188 lines
6.3 KiB
Plaintext
188 lines
6.3 KiB
Plaintext
#--------------------------------------------------------------------
|
||
# Copyright (c) 1999-2004, International Business Machines
|
||
# Corporation and others. All Rights Reserved.
|
||
#--------------------------------------------------------------------
|
||
|
||
# Thai-Latin
|
||
# This set of rules follows ISO 11940
|
||
# see http://homepage.mac.com/sirbinks/pdf/Thai.r2.pdf
|
||
# except that that does not mention an implicit vowel, so we use ọ
|
||
#
|
||
# The transcription is fairly ugly, so we ought to also do the UNGEGN version
|
||
# see: http://www.eki.ee/wgrs/rom1_th.pdf
|
||
# and probably make that the main variant.
|
||
|
||
# Note: this is an internal file. The NFD/NFC is handled externally, in the index
|
||
# The insertion of spaces between words, the reversal of the vowels
|
||
# and the conversion of space to semicolon are done *outside* of these rules.
|
||
# So as far as these rules are concerned, the vowels are in logical order!
|
||
|
||
# insert implicit vowel (and remove it going the other way)
|
||
# COMMENTED out: the implicit vowel positions cannot be predicted algorithmically
|
||
#$consonant = [ก-ฮ];
|
||
#$vowel = [ะ-ฺเ-ไ็];
|
||
|
||
#{ ( $consonant ) } [^$vowel ] > | $1 ;
|
||
# > ọ ;
|
||
# < ọ ;
|
||
|
||
$notAbove = [^\p{ccc=0}\p{ccc=above}] ;
|
||
$notBelow = [^\p{ccc=0}\p{ccc=below}] ;
|
||
|
||
# Consonants
|
||
# Warning: the 'h's need to be handled carefully!
|
||
# What we really want to say is the following, but we can't
|
||
# $notHAccent = !($notAbove* ̄ | $notBelow* ̣) ;
|
||
|
||
# Since the only accents we care about that could cause problems are free-standing accents below, we use instead:
|
||
$freeStandingBelow = [\u0325 ];
|
||
$hAccent = [ ̄ ̣];
|
||
$notHAccent0 = [^$freeStandingBelow$hAccent];
|
||
$notHAccent1 = $freeStandingBelow [^$hAccent];
|
||
|
||
ห > h̄ ; # THAI CHARACTER HO HIP
|
||
ห | $1 < h ($notAbove*) ̄; # backward case, account for reordering
|
||
ฮ <> ḥ ; # THAI CHARACTER HO NOKHUK
|
||
|
||
ข <> k̄h ; # THAI CHARACTER KHO KHAI
|
||
ฃ <> ḳ̄h ; # THAI CHARACTER KHO KHUAT
|
||
ฅ <> kʹh ; # THAI CHARACTER KHO KHON
|
||
ฆ <> ḳh ; # THAI CHARACTER KHO RAKHANG
|
||
ค < kh } $notHAccent1 ; # THAI CHARACTER KHO KHWAI
|
||
ค <> kh } $notHAccent0 ; # THAI CHARACTER KHO KHWAI
|
||
ก <> k ; # THAI CHARACTER KO KAI
|
||
|
||
ภ <> p̣h ; # THAI CHARACTER PHO SAMPHAO
|
||
ผ <> p̄h ; # THAI CHARACTER PHO PHUNG
|
||
พ < ph } $notHAccent1 ; # THAI CHARACTER PHO PHAN
|
||
พ <> ph } $notHAccent0 ; # THAI CHARACTER PHO PHAN
|
||
ป <> p ; # THAI CHARACTER PO PLA
|
||
|
||
ฉ <> c̄h ; # THAI CHARACTER CHO CHING
|
||
ฌ <> c̣h ; # THAI CHARACTER CHO CHOE
|
||
ช < ch } $notHAccent1 ; # THAI CHARACTER CHO CHANG
|
||
ช <> ch } $notHAccent0 ; # THAI CHARACTER CHO CHANG
|
||
จ <> c ; # THAI CHARACTER CHO CHAN
|
||
|
||
ฐ <> ṭ̄h ; # THAI CHARACTER THO THAN
|
||
ฑ <> ṯh ; # THAI CHARACTER THO NANGMONTHO
|
||
ฒ <> tʹh ; # THAI CHARACTER THO PHUTHAO
|
||
ถ <> t̄h ; # THAI CHARACTER THO THUNG
|
||
ธ <> ṭh ; # THAI CHARACTER THO THONG
|
||
ท < th } $notHAccent1 ; # THAI CHARACTER THO THAHAN
|
||
ท <> th } $notHAccent0 ; # THAI CHARACTER THO THAHAN
|
||
#Note: TO PATAK deviates from ISO since t-dotunder + h would be ambigous. So it uses vertical tick.
|
||
ฏ <> t̩ ; # THAI CHARACTER TO PATAK
|
||
ต <> t ; # THAI CHARACTER TO TAO
|
||
|
||
# since there is no singleton g (generated), don't worry about that.
|
||
ง <> ng ; # THAI CHARACTER NGO NGU
|
||
ณ <> ṇ ; # THAI CHARACTER NO NEN
|
||
น <> n ; # THAI CHARACTER NO NU
|
||
|
||
ญ <> ỵ ; # THAI CHARACTER YO YING
|
||
ฎ <> ḍ ; # THAI CHARACTER DO CHADA
|
||
ด <> d ; # THAI CHARACTER DO DEK
|
||
|
||
บ <> b ; # THAI CHARACTER BO BAIMAI
|
||
ฝ <> f̄ ; # THAI CHARACTER FO FA
|
||
ฝ | $1 < f ($notAbove*) ̄; # backward case, account for reordering
|
||
|
||
ม <> m ; # THAI CHARACTER MO MA
|
||
ย <> y ; # THAI CHARACTER YO YAK
|
||
ร <> r ; # THAI CHARACTER RO RUA
|
||
ฤ <> v ; # THAI CHARACTER RU
|
||
ฦ <> ł ; # THAI CHARACTER LU
|
||
ว <> w ; # THAI CHARACTER WO WAEN
|
||
|
||
ศ <> ṣ̄ ; # THAI CHARACTER SO SALA***
|
||
ศ | $1 < s ̣ ($notAbove*) ̄; # backward case, account for reordering
|
||
ษ <> s̄ʹ ; # THAI CHARACTER SO RUSI
|
||
ส > s̄ ; # THAI CHARACTER SO SUA***
|
||
ส | $1 < s ($notAbove*) ̄; # backward case, account for reordering
|
||
|
||
ฬ <> ḷ ; # THAI CHARACTER LO CHULA
|
||
ล <> l ; # THAI CHARACTER LO LING
|
||
ฟ <> f ; # THAI CHARACTER FO FAN
|
||
|
||
อ <> x ; # THAI CHARACTER O ANG
|
||
ซ <> s ; # THAI CHARACTER SO SO
|
||
|
||
# vowels
|
||
|
||
ั <> ạ ; # THAI CHARACTER MAI HAN-AKAT
|
||
|
||
า > ā ; # THAI CHARACTER SARA AA
|
||
า | $1 < a ($notAbove*) ̄; # backward case, account for reordering
|
||
|
||
# We deviate from ISO for SARA AM for disambiguation
|
||
ำ > a ̉; # THAI CHARACTER SARA AM
|
||
ำ | $1 < a ($notAbove*) ̉ ; # backward case, account for reordering
|
||
|
||
ะ <> a ; # THAI CHARACTER SARA A
|
||
ี <> ī ; # THAI CHARACTER SARA II
|
||
ี | $1 < i ($notAbove*) ̄ ; # backward case, account for reordering
|
||
|
||
ื <> ụ̄ ; # THAI CHARACTER SARA UEE
|
||
ื | $1 < u ̣ ($notAbove*) ̄ ; # backward case, account for reordering
|
||
|
||
ึ <> ụ ; # THAI CHARACTER SARA UE
|
||
ู <> ū ; # THAI CHARACTER SARA UU
|
||
ู | $1 < u ($notAbove*) ̄ ; # backward case, account for reordering
|
||
|
||
ุ <> u ; # THAI CHARACTER SARA U
|
||
|
||
ฯ <> ‡ ; # THAI CHARACTER PAIYANNOI
|
||
|
||
# ฿ <> XXX ; # THAI CURRENCY SYMBOL BAHT
|
||
|
||
เ <> e ; # THAI CHARACTER SARA E
|
||
แ <> æ ; # THAI CHARACTER SARA AE
|
||
โ <> o ; # THAI CHARACTER SARA O
|
||
ใ <> ı ; # THAI CHARACTER SARA AI MAIMUAN
|
||
ไ <> ị ; # THAI CHARACTER SARA AI MAIMALAI
|
||
ๅ <> ɨ ; # THAI CHARACTER LAKKHANGYAO
|
||
็ <> ̆ ; # THAI CHARACTER MAITAIKHU
|
||
่ <> ̀ ; # THAI CHARACTER MAI EK
|
||
้ <> ̂ ; # THAI CHARACTER MAI THO
|
||
๊ <> ́ ; # THAI CHARACTER MAI TRI
|
||
๋ <> ̌ ; # THAI CHARACTER MAI CHATTAWA
|
||
์ <> ̒ ; # THAI CHARACTER THANTHAKHAT
|
||
๎ <> '~' ; # THAI CHARACTER YAMAKKAN
|
||
|
||
# We deviate from ISO for disambiguation
|
||
ํ <> ̊ ; # THAI CHARACTER NIKHAHIT
|
||
|
||
๏ <> § ; # THAI CHARACTER FONGMAN
|
||
|
||
๐ <> 0 ; # THAI DIGIT ZERO
|
||
๑ <> 1 ; # THAI DIGIT ONE
|
||
๒ <> 2 ; # THAI DIGIT TWO
|
||
๓ <> 3 ; # THAI DIGIT THREE
|
||
๔ <> 4 ; # THAI DIGIT FOUR
|
||
๕ <> 5 ; # THAI DIGIT FIVE
|
||
๖ <> 6 ; # THAI DIGIT SIX
|
||
๗ <> 7 ; # THAI DIGIT SEVEN
|
||
๘ <> 8 ; # THAI DIGIT EIGHT
|
||
๙ <> 9 ; # THAI DIGIT NINE
|
||
|
||
๚ <> '||' ; # THAI CHARACTER ANGKHANKHU
|
||
|
||
๛ <> » ; # THAI CHARACTER KHOMUT
|
||
ๆ <> « ; # THAI CHARACTER MAIYAMOK
|
||
|
||
# moved down to make shorter first
|
||
#Note: PHINTHU deviates from ISO since underring causes canonical problems. So it uses spacing tick below.
|
||
ฺ <> ˌ ; # THAI CHARACTER PHINTHU
|
||
ิ <> i ; # THAI CHARACTER SARA I
|
||
|
||
# fallbacks
|
||
|
||
| k < g ;
|
||
| k < h ;
|
||
| c < j ;
|
||
| k < q ;
|
||
| s < z ;
|
||
|
||
:: (lower);
|