FM / unicode

/usr/include/unicode

Name	Size	Mode	Actions
alphaindex.h	27118	0644	edit dl rm
appendable.h	8694	0644	edit dl rm
basictz.h	9491	0644	edit dl rm
brkiter.h	28464	0644	edit dl rm
bytestream.h	11037	0644	edit dl rm
bytestrie.h	21266	0644	edit dl rm
bytestriebuilder.h	7248	0644	edit dl rm
calendar.h	108278	0644	edit dl rm
caniter.h	7611	0644	edit dl rm
casemap.h	25933	0644	edit dl rm
char16ptr.h	7393	0644	edit dl rm
chariter.h	24632	0644	edit dl rm
choicfmt.h	24482	0644	edit dl rm
coleitr.h	14094	0644	edit dl rm
coll.h	57581	0644	edit dl rm
compactdecimalformat.h	7047	0644	edit dl rm
curramt.h	3851	0644	edit dl rm
currpinf.h	7473	0644	edit dl rm
currunit.h	4094	0644	edit dl rm
datefmt.h	41641	0644	edit dl rm
dbbi.h	1223	0644	edit dl rm
dcfmtsym.h	20897	0644	edit dl rm
decimfmt.h	89278	0644	edit dl rm
docmain.h	7142	0644	edit dl rm
dtfmtsym.h	38609	0644	edit dl rm
dtintrv.h	3930	0644	edit dl rm
dtitvfmt.h	47634	0644	edit dl rm
dtitvinf.h	19064	0644	edit dl rm
dtptngen.h	26419	0644	edit dl rm
dtrule.h	8888	0644	edit dl rm
edits.h	21237	0644	edit dl rm
enumset.h	2130	0644	edit dl rm
errorcode.h	4956	0644	edit dl rm
fieldpos.h	8899	0644	edit dl rm
filteredbrk.h	5501	0644	edit dl rm
fmtable.h	25007	0644	edit dl rm
format.h	12802	0644	edit dl rm
formattedvalue.h	9987	0644	edit dl rm
fpositer.h	3109	0644	edit dl rm
gender.h	3408	0644	edit dl rm
gregocal.h	32472	0644	edit dl rm
icudataver.h	1051	0644	edit dl rm
icuplug.h	12166	0644	edit dl rm
idna.h	13000	0644	edit dl rm
listformatter.h	9493	0644	edit dl rm
localebuilder.h	11502	0644	edit dl rm
localematcher.h	25147	0644	edit dl rm
localpointer.h	19829	0644	edit dl rm
locdspnm.h	7292	0644	edit dl rm
locid.h	48821	0644	edit dl rm
measfmt.h	11603	0644	edit dl rm
measunit.h	97563	0644	edit dl rm
measure.h	4423	0644	edit dl rm
messagepattern.h	34521	0644	edit dl rm
msgfmt.h	45168	0644	edit dl rm
normalizer2.h	34851	0644	edit dl rm
normlzr.h	31682	0644	edit dl rm
nounit.h	2754	0644	edit dl rm
numberformatter.h	86276	0644	edit dl rm
numberrangeformatter.h	28617	0644	edit dl rm
numfmt.h	50950	0644	edit dl rm
numsys.h	7500	0644	edit dl rm
parseerr.h	3155	0644	edit dl rm
parsepos.h	5692	0644	edit dl rm
platform.h	28751	0644	edit dl rm
plurfmt.h	25800	0644	edit dl rm
plurrule.h	18780	0644	edit dl rm
ptypes.h	3577	0644	edit dl rm
putil.h	6487	0644	edit dl rm
rbbi.h	27218	0644	edit dl rm
rbnf.h	49899	0644	edit dl rm
rbtz.h	15979	0644	edit dl rm
regex.h	86367	0644	edit dl rm
region.h	9404	0644	edit dl rm
reldatefmt.h	22801	0644	edit dl rm
rep.h	9599	0644	edit dl rm
resbund.h	18503	0644	edit dl rm
schriter.h	6475	0644	edit dl rm
scientificnumberformatter.h	6553	0644	edit dl rm
search.h	22757	0644	edit dl rm
selfmt.h	14643	0644	edit dl rm
simpleformatter.h	12888	0644	edit dl rm
simpletz.h	46527	0644	edit dl rm
smpdtfmt.h	72713	0644	edit dl rm
sortkey.h	11444	0644	edit dl rm
std_string.h	1076	0644	edit dl rm
strenum.h	10158	0644	edit dl rm
stringoptions.h	5926	0644	edit dl rm
stringpiece.h	10597	0644	edit dl rm
stringtriebuilder.h	15698	0644	edit dl rm
stsearch.h	21810	0644	edit dl rm
symtable.h	4374	0644	edit dl rm
tblcoll.h	37489	0644	edit dl rm
timezone.h	42005	0644	edit dl rm
tmunit.h	3461	0644	edit dl rm
tmutamt.h	5015	0644	edit dl rm
tmutfmt.h	8042	0644	edit dl rm
translit.h	67400	0644	edit dl rm
tzfmt.h	43916	0644	edit dl rm
tznames.h	17252	0644	edit dl rm
tzrule.h	36215	0644	edit dl rm
tztrans.h	6271	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	58265	0644	edit dl rm
ucasemap.h	15546	0644	edit dl rm
ucat.h	5484	0644	edit dl rm
uchar.h	144630	0644	edit dl rm
ucharstrie.h	23120	0644	edit dl rm
ucharstriebuilder.h	7378	0644	edit dl rm
uchriter.h	13521	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	62939	0644	edit dl rm
ucoleitr.h	9684	0644	edit dl rm
uconfig.h	12356	0644	edit dl rm
ucpmap.h	5663	0644	edit dl rm
ucptrie.h	23002	0644	edit dl rm
ucsdet.h	15018	0644	edit dl rm
ucurr.h	16507	0644	edit dl rm
udat.h	62851	0644	edit dl rm
udata.h	15930	0644	edit dl rm
udateintervalformat.h	10995	0644	edit dl rm
udatpg.h	27447	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
uformattedvalue.h	12413	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	11086	0644	edit dl rm
uloc.h	54432	0644	edit dl rm
ulocdata.h	11533	0644	edit dl rm
umachine.h	14884	0644	edit dl rm
umisc.h	1365	0644	edit dl rm
umsg.h	24812	0644	edit dl rm
umutablecptrie.h	8435	0644	edit dl rm
unifilt.h	4055	0644	edit dl rm
unifunct.h	4141	0644	edit dl rm
unimatch.h	6244	0644	edit dl rm
unirepl.h	3464	0644	edit dl rm
uniset.h	66459	0644	edit dl rm
unistr.h	174523	0644	edit dl rm
unorm.h	21015	0644	edit dl rm
unorm2.h	25254	0644	edit dl rm
unum.h	54743	0644	edit dl rm
unumberformatter.h	25824	0644	edit dl rm
unumsys.h	7387	0644	edit dl rm
uobject.h	10936	0644	edit dl rm
upluralrules.h	8013	0644	edit dl rm
uregex.h	73784	0644	edit dl rm
uregion.h	10073	0644	edit dl rm
ureldatefmt.h	17409	0644	edit dl rm
urename.h	134449	0644	edit dl rm
urep.h	5507	0644	edit dl rm
ures.h	37415	0644	edit dl rm
uscript.h	27867	0644	edit dl rm
usearch.h	39039	0644	edit dl rm
uset.h	40958	0644	edit dl rm
usetiter.h	9781	0644	edit dl rm
ushape.h	18432	0644	edit dl rm
uspoof.h	67480	0644	edit dl rm
usprep.h	8331	0644	edit dl rm
ustdio.h	39469	0644	edit dl rm
ustream.h	1934	0644	edit dl rm
ustring.h	74211	0644	edit dl rm
ustringtrie.h	3224	0644	edit dl rm
utext.h	59527	0644	edit dl rm
utf.h	8046	0644	edit dl rm
utf8.h	31700	0644	edit dl rm
utf16.h	23878	0644	edit dl rm
utf32.h	763	0644	edit dl rm
utf_old.h	46929	0644	edit dl rm
utmscale.h	14113	0644	edit dl rm
utrace.h	17706	0644	edit dl rm
utrans.h	26130	0644	edit dl rm
utypes.h	31481	0644	edit dl rm
uvernum.h	6832	0644	edit dl rm
uversion.h	6145	0644	edit dl rm
vtzone.h	20784	0644	edit dl rm

Edit: /usr/include/unicode/utf16.h (23878B)

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
*   Copyright (C) 1999-2012, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
*******************************************************************************
*   file name:  utf16.h
*   encoding:   UTF-8
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 1999sep09
*   created by: Markus W. Scherer
*/

/**
 * \file
 * \brief C API: 16-bit Unicode handling macros
 * 
 * This file defines macros to deal with 16-bit Unicode (UTF-16) code units 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 __UTF16_H__
#define __UTF16_H__

#include "unicode/umachine.h"
#ifndef __UTF_H__
#   include "unicode/utf.h"
#endif

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

/**
 * Does this code unit alone encode a code point (BMP, not a surrogate)?
 * @param c 16-bit code unit
 * @return TRUE or FALSE
 * @stable ICU 2.4
 */
#define U16_IS_SINGLE(c) !U_IS_SURROGATE(c)

/**
 * Is this code unit a lead surrogate (U+d800..U+dbff)?
 * @param c 16-bit code unit
 * @return TRUE or FALSE
 * @stable ICU 2.4
 */
#define U16_IS_LEAD(c) (((c)&0xfffffc00)==0xd800)

/**
 * Is this code unit a trail surrogate (U+dc00..U+dfff)?
 * @param c 16-bit code unit
 * @return TRUE or FALSE
 * @stable ICU 2.4
 */
#define U16_IS_TRAIL(c) (((c)&0xfffffc00)==0xdc00)

/**
 * Is this code unit a surrogate (U+d800..U+dfff)?
 * @param c 16-bit code unit
 * @return TRUE or FALSE
 * @stable ICU 2.4
 */
#define U16_IS_SURROGATE(c) U_IS_SURROGATE(c)

/**
 * Assuming c is a surrogate code point (U16_IS_SURROGATE(c)),
 * is it a lead surrogate?
 * @param c 16-bit code unit
 * @return TRUE or FALSE
 * @stable ICU 2.4
 */
#define U16_IS_SURROGATE_LEAD(c) (((c)&0x400)==0)

/**
 * Assuming c is a surrogate code point (U16_IS_SURROGATE(c)),
 * is it a trail surrogate?
 * @param c 16-bit code unit
 * @return TRUE or FALSE
 * @stable ICU 4.2
 */
#define U16_IS_SURROGATE_TRAIL(c) (((c)&0x400)!=0)

/**
 * Helper constant for U16_GET_SUPPLEMENTARY.
 * @internal
 */
#define U16_SURROGATE_OFFSET ((0xd800<<10UL)+0xdc00-0x10000)

/**
 * Get a supplementary code point value (U+10000..U+10ffff)
 * from its lead and trail surrogates.
 * The result is undefined if the input values are not
 * lead and trail surrogates.
 *
 * @param lead lead surrogate (U+d800..U+dbff)
 * @param trail trail surrogate (U+dc00..U+dfff)
 * @return supplementary code point (U+10000..U+10ffff)
 * @stable ICU 2.4
 */
#define U16_GET_SUPPLEMENTARY(lead, trail) \
    (((UChar32)(lead)<<10UL)+(UChar32)(trail)-U16_SURROGATE_OFFSET)

/**
 * Get the lead surrogate (0xd800..0xdbff) for a
 * supplementary code point (0x10000..0x10ffff).
 * @param supplementary 32-bit code point (U+10000..U+10ffff)
 * @return lead surrogate (U+d800..U+dbff) for supplementary
 * @stable ICU 2.4
 */
#define U16_LEAD(supplementary) (UChar)(((supplementary)>>10)+0xd7c0)

/**
 * Get the trail surrogate (0xdc00..0xdfff) for a
 * supplementary code point (0x10000..0x10ffff).
 * @param supplementary 32-bit code point (U+10000..U+10ffff)
 * @return trail surrogate (U+dc00..U+dfff) for supplementary
 * @stable ICU 2.4
 */
#define U16_TRAIL(supplementary) (UChar)(((supplementary)&0x3ff)|0xdc00)

/**
 * How many 16-bit code units are used to encode this Unicode code point? (1 or 2)
 * The result is not defined if c is not a Unicode code point (U+0000..U+10ffff).
 * @param c 32-bit code point
 * @return 1 or 2
 * @stable ICU 2.4
 */
#define U16_LENGTH(c) ((uint32_t)(c)<=0xffff ? 1 : 2)

/**
 * The maximum number of 16-bit code units per Unicode code point (U+0000..U+10ffff).
 * @return 2
 * @stable ICU 2.4
 */
#define U16_MAX_LENGTH 2

/**
 * Get a code point from a string at a random-access offset,
 * without changing the offset.
 * "Unsafe" macro, assumes well-formed UTF-16.
 *
 * The offset may point to either the lead or trail surrogate unit
 * for a supplementary code point, in which case the macro will read
 * the adjacent matching surrogate as well.
 * The result is undefined if the offset points to a single, unpaired surrogate.
 * Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT.
 *
 * @param s const UChar * string
 * @param i string offset
 * @param c output UChar32 variable
 * @see U16_GET
 * @stable ICU 2.4
 */
#define U16_GET_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \
    (c)=(s)[i]; \
    if(U16_IS_SURROGATE(c)) { \
        if(U16_IS_SURROGATE_LEAD(c)) { \
            (c)=U16_GET_SUPPLEMENTARY((c), (s)[(i)+1]); \
        } else { \
            (c)=U16_GET_SUPPLEMENTARY((s)[(i)-1], (c)); \
        } \
    } \
} UPRV_BLOCK_MACRO_END

/**
 * Get a code point from a string at a random-access offset,
 * without changing the offset.
 * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
 *
 * The offset may point to either the lead or trail surrogate unit
 * for a supplementary code point, in which case the macro will read
 * the adjacent matching surrogate as well.
 *
 * The length can be negative for a NUL-terminated string.
 *
 * If the offset points to a single, unpaired surrogate, then
 * c is set to that unpaired surrogate.
 * Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT.
 *
 * @param s const UChar * string
 * @param start starting string offset (usually 0)
 * @param i string offset, must be start<=i<length
 * @param length string length
 * @param c output UChar32 variable
 * @see U16_GET_UNSAFE
 * @stable ICU 2.4
 */
#define U16_GET(s, start, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \
    (c)=(s)[i]; \
    if(U16_IS_SURROGATE(c)) { \
        uint16_t __c2; \
        if(U16_IS_SURROGATE_LEAD(c)) { \
            if((i)+1!=(length) && U16_IS_TRAIL(__c2=(s)[(i)+1])) { \
                (c)=U16_GET_SUPPLEMENTARY((c), __c2); \
            } \
        } else { \
            if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
                (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
            } \
        } \
    } \
} UPRV_BLOCK_MACRO_END

/**
 * Get a code point from a string at a random-access offset,
 * without changing the offset.
 * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
 *
 * The offset may point to either the lead or trail surrogate unit
 * for a supplementary code point, in which case the macro will read
 * the adjacent matching surrogate as well.
 *
 * The length can be negative for a NUL-terminated string.
 *
 * If the offset points to a single, unpaired surrogate, then
 * c is set to U+FFFD.
 * Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT_OR_FFFD.
 *
 * @param s const UChar * string
 * @param start starting string offset (usually 0)
 * @param i string offset, must be start<=i<length
 * @param length string length
 * @param c output UChar32 variable
 * @see U16_GET_UNSAFE
 * @stable ICU 60
 */
#define U16_GET_OR_FFFD(s, start, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \
    (c)=(s)[i]; \
    if(U16_IS_SURROGATE(c)) { \
        uint16_t __c2; \
        if(U16_IS_SURROGATE_LEAD(c)) { \
            if((i)+1!=(length) && U16_IS_TRAIL(__c2=(s)[(i)+1])) { \
                (c)=U16_GET_SUPPLEMENTARY((c), __c2); \
            } else { \
                (c)=0xfffd; \
            } \
        } else { \
            if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
                (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
            } else { \
                (c)=0xfffd; \
            } \
        } \
    } \
} 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-16.
 *
 * The offset may point to the lead surrogate unit
 * for a supplementary code point, in which case the macro will read
 * the following trail surrogate as well.
 * If the offset points to a trail surrogate, then that itself
 * will be returned as the code point.
 * The result is undefined if the offset points to a single, unpaired lead surrogate.
 *
 * @param s const UChar * string
 * @param i string offset
 * @param c output UChar32 variable
 * @see U16_NEXT
 * @stable ICU 2.4
 */
#define U16_NEXT_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \
    (c)=(s)[(i)++]; \
    if(U16_IS_LEAD(c)) { \
        (c)=U16_GET_SUPPLEMENTARY((c), (s)[(i)++]); \
    } \
} 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, handles unpaired surrogates and checks for string boundaries.
 *
 * The length can be negative for a NUL-terminated string.
 *
 * The offset may point to the lead surrogate unit
 * for a supplementary code point, in which case the macro will read
 * the following trail surrogate as well.
 * If the offset points to a trail surrogate or
 * to a single, unpaired lead surrogate, then c is set to that unpaired surrogate.
 *
 * @param s const UChar * string
 * @param i string offset, must be i<length
 * @param length string length
 * @param c output UChar32 variable
 * @see U16_NEXT_UNSAFE
 * @stable ICU 2.4
 */
#define U16_NEXT(s, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \
    (c)=(s)[(i)++]; \
    if(U16_IS_LEAD(c)) { \
        uint16_t __c2; \
        if((i)!=(length) && U16_IS_TRAIL(__c2=(s)[(i)])) { \
            ++(i); \
            (c)=U16_GET_SUPPLEMENTARY((c), __c2); \
        } \
    } \
} 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, handles unpaired surrogates and checks for string boundaries.
 *
 * The length can be negative for a NUL-terminated string.
 *
 * The offset may point to the lead surrogate unit
 * for a supplementary code point, in which case the macro will read
 * the following trail surrogate as well.
 * If the offset points to a trail surrogate or
 * to a single, unpaired lead surrogate, then c is set to U+FFFD.
 *
 * @param s const UChar * string
 * @param i string offset, must be i<length
 * @param length string length
 * @param c output UChar32 variable
 * @see U16_NEXT_UNSAFE
 * @stable ICU 60
 */
#define U16_NEXT_OR_FFFD(s, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \
    (c)=(s)[(i)++]; \
    if(U16_IS_SURROGATE(c)) { \
        uint16_t __c2; \
        if(U16_IS_SURROGATE_LEAD(c) && (i)!=(length) && U16_IS_TRAIL(__c2=(s)[(i)])) { \
            ++(i); \
            (c)=U16_GET_SUPPLEMENTARY((c), __c2); \
        } else { \
            (c)=0xfffd; \
        } \
    } \
} UPRV_BLOCK_MACRO_END

/**
 * Append a code point to a string, overwriting 1 or 2 code units.
 * 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 UChar * string buffer
 * @param i string offset
 * @param c code point to append
 * @see U16_APPEND
 * @stable ICU 2.4
 */
#define U16_APPEND_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \
    if((uint32_t)(c)<=0xffff) { \
        (s)[(i)++]=(uint16_t)(c); \
    } else { \
        (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \
        (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \
    } \
} UPRV_BLOCK_MACRO_END

/**
 * Append a code point to a string, overwriting 1 or 2 code units.
 * 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 surrogate pair is written, checks for sufficient space in the string.
 * If the code point is not valid or a trail surrogate does not fit,
 * then isError is set to TRUE.
 *
 * @param s const UChar * string buffer
 * @param i string offset, must be i<capacity
 * @param capacity size of the string buffer
 * @param c code point to append
 * @param isError output UBool set to TRUE if an error occurs, otherwise not modified
 * @see U16_APPEND_UNSAFE
 * @stable ICU 2.4
 */
#define U16_APPEND(s, i, capacity, c, isError) UPRV_BLOCK_MACRO_BEGIN { \
    if((uint32_t)(c)<=0xffff) { \
        (s)[(i)++]=(uint16_t)(c); \
    } else if((uint32_t)(c)<=0x10ffff && (i)+1<(capacity)) { \
        (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \
        (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \
    } else /* c>0x10ffff or not enough space */ { \
        (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-16.
 *
 * @param s const UChar * string
 * @param i string offset
 * @see U16_FWD_1
 * @stable ICU 2.4
 */
#define U16_FWD_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \
    if(U16_IS_LEAD((s)[(i)++])) { \
        ++(i); \
    } \
} UPRV_BLOCK_MACRO_END

/**
 * Advance the string offset from one code point boundary to the next.
 * (Post-incrementing iteration.)
 * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
 *
 * The length can be negative for a NUL-terminated string.
 *
 * @param s const UChar * string
 * @param i string offset, must be i<length
 * @param length string length
 * @see U16_FWD_1_UNSAFE
 * @stable ICU 2.4
 */
#define U16_FWD_1(s, i, length) UPRV_BLOCK_MACRO_BEGIN { \
    if(U16_IS_LEAD((s)[(i)++]) && (i)!=(length) && U16_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-16.
 *
 * @param s const UChar * string
 * @param i string offset
 * @param n number of code points to skip
 * @see U16_FWD_N
 * @stable ICU 2.4
 */
#define U16_FWD_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \
    int32_t __N=(n); \
    while(__N>0) { \
        U16_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, handles unpaired surrogates and checks for string boundaries.
 *
 * The length can be negative for a NUL-terminated string.
 *
 * @param s const UChar * 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 U16_FWD_N_UNSAFE
 * @stable ICU 2.4
 */
#define U16_FWD_N(s, i, length, n) UPRV_BLOCK_MACRO_BEGIN { \
    int32_t __N=(n); \
    while(__N>0 && ((i)<(length) || ((length)<0 && (s)[i]!=0))) { \
        U16_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 the trail surrogate of a surrogate pair,
 * then the offset is decremented.
 * Otherwise, it is not modified.
 * "Unsafe" macro, assumes well-formed UTF-16.
 *
 * @param s const UChar * string
 * @param i string offset
 * @see U16_SET_CP_START
 * @stable ICU 2.4
 */
#define U16_SET_CP_START_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \
    if(U16_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 the trail surrogate of a surrogate pair,
 * then the offset is decremented.
 * Otherwise, it is not modified.
 * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
 *
 * @param s const UChar * string
 * @param start starting string offset (usually 0)
 * @param i string offset, must be start<=i
 * @see U16_SET_CP_START_UNSAFE
 * @stable ICU 2.4
 */
#define U16_SET_CP_START(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \
    if(U16_IS_TRAIL((s)[i]) && (i)>(start) && U16_IS_LEAD((s)[(i)-1])) { \
        --(i); \
    } \
} 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-16.
 *
 * The input offset may be the same as the string length.
 * If the offset is behind a trail surrogate unit
 * for a supplementary code point, then the macro will read
 * the preceding lead surrogate as well.
 * If the offset is behind a lead surrogate, then that itself
 * will be returned as the code point.
 * The result is undefined if the offset is behind a single, unpaired trail surrogate.
 *
 * @param s const UChar * string
 * @param i string offset
 * @param c output UChar32 variable
 * @see U16_PREV
 * @stable ICU 2.4
 */
#define U16_PREV_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \
    (c)=(s)[--(i)]; \
    if(U16_IS_TRAIL(c)) { \
        (c)=U16_GET_SUPPLEMENTARY((s)[--(i)], (c)); \
    } \
} 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, handles unpaired surrogates and checks for string boundaries.
 *
 * The input offset may be the same as the string length.
 * If the offset is behind a trail surrogate unit
 * for a supplementary code point, then the macro will read
 * the preceding lead surrogate as well.
 * If the offset is behind a lead surrogate or behind a single, unpaired
 * trail surrogate, then c is set to that unpaired surrogate.
 *
 * @param s const UChar * string
 * @param start starting string offset (usually 0)
 * @param i string offset, must be start<i
 * @param c output UChar32 variable
 * @see U16_PREV_UNSAFE
 * @stable ICU 2.4
 */
#define U16_PREV(s, start, i, c) UPRV_BLOCK_MACRO_BEGIN { \
    (c)=(s)[--(i)]; \
    if(U16_IS_TRAIL(c)) { \
        uint16_t __c2; \
        if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
            --(i); \
            (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
        } \
    } \
} 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, handles unpaired surrogates and checks for string boundaries.
 *
 * The input offset may be the same as the string length.
 * If the offset is behind a trail surrogate unit
 * for a supplementary code point, then the macro will read
 * the preceding lead surrogate as well.
 * If the offset is behind a lead surrogate or behind a single, unpaired
 * trail surrogate, then c is set to U+FFFD.
 *
 * @param s const UChar * string
 * @param start starting string offset (usually 0)
 * @param i string offset, must be start<i
 * @param c output UChar32 variable
 * @see U16_PREV_UNSAFE
 * @stable ICU 60
 */
#define U16_PREV_OR_FFFD(s, start, i, c) UPRV_BLOCK_MACRO_BEGIN { \
    (c)=(s)[--(i)]; \
    if(U16_IS_SURROGATE(c)) { \
        uint16_t __c2; \
        if(U16_IS_SURROGATE_TRAIL(c) && (i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
            --(i); \
            (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
        } else { \
            (c)=0xfffd; \
        } \
    } \
} 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-16.
 *
 * @param s const UChar * string
 * @param i string offset
 * @see U16_BACK_1
 * @stable ICU 2.4
 */
#define U16_BACK_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \
    if(U16_IS_TRAIL((s)[--(i)])) { \
        --(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, handles unpaired surrogates and checks for string boundaries.
 *
 * @param s const UChar * string
 * @param start starting string offset (usually 0)
 * @param i string offset, must be start<i
 * @see U16_BACK_1_UNSAFE
 * @stable ICU 2.4
 */
#define U16_BACK_1(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \
    if(U16_IS_TRAIL((s)[--(i)]) && (i)>(start) && U16_IS_LEAD((s)[(i)-1])) { \
        --(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-16.
 *
 * @param s const UChar * string
 * @param i string offset
 * @param n number of code points to skip
 * @see U16_BACK_N
 * @stable ICU 2.4
 */
#define U16_BACK_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \
    int32_t __N=(n); \
    while(__N>0) { \
        U16_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, handles unpaired surrogates and checks for string boundaries.
 *
 * @param s const UChar * string
 * @param start start of string
 * @param i string offset, must be start<i
 * @param n number of code points to skip
 * @see U16_BACK_N_UNSAFE
 * @stable ICU 2.4
 */
#define U16_BACK_N(s, start, i, n) UPRV_BLOCK_MACRO_BEGIN { \
    int32_t __N=(n); \
    while(__N>0 && (i)>(start)) { \
        U16_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 the lead surrogate of a surrogate pair,
 * then the offset is incremented.
 * Otherwise, it is not modified.
 * The input offset may be the same as the string length.
 * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
 *
 * The length can be negative for a NUL-terminated string.
 *
 * @param s const UChar * string
 * @param start int32_t starting string offset (usually 0)
 * @param i int32_t string offset, start<=i<=length
 * @param length int32_t string length
 * @see U16_SET_CP_LIMIT_UNSAFE
 * @stable ICU 2.4
 */
#define U16_SET_CP_LIMIT(s, start, i, length) UPRV_BLOCK_MACRO_BEGIN { \
    if((start)<(i) && ((i)<(length) || (length)<0) && U16_IS_LEAD((s)[(i)-1]) && U16_IS_TRAIL((s)[i])) { \
        ++(i); \
    } \
} UPRV_BLOCK_MACRO_END

#endif

cmd: