icuSources/data/translit/sat_Olck_sat_FONIPA.txt

   1 # © 2016 and later: Unicode, Inc. and others.
   2 # License & terms of use: http://www.unicode.org/copyright.html#License
   3 #
   4 # File: sat_Olck_sat_FONIPA.txt
   5 # Generated from CLDR
   6 #
   7
   8 # Santali (Ol Chiki) → Santali (International Phonetic Alphabet)
   9 # Output
  10 # ------
  11 # m mː n nː ɳ ɳː ɲ ɲː ŋ ŋː
  12 # p pʰ pʼ b bʰ t tʰ tʼ d dʰ ʈ ʈʰ ɖ ɖʰ c cʰ cʼ k kʰ kʼ ɡ ʔ
  13 # s sː h
  14 # d\u0361ʒ
  15 # ɽ r
  16 # l lː
  17 # w wː w\u0303 w\u0303ː
  18 #
  19 # i iː ĩ ĩː u uː ũ ũː
  20 # e eː ẽ ẽː ə əː ə\u0303 ə\u0303ː o oː õ õː
  21 # ɛ ɛː ɛ\u0303 ɛ\u0303ː ɔ ɔː ɔ\u0303 ɔ\u0303ː
  22 # a aː ã ãː
  23 # References
  24 # ----------
  25 # [1] Michael Everson: Final proposal to encode the Ol Chiki script
  26 #     in the UCS.  ISO/IEC JTC1/SC2/WG2 Working Group Document N2984R,
  27 #     September 21, 2005.  http://std.dkuug.dk/jtc1/sc2/wg2/docs/n2984.pdf
  28 #
  29 # [2] George L. Campbell: Compendium of the World's Languages.
  30 #     Volume 2: Ladakhi to Zuni. ISBN 0-415-20297-3.  Taylor & Francis, 2000.
  31 #     Pages 1454 to 1458.
  32 # Notes
  33 # -----
  34 # According to [1] (page 3), ᱽ can only follow the four ejective
  35 # consonants ᱵ /pʼ/, ᱡ /cʼ/, ᱫ /tʼ/, and ᱜ /kʼ/; these become
  36 # ᱵᱽ /b/, ᱫᱽ /d/, ᱡᱽ /d\u0361ʒ/, and ᱜᱽ /ɡ/.  In online texts, however,
  37 # we have occasionally encountered ᱽ following non-ejective plosives,
  38 # for example after ᱯ /p/. These might possibly be typos.  Our rules
  39 # try to be resilient and handle ᱯᱽ as /b/.
  40 #
  41 # According to [1] (page 2), U+1C7C PHAARKAA follows the four “glottal”
  42 # consonants ᱵ /pʼ/, ᱡ /cʼ/, ᱫ /tʼ/, and ᱜ /kʼ/ (these are actually
  43 # ejective, not glottal).  In online texts, however, we have frequently
  44 # encountered ᱼ following non-ejective consonants.
  45 $inword = [[:L:][:M:]];
  46 # Some online texts use a decomposed form of U+1C7A MU-GAAHLAA TTUDDAG.
  47 ᱹᱸ → ᱺ ;
  48 ᱸᱹ → ᱺ ;
  49 ::null();
  50 # To simplify the rules below, enforce a uniform ordering of marks.
  51 ᱻᱹ → ᱹᱻ ;
  52 ᱻᱸ → ᱸᱻ ;
  53 ᱻᱺ → ᱺᱻ ;
  54 ᱼᱹ → ᱹᱼ ;
  55 ᱼᱸ → ᱸᱼ ;
  56 ᱼᱺ → ᱺᱼ ;
  57 ::null();
  58 # Some online texts use U+1C7C PHAARKAA instead of U+1C7B RELAA for indicating
  59 # long phonemes, presumably because the graphemes look similar in some fonts.
  60 # Since phaarkaa is used for voicing ejectives and plosives (which cannot
  61 # be lenghtened), we rewrite phaarkaa to relaa.
  62 [ᱚᱟᱤᱩᱮᱳᱶᱢᱝᱞᱱ] [ᱹᱸᱺ]* {ᱼ} → ᱻ ;
  63 ::null();
  64 ᱚᱹᱻ → ɔː ;
  65 ᱚᱹ → ɔ ;
  66 ᱚᱸᱻ → ɔ\u0303ː ;
  67 ᱚᱸ → ɔ\u0303 ;
  68 ᱚᱺᱻ → ɔ\u0303ː ;
  69 ᱚᱺ → ɔ\u0303 ;
  70 ᱚᱻ → ɔː ;
  71 ᱚ → ɔ ;
  72 ᱛᱼ → t ;
  73 ᱛᱷ → tʰ ;
  74 ᱛᱽ → d ;
  75 $inword {ᱛ} → d ;
  76 ᱛ → t ;
  77 ᱜᱼ → kʼ ;
  78 ᱜᱷ → kʰ ;
  79 ᱜᱽ → ɡ ;
  80 $inword {ᱜ} → ɡ ;
  81 ᱜ → kʼ ;
  82 ᱝᱻ → ŋː ;
  83 ᱝ → ŋ ;
  84 ᱞᱻ → lː ;
  85 ᱞ → l ;
  86 ᱟᱹᱻ → əː ;
  87 ᱟᱹ → ə ;
  88 ᱟᱸᱻ → ãː ;
  89 ᱟᱸ → ã ;
  90 ᱟᱺᱻ → ə\u0303ː ;
  91 ᱟᱺ → ə\u0303 ;
  92 ᱟᱻ → aː ;
  93 ᱟ → a ;
  94 ᱠᱼ → k ;
  95 ᱠᱷ → kʰ ;
  96 ᱠᱽ → ɡ ;
  97 ᱠ → k ;
  98 ᱡᱼ → cʼ ;
  99 ᱡᱷ → cʰ ;
 100 ᱡᱽ →  d\u0361ʒ ;
 101 $inword {ᱡ} →  d\u0361ʒ ;
 102 ᱡ → cʼ ;
 103 ᱢᱻ → mː ;
 104 ᱢ → m ;
 105 # According to [1], ᱣ is sometimes /v/ and sometimes /w/.
 106 # TODO: Find out if there is a rule for this.
 107 ᱣᱸ → w\u0303 ;
 108 ᱣ → w ;
 109 ᱤᱹᱻ → iː ;
 110 ᱤᱹ → i ;
 111 ᱤᱸᱻ → ĩː ;
 112 ᱤᱸ → ĩ ;
 113 ᱤᱺᱻ → ĩː ;
 114 ᱤᱺ → ĩ ;
 115 ᱤᱻ → iː ;
 116 ᱤ → i ;
 117 ᱥᱻ → sː ;
 118 ᱥ → s ;
 119 # According to [1], ᱦ is sometimes /h/ and sometimes /ʔ/.
 120 # TODO: Find out if there is a rule for this.
 121 ᱦ → h ;
 122 ᱧᱻ → ɲː ;
 123 ᱧ → ɲ ;
 124 ᱨᱻ → r ;
 125 ᱨ → r ;
 126 ᱩᱹᱻ → uː ;
 127 ᱩᱹ → u ;
 128 ᱩᱸᱻ → ũː ;
 129 ᱩᱸ → ũ ;
 130 ᱩᱺᱻ → ũː ;
 131 ᱩᱺ → ũ ;
 132 ᱩᱻ → uː ;
 133 ᱩ → u ;
 134 ᱪᱼ → c ;
 135 ᱪᱷ → cʰ ;
 136 ᱪᱽ →  d\u0361ʒ ;
 137 ᱪ → c ;
 138 ᱫᱼ → tʼ ;
 139 ᱫᱷ → tʰ ;
 140 ᱫᱽ → d ;
 141 $inword {ᱫ} → d ;
 142 ᱫ → tʼ ;
 143 ᱬᱻ → ɳː ;
 144 ᱬ → ɳ ;
 145 # TODO: ᱵᱷᱭᱨᱚᱵ → bʰhrɔb seems unlikely; would be good to verify.
 146 ᱭ → h ;
 147 ᱮᱹᱻ → ɛː ;
 148 ᱮᱹ → ɛ ;
 149 ᱮᱺᱻ → ɛ\u0303ː ;
 150 ᱮᱺ → ɛ\u0303 ;
 151 ᱮᱸᱻ → ẽː ;
 152 ᱮᱸ → ẽ ;
 153 ᱮᱻ → eː ;
 154 ᱮ → e ;
 155 ᱯᱼ → p ;
 156 ᱯᱷ → pʰ ;
 157 ᱯᱽ → b ;
 158 ᱯ → p ;
 159 ᱰᱷ → ɖʰ ;
 160 ᱰ → ɖ ;
 161 ᱱᱻ → nː ;
 162 ᱱ → n ;
 163 ᱲᱻ → ɽ ;
 164 ᱲ → ɽ ;
 165 ᱳᱸᱻ → õː ;
 166 ᱳᱸ → õ ;
 167 ᱳᱻ → oː ;
 168 ᱳ → o ;
 169 ᱴᱼ → ʈ ;
 170 ᱴᱷ → ʈʰ ;
 171 ᱴᱽ → ɖ ;
 172 ᱴ → ʈ ;
 173 ᱵᱼ → pʼ ;
 174 ᱵᱷ → bʰ ;
 175 ᱵᱽ → b ;
 176 $inword {ᱵ} → b ;
 177 ᱵ → pʼ ;
 178 ᱶᱻ → w\u0303ː ;
 179 ᱶ → w\u0303 ;
 180