| Index: source/data/translit/InterIndic_Arabic.txt
|
| diff --git a/source/data/translit/InterIndic_Arabic.txt b/source/data/translit/InterIndic_Arabic.txt
|
| new file mode 100644
|
| index 0000000000000000000000000000000000000000..71f485267a5f5ecb33931693c9bec1f97fe3c06e
|
| --- /dev/null
|
| +++ b/source/data/translit/InterIndic_Arabic.txt
|
| @@ -0,0 +1,132 @@
|
| +# © 2016 and later: Unicode, Inc. and others.
|
| +# License & terms of use: http://www.unicode.org/copyright.html#License
|
| +#
|
| +# File: InterIndic_Arabic.txt
|
| +# Generated from CLDR
|
| +#
|
| +
|
| +$nonword = [^\uE000-\uE0FF];
|
| +\uE015\uE03F\uE02F\uE03E } $nonword→كيا; # किया
|
| +\uE026\uE03F\uE02F\uE03E } $nonword→ديا; # दिया
|
| +\uE015\uE03F } $nonword→كي; # कि at word end
|
| +\uE039\uE048→هي; # ह\u0948
|
| +\uE001 } $nonword→ن; # chandrabindu at end to noon
|
| +\uE001→ن; # chandrabindu not at end to noon
|
| +\uE002 } $nonword→ن; # anusvara to noon at end
|
| +\uE002→ن; # anusvara to noon \u0902
|
| +\uE003→ه ا; # viarga to ha + alif ः
|
| +\uE004→ا; # short a to alif ऄ
|
| +\uE005→ا; # अ
|
| +\uE006→ا \u0653; # alif with mad आ
|
| +[[:L:][:M:]] {\uE007}→ي; # इ after another letter or mark
|
| +\uE007→إ; # इ at beginning of word
|
| +[[:L:][:M:]] {\uE008}→ي; # ई after another letter or mark
|
| +\uE008→إ; # ई at beginning of word
|
| +\uE009→و; # उ
|
| +\uE00A→و; # ऊ
|
| +\uE00B→ر; # ऋ
|
| +\uE00C→ل; # ऌ
|
| +\uE00D→ا ي; # ऍ
|
| +\uE00E→ي; # ऎ
|
| +\uE00F } $nonword→ي; # ए use ي when at end
|
| +\uE00F→ي; # ए use ي when not at end
|
| +\uE010 } $nonword→ا ي; # ऐ use ي when at end
|
| +\uE010→ا ي; # ऐ use ي when not at end
|
| +\uE011→ا و; # ऑ
|
| +\uE012→ا و; # ऒ
|
| +\uE013→ا و; # ओ
|
| +\uE014→ا و; # औ
|
| +\uE015→ك; # क
|
| +\uE016→كه; # ख
|
| +\uE017→ج; # ग
|
| +\uE018→جه; # घ
|
| +\uE019→نج; # ङ
|
| +\uE01A→تش; # च
|
| +\uE01B→تشه; # छ
|
| +\uE01C→ج; # ज
|
| +\uE01D→جه; # झ
|
| +\uE01E→ن; # ञ
|
| +\uE01F→ط; # ट
|
| +\uE020→طه; # ठ
|
| +\uE021→د; # ड
|
| +\uE022→ده; # ढ
|
| +\uE023→ن; # ण
|
| +\uE024→ت; # त
|
| +\uE025→ته; # थ
|
| +\uE026→د; # द
|
| +\uE027→ده; # ध
|
| +\uE028→ن; # न
|
| +\uE029→ن; # ऩ
|
| +\uE02A→ب; # प
|
| +\uE02B→به; # फ
|
| +\uE02C→ب; # ब
|
| +\uE02D→به; # भ
|
| +\uE02E→م; # म
|
| +\uE02F→ي; # य
|
| +\uE030→ر; # र
|
| +\uE031→ر; # ऱ
|
| +\uE032→ل; # ल
|
| +\uE033→ر; # ळ
|
| +\uE034→ر; # ऴ
|
| +\uE035→و; # व
|
| +\uE036→ش; # श
|
| +\uE037→ش; # ष
|
| +\uE038→س; # स
|
| +\uE039→ه; # ह
|
| +\uE03C→; # \u093C
|
| +\uE03D→; # ऽ
|
| +\uE03E→ا; # ा
|
| +\uE03F→ي; # ि
|
| +\uE040→ي; # ी
|
| +\uE041→و; # \u0941
|
| +\uE042→و; # \u0942
|
| +\uE043→ر; # \u0943
|
| +\uE044→ر; # \u0944
|
| +\uE045→ن; # \u0945
|
| +\uE046→ي; # \u0946
|
| +\uE047 } $nonword→ي; # \u0947 use ي when at end
|
| +\uE047→ي; # \u0947 use ي when not at end
|
| +\uE048 } $nonword→ا ي; # \u0948 use ي when at end
|
| +\uE048→ا ي; # \u0948 use ي when not at end
|
| +\uE049→و; # ॉ
|
| +\uE04A→ا و; # ॊ
|
| +\uE04B→و; # ो
|
| +\uE04C→ا و; # ौ
|
| +\uE04D→; # \u094D
|
| +\uE050→ا و; # ॐ
|
| +\uE051→; # \u0951
|
| +\uE052→; # \u0952
|
| +\uE053→; # \u0953
|
| +\uE054→; # \u0954
|
| +\uE058→ق; # क़
|
| +\uE059→خ; # ख़
|
| +\uE05A→غ; # ग़
|
| +\uE05B→ز; # ज़
|
| +\uE05C→ر; # ड़
|
| +\uE05D→ره; # ढ़
|
| +\uE05E→ف; # फ़
|
| +\uE05F→ي; # य़
|
| +\uE060→ر; # ॠ
|
| +\uE061→ل; # ॡ
|
| +\uE062→ل; # \u0962
|
| +\uE063→ل; # \u0963
|
| +\uE064→۔; # ।
|
| +\uE065→۔; # ॥
|
| +\uE066→\.; # ०
|
| +\uE067→١; # १
|
| +\uE068→٢; # २
|
| +\uE069→٣; # ३
|
| +\uE06A→٤; # ४
|
| +\uE06B→٥; # ५
|
| +\uE06C→٦; # ६
|
| +\uE06D→٧; # ७
|
| +\uE06E→٨; # ८
|
| +\uE06F→٩; # ९
|
| +\uE070→\.; # ॰
|
| +\uE082→; # ॽ
|
| +# Remove sequences of alif characters.
|
| +# For example, transform पाओला → بااولا → باولا.
|
| +::null;
|
| +$alif = [أإآا] [:M:]*;
|
| +($alif) $alif+ → $1;
|
| +
|
|
|