1<?xml version="1.0" encoding="UTF-8" ?> 2<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd"> 3<!-- 4Copyright © 1991-2013 Unicode, Inc. 5CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/) 6For terms of use, see http://www.unicode.org/copyright.html 7--> 8<supplementalData> 9 <version number="$Revision: 13787 $"/> 10 <transforms> 11 <transform source="ar" target="ar_Latn" variant="BGN" direction="forward" draft="contributed" alias="Arabic-Latin/BGN ar-Latn-t-ar-m0-bgn"> 12 <tRule> 13# 14######################################################################## 15# BGN/PCGN 1956 System 16# 17# This system was adopted by the BGN in 1946 and by the PCGN 18# in 1956 and has been applied in the systematic romanization 19# of geographic names in Bahrain, Egypt, Iraq, Jordan, 20# Kuwait, Lebanon, Libya, Oman, Qatar, Saudi Arabia, Sudan, 21# Syria, Tunisia, the United Arab Emirates, and Yemen, all 22# of which has been covered by published BGN engineers. 23# 24# Originally prepared by Michael Everson <everson@evertype.com> 25######################################################################## 26# 27# MINIMAL FILTER: Arabic-Latin 28# 29 30:: [[:arabic:][:block=ARABIC:][ءآابةتثجحخدذرزسشصضطظعغفقكلمنهوىيًٌٍَُِّْ٠١٢٣٤٥٦٧٨٩ٱ]] ; 31:: NFKD (NFC) ; 32# 33# 34######################################################################## 35 36 37# 38######################################################################## 39# 40# Define All Transformation Variables 41# 42######################################################################## 43# 44 45$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 69۰ ↔ 0 $disambig ; # EXTENDED ARABIC-INDIC DIGIT ZERO 70۱ ↔ 1 $disambig ; # EXTENDED ARABIC-INDIC DIGIT ONE 71۲ ↔ 2 $disambig ; # EXTENDED ARABIC-INDIC DIGIT TWO 72۳ ↔ 3 $disambig ; # EXTENDED ARABIC-INDIC DIGIT THREE 73۴ ↔ 4 $disambig ; # EXTENDED ARABIC-INDIC DIGIT FOUR 74۵ ↔ 5 $disambig ; # EXTENDED ARABIC-INDIC DIGIT FIVE 75۶ ↔ 6 $disambig ; # EXTENDED ARABIC-INDIC DIGIT SIX 76۷ ↔ 7 $disambig ; # EXTENDED ARABIC-INDIC DIGIT SEVEN 77۸ ↔ 8 $disambig ; # EXTENDED ARABIC-INDIC DIGIT EIGHT 78۹ ↔ 9 $disambig ; # EXTENDED ARABIC-INDIC DIGIT NINE 79٠ ↔ 0 ; # ARABIC-INDIC DIGIT ZERO 80١ ↔ 1 ; # ARABIC-INDIC DIGIT ONE 81٢ ↔ 2 ; # ARABIC-INDIC DIGIT TWO 82٣ ↔ 3 ; # ARABIC-INDIC DIGIT THREE 83٤ ↔ 4 ; # ARABIC-INDIC DIGIT FOUR 84٥ ↔ 5 ; # ARABIC-INDIC DIGIT FIVE 85٦ ↔ 6 ; # ARABIC-INDIC DIGIT SIX 86٧ ↔ 7 ; # ARABIC-INDIC DIGIT SEVEN 87٨ ↔ 8 ; # ARABIC-INDIC DIGIT EIGHT 88٩ ↔ 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 ت , كه , ته , and سه may be romanized t·h, k·h, 104# d·h, and s·h in order to differentiate those romanizations from the 105# digraphs th, kh, dh, and sh. 106# 107######################################################################## 108# 109 110ته → t·h ; # ARABIC LETTER TEH + HEH 111كه → k·h ; # ARABIC LETTER KAF + HEH 112ده → d·h ; # ARABIC LETTER DAL + HEH 113سه → s·h ; # 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 137بّ → bb ; # ARABIC LETTER BEH + SHADDA 138تّ → tt ; # ARABIC LETTER TEH + SHADDA 139ثّ → thth ; # ARABIC LETTER THEH + SHADDA 140جّ → jj ; # ARABIC LETTER JEEM + SHADDA 141حّ → ḥḥ ; # ARABIC LETTER HAH + SHADDA 142خّ → khkh ; # ARABIC LETTER KHAH + SHADDA 143دّ → dd ; # ARABIC LETTER DAL + SHADDA 144ذّ → dhdh ; # ARABIC LETTER THAL + SHADDA 145رّ → rr ; # ARABIC LETTER REH + SHADDA 146زّ → zz ; # ARABIC LETTER ZAIN + SHADDA 147سّ → ss ; # ARABIC LETTER SEEN + SHADDA 148شّ → shsh ; # ARABIC LETTER SHEEN + SHADDA 149صّ → ṣṣ ; # ARABIC LETTER SAD + SHADDA 150ضّ → ḍḍ ; # ARABIC LETTER DAD + SHADDA 151طّ → ṭṭ ; # ARABIC LETTER TAH + SHADDA 152ظّ → ẓẓ ; # ARABIC LETTER ZAH + SHADDA 153عّ → $ayin $ayin ; # ARABIC LETTER AIN + SHADDA 154غّ → ghgh ; # ARABIC LETTER GHAIN + SHADDA 155فّ → ff ; # ARABIC LETTER FEH + SHADDA 156قّ → qq ; # ARABIC LETTER QAF + SHADDA 157كّ → kk ; # ARABIC LETTER KAF + SHADDA 158لّ → ll ; # ARABIC LETTER LAM + SHADDA 159مّ → mm ; # ARABIC LETTER MEEM + SHADDA 160نّ → nn ; # ARABIC LETTER NOON + SHADDA 161هّ → hh ; # ARABIC LETTER HEH + SHADDA 162وّ → ww ; # ARABIC LETTER WAW + SHADDA 163ىّ → yy ; # ARABIC LETTER YEH + SHADDA 164# 165# 166######################################################################## 167# 168# End Rule 9 169# 170######################################################################## 171 172 173# 174######################################################################## 175# 176# Start of Transformations 177# 178######################################################################## 179# 180 181$wordBoundary{ء → ; # ARABIC LETTER HAMZA 182ء → $alef ; # ARABIC LETTER HAMZA 183$wordBoundary{ا → ; # ARABIC LETTER ALEF 184ٱ → $alef ; # ARABIC LETTER ALEF WASLA 185$wordBoundary{آ → ā ; # ARABIC LETTER ALEF WITH MADDA ABOVE 186آ → $alef ā ; # ARABIC LETTER ALEF WITH MADDA ABOVE 187ب → b ; # ARABIC LETTER BEH 188ت → t ; # ARABIC LETTER TEH 189ة → h ; # ARABIC LETTER TEH MARBUTA 190ث → th ; # ARABIC LETTER THEH 191ج → j ; # ARABIC LETTER JEEM 192ح → ḩ ; # ARABIC LETTER HAH 193خ → kh ; # ARABIC LETTER KHAH 194د → d ; # ARABIC LETTER DAL 195ذ → dh ; # ARABIC LETTER THAL 196ر → r ; # ARABIC LETTER REH 197ز → z ; # ARABIC LETTER ZAIN 198س → s ; # ARABIC LETTER SEEN 199ش → sh ; # ARABIC LETTER SHEEN 200ص → ş ; # ARABIC LETTER SAD 201ض → ḑ ; # ARABIC LETTER DAD 202ط → ţ ; # ARABIC LETTER TAH 203ظ → z̧ ; # ARABIC LETTER ZAH 204ع → $ayin ; # ARABIC LETTER AIN 205غ → gh ; # ARABIC LETTER GHAIN 206ف → f ; # ARABIC LETTER FEH 207ق → q ; # ARABIC LETTER QAF 208ک ↔ k $disambig ; # ARABIC LETTER KEHEH 209ك ↔ k ; # ARABIC LETTER KAF 210ل → l ; # ARABIC LETTER LAM 211م → m ; # ARABIC LETTER MEEM 212ن → n ; # ARABIC LETTER NOON 213ه → h ; # ARABIC LETTER HEH 214و → w ; # ARABIC LETTER WAW 215ى → y ; # ARABIC LETTER YEH 216 217َا → ā ; # ARABIC FATHA + ALEF 218َى → á ; # ARABIC FATHA + ALEF MAKSURA 219َيْ → ay ; # ARABIC FATHA + YEH + SUKUN 220َوْ → aw ; # ARABIC FATHA + WAW + SUKUN 221َ → a ; # ARABIC FATHA 222 223ِي → ī ; # ARABIC KASRA + YEH 224ِ → i ; # ARABIC KASRA 225 226ُو → ū ; # ARABIC DAMMA + WAW 227ُ → u ; # ARABIC DAMMA 228 229ْ → ; # ARABIC SUKUN 230ً → aⁿ ; # ARABIC FATHATAN 231ٍ → iⁿ ; # ARABIC KASRATAN 232ٌ → uⁿ ; # ARABIC DAMMATAN 233::NFC (NFD) ; 234 235# 236# 237######################################################################## 238 239 </tRule> 240 </transform> 241 </transforms> 242</supplementalData> 243