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: Grek_Latn_UNGEGN.txt 6# Generated from CLDR 7# 8 9# For modern Greek, based on UNGEGN rules. 10# Rules are predicated on running NFD first, and NFC afterwards 11# MINIMAL FILTER GENERATED FOR: Greek-Latin/UNGEGN 12# WARNING: need to add accents to both filters ### 13# :: [\u0301\u0304\u0306\u0308;µ·ÀÂÈÊÌÎÒÔÙÛàâèêìîòôùûĈ-ĉĜ-ĝĤ-ĥĴ-ĵŜ-ŝŴ-ŷǛ-ǜǸ-ǹ\u0300\u0302\u0313-\u0314\u0340\u0342-\u0343\u0345ͺ;Ά-ΊΌΎ-ΡΣ-ώϐ-ϖϰ-ϵЀЍѐѝḔ-ḕṐ-ṑẀ-ẁẐ-ẑẤ-ậẰ-ằẾ-ệỐ-ộỜ-ờỪ-ừỲ-ỳἀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ᾼι῁-ῄῆ-῍῏-ΐῖ-Ί῝῟-῭ῲ-ῴῶ-ῼΩϷ-\u07FBϹ] ; 14:: [[[:Greek:][:Mn:][:Me:]] [\:-;?·;·]] ; 15::NFD (NFC) ; 16# Useful variables 17$lower = [[:latin:][:greek:] & [:Ll:]] ; 18$upper = [[:latin:][:greek:] & [:Lu:]] ; 19$accent = [[:Mn:][:Me:]] ; 20$macron = \u0304 ; 21$ddot = \u0308 ; 22$lcgvowel = [αεηιουω] ; 23$ucgvowel = [ΑΕΗΙΟΥΩ] ; 24$gvowel = [$lcgvowel $ucgvowel] ; 25$lcgvowelC = [$lcgvowel $accent] ; 26$evowel = [aeiouyAEIOUY]; 27$vowel = [ $evowel $gvowel] ; 28$beforeLower = $accent * $lower ; 29$gammaLike = [ΓΚΞΧγκξχϰ] ; 30$egammaLike = [GKXCgkxc] ; 31$smooth = \u0313 ; 32$rough = \u0314 ; 33$iotasub = \u0345 ; 34$softener = [βΒγΓδΔζΖλΛμΜνΝρΡ$gvowel] ; 35$under = \u0331; 36$caron = \u030C; 37$afterLetter = [:L:] [\'$accent]* ; 38$beforeLetter = [\'$accent]* [:L:] ; 39# Fix punctuation 40# preserve original 41\: ↔ \: $under ; 42\? ↔ \? $under ; 43\; ↔ \? ; 44· ↔ \: ; 45# Fix any ancient characters that creep in 46\u0342 → \u0301 ; 47\u0302 → \u0301 ; 48\u0300 → \u0301 ; 49$smooth → ; 50$rough → ; 51$iotasub → ; 52ͺ → ; 53# need to have these up here so the rules don't mask 54η ↔ i $under ; 55Η ↔ I $under ; 56Ψ } $beforeLower ↔ Ps ; 57Ψ ↔ PS ; 58ψ ↔ ps ; 59ω ↔ o $under ; 60Ω ↔ O $under; 61# at begining or end of word, convert mp to b 62[^[:L:]$accent] { μπ → b ; 63μπ } [^[:L:]$accent] → b ; 64[^[:L:]$accent] { [Μμ][Ππ] → B ; 65[Μμ][Ππ] } [^[:L:]$accent] → B ; 66μπ ← b ; 67Μπ ← B } $beforeLower ; 68ΜΠ ← B ; 69# handle diphthongs ending with upsilon 70ου ↔ ou ; 71ΟΥ ↔ OU ; 72Ου ↔ Ou ; 73οΥ ↔ oU ; 74$fmaker = [aeiAEI] $under ? ; 75$shiftForwardVowels = [[:Mn:]-[\u0308]]; # note: a diaeresis keeps the items separate 76$fmaker { υ ( $shiftForwardVowels )* } $softener → $1 v $under ; 77υ $1 ← ( $shiftForwardVowels )* v $under ; 78$fmaker { υ ( $shiftForwardVowels )* } → $1 f $under; 79υ $1 ← ( $shiftForwardVowels )* f $under ; 80$fmaker { Υ } $softener ↔ V $under ; 81$fmaker { Υ ↔ U $under ; 82υ ↔ y ; 83Υ ↔ Y ; 84# NORMAL 85α ↔ a ; 86Α ↔ A ; 87β ↔ v ; 88Β ↔ V ; 89γ } $gammaLike ↔ n } $egammaLike ; 90γ ↔ g ; 91Γ } $gammaLike ↔ N } $egammaLike ; 92Γ ↔ G ; 93δ ↔ d ; 94Δ ↔ D ; 95ε ↔ e ; 96Ε ↔ E ; 97ζ ↔ z ; 98Ζ ↔ Z ; 99θ ↔ th ; 100Θ } $beforeLower ↔ Th ; 101Θ ↔ TH ; 102ι ↔ i ; 103Ι ↔ I ; 104κ ↔ k ; 105Κ ↔ K ; 106λ ↔ l ; 107Λ ↔ L ; 108μ ↔ m ; 109Μ ↔ M ; 110ν } $gammaLike → n\' ; 111ν ↔ n ; 112Ν } $gammaLike ↔ N\' ; 113Ν ↔ N ; 114ξ ↔ x ; 115Ξ ↔ X ; 116ο ↔ o ; 117Ο ↔ O ; 118π ↔ p ; 119Π ↔ P ; 120ρ ↔ r ; 121Ρ ↔ R ; 122# insert separator before things that turn into s 123[Pp] { } [ςσΣϷϸϺϻ] → \' ; 124# special S variants 125Ϸ ↔ S\u030C ; # Ϸ GREEK CAPITAL LETTER SHO Uppercase_Letter Grek - L 126ϸ ↔ s\u030C ; #ϸ GREEK SMALL LETTER SHO Lowercase_Letter Grek - L 127Ϻ ↔ S\u0302 ; # Ϻ GREEK CAPITAL LETTER SAN Uppercase_Letter Grek - L 128ϻ ↔ s\u0302 ; # ϻ GREEK SMALL LETTER SAN Lowercase_Letter Grek - L 129# Caron means exception 130# before a letter, initial 131ς } $beforeLetter ↔ s $under } $beforeLetter; 132σ } $beforeLetter ↔ s } $beforeLetter; 133# otherwise, after a letter = final 134$afterLetter { σ ↔ $afterLetter { s $under; 135$afterLetter { ς ↔ $afterLetter { s ; 136# otherwise (isolated) = initial 137ς ↔ s $under; 138σ ↔ s ; 139# [Pp] { Σ ↔ \'S ; 140Σ ↔ S ; 141τ ↔ t ; 142Τ ↔ T ; 143φ ↔ f ; 144Φ ↔ F ; 145χ ↔ ch ; 146Χ } $beforeLower ↔ Ch ; 147Χ ↔ CH ; 148# Completeness for ASCII 149# $ignore = [[:Mark:]''] * ; 150| ch ← h ; 151| k ← c ; 152| i ← j ; 153| k ← q ; 154| b ← u } $vowel ; 155| b ← w } $vowel ; 156| y ← u ; 157| y ← w ; 158| Ch ← H ; 159| K ← C ; 160| I ← J ; 161| K ← Q ; 162| B ← W } $vowel ; 163| B ← U } $vowel ; 164| Y ← W ; 165| Y ← U ; 166# Completeness for Greek 167ϐ → | β ; 168ϑ → | θ ; 169ϒ → | Υ ; 170ϕ → | φ ; 171ϖ → | π ; 172ϰ → | κ ; 173ϱ → | ρ ; 174ϲ → | σ ; 175Ϲ → | Σ; #U+03F9 GREEK CAPITAL LUNATE SIGMA SYMBOL 176ϳ → j ; 177ϴ → | Θ ; 178ϵ → | ε ; 179µ → | μ ; 180# delete any trailing ' marks used for roundtripping 181← [Ππ] { \' } [Ss] ; 182← [Νν] { \' } $egammaLike ; 183::NFC (NFD) ; 184# MINIMAL FILTER GENERATED FOR: Latin-Greek/UNGEGN BACKWARD 185:: ([[[:Latin:][:Mn:][:Me:]] ['\:?]]) ; 186 187