ICU-8.11.tar.gz

[apple/icu.git] / icuSources / data / translit / ThaiLogical_Latin.txt

diff --git a/icuSources/data/translit/ThaiLogical_Latin.txt b/icuSources/data/translit/ThaiLogical_Latin.txt
index 558fd84a173a5de1ba64eead4e41efc3164003e8..16a4ab6165120791fd6cd5c77d7489aae6473d3a 100644 (file)
--- a/icuSources/data/translit/ThaiLogical_Latin.txt
+++ b/icuSources/data/translit/ThaiLogical_Latin.txt
@@ -1,160 +1,102 @@
-#--------------------------------------------------------------------
-# 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
+# ***************************************************************************
+# *
+# *  Copyright (C) 2004-2006, International Business Machines
+# *  Corporation; Unicode, Inc.; and others.  All Rights Reserved.
+# *
+# ***************************************************************************
+# File: ThaiLogical_Latin.txt
+# Generated from CLDR: Thu Jul 20 16:27:19 PDT 2006

 #
 #

-# 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}] ;
 $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  ];
 $freeStandingBelow = [\u0325  ];

-$hAccent =  [   ̄     ̣];
+$hAccent =  [   \u0304     \u0323];

 $notHAccent0 = [^$freeStandingBelow$hAccent];
 $notHAccent1 = $freeStandingBelow [^$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  
+ห > h\u0304 ; # THAI CHARACTER HO HIP
+ห | $1 < h ($notAbove*)    \u0304; # backward case, account for reordering
+ฮ <> h\u0323 ; # THAI CHARACTER HO NOKHUK
+ข <> k\u0304h ; # THAI CHARACTER KHO KHAI
+ฃ <> k\u0323\u0304h ; # THAI CHARACTER KHO KHUAT
+ฅ <> kʹh ; # THAI CHARACTER KHO KHON
+ฆ <> k\u0323h ; # THAI CHARACTER KHO RAKHANG
+ค < kh } $notHAccent1 ; # THAI CHARACTER KHO KHWAI
+ค <> kh } $notHAccent0 ; # THAI CHARACTER KHO KHWAI

 ก <> k ; # THAI CHARACTER KO KAI
 ก <> k ; # THAI CHARACTER KO KAI

-
-ภ <> p̣h ; # THAI CHARACTER PHO SAMPHAO
-ผ <> p̄h ; # THAI CHARACTER PHO PHUNG
+ภ <> p\u0323h ; # THAI CHARACTER PHO SAMPHAO
+ผ <> p\u0304h ; # THAI CHARACTER PHO PHUNG

 พ < ph } $notHAccent1 ; # THAI CHARACTER PHO PHAN
 พ <> ph } $notHAccent0 ; # THAI CHARACTER PHO PHAN
 ป <> p ; # THAI CHARACTER PO PLA
 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
+ฉ <> c\u0304h ; # THAI CHARACTER CHO CHING
+ฌ <> c\u0323h ; # THAI CHARACTER CHO CHOE

 ช < ch } $notHAccent1 ; # THAI CHARACTER CHO CHANG
 ช <> ch } $notHAccent0 ; # THAI CHARACTER CHO CHANG
 จ <> c ; # THAI CHARACTER CHO CHAN
 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
+ฐ <> t\u0323\u0304h ; # THAI CHARACTER THO THAN
+ฑ <> t\u0331h ; # THAI CHARACTER THO NANGMONTHO

 ฒ <> tʹh ; # THAI CHARACTER THO PHUTHAO
 ฒ <> tʹh ; # THAI CHARACTER THO PHUTHAO

-ถ <> t̄h ; # THAI CHARACTER THO THUNG
-ธ <> ṭh ; # THAI CHARACTER THO THONG
+ถ <> t\u0304h ; # THAI CHARACTER THO THUNG
+ธ <> t\u0323h ; # THAI CHARACTER THO THONG

 ท < th } $notHAccent1 ; # THAI CHARACTER THO THAHAN
 ท <> th } $notHAccent0 ; # THAI CHARACTER THO THAHAN
 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
+ฏ <> t\u0329 ; # THAI CHARACTER TO PATAK

 ต <> t ; # THAI CHARACTER TO TAO
 ต <> t ; # THAI CHARACTER TO TAO

-
-# since there is no singleton g (generated), don't worry about that.

 ง <> ng ; # THAI CHARACTER NGO NGU
 ง <> ng ; # THAI CHARACTER NGO NGU

-ณ <> ṇ ; # THAI CHARACTER NO NEN
+ณ <> n\u0323 ; # THAI CHARACTER NO NEN

 น <> n ; # THAI CHARACTER NO NU
 น <> n ; # THAI CHARACTER NO NU

-
-ญ <> ỵ  ; # THAI CHARACTER YO YING
-ฎ <> ḍ ; # THAI CHARACTER DO CHADA
+ญ <> y\u0323  ; # THAI CHARACTER YO YING
+ฎ <> d\u0323 ; # THAI CHARACTER DO CHADA

 ด <> d ; # THAI CHARACTER DO DEK
 ด <> d ; # THAI CHARACTER DO DEK

-

 บ <> b ; # THAI CHARACTER BO BAIMAI
 บ <> b ; # THAI CHARACTER BO BAIMAI

-ฝ <> f̄ ; # THAI CHARACTER FO FA
- ฝ | $1 < f ($notAbove*)    ̄; # backward case, account for reordering
-
+ฝ <> f\u0304 ; # THAI CHARACTER FO FA
+ฝ | $1 < f ($notAbove*)    \u0304; # 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
 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
+ศ <> s\u0323\u0304 ; # THAI CHARACTER SO SALA***
+ศ | $1 < s    \u0323 ($notAbove*)    \u0304; # backward case, account for reordering
+ษ <> s\u0304ʹ ; # THAI CHARACTER SO RUSI
+ส > s\u0304 ; # THAI CHARACTER SO SUA***
+ส | $1 < s ($notAbove*)    \u0304; # backward case, account for reordering
+ฬ <> l\u0323 ; # THAI CHARACTER LO CHULA

 ล <> l ; # THAI CHARACTER LO LING
 ฟ <> f ; # THAI CHARACTER FO FAN
 ล <> l ; # THAI CHARACTER LO LING
 ฟ <> f ; # THAI CHARACTER FO FAN

-

 อ <> x ; # THAI CHARACTER O ANG
 ซ <> s ; # THAI CHARACTER SO SO
 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
-
+\u0E31 <> a\u0323 ; # THAI CHARACTER MAI HAN-AKAT
+า > a\u0304 ; # THAI CHARACTER SARA AA
+า | $1 < a ($notAbove*)    \u0304; # backward case, account for reordering
+ำ > a  \u0309; # THAI CHARACTER SARA AM
+ำ | $1 < a ($notAbove*)  \u0309 ; # backward case, account for reordering

 ะ <> a ; # THAI CHARACTER SARA A
 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
-
+\u0E35 <> i\u0304 ; # THAI CHARACTER SARA II
+\u0E35 | $1 < i ($notAbove*)    \u0304  ; # backward case, account for reordering
+\u0E37 <> u\u0323\u0304 ; # THAI CHARACTER SARA UEE
+\u0E37 | $1 < u   \u0323 ($notAbove*)    \u0304  ; # backward case, account for reordering
+\u0E36 <> u\u0323 ; # THAI CHARACTER SARA UE
+\u0E39 <> u\u0304 ; # THAI CHARACTER SARA UU
+\u0E39 | $1 < u  ($notAbove*)    \u0304  ; # backward case, account for reordering
+\u0E38 <> u ; # THAI CHARACTER SARA U

 ฯ <> ‡ ; # THAI CHARACTER PAIYANNOI
 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
 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
+ไ <> i\u0323 ; # THAI CHARACTER SARA AI MAIMALAI

 ๅ <> ɨ ; # THAI CHARACTER LAKKHANGYAO
 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
-
+\u0E47 <> \u0306 ; # THAI CHARACTER MAITAIKHU
+\u0E48 <> \u0300 ; # THAI CHARACTER MAI EK
+\u0E49 <> \u0302 ; # THAI CHARACTER MAI THO
+\u0E4A <> \u0301 ; # THAI CHARACTER MAI TRI
+\u0E4B <> \u030C ; # THAI CHARACTER MAI CHATTAWA
+\u0E4C <> \u0312 ; # THAI CHARACTER THANTHAKHAT
+\u0E4E <> '~' ; # THAI CHARACTER YAMAKKAN
+\u0E4D <>  \u030A ; # THAI CHARACTER NIKHAHIT
+๏ <> '§' ; # THAI CHARACTER FONGMAN

 ๐ <> 0 ; # THAI DIGIT ZERO
 ๑ <> 1 ; # THAI DIGIT ONE
 ๒ <> 2 ; # THAI DIGIT TWO
 ๐ <> 0 ; # THAI DIGIT ZERO
 ๑ <> 1 ; # THAI DIGIT ONE
 ๒ <> 2 ; # THAI DIGIT TWO


@@ -165,23 +107,14 @@ $notHAccent1 = $freeStandingBelow [^$hAccent];
 ๗ <> 7 ; # THAI DIGIT SEVEN
 ๘ <> 8 ; # THAI DIGIT EIGHT
 ๙ <> 9 ; # THAI DIGIT NINE
 ๗ <> 7 ; # THAI DIGIT SEVEN
 ๘ <> 8 ; # THAI DIGIT EIGHT
 ๙ <> 9 ; # THAI DIGIT NINE

-

 ๚ <> '||' ; # THAI CHARACTER ANGKHANKHU
 ๚ <> '||' ; # THAI CHARACTER ANGKHANKHU

-

 ๛ <> » ; # THAI CHARACTER KHOMUT
 ๆ <> « ; # THAI CHARACTER MAIYAMOK
 ๛ <> » ; # 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
-
+\u0E3A <> ˌ ; # THAI CHARACTER PHINTHU
+\u0E34 <> i ; # THAI CHARACTER SARA I

 | k < g ;
 | k < h ;
 | c < j ;
 | k < q ;
 | s < z ;
 | k < g ;
 | k < h ;
 | c < j ;
 | k < q ;
 | s < z ;

-

 :: (lower);
 :: (lower);