PNG  IHDRxsBIT|d pHYs+tEXtSoftwarewww.inkscape.org<,tEXtComment File Manager

File Manager

Path: /opt/alt/alt-nodejs24/root/usr/include/unicode/

Viewing File: utf.h

// © 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__ */
b IDATxytVսϓ22 A@IR :hCiZ[v*E:WũZA ^dQeQ @ !jZ'>gsV仿$|?g)&x-EIENT ;@xT.i%-X}SvS5.r/UHz^_$-W"w)Ɗ/@Z &IoX P$K}JzX:;` &, ŋui,e6mX ԵrKb1ԗ)DADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADA݀!I*]R;I2$eZ#ORZSrr6mteffu*((Pu'v{DIߔ4^pIm'77WEEE;vƎ4-$]'RI{\I&G :IHJ DWBB=\WR޽m o$K(V9ABB.}jѢv`^?IOȅ} ڶmG}T#FJ`56$-ھ}FI&v;0(h;Б38CӧOWf!;A i:F_m9s&|q%=#wZprrrla A &P\\СC[A#! {olF} `E2}MK/vV)i{4BffV\|ۭX`b@kɶ@%i$K z5zhmX[IXZ` 'b%$r5M4º/l ԃߖxhʔ)[@=} K6IM}^5k㏷݆z ΗÿO:gdGBmyT/@+Vɶ纽z񕏵l.y޴it뭷zV0[Y^>Wsqs}\/@$(T7f.InݺiR$푔n.~?H))\ZRW'Mo~v Ov6oԃxz! S,&xm/yɞԟ?'uaSѽb,8GלKboi&3t7Y,)JJ c[nzӳdE&KsZLӄ I?@&%ӟ۶mSMMњ0iؐSZ,|J+N ~,0A0!5%Q-YQQa3}$_vVrf9f?S8`zDADADADADADADADADAdqP,تmMmg1V?rSI꒟]u|l RCyEf٢9 jURbztѰ!m5~tGj2DhG*{H9)꒟ר3:(+3\?/;TUݭʴ~S6lڧUJ*i$d(#=Yݺd{,p|3B))q:vN0Y.jkק6;SɶVzHJJЀ-utѹսk>QUU\޲~]fFnK?&ߡ5b=z9)^|u_k-[y%ZNU6 7Mi:]ۦtk[n X(e6Bb."8cۭ|~teuuw|ήI-5"~Uk;ZicEmN/:]M> cQ^uiƞ??Ңpc#TUU3UakNwA`:Y_V-8.KKfRitv޲* 9S6ֿj,ՃNOMߤ]z^fOh|<>@Å5 _/Iu?{SY4hK/2]4%it5q]GGe2%iR| W&f*^]??vq[LgE_3f}Fxu~}qd-ږFxu~I N>\;͗O֊:̗WJ@BhW=y|GgwܷH_NY?)Tdi'?խwhlmQi !SUUsw4kӺe4rfxu-[nHtMFj}H_u~w>)oV}(T'ebʒv3_[+vn@Ȭ\S}ot}w=kHFnxg S 0eޢm~l}uqZfFoZuuEg `zt~? b;t%>WTkķh[2eG8LIWx,^\thrl^Ϊ{=dž<}qV@ ⠨Wy^LF_>0UkDuʫuCs$)Iv:IK;6ֲ4{^6եm+l3>݆uM 9u?>Zc }g~qhKwڭeFMM~pМuqǿz6Tb@8@Y|jx](^]gf}M"tG -w.@vOqh~/HII`S[l.6nØXL9vUcOoB\xoǤ'T&IǍQw_wpv[kmO{w~>#=P1Pɞa-we:iǏlHo׈꒟f9SzH?+shk%Fs:qVhqY`jvO'ρ?PyX3lх]˾uV{ݞ]1,MzYNW~̈́ joYn}ȚF߾׮mS]F z+EDxm/d{F{-W-4wY듏:??_gPf ^3ecg ҵs8R2מz@TANGj)}CNi/R~}c:5{!ZHӋӾ6}T]G]7W6^n 9*,YqOZj:P?Q DFL|?-^.Ɵ7}fFh׶xe2Pscz1&5\cn[=Vn[ĶE鎀uˌd3GII k;lNmشOuuRVfBE]ۣeӶu :X-[(er4~LHi6:Ѻ@ԅrST0trk%$Č0ez" *z"T/X9|8.C5Feg}CQ%͞ˣJvL/?j^h&9xF`њZ(&yF&Iݻfg#W;3^{Wo^4'vV[[K';+mӍִ]AC@W?1^{එyh +^]fm~iԵ]AB@WTk̏t uR?l.OIHiYyԶ]Aˀ7c:q}ힽaf6Z~қm(+sK4{^6}T*UUu]n.:kx{:2 _m=sAߤU@?Z-Vކеz왍Nэ{|5 pڶn b p-@sPg]0G7fy-M{GCF'%{4`=$-Ge\ eU:m+Zt'WjO!OAF@ik&t݆ϥ_ e}=]"Wz_.͜E3leWFih|t-wZۍ-uw=6YN{6|} |*={Ѽn.S.z1zjۻTH]흾 DuDvmvK.`V]yY~sI@t?/ϓ. m&["+P?MzovVЫG3-GRR[(!!\_,^%?v@ҵő m`Y)tem8GMx.))A]Y i`ViW`?^~!S#^+ѽGZj?Vģ0.))A꨷lzL*]OXrY`DBBLOj{-MH'ii-ϰ ok7^ )쭡b]UXSְmռY|5*cֽk0B7镹%ڽP#8nȎq}mJr23_>lE5$iwui+ H~F`IjƵ@q \ @#qG0".0" l`„.0! ,AQHN6qzkKJ#o;`Xv2>,tێJJ7Z/*A .@fفjMzkg @TvZH3Zxu6Ra'%O?/dQ5xYkU]Rֽkق@DaS^RSּ5|BeHNN͘p HvcYcC5:y #`οb;z2.!kr}gUWkyZn=f Pvsn3p~;4p˚=ē~NmI] ¾ 0lH[_L hsh_ғߤc_њec)g7VIZ5yrgk̞W#IjӪv>՞y睝M8[|]\շ8M6%|@PZڨI-m>=k='aiRo-x?>Q.}`Ȏ:Wsmu u > .@,&;+!!˱tﭧDQwRW\vF\~Q7>spYw$%A~;~}6¾ g&if_=j,v+UL1(tWake:@Ș>j$Gq2t7S?vL|]u/ .(0E6Mk6hiۺzښOrifޱxm/Gx> Lal%%~{lBsR4*}{0Z/tNIɚpV^#Lf:u@k#RSu =S^ZyuR/.@n&΃z~B=0eg뺆#,Þ[B/?H uUf7y Wy}Bwegל`Wh(||`l`.;Ws?V@"c:iɍL֯PGv6zctM̠':wuW;d=;EveD}9J@B(0iհ bvP1{\P&G7D޴Iy_$-Qjm~Yrr&]CDv%bh|Yzni_ˆR;kg}nJOIIwyuL}{ЌNj}:+3Y?:WJ/N+Rzd=hb;dj͒suݔ@NKMԄ jqzC5@y°hL m;*5ezᕏ=ep XL n?מ:r`۵tŤZ|1v`V뽧_csج'ߤ%oTuumk%%%h)uy]Nk[n 'b2 l.=͜E%gf$[c;s:V-͞WߤWh-j7]4=F-X]>ZLSi[Y*We;Zan(ӇW|e(HNNP5[= r4tP &0<pc#`vTNV GFqvTi*Tyam$ߏWyE*VJKMTfFw>'$-ؽ.Ho.8c"@DADADADADADADADADA~j*֘,N;Pi3599h=goضLgiJ5փy~}&Zd9p֚ e:|hL``b/d9p? fgg+%%hMgXosج, ΩOl0Zh=xdjLmhݻoO[g_l,8a]٭+ӧ0$I]c]:粹:Teꢢ"5a^Kgh,&= =՟^߶“ߢE ܹS J}I%:8 IDAT~,9/ʃPW'Mo}zNƍ쨓zPbNZ~^z=4mswg;5 Y~SVMRXUյڱRf?s:w ;6H:ºi5-maM&O3;1IKeamZh͛7+##v+c ~u~ca]GnF'ټL~PPPbn voC4R,ӟgg %hq}@#M4IÇ Oy^xMZx ) yOw@HkN˖-Sǎmb]X@n+i͖!++K3gd\$mt$^YfJ\8PRF)77Wא!Cl$i:@@_oG I{$# 8磌ŋ91A (Im7֭>}ߴJq7ޗt^ -[ԩSj*}%]&' -ɓ'ꫯVzzvB#;a 7@GxI{j޼ƌ.LÇWBB7`O"I$/@R @eee@۷>}0,ɒ2$53Xs|cS~rpTYYY} kHc %&k.], @ADADADADADADADADA@lT<%''*Lo^={رc5h %$+CnܸQ3fҥK}vUVVs9G R,_{xˇ3o߾;TTTd}馛]uuuG~iԩ@4bnvmvfϞ /Peeeq}}za I~,誫{UWW뮻}_~YƍSMMMYχ֝waw\ďcxꩧtEƍկ_?۷5@u?1kNׯWzz/wy>}zj3 k(ٺuq_Zvf̘:~ ABQ&r|!%KҥKgԞ={<_X-z !CyFUUz~ ABQIIIjݺW$UXXDٳZ~ ABQƍecW$<(~<RSSvZujjjԧOZQu@4 8m&&&jԩg$ď1h ͟?_{768@g =@`)))5o6m3)ѣƌJ;wҿUTT /KZR{~a=@0o<*狔iFɶ[ˎ;T]]OX@?K.ۈxN pppppppppppppppppPfl߾] ,{ァk۶mڿo5BTӦMӴiӴ|r DB2e|An!Dy'tkΝ[A $***t5' "!駟oaDnΝ:t֭[gDШQ06qD;@ x M6v(PiizmZ4ew"@̴ixf [~-Fٱc&IZ2|n!?$@{[HTɏ#@hȎI# _m(F /6Z3z'\r,r!;w2Z3j=~GY7"I$iI.p_"?pN`y DD?: _  Gÿab7J !Bx@0 Bo cG@`1C[@0G @`0C_u V1 aCX>W ` | `!<S `"<. `#c`?cAC4 ?c p#~@0?:08&_MQ1J h#?/`7;I  q 7a wQ A 1 Hp !#<8/#@1Ul7=S=K.4Z?E_$i@!1!E4?`P_  @Bă10#: "aU,xbFY1 [n|n #'vEH:`xb #vD4Y hi.i&EΖv#O H4IŶ}:Ikh @tZRF#(tXҙzZ ?I3l7q@õ|ۍ1,GpuY Ꮿ@hJv#xxk$ v#9 5 }_$c S#=+"K{F*m7`#%H:NRSp6I?sIՖ{Ap$I$I:QRv2$Z @UJ*$]<FO4IENDB`