tor-browser

The Tor Browser
git clone https://git.dasho.dev/tor-browser.git
Log | Files | Refs | README | LICENSE

InterIndic_Latin.txt (11809B)


      1 # © 2016 and later: Unicode, Inc. and others.
      2 # License & terms of use: http://www.unicode.org/copyright.html
      3 # Generated using tools/cldr/cldr-to-icu/
      4 #
      5 # File: InterIndic_Latin.txt
      6 # Generated from CLDR
      7 #
      8 
      9 # InterIndic-Latin
     10 #\u0E00 reserved
     11 #consonants
     12 $chandrabindu=\uE001;
     13 $anusvara=\uE002;
     14 $visarga=\uE003;
     15 #\u0E004 reserved
     16 # w←vowel→ represents the stand-alone form
     17 $wa=\uE005;
     18 $waa=\uE006;
     19 $wi=\uE007;
     20 $wii=\uE008;
     21 $wu=\uE009;
     22 $wuu=\uE00A;
     23 $wr=\uE00B;
     24 $wl=\uE00C;
     25 $wce=\uE00D; # LETTER CANDRA E
     26 $wse=\uE00E; # LETTER SHORT E
     27 $we=\uE00F;  # ए LETTER E
     28 $wai=\uE010;
     29 $wco=\uE011; # LETTER CANDRA O
     30 $wso=\uE012; # LETTER SHORT O
     31 $wo=\uE013;  # ओ LETTER O
     32 $wau=\uE014;
     33 $ka=\uE015;
     34 $kha=\uE016;
     35 $ga=\uE017;
     36 $gha=\uE018;
     37 $nga=\uE019;
     38 $ca=\uE01A;
     39 $cha=\uE01B;
     40 $ja=\uE01C;
     41 $jha=\uE01D;
     42 $nya=\uE01E;
     43 $tta=\uE01F;
     44 $ttha=\uE020;
     45 $dda=\uE021;
     46 $ddha=\uE022;
     47 $nna=\uE023;
     48 $ta=\uE024;
     49 $tha=\uE025;
     50 $da=\uE026;
     51 $dha=\uE027;
     52 $na=\uE028;
     53 $ena=\uE029; #compatibility
     54 $pa=\uE02A;
     55 $pha=\uE02B;
     56 $ba=\uE02C;
     57 $bha=\uE02D;
     58 $ma=\uE02E;
     59 $ya=\uE02F;
     60 $ra=\uE030;
     61 $vva=\uE081;
     62 $rra=\uE031;
     63 $la=\uE032;
     64 $lla=\uE033;
     65 $ela=\uE034; #compatibility
     66 $va=\uE035;
     67 $sha=\uE036;
     68 $ssa=\uE037;
     69 $sa=\uE038;
     70 $ha=\uE039;
     71 #\u093A Reserved
     72 #\u093B Reserved
     73 $nukta=\uE03C;
     74 $avagraha=\uE03D; # SIGN AVAGRAHA
     75 # ←vowel→ represents the dependent form
     76 $aa=\uE03E;
     77 $i=\uE03F;
     78 $ii=\uE040;
     79 $u=\uE041;
     80 $uu=\uE042;
     81 $rh=\uE043;
     82 $rrh=\uE044;
     83 $ce=\uE045; #VOWEL SIGN CANDRA E
     84 $se=\uE046; #VOWEL SIGN SHORT E
     85 $e=\uE047;
     86 $ai=\uE048;
     87 $co=\uE049; # VOWEL SIGN CANDRA O
     88 $so=\uE04A; # VOWEL SIGN SHORT O
     89 $o=\uE04B;  # ो
     90 $au=\uE04C;
     91 $virama=\uE04D;
     92 # \u094E Reserved
     93 # \u094F Reserved
     94 $om=\uE050; # OM
     95 \uE051→;        # UNMAPPED STRESS SIGN UDATTA
     96 \uE052→;        # UNMAPPED STRESS SIGN ANUDATTA
     97 \uE053→;        # UNMAPPED GRAVE ACCENT
     98 \uE054→;        # UNMAPPED ACUTE ACCENT
     99 $lm = \uE055;#  Telugu Length Mark
    100 $ailm=\uE056;#  AI Length Mark
    101 $aulm=\uE057;#  AU Length Mark
    102 #urdu compatibility forms
    103 $uka=\uE058;
    104 $ukha=\uE059;
    105 $ugha=\uE05A;
    106 $ujha=\uE05B;
    107 $uddha=\uE05C;
    108 $udha=\uE05D;
    109 $ufa=\uE05E;
    110 $uya=\uE05F;
    111 $wrr=\uE060;
    112 $wll=\uE061;
    113 $lh=\uE062;
    114 $llh=\uE063;
    115 $danda=\uE064;
    116 $doubleDanda=\uE065;
    117 $zero=\uE066;     # DIGIT ZERO
    118 $one=\uE067;      # DIGIT ONE
    119 $two=\uE068;      # DIGIT TWO
    120 $three=\uE069;    # DIGIT THREE
    121 $four=\uE06A;     # DIGIT FOUR
    122 $five=\uE06B;     # DIGIT FIVE
    123 $six=\uE06C;      # DIGIT SIX
    124 $seven=\uE06D;    # DIGIT SEVEN
    125 $eight=\uE06E;    # DIGIT EIGHT
    126 $nine=\uE06F;     # DIGIT NINE
    127 # Glottal stop
    128 $dgs=\uE082;
    129 #Khanda-ta
    130 $kta=\uE083;
    131 $depVowelAbove=[\uE03E-\uE040\uE045-\uE04C];
    132 $depVowelBelow=[\uE041-\uE044];
    133 # $x was originally called '§'; $z was '%'
    134 $x=[$aa$ai$au$ii$i$uu$u$rrh$rh$lh$llh$e$o$se$ce$so$co];
    135 $z=[bcdfghjklmnpqrstvwxyz];
    136 $vowels=[aeiour\u0304\u0325\u0306];
    137 $forceIndependentMatra = [^[[:L:][\u0300-\u034C]]];
    138 ######################################################################
    139 # convert from Native letters to Latin letters
    140 ######################################################################
    141 #transliterations for anusvara
    142 $anusvara} [$ka$kha$ga$gha$nga]             → n\u0307;
    143 $anusvara} [$ca$cha$ja$jha$nya]             → n\u0304;
    144 $anusvara} [$tta$ttha$dda$ddha$nna]         → n\u0323;
    145 $anusvara} [$ta$tha$da$dha$na]              → n;
    146 $anusvara} [$pa$pha$ba$bha$ma]              → m;
    147 $anusvara} [$ya$ra$lla$la$va$ssa$sha$sa$ha] → n;
    148 $anusvara→ m\u0307;
    149 # Urdu compatibility
    150 $ya$nukta}$x        → y\u0307;
    151 $ya$nukta$virama    → y\u0307;
    152 $ya$nukta           → y\u0307a;
    153 $la$nukta }$x       → l\u0331;
    154 $la$nukta$virama    → l\u0331;
    155 $la$nukta           → l\u0331a;
    156 $na$nukta }$x       → n\u0331;
    157 $na$nukta$virama    → n\u0331;
    158 $na$nukta           → n\u0331a;
    159 $ena }$x            → n\u0331;
    160 $ena$virama         → n\u0331;
    161 $ena                → n\u0331a;
    162 $uka                → qa;
    163 $ka$nukta }$x       → q;
    164 $ka$nukta$virama    → q;
    165 $ka$nukta           → qa;
    166 $kha$nukta }$x      → k\u0331h\u0331;
    167 $kha$nukta$virama   → k\u0331h\u0331;
    168 $kha$nukta          → k\u0331h\u0331a;
    169 $ukha$virama        → k\u0331h\u0331;
    170 $ukha               → k\u0331h\u0331a;
    171 $ugha               → g\u0307a;
    172 $ga$nukta }$x       → g\u0307;
    173 $ga$nukta$virama    → g\u0307;
    174 $ga$nukta           → g\u0307a;
    175 $ujha               → za;
    176 $ja$nukta }$x       → z;
    177 $ja$nukta$virama    → z;
    178 $ja$nukta           → za;
    179 $ddha$nukta}$x      → r\u0323h;
    180 $ddha$nukta$virama  → r\u0323h;
    181 $ddha$nukta         → r\u0323ha;
    182 $uddha}$x           → r\u0323;
    183 $uddha$virama       → r\u0323;
    184 $uddha              → r\u0323a;
    185 $udha               → r\u0323a;
    186 $dda$nukta}$x       → r\u0323;
    187 $dda$nukta$virama   → r\u0323;
    188 $dda$nukta          → r\u0323a;
    189 $pha$nukta }$x      → f;
    190 $pha$nukta$virama   → f;
    191 $pha$nukta          → fa;
    192 $ufa }$x            → f;
    193 $ufa$virama         → f;
    194 $ufa                → fa;
    195 $ra$nukta}$x        → r\u0331;
    196 $ra$nukta$virama    → r\u0331;
    197 $ra$nukta           → r\u0331a;
    198 $lla$nukta}$x       → l\u0331;
    199 $lla$nukta$virama   → l\u0331;
    200 $lla$nukta          → l\u0331a;
    201 $ela}$x             → l\u0331;
    202 $ela$virama         → l\u0331;
    203 $ela                → l\u0331a;
    204 $uya}$x             → y\u0307;
    205 $uya$virama         → y\u0307;
    206 $uya                → y\u0307a;
    207 # normal consonants
    208 $ka$virama}$ha→k'';
    209 $ka}$x→k;
    210 $ka$virama→k;
    211 $ka→ka;
    212 $kha}$x→kh;
    213 $kha$virama→kh;
    214 $kha→kha;
    215 $ga$virama}$ha→g'';
    216 $ga}$x→g;
    217 $ga$virama→g;
    218 $ga→ga;
    219 $gha}$x→gh;
    220 $gha$virama→gh;
    221 $gha→gha;
    222 $nga}$x→n\u0307;
    223 $nga$virama→n\u0307;
    224 $nga→n\u0307a;
    225 $ca$virama}$ha→c'';
    226 $ca}$x→c;
    227 $ca$virama→c;
    228 $ca→ca;
    229 $cha}$x→ch;
    230 $cha$virama→ch;
    231 $cha→cha;
    232 $ja$virama}$ha→j'';
    233 $ja}$x→j;
    234 $ja$virama→j;
    235 $ja→ja;
    236 $jha}$x→jh;
    237 $jha$virama→jh;
    238 $jha→jha;
    239 $nya }$x→n\u0303;
    240 $nya$virama→n\u0303;
    241 $nya → n\u0303a;
    242 $tta$virama}$ha→t\u0323'';
    243 $tta}$x→t\u0323;
    244 $tta$virama→t\u0323;
    245 $tta→t\u0323a;
    246 $ttha}$x→t\u0323h;
    247 $ttha$virama→t\u0323h;
    248 $ttha→t\u0323ha;
    249 $dda}$x$ha→d\u0323'';
    250 $dda}$x→d\u0323;
    251 $dda$virama→d\u0323;
    252 $dda→d\u0323a;
    253 $ddha}$x→d\u0323h;
    254 $ddha$virama→d\u0323h;
    255 $ddha→d\u0323ha;
    256 $nna}$x→n\u0323;
    257 $nna$virama→n\u0323;
    258 $nna→n\u0323a;
    259 $ta$virama}$ha→t'';
    260 $ta$virama}$ttha→t'';
    261 $ta$virama}$tta→t'';
    262 $ta$virama}$tha→t'';
    263 $ta}$x→t;
    264 $ta$virama→t;
    265 $ta→ta;
    266 $tha}$x→th;
    267 $tha$virama→th;
    268 $tha→tha;
    269 $da$virama}$ha→d'';
    270 $da$virama}$ddha→d'';
    271 $da$virama}$dda→d'';
    272 $da$virama}$dha→d'';
    273 $da}$x→d;
    274 $da$virama→d;
    275 $da→da;
    276 $dha}$x→dh;
    277 $dha$virama→dh;
    278 $dha→dha;
    279 $na$virama}$ga→n'';
    280 $na$virama}$ya→n'';
    281 $na}$x→n;
    282 $na$virama→n;
    283 $na→na;
    284 $pa$virama}$ha→p'';
    285 $pa}$x→p;
    286 $pa$virama→p;
    287 $pa→pa;
    288 $pha}$x→ph;
    289 $pha$virama→ph;
    290 $pha→pha;
    291 $ba$virama}$ha→b'';
    292 $ba}$x→b;
    293 $ba$virama→b;
    294 $ba→ba;
    295 $bha}$x→bh;
    296 $bha$virama→bh;
    297 $bha→bha;
    298 $ma$virama}$ma→m'';
    299 $ma}$x→m;
    300 $ma$virama→m;
    301 $ma→ma;
    302 $ya}$x→y;
    303 $ya$virama→y;
    304 $ya→ya;
    305 $ra$virama}$ha→r'';
    306 $ra}$x→r;
    307 $ra$virama→r;
    308 $ra→ra;
    309 $vva$virama}$ha→w\u0307'';
    310 $vva}$x→w\u0307;
    311 $vva$virama→w\u0307;
    312 $vva→w\u0307a;
    313 $rra$virama}$ha→r\u0331'';
    314 $rra}$x→r\u0331;
    315 $rra$virama→r\u0331;
    316 $rra→r\u0331a;
    317 $la$virama}$ha→l'';
    318 $la}$x→l;
    319 $la$virama→l;
    320 $la→la;
    321 $lla$virama}$ha→l\u0323'';
    322 $lla}$x→l\u0323;
    323 $lla$virama→l\u0323;
    324 $lla→l\u0323a;
    325 $va}$x→v;
    326 $va$virama→v;
    327 $va→va;
    328 $sa$virama}$ha→s'';
    329 $sa$virama}$sha→s'';
    330 $sa$virama}$ssa→s'';
    331 $sa$virama}$sa→s'';
    332 $sa}$x→s;
    333 $sa$virama→s;
    334 #for gurmukhi
    335 $sa$nukta}$x→s\u0301;
    336 $sa$nukta$virama→s\u0301;
    337 $sa$nukta→s\u0301a;
    338 $sa→sa;
    339 $sha}$x→s\u0301;
    340 $sha$virama→s\u0301;
    341 $sha→s\u0301a;
    342 $ssa}$x→s\u0323;
    343 $ssa$virama→s\u0323;
    344 $ssa→s\u0323a;
    345 $ha}$x→h;
    346 $ha$virama→h;
    347 $ha→ha;
    348 # dependent vowels (should never occur except following consonants)
    349 $forceIndependentMatra{$aa  → \u0314a\u0304;
    350 $forceIndependentMatra{$ai  → \u0314ai;
    351 $forceIndependentMatra{$au  → \u0314au;
    352 $forceIndependentMatra{$ii  → \u0314i\u0304;
    353 $forceIndependentMatra{$i   → \u0314i;
    354 $forceIndependentMatra{$uu  → \u0314u\u0304;
    355 $forceIndependentMatra{$u   → \u0314u;
    356 $forceIndependentMatra{$rrh → \u0314r\u0325\u0304;
    357 $forceIndependentMatra{$rh  → \u0314r\u0325;
    358 $forceIndependentMatra{$llh → \u0314l\u0325\u0304;
    359 $forceIndependentMatra{$lh  → \u0314l\u0325;
    360 $forceIndependentMatra{$e   → \u0314e\u0304;
    361 $forceIndependentMatra{$o   → \u0314o\u0304;
    362 #extra vowels
    363 $forceIndependentMatra{$ce  → \u0314e\u0306;
    364 $forceIndependentMatra{$co  → \u0314o\u0306;
    365 $forceIndependentMatra{$se  → \u0314e;
    366 $forceIndependentMatra{$so  → \u0314o;
    367 $forceIndependentMatra{$nukta  →; # Nukta cannot appear independently or as first character
    368 $forceIndependentMatra{$virama →; # Virama cannot appear independently or as first character
    369 $aa  → a\u0304;
    370 $ai  → ai;
    371 $au  → au;
    372 $ii  → i\u0304;
    373 $i   → i;
    374 $uu  → u\u0304;
    375 $u   → u;
    376 $rrh → r\u0325\u0304;
    377 $rh  → r\u0325;
    378 $llh → l\u0325\u0304;
    379 $lh  → l\u0325;
    380 $e   → e\u0304;
    381 $o   → o\u0304;
    382 #extra vowels
    383 $ce  → e\u0306;
    384 $co  → o\u0306;
    385 $se  → e;
    386 $so  → o;
    387 #dependent vowels when following independent vowels. Generally Illegal only for roundtripping
    388 $waa} $x → a\u0304\u0314;
    389 $wai} $x → ai\u0314;
    390 $wau} $x → au\u0314;
    391 $wii} $x → i\u0304\u0314;
    392 $wi } $x → i\u0314;
    393 $wuu} $x → u\u0304\u0314;
    394 $wu } $x → u\u0314;
    395 $wrr} $x → r\u0325\u0304\u0314;
    396 $wr } $x → r\u0325\u0314;
    397 $wll} $x → l\u0325\u0304\u0314;
    398 $wl } $x → l\u0325\u0314;
    399 $we } $x → e\u0304\u0314;
    400 $wo } $x → o\u0304\u0314;
    401 $wa } $x → a\u0314;
    402 #extra vowels
    403 $wce} $x → e\u0306\u0314;
    404 $wco} $x → o\u0306\u0314;
    405 $wse} $x → e\u0314;
    406 $wso} $x → o\u0314;
    407 $om} $x → ''om\u0314;
    408 # independent vowels when preceded by vowels
    409 $vowels{$waa  → ''a\u0304;
    410 $vowels{$wai  → ''ai;
    411 $vowels{$wau  → ''au;
    412 $vowels{$wii  → ''i\u0304;
    413 $vowels{$wi   → ''i;
    414 $vowels{$wuu  → ''u\u0304;
    415 $vowels{$wu   → ''u;
    416 $vowels{$wrr  → ''r\u0325\u0304;
    417 $vowels{$wr   → ''r\u0325;
    418 $vowels{$wll  → ''l\u0325\u0304;
    419 $vowels{$wl   → ''l\u0325;
    420 $vowels{$we   → ''e\u0304;
    421 $vowels{$wo   → ''o\u0304;
    422 $vowels{$wa   → ''a;
    423 #extra vowels
    424 $vowels{$wce  → ''e\u0306;
    425 $vowels{$wco  → ''o\u0306;
    426 $vowels{$wse  → ''e;
    427 $vowels{$wso  → ''o;
    428 # independent vowels (otherwise)
    429 $waa → a\u0304;
    430 $wai → ai;
    431 $wau → au;
    432 $wii → i\u0304;
    433 $wi  → i;
    434 $wuu → u\u0304;
    435 $wu  → u;
    436 $wrr → r\u0325\u0304;
    437 $wr  → r\u0325;
    438 $wll → l\u0325\u0304;
    439 $wl  → l\u0325;
    440 $we  → e\u0304;
    441 $wo  → o\u0304;
    442 $wa  → a;
    443 #extra vowels
    444 $wce → e\u0306;
    445 $wco → o\u0306;
    446 $wse → e;
    447 $wso → o;
    448 $om → ''om;
    449 #stress marks
    450 $avagraha → \u0315;
    451 $chandrabindu$anusvara→\u0303;
    452 $chandrabindu → m\u0310;
    453 $visarga→h\u0323;
    454 #numbers
    455 $zero  → 0;
    456 $one   → 1;
    457 $two   → 2;
    458 $three → 3;
    459 $four  → 4;
    460 $five  → 5;
    461 $six   → 6;
    462 $seven → 7;
    463 $eight → 8;
    464 $nine  → 9;
    465 $lm   →;
    466 $ailm →;
    467 $aulm →;
    468 $dgs→ʔ;
    469 $kta→t\u0331;
    470 $danda→'.';
    471 $doubleDanda→'.';
    472 \uE070→'.';       # ABBREVIATION SIGN
    473 # LETTER RA WITH MIDDLE DIAGONAL
    474 \uE071}$x→ra;
    475 \uE071$virama→r;
    476 \uE071→ra;
    477 # LETTER RA WITH LOWER DIAGONAL
    478 \uE072}$x→ra;
    479 \uE072$virama→r;
    480 \uE072→ra;
    481 \uE073→;       # RUPEE MARK
    482 \uE074→;       # RUPEE SIGN
    483 \uE075→;       # CURRENCY NUMERATOR ONE
    484 \uE076→;       # CURRENCY NUMERATOR TWO
    485 \uE077→;       # CURRENCY NUMERATOR THREE
    486 \uE078→;       # CURRENCY NUMERATOR FOUR
    487 \uE079→;       # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
    488 \uE07A→;       # CURRENCY DENOMINATOR SIXTEEN
    489 \uE07B→;       # ISSHAR
    490 \uE07C→;       # TIPPI
    491 \uE07D→;       # ADDAK
    492 \uE07E→;       # IRI
    493 \uE07F→;       # URA
    494 \uE080→;       # EK ONKAR
    495 \uE004→;       # DEVANAGARI VOWEL SIGN SHORT A
    496 $virama→; # remove remaining viramas
    497 $nukta→\u0323 ;  # combining dot below
    498 \uE084→æ;       # DEVANAGARI VOWEL SIGN SHORT A