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="ar" target="ar_Latn" variant="BGN" direction="forward" draft="contributed" alias="Arabic-Latin/BGN ar-Latn-t-ar-m0-bgn"> 12 <tRule> 13 # 14 ######################################################################## 15 # BGN/PCGN 1956 System 16 # 17 # This system was adopted by the BGN in 1946 and by the PCGN 18 # in 1956 and has been applied in the systematic romanization 19 # of geographic names in Bahrain, Egypt, Iraq, Jordan, 20 # Kuwait, Lebanon, Libya, Oman, Qatar, Saudi Arabia, Sudan, 21 # Syria, Tunisia, the United Arab Emirates, and Yemen, all 22 # of which has been covered by published BGN engineers. 23 # 24 # Originally prepared by Michael Everson <everson (a] evertype.com> 25 ######################################################################## 26 # 27 # MINIMAL FILTER: Arabic-Latin 28 # 29 30 :: [[:arabic:][:block=ARABIC:][]] ; 31 :: NFKD (NFC) ; 32 # 33 # 34 ######################################################################## 35 36 37 # 38 ######################################################################## 39 # 40 # Define All Transformation Variables 41 # 42 ######################################################################## 43 # 44 45 $alef = ; 46 $ayin = ; 47 $disambig = ; 48 # 49 # 50 # Use this $wordBoundary until bug 2034 is fixed in ICU: 51 # http://bugs.icu-project.org/cgi-bin/icu-bugs/transliterate?id=2034;expression=boundary;user=guest 52 # 53 54 $wordBoundary = [^[:L:][:M:][:N:]] ; 55 # 56 # 57 ######################################################################## 58 59 # non-letters 60 [:Nd:]{}[:Nd:] [:Nd:]{','}[:Nd:] ; # ARABIC DECIMAL SEPARATOR 61 [:Nd:]{}[:Nd:] [:Nd:]{'.'}[:Nd:] ; # ARABIC THOUSANDS SEPARATOR 62 ',' $disambig ; # ARABIC DECIMAL SEPARATOR 63 '.' $disambig ; # ARABIC THOUSANDS SEPARATOR 64 # ; # ARABIC FIVE POINTED STAR // no need to transliterate 65 ',' ; # ARABIC COMMA 66 ';' ; # ARABIC SEMICOLON 67 '?' ; # ARABIC QUESTION MARK 68 '%' ; # ARABIC PERCENT SIGN 69 0 $disambig ; # EXTENDED ARABIC-INDIC DIGIT ZERO 70 1 $disambig ; # EXTENDED ARABIC-INDIC DIGIT ONE 71 2 $disambig ; # EXTENDED ARABIC-INDIC DIGIT TWO 72 3 $disambig ; # EXTENDED ARABIC-INDIC DIGIT THREE 73 4 $disambig ; # EXTENDED ARABIC-INDIC DIGIT FOUR 74 5 $disambig ; # EXTENDED ARABIC-INDIC DIGIT FIVE 75 6 $disambig ; # EXTENDED ARABIC-INDIC DIGIT SIX 76 7 $disambig ; # EXTENDED ARABIC-INDIC DIGIT SEVEN 77 8 $disambig ; # EXTENDED ARABIC-INDIC DIGIT EIGHT 78 9 $disambig ; # EXTENDED ARABIC-INDIC DIGIT NINE 79 0 ; # ARABIC-INDIC DIGIT ZERO 80 1 ; # ARABIC-INDIC DIGIT ONE 81 2 ; # ARABIC-INDIC DIGIT TWO 82 3 ; # ARABIC-INDIC DIGIT THREE 83 4 ; # ARABIC-INDIC DIGIT FOUR 84 5 ; # ARABIC-INDIC DIGIT FIVE 85 6 ; # ARABIC-INDIC DIGIT SIX 86 7 ; # ARABIC-INDIC DIGIT SEVEN 87 8 ; # ARABIC-INDIC DIGIT EIGHT 88 9 ; # ARABIC-INDIC DIGIT NINE 89 90 # 91 ######################################################################## 92 # 93 # Rules moved to front to avoid masking 94 # 95 ######################################################################## 96 97 98 # 99 ######################################################################## 100 # 101 # BGN Page 8 Rule 5 102 # 103 # The character sequences , , , and may be romanized th, kh, 104 # dh, and sh in order to differentiate those romanizations from the 105 # digraphs th, kh, dh, and sh. 106 # 107 ######################################################################## 108 # 109 110 th ; # ARABIC LETTER TEH + HEH 111 kh ; # ARABIC LETTER KAF + HEH 112 dh ; # ARABIC LETTER DAL + HEH 113 sh ; # ARABIC LETTER SEEN + HEH 114 # 115 # 116 ######################################################################## 117 # 118 # End Rule 5 119 # 120 ######################################################################## 121 122 123 ######################################################################## 124 125 # 126 # 127 # BGN Page 8 Rule 9 128 # 129 # Doubles consonant sounds are represented in Arabic script by placing 130 # a shaddah ( ) over a consonant character. In romanization the letter 131 # should be doubled. [The remainder of this rule deals with the definite 132 # article and is lexical.] 133 # 134 ######################################################################## 135 # 136 137 bb ; # ARABIC LETTER BEH + SHADDA 138 tt ; # ARABIC LETTER TEH + SHADDA 139 thth ; # ARABIC LETTER THEH + SHADDA 140 jj ; # ARABIC LETTER JEEM + SHADDA 141 ; # ARABIC LETTER HAH + SHADDA 142 khkh ; # ARABIC LETTER KHAH + SHADDA 143 dd ; # ARABIC LETTER DAL + SHADDA 144 dhdh ; # ARABIC LETTER THAL + SHADDA 145 rr ; # ARABIC LETTER REH + SHADDA 146 zz ; # ARABIC LETTER ZAIN + SHADDA 147 ss ; # ARABIC LETTER SEEN + SHADDA 148 shsh ; # ARABIC LETTER SHEEN + SHADDA 149 ; # ARABIC LETTER SAD + SHADDA 150 ; # ARABIC LETTER DAD + SHADDA 151 ; # ARABIC LETTER TAH + SHADDA 152 ; # ARABIC LETTER ZAH + SHADDA 153 $ayin $ayin ; # ARABIC LETTER AIN + SHADDA 154 ghgh ; # ARABIC LETTER GHAIN + SHADDA 155 ff ; # ARABIC LETTER FEH + SHADDA 156 qq ; # ARABIC LETTER QAF + SHADDA 157 kk ; # ARABIC LETTER KAF + SHADDA 158 ll ; # ARABIC LETTER LAM + SHADDA 159 mm ; # ARABIC LETTER MEEM + SHADDA 160 nn ; # ARABIC LETTER NOON + SHADDA 161 hh ; # ARABIC LETTER HEH + SHADDA 162 ww ; # ARABIC LETTER WAW + SHADDA 163 yy ; # ARABIC LETTER YEH + SHADDA 164 # 165 # 166 ######################################################################## 167 # 168 # End Rule 9 169 # 170 ######################################################################## 171 172 173 # 174 ######################################################################## 175 # 176 # Start of Transformations 177 # 178 ######################################################################## 179 # 180 181 $wordBoundary{ ; # ARABIC LETTER HAMZA 182 $alef ; # ARABIC LETTER HAMZA 183 $wordBoundary{ ; # ARABIC LETTER ALEF 184 $alef ; # ARABIC LETTER ALEF WASLA 185 $wordBoundary{ ; # ARABIC LETTER ALEF WITH MADDA ABOVE 186 $alef ; # ARABIC LETTER ALEF WITH MADDA ABOVE 187 b ; # ARABIC LETTER BEH 188 t ; # ARABIC LETTER TEH 189 h ; # ARABIC LETTER TEH MARBUTA 190 th ; # ARABIC LETTER THEH 191 j ; # ARABIC LETTER JEEM 192 ; # ARABIC LETTER HAH 193 kh ; # ARABIC LETTER KHAH 194 d ; # ARABIC LETTER DAL 195 dh ; # ARABIC LETTER THAL 196 r ; # ARABIC LETTER REH 197 z ; # ARABIC LETTER ZAIN 198 s ; # ARABIC LETTER SEEN 199 sh ; # ARABIC LETTER SHEEN 200 ; # ARABIC LETTER SAD 201 ; # ARABIC LETTER DAD 202 ; # ARABIC LETTER TAH 203 z ; # ARABIC LETTER ZAH 204 $ayin ; # ARABIC LETTER AIN 205 gh ; # ARABIC LETTER GHAIN 206 f ; # ARABIC LETTER FEH 207 q ; # ARABIC LETTER QAF 208 k $disambig ; # ARABIC LETTER KEHEH 209 k ; # ARABIC LETTER KAF 210 l ; # ARABIC LETTER LAM 211 m ; # ARABIC LETTER MEEM 212 n ; # ARABIC LETTER NOON 213 h ; # ARABIC LETTER HEH 214 w ; # ARABIC LETTER WAW 215 y ; # ARABIC LETTER YEH 216 217 ; # ARABIC FATHA + ALEF 218 ; # ARABIC FATHA + ALEF MAKSURA 219 ay ; # ARABIC FATHA + YEH + SUKUN 220 aw ; # ARABIC FATHA + WAW + SUKUN 221 a ; # ARABIC FATHA 222 223 ; # ARABIC KASRA + YEH 224 i ; # ARABIC KASRA 225 226 ; # ARABIC DAMMA + WAW 227 u ; # ARABIC DAMMA 228 229 ; # ARABIC SUKUN 230 a ; # ARABIC FATHATAN 231 i ; # ARABIC KASRATAN 232 u ; # ARABIC DAMMATAN 233 ::NFC (NFD) ; 234 235 # 236 # 237 ######################################################################## 238 239 </tRule> 240 </transform> 241 </transforms> 242 </supplementalData> 243
