1# © 2016 and later: Unicode, Inc. and others. 2# License & terms of use: http://www.unicode.org/copyright.html 3# Generated using tools/cldr/cldr-to-icu/build-icu-data.xml 4# 5# File: ar_ar_Latn_BGN.txt 6# Generated from CLDR 7# 8 9# 10######################################################################## 11# BGN/PCGN 1956 System 12# 13# This system was adopted by the BGN in 1946 and by the PCGN 14# in 1956 and has been applied in the systematic romanization 15# of geographic names in Bahrain, Egypt, Iraq, Jordan, 16# Kuwait, Lebanon, Libya, Oman, Qatar, Saudi Arabia, Sudan, 17# Syria, Tunisia, the United Arab Emirates, and Yemen, all 18# of which has been covered by published BGN engineers. 19# 20# Originally prepared by Michael Everson <everson@evertype.com> 21######################################################################## 22# 23# MINIMAL FILTER: Arabic-Latin 24# 25:: [[:arabic:][:block=ARABIC:][ءآابةتثجحخدذرزسشصضطظعغفقكلمنهوىي\u064B\u064C\u064D\u064E\u064F\u0650\u0651\u0652٠١٢٣٤٥٦٧٨٩ٱ]] ; 26:: NFKD (NFC) ; 27# 28# 29######################################################################## 30# 31######################################################################## 32# 33# Define All Transformation Variables 34# 35######################################################################## 36# 37$alef = ’; 38$ayin = ‘; 39$disambig = \u0331 ; 40# 41# 42# Use this $wordBoundary until bug 2034 is fixed in ICU: 43# http://bugs.icu-project.org/cgi-bin/icu-bugs/transliterate?id=2034;expression=boundary;user=guest 44# 45$wordBoundary = [^[:L:][:M:][:N:]] ; 46# 47# 48######################################################################## 49# non-letters 50[:Nd:]{٫}[:Nd:] ↔ [:Nd:]{','}[:Nd:] ; # ARABIC DECIMAL SEPARATOR 51[:Nd:]{٬}[:Nd:] ↔ [:Nd:]{'.'}[:Nd:] ; # ARABIC THOUSANDS SEPARATOR 52٫ ↔ ',' $disambig ; # ARABIC DECIMAL SEPARATOR 53٬ ↔ '.' $disambig ; # ARABIC THOUSANDS SEPARATOR 54# ٭ ↔ ; # ARABIC FIVE POINTED STAR // no need to transliterate 55، ↔ ',' ; # ARABIC COMMA 56؛ ↔ ';' ; # ARABIC SEMICOLON 57؟ ↔ '?' ; # ARABIC QUESTION MARK 58٪ ↔ '%' ; # ARABIC PERCENT SIGN 59۰ ↔ 0 $disambig ; # EXTENDED ARABIC-INDIC DIGIT ZERO 60۱ ↔ 1 $disambig ; # EXTENDED ARABIC-INDIC DIGIT ONE 61۲ ↔ 2 $disambig ; # EXTENDED ARABIC-INDIC DIGIT TWO 62۳ ↔ 3 $disambig ; # EXTENDED ARABIC-INDIC DIGIT THREE 63۴ ↔ 4 $disambig ; # EXTENDED ARABIC-INDIC DIGIT FOUR 64۵ ↔ 5 $disambig ; # EXTENDED ARABIC-INDIC DIGIT FIVE 65۶ ↔ 6 $disambig ; # EXTENDED ARABIC-INDIC DIGIT SIX 66۷ ↔ 7 $disambig ; # EXTENDED ARABIC-INDIC DIGIT SEVEN 67۸ ↔ 8 $disambig ; # EXTENDED ARABIC-INDIC DIGIT EIGHT 68۹ ↔ 9 $disambig ; # EXTENDED ARABIC-INDIC DIGIT NINE 69٠ ↔ 0 ; # ARABIC-INDIC DIGIT ZERO 70١ ↔ 1 ; # ARABIC-INDIC DIGIT ONE 71٢ ↔ 2 ; # ARABIC-INDIC DIGIT TWO 72٣ ↔ 3 ; # ARABIC-INDIC DIGIT THREE 73٤ ↔ 4 ; # ARABIC-INDIC DIGIT FOUR 74٥ ↔ 5 ; # ARABIC-INDIC DIGIT FIVE 75٦ ↔ 6 ; # ARABIC-INDIC DIGIT SIX 76٧ ↔ 7 ; # ARABIC-INDIC DIGIT SEVEN 77٨ ↔ 8 ; # ARABIC-INDIC DIGIT EIGHT 78٩ ↔ 9 ; # ARABIC-INDIC DIGIT NINE 79# 80######################################################################## 81# 82# Rules moved to front to avoid masking 83# 84######################################################################## 85# 86######################################################################## 87# 88# BGN Page 8 Rule 5 89# 90# The character sequences ت , كه , ته , and سه may be romanized t·h, k·h, 91# d·h, and s·h in order to differentiate those romanizations from the 92# digraphs th, kh, dh, and sh. 93# 94######################################################################## 95# 96ته → t·h ; # ARABIC LETTER TEH + HEH 97كه → k·h ; # ARABIC LETTER KAF + HEH 98ده → d·h ; # ARABIC LETTER DAL + HEH 99سه → s·h ; # ARABIC LETTER SEEN + HEH 100# 101# 102######################################################################## 103# 104# End Rule 5 105# 106######################################################################## 107######################################################################## 108# 109# 110# BGN Page 8 Rule 9 111# 112# Doubles consonant sounds are represented in Arabic script by placing 113# a shaddah ( \u0651 ) over a consonant character. In romanization the letter 114# should be doubled. [The remainder of this rule deals with the definite 115# article and is lexical.] 116# 117######################################################################## 118# 119ب\u0651 → bb ; # ARABIC LETTER BEH + SHADDA 120ت\u0651 → tt ; # ARABIC LETTER TEH + SHADDA 121ث\u0651 → thth ; # ARABIC LETTER THEH + SHADDA 122ج\u0651 → jj ; # ARABIC LETTER JEEM + SHADDA 123ح\u0651 → ḥḥ ; # ARABIC LETTER HAH + SHADDA 124خ\u0651 → khkh ; # ARABIC LETTER KHAH + SHADDA 125د\u0651 → dd ; # ARABIC LETTER DAL + SHADDA 126ذ\u0651 → dhdh ; # ARABIC LETTER THAL + SHADDA 127ر\u0651 → rr ; # ARABIC LETTER REH + SHADDA 128ز\u0651 → zz ; # ARABIC LETTER ZAIN + SHADDA 129س\u0651 → ss ; # ARABIC LETTER SEEN + SHADDA 130ش\u0651 → shsh ; # ARABIC LETTER SHEEN + SHADDA 131ص\u0651 → ṣṣ ; # ARABIC LETTER SAD + SHADDA 132ض\u0651 → ḍḍ ; # ARABIC LETTER DAD + SHADDA 133ط\u0651 → ṭṭ ; # ARABIC LETTER TAH + SHADDA 134ظ\u0651 → ẓẓ ; # ARABIC LETTER ZAH + SHADDA 135ع\u0651 → $ayin $ayin ; # ARABIC LETTER AIN + SHADDA 136غ\u0651 → ghgh ; # ARABIC LETTER GHAIN + SHADDA 137ف\u0651 → ff ; # ARABIC LETTER FEH + SHADDA 138ق\u0651 → qq ; # ARABIC LETTER QAF + SHADDA 139ك\u0651 → kk ; # ARABIC LETTER KAF + SHADDA 140ل\u0651 → ll ; # ARABIC LETTER LAM + SHADDA 141م\u0651 → mm ; # ARABIC LETTER MEEM + SHADDA 142ن\u0651 → nn ; # ARABIC LETTER NOON + SHADDA 143ه\u0651 → hh ; # ARABIC LETTER HEH + SHADDA 144و\u0651 → ww ; # ARABIC LETTER WAW + SHADDA 145ى\u0651 → yy ; # ARABIC LETTER YEH + SHADDA 146# 147# 148######################################################################## 149# 150# End Rule 9 151# 152######################################################################## 153# 154######################################################################## 155# 156# Start of Transformations 157# 158######################################################################## 159# 160$wordBoundary{ء → ; # ARABIC LETTER HAMZA 161ء → $alef ; # ARABIC LETTER HAMZA 162$wordBoundary{ا → ; # ARABIC LETTER ALEF 163ٱ → $alef ; # ARABIC LETTER ALEF WASLA 164$wordBoundary{آ → ā ; # ARABIC LETTER ALEF WITH MADDA ABOVE 165آ → $alef ā ; # ARABIC LETTER ALEF WITH MADDA ABOVE 166ب → b ; # ARABIC LETTER BEH 167ت → t ; # ARABIC LETTER TEH 168ة → h ; # ARABIC LETTER TEH MARBUTA 169ث → th ; # ARABIC LETTER THEH 170ج → j ; # ARABIC LETTER JEEM 171ح → ḩ ; # ARABIC LETTER HAH 172خ → kh ; # ARABIC LETTER KHAH 173د → d ; # ARABIC LETTER DAL 174ذ → dh ; # ARABIC LETTER THAL 175ر → r ; # ARABIC LETTER REH 176ز → z ; # ARABIC LETTER ZAIN 177س → s ; # ARABIC LETTER SEEN 178ش → sh ; # ARABIC LETTER SHEEN 179ص → ş ; # ARABIC LETTER SAD 180ض → ḑ ; # ARABIC LETTER DAD 181ط → ţ ; # ARABIC LETTER TAH 182ظ → z\u0327 ; # ARABIC LETTER ZAH 183ع → $ayin ; # ARABIC LETTER AIN 184غ → gh ; # ARABIC LETTER GHAIN 185ف → f ; # ARABIC LETTER FEH 186ق → q ; # ARABIC LETTER QAF 187ک ↔ k $disambig ; # ARABIC LETTER KEHEH 188ك ↔ k ; # ARABIC LETTER KAF 189ل → l ; # ARABIC LETTER LAM 190م → m ; # ARABIC LETTER MEEM 191ن → n ; # ARABIC LETTER NOON 192ه → h ; # ARABIC LETTER HEH 193و → w ; # ARABIC LETTER WAW 194ى → y ; # ARABIC LETTER YEH 195\u064Eا → ā ; # ARABIC FATHA + ALEF 196\u064Eى → á ; # ARABIC FATHA + ALEF MAKSURA 197\u064Eي\u0652 → ay ; # ARABIC FATHA + YEH + SUKUN 198\u064Eو\u0652 → aw ; # ARABIC FATHA + WAW + SUKUN 199\u064E → a ; # ARABIC FATHA 200\u0650ي → ī ; # ARABIC KASRA + YEH 201\u0650 → i ; # ARABIC KASRA 202\u064Fو → ū ; # ARABIC DAMMA + WAW 203\u064F → u ; # ARABIC DAMMA 204\u0652 → ; # ARABIC SUKUN 205\u064B → aⁿ ; # ARABIC FATHATAN 206\u064D → iⁿ ; # ARABIC KASRATAN 207\u064C → uⁿ ; # ARABIC DAMMATAN 208::NFC (NFD) ; 209# 210# 211######################################################################## 212 213