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/utf8.h (20512B)

/*
*******************************************************************************
*
*   Copyright (C) 1999-2007, 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.
 * utf8.h is included by utf.h after unicode/umachine.h
 * and some common definitions.
 *
 * For more information see utf.h and 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.
 */

#ifndef __UTF8_H__
#define __UTF8_H__

/* utf.h must be included first. */
#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.
 * @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];

/**
 * Count the trail bytes for a UTF-8 lead byte.
 * @internal
 */
#define U8_COUNT_TRAIL_BYTES(leadByte) (utf8_countTrailBytes[(uint8_t)leadByte])

/**
 * Mask a UTF-8 lead byte, leave only the lower bits that form part of the code point value.
 * @internal
 */
#define U8_MASK_LEAD_BYTE(leadByte, countTrailBytes) ((leadByte)&=(1<<(6-(countTrailBytes)))-1)

/**
 * Function for handling "next code point" with error-checking.
 * @internal
 */
U_INTERNAL 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.
 * @internal
 */
U_INTERNAL 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.
 * @internal
 */
U_INTERNAL 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.
 * @internal
 */
U_INTERNAL 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.
 * 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 starting string offset
 * @param i string offset, must be start<=i<length
 * @param length 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=(int32_t)(i); \
    U8_SET_CP_START(s, start, _u8_get_index); \
    U8_NEXT(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((uint8_t)((c)-0xc0)<0x35) { \
        uint8_t __count=U8_COUNT_TRAIL_BYTES(c); \
        U8_MASK_LEAD_BYTE(c, __count); \
        switch(__count) { \
        /* each following branch falls through to the next one */ \
        case 3: \
            (c)=((c)<<6)|((s)[(i)++]&0x3f); \
        case 2: \
            (c)=((c)<<6)|((s)[(i)++]&0x3f); \
        case 1: \
            (c)=((c)<<6)|((s)[(i)++]&0x3f); \
        /* no other branches to optimize switch() */ \
            break; \
        } \
    } \
}

/**
 * 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 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 string offset, must be i<length
 * @param length 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)) && \
            (__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)=(UChar)((((c)&0x1f)<<6)|__t1); \
            ++(i); \
        } else if(U8_IS_LEAD(c)) { \
            /* function call for "complicated" and error cases */ \
            (c)=utf8_nextCharSafeBody((const uint8_t *)s, &(i), (int32_t)(length), c, -1); \
        } else { \
            (c)=U_SENTINEL; \
        } \
    } \
}

/**
 * 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 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 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, (int32_t)(i), (int32_t)(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((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.
 *
 * @param s const uint8_t * string
 * @param i string offset, must be i<length
 * @param length 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)) { \
            __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.
 *
 * @param s const uint8_t * string
 * @param i string offset, must be i<length
 * @param length 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)) { \
        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 starting string offset (usually 0)
 * @param i 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, (int32_t)(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 starting string offset (usually 0)
 * @param i 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) { \
        if((c)<=0xbf) { \
            (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -1); \
        } else { \
            (c)=U_SENTINEL; \
        } \
    } \
}

/**
 * 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 starting string offset (usually 0)
 * @param i 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, (int32_t)(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 index of the start of the string
 * @param i 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.
 *
 * @param s const uint8_t * string
 * @param start starting string offset (usually 0)
 * @param i string offset, must be start<=i<=length
 * @param length 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)) { \
        U8_BACK_1(s, start, i); \
        U8_FWD_1(s, i, length); \
    } \
}

#endif

cmd: