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: und_FONIPA_ar.txt 6# Generated from CLDR 7# 8 9# Vowels 10# ------ 11# In these rules, we produce ي و ا both for short and for long vowels. 12# This would be wrong for writing Arabic, but when transliterating 13# foreign words and names, it is strongly preferred to vowel marks. 14# However, we emit short schwa [ə] and a few other, schwa-like vowels. 15$IVowel = [i ɪ e {e\u031E}]; 16$UVowel = [y {ɨ} {ʉ} ɯ u ʏ {ɪ\u0308} {ʊ\u0308} {ɯ\u033D} {ʊ} ø ɤ o {ø\u031E} {ɤ\u031E} {o\u031E} ɞ ɔ w {w\u0325} ʍ ʷ]; 17$AVowel = [ɛ œ ɜ ʌ æ ɐ a ɶ {ä} {ɒ\u0308} ɑ ɒ]; 18$SchwaVowel = [ɘ ɵ ə {ɵ\u031E}]; 19$Vowel = [$IVowel $UVowel $AVowel $SchwaVowel]; 20$Click = [ʘ ɋ ǀ ʇ ǃ ʗ ǂ ʄ ǁ ʖ]; 21$Boundary = [^[:L:][:M:][:N:]]; 22::NFD; 23[ʰ ʱ ʼ \u0303 \u0330 \u030B \u0301 \u0304 \u0300 \u030F \u030C \u0302 ˥ ˦ ˧ ˨ ˩ ꜜ ꜛ ↗ ↘ \u0361 \u035C \u032F] → ; 24ʲ → j; 25ᵐ → m; 26ⁿ → n; 27ᵑ → ŋ; 28::NFC; 29# TODO: Diphthongs probably need more work. 30# Romanian [sekujesk] → [sekujask], for emitting سيكوياسك not سيكويسك 31$UVowel [j $IVowel] [e {e\u031E} $SchwaVowel] → uia; 32# Kazakh Аягөз [ɑjɑɡy\u032Fʉz] → [ɑjɑɡiuz], to emit TODO 33yʉ → iu; 34::NULL; 35# Vowels 36$Boundary {ʔ? $IVowel ː} → إ\u0650ي; 37$Boundary {ʔ? $IVowel} → إ\u0650; 38{$IVowel ʔ} $Boundary → ئ; 39{$IVowel ː ʔ} $Boundary → يء; 40{$IVowel ː ʔ} [$Vowel] → ئ; 41$IVowel ː? → ي; 42$Boundary {ʔ? $UVowel ː} → أو; 43$Boundary {ʔ? $UVowel} → أ; 44{$UVowel ʔ} $Boundary → ؤ; 45{$UVowel ː ʔ} $Boundary → وء; 46$UVowel ː? → و; 47$Boundary {ʔ? $AVowel ː} → آ; 48$Boundary {ʔ? $AVowel} → أ; 49{$AVowel ʔ} $Boundary → أ; 50{$AVowel ː ʔ} $Boundary → اء; 51$AVowel ː? ʔ $AVowel ː? → اءا; 52$AVowel ː? → ا; 53$Boundary {ʔ? $SchwaVowel ː} → إ\u0650ي; 54$Boundary {ʔ? $SchwaVowel} → أ; 55$SchwaVowel ː → ي; 56$SchwaVowel → ; 57# TODO: Handle glottal stop. 58ʔ → ; 59# Shadda for long (geminated) consonants 60ː → \u0651; 61# Affricates 62[{t\u0361ʃ} ʧ] → ت\u0652ش; 63# Clicks 64[ɡ g ɠ k] $Click → ك\u0652ش; 65$Click → ت\u0652ش; 66# Nasal stops 67[{m\u0325} m ɱ] → م; 68[{n\u033C\u030A} {n\u033C} {n\u0325} n {ɳ\u030A} ɳ {ɲ\u030A} {ɲ\u0325} ɲ] → ن; 69[{ŋ\u030A} ŋ {ɴ\u0325} ɴ] k → نك; 70[{ŋ\u030A} ŋ {ɴ\u0325} ɴ] [ɡ g ɠ]? → ن\u0652غ; 71# Non-nasal stops 72[p b {p\u032A} {b\u032A} ɓ] → ب; 73[{d\u033C} d ɗ ᶑ] → د; 74[{t\u033C} t] → ت; 75[ʈ] → ط; 76[ɖ] → ض; 77c → ت\u0652ش; 78ɟ → دج; 79k → ك; 80[ɡ g ɠ] → غ; 81[q ɢ ʡ ʛ] → ق; 82# Sibilant fricatives 83s → س; 84z → ز; 85[ʃ ʂ ɕ ʄ] → ش; 86[ʒ ʐ ʑ] → ج; 87# Non-sibilant fricatives 88[ɸ f v] → ف; 89β → ب; 90[{θ\u033C} θ {θ\u0331}] → ث; 91[{ð\u033C} ð {ð\u0320}] → ذ; 92ç → ش; 93ʝ $IVowel? ː? → ي; 94[x χ] → خ; 95[ɣ ʁ] → غ; 96ħ → ح; 97ʕ → ع; 98[h ɦ {ʔ\u031E}] → ه; 99# Approximants, trills, flaps 100ʋ → و; 101ʙ → بر; 102{r\u031D} → رش; 103[{ɹ\u0325} {ɹ} {ɻ\u030A} {ɻ} {ɾ\u0325} ɾ {ɽ\u030A} ɽ {r\u033C} {r\u0325} r] → ر; 104[{ʀ\u0325} ʀ] → غ; 105ʜ → ح; 106ʢ → ع; 107j $IVowel? ː? → ي; 108# Laterals 109ɬ → ش\u0652ل; 110ɮ → ج\u0652ل; 111{[{ʎ\u0325} ʎ]} [^ $IVowel j ʝ] → لي; 112[{l\u033C} {l\u0325} l {ɭ\u030A} ɭ {ʎ\u0325} ʎ] → ل; 113[ʟ {ʟ\u0320}] → غ; 114# Independent pass for misc cleanup. 115::NULL; 116# Strip off syllable markers 117\. → ; 118# Sequences of three or more ووو look very confusing; we shorten them. 119# Polish Darłowo [darwɔvɔ] → داروو → داروووو 120ووو+ → وو; 121 122