icuSources/data/translit/ThaiLogical_Latin.txt

   1 # © 2016 and later: Unicode, Inc. and others.
   2 # License & terms of use: http://www.unicode.org/copyright.html#License
   3 #
   4 # File: ThaiLogical_Latin.txt
   5 # Generated from CLDR
   6 #
   7
   8 # Thai-Latin
   9 # This set of rules follows ISO 11940
  10 #     see http://homepage.mac.com/sirbinks/pdf/Thai.r2.pdf
  11 # except that that does not mention an implicit vowel, so we use o\u0323
  12 #
  13 # The transcription is fairly ugly, so we ought to also do the UNGEGN version
  14 #     see: http://www.eki.ee/wgrs/rom1_th.pdf
  15 # and probably make that the main variant.
  16 #
  17 # Note: this is an internal file. The NFD/NFC is handled externally, in the index
  18 # The insertion of spaces between words, the reversal of the vowels
  19 # and the conversion of space to semicolon are done *outside* of these rules.
  20 # So as far as these rules are concerned, the vowels are in logical order!
  21 # insert implicit vowel (and remove it going the other way)
  22 # COMMENTED out: the implicit vowel positions cannot be predicted algorithmically
  23 #$consonant = [ก-ฮ];
  24 #$vowel = [ะ-\u0E3Aเ-ไ\u0E47];
  25 #{ ( $consonant ) } [^$vowel \uE000] → | $1 \uE000 ;
  26 #\uE000 → o\u0323 ;
  27 # ← o\u0323 ;
  28 $notAbove = [^\p{ccc=0}\p{ccc=above}] ;
  29 $notBelow = [^\p{ccc=0}\p{ccc=below}] ;
  30 # Consonants
  31 # Warning: the 'h's need to be handled carefully!
  32 # What we really want to say is the following, but we can't
  33 # $notHAccent = !($notAbove*   \u0304 | $notBelow*   \u0323) ;
  34 # Since the only accents we care about that could cause problems are free-standing accents below, we use instead:
  35 $freeStandingBelow = [\u0325  ];
  36 $hAccent =  [   \u0304     \u0323];
  37 $notHAccent0 = [^$freeStandingBelow$hAccent];
  38 $notHAccent1 = $freeStandingBelow [^$hAccent];
  39 ห → h\u0304 ; # THAI CHARACTER HO HIP
  40 ห | $1 ← h ($notAbove*)    \u0304; # backward case, account for reordering
  41 ฮ ↔ h\u0323 ; # THAI CHARACTER HO NOKHUK
  42 ข ↔ k\u0304h ; # THAI CHARACTER KHO KHAI
  43 ฃ ↔ k\u0323\u0304h ; # THAI CHARACTER KHO KHUAT
  44 ฅ ↔ kʹh ; # THAI CHARACTER KHO KHON
  45 ฆ ↔ k\u0323h ; # THAI CHARACTER KHO RAKHANG
  46 ค ← kh } $notHAccent1 ; # THAI CHARACTER KHO KHWAI
  47 ค ↔ kh } $notHAccent0 ; # THAI CHARACTER KHO KHWAI
  48 ก ↔ k ; # THAI CHARACTER KO KAI
  49 ภ ↔ p\u0323h ; # THAI CHARACTER PHO SAMPHAO
  50 ผ ↔ p\u0304h ; # THAI CHARACTER PHO PHUNG
  51 พ ← ph } $notHAccent1 ; # THAI CHARACTER PHO PHAN
  52 พ ↔ ph } $notHAccent0 ; # THAI CHARACTER PHO PHAN
  53 ป ↔ p ; # THAI CHARACTER PO PLA
  54 ฉ ↔ c\u0304h ; # THAI CHARACTER CHO CHING
  55 ฌ ↔ c\u0323h ; # THAI CHARACTER CHO CHOE
  56 ช ← ch } $notHAccent1 ; # THAI CHARACTER CHO CHANG
  57 ช ↔ ch } $notHAccent0 ; # THAI CHARACTER CHO CHANG
  58 จ ↔ c ; # THAI CHARACTER CHO CHAN
  59 ฐ ↔ t\u0323\u0304h ; # THAI CHARACTER THO THAN
  60 ฑ ↔ t\u0331h ; # THAI CHARACTER THO NANGMONTHO
  61 ฒ ↔ tʹh ; # THAI CHARACTER THO PHUTHAO
  62 ถ ↔ t\u0304h ; # THAI CHARACTER THO THUNG
  63 ธ ↔ t\u0323h ; # THAI CHARACTER THO THONG
  64 ท ← th } $notHAccent1 ; # THAI CHARACTER THO THAHAN
  65 ท ↔ th } $notHAccent0 ; # THAI CHARACTER THO THAHAN
  66 #Note: TO PATAK deviates from ISO since t-dotunder + h would be ambigous. So it uses vertical tick.
  67 ฏ ↔ t\u0329 ; # THAI CHARACTER TO PATAK
  68 ต ↔ t ; # THAI CHARACTER TO TAO
  69 # since there is no singleton g (generated), don't worry about that.
  70 ง ↔ ng ; # THAI CHARACTER NGO NGU
  71 ณ ↔ n\u0323 ; # THAI CHARACTER NO NEN
  72 น ↔ n ; # THAI CHARACTER NO NU
  73 ญ ↔ y\u0323  ; # THAI CHARACTER YO YING
  74 ฎ ↔ d\u0323 ; # THAI CHARACTER DO CHADA
  75 ด ↔ d ; # THAI CHARACTER DO DEK
  76 บ ↔ b ; # THAI CHARACTER BO BAIMAI
  77 ฝ ↔ f\u0304 ; # THAI CHARACTER FO FA
  78 ฝ | $1 ← f ($notAbove*)    \u0304; # backward case, account for reordering
  79 ม ↔ m ; # THAI CHARACTER MO MA
  80 ย ↔ y ; # THAI CHARACTER YO YAK
  81 ร ↔ r ; # THAI CHARACTER RO RUA
  82 ฤ ↔ v ; # THAI CHARACTER RU
  83 ฦ ↔ ł ; # THAI CHARACTER LU
  84 ว ↔ w ; # THAI CHARACTER WO WAEN
  85 ศ ↔ s\u0323\u0304 ; # THAI CHARACTER SO SALA***
  86 ศ | $1 ← s    \u0323 ($notAbove*)    \u0304; # backward case, account for reordering
  87 ษ ↔ s\u0304ʹ ; # THAI CHARACTER SO RUSI
  88 ส → s\u0304 ; # THAI CHARACTER SO SUA***
  89 ส | $1 ← s ($notAbove*)    \u0304; # backward case, account for reordering
  90 ฬ ↔ l\u0323 ; # THAI CHARACTER LO CHULA
  91 ล ↔ l ; # THAI CHARACTER LO LING
  92 ฟ ↔ f ; # THAI CHARACTER FO FAN
  93 อ ↔ x ; # THAI CHARACTER O ANG
  94 ซ ↔ s ; # THAI CHARACTER SO SO
  95 # vowels
  96 \u0E31 ↔ a\u0323 ; # THAI CHARACTER MAI HAN-AKAT
  97 า → a\u0304 ; # THAI CHARACTER SARA AA
  98 า | $1 ← a ($notAbove*)    \u0304; # backward case, account for reordering
  99 # We deviate from ISO for SARA AM for disambiguation
 100 ำ → a  \u0309; # THAI CHARACTER SARA AM
 101 ำ | $1 ← a ($notAbove*)  \u0309 ; # backward case, account for reordering
 102 ะ ↔ a ; # THAI CHARACTER SARA A
 103 \u0E35 ↔ i\u0304 ; # THAI CHARACTER SARA II
 104 \u0E35 | $1 ← i ($notAbove*)    \u0304  ; # backward case, account for reordering
 105 \u0E37 ↔ u\u0323\u0304 ; # THAI CHARACTER SARA UEE
 106 \u0E37 | $1 ← u   \u0323 ($notAbove*)    \u0304  ; # backward case, account for reordering
 107 \u0E36 ↔ u\u0323 ; # THAI CHARACTER SARA UE
 108 \u0E39 ↔ u\u0304 ; # THAI CHARACTER SARA UU
 109 \u0E39 | $1 ← u  ($notAbove*)    \u0304  ; # backward case, account for reordering
 110 \u0E38 ↔ u ; # THAI CHARACTER SARA U
 111 ฯ ↔ ‡ ; # THAI CHARACTER PAIYANNOI
 112 # ฿ ↔ XXX ; # THAI CURRENCY SYMBOL BAHT
 113 เ ↔ e ; # THAI CHARACTER SARA E
 114 แ ↔ æ ; # THAI CHARACTER SARA AE
 115 โ ↔ o ; # THAI CHARACTER SARA O
 116 ใ ↔ ı ; # THAI CHARACTER SARA AI MAIMUAN
 117 ไ ↔ i\u0323 ; # THAI CHARACTER SARA AI MAIMALAI
 118 ๅ ↔ ɨ ; # THAI CHARACTER LAKKHANGYAO
 119 \u0E47 ↔ \u0306 ; # THAI CHARACTER MAITAIKHU
 120 \u0E48 ↔ \u0300 ; # THAI CHARACTER MAI EK
 121 \u0E49 ↔ \u0302 ; # THAI CHARACTER MAI THO
 122 \u0E4A ↔ \u0301 ; # THAI CHARACTER MAI TRI
 123 \u0E4B ↔ \u030C ; # THAI CHARACTER MAI CHATTAWA
 124 \u0E4C ↔ \u0312 ; # THAI CHARACTER THANTHAKHAT
 125 \u0E4E ↔ '~' ; # THAI CHARACTER YAMAKKAN
 126 # We deviate from ISO for disambiguation
 127 \u0E4D ↔  \u030A ; # THAI CHARACTER NIKHAHIT
 128 ๏ ↔ '§' ; # THAI CHARACTER FONGMAN
 129 ๐ ↔ 0 ; # THAI DIGIT ZERO
 130 ๑ ↔ 1 ; # THAI DIGIT ONE
 131 ๒ ↔ 2 ; # THAI DIGIT TWO
 132 ๓ ↔ 3 ; # THAI DIGIT THREE
 133 ๔ ↔ 4 ; # THAI DIGIT FOUR
 134 ๕ ↔ 5 ; # THAI DIGIT FIVE
 135 ๖ ↔ 6 ; # THAI DIGIT SIX
 136 ๗ ↔ 7 ; # THAI DIGIT SEVEN
 137 ๘ ↔ 8 ; # THAI DIGIT EIGHT
 138 ๙ ↔ 9 ; # THAI DIGIT NINE
 139 ๚ ↔ '||' ; # THAI CHARACTER ANGKHANKHU
 140 ๛ ↔ » ; # THAI CHARACTER KHOMUT
 141 ๆ ↔ « ; # THAI CHARACTER MAIYAMOK
 142 # moved down to make shorter first
 143 #Note: PHINTHU deviates from ISO since underring causes canonical problems. So it uses spacing tick below.
 144 \u0E3A ↔ ˌ ; # THAI CHARACTER PHINTHU
 145 \u0E34 ↔ i ; # THAI CHARACTER SARA I
 146 # fallbacks
 147 | k ← g ;
 148 | k ← h ;
 149 | c ← j ;
 150 | k ← q ;
 151 | s ← z ;
 152 :: (lower);
 153