icuSources/data/translit/Grek_Latn.txt

   1 # © 2016 and later: Unicode, Inc. and others.
   2 # License & terms of use: http://www.unicode.org/copyright.html#License
   3 #
   4 # File: Grek_Latn.txt
   5 # Generated from CLDR
   6 #
   7
   8 # Rules are predicated on running NFD first, and NFC afterwards
   9 # :: [\u0000-\u007F \u0370-Ͽ [:Greek:] [:nonspacing mark:]] ;
  10 # MINIMAL FILTER GENERATED FOR: Greek-Latin
  11 :: [;µ·ÄËÏÖÜäëïöüÿ-āĒ-ēĪ-īŌ-ōŪ-ūŸǕ-ǜǞ-ǣǬ-ǭȪ-ȭȰ-ȳ\u0304\u0308\u0313-\u0314\u0342-\u0345ͺ;Ά-ΊΌΎ-ΡΣ-ώϐ-ϗϛϝϟϡϣϥϧϩϫϭϯ-ϵϷ-\u07FBЁЇёїӒ-ӓӚ-ӟӢ-ӧӪ-ӱӴ-ӵӸ-ӹḔ-ḗḠ-ḡḦ-ḧḮ-ḯḸ-ḹṎ-ṓṜ-ṝṺ-ṻẄ-ẅẌ-ẍẗἀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ᾼι῁-ῄῆ-ῌ῏-ΐῖ-Ί῟-Ῥῲ-ῴῶ-ῼΩϹ] ;
  12 :: NFD (NFC) ;
  13 # TEST CASES
  14 # Ὀλίγοι ἔμφονες πολλῶν ἀφρόνων φοβερώτεροι — Πλάτωνος
  15 # ᾂ ᾒ ᾢ ᾃ ᾓ ᾣ
  16 # ᾳ ῃ ῳ ὃ ὄ
  17 # ὠς ὡς ὢς ὣς
  18 # Ὠς Ὡς Ὢς Ὣς
  19 # ὨΣ ὩΣ ὪΣ ὫΣ
  20 # Ạ, ạ, Ẹ, ẹ, Ọ, ọ
  21 # Useful variables
  22 $lower = [[:latin:][:greek:] & [:Ll:]];
  23 $glower = [[:greek:] & [:Ll:]];
  24 $upper = [[:latin:][:greek:] & [:Lu:]] ;
  25 $accent = [:M:] ;
  26 # NOTE: restrict to just the Greek & Latin accents that we care about
  27 # TODO: broaden out once interation is fixed
  28 $accentMinus = [ [\u0300-\u0345] & [:M:] - [\u0338]] ;
  29 $macron = \u0304 ;
  30 $ddot = \u0308 ;
  31 $ddotmac = [$ddot$macron];
  32 $lcgvowel = [αεηιουω] ;
  33 $ucgvowel = [ΑΕΗΙΟΥΩ] ;
  34 $gvowel = [$lcgvowel $ucgvowel] ;
  35 $lcgvowelC = [$lcgvowel $accent] ;
  36 $evowel = [aeiouyAEIOUY];
  37 $evowel2 = [iuyIUY];
  38 $vowel = [ $evowel $gvowel] ;
  39 $gammaLike = [ΓΚΞΧγκξχϰ] ;
  40 $egammaLike = [GKXCgkxc] ;
  41 $smooth = \u0313 ;
  42 $rough = \u0314 ;
  43 $iotasub = \u0345 ;
  44 $evowel_i = [$evowel-[iI]] ;
  45 $evowel2_i = [uyUY];
  46 $underbar = \u0331;
  47 $afterLetter = [:L:] [[:M:]\']* ;
  48 $beforeLetter = [[:M:]\']* [:L:] ;
  49 $beforeLower = $accent * $lower ;
  50 $notLetter = [^[:L:][:M:]] ;
  51 $under = \u0331;
  52 # Fix punctuation
  53 # preserve original
  54 \: ↔ \: $under ;
  55 \? ↔ \? $under ;
  56 \; ↔ \? ;
  57 · ↔ \: ;
  58 # CIRCUMFLEX: convert greek circumflex to normal one. Could use tilde or inverted breve
  59 \u0342 ↔ \u0302 ;
  60 # IOTA: convert iota subscript to iota
  61 # first make previous alpha long!
  62 $accent_minus = [[$accent]-[$iotasub$macron]];
  63 Α } $accent_minus * $iotasub → | Α $macron ;
  64 α } $accent_minus * $iotasub → | α $macron ;
  65 # now convert to uppercase if after uppercase, ow to lowercase
  66 $upper $accent * { $iotasub → I ;
  67 $iotasub → i ;
  68 | $1 $iotasub ← ($evowel $macron $accentMinus *) i ;
  69 | $1 $iotasub ← ($evowel $macron $accentMinus *) I ;
  70 # BREATHING
  71 # Convert rough breathing to h, and move before letters.
  72 # Make A ` x = → H a x
  73 Α ($macron?) $rough } $beforeLower → H | α $1;
  74 Ε $rough } $beforeLower → H | ε;
  75 Η $rough } $beforeLower → H | η ;
  76 Ι ($ddot?) $rough } $beforeLower → H | ι  $1;
  77 Ο $rough } $beforeLower → H | ο ;
  78 Υ $rough } $beforeLower → H | υ ;
  79 Ω ($ddot?) $rough } $beforeLower → H | ω $1;
  80 # Make A x ` = → H a x
  81 Α ($glower $macron?) $rough → H | α $1 ;
  82 Ε ($glower) $rough → H | ε $1 ;
  83 Η ($glower) $rough → H | η $1 ;
  84 Ι ($glower $ddot?) $rough → H | ι $1 ;
  85 Ο ($glower) $rough → H | ο $1 ;
  86 Υ ($glower) $rough → H | υ $1 ;
  87 Ω ($glower  $ddot?) $rough → H | ω $1 ;
  88 #Otherwise, make x ` into h x and X ` into H X
  89 ($lcgvowel + $ddotmac? ) $rough → h | $1 ;
  90 ($gvowel + $ddotmac? ) $rough → H | $1 ;
  91 # Go backwards with H
  92 | $1 $rough ← h ($evowel $macron $ddot? $evowel2_i $macron?) ;
  93 | $1 $rough ← h ($evowel $ddot? $evowel2 $macron?) ;
  94 | $1 $rough ← h ($evowel $macron? $ddot?) ;
  95 | $1 $rough ← H ([AEIOUY] $macron $ddot? $evowel2_i $macron?) ;
  96 | $1 $rough ← H ([AEIOUY] $ddot? $evowel2 $macron?) ;
  97 | $1 $rough ← H ([AEIOUY] $macron? $ddot?) ;
  98 # titlecase, have to fix individually
  99 # in the future, we should add &uppercase() to make this easier
 100 | A $1 $rough ← H a ($macron  $ddot? $evowel2_i $macron?) ;
 101 | E $1 $rough ← H e ($macron  $ddot? $evowel2_i $macron?) ;
 102 | I $1 $rough ← H i ($macron  $ddot? $evowel2_i $macron?) ;
 103 | O $1 $rough ← H o ($macron  $ddot? $evowel2_i $macron?) ;
 104 | U $1 $rough ← H u ($macron $ddot? $evowel2_i $macron?) ;
 105 | Y $1 $rough ← H y ($macron $ddot? $evowel2_i $macron?) ;
 106 | A $1 $rough ← H a ($ddot? $evowel2 $macron?) ;
 107 | E $1 $rough ← H e ($ddot? $evowel2 $macron?) ;
 108 | I $1 $rough ← H i ($ddot? $evowel2 $macron?) ;
 109 | O $1 $rough ← H o ($ddot? $evowel2 $macron?) ;
 110 | U $1 $rough ← H u ($ddot? $evowel2 $macron?) ;
 111 | Y $1 $rough ← H y ($ddot? $evowel2 $macron?) ;
 112 | A $1 $rough ← H a ($macron? $ddot? ) ;
 113 | E $1 $rough ← H e ($macron? $ddot? ) ;
 114 | I $1 $rough ← H i ($macron? $ddot? ) ;
 115 | O $1 $rough ← H o ($macron? $ddot? ) ;
 116 | U $1 $rough ← H u ($macron? $ddot? ) ;
 117 | Y $1 $rough ← H y ($macron? $ddot? ) ;
 118 # Now do smooth
 119 #delete smooth breathing for Latin
 120 $smooth → ;
 121 # insert in Greek
 122 # the assumption is that all Marks are on letters.
 123 | $1 $smooth ← $notLetter { ([rR]) } [^hH$smooth$rough] ;
 124 | $1 $smooth ← $notLetter { ($evowel $macron? $evowel2 $macron?) } [^$smooth$rough] ;
 125 | $1 $smooth ← $notLetter { ($evowel $macron?) } [^$evowel2$smooth$rough] ;
 126 # TODO: preserve smooth/rough breathing if not
 127 # on initial vowel sequence
 128 # need to have these up here so the rules don't mask
 129 # remove now superfluous macron when returning
 130 Α ← A $macron ;
 131 α ← a $macron ;
 132 η ↔ e $macron ;
 133 Η ↔ E $macron ;
 134 φ ↔ ph ;
 135 Ψ } $beforeLower ↔ Ps ;
 136 Ψ ↔ PS ;
 137 Φ } $beforeLower ↔ Ph ;
 138 Φ ↔ PH ;
 139 ψ ↔ ps ;
 140 ω ↔ o $macron ;
 141 Ω ↔  O $macron;
 142 # NORMAL
 143 α ↔ a ;
 144 Α ↔ A ;
 145 β ↔ b ;
 146 Β ↔ B ;
 147 γ } $gammaLike ↔ n } $egammaLike ;
 148 γ ↔ g ;
 149 Γ } $gammaLike ↔ N } $egammaLike ;
 150 Γ ↔ G ;
 151 δ ↔ d ;
 152 Δ ↔ D ;
 153 ε ↔ e ;
 154 Ε ↔ E ;
 155 ζ ↔ z ;
 156 Ζ ↔ Z ;
 157 θ ↔ th ;
 158 Θ } $beforeLower ↔ Th ;
 159 Θ ↔ TH ;
 160 ι ↔ i ;
 161 Ι ↔ I ;
 162 κ ↔ k ;
 163 Κ ↔ K ;
 164 λ ↔ l ;
 165 Λ ↔ L ;
 166 μ ↔ m ;
 167 Μ ↔ M ;
 168 ν } $gammaLike → n\' ;
 169 ν ↔ n ;
 170 Ν } $gammaLike ↔ N\' ;
 171 Ν ↔ N ;
 172 ξ ↔ x ;
 173 Ξ ↔ X ;
 174 ο ↔ o ;
 175 Ο ↔ O ;
 176 π ↔ p ;
 177 Π ↔ P ;
 178 ρ $rough ↔ rh;
 179 Ρ $rough } $beforeLower ↔ Rh ;
 180 Ρ $rough ↔ RH ;
 181 ρ ↔ r ;
 182 Ρ ↔ R ;
 183 # insert separator before things that turn into s
 184 [Pp] { } [ςσΣϷϸϺϻ] → \' ;
 185 # special S variants
 186 Ϸ ↔ S\u030C ; # Ϸ GREEK CAPITAL LETTER SHO Uppercase_Letter Grek - L
 187 ϸ ↔ s\u030C ; #ϸ GREEK SMALL LETTER SHO Lowercase_Letter Grek - L
 188 Ϻ ↔ S\u0302 ; # Ϻ GREEK CAPITAL LETTER SAN Uppercase_Letter Grek - L
 189 ϻ ↔ s\u0302 ; # ϻ GREEK SMALL LETTER SAN Lowercase_Letter Grek - L
 190 # underbar means exception
 191 # before a letter, initial
 192 ς } $beforeLetter ↔ s $underbar } $beforeLetter;
 193 σ } $beforeLetter ↔ s } $beforeLetter;
 194 # otherwise, after a letter = final
 195 $afterLetter { σ ↔ $afterLetter { s $underbar;
 196 $afterLetter { ς ↔ $afterLetter { s ;
 197 # otherwise (isolated) = initial
 198 ς ↔ s $underbar;
 199 σ ↔ s ;
 200 # [Pp] { Σ ↔ \'S ;
 201 Σ ↔ S ;
 202 τ ↔ t ;
 203 Τ ↔ T ;
 204 $vowel {υ } ↔ u ;
 205 υ ↔ y ;
 206 $vowel { Υ ↔ U ;
 207 Υ ↔ Y ;
 208 χ ↔ ch ;
 209 Χ } $beforeLower ↔ Ch ;
 210 Χ ↔ CH ;
 211 # Completeness for ASCII
 212 $ignore = [[:Mark:]''] * ;
 213 | k  ← c ;
 214 | ph ← f ;
 215 | i  ← j ;
 216 | k ← q ;
 217 | b ← v } $vowel ;
 218 | b ← w } $vowel;
 219 | u ← v ;
 220 | u ← w;
 221 | K ← C ;
 222 | Ph ← F ;
 223 | I ← J ;
 224 | K ← Q ;
 225 | B ← V  } $vowel ;
 226 | B ← W  } $vowel ;
 227 | U ← V ;
 228 | U ← W ;
 229 $rough } $ignore [:UppercaseLetter:] → H ;
 230 $ignore [:UppercaseLetter:] { $rough → H ;
 231 $rough ← H ;
 232 $rough ↔ h ;
 233 # Completeness for Greek
 234 ϐ → | β ;
 235 ϑ → | θ ;
 236 ϒ → | Υ ;
 237 ϕ → | φ ;
 238 ϖ → | π ;
 239 ϰ → | κ ;
 240 ϱ → | ρ ;
 241 ϲ → | σ ;
 242 Ϲ → | Σ; #U+03F9 GREEK CAPITAL LUNATE SIGMA SYMBOL
 243 ϳ → j ;
 244 ϴ → | Θ ;
 245 ϵ → | ε ;
 246 µ → | μ ;
 247 ͺ → i;
 248 # delete any trailing ' marks used for roundtripping
 249 ← [Ππ] { \' } [Ss] ;
 250 ← [Νν] { \' } $egammaLike ;
 251 ::NFC (NFD) ;
 252 # ([\u0000-\u007F [:Latin:] [:Greek:] [:nonspacing mark:]]) ;
 253 # ([\u0000-\u007F · [:Latin:] [:nonspacing mark:]]) ;
 254 # MINIMAL FILTER GENERATED FOR: Latin-Greek BACKWARD
 255 :: ( [':?A-Za-zÀ-ÅÇ-ÏÑ-ÖÙ-Ýà-åç-ïñ-öù-ýÿ-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǰǴ-ǵǸ-țȞ-ȟȦ-ȳ\u0300-\u0337\u0339-\u0345΅-ΆΈ-ΊΌΎ-ΐΪ-ΰϊ-ώϓ-ϔЀ-ЁЃЇЌ-ЎЙйѐ-ёѓїќ-ўѶ-ѷӁ-ӂӐ-ӓӖ-ӗӚ-ӟӢ-ӧӪ-ӵӸ-ӹḀ-ẙẛẠ-ỹἀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ᾼ῁-ῄῆ-ΐῖ-Ί῝-΅ῲ-ῴῶ-ῼK-Å] ) ;
 256