icuSources/data/translit/ThaiLogical_Latin.txt

   1 # ***************************************************************************
   2 # *
   3 # *  Copyright (C) 2004-2016, International Business Machines
   4 # *  Corporation; Unicode, Inc.; and others.  All Rights Reserved.
   5 # *
   6 # ***************************************************************************
   7 # File: ThaiLogical_Latin.txt
   8 # Generated from CLDR
   9 #
  10
  11 # Thai-Latin
  12 # This set of rules follows ISO 11940
  13 #     see http://homepage.mac.com/sirbinks/pdf/Thai.r2.pdf
  14 # except that that does not mention an implicit vowel, so we use o\u0323
  15 #
  16 # The transcription is fairly ugly, so we ought to also do the UNGEGN version
  17 #     see: http://www.eki.ee/wgrs/rom1_th.pdf
  18 # and probably make that the main variant.
  19 #
  20 # Note: this is an internal file. The NFD/NFC is handled externally, in the index
  21 # The insertion of spaces between words, the reversal of the vowels
  22 # and the conversion of space to semicolon are done *outside* of these rules.
  23 # So as far as these rules are concerned, the vowels are in logical order!
  24 # insert implicit vowel (and remove it going the other way)
  25 # COMMENTED out: the implicit vowel positions cannot be predicted algorithmically
  26 #$consonant = [ก-ฮ];
  27 #$vowel = [ะ-\u0E3Aเ-ไ\u0E47];
  28 #{ ( $consonant ) } [^$vowel \uE000] → | $1 \uE000 ;
  29 #\uE000 → o\u0323 ;
  30 # ← o\u0323 ;
  31 $notAbove = [^\p{ccc=0}\p{ccc=above}] ;
  32 $notBelow = [^\p{ccc=0}\p{ccc=below}] ;
  33 # Consonants
  34 # Warning: the 'h's need to be handled carefully!
  35 # What we really want to say is the following, but we can't
  36 # $notHAccent = !($notAbove*   \u0304 | $notBelow*   \u0323) ;
  37 # Since the only accents we care about that could cause problems are free-standing accents below, we use instead:
  38 $freeStandingBelow = [\u0325  ];
  39 $hAccent =  [   \u0304     \u0323];
  40 $notHAccent0 = [^$freeStandingBelow$hAccent];
  41 $notHAccent1 = $freeStandingBelow [^$hAccent];
  42 ห → h\u0304 ; # THAI CHARACTER HO HIP
  43 ห | $1 ← h ($notAbove*)    \u0304; # backward case, account for reordering
  44 ฮ ↔ h\u0323 ; # THAI CHARACTER HO NOKHUK
  45 ข ↔ k\u0304h ; # THAI CHARACTER KHO KHAI
  46 ฃ ↔ k\u0323\u0304h ; # THAI CHARACTER KHO KHUAT
  47 ฅ ↔ kʹh ; # THAI CHARACTER KHO KHON
  48 ฆ ↔ k\u0323h ; # THAI CHARACTER KHO RAKHANG
  49 ค ← kh } $notHAccent1 ; # THAI CHARACTER KHO KHWAI
  50 ค ↔ kh } $notHAccent0 ; # THAI CHARACTER KHO KHWAI
  51 ก ↔ k ; # THAI CHARACTER KO KAI
  52 ภ ↔ p\u0323h ; # THAI CHARACTER PHO SAMPHAO
  53 ผ ↔ p\u0304h ; # THAI CHARACTER PHO PHUNG
  54 พ ← ph } $notHAccent1 ; # THAI CHARACTER PHO PHAN
  55 พ ↔ ph } $notHAccent0 ; # THAI CHARACTER PHO PHAN
  56 ป ↔ p ; # THAI CHARACTER PO PLA
  57 ฉ ↔ c\u0304h ; # THAI CHARACTER CHO CHING
  58 ฌ ↔ c\u0323h ; # THAI CHARACTER CHO CHOE
  59 ช ← ch } $notHAccent1 ; # THAI CHARACTER CHO CHANG
  60 ช ↔ ch } $notHAccent0 ; # THAI CHARACTER CHO CHANG
  61 จ ↔ c ; # THAI CHARACTER CHO CHAN
  62 ฐ ↔ t\u0323\u0304h ; # THAI CHARACTER THO THAN
  63 ฑ ↔ t\u0331h ; # THAI CHARACTER THO NANGMONTHO
  64 ฒ ↔ tʹh ; # THAI CHARACTER THO PHUTHAO
  65 ถ ↔ t\u0304h ; # THAI CHARACTER THO THUNG
  66 ธ ↔ t\u0323h ; # THAI CHARACTER THO THONG
  67 ท ← th } $notHAccent1 ; # THAI CHARACTER THO THAHAN
  68 ท ↔ th } $notHAccent0 ; # THAI CHARACTER THO THAHAN
  69 #Note: TO PATAK deviates from ISO since t-dotunder + h would be ambigous. So it uses vertical tick.
  70 ฏ ↔ t\u0329 ; # THAI CHARACTER TO PATAK
  71 ต ↔ t ; # THAI CHARACTER TO TAO
  72 # since there is no singleton g (generated), don't worry about that.
  73 ง ↔ ng ; # THAI CHARACTER NGO NGU
  74 ณ ↔ n\u0323 ; # THAI CHARACTER NO NEN
  75 น ↔ n ; # THAI CHARACTER NO NU
  76 ญ ↔ y\u0323  ; # THAI CHARACTER YO YING
  77 ฎ ↔ d\u0323 ; # THAI CHARACTER DO CHADA
  78 ด ↔ d ; # THAI CHARACTER DO DEK
  79 บ ↔ b ; # THAI CHARACTER BO BAIMAI
  80 ฝ ↔ f\u0304 ; # THAI CHARACTER FO FA
  81 ฝ | $1 ← f ($notAbove*)    \u0304; # backward case, account for reordering
  82 ม ↔ m ; # THAI CHARACTER MO MA
  83 ย ↔ y ; # THAI CHARACTER YO YAK
  84 ร ↔ r ; # THAI CHARACTER RO RUA
  85 ฤ ↔ v ; # THAI CHARACTER RU
  86 ฦ ↔ ł ; # THAI CHARACTER LU
  87 ว ↔ w ; # THAI CHARACTER WO WAEN
  88 ศ ↔ s\u0323\u0304 ; # THAI CHARACTER SO SALA***
  89 ศ | $1 ← s    \u0323 ($notAbove*)    \u0304; # backward case, account for reordering
  90 ษ ↔ s\u0304ʹ ; # THAI CHARACTER SO RUSI
  91 ส → s\u0304 ; # THAI CHARACTER SO SUA***
  92 ส | $1 ← s ($notAbove*)    \u0304; # backward case, account for reordering
  93 ฬ ↔ l\u0323 ; # THAI CHARACTER LO CHULA
  94 ล ↔ l ; # THAI CHARACTER LO LING
  95 ฟ ↔ f ; # THAI CHARACTER FO FAN
  96 อ ↔ x ; # THAI CHARACTER O ANG
  97 ซ ↔ s ; # THAI CHARACTER SO SO
  98 # vowels
  99 \u0E31 ↔ a\u0323 ; # THAI CHARACTER MAI HAN-AKAT
 100 า → a\u0304 ; # THAI CHARACTER SARA AA
 101 า | $1 ← a ($notAbove*)    \u0304; # backward case, account for reordering
 102 # We deviate from ISO for SARA AM for disambiguation
 103 ำ → a  \u0309; # THAI CHARACTER SARA AM
 104 ำ | $1 ← a ($notAbove*)  \u0309 ; # backward case, account for reordering
 105 ะ ↔ a ; # THAI CHARACTER SARA A
 106 \u0E35 ↔ i\u0304 ; # THAI CHARACTER SARA II
 107 \u0E35 | $1 ← i ($notAbove*)    \u0304  ; # backward case, account for reordering
 108 \u0E37 ↔ u\u0323\u0304 ; # THAI CHARACTER SARA UEE
 109 \u0E37 | $1 ← u   \u0323 ($notAbove*)    \u0304  ; # backward case, account for reordering
 110 \u0E36 ↔ u\u0323 ; # THAI CHARACTER SARA UE
 111 \u0E39 ↔ u\u0304 ; # THAI CHARACTER SARA UU
 112 \u0E39 | $1 ← u  ($notAbove*)    \u0304  ; # backward case, account for reordering
 113 \u0E38 ↔ u ; # THAI CHARACTER SARA U
 114 ฯ ↔ ‡ ; # THAI CHARACTER PAIYANNOI
 115 # ฿ ↔ XXX ; # THAI CURRENCY SYMBOL BAHT
 116 เ ↔ e ; # THAI CHARACTER SARA E
 117 แ ↔ æ ; # THAI CHARACTER SARA AE
 118 โ ↔ o ; # THAI CHARACTER SARA O
 119 ใ ↔ ı ; # THAI CHARACTER SARA AI MAIMUAN
 120 ไ ↔ i\u0323 ; # THAI CHARACTER SARA AI MAIMALAI
 121 ๅ ↔ ɨ ; # THAI CHARACTER LAKKHANGYAO
 122 \u0E47 ↔ \u0306 ; # THAI CHARACTER MAITAIKHU
 123 \u0E48 ↔ \u0300 ; # THAI CHARACTER MAI EK
 124 \u0E49 ↔ \u0302 ; # THAI CHARACTER MAI THO
 125 \u0E4A ↔ \u0301 ; # THAI CHARACTER MAI TRI
 126 \u0E4B ↔ \u030C ; # THAI CHARACTER MAI CHATTAWA
 127 \u0E4C ↔ \u0312 ; # THAI CHARACTER THANTHAKHAT
 128 \u0E4E ↔ '~' ; # THAI CHARACTER YAMAKKAN
 129 # We deviate from ISO for disambiguation
 130 \u0E4D ↔  \u030A ; # THAI CHARACTER NIKHAHIT
 131 ๏ ↔ '§' ; # THAI CHARACTER FONGMAN
 132 ๐ ↔ 0 ; # THAI DIGIT ZERO
 133 ๑ ↔ 1 ; # THAI DIGIT ONE
 134 ๒ ↔ 2 ; # THAI DIGIT TWO
 135 ๓ ↔ 3 ; # THAI DIGIT THREE
 136 ๔ ↔ 4 ; # THAI DIGIT FOUR
 137 ๕ ↔ 5 ; # THAI DIGIT FIVE
 138 ๖ ↔ 6 ; # THAI DIGIT SIX
 139 ๗ ↔ 7 ; # THAI DIGIT SEVEN
 140 ๘ ↔ 8 ; # THAI DIGIT EIGHT
 141 ๙ ↔ 9 ; # THAI DIGIT NINE
 142 ๚ ↔ '||' ; # THAI CHARACTER ANGKHANKHU
 143 ๛ ↔ » ; # THAI CHARACTER KHOMUT
 144 ๆ ↔ « ; # THAI CHARACTER MAIYAMOK
 145 # moved down to make shorter first
 146 #Note: PHINTHU deviates from ISO since underring causes canonical problems. So it uses spacing tick below.
 147 \u0E3A ↔ ˌ ; # THAI CHARACTER PHINTHU
 148 \u0E34 ↔ i ; # THAI CHARACTER SARA I
 149 # fallbacks
 150 | k ← g ;
 151 | k ← h ;
 152 | c ← j ;
 153 | k ← q ;
 154 | s ← z ;
 155 :: (lower);
 156