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 -->
      8 <supplementalData>
      9 	<version number="$Revision: 13787 $"/>
     10 	<transforms>
     11 		<transform source="mk" target="mk_Latn" variant="BGN" direction="forward" draft="contributed" alias="Macedonian-Latin/BGN mk-Latn-t-mk-m0-bgn">
     12 			<tRule><![CDATA[
     13 #
     14 ########################################################################
     15 # BGN/PCGN 1981 System
     16 #
     17 # Macedonian was official established as a literary language in
     18 # Yugoslavia during World War II and is now the official language
     19 # of Macedonia. Its alphabet is identical to Serbian, except
     20 # that the letters  and  are replaced by  and , and
     21 # the letter  and the apostrophe are added.
     22 #
     23 # The Macedonian Alphabet as defined by the BGN (Page 69):
     24 #
     25 #   
     26 #   
     27 #
     28 # Originally prepared by Michael Everson <everson (a] evertype.com>
     29 ########################################################################
     30 #
     31 # MINIMAL FILTER: Macedonian-Latin
     32 #
     33 
     34 :: [] ;
     35 :: NFD (NFC) ;
     36 #
     37 #
     38 ########################################################################
     39 
     40 
     41 #
     42 ########################################################################
     43 #
     44 # Define All Transformation Variables
     45 #
     46 ########################################################################
     47 #
     48 
     49 $prime  =  ;
     50 
     51 $upperConsonants = [] ;
     52 $lowerConsonants = [] ;
     53 $consonants = [$upperConsonants $lowerConsonants] ;
     54 
     55 $upperVowels = [] ;
     56 $lowerVowels = [] ;
     57 $vowels = [$upperVowels $lowerVowels] ;
     58 
     59 $lower = [$lowerConsonants $lowerVowels] ;
     60 #
     61 #
     62 # Use this $wordBoundary until bug 2034 is fixed in ICU:
     63 # http://bugs.icu-project.org/cgi-bin/icu-bugs/transliterate?id=2034;expression=boundary;user=guest
     64 #
     65 
     66 $wordBoundary =  [^[:L:][:M:][:N:]] ;
     67 #
     68 #
     69 ########################################################################
     70 
     71 
     72 #
     73 ########################################################################
     74 #
     75 # Start of Alphabetic Transformations
     76 #
     77 ########################################################################
     78 #
     79 
     80   A ; # CYRILLIC CAPITAL LETTER A
     81   a ; # CYRILLIC SMALL LETTER A
     82   B ; # CYRILLIC CAPITAL LETTER BE
     83   b ; # CYRILLIC SMALL LETTER BE
     84   V ; # CYRILLIC CAPITAL LETTER VE
     85   v ; # CYRILLIC SMALL LETTER VE
     86   G ; # CYRILLIC CAPITAL LETTER GHE
     87   g ; # CYRILLIC SMALL LETTER GHE
     88   D ; # CYRILLIC CAPITAL LETTER DE
     89   d ; # CYRILLIC SMALL LETTER DE
     90 #
     91 #
     92 ########################################################################
     93 #
     94 # BGN Page 70 Rule 1:
     95 #
     96 # The character  should be romanized g when it occurs before 
     97 # and . In all other instances, it should be romanized  ().
     98 #
     99 ########################################################################
    100 #
    101 
    102 }[]  G ; # CYRILLIC CAPITAL LETTER GJE
    103 }[]  g ; # CYRILLIC SMALL LETTER GJE
    104    ; # CYRILLIC CAPITAL LETTER GJE
    105    ; # CYRILLIC SMALL LETTER GJE
    106 #
    107 #
    108 ########################################################################
    109 #
    110 # End Rule 1
    111 #
    112 ########################################################################
    113 #
    114 
    115   E ; # CYRILLIC CAPITAL LETTER DE
    116   e ; # CYRILLIC SMALL LETTER DE
    117    ; # CYRILLIC CAPITAL LETTER ZHE
    118    ; # CYRILLIC SMALL LETTER ZHE
    119   Z ; # CYRILLIC CAPITAL LETTER ZE
    120   z ; # CYRILLIC SMALL LETTER ZE
    121 } $lower  Dz ; # CYRILLIC CAPITAL LETTER DZE
    122   DZ ; # CYRILLIC CAPITAL LETTER DZE
    123   dz ; # CYRILLIC SMALL LETTER DZE
    124   I ; # CYRILLIC CAPITAL LETTER I
    125   i ; # CYRILLIC SMALL LETTER I
    126   J ; # CYRILLIC CAPITAL LETTER JE
    127   j ; # CYRILLIC SMALL LETTER JE
    128   K ; # CYRILLIC CAPITAL LETTER KA
    129   k ; # CYRILLIC SMALL LETTER KA
    130   L ; # CYRILLIC CAPITAL LETTER EL
    131   l ; # CYRILLIC SMALL LETTER EL
    132 } $lower  Lj ; # CYRILLIC CAPITAL LETTER LJE
    133   LJ ; # CYRILLIC CAPITAL LETTER LJE
    134   lj ; # CYRILLIC SMALL LETTER LJE
    135   M ; # CYRILLIC CAPITAL LETTER EM
    136   m ; # CYRILLIC SMALL LETTER EM
    137   N ; # CYRILLIC CAPITAL LETTER EN
    138   n ; # CYRILLIC SMALL LETTER EN
    139 } $lower  Nj ; # CYRILLIC CAPITAL LETTER NJE
    140   NJ ; # CYRILLIC CAPITAL LETTER NJE
    141   nj ; # CYRILLIC SMALL LETTER NJE
    142   O ; # CYRILLIC CAPITAL LETTER O
    143   o ; # CYRILLIC SMALL LETTER O
    144   P ; # CYRILLIC CAPITAL LETTER PE
    145   p ; # CYRILLIC SMALL LETTER PE
    146   R ; # CYRILLIC CAPITAL LETTER ER
    147   r ; # CYRILLIC SMALL LETTER ER
    148   S ; # CYRILLIC CAPITAL LETTER ES
    149   s ; # CYRILLIC SMALL LETTER ES
    150   T ; # CYRILLIC CAPITAL LETTER TE
    151   t ; # CYRILLIC SMALL LETTER TE
    152 #
    153 #
    154 ########################################################################
    155 #
    156 # BGN Page 70 Rule 2:
    157 #
    158 # The character  should be romanized k when it occurs before 
    159 # and . In all other instances, it should be romanized c.
    160 #
    161 ########################################################################
    162 #
    163 
    164 }[]  K ; # CYRILLIC CAPITAL LETTER KJE
    165 }[]  k ; # CYRILLIC SMALL LETTER KJE
    166   C ; # CYRILLIC CAPITAL LETTER KJE
    167   c ; # CYRILLIC SMALL LETTER KJE
    168 #
    169 #
    170 ########################################################################
    171 #
    172 # End Rule 2
    173 #
    174 ########################################################################
    175 #
    176 
    177   U ; # CYRILLIC CAPITAL LETTER U
    178   u ; # CYRILLIC SMALL LETTER U
    179   F ; # CYRILLIC CAPITAL LETTER EF
    180   f ; # CYRILLIC SMALL LETTER EF
    181   H ; # CYRILLIC CAPITAL LETTER HA
    182   h ; # CYRILLIC SMALL LETTER HA
    183   C ; # CYRILLIC CAPITAL LETTER TSE
    184   c ; # CYRILLIC SMALL LETTER TSE
    185    ; # CYRILLIC CAPITAL LETTER CHE
    186    ; # CYRILLIC SMALL LETTER CHE
    187 } $lower  D ; # CYRILLIC CAPITAL LETTER SHA
    188   D ; # CYRILLIC CAPITAL LETTER SHA
    189   d ; # CYRILLIC SMALL LETTER SHA
    190    ; # CYRILLIC CAPITAL LETTER SHA
    191    ; # CYRILLIC SMALL LETTER SHA
    192 #
    193 #
    194 ########################################################################
    195 #
    196 # BGN Page 69 Rule 32, maps the symbol onto itself and
    197 # is ignored here for computational efficiency.
    198 #
    199 # $prime  $prime ; # RIGHT SINGLE QUOTATION MARK
    200 #
    201 ########################################################################
    202 
    203 			]]></tRule>
    204 		</transform>
    205 	</transforms>
    206 </supplementalData>
    207