Home | History | Annotate | Download | only in transforms
      1 <?xml version="1.0" encoding="UTF-8" ?>
      2 <!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
      3 <!--
      4 Copyright  1991-2013 Unicode, Inc.
      5 CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
      6 For terms of use, see http://www.unicode.org/copyright.html
      7 Originally prepared by Waris Abdukerim Janbaz <oyghan (a] gmail.com> of the Uyghur Computer Science Association http://ukij.org
      8 -->
      9 <supplementalData>
     10 	<version number="$Revision: 11914 $"/>
     11     <transforms>
     12         <transform source="ug" target="Latin" direction="both" draft="provisional">
     13             <comment># Follows the Latin-Script Uyghur alphabet 2001-todate rules defined at http://ukij.org/html/ , https://en.wikipedia.org/wiki/Uyghur_Latin_alphabet, 			         			http://www.uyghurdictionary.org/excerpts/An%20Introduction%20to%20LSU.pdf
     14 				</comment>
     15 				<comment># Rules are predicated on running NFD first, and NFC afterwards</comment>
     16 				<tRule>:: NFD (NFC) ;</tRule>
     17 				<tRule>$lsuVowels = [aAeEoOuUiI'] ;</tRule>
     18               <tRule>$disambig =   ;</tRule>
     19               <tRule>[:Separator:]*  ' ';</tRule>
     20 				<tRule>$space = [:Separator:]*;</tRule>
     21               <tRule>  ',' $disambig ; # ARABIC DECIMAL SEPARATOR</tRule>
     22               <tRule>  ',' ; # ARABIC COMMA</tRule>
     23               <tRule>  ';' ; # ARABIC SEMICOLON</tRule>
     24               <tRule>  '?' ; # ARABIC QUESTION MARK</tRule>
     25 				<tRule>   ;</tRule>
     26 				<tRule>   ;</tRule>
     27               <tRule>  ; # Uyghur Hamza</tRule>
     28 			    <tRule>  ; # ARABIC/UYGHUR TATWEEL</tRule>
     29 
     30 				<comment># special treatment for Uyghur hamza</comment>
     31 				<tRule>  $space { [aA] ;</tRule>
     32 				<tRule>  $space { [eE] ;</tRule>
     33 				<tRule>  $space { [oO] ;</tRule>
     34 				<tRule>  $space { [uU] ;</tRule>
     35 				<tRule>  $space { [] ;</tRule>
     36 				<tRule>  $space { [] ;</tRule>
     37 				<tRule>  $space { [] ;</tRule>
     38 				<tRule>  $space { [iI] ;</tRule>
     39 				<tRule>  $lsuVowels { [aA] ;</tRule>
     40 				<tRule>  $lsuVowels { [eE] ;</tRule>
     41 				<tRule>  $lsuVowels { [oO] ;</tRule>
     42 				<tRule>  $lsuVowels { [uU] ;</tRule>
     43 				<tRule>  $lsuVowels { [] ;</tRule>
     44 				<tRule>  $lsuVowels { [] ;</tRule>
     45 				<tRule>  $lsuVowels { [] ;</tRule>
     46 				<tRule>  $lsuVowels { [iI] ;</tRule>
     47 
     48 				<comment># special treatment for apostrof</comment>
     49 				<tRule>  s ['] { h ;</tRule>
     50 				<tRule>  n ['] { gh ;</tRule>
     51 				<tRule>  n ['] { g ;</tRule>
     52 				<tRule>  ng ['] { h ;</tRule>
     53 				<tRule>  S ['] { H ;</tRule>
     54 				<tRule>  N ['] { GH ;</tRule>
     55 				<tRule>  N ['] { G ;</tRule>
     56 				<tRule>  NG ['] { H ;</tRule>
     57 
     58 				<comment># special treatment for apostrof</comment>
     59 				<tRule>  s''h ;</tRule>
     60 				<tRule>  n''gh ;</tRule>
     61 				<tRule>  n''g ;</tRule>
     62 				<tRule>  ng''h ;</tRule>
     63                                 <!-- following 4 were duplicates. -->
     64 				<!-- <tRule>  S''H ;</tRule> -->
     65 				<!-- <tRule>  N''GH ;</tRule> -->
     66 				<!-- <tRule>  N''G ;</tRule> -->
     67 				<!-- <tRule>  NG''H ;</tRule> -->
     68 
     69 				<comment># disambiguation for  by covering the most common words with </comment>
     70 				<tRule>  dirijor ;</tRule>
     71 				<tRule>  rjissor ;</tRule>
     72 				<tRule>  jurnili ;</tRule>
     73 				<tRule>  chrtyoj ;</tRule>
     74 				<tRule>  purjin ;</tRule>
     75 				<tRule>  prsonaj ;</tRule>
     76 				<tRule>  maroj ;</tRule>
     77 				<tRule>  parij ;</tRule>
     78 				<tRule>  jurnal ;</tRule>
     79 				<tRule>  bujghun ;</tRule>
     80 				<tRule>  woltaj ;</tRule>
     81 				<tRule>  oranj ;</tRule>
     82 				<tRule>  tamojna ;</tRule>
     83 				<tRule>  garaj ;</tRule>
     84 				<tRule>  ghujmek ;</tRule>
     85 				<tRule>  tiraj ;</tRule>
     86 				<tRule>  staj ;</tRule>
     87 				<tRule>  projktor ;</tRule>
     88 				<tRule>'-'  'gaj-guj' ;</tRule>
     89 				<tRule>'-'  'paj-puj' ;</tRule>
     90 				<tRule>'-'  'waj-wuj' ;</tRule>
     91 				<tRule>'-'  'pij-pij' ;</tRule>
     92 				<tRule>'-'  'gij-gij' ;</tRule>
     93 				<tRule>'-'  'mij-mij' ;</tRule>
     94 				<tRule>  jandarm ;</tRule>
     95 
     96 				<tRule>  DIRIJOR ;</tRule>
     97 				<tRule>  RJISSOR ;</tRule>
     98 				<tRule>  JURNILI ;</tRule>
     99 				<tRule>  CHRTYOJ ;</tRule>
    100 				<tRule>  PURJIN ;</tRule>
    101 				<tRule>  PRSONAJ ;</tRule>
    102 				<tRule>  MAROJ ;</tRule>
    103 				<tRule>  PARIJ ;</tRule>
    104 				<tRule>  JURNAL ;</tRule>
    105 				<tRule>  BUJGHUN ;</tRule>
    106 				<tRule>  WOLTAJ ;</tRule>
    107 				<tRule>  ORANJ ;</tRule>
    108 				<tRule>  TAMOJNA ;</tRule>
    109 				<tRule>  GARAJ ;</tRule>
    110 				<tRule>  GHUJMEK ;</tRule>
    111 				<tRule>  TIRAJ ;</tRule>
    112 				<tRule>  STAJ ;</tRule>
    113 				<tRule>  PROJKTOR ;</tRule>
    114 				<tRule>'-'  'GAJ-GUJ' ;</tRule>
    115 				<tRule>'-'  'PAJ-PUJ' ;</tRule>
    116 				<tRule>'-'  'WAJ-WUJ' ;</tRule>
    117 				<tRule>'-'  'PIJ-PIJ' ;</tRule>
    118 				<tRule>'-'  'GIJ-GIJ' ;</tRule>
    119 				<tRule>'-'  'MIJ-MIJ' ;</tRule>
    120 				<tRule>  JANDARM ;</tRule>
    121 
    122 				<comment># letters</comment>
    123 				<tRule>  a ;</tRule>
    124 				<tRule>  e ;</tRule>
    125 				<tRule>  b ;</tRule>
    126 				<tRule>  p ;</tRule>
    127 				<tRule>  t ;</tRule>
    128 				<tRule>  j ;</tRule>
    129 				<tRule>  ch ;</tRule>
    130 				<tRule>  x ;</tRule>
    131 				<tRule>  d ;</tRule>
    132 				<tRule>  r ;</tRule>
    133 				<tRule>  z ;</tRule>
    134 				<tRule>  j ;</tRule>
    135 				<tRule>  sh ;</tRule>
    136 				<tRule>  s ;</tRule>
    137 				<tRule>  gh ;</tRule>
    138 				<tRule>  f ;</tRule>
    139 				<tRule>  q ;</tRule>
    140 				<tRule>  k ;</tRule>
    141 				<tRule>  ng ;</tRule>
    142 				<tRule>  g ;</tRule>
    143 				<tRule>  l ;</tRule>
    144 				<tRule>  m ;</tRule>
    145 				<tRule>  n ;</tRule>
    146 				<tRule>  h ;</tRule>
    147 				<tRule>  o ;</tRule>
    148 				<tRule>  u ;</tRule>
    149 				<tRule>   ;</tRule>
    150 				<tRule>   ;</tRule>
    151 				<tRule>  w ;</tRule>
    152 				<tRule>   ;</tRule>
    153 				<tRule>  i ;</tRule>
    154 				<tRule>  y ;</tRule>
    155 
    156 				<tRule>  A ;</tRule>
    157 				<tRule>  E ;</tRule>
    158 				<tRule>  B ;</tRule>
    159 				<tRule>  P ;</tRule>
    160 				<tRule>  T ;</tRule>
    161 				<tRule>  J ;</tRule>
    162 				<tRule>  CH ;</tRule>
    163 				<tRule>  Ch ;</tRule>
    164 				<tRule>  X ;</tRule>
    165 				<tRule>  D ;</tRule>
    166 				<tRule>  R ;</tRule>
    167 				<tRule>  Z ;</tRule>
    168 
    169 				<tRule>  SH ;</tRule>
    170 				<tRule>  Sh ;</tRule>
    171 				<tRule>  S ;</tRule>
    172 				<tRule>  GH ;</tRule>
    173 				<tRule>  Gh ;</tRule>
    174 				<tRule>  F ;</tRule>
    175 				<tRule>  Q ;</tRule>
    176 				<tRule>  K ;</tRule>
    177 				<tRule>  NG ;</tRule>
    178 				<tRule>  Ng ;</tRule>
    179 				<tRule>  G ;</tRule>
    180 				<tRule>  L ;</tRule>
    181 				<tRule>  M ;</tRule>
    182 				<tRule>  N ;</tRule>
    183 				<tRule>  H ;</tRule>
    184 				<tRule>  O ;</tRule>
    185 				<tRule>  U ;</tRule>
    186 				<tRule>   ;</tRule>
    187 				<tRule>   ;</tRule>
    188 				<tRule>  W ;</tRule>
    189 				<tRule>   ;</tRule>
    190 				<tRule>  I ;</tRule>
    191 				<tRule>  Y ;</tRule>
    192 
    193 			   <tRule>::NFC (NFD) ;</tRule>
    194         </transform>
    195     </transforms>
    196 </supplementalData>
    197