl rm
ucasemap.h	15546	0644	edit dl rm
ucat.h	5484	0644	edit dl rm
uchar.h	143314	0644	edit dl rm
ucharstrie.h	21569	0644	edit dl rm
ucharstriebuilder.h	7316	0644	edit dl rm
uchriter.h	13457	0644	edit dl rm
uclean.h	11474	0644	edit dl rm
ucnv.h	85085	0644	edit dl rm
ucnvsel.h	6283	0644	edit dl rm
ucnv_cb.h	6748	0644	edit dl rm
ucnv_err.h	21492	0644	edit dl rm
ucol.h	62864	0644	edit dl rm
ucoleitr.h	9684	0644	edit dl rm
uconfig.h	11949	0644	edit dl rm
ucpmap.h	5709	0644	edit dl rm
ucptrie.h	22824	0644	edit dl rm
ucsdet.h	15018	0644	edit dl rm
ucurr.h	15947	0644	edit dl rm
udat.h	61572	0644	edit dl rm
udata.h	15905	0644	edit dl rm
udateintervalformat.h	6950	0644	edit dl rm
udatpg.h	26664	0644	edit dl rm
udisplaycontext.h	6029	0644	edit dl rm
uenum.h	7970	0644	edit dl rm
ufieldpositer.h	4461	0644	edit dl rm
uformattable.h	11198	0644	edit dl rm
ugender.h	2052	0644	edit dl rm
uidna.h	34169	0644	edit dl rm
uiter.h	23319	0644	edit dl rm
uldnames.h	10702	0644	edit dl rm
ulistformatter.h	5148	0644	edit dl rm
uloc.h	51971	0644	edit dl rm
ulocdata.h	11533	0644	edit dl rm
umachine.h	13509	0644	edit dl rm
umisc.h	1365	0644	edit dl rm
umsg.h	24812	0644	edit dl rm
umutablecptrie.h	8477	0644	edit dl rm
unifilt.h	3716	0644	edit dl rm
unifunct.h	4079	0644	edit dl rm
unimatch.h	6184	0644	edit dl rm
unirepl.h	3403	0644	edit dl rm
uniset.h	65796	0644	edit dl rm
unistr.h	178587	0644	edit dl rm
unorm.h	20938	0644	edit dl rm
unorm2.h	25254	0644	edit dl rm
unum.h	54666	0644	edit dl rm
unumberformatter.h	24335	0644	edit dl rm
unumsys.h	7314	0644	edit dl rm
uobject.h	10958	0644	edit dl rm
upluralrules.h	6880	0644	edit dl rm
uregex.h	73784	0644	edit dl rm
uregion.h	10073	0644	edit dl rm
ureldatefmt.h	12518	0644	edit dl rm
urename.h	130791	0644	edit dl rm
urep.h	5507	0644	edit dl rm
ures.h	37404	0644	edit dl rm
uscript.h	27153	0644	edit dl rm
usearch.h	39038	0644	edit dl rm
uset.h	40958	0644	edit dl rm
usetiter.h	9719	0644	edit dl rm
ushape.h	18432	0644	edit dl rm
uspoof.h	67613	0644	edit dl rm
usprep.h	8331	0644	edit dl rm
ustdio.h	39469	0644	edit dl rm
ustream.h	1844	0644	edit dl rm
ustring.h	74211	0644	edit dl rm
ustringtrie.h	3224	0644	edit dl rm
utext.h	59503	0644	edit dl rm
utf.h	8046	0644	edit dl rm
utf8.h	30734	0644	edit dl rm
utf16.h	22866	0644	edit dl rm
utf32.h	763	0644	edit dl rm
utf_old.h	44827	0644	edit dl rm
utmscale.h	14113	0644	edit dl rm
utrace.h	14219	0644	edit dl rm
utrans.h	26157	0644	edit dl rm
utypes.h	31212	0644	edit dl rm
uvernum.h	6206	0644	edit dl rm
uversion.h	6865	0644	edit dl rm
vtzone.h	20651	0644	edit dl rm

Edit: /opt/alt/libicu/usr/include/unicode/utf.h (8046B)

// © 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
 * (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.
 *
 * @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__ */

cmd: