From d54e1248a8036e9ee3bcd6508fa396cd3421bc3e Mon Sep 17 00:00:00 2001 From: "Libor M." Date: Tue, 17 Dec 2024 16:55:46 +0100 Subject: [PATCH] Upgrade to Unicode 15 --- src/classes.trie | Bin 3870 -> 3977 bytes src/generate_data.js | 2 +- test/LineBreakTest.txt | 10 +++++----- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/src/classes.trie b/src/classes.trie index 01564d74b5b8b156d1638d2782c2607cc65c2caf..34190caba744657da4895d6457b922fc031cc37e 100644 GIT binary patch literal 3977 zcmV;44|ebX2o3-M0000$<^TWzcn^p0?VWp!T}2(o=d!zZ_ujp`?cK7aQkK##6<9zl zXn+s`4Kb9UfdYnC6vQZx;vbbFV#6OuFc6gR5C|ACfHY7+rCRU>Dx^x#CT*k&A}XXH zA{8YR4D#?hoEh)zbe?A(=a$}0KACgQJbu6V&2JuO&N+AQ>?7n}uogTBo&#IJR`3?+ z>nCKm-#;7!yMhH^3LF3qcF1=GINA{ZG4OHl3Gf-P3|s&%2A2xyz5=cWH-K+~JHU6q zYOn_U1Uw8L0~^66miK8EJ_ojdSHWxGZBQQ|WE9KG3E$4uGhl3f1gCiJXS`$Yj?Qv52b0P0! zk1||1Ln!ZT94`YGfR*5~dZ)fu;rM#+4N3kTIKN3azZ2*8g0(_k%1>FoM}+IY!SV0F zQ}x2{DYShj5I#%OfmgsAEN^YF2!{~P1iK7&o4K>Rf(;_ z@mruaL`Va)!5pv$*c*Hh90HC6OTh8q6mTXuXQ(Lue1t2&m)QBG2(K9Ox7jr;&rJw# z^~k@fgsgj|JZpvXJDHC?h->S>`k|sfZyIvv_u$XqdGJs08h9Jj8^!Tx!<>J%5Wl-6 zZI2#3;=#v(s`cp6qeqV(J$m%$v3;?iOYhtEX-wY_(eZ&sv6n}W55n<1Lfl~ud;X)4 z=2({Q1cZzGi~X9@aC{ak`#glp!NrYYKkg#Be}LmFS-xu#-rShJKSa3=*H#&1-;MbD zz#8xa@I$Z`+z%e;#r5KPalN=+T=ckyz&h|Kcz4gVLN+w2rRw_k=+V^#u4A7-ANwoV z+$jH??gdTWf8qLn0BI632xc^=$Irs~Trdgt1qXpcnuT6RB3#m}e*D>aM#0y?OVY^W1+t=A%=Z`uNkD+pbx7+*yb_Ps;l_oL|VUov3;DioTb1edPDDOkAX?-zA26 zQ!c0L8u~7mBHeZD+AWqcY}~G}uL_=iHB0|JLGAkxm-@bo;l<9sz( z1MUY8u`<>nT+fa-B79OKSFX=9NcRHR0$x$bdV`g@Q>#-q8%?AgYZZIRyS6&l=i_)G z*uRypf4T7CF4Lz94rey_h`|<1G;zn_`pGRf-$+T>x}OoT{pq`jXSX`XbS^ocov%Q+ zGLx@;StIAlR`KrS)k1sS*b2Ybw^6npw=z9fb%B3X$!fl)evJbsc^C z_qtZ+UGp84^`7I&<4FG}>K}@=;pXjZ9{fA>-4a1(YR9e2m)@l1jbIHkQoX;6eowy< z(8W`|$3}{DyCB?cWZV3E;@W;A?lxJ((jFRM2fE%{oY;;!{f`-$9=|k0d!EW{_DK&r zo0#pQvt?ZWEXr6mQhZ0UoP}Q)DdH{}vFDe$9C^M5ZU8q6`ESGVUEurRN5b`A;P}^I zJ=g&Lz~Y`pxLHW|4;;VD&R<9P4m%d@F(~X8oWSzUVAsZ3IDzoDLb(fYJ~dh#AIQQ( z5FRl)z5Kz^>GeDs=f@iMCun~>an#>_?{DW%F-zVY;rIDz>(*+V4_AZ9&I; zK4y)z2 zbz-l(%|3FxDlJdrYLD3M`d;uUd3=2@;bVsuDStmzh5x0riJXUy&Ad;G_mJX!TMk`y z`pegK>2msd4!J(}_onuZ(SOR2Lqh_6&sa;5q z&ov+A>i=bYTK2gr`n^uiSavtrz&1{#x)0#vu5QdDevDRj7hwHiL zMAtEj_m9xAUGy#8+JZly4jC79`iAyFSNXd9@2i+yD`sxRq*_av#tnI$Wa>w$sZw@s z`ShEE{WkMNAfpGF8Rye--zQ&!$8v#@0+)&I1Z7~@Mx!yIn#AM<^C?WVUxJE ziF0d~_;X7nNS}HB~$hafPmG5e^P}_y-<;#o+I?zAyxocTnM;SgcQ`mG= zBBZR4c~yt+{E?DY$vm=Oq|nQ!55ODoqTXbJ^ck@7%~fZ$s{zDxaRONw4Y;a-7)j zbaqndp(;nE&xAp)3YD!UBy#zPc;2Uh#_{KTvi|h1Rw7I>50~|Ku2arF;%cWVWcr3x z+AXK-T)q;^uVqa8sPZ#?c@MWv+@7!4aD5L*_iRQtM%gg!`-}V3M5?Da28!qO&(tU6 z^7%U}s(o>lon|p~d+9_WLsuuAEIy{Y)P=W!@7x|6*(dn#GuDJO1H!SbZbZs!OE(}K zi}`Hm_QG{(RoD5m8QC6_?AR8jCYKzWe3yFL;wH(q&x8jgc$;*a{bSW%<$sez?T4a2 z`Y;)Y%_g?>Vv2Uq*~W(N^RJLOIM#fwTVMFTKM`98an2KQwXdv`?|U67?5Wei$3I-3 zjh2Off5X=nE^E3n&xk|bZ*r0Ei;sO={KqCQ#dia#pXE~-ReX~qx3{kTF7ITP^*5fs z%J0Km=Z}={b@+~-a@oH2cWqZ!JE+PDslTm{ht^+a7ceIyx#jt;KVyD-D3@Ku_lL3$ zdsj@#wMI+Rru4UU$BEzX@OIm8{D#8!EON`0*O#H|sv*+ZYvI3jEbm*<_exT&?^O3` zT&`;<=QG^{)`XDi&+oOx=Px!nHu!s>s(a2Ve3i?d%|c#JSyz<}Yf|WQk1pS**FDP! zg_P7im3(g7nsm(V6l+f=2c|u$)QJ6w`ffvt=kI#j`kU(-MjWs9AjQ5`75&+CpRU?_ zscLQ%*VC!$?bCKu*+I66%l%wc`f*>XLhh6#KgT{%S$}hRCg|!5E^V)qV_K8t@F!QB z*!qD@|Iqt!pZbXV0&@P4F(?!l|IXb!VsUS`2BAgAC=#yQTZ7^_W53ZOe()jU-xZG-TOy!zpiR7 zajCQEId0DJC3pXgJqD@#H)M>M63W)~E!R4S>SJrCGV`%+ToC(_?>NcpuWJWYyQQ2z zs7(I*nfyHw`8QZ?_ZVf?+oF6qtxx-f)?fbZS{HJUe<6LuX46png%bKZV6OVhzmL~0 zAu9!`=YP}Kl6t<>t((MheBRZH;jdNOfY*OaC@Y7biS^IvFJK9|7rqqI{6w;Pc-RM z>#Wn$mwp3Wj_Mi@O=C#vxg^9tVzpb@@hJAQ9@G5l)8|6<@LA)k;Bm3nXF0}_&^A@g z)uH_;#=VV*{7t0p|LWM*AKf+|yUO={A1pSZb&REF=y#m4h|yjqQjZy?F;w;J(RYrF zsgG{#NIgEq9>aX=oU`qH=e5+NYFm|EQ_W*OZ78NyJC ziR;POzk3(EyjB8zQ+#u?TP9SpCp6b%plXAhGIZC)->OvEK^32y-4)3Csr0oGLpL9J zKKiKilheA^Wx`OVk8i0$oh)76vVFibc89j1>l~4?>{NBL`K?R)l`Y>@W(;!Mv5Xv3 zU(fZs!QyXen*L8zY@hHQcYS5X_N&--Pc1*T{;~8+)n7yFr(5s1_^;1e!pGlz)(AP* jWvOJS)-oaTOzWeNHDMKN;L!DJ=)HO9{zxu6xz_uCdfrxJ literal 3870 zcmV+(58?0t2o3-M0000G;Q#;u4G;40?VSsZT}2tk=d!!Ed+*-e_HJ7qg{8EmRF=rg zSWOiq*q}m#6{|te}V&QY(CGZ;f8~8Wq>my_kOa_O5nP46`7Muv)4Nha}9|Vh8I*p$P z&IilD#o%&qHMo|gUk_G;wJd%o*wk0Z-->Vtc#zdk^?MlMqu_Dy8?YDb=_%qbg1@l% z-x2#IVFT!K$MPAPF^>OAi-V07;hcg zg-;9hU4-LHz!hL6SXCcy?~ORV1>7#lUyt}2AwGuq7O-6?OSzYo+bNvih2!1e$$H`U z6xzQ>AlysyfmgvBtSp&Sgp&|X1_w_XmwP0RkDjD&C$B%oR>z_KcYybR_k***x!{xF z0EKLo4){br^9zI*fiJN5l?Ye%``c_4D{}+F)gI;72FSWY zDzj0Dk1-$nG0xos9_TN|^TYk_{2V+6o&e8)7r-lEA3G)ubNPNDeTpS-mo8n>!RLXh z_2|;2OP4NPx^(IC=3-ihUbh|In0P-#$5D;qULHN3i{rb5w6{0x<==@sr?7kr5uVmt z+^<=L<0Y)_r3fzopKlcRtuurn$^!gQzjRz29JUMDS8%y>%b00+CC|M zVw;f5z$WlayEr#(n2^QbdN2l_1AC#vOxWRka0hrA^b8Pk(m?Ti_S}IYF0u;TS{r94 z%ggyQ;>WcJISX6{t^(V@tKg(ToC90ID}xj3InbCgG|_Hdx^(GsAhCGJy!M}t_2|r| zK7CPh|2+#&TY|KuQdzprEo0}-(Y$*_-^;os@q1Y&F4nYfxuM;Z6?8uXU9VB(yN;c^ z$x?@n+Z6Uy!Sk`s9C%Vb~ujj#_|0u{t&`Pz^_>Rw+Md^o@a4-@A2j4 z_sic-O#qoaTQY;vZmj zd>G+*ES=s1Js-!*4D~G^P}`l~)4dAmUm2KK<{OCL4Ay|#!FpE5W`x@`^=W;G%0ih3 z!9!q|Le_3p=aWL)Y&>hw;{~L>;;CnD_H~#(RX|!r*x%CU8PKE+x2nHZ4Q=-fLwkLp z?WFCv3fN*|7Std@=$XVDb-kbc8&|e>E<$s+iVe_rV*;K3{~kH> zrMnT{4}R7`^UYY@oKE%rr9ofX#yv=X%EMNBS>6{r$PO-Z0_WA%#Pl~xXh&_ZkX0W{ zg*e=+0AuD$uJGYaCyAXa!sP|DEKhEM$v+xfH zUy|zIF4^LB#P=Eck$$g3hRT00sFUbN`xp0yuU(xq$A&VU*lB~gU^e4uhcd1l3$Q$p zp5pS2ezHWG?3kXTe+LO^=r%Hih17)y9O-AY1nN>eH-xp}pb}-u@@ZezSbRF^{*4~s zsK(?mn)5m6W&J?Md_#cx=PU+4=5s`wjQcb%$MX(LWkq_VI3an*+pNs>ce?yegZqc* z13d0(GufxaGQ*a#Wl+|*eKXJ-SVl*P4x#-h?^SGlTeaWigxZ46`Fzdd=Nm-7hIKk^ zq2Hz}j_WM6t>1$kL}>pu1>}9Yk4@`B$f??QbI;AL*FR0+Sk@_Lo9o2hcAI_VbX8uS z$JHLG`}M8hQ}X=!R>H>)EfRh`RfYfMw254X&dq#Gi`S6ibz2#_>hzb->++T9>t)FG zxxP2`Z;J5~LK!k*+Mm-WQnuYzm#=owqgD4$3QYZC(;;RbpcvPjE4rX_kUUIQCZ_Z#HVGS zt76>i^h{-UlMQV1M6T-qJ`cO@@7@gK-?dM2kAG7iy57$hbuRlEK$&xqX-29q(d4`1;(u4nfwd5m{f$!;bvAu+weh>lZ4U z3`>aTdWGXQi`NzOvU2h>3EO;-`np?w?!-g-R};dRy+o?LS=-@!*=wTf9L2{+?A$K; zmTqsspHIiki#mN{$DylyUHQW*W=6#vUNO1$Ql@!B-Y1#HQEsY~UABDsS0fYW4_{qv z^Ij;f`@me+2J-r&+WX|x!KdA+<&Q?lPra|>w(k?--1o%&Z>swMsrrxa1G)ag(s|j( z`1@u#^pDxwr6lKdqU-fzON#UUh~2luUd#FVuj!gD7bg4iJXK!%`HY`fQqO;}*G}>t z$~F#Tt{2)QZ0%2>yC`3^cdUY#K1y}HpK5-zttUC>XW6fO-b2voocexBE?mcwt-oX+ zOEG_##@2M{xazS;;d?EePjPys_%x>bOrafezNuv5w;(-a{JX^-MO@5FnJhr-L9ev`k7eydv_4px-)S?6TGclpMNw@>_DNB)M#rF`i1 zfH)o-2AY<1-?B}`ag2bGvQ^))slJ0W zp_AuZ&ebk*|K^bAqf=;GRC>whROvjFzk9Xyt;!a18%(w{`H+i0g!HvdZi?|>vW+R8 z!hcfL?`pGH+r{eT%j5()&_D4xWvH%03?G>}Y&s+nQ&-Hos>65v$Vn@(jO-UV^zs=) zDP)D};A%^sdQ@@O^Ku=r?Q^xeYndG5+thBG-FQ7beMli^gru2ILfWXaVG3Ku^t;OE zxcyXlQs`Wk{cY_o8`xsK0Za${ZuEcB(?AZ&;<>%9LG}ucY#88Pk1K`5Cx;54TR- zo=4bleQ!qhEJHU(*)ZMr7w=OOsh#2+D8}iZX-vrV^LIQ{_r+Cqn#$1KOD75$x;E)# z@j2b4ExZqW*Y?!NKEZ#_uqNc`6OL_dBT`vgzCPhtEN4S^FI<;bb)G+)k?k>u9oxd( zlqJU|-=*EQv^iw|XQ+J=yiYpK{;Arp^1nGm?T4a2`YS_m7Ju&UKjq%v_%Nzm@Es?V2`R+eceybX#{5??BHD?vR%4HwSLf%eUSCtKGQs{GyE?=kDJ?n^t1nQnkKDTX6I_7ptbx)=Y zO!ugABaSEPyA3Iwzw2omZ?1b7alSf=6!*2N7|*8bbk)6=s@6tvKb@=HK7Ch}9b}uh zT+dadANQpy=6%eYSz>TfR31YLc>rSEleOnb62{K?fOwsBz7KlXaur#<3*fzNd3iTs-T)N&*%Q1&kHQqzl6d%1*^IuhCkjoUm z&kgZW`F$6apYda#@4tto`a{OLZ(r)(590moBGdGov&`{b<$9T74p8||%orUN>el(T zYnx;B@!8|Ju7|pDDf+SRJjL6u>jzc8<($8%O#XX}{5=Z!H$828@R0qeC|}O&(|@t; zmwyY@1t0xVuJs{f!DiD~`^6IbyHc+D%fGkQ4v>|D-0QDtZppn~>h>*SJwER;rSR9P zZNS?qG3lKVC=ZT#>qeRfvBz z0Xd(1j^`(u{JC}3>FL`)rvC@e<>cs}RCWuUzf#}ZHqFOAJ|C-x&z?dBPfNX?mob)O z`&6~I+H4v_h>r3%TDt#>VcRc+tOq&!&{e+g`zfi3ZDUz_>WKXwEk*yB$UR4x=1kSI z72o}MN_}*5Meg}1^_=C~<}&-mu5!$yvY%C9PuXTM_gj2^!`D@x*!9ikA9DH7_Vd50#ssHniKim8Z6UuYCGNjc z|4vov`dS(E&GC->5hbCLJ)$|E0#zTBDMNQ&{B1dv9aQOMbEE=UKb5{VQt0L*&qp7X zesW&dwu~6+^zkiKsFS5D8#)F|bAD_ex~?rb>(13So8P+hUugZVGE-2t9Yf@p#(G)5 z^C|xJo$3F&r1lBldDmBFYQIWt_uTSR>z_)$T;nyieY*XQi~suUC4BtdXOB?kzATpv g)m|n>o@sv+vnQ-#4;;I1jlI^7eZQqFJGr*|e{?M%{{R30 diff --git a/src/generate_data.js b/src/generate_data.js index 16f88cc..fe90760 100644 --- a/src/generate_data.js +++ b/src/generate_data.js @@ -5,7 +5,7 @@ import UnicodeTrieBuilder from 'unicode-trie/builder.js'; // this loads the LineBreak.txt file for Unicode and parses it to // combine ranges and generate JavaScript -request('http://www.unicode.org/Public/14.0.0/ucd/LineBreak.txt', function (err, res, data) { +request('https://www.unicode.org/Public/15.0.0/ucd/LineBreak.txt', function (err, res, data) { const matches = data.match(/^[0-9A-F]+(\.\.[0-9A-F]+)?;[A-Z][A-Z0-9]([A-Z])?/gm); let start = null; diff --git a/test/LineBreakTest.txt b/test/LineBreakTest.txt index 8d1cef0..3122a2e 100644 --- a/test/LineBreakTest.txt +++ b/test/LineBreakTest.txt @@ -1,11 +1,11 @@ -# LineBreakTest-14.0.0.txt -# Date: 2021-08-20, 21:08:45 GMT -# © 2021 Unicode®, Inc. +# LineBreakTest-15.0.0.txt +# Date: 2022-02-26, 00:38:39 GMT +# © 2022 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. -# For terms of use, see http://www.unicode.org/terms_of_use.html +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # # Default Line_Break Test #