PNG  IHDRX cHRMz&u0`:pQ<bKGD pHYsodtIME MeqIDATxw]Wug^Qd˶ 6`!N:!@xI~)%7%@Bh&`lnjVF29gΨ4E$|>cɚ{gk= %,a KX%,a KX%,a KX%,a KX%,a KX%,a KX%, b` ǟzeאfp]<!SJmɤY޲ڿ,%c ~ع9VH.!Ͳz&QynֺTkRR.BLHi٪:l;@(!MԴ=žI,:o&N'Kù\vRmJ雵֫AWic H@" !: Cé||]k-Ha oݜ:y F())u]aG7*JV@J415p=sZH!=!DRʯvɱh~V\}v/GKY$n]"X"}t@ xS76^[bw4dsce)2dU0 CkMa-U5tvLƀ~mlMwfGE/-]7XAƟ`׮g ewxwC4\[~7@O-Q( a*XGƒ{ ՟}$_y3tĐƤatgvێi|K=uVyrŲlLӪuܿzwk$m87k( `múcE)"@rK( z4$D; 2kW=Xb$V[Ru819קR~qloѱDyįݎ*mxw]y5e4K@ЃI0A D@"BDk_)N\8͜9dz"fK0zɿvM /.:2O{ Nb=M=7>??Zuo32 DLD@D| &+֎C #B8ַ`bOb $D#ͮҪtx]%`ES`Ru[=¾!@Od37LJ0!OIR4m]GZRJu$‡c=%~s@6SKy?CeIh:[vR@Lh | (BhAMy=݃  G"'wzn޺~8ԽSh ~T*A:xR[ܹ?X[uKL_=fDȊ؂p0}7=D$Ekq!/t.*2ʼnDbŞ}DijYaȲ(""6HA;:LzxQ‘(SQQ}*PL*fc\s `/d'QXW, e`#kPGZuŞuO{{wm[&NBTiiI0bukcA9<4@SӊH*؎4U/'2U5.(9JuDfrޱtycU%j(:RUbArLֺN)udA':uGQN"-"Is.*+k@ `Ojs@yU/ H:l;@yyTn}_yw!VkRJ4P)~y#)r,D =ě"Q]ci'%HI4ZL0"MJy 8A{ aN<8D"1#IJi >XjX֔#@>-{vN!8tRݻ^)N_╗FJEk]CT՟ YP:_|H1@ CBk]yKYp|og?*dGvzنzӴzjֺNkC~AbZƷ`.H)=!QͷVTT(| u78y֮}|[8-Vjp%2JPk[}ԉaH8Wpqhwr:vWª<}l77_~{s۴V+RCģ%WRZ\AqHifɤL36: #F:p]Bq/z{0CU6ݳEv_^k7'>sq*+kH%a`0ԣisqにtү04gVgW΂iJiS'3w.w}l6MC2uԯ|>JF5`fV5m`Y**Db1FKNttu]4ccsQNnex/87+}xaUW9y>ͯ骵G{䩓Գ3+vU}~jJ.NFRD7<aJDB1#ҳgSb,+CS?/ VG J?|?,2#M9}B)MiE+G`-wo߫V`fio(}S^4e~V4bHOYb"b#E)dda:'?}׮4繏`{7Z"uny-?ǹ;0MKx{:_pÚmFמ:F " .LFQLG)Q8qN q¯¯3wOvxDb\. BKD9_NN &L:4D{mm o^tֽ:q!ƥ}K+<"m78N< ywsard5+вz~mnG)=}lYݧNj'QJS{S :UYS-952?&O-:W}(!6Mk4+>A>j+i|<<|;ر^߉=HE|V#F)Emm#}/"y GII웻Jі94+v뾧xu~5C95~ūH>c@덉pʃ1/4-A2G%7>m;–Y,cyyaln" ?ƻ!ʪ<{~h~i y.zZB̃/,雋SiC/JFMmBH&&FAbϓO^tubbb_hZ{_QZ-sύodFgO(6]TJA˯#`۶ɟ( %$&+V'~hiYy>922 Wp74Zkq+Ovn錄c>8~GqܲcWꂎz@"1A.}T)uiW4="jJ2W7mU/N0gcqܗOO}?9/wìXžΏ0 >֩(V^Rh32!Hj5`;O28؇2#ݕf3 ?sJd8NJ@7O0 b־?lldщ̡&|9C.8RTWwxWy46ah嘦mh٤&l zCy!PY?: CJyв]dm4ǜҐR޻RլhX{FƯanшQI@x' ao(kUUuxW_Ñ줮[w8 FRJ(8˼)_mQ _!RJhm=!cVmm ?sFOnll6Qk}alY}; "baӌ~M0w,Ggw2W:G/k2%R,_=u`WU R.9T"v,<\Ik޽/2110Ӿxc0gyC&Ny޽JҢrV6N ``یeA16"J³+Rj*;BϜkZPJaÍ<Jyw:NP8/D$ 011z֊Ⱳ3ι֘k1V_"h!JPIΣ'ɜ* aEAd:ݺ>y<}Lp&PlRfTb1]o .2EW\ͮ]38؋rTJsǏP@芎sF\> P^+dYJLbJ C-xϐn> ι$nj,;Ǖa FU *择|h ~izť3ᤓ`K'-f tL7JK+vf2)V'-sFuB4i+m+@My=O҈0"|Yxoj,3]:cо3 $#uŘ%Y"y죯LebqtҢVzq¼X)~>4L׶m~[1_k?kxֺQ`\ |ٛY4Ѯr!)N9{56(iNq}O()Em]=F&u?$HypWUeB\k]JɩSع9 Zqg4ZĊo oMcjZBU]B\TUd34ݝ~:7ڶSUsB0Z3srx 7`:5xcx !qZA!;%͚7&P H<WL!džOb5kF)xor^aujƍ7 Ǡ8/p^(L>ὴ-B,{ۇWzֺ^k]3\EE@7>lYBȝR.oHnXO/}sB|.i@ɥDB4tcm,@ӣgdtJ!lH$_vN166L__'Z)y&kH;:,Y7=J 9cG) V\hjiE;gya~%ks_nC~Er er)muuMg2;֫R)Md) ,¶ 2-wr#F7<-BBn~_(o=KO㭇[Xv eN_SMgSҐ BS헃D%g_N:/pe -wkG*9yYSZS.9cREL !k}<4_Xs#FmҶ:7R$i,fi!~' # !6/S6y@kZkZcX)%5V4P]VGYq%H1!;e1MV<!ϐHO021Dp= HMs~~a)ަu7G^];git!Frl]H/L$=AeUvZE4P\.,xi {-~p?2b#amXAHq)MWǾI_r`S Hz&|{ +ʖ_= (YS(_g0a03M`I&'9vl?MM+m~}*xT۲(fY*V4x@29s{DaY"toGNTO+xCAO~4Ϳ;p`Ѫ:>Ҵ7K 3}+0 387x\)a"/E>qpWB=1 ¨"MP(\xp߫́A3+J] n[ʼnӼaTbZUWb={~2ooKױӰp(CS\S筐R*JغV&&"FA}J>G֐p1ٸbk7 ŘH$JoN <8s^yk_[;gy-;߉DV{c B yce% aJhDȶ 2IdйIB/^n0tNtџdcKj4϶v~- CBcgqx9= PJ) dMsjpYB] GD4RDWX +h{y`,3ꊕ$`zj*N^TP4L:Iz9~6s) Ga:?y*J~?OrMwP\](21sZUD ?ܟQ5Q%ggW6QdO+\@ ̪X'GxN @'4=ˋ+*VwN ne_|(/BDfj5(Dq<*tNt1х!MV.C0 32b#?n0pzj#!38}޴o1KovCJ`8ŗ_"]] rDUy޲@ Ȗ-;xџ'^Y`zEd?0„ DAL18IS]VGq\4o !swV7ˣι%4FѮ~}6)OgS[~Q vcYbL!wG3 7띸*E Pql8=jT\꘿I(z<[6OrR8ºC~ډ]=rNl[g|v TMTղb-o}OrP^Q]<98S¤!k)G(Vkwyqyr޽Nv`N/e p/~NAOk \I:G6]4+K;j$R:Mi #*[AȚT,ʰ,;N{HZTGMoּy) ]%dHء9Պ䠬|<45,\=[bƟ8QXeB3- &dҩ^{>/86bXmZ]]yޚN[(WAHL$YAgDKp=5GHjU&99v簪C0vygln*P)9^͞}lMuiH!̍#DoRBn9l@ xA/_v=ȺT{7Yt2N"4!YN`ae >Q<XMydEB`VU}u]嫇.%e^ánE87Mu\t`cP=AD/G)sI"@MP;)]%fH9'FNsj1pVhY&9=0pfuJ&gޤx+k:!r˭wkl03׼Ku C &ѓYt{.O.zҏ z}/tf_wEp2gvX)GN#I ݭ߽v/ .& и(ZF{e"=V!{zW`, ]+LGz"(UJp|j( #V4, 8B 0 9OkRrlɱl94)'VH9=9W|>PS['G(*I1==C<5"Pg+x'K5EMd؞Af8lG ?D FtoB[je?{k3zQ vZ;%Ɠ,]E>KZ+T/ EJxOZ1i #T<@ I}q9/t'zi(EMqw`mYkU6;[t4DPeckeM;H}_g pMww}k6#H㶏+b8雡Sxp)&C $@'b,fPߑt$RbJ'vznuS ~8='72_`{q纶|Q)Xk}cPz9p7O:'|G~8wx(a 0QCko|0ASD>Ip=4Q, d|F8RcU"/KM opKle M3#i0c%<7׿p&pZq[TR"BpqauIp$ 8~Ĩ!8Սx\ւdT>>Z40ks7 z2IQ}ItԀ<-%S⍤};zIb$I 5K}Q͙D8UguWE$Jh )cu4N tZl+[]M4k8֦Zeq֮M7uIqG 1==tLtR,ƜSrHYt&QP윯Lg' I,3@P'}'R˪e/%-Auv·ñ\> vDJzlӾNv5:|K/Jb6KI9)Zh*ZAi`?S {aiVDԲuy5W7pWeQJk֤#5&V<̺@/GH?^τZL|IJNvI:'P=Ϛt"¨=cud S Q.Ki0 !cJy;LJR;G{BJy޺[^8fK6)=yʊ+(k|&xQ2`L?Ȓ2@Mf 0C`6-%pKpm')c$׻K5[J*U[/#hH!6acB JA _|uMvDyk y)6OPYjœ50VT K}cǻP[ $:]4MEA.y)|B)cf-A?(e|lɉ#P9V)[9t.EiQPDѠ3ϴ;E:+Օ t ȥ~|_N2,ZJLt4! %ա]u {+=p.GhNcŞQI?Nd'yeh n7zi1DB)1S | S#ًZs2|Ɛy$F SxeX{7Vl.Src3E℃Q>b6G ўYCmtկ~=K0f(=LrAS GN'ɹ9<\!a`)֕y[uՍ[09` 9 +57ts6}b4{oqd+J5fa/,97J#6yν99mRWxJyѡyu_TJc`~W>l^q#Ts#2"nD1%fS)FU w{ܯ R{ ˎ󅃏џDsZSQS;LV;7 Od1&1n$ N /.q3~eNɪ]E#oM~}v֯FڦwyZ=<<>Xo稯lfMFV6p02|*=tV!c~]fa5Y^Q_WN|Vs 0ҘދU97OI'N2'8N֭fgg-}V%y]U4 峧p*91#9U kCac_AFңĪy뚇Y_AiuYyTTYЗ-(!JFLt›17uTozc. S;7A&&<ԋ5y;Ro+:' *eYJkWR[@F %SHWP 72k4 qLd'J "zB6{AC0ƁA6U.'F3:Ȅ(9ΜL;D]m8ڥ9}dU "v!;*13Rg^fJyShyy5auA?ɩGHRjo^]׽S)Fm\toy 4WQS@mE#%5ʈfFYDX ~D5Ϡ9tE9So_aU4?Ѽm%&c{n>.KW1Tlb}:j uGi(JgcYj0qn+>) %\!4{LaJso d||u//P_y7iRJ߬nHOy) l+@$($VFIQ9%EeKʈU. ia&FY̒mZ=)+qqoQn >L!qCiDB;Y<%} OgBxB!ØuG)WG9y(Ą{_yesuZmZZey'Wg#C~1Cev@0D $a@˲(.._GimA:uyw֬%;@!JkQVM_Ow:P.s\)ot- ˹"`B,e CRtaEUP<0'}r3[>?G8xU~Nqu;Wm8\RIkբ^5@k+5(By'L&'gBJ3ݶ!/㮻w҅ yqPWUg<e"Qy*167΃sJ\oz]T*UQ<\FԎ`HaNmڜ6DysCask8wP8y9``GJ9lF\G g's Nn͵MLN֪u$| /|7=]O)6s !ĴAKh]q_ap $HH'\1jB^s\|- W1:=6lJBqjY^LsPk""`]w)󭃈,(HC ?䔨Y$Sʣ{4Z+0NvQkhol6C.婧/u]FwiVjZka&%6\F*Ny#8O,22+|Db~d ~Çwc N:FuuCe&oZ(l;@ee-+Wn`44AMK➝2BRՈt7g*1gph9N) *"TF*R(#'88pm=}X]u[i7bEc|\~EMn}P瘊J)K.0i1M6=7'_\kaZ(Th{K*GJyytw"IO-PWJk)..axӝ47"89Cc7ĐBiZx 7m!fy|ϿF9CbȩV 9V-՛^pV̌ɄS#Bv4-@]Vxt-Z, &ֺ*diؠ2^VXbs֔Ìl.jQ]Y[47gj=幽ex)A0ip׳ W2[ᎇhuE^~q흙L} #-b۸oFJ_QP3r6jr+"nfzRJTUqoaۍ /$d8Mx'ݓ= OՃ| )$2mcM*cЙj}f };n YG w0Ia!1Q.oYfr]DyISaP}"dIӗթO67jqR ҊƐƈaɤGG|h;t]䗖oSv|iZqX)oalv;۩meEJ\!8=$4QU4Xo&VEĊ YS^E#d,yX_> ۘ-e\ "Wa6uLĜZi`aD9.% w~mB(02G[6y.773a7 /=o7D)$Z 66 $bY^\CuP. (x'"J60׿Y:Oi;F{w佩b+\Yi`TDWa~|VH)8q/=9!g߆2Y)?ND)%?Ǐ`k/sn:;O299yB=a[Ng 3˲N}vLNy;*?x?~L&=xyӴ~}q{qE*IQ^^ͧvü{Huu=R|>JyUlZV, B~/YF!Y\u_ݼF{_C)LD]m {H 0ihhadd nUkf3oٺCvE\)QJi+֥@tDJkB$1!Đr0XQ|q?d2) Ӣ_}qv-< FŊ߫%roppVBwü~JidY4:}L6M7f٬F "?71<2#?Jyy4뷢<_a7_=Q E=S1И/9{+93֮E{ǂw{))?maÆm(uLE#lïZ  ~d];+]h j?!|$F}*"4(v'8s<ŏUkm7^7no1w2ؗ}TrͿEk>p'8OB7d7R(A 9.*Mi^ͳ; eeUwS+C)uO@ =Sy]` }l8^ZzRXj[^iUɺ$tj))<sbDJfg=Pk_{xaKo1:-uyG0M ԃ\0Lvuy'ȱc2Ji AdyVgVh!{]/&}}ċJ#%d !+87<;qN޼Nفl|1N:8ya  8}k¾+-$4FiZYÔXk*I&'@iI99)HSh4+2G:tGhS^繿 Kتm0 вDk}֚+QT4;sC}rՅE,8CX-e~>G&'9xpW,%Fh,Ry56Y–hW-(v_,? ; qrBk4-V7HQ;ˇ^Gv1JVV%,ik;D_W!))+BoS4QsTM;gt+ndS-~:11Sgv!0qRVh!"Ȋ(̦Yl.]PQWgٳE'`%W1{ndΗBk|Ž7ʒR~,lnoa&:ü$ 3<a[CBݮwt"o\ePJ=Hz"_c^Z.#ˆ*x z̝grY]tdkP*:97YľXyBkD4N.C_[;F9`8& !AMO c `@BA& Ost\-\NX+Xp < !bj3C&QL+*&kAQ=04}cC!9~820G'PC9xa!w&bo_1 Sw"ܱ V )Yl3+ס2KoXOx]"`^WOy :3GO0g;%Yv㐫(R/r (s } u B &FeYZh0y> =2<Ϟc/ -u= c&׭,.0"g"7 6T!vl#sc>{u/Oh Bᾈ)۴74]x7 gMӒ"d]U)}" v4co[ ɡs 5Gg=XR14?5A}D "b{0$L .\4y{_fe:kVS\\O]c^W52LSBDM! C3Dhr̦RtArx4&agaN3Cf<Ԉp4~ B'"1@.b_/xQ} _߃҉/gٓ2Qkqp0շpZ2fԫYz< 4L.Cyυι1t@鎫Fe sYfsF}^ V}N<_`p)alٶ "(XEAVZ<)2},:Ir*#m_YӼ R%a||EƼIJ,,+f"96r/}0jE/)s)cjW#w'Sʯ5<66lj$a~3Kʛy 2:cZ:Yh))+a߭K::N,Q F'qB]={.]h85C9cr=}*rk?vwV렵ٸW Rs%}rNAkDv|uFLBkWY YkX מ|)1!$#3%y?pF<@<Rr0}: }\J [5FRxY<9"SQdE(Q*Qʻ)q1E0B_O24[U'],lOb ]~WjHޏTQ5Syu wq)xnw8~)c 쫬gٲߠ H% k5dƝk> kEj,0% b"vi2Wس_CuK)K{n|>t{P1򨾜j>'kEkƗBg*H%'_aY6Bn!TL&ɌOb{c`'d^{t\i^[uɐ[}q0lM˕G:‚4kb祔c^:?bpg… +37stH:0}en6x˟%/<]BL&* 5&fK9Mq)/iyqtA%kUe[ڛKN]Ě^,"`/ s[EQQm?|XJ߅92m]G.E΃ח U*Cn.j_)Tѧj̿30ڇ!A0=͜ar I3$C^-9#|pk!)?7.x9 @OO;WƝZBFU keZ75F6Tc6"ZȚs2y/1 ʵ:u4xa`C>6Rb/Yм)^=+~uRd`/|_8xbB0?Ft||Z\##|K 0>>zxv8۴吅q 8ĥ)"6>~\8:qM}#͚'ĉ#p\׶ l#bA?)|g g9|8jP(cr,BwV (WliVxxᡁ@0Okn;ɥh$_ckCgriv}>=wGzβ KkBɛ[˪ !J)h&k2%07δt}!d<9;I&0wV/ v 0<H}L&8ob%Hi|޶o&h1L|u֦y~󛱢8fٲUsւ)0oiFx2}X[zVYr_;N(w]_4B@OanC?gĦx>мgx>ΛToZoOMp>40>V Oy V9iq!4 LN,ˢu{jsz]|"R޻&'ƚ{53ўFu(<٪9:΋]B;)B>1::8;~)Yt|0(pw2N%&X,URBK)3\zz&}ax4;ǟ(tLNg{N|Ǽ\G#C9g$^\}p?556]/RP.90 k,U8/u776s ʪ_01چ|\N 0VV*3H鴃J7iI!wG_^ypl}r*jɤSR 5QN@ iZ#1ٰy;_\3\BQQ x:WJv츟ٯ$"@6 S#qe딇(/P( Dy~TOϻ<4:-+F`0||;Xl-"uw$Цi󼕝mKʩorz"mϺ$F:~E'ҐvD\y?Rr8_He@ e~O,T.(ފR*cY^m|cVR[8 JҡSm!ΆԨb)RHG{?MpqrmN>߶Y)\p,d#xۆWY*,l6]v0h15M˙MS8+EdI='LBJIH7_9{Caз*Lq,dt >+~ّeʏ?xԕ4bBAŚjﵫ!'\Ը$WNvKO}ӽmSşذqsOy?\[,d@'73'j%kOe`1.g2"e =YIzS2|zŐƄa\U,dP;jhhhaxǶ?КZ՚.q SE+XrbOu%\GتX(H,N^~]JyEZQKceTQ]VGYqnah;y$cQahT&QPZ*iZ8UQQM.qo/T\7X"u?Mttl2Xq(IoW{R^ ux*SYJ! 4S.Jy~ BROS[V|žKNɛP(L6V^|cR7i7nZW1Fd@ Ara{詑|(T*dN]Ko?s=@ |_EvF]׍kR)eBJc" MUUbY6`~V޴dJKß&~'d3i WWWWWW
Current Directory: /opt/alt/alt-nodejs18/root/usr/include/unicode
Viewing File: /opt/alt/alt-nodejs18/root/usr/include/unicode/utf_old.h
// © 2016 and later: Unicode, Inc. and others. // License & terms of use: http://www.unicode.org/copyright.html /* ******************************************************************************* * * Copyright (C) 2002-2012, International Business Machines * Corporation and others. All Rights Reserved. * ******************************************************************************* * file name: utf_old.h * encoding: UTF-8 * tab size: 8 (not used) * indentation:4 * * created on: 2002sep21 * created by: Markus W. Scherer */ /** * \file * \brief C API: Deprecated macros for Unicode string handling * * The macros in utf_old.h are all deprecated and their use discouraged. * Some of the design principles behind the set of UTF macros * have changed or proved impractical. * Almost all of the old "UTF macros" are at least renamed. * If you are looking for a new equivalent to an old macro, please see the * comment at the old one. * * Brief summary of reasons for deprecation: * - Switch on UTF_SIZE (selection of UTF-8/16/32 default string processing) * was impractical. * - Switch on UTF_SAFE etc. (selection of unsafe/safe/strict default string processing) * was of little use and impractical. * - Whole classes of macros became obsolete outside of the UTF_SIZE/UTF_SAFE * selection framework: UTF32_ macros (all trivial) * and UTF_ default and intermediate macros (all aliases). * - The selection framework also caused many macro aliases. * - Change in Unicode standard: "irregular" sequences (3.0) became illegal (3.2). * - Change of language in Unicode standard: * Growing distinction between internal x-bit Unicode strings and external UTF-x * forms, with the former more lenient. * Suggests renaming of UTF16_ macros to U16_. * - The prefix "UTF_" without a width number confused some users. * - "Safe" append macros needed the addition of an error indicator output. * - "Safe" UTF-8 macros used legitimate (if rarely used) code point values * to indicate error conditions. * - The use of the "_CHAR" infix for code point operations confused some users. * * More details: * * Until ICU 2.2, utf.h theoretically allowed to choose among UTF-8/16/32 * for string processing, and among unsafe/safe/strict default macros for that. * * It proved nearly impossible to write non-trivial, high-performance code * that is UTF-generic. * Unsafe default macros would be dangerous for default string processing, * and the main reason for the "strict" versions disappeared: * Between Unicode 3.0 and 3.2 all "irregular" UTF-8 sequences became illegal. * The only other conditions that "strict" checked for were non-characters, * which are valid during processing. Only during text input/output should they * be checked, and at that time other well-formedness checks may be * necessary or useful as well. * This can still be done by using U16_NEXT and U_IS_UNICODE_NONCHAR * or U_IS_UNICODE_CHAR. * * The old UTF8_..._SAFE macros also used some normal Unicode code points * to indicate malformed sequences. * The new UTF8_ macros without suffix use negative values instead. * * The entire contents of utf32.h was moved here without replacement * because all those macros were trivial and * were meaningful only in the framework of choosing the UTF size. * * See Jitterbug 2150 and its discussion on the ICU mailing list * in September 2002. * * <hr> * * <em>Obsolete part</em> of pre-ICU 2.4 utf.h file documentation: * * <p>The original concept for these files was for ICU to allow * in principle to set which UTF (UTF-8/16/32) is used internally * by defining UTF_SIZE to either 8, 16, or 32. utf.h would then define the UChar type * accordingly. UTF-16 was the default.</p> * * <p>This concept has been abandoned. * A lot of the ICU source code assumes UChar strings are in UTF-16. * This is especially true for low-level code like * conversion, normalization, and collation. * The utf.h header enforces the default of UTF-16. * The UTF-8 and UTF-32 macros remain for now for completeness and backward compatibility.</p> * * <p>Accordingly, 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.</p> * * <p>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.</p> * * <p>utf.h also defines a number of C macros for handling single Unicode code points and * for using UTF Unicode strings. It includes utf8.h, utf16.h, and utf32.h for the actual * implementations of those macros and then aliases one set of them (for UTF-16) for general use. * The UTF-specific macros have the UTF size in the macro name prefixes (UTF16_...), while * the general alias macros always begin with UTF_...</p> * * <p>Many string operations can be done with or without error checking. * Where such a distinction is useful, there are two versions of the macros, "unsafe" and "safe" * ones with ..._UNSAFE and ..._SAFE suffixes. The unsafe macros are fast but may cause * program failures if the strings are not well-formed. The safe macros have an additional, boolean * parameter "strict". If strict is false, then only illegal sequences are detected. * Otherwise, irregular sequences and non-characters are detected as well (like single surrogates). * Safe macros return special error code points for illegal/irregular sequences: * Typically, U+ffff, or values that would result in a code unit sequence of the same length * as the erroneous input sequence.<br> * Note that _UNSAFE macros have fewer parameters: They do not have the strictness parameter, and * they do not have start/length parameters for boundary checking.</p> * * <p>Here, the macros are aliased in two steps: * In the first step, the UTF-specific macros with UTF16_ prefix and _UNSAFE and _SAFE suffixes are * aliased according to the UTF_SIZE to macros with UTF_ prefix and the same suffixes and signatures. * Then, in a second step, the default, general alias macros are set to use either the unsafe or * the safe/not strict (default) or the safe/strict macro; * these general macros do not have a strictness parameter.</p> * * <p>It is possible to change the default choice for the general alias macros to be unsafe, safe/not strict or safe/strict. * The default is safe/not strict. It is not recommended to select the unsafe macros as the basis for * Unicode string handling in ICU! To select this, define UTF_SAFE, UTF_STRICT, or UTF_UNSAFE.</p> * * <p>For general use, one should use the default, general macros with UTF_ prefix and no _SAFE/_UNSAFE suffix. * Only in some cases it may be necessary to control the choice of macro directly and use a less generic alias. * For example, if it can be assumed that a string is well-formed and the index will stay within the bounds, * then the _UNSAFE version may be used. * If a UTF-8 string is to be processed, then the macros with UTF8_ prefixes need to be used.</p> * * <hr> * * Deprecated ICU 2.4. Use the macros in utf.h, utf16.h, utf8.h instead. */ #ifndef __UTF_OLD_H__ #define __UTF_OLD_H__ #include "unicode/utf.h" #include "unicode/utf8.h" #include "unicode/utf16.h" /** * \def U_HIDE_OBSOLETE_UTF_OLD_H * * Hides the obsolete definitions in unicode/utf_old.h. * Recommended to be set to 1 at compile time to make sure * the long-deprecated macros are no longer used. * * For reasons for the deprecation see the utf_old.h file comments. * * @internal */ #ifndef U_HIDE_OBSOLETE_UTF_OLD_H # define U_HIDE_OBSOLETE_UTF_OLD_H 0 #endif #if !defined(U_HIDE_DEPRECATED_API) && !U_HIDE_OBSOLETE_UTF_OLD_H /* Formerly utf.h, part 1 --------------------------------------------------- */ #ifdef U_USE_UTF_DEPRECATES /** * Unicode string and array offset and index type. * ICU always counts Unicode code units (UChars) for * string offsets, indexes, and lengths, not Unicode code points. * * @obsolete ICU 2.6. Use int32_t directly instead since this API will be removed in that release. */ typedef int32_t UTextOffset; #endif /** Number of bits in a Unicode string code unit - ICU uses 16-bit Unicode. @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF_SIZE 16 /** * The default choice for general Unicode string macros is to use the ..._SAFE macro implementations * with strict=false. * * @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF_SAFE /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #undef UTF_UNSAFE /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #undef UTF_STRICT /** * UTF8_ERROR_VALUE_1 and UTF8_ERROR_VALUE_2 are special error values for UTF-8, * which need 1 or 2 bytes in UTF-8: * \code * U+0015 = NAK = Negative Acknowledge, C0 control character * U+009f = highest C1 control character * \endcode * * These are used by UTF8_..._SAFE macros so that they can return an error value * that needs the same number of code units (bytes) as were seen by * a macro. They should be tested with UTF_IS_ERROR() or UTF_IS_VALID(). * * @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF8_ERROR_VALUE_1 0x15 /** * See documentation on UTF8_ERROR_VALUE_1 for details. * * @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF8_ERROR_VALUE_2 0x9f /** * Error value for all UTFs. This code point value will be set by macros with error * checking if an error is detected. * * @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF_ERROR_VALUE 0xffff /** * Is a given 32-bit code an error value * as returned by one of the macros for any UTF? * * @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF_IS_ERROR(c) \ (((c)&0xfffe)==0xfffe || (c)==UTF8_ERROR_VALUE_1 || (c)==UTF8_ERROR_VALUE_2) /** * This is a combined macro: Is c a valid Unicode value _and_ not an error code? * * @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF_IS_VALID(c) \ (UTF_IS_UNICODE_CHAR(c) && \ (c)!=UTF8_ERROR_VALUE_1 && (c)!=UTF8_ERROR_VALUE_2) /** * Is this code unit or code point a surrogate (U+d800..U+dfff)? * @deprecated ICU 2.4. Renamed to U_IS_SURROGATE and U16_IS_SURROGATE, see utf_old.h. */ #define UTF_IS_SURROGATE(uchar) (((uchar)&0xfffff800)==0xd800) /** * Is a given 32-bit code point a Unicode noncharacter? * * @deprecated ICU 2.4. Renamed to U_IS_UNICODE_NONCHAR, see utf_old.h. */ #define UTF_IS_UNICODE_NONCHAR(c) \ ((c)>=0xfdd0 && \ ((uint32_t)(c)<=0xfdef || ((c)&0xfffe)==0xfffe) && \ (uint32_t)(c)<=0x10ffff) /** * Is a given 32-bit value 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. * * @deprecated ICU 2.4. Renamed to U_IS_UNICODE_CHAR, see utf_old.h. */ #define UTF_IS_UNICODE_CHAR(c) \ ((uint32_t)(c)<0xd800 || \ ((uint32_t)(c)>0xdfff && \ (uint32_t)(c)<=0x10ffff && \ !UTF_IS_UNICODE_NONCHAR(c))) /* Formerly utf8.h ---------------------------------------------------------- */ /** * \var utf8_countTrailBytes * Internal array with numbers of trail bytes for any given byte used in * lead byte position. * * This is internal since it is not meant to be called directly by external clients; * however it is called by public macros in this file and thus must remain stable, * and should not be hidden when other internal functions are hidden (otherwise * public macros would fail to compile). * @internal */ #ifdef U_UTF8_IMPL // No forward declaration if compiling utf_impl.cpp, which defines utf8_countTrailBytes. #elif defined(U_STATIC_IMPLEMENTATION) || defined(U_COMMON_IMPLEMENTATION) U_CAPI const uint8_t utf8_countTrailBytes[]; #else U_CFUNC U_IMPORT const uint8_t utf8_countTrailBytes[]; #endif /** * Count the trail bytes for a UTF-8 lead byte. * @deprecated ICU 2.4. Renamed to U8_COUNT_TRAIL_BYTES, see utf_old.h. */ #define UTF8_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. * @deprecated ICU 2.4. Renamed to U8_MASK_LEAD_BYTE, see utf_old.h. */ #define UTF8_MASK_LEAD_BYTE(leadByte, countTrailBytes) ((leadByte)&=(1<<(6-(countTrailBytes)))-1) /** Is this this code point a single code unit (byte)? @deprecated ICU 2.4. Renamed to U8_IS_SINGLE, see utf_old.h. */ #define UTF8_IS_SINGLE(uchar) (((uchar)&0x80)==0) /** Is this this code unit the lead code unit (byte) of a code point? @deprecated ICU 2.4. Renamed to U8_IS_LEAD, see utf_old.h. */ #define UTF8_IS_LEAD(uchar) ((uint8_t)((uchar)-0xc0)<0x3e) /** Is this this code unit a trailing code unit (byte) of a code point? @deprecated ICU 2.4. Renamed to U8_IS_TRAIL, see utf_old.h. */ #define UTF8_IS_TRAIL(uchar) (((uchar)&0xc0)==0x80) /** Does this scalar Unicode value need multiple code units for storage? @deprecated ICU 2.4. Use U8_LENGTH or test ((uint32_t)(c)>0x7f) instead, see utf_old.h. */ #define UTF8_NEED_MULTIPLE_UCHAR(c) ((uint32_t)(c)>0x7f) /** * Given the lead character, how many bytes are taken by this code point. * ICU does not deal with code points >0x10ffff * unless necessary for advancing in the byte stream. * * These length macros take into account that for values >0x10ffff * the UTF8_APPEND_CHAR_SAFE macros would write the error code point 0xffff * with 3 bytes. * Code point comparisons need to be in uint32_t because UChar32 * may be a signed type, and negative values must be recognized. * * @deprecated ICU 2.4. Use U8_LENGTH instead, see utf.h. */ #if 1 # define UTF8_CHAR_LENGTH(c) \ ((uint32_t)(c)<=0x7f ? 1 : \ ((uint32_t)(c)<=0x7ff ? 2 : \ ((uint32_t)((c)-0x10000)>0xfffff ? 3 : 4) \ ) \ ) #else # define UTF8_CHAR_LENGTH(c) \ ((uint32_t)(c)<=0x7f ? 1 : \ ((uint32_t)(c)<=0x7ff ? 2 : \ ((uint32_t)(c)<=0xffff ? 3 : \ ((uint32_t)(c)<=0x10ffff ? 4 : \ ((uint32_t)(c)<=0x3ffffff ? 5 : \ ((uint32_t)(c)<=0x7fffffff ? 6 : 3) \ ) \ ) \ ) \ ) \ ) #endif /** The maximum number of bytes per code point. @deprecated ICU 2.4. Renamed to U8_MAX_LENGTH, see utf_old.h. */ #define UTF8_MAX_CHAR_LENGTH 4 /** Average number of code units compared to UTF-16. @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF8_ARRAY_SIZE(size) ((5*(size))/2) /** @deprecated ICU 2.4. Renamed to U8_GET_UNSAFE, see utf_old.h. */ #define UTF8_GET_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ int32_t _utf8_get_char_unsafe_index=(int32_t)(i); \ UTF8_SET_CHAR_START_UNSAFE(s, _utf8_get_char_unsafe_index); \ UTF8_NEXT_CHAR_UNSAFE(s, _utf8_get_char_unsafe_index, c); \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Use U8_GET instead, see utf_old.h. */ #define UTF8_GET_CHAR_SAFE(s, start, i, length, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ int32_t _utf8_get_char_safe_index=(int32_t)(i); \ UTF8_SET_CHAR_START_SAFE(s, start, _utf8_get_char_safe_index); \ UTF8_NEXT_CHAR_SAFE(s, _utf8_get_char_safe_index, length, c, strict); \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U8_NEXT_UNSAFE, see utf_old.h. */ #define UTF8_NEXT_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(s)[(i)++]; \ if((uint8_t)((c)-0xc0)<0x35) { \ uint8_t __count=UTF8_COUNT_TRAIL_BYTES(c); \ UTF8_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; \ } \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U8_APPEND_UNSAFE, see utf_old.h. */ #define UTF8_APPEND_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ 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); \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U8_FWD_1_UNSAFE, see utf_old.h. */ #define UTF8_FWD_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ (i)+=1+UTF8_COUNT_TRAIL_BYTES((s)[i]); \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U8_FWD_N_UNSAFE, see utf_old.h. */ #define UTF8_FWD_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ int32_t __N=(n); \ while(__N>0) { \ UTF8_FWD_1_UNSAFE(s, i); \ --__N; \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U8_SET_CP_START_UNSAFE, see utf_old.h. */ #define UTF8_SET_CHAR_START_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ while(UTF8_IS_TRAIL((s)[i])) { --(i); } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Use U8_NEXT instead, see utf_old.h. */ #define UTF8_NEXT_CHAR_SAFE(s, i, length, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(s)[(i)++]; \ if((c)>=0x80) { \ if(UTF8_IS_LEAD(c)) { \ (c)=utf8_nextCharSafeBody(s, &(i), (int32_t)(length), c, strict); \ } else { \ (c)=UTF8_ERROR_VALUE_1; \ } \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Use U8_APPEND instead, see utf_old.h. */ #define UTF8_APPEND_CHAR_SAFE(s, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ if((uint32_t)(c)<=0x7f) { \ (s)[(i)++]=(uint8_t)(c); \ } else { \ (i)=utf8_appendCharSafeBody(s, (int32_t)(i), (int32_t)(length), c, NULL); \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U8_FWD_1, see utf_old.h. */ #define UTF8_FWD_1_SAFE(s, i, length) U8_FWD_1(s, i, length) /** @deprecated ICU 2.4. Renamed to U8_FWD_N, see utf_old.h. */ #define UTF8_FWD_N_SAFE(s, i, length, n) U8_FWD_N(s, i, length, n) /** @deprecated ICU 2.4. Renamed to U8_SET_CP_START, see utf_old.h. */ #define UTF8_SET_CHAR_START_SAFE(s, start, i) U8_SET_CP_START(s, start, i) /** @deprecated ICU 2.4. Renamed to U8_PREV_UNSAFE, see utf_old.h. */ #define UTF8_PREV_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(s)[--(i)]; \ if(UTF8_IS_TRAIL(c)) { \ uint8_t __b, __count=1, __shift=6; \ \ /* c is a trail byte */ \ (c)&=0x3f; \ for(;;) { \ __b=(s)[--(i)]; \ if(__b>=0xc0) { \ UTF8_MASK_LEAD_BYTE(__b, __count); \ (c)|=(UChar32)__b<<__shift; \ break; \ } else { \ (c)|=(UChar32)(__b&0x3f)<<__shift; \ ++__count; \ __shift+=6; \ } \ } \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U8_BACK_1_UNSAFE, see utf_old.h. */ #define UTF8_BACK_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ while(UTF8_IS_TRAIL((s)[--(i)])) {} \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U8_BACK_N_UNSAFE, see utf_old.h. */ #define UTF8_BACK_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ int32_t __N=(n); \ while(__N>0) { \ UTF8_BACK_1_UNSAFE(s, i); \ --__N; \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U8_SET_CP_LIMIT_UNSAFE, see utf_old.h. */ #define UTF8_SET_CHAR_LIMIT_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ UTF8_BACK_1_UNSAFE(s, i); \ UTF8_FWD_1_UNSAFE(s, i); \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Use U8_PREV instead, see utf_old.h. */ #define UTF8_PREV_CHAR_SAFE(s, start, i, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(s)[--(i)]; \ if((c)>=0x80) { \ if((c)<=0xbf) { \ (c)=utf8_prevCharSafeBody(s, start, &(i), c, strict); \ } else { \ (c)=UTF8_ERROR_VALUE_1; \ } \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U8_BACK_1, see utf_old.h. */ #define UTF8_BACK_1_SAFE(s, start, i) U8_BACK_1(s, start, i) /** @deprecated ICU 2.4. Renamed to U8_BACK_N, see utf_old.h. */ #define UTF8_BACK_N_SAFE(s, start, i, n) U8_BACK_N(s, start, i, n) /** @deprecated ICU 2.4. Renamed to U8_SET_CP_LIMIT, see utf_old.h. */ #define UTF8_SET_CHAR_LIMIT_SAFE(s, start, i, length) U8_SET_CP_LIMIT(s, start, i, length) /* Formerly utf16.h --------------------------------------------------------- */ /** Is uchar a first/lead surrogate? @deprecated ICU 2.4. Renamed to U_IS_LEAD and U16_IS_LEAD, see utf_old.h. */ #define UTF_IS_FIRST_SURROGATE(uchar) (((uchar)&0xfffffc00)==0xd800) /** Is uchar a second/trail surrogate? @deprecated ICU 2.4. Renamed to U_IS_TRAIL and U16_IS_TRAIL, see utf_old.h. */ #define UTF_IS_SECOND_SURROGATE(uchar) (((uchar)&0xfffffc00)==0xdc00) /** Assuming c is a surrogate, is it a first/lead surrogate? @deprecated ICU 2.4. Renamed to U_IS_SURROGATE_LEAD and U16_IS_SURROGATE_LEAD, see utf_old.h. */ #define UTF_IS_SURROGATE_FIRST(c) (((c)&0x400)==0) /** Helper constant for UTF16_GET_PAIR_VALUE. @deprecated ICU 2.4. Renamed to U16_SURROGATE_OFFSET, see utf_old.h. */ #define UTF_SURROGATE_OFFSET ((0xd800<<10UL)+0xdc00-0x10000) /** Get the UTF-32 value from the surrogate code units. @deprecated ICU 2.4. Renamed to U16_GET_SUPPLEMENTARY, see utf_old.h. */ #define UTF16_GET_PAIR_VALUE(first, second) \ (((first)<<10UL)+(second)-UTF_SURROGATE_OFFSET) /** @deprecated ICU 2.4. Renamed to U16_LEAD, see utf_old.h. */ #define UTF_FIRST_SURROGATE(supplementary) (UChar)(((supplementary)>>10)+0xd7c0) /** @deprecated ICU 2.4. Renamed to U16_TRAIL, see utf_old.h. */ #define UTF_SECOND_SURROGATE(supplementary) (UChar)(((supplementary)&0x3ff)|0xdc00) /** @deprecated ICU 2.4. Renamed to U16_LEAD, see utf_old.h. */ #define UTF16_LEAD(supplementary) UTF_FIRST_SURROGATE(supplementary) /** @deprecated ICU 2.4. Renamed to U16_TRAIL, see utf_old.h. */ #define UTF16_TRAIL(supplementary) UTF_SECOND_SURROGATE(supplementary) /** @deprecated ICU 2.4. Renamed to U16_IS_SINGLE, see utf_old.h. */ #define UTF16_IS_SINGLE(uchar) !UTF_IS_SURROGATE(uchar) /** @deprecated ICU 2.4. Renamed to U16_IS_LEAD, see utf_old.h. */ #define UTF16_IS_LEAD(uchar) UTF_IS_FIRST_SURROGATE(uchar) /** @deprecated ICU 2.4. Renamed to U16_IS_TRAIL, see utf_old.h. */ #define UTF16_IS_TRAIL(uchar) UTF_IS_SECOND_SURROGATE(uchar) /** Does this scalar Unicode value need multiple code units for storage? @deprecated ICU 2.4. Use U16_LENGTH or test ((uint32_t)(c)>0xffff) instead, see utf_old.h. */ #define UTF16_NEED_MULTIPLE_UCHAR(c) ((uint32_t)(c)>0xffff) /** @deprecated ICU 2.4. Renamed to U16_LENGTH, see utf_old.h. */ #define UTF16_CHAR_LENGTH(c) ((uint32_t)(c)<=0xffff ? 1 : 2) /** @deprecated ICU 2.4. Renamed to U16_MAX_LENGTH, see utf_old.h. */ #define UTF16_MAX_CHAR_LENGTH 2 /** Average number of code units compared to UTF-16. @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF16_ARRAY_SIZE(size) (size) /** * Get a single code point from an offset that points to any * of the code units that belong to that code point. * Assume 0<=i<length. * * This could be used for iteration together with * UTF16_CHAR_LENGTH() and UTF_IS_ERROR(), * but the use of UTF16_NEXT_CHAR[_UNSAFE]() and * UTF16_PREV_CHAR[_UNSAFE]() is more efficient for that. * @deprecated ICU 2.4. Renamed to U16_GET_UNSAFE, see utf_old.h. */ #define UTF16_GET_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(s)[i]; \ if(UTF_IS_SURROGATE(c)) { \ if(UTF_IS_SURROGATE_FIRST(c)) { \ (c)=UTF16_GET_PAIR_VALUE((c), (s)[(i)+1]); \ } else { \ (c)=UTF16_GET_PAIR_VALUE((s)[(i)-1], (c)); \ } \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Use U16_GET instead, see utf_old.h. */ #define UTF16_GET_CHAR_SAFE(s, start, i, length, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(s)[i]; \ if(UTF_IS_SURROGATE(c)) { \ uint16_t __c2; \ if(UTF_IS_SURROGATE_FIRST(c)) { \ if((i)+1<(length) && UTF_IS_SECOND_SURROGATE(__c2=(s)[(i)+1])) { \ (c)=UTF16_GET_PAIR_VALUE((c), __c2); \ /* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \ } else if(strict) {\ /* unmatched first surrogate */ \ (c)=UTF_ERROR_VALUE; \ } \ } else { \ if((i)-1>=(start) && UTF_IS_FIRST_SURROGATE(__c2=(s)[(i)-1])) { \ (c)=UTF16_GET_PAIR_VALUE(__c2, (c)); \ /* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \ } else if(strict) {\ /* unmatched second surrogate */ \ (c)=UTF_ERROR_VALUE; \ } \ } \ } else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \ (c)=UTF_ERROR_VALUE; \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U16_NEXT_UNSAFE, see utf_old.h. */ #define UTF16_NEXT_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(s)[(i)++]; \ if(UTF_IS_FIRST_SURROGATE(c)) { \ (c)=UTF16_GET_PAIR_VALUE((c), (s)[(i)++]); \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U16_APPEND_UNSAFE, see utf_old.h. */ #define UTF16_APPEND_CHAR_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 /** @deprecated ICU 2.4. Renamed to U16_FWD_1_UNSAFE, see utf_old.h. */ #define UTF16_FWD_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ if(UTF_IS_FIRST_SURROGATE((s)[(i)++])) { \ ++(i); \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U16_FWD_N_UNSAFE, see utf_old.h. */ #define UTF16_FWD_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ int32_t __N=(n); \ while(__N>0) { \ UTF16_FWD_1_UNSAFE(s, i); \ --__N; \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U16_SET_CP_START_UNSAFE, see utf_old.h. */ #define UTF16_SET_CHAR_START_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ if(UTF_IS_SECOND_SURROGATE((s)[i])) { \ --(i); \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Use U16_NEXT instead, see utf_old.h. */ #define UTF16_NEXT_CHAR_SAFE(s, i, length, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(s)[(i)++]; \ if(UTF_IS_FIRST_SURROGATE(c)) { \ uint16_t __c2; \ if((i)<(length) && UTF_IS_SECOND_SURROGATE(__c2=(s)[(i)])) { \ ++(i); \ (c)=UTF16_GET_PAIR_VALUE((c), __c2); \ /* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \ } else if(strict) {\ /* unmatched first surrogate */ \ (c)=UTF_ERROR_VALUE; \ } \ } else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \ /* unmatched second surrogate or other non-character */ \ (c)=UTF_ERROR_VALUE; \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Use U16_APPEND instead, see utf_old.h. */ #define UTF16_APPEND_CHAR_SAFE(s, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ if((uint32_t)(c)<=0xffff) { \ (s)[(i)++]=(uint16_t)(c); \ } else if((uint32_t)(c)<=0x10ffff) { \ if((i)+1<(length)) { \ (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \ (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \ } else /* not enough space */ { \ (s)[(i)++]=UTF_ERROR_VALUE; \ } \ } else /* c>0x10ffff, write error value */ { \ (s)[(i)++]=UTF_ERROR_VALUE; \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U16_FWD_1, see utf_old.h. */ #define UTF16_FWD_1_SAFE(s, i, length) U16_FWD_1(s, i, length) /** @deprecated ICU 2.4. Renamed to U16_FWD_N, see utf_old.h. */ #define UTF16_FWD_N_SAFE(s, i, length, n) U16_FWD_N(s, i, length, n) /** @deprecated ICU 2.4. Renamed to U16_SET_CP_START, see utf_old.h. */ #define UTF16_SET_CHAR_START_SAFE(s, start, i) U16_SET_CP_START(s, start, i) /** @deprecated ICU 2.4. Renamed to U16_PREV_UNSAFE, see utf_old.h. */ #define UTF16_PREV_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(s)[--(i)]; \ if(UTF_IS_SECOND_SURROGATE(c)) { \ (c)=UTF16_GET_PAIR_VALUE((s)[--(i)], (c)); \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U16_BACK_1_UNSAFE, see utf_old.h. */ #define UTF16_BACK_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ if(UTF_IS_SECOND_SURROGATE((s)[--(i)])) { \ --(i); \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U16_BACK_N_UNSAFE, see utf_old.h. */ #define UTF16_BACK_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ int32_t __N=(n); \ while(__N>0) { \ UTF16_BACK_1_UNSAFE(s, i); \ --__N; \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT_UNSAFE, see utf_old.h. */ #define UTF16_SET_CHAR_LIMIT_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ if(UTF_IS_FIRST_SURROGATE((s)[(i)-1])) { \ ++(i); \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Use U16_PREV instead, see utf_old.h. */ #define UTF16_PREV_CHAR_SAFE(s, start, i, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(s)[--(i)]; \ if(UTF_IS_SECOND_SURROGATE(c)) { \ uint16_t __c2; \ if((i)>(start) && UTF_IS_FIRST_SURROGATE(__c2=(s)[(i)-1])) { \ --(i); \ (c)=UTF16_GET_PAIR_VALUE(__c2, (c)); \ /* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \ } else if(strict) {\ /* unmatched second surrogate */ \ (c)=UTF_ERROR_VALUE; \ } \ } else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \ /* unmatched first surrogate or other non-character */ \ (c)=UTF_ERROR_VALUE; \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Renamed to U16_BACK_1, see utf_old.h. */ #define UTF16_BACK_1_SAFE(s, start, i) U16_BACK_1(s, start, i) /** @deprecated ICU 2.4. Renamed to U16_BACK_N, see utf_old.h. */ #define UTF16_BACK_N_SAFE(s, start, i, n) U16_BACK_N(s, start, i, n) /** @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT, see utf_old.h. */ #define UTF16_SET_CHAR_LIMIT_SAFE(s, start, i, length) U16_SET_CP_LIMIT(s, start, i, length) /* Formerly utf32.h --------------------------------------------------------- */ /* * Old documentation: * * This file defines macros to deal with UTF-32 code units and code points. * Signatures and semantics are the same as for the similarly named macros * in utf16.h. * utf32.h is included by utf.h after unicode/umachine.h</p> * and some common definitions. * <p><b>Usage:</b> 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.</p> */ /* internal definitions ----------------------------------------------------- */ /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_IS_SAFE(c, strict) \ (!(strict) ? \ (uint32_t)(c)<=0x10ffff : \ UTF_IS_UNICODE_CHAR(c)) /* * For the semantics of all of these macros, see utf16.h. * The UTF-32 versions are trivial because any code point is * encoded using exactly one code unit. */ /* single-code point definitions -------------------------------------------- */ /* classes of code unit values */ /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_IS_SINGLE(uchar) 1 /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_IS_LEAD(uchar) 0 /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_IS_TRAIL(uchar) 0 /* number of code units per code point */ /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_NEED_MULTIPLE_UCHAR(c) 0 /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_CHAR_LENGTH(c) 1 /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_MAX_CHAR_LENGTH 1 /* average number of code units compared to UTF-16 */ /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_ARRAY_SIZE(size) (size) /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_GET_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(s)[i]; \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_GET_CHAR_SAFE(s, start, i, length, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(s)[i]; \ if(!UTF32_IS_SAFE(c, strict)) { \ (c)=UTF_ERROR_VALUE; \ } \ } UPRV_BLOCK_MACRO_END /* definitions with forward iteration --------------------------------------- */ /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_NEXT_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(s)[(i)++]; \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_APPEND_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ (s)[(i)++]=(c); \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_FWD_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ ++(i); \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_FWD_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ (i)+=(n); \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_SET_CHAR_START_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_NEXT_CHAR_SAFE(s, i, length, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(s)[(i)++]; \ if(!UTF32_IS_SAFE(c, strict)) { \ (c)=UTF_ERROR_VALUE; \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_APPEND_CHAR_SAFE(s, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ if((uint32_t)(c)<=0x10ffff) { \ (s)[(i)++]=(c); \ } else /* c>0x10ffff, write 0xfffd */ { \ (s)[(i)++]=0xfffd; \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_FWD_1_SAFE(s, i, length) UPRV_BLOCK_MACRO_BEGIN { \ ++(i); \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_FWD_N_SAFE(s, i, length, n) UPRV_BLOCK_MACRO_BEGIN { \ if(((i)+=(n))>(length)) { \ (i)=(length); \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_SET_CHAR_START_SAFE(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \ } UPRV_BLOCK_MACRO_END /* definitions with backward iteration -------------------------------------- */ /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_PREV_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(s)[--(i)]; \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_BACK_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ --(i); \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_BACK_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ (i)-=(n); \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_SET_CHAR_LIMIT_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_PREV_CHAR_SAFE(s, start, i, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ (c)=(s)[--(i)]; \ if(!UTF32_IS_SAFE(c, strict)) { \ (c)=UTF_ERROR_VALUE; \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_BACK_1_SAFE(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \ --(i); \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_BACK_N_SAFE(s, start, i, n) UPRV_BLOCK_MACRO_BEGIN { \ (i)-=(n); \ if((i)<(start)) { \ (i)=(start); \ } \ } UPRV_BLOCK_MACRO_END /** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF32_SET_CHAR_LIMIT_SAFE(s, i, length) UPRV_BLOCK_MACRO_BEGIN { \ } UPRV_BLOCK_MACRO_END /* Formerly utf.h, part 2 --------------------------------------------------- */ /** * Estimate the number of code units for a string based on the number of UTF-16 code units. * * @deprecated ICU 2.4. Obsolete, see utf_old.h. */ #define UTF_ARRAY_SIZE(size) UTF16_ARRAY_SIZE(size) /** @deprecated ICU 2.4. Renamed to U16_GET_UNSAFE, see utf_old.h. */ #define UTF_GET_CHAR_UNSAFE(s, i, c) UTF16_GET_CHAR_UNSAFE(s, i, c) /** @deprecated ICU 2.4. Use U16_GET instead, see utf_old.h. */ #define UTF_GET_CHAR_SAFE(s, start, i, length, c, strict) UTF16_GET_CHAR_SAFE(s, start, i, length, c, strict) /** @deprecated ICU 2.4. Renamed to U16_NEXT_UNSAFE, see utf_old.h. */ #define UTF_NEXT_CHAR_UNSAFE(s, i, c) UTF16_NEXT_CHAR_UNSAFE(s, i, c) /** @deprecated ICU 2.4. Use U16_NEXT instead, see utf_old.h. */ #define UTF_NEXT_CHAR_SAFE(s, i, length, c, strict) UTF16_NEXT_CHAR_SAFE(s, i, length, c, strict) /** @deprecated ICU 2.4. Renamed to U16_APPEND_UNSAFE, see utf_old.h. */ #define UTF_APPEND_CHAR_UNSAFE(s, i, c) UTF16_APPEND_CHAR_UNSAFE(s, i, c) /** @deprecated ICU 2.4. Use U16_APPEND instead, see utf_old.h. */ #define UTF_APPEND_CHAR_SAFE(s, i, length, c) UTF16_APPEND_CHAR_SAFE(s, i, length, c) /** @deprecated ICU 2.4. Renamed to U16_FWD_1_UNSAFE, see utf_old.h. */ #define UTF_FWD_1_UNSAFE(s, i) UTF16_FWD_1_UNSAFE(s, i) /** @deprecated ICU 2.4. Renamed to U16_FWD_1, see utf_old.h. */ #define UTF_FWD_1_SAFE(s, i, length) UTF16_FWD_1_SAFE(s, i, length) /** @deprecated ICU 2.4. Renamed to U16_FWD_N_UNSAFE, see utf_old.h. */ #define UTF_FWD_N_UNSAFE(s, i, n) UTF16_FWD_N_UNSAFE(s, i, n) /** @deprecated ICU 2.4. Renamed to U16_FWD_N, see utf_old.h. */ #define UTF_FWD_N_SAFE(s, i, length, n) UTF16_FWD_N_SAFE(s, i, length, n) /** @deprecated ICU 2.4. Renamed to U16_SET_CP_START_UNSAFE, see utf_old.h. */ #define UTF_SET_CHAR_START_UNSAFE(s, i) UTF16_SET_CHAR_START_UNSAFE(s, i) /** @deprecated ICU 2.4. Renamed to U16_SET_CP_START, see utf_old.h. */ #define UTF_SET_CHAR_START_SAFE(s, start, i) UTF16_SET_CHAR_START_SAFE(s, start, i) /** @deprecated ICU 2.4. Renamed to U16_PREV_UNSAFE, see utf_old.h. */ #define UTF_PREV_CHAR_UNSAFE(s, i, c) UTF16_PREV_CHAR_UNSAFE(s, i, c) /** @deprecated ICU 2.4. Use U16_PREV instead, see utf_old.h. */ #define UTF_PREV_CHAR_SAFE(s, start, i, c, strict) UTF16_PREV_CHAR_SAFE(s, start, i, c, strict) /** @deprecated ICU 2.4. Renamed to U16_BACK_1_UNSAFE, see utf_old.h. */ #define UTF_BACK_1_UNSAFE(s, i) UTF16_BACK_1_UNSAFE(s, i) /** @deprecated ICU 2.4. Renamed to U16_BACK_1, see utf_old.h. */ #define UTF_BACK_1_SAFE(s, start, i) UTF16_BACK_1_SAFE(s, start, i) /** @deprecated ICU 2.4. Renamed to U16_BACK_N_UNSAFE, see utf_old.h. */ #define UTF_BACK_N_UNSAFE(s, i, n) UTF16_BACK_N_UNSAFE(s, i, n) /** @deprecated ICU 2.4. Renamed to U16_BACK_N, see utf_old.h. */ #define UTF_BACK_N_SAFE(s, start, i, n) UTF16_BACK_N_SAFE(s, start, i, n) /** @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT_UNSAFE, see utf_old.h. */ #define UTF_SET_CHAR_LIMIT_UNSAFE(s, i) UTF16_SET_CHAR_LIMIT_UNSAFE(s, i) /** @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT, see utf_old.h. */ #define UTF_SET_CHAR_LIMIT_SAFE(s, start, i, length) UTF16_SET_CHAR_LIMIT_SAFE(s, start, i, length) /* Define default macros (UTF-16 "safe") ------------------------------------ */ /** * Does this code unit alone encode a code point (BMP, not a surrogate)? * Same as UTF16_IS_SINGLE. * @deprecated ICU 2.4. Renamed to U_IS_SINGLE and U16_IS_SINGLE, see utf_old.h. */ #define UTF_IS_SINGLE(uchar) U16_IS_SINGLE(uchar) /** * Is this code unit the first one of several (a lead surrogate)? * Same as UTF16_IS_LEAD. * @deprecated ICU 2.4. Renamed to U_IS_LEAD and U16_IS_LEAD, see utf_old.h. */ #define UTF_IS_LEAD(uchar) U16_IS_LEAD(uchar) /** * Is this code unit one of several but not the first one (a trail surrogate)? * Same as UTF16_IS_TRAIL. * @deprecated ICU 2.4. Renamed to U_IS_TRAIL and U16_IS_TRAIL, see utf_old.h. */ #define UTF_IS_TRAIL(uchar) U16_IS_TRAIL(uchar) /** * Does this code point require multiple code units (is it a supplementary code point)? * Same as UTF16_NEED_MULTIPLE_UCHAR. * @deprecated ICU 2.4. Use U16_LENGTH or test ((uint32_t)(c)>0xffff) instead. */ #define UTF_NEED_MULTIPLE_UCHAR(c) UTF16_NEED_MULTIPLE_UCHAR(c) /** * How many code units are used to encode this code point (1 or 2)? * Same as UTF16_CHAR_LENGTH. * @deprecated ICU 2.4. Renamed to U16_LENGTH, see utf_old.h. */ #define UTF_CHAR_LENGTH(c) U16_LENGTH(c) /** * How many code units are used at most for any Unicode code point (2)? * Same as UTF16_MAX_CHAR_LENGTH. * @deprecated ICU 2.4. Renamed to U16_MAX_LENGTH, see utf_old.h. */ #define UTF_MAX_CHAR_LENGTH U16_MAX_LENGTH /** * Set c to the code point that contains the code unit i. * i could point to the lead or the trail surrogate for the code point. * i is not modified. * Same as UTF16_GET_CHAR. * \pre 0<=i<length * * @deprecated ICU 2.4. Renamed to U16_GET, see utf_old.h. */ #define UTF_GET_CHAR(s, start, i, length, c) U16_GET(s, start, i, length, c) /** * Set c to the code point that starts at code unit i * and advance i to beyond the code units of this code point (post-increment). * i must point to the first code unit of a code point. * Otherwise c is set to the trail unit (surrogate) itself. * Same as UTF16_NEXT_CHAR. * \pre 0<=i<length * \post 0<i<=length * * @deprecated ICU 2.4. Renamed to U16_NEXT, see utf_old.h. */ #define UTF_NEXT_CHAR(s, i, length, c) U16_NEXT(s, i, length, c) /** * Append the code units of code point c to the string at index i * and advance i to beyond the new code units (post-increment). * The code units beginning at index i will be overwritten. * Same as UTF16_APPEND_CHAR. * \pre 0<=c<=0x10ffff * \pre 0<=i<length * \post 0<i<=length * * @deprecated ICU 2.4. Use U16_APPEND instead, see utf_old.h. */ #define UTF_APPEND_CHAR(s, i, length, c) UTF16_APPEND_CHAR_SAFE(s, i, length, c) /** * Advance i to beyond the code units of the code point that begins at i. * I.e., advance i by one code point. * Same as UTF16_FWD_1. * \pre 0<=i<length * \post 0<i<=length * * @deprecated ICU 2.4. Renamed to U16_FWD_1, see utf_old.h. */ #define UTF_FWD_1(s, i, length) U16_FWD_1(s, i, length) /** * Advance i to beyond the code units of the n code points where the first one begins at i. * I.e., advance i by n code points. * Same as UT16_FWD_N. * \pre 0<=i<length * \post 0<i<=length * * @deprecated ICU 2.4. Renamed to U16_FWD_N, see utf_old.h. */ #define UTF_FWD_N(s, i, length, n) U16_FWD_N(s, i, length, n) /** * Take the random-access index i and adjust it so that it points to the beginning * of a code point. * The input index points to any code unit of a code point and is moved to point to * the first code unit of the same code point. i is never incremented. * In other words, if i points to a trail surrogate that is preceded by a matching * lead surrogate, then i is decremented. Otherwise it is not modified. * This can be used to start an iteration with UTF_NEXT_CHAR() from a random index. * Same as UTF16_SET_CHAR_START. * \pre start<=i<length * \post start<=i<length * * @deprecated ICU 2.4. Renamed to U16_SET_CP_START, see utf_old.h. */ #define UTF_SET_CHAR_START(s, start, i) U16_SET_CP_START(s, start, i) /** * Set c to the code point that has code units before i * and move i backward (towards the beginning of the string) * to the first code unit of this code point (pre-increment). * i must point to the first code unit after the last unit of a code point (i==length is allowed). * Same as UTF16_PREV_CHAR. * \pre start<i<=length * \post start<=i<length * * @deprecated ICU 2.4. Renamed to U16_PREV, see utf_old.h. */ #define UTF_PREV_CHAR(s, start, i, c) U16_PREV(s, start, i, c) /** * Move i backward (towards the beginning of the string) * to the first code unit of the code point that has code units before i. * I.e., move i backward by one code point. * i must point to the first code unit after the last unit of a code point (i==length is allowed). * Same as UTF16_BACK_1. * \pre start<i<=length * \post start<=i<length * * @deprecated ICU 2.4. Renamed to U16_BACK_1, see utf_old.h. */ #define UTF_BACK_1(s, start, i) U16_BACK_1(s, start, i) /** * Move i backward (towards the beginning of the string) * to the first code unit of the n code points that have code units before i. * I.e., move i backward by n code points. * i must point to the first code unit after the last unit of a code point (i==length is allowed). * Same as UTF16_BACK_N. * \pre start<i<=length * \post start<=i<length * * @deprecated ICU 2.4. Renamed to U16_BACK_N, see utf_old.h. */ #define UTF_BACK_N(s, start, i, n) U16_BACK_N(s, start, i, n) /** * Take the random-access index i and adjust it so that it points beyond * a code point. The input index points beyond any code unit * of a code point and is moved to point beyond the last code unit of the same * code point. i is never decremented. * In other words, if i points to a trail surrogate that is preceded by a matching * lead surrogate, then i is incremented. Otherwise it is not modified. * This can be used to start an iteration with UTF_PREV_CHAR() from a random index. * Same as UTF16_SET_CHAR_LIMIT. * \pre start<i<=length * \post start<i<=length * * @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT, see utf_old.h. */ #define UTF_SET_CHAR_LIMIT(s, start, i, length) U16_SET_CP_LIMIT(s, start, i, length) #endif // !U_HIDE_DEPRECATED_API && !U_HIDE_OBSOLETE_UTF_OLD_H #endif