144 lines
3.7 KiB
XML
144 lines
3.7 KiB
XML
<?xml version="1.0" encoding="UTF-8" ?>
|
||
<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
|
||
<!--
|
||
Copyright © 1991-2016 Unicode, Inc.
|
||
CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
|
||
For terms of use, see http://www.unicode.org/copyright.html
|
||
-->
|
||
<supplementalData>
|
||
<version number="$Revision$"/>
|
||
<transforms>
|
||
<transform source="InterIndic" target="Arabic" direction="forward" visibility="internal">
|
||
<tRule><![CDATA[
|
||
$nonword = [^\uE000-\uE0FF];
|
||
$wordBoundary = [^[:L:][:M:][:N:]];
|
||
\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; # है
|
||
\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 ं
|
||
\uE003→ه ا; # viarga to ha + alif ः
|
||
\uE004→ا; # short a to alif ऄ
|
||
\uE005→ا; # अ
|
||
\uE006→ا ٓ; # 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
|
||
$wordBoundary {\uE00F} → إي; # word-initial ए
|
||
\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→; # ़
|
||
\uE03D→; # ऽ
|
||
\uE03E→ا; # ा
|
||
\uE03F→ي; # ि
|
||
\uE040→ي; # ी
|
||
\uE041→و; # ु
|
||
\uE042→و; # ू
|
||
\uE043→ر; # ृ
|
||
\uE044→ر; # ॄ
|
||
\uE045→ن; # ॅ
|
||
\uE046→ي; # ॆ
|
||
\uE047 } $nonword→ي; # े use ي when at end
|
||
\uE047→ي; # े use ي when not at end
|
||
\uE048 } $nonword→ا ي; # ै use ي when at end
|
||
\uE048→ا ي; # ै use ي when not at end
|
||
\uE049→و; # ॉ
|
||
\uE04A→ا و; # ॊ
|
||
\uE04B→و; # ो
|
||
\uE04C→ا و; # ौ
|
||
\uE04D→; # ्
|
||
\uE050→ا و; # ॐ
|
||
\uE051→; # ॑
|
||
\uE052→; # ॒
|
||
\uE053→; # ॓
|
||
\uE054→; # ॔
|
||
\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; # ॢ
|
||
\uE063→ل; # ॣ
|
||
\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;
|
||
]]></tRule>
|
||
</transform>
|
||
</transforms>
|
||
</supplementalData>
|