FM / unicode

/usr/include/unicode

Name	Size	Mode	Actions
basictz.h	8913	0644	edit dl rm
bms.h	8664	0644	edit dl rm
bmsearch.h	7316	0644	edit dl rm
brkiter.h	23001	0644	edit dl rm
bytestream.h	8531	0644	edit dl rm
calendar.h	90659	0644	edit dl rm
caniter.h	7288	0644	edit dl rm
chariter.h	24186	0644	edit dl rm
choicfmt.h	29528	0644	edit dl rm
coleitr.h	12990	0644	edit dl rm
coll.h	48468	0644	edit dl rm
colldata.h	11957	0644	edit dl rm
curramt.h	3659	0644	edit dl rm
currpinf.h	7061	0644	edit dl rm
currunit.h	3057	0644	edit dl rm
datefmt.h	27946	0644	edit dl rm
dbbi.h	966	0644	edit dl rm
dcfmtsym.h	14040	0644	edit dl rm
decimfmt.h	88612	0644	edit dl rm
docmain.h	6003	0644	edit dl rm
dtfmtsym.h	26145	0644	edit dl rm
dtintrv.h	3734	0644	edit dl rm
dtitvfmt.h	39700	0644	edit dl rm
dtitvinf.h	18704	0644	edit dl rm
dtptngen.h	17303	0644	edit dl rm
dtrule.h	8718	0644	edit dl rm
errorcode.h	4361	0644	edit dl rm
fieldpos.h	8713	0644	edit dl rm
fmtable.h	18794	0644	edit dl rm
format.h	12083	0644	edit dl rm
gregocal.h	33797	0644	edit dl rm
locid.h	30241	0644	edit dl rm
measfmt.h	1897	0644	edit dl rm
measunit.h	1635	0644	edit dl rm
measure.h	3321	0644	edit dl rm
msgfmt.h	39435	0644	edit dl rm
normlzr.h	30337	0644	edit dl rm
numfmt.h	33987	0644	edit dl rm
numsys.h	5004	0644	edit dl rm
parseerr.h	3044	0644	edit dl rm
parsepos.h	5468	0644	edit dl rm
platform.h	9961	0644	edit dl rm
plurfmt.h	23079	0644	edit dl rm
plurrule.h	9901	0644	edit dl rm
ppalmos.h	6992	0644	edit dl rm
putil.h	6686	0644	edit dl rm
pwin32.h	8668	0644	edit dl rm
rbbi.h	26993	0644	edit dl rm
rbnf.h	45681	0644	edit dl rm
rbtz.h	15695	0644	edit dl rm
regex.h	52316	0644	edit dl rm
rep.h	9559	0644	edit dl rm
resbund.h	18130	0644	edit dl rm
schriter.h	6293	0644	edit dl rm
search.h	22357	0644	edit dl rm
simpletz.h	46179	0644	edit dl rm
smpdtfmt.h	48325	0644	edit dl rm
sortkey.h	11111	0644	edit dl rm
std_string.h	1769	0644	edit dl rm
strenum.h	9888	0644	edit dl rm
stringpiece.h	5484	0644	edit dl rm
stsearch.h	22287	0644	edit dl rm
symtable.h	4199	0644	edit dl rm
tblcoll.h	38199	0644	edit dl rm
timezone.h	34584	0644	edit dl rm
tmunit.h	3454	0644	edit dl rm
tmutamt.h	4787	0644	edit dl rm
tmutfmt.h	8669	0644	edit dl rm
translit.h	54780	0644	edit dl rm
tzrule.h	36057	0644	edit dl rm
tztrans.h	6101	0644	edit dl rm
ubidi.h	83092	0644	edit dl rm
ubrk.h	17688	0644	edit dl rm
ucal.h	40177	0644	edit dl rm
ucasemap.h	16420	0644	edit dl rm
ucat.h	5371	0644	edit dl rm
uchar.h	111062	0644	edit dl rm
uchriter.h	13132	0644	edit dl rm
uclean.h	11855	0644	edit dl rm
ucnv.h	83111	0644	edit dl rm
ucnvsel.h	5630	0644	edit dl rm
ucnv_cb.h	6635	0644	edit dl rm
ucnv_err.h	21375	0644	edit dl rm
ucol.h	48826	0644	edit dl rm
ucoleitr.h	12356	0644	edit dl rm
uconfig.h	6035	0644	edit dl rm
ucsdet.h	12464	0644	edit dl rm
ucurr.h	11572	0644	edit dl rm
udat.h	34496	0644	edit dl rm
udata.h	14265	0644	edit dl rm
udatpg.h	18715	0644	edit dl rm
udeprctd.h	2284	0644	edit dl rm
udraft.h	7600	0644	edit dl rm
uenum.h	5796	0644	edit dl rm
uidna.h	15918	0644	edit dl rm
uintrnal.h	15752	0644	edit dl rm
uiter.h	23234	0644	edit dl rm
uloc.h	44548	0644	edit dl rm
ulocdata.h	9739	0644	edit dl rm
umachine.h	11360	0644	edit dl rm
umisc.h	1255	0644	edit dl rm
umsg.h	26076	0644	edit dl rm
unifilt.h	3770	0644	edit dl rm
unifunct.h	3966	0644	edit dl rm
unimatch.h	6071	0644	edit dl rm
unirepl.h	3290	0644	edit dl rm
uniset.h	61771	0644	edit dl rm
unistr.h	161321	0644	edit dl rm
unorm.h	23621	0644	edit dl rm
unum.h	32145	0644	edit dl rm
uobject.h	11393	0644	edit dl rm
uobslete.h	852	0644	edit dl rm
uregex.h	43948	0644	edit dl rm
urename.h	92538	0644	edit dl rm
urep.h	5394	0644	edit dl rm
ures.h	36348	0644	edit dl rm
uscript.h	11360	0644	edit dl rm
usearch.h	34223	0644	edit dl rm
uset.h	39868	0644	edit dl rm
usetiter.h	9606	0644	edit dl rm
ushape.h	17907	0644	edit dl rm
uspoof.h	38752	0644	edit dl rm
usprep.h	7750	0644	edit dl rm
ustdio.h	35333	0644	edit dl rm
ustream.h	1891	0644	edit dl rm
ustring.h	69383	0644	edit dl rm
usystem.h	1925	0644	edit dl rm
utext.h	58394	0644	edit dl rm
utf.h	8273	0644	edit dl rm
utf8.h	20512	0644	edit dl rm
utf16.h	18776	0644	edit dl rm
utf32.h	653	0644	edit dl rm
utf_old.h	43646	0644	edit dl rm
utmscale.h	13689	0644	edit dl rm
utrace.h	13355	0644	edit dl rm
utrans.h	23129	0644	edit dl rm
utypes.h	34513	0644	edit dl rm
uversion.h	10902	0644	edit dl rm
vtzone.h	20048	0644	edit dl rm

Edit: /usr/include/unicode/utf.h (8273B)

/*
*******************************************************************************
*
*   Copyright (C) 1999-2008, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
*******************************************************************************
*   file name:  utf.h
*   encoding:   US-ASCII
*   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.
 *
 * The UChar and UChar32 data types for Unicode code units and code points
 * are defined in umachines.h because they can be machine-dependent.
 *
 * utf.h is included by utypes.h and itself includes utf8.h and utf16.h after some
 * common definitions. Those files 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 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.
 *
 * utf.h defines UChar to be an unsigned 16-bit integer. If this matches wchar_t, then
 * UChar is defined to be exactly wchar_t, otherwise uint16_t.
 *
 * 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).
 * 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 also 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.
 * The macros will 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.
 * (It is an accidental property of Unicode and UTF-16 that all
 * malformed sequences can be expressed unambiguously with a distinct subrange
 * of Unicode code points.)
 *
 * 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 all but the
 * trivial (ASCII) cases.
 * (ICU 3.6 optimizes U8_NEXT() and U8_APPEND() to handle most other common
 * characters inline as well.)
 *
 * 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://icu-project.org/userguide/strings.html).
 *
 * <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/utypes.h"
/* include the utfXX.h after the following definitions */

/* single-code point definitions -------------------------------------------- */

/**
 * This value is intended for sentinel values for APIs that
 * (take or) return single code points (UChar32).
 * It is outside of the Unicode code point range 0..0x10ffff.
 * 
 * For example, a "done" or "error" value in a new API
 * could be indicated with U_SENTINEL.
 *
 * ICU APIs designed before ICU 2.4 usually define service-specific "done"
 * values, mostly 0xffff.
 * Those may need to be distinguished from
 * actual U+ffff text contents by calling functions like
 * CharacterIterator::hasNext() or UnicodeString::length().
 *
 * @return -1
 * @see UChar32
 * @stable ICU 2.4
 */
#define U_SENTINEL (-1)

/**
 * 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 && \
     ((uint32_t)(c)<=0xfdef || ((c)&0xfffe)==0xfffe) && \
     (uint32_t)(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 || \
        ((uint32_t)(c)>0xdfff && \
         (uint32_t)(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
 * @draft ICU 4.2
 */
#define U_IS_SURROGATE_TRAIL(c) (((c)&0x400)!=0)

/* include the utfXX.h ------------------------------------------------------ */

#include "unicode/utf8.h"
#include "unicode/utf16.h"

/* utf_old.h contains deprecated, pre-ICU 2.4 definitions */
#include "unicode/utf_old.h"

#endif

cmd: