1<?xml version="1.0" encoding="UTF-8" ?> 2<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd"> 3<!-- 4Copyright © 1991-2016 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: 12352 $"/> 10 <transforms> 11 <transform source="und_FONIPA" target="fa" direction="forward" alias="fa-t-und-fonipa"> 12 <tRule><![CDATA[ 13# Vowels 14# ------ 15# In these rules, we produce ی و ا both for short and for long vowels. 16# This would be wrong for writing Farsi or Arabic, but when transliterating 17# foreign words and names, it is strongly preferred to vowel marks. 18# Short schwa [ə] and a few other, schwa-like vowels get omitted entirely 19# unless at the end of the word, in which case we emit ه whose Farsi 20# word-final pronunciation comes close to [ə]. At the beginning of words, 21# Farsi speakers prefer to see آ for [ɑ] and a few other similar-sounding 22# dark vowels; note that this use of آ is quite different from Arabic. 23 24$IVowel = [i ɪ e {e̞}]; 25$UVowel = [y {ɨ} {ʉ} ɯ u ʏ {ɪ̈} {ʊ̈} {ɯ̽} {ʊ} ø ɤ o {ø̞} {ɤ̞} {o̞} ɔ w {w̥} ʍ ʷ]; 26$AVowel = [ɛ œ ɜ æ ɶ]; 27$DarkAVowel = [ʌ a ɑ ɒ ɐ ɞ {ä} {ɒ̈}]; # آ instead of ا at beginning of words 28$SchwaVowel = [ɘ ɵ ə {ɵ̞}]; 29$Click = [ʘ ɋ ǀ ʇ ǃ ʗ ǂ ʄ ǁ ʖ]; 30$Boundary = [^[:L:][:M:][:N:]]; 31 32::NFD; 33[ʰ ʱ ʼ ̃ ̰ ̋ ́ ̄ ̀ ̏ ̌ ̂ ˥ ˦ ˧ ˨ ˩ ꜜ ꜛ ↗ ↘ ͡ ͜ ̯] → ; 34ʲ → j; 35ᵐ → m; 36ⁿ → n; 37ᵑ → ŋ; 38::NFC; 39 40# TODO: Diphthongs probably need more work. 41 42# Romanian [sekujesk] → [sekujask], for emitting سیکویاسک not سیکویسک 43$UVowel [j $IVowel] [e {e̞} $SchwaVowel] → uia; 44 45# Kazakh Аягөз [ɑjɑɡy̯ʉz] → [ɑjɑɡiuz], to emit آیاگیوز not آیاگووز 46yʉ → iu; 47 48::NULL; 49 50# Vowels 51$Boundary {$SchwaVowel ː?} → ای; 52$SchwaVowel ː → ی; 53{[$SchwaVowel e {e̞}]} [^[:L:][:M:][:N:][\.]] → ه; 54$SchwaVowel → ; 55 56$Boundary {$IVowel ː?} → ای; 57$IVowel ː? j? → ی; 58 59$Boundary {$UVowel ː?} → او; 60$UVowel ː? → و; 61 62$Boundary {$AVowel ː?} → ا; 63$AVowel ː? → ا; 64 65$Boundary {$DarkAVowel ː?} → آ; 66$DarkAVowel ː? → ا; 67 68# Shadda for long (geminated) consonants 69ː → ّ; 70 71# Affricates 72[{t͡ʃ} ʧ] → چ; 73 74# Clicks 75[ɡ g ɠ k] $Click → کچ; 76[n ɲ]? $Click → نچ; 77 78# Nasal stops 79[{m̥} m ɱ] → م; 80[{n̼̊} {n̼} {n̥} n {ɳ̊} ɳ {ɲ̊} {ɲ̥} ɲ] → ن; 81[{ŋ̊} ŋ {ɴ̥} ɴ] k → نک; 82[{ŋ̊} ŋ {ɴ̥} ɴ] [ɡ g]? → نگ; 83 84# Non-nasal stops 85[p {p̪}] → پ; 86[b {b̪} ɓ] → ب; 87[{d̼} d ɗ ᶑ] → د; 88[{t̼} t] → ت; 89[ʈ] → ط; 90[ɖ] → ض; 91c → چ; 92ɟ → دج; 93k → ک; 94[ɡ g ɠ] → گ; 95[q ɢ ʡ ʛ] → ق; 96ʔ → ; 97 98# Sibilant fricatives 99s → س; 100z → ز; 101[ʃ ʂ ɕ ʄ] → ش; 102[ʒ ʐ ʑ] → ژ; 103 104# Non-sibilant fricatives 105[ɸ f] → ف; 106[β v] → و; 107[{θ̼} θ {θ̱}] → ث; 108[{ð̼} ð {ð̠}] → ذ; 109ç → ش; 110ʝ $IVowel? ː? → ی; 111[x χ] → خ; 112[ɣ ʁ] → غ; 113ħ → ح; 114ʕ → ع; 115[h ɦ {ʔ̞}] → ه; 116 117# Approximants, trills, flaps 118ʋ → و; 119ʙ → بر; 120{r̝} → رژ; 121[{ɹ̥} {ɹ} {ɻ̊} {ɻ} {ɾ̥} ɾ {ɽ̊} ɽ {r̼} {r̥} r] → ر; 122[{ʀ̥} ʀ] → غ; 123ʜ → ح; 124ʢ → ع; 125j $IVowel? ː? → ی; 126 127# Laterals 128ɬ → شل; 129ɮ → ژل; 130{[{ʎ̥} ʎ]} [^ $IVowel j ʝ] → لی; 131[{l̼} {l̥} l {ɭ̊} ɭ {ʎ̥} ʎ] → ل; 132[ʟ {ʟ̠}] → غ; 133 134# Independent pass for misc cleanup. 135::NULL; 136 137# Strip off syllable markers 138\. → ; 139 140# Sequences of three or more ووو look very confusing; we shorten them. 141# Polish Darłowo [darwɔvɔ] → داروو → داروووو 142ووو+ → وو; 143 144 ]]></tRule> 145 </transform> 146 </transforms> 147</supplementalData> 148