287 lines
12 KiB
Plaintext
287 lines
12 KiB
Plaintext
// *******************************************************************************
|
|
// *
|
|
// * Copyright (C) 1999-2001, International Business Machines
|
|
// * Corporation and others. All Rights Reserved.
|
|
// *
|
|
// *******************************************************************************
|
|
|
|
th {
|
|
BreakDictionaryData:import { "../brkitr/thaidict.brk" }
|
|
AmPmMarkers {
|
|
"\u0E01\u0E48\u0E2D\u0E19\u0E40\u0E17\u0E35\u0E48\u0E22\u0E07",
|
|
"\u0E2B\u0E25\u0E31\u0E07\u0E40\u0E17\u0E35\u0E48\u0E22\u0E07",
|
|
}
|
|
Version{ "1.1.1" }
|
|
// -------------------- ibm.597 --------------------
|
|
//
|
|
// First put in all of the consonants, after Z
|
|
//
|
|
CollationElements {
|
|
Version { "2.0" }
|
|
Sequence { "[normalization on]& Z "
|
|
"< \u0E01 " // KO KAI
|
|
"< \u0E02 " // KHO KHAI
|
|
"< \u0E03 " // KHO KHUAT
|
|
"< \u0E04 " // KHO KHWAI
|
|
"< \u0E05 " // KHO KHON
|
|
"< \u0E06 " // KHO RAKHANG
|
|
"< \u0E07 " // NGO NGU
|
|
"< \u0E08 " // CHO CHAN
|
|
"< \u0E09 " // CHO CHING
|
|
"< \u0E0A " // CHO CHANG
|
|
"< \u0E0B " // SO SO
|
|
"< \u0E0C " // CHO CHOE
|
|
"< \u0E0D " // YO YING
|
|
"< \u0E0E " // DO CHADA
|
|
"< \u0E0F " // TO PATAK
|
|
"< \u0E10 " // THO THAN
|
|
"< \u0E11 " // THO NANGMONTHO
|
|
"< \u0E12 " // THO PHUTHAO
|
|
"< \u0E13 " // NO NEN
|
|
"< \u0E14 " // DO DEK
|
|
"< \u0E15 " // TO TAO
|
|
"< \u0E16 " // THO THUNG
|
|
"< \u0E17 " // THO THAHAN
|
|
"< \u0E18 " // THO THONG
|
|
"< \u0E19 " // NO NU
|
|
"< \u0E1A " // BO BAIMAI
|
|
"< \u0E1B " // PO PLA
|
|
"< \u0E1C " // PHO PHUNG
|
|
"< \u0E1D " // FO FA
|
|
"< \u0E1E " // PHO PHAN
|
|
"< \u0E1F " // FO FAN
|
|
"< \u0E20 " // PHO SAMPHAO
|
|
"< \u0E21 " // MO MA
|
|
"< \u0E22 " // YO YAK
|
|
"< \u0E23 " // RO RUA
|
|
"< \u0E24 " // RU
|
|
"< \u0E24\u0E45 " // See the comment below on LAKKHANGYAO
|
|
"< \u0E25 " // LO LING
|
|
"< \u0E26 " // LU
|
|
"< \u0E26\u0E45 " // See the comment below on LAKKHANGYAO
|
|
"< \u0E27 " // WO WAEN
|
|
"< \u0E28 " // SO SALA
|
|
"< \u0E29 " // SO RUSI
|
|
"< \u0E2A " // SO SUA
|
|
"< \u0E2B " // HO HIP
|
|
"< \u0E2C " // LO CHULA
|
|
"< \u0E2D " // O ANG
|
|
"< \u0E2E " // HO NOKHUK
|
|
|
|
//
|
|
// Normal vowels
|
|
//
|
|
"< \u0E30 " // SARA A
|
|
"< \u0E31 " // MAI HAN-AKAT
|
|
"< \u0E32 " // SARA AA
|
|
|
|
// Normalizer will decompose this character to \u0e4d\u0e32.
|
|
// This is a Bad Thing, because we want the separate
|
|
// characters to sort differently than this individual one.
|
|
// Since there's no public way to set the decomposition to be
|
|
// used when creating a collator, there's no way around this
|
|
// right now. It's best to go ahead and leave the character
|
|
// in, because it occurs this way a lot more often than it
|
|
// occurs as separate characters.
|
|
"< \u0E33 " // SARA AM
|
|
|
|
"< \u0E34 " // SARA I
|
|
|
|
"< \u0E35 " // SARA II
|
|
"< \u0E36 " // SARA UE
|
|
"< \u0E37 " // SARA UEE
|
|
"< \u0E38 " // SARA U
|
|
"< \u0E39 " // SARA UU
|
|
|
|
//
|
|
// Preceding vowels
|
|
//
|
|
"< \u0E40 " // SARA E
|
|
"< \u0E41 " // SARA AE
|
|
"< \u0E42 " // SARA O
|
|
"< \u0E43 " // SARA AI MAIMUAN
|
|
"< \u0E44 " // SARA AI MAIMALAI
|
|
|
|
//
|
|
// Digits
|
|
//
|
|
"< \u0E50 " // DIGIT ZERO
|
|
"< \u0E51 " // DIGIT ONE
|
|
"< \u0E52 " // DIGIT TWO
|
|
"< \u0E53 " // DIGIT THREE
|
|
"< \u0E54 " // DIGIT FOUR
|
|
"< \u0E55 " // DIGIT FIVE
|
|
"< \u0E56 " // DIGIT SIX
|
|
"< \u0E57 " // DIGIT SEVEN
|
|
"< \u0E58 " // DIGIT EIGHT
|
|
"< \u0E59 " // DIGIT NINE
|
|
|
|
// Sorta tonal marks, but maybe not really
|
|
"< \u0E4D " // NIKHAHIT
|
|
|
|
// Thai symbols are supposed to sort "after white space". I'm
|
|
// treating this as making them sort just after the normal
|
|
// Latin-1 symbols, which are in turn after the white space.
|
|
"&'\u007d'" // right-brace
|
|
"< \u0E2F " // PAIYANNOI (ellipsis, abbreviation)
|
|
"< \u0E46 " // MAIYAMOK
|
|
"< \u0E4F " // FONGMAN
|
|
"< \u0E5A " // ANGKHANKHU
|
|
"< \u0E5B " // KHOMUT
|
|
"< \u0E3F " // CURRENCY SYMBOL BAHT
|
|
|
|
// These symbols are supposed to be "after all characters"
|
|
"< \u0E4E " // YAMAKKAN
|
|
|
|
// This rare symbol also comes after all characters. But when it is
|
|
// used in combination with RU and LU, the combination is treated as
|
|
// a separate letter, ala "CH" sorting after "C" in traditional Spanish.
|
|
// see above.
|
|
"< \u0E45 " // LAKKHANGYAO
|
|
|
|
// Tonal marks are primary ignorables but are treated as secondary
|
|
// differences
|
|
"& \u0301 " // acute accent
|
|
"; \u0E47 " // MAITAIKHU
|
|
"; \u0E48 " // MAI EK
|
|
"; \u0E49 " // MAI THO
|
|
"; \u0E4A " // MAI TRI
|
|
"; \u0E4B " // MAI CHATTAWA
|
|
"; \u0E4C " // THANTHAKHAT
|
|
|
|
|
|
// These are supposed to be ignored, so I'm treating them as controls
|
|
"& \u0001 "
|
|
"= \u0E3A " // PHINTHU
|
|
"= '.' " // period
|
|
}
|
|
}
|
|
Countries {
|
|
TH { "\u0E1B\u0E23\u0E30\u0E40\u0E17\u0E28\u0E44\u0E17\u0E22" }
|
|
}
|
|
DateTimePatterns {
|
|
"H' \u0E19\u0E32\u0E2C\u0E34\u0E01\u0E32 'm' \u0E19\u0E32\u0E17\u0E35 'ss' \u0E27"
|
|
"\u0E34\u0E19\u0E32\u0E17\u0E35'",
|
|
"H' \u0E19\u0E32\u0E2C\u0E34\u0E01\u0E32 'm' \u0E19\u0E32\u0E17\u0E35'",
|
|
"H:mm:ss",
|
|
"H:mm",
|
|
"EEEE'\u0E17\u0E35\u0E48 'd MMMM G yyyy",
|
|
"d MMMM yyyy",
|
|
"d MMM yyyy",
|
|
"d/M/yyyy",
|
|
"{1}, {0}",
|
|
}
|
|
DayAbbreviations {
|
|
"\u0E2D\u0E32.",
|
|
"\u0E08.",
|
|
"\u0E2D.",
|
|
"\u0E1E.",
|
|
"\u0E1E\u0E24.",
|
|
"\u0E28.",
|
|
"\u0E2A.",
|
|
}
|
|
DayNames {
|
|
"\u0E27\u0E31\u0E19\u0E2D\u0E32\u0E17\u0E34\u0E15\u0E22\u0E4C",
|
|
"\u0E27\u0E31\u0E19\u0E08\u0E31\u0E19\u0E17\u0E23\u0E4C",
|
|
"\u0E27\u0E31\u0E19\u0E2D\u0E31\u0E07\u0E04\u0E32\u0E23",
|
|
"\u0E27\u0E31\u0E19\u0E1E\u0E38\u0E18",
|
|
"\u0E27\u0E31\u0E19\u0E1E\u0E24\u0E2B\u0E31\u0E2A\u0E1A\u0E14\u0E35",
|
|
"\u0E27\u0E31\u0E19\u0E28\u0E38\u0E01\u0E23\u0E4C",
|
|
"\u0E27\u0E31\u0E19\u0E40\u0E2A\u0E32\u0E23\u0E4C",
|
|
}
|
|
Eras {
|
|
"\u0E1B\u0E35\u0E01\u0E48\u0E2D\u0E19\u0E04\u0E23\u0E34\u0E2A\u0E15\u0E4C\u0E01\u0E32"
|
|
"\u0E25\u0E17\u0E35\u0E48",
|
|
"\u0E04.\u0E28.",
|
|
}
|
|
Languages {
|
|
th { "\u0E44\u0E17\u0E22" }
|
|
}
|
|
LocaleID { "1e" }
|
|
LocaleString { "th" }
|
|
MonthAbbreviations {
|
|
"\u0E21.\u0E04.",
|
|
"\u0E01.\u0E1E.",
|
|
"\u0E21\u0E35.\u0E04.",
|
|
"\u0E40\u0E21.\u0E22.",
|
|
"\u0E1E.\u0E04.",
|
|
"\u0E21\u0E34.\u0E22.",
|
|
"\u0E01.\u0E04.",
|
|
"\u0E2A.\u0E04.",
|
|
"\u0E01.\u0E22.",
|
|
"\u0E15.\u0E04.",
|
|
"\u0E1E.\u0E22.",
|
|
"\u0E18.\u0E04.",
|
|
"",
|
|
}
|
|
MonthNames {
|
|
"\u0E21\u0E01\u0E23\u0E32\u0E04\u0E21",
|
|
"\u0E01\u0E38\u0E21\u0E20\u0E32\u0E1E\u0E31\u0E19\u0E18\u0E4C",
|
|
"\u0E21\u0E35\u0E19\u0E32\u0E04\u0E21",
|
|
"\u0E40\u0E21\u0E29\u0E32\u0E22\u0E19",
|
|
"\u0E1E\u0E24\u0E29\u0E20\u0E32\u0E04\u0E21",
|
|
"\u0E21\u0E34\u0E16\u0E38\u0E19\u0E32\u0E22\u0E19",
|
|
"\u0E01\u0E23\u0E01\u0E0E\u0E32\u0E04\u0E21",
|
|
"\u0E2A\u0E34\u0E07\u0E2B\u0E32\u0E04\u0E21",
|
|
"\u0E01\u0E31\u0E19\u0E22\u0E32\u0E22\u0E19",
|
|
"\u0E15\u0E38\u0E25\u0E32\u0E04\u0E21",
|
|
"\u0E1E\u0E24\u0E28\u0E08\u0E34\u0E01\u0E32\u0E22\u0E19",
|
|
"\u0E18\u0E31\u0E19\u0E27\u0E32\u0E04\u0E21",
|
|
"",
|
|
}
|
|
ShortLanguage { "tha" }
|
|
localPatternChars { "GanjkHmsSEDFwWxhKzAe" }
|
|
zoneStrings {
|
|
{
|
|
"THA",
|
|
"Thailand Time",
|
|
"THA",
|
|
"Thailand Time",
|
|
"THA",
|
|
"Bangkok",
|
|
}
|
|
}
|
|
LocaleScript{
|
|
"Thai", // Script Name
|
|
}
|
|
|
|
//------------------------------------------------------------
|
|
// Rule Based Number Format Support
|
|
//------------------------------------------------------------
|
|
|
|
// Spellout rules for Thai. Data from Suwit Srivilairith, IBM Thailand
|
|
|
|
SpelloutRules {
|
|
"%default:\n"
|
|
" -x: \u0e25\u0e1a>>;\n"
|
|
" x.x: <<\u0e08\u0e38\u0e14>>>;\n"
|
|
" \u0e28\u0e39\u0e19\u0e22\u0e4c; \u0e2b\u0e19\u0e36\u0e48\u0e07; \u0e2a\u0e2d\u0e07; \u0e2a\u0e32\u0e21;\n"
|
|
" \u0e2a\u0e35\u0e48; \u0e2b\u0e49\u0e32; \u0e2b\u0e01; \u0e40\u0e08\u0e47\u0e14; \u0e41\u0e1b\u0e14;\n"
|
|
" \u0e40\u0e01\u0e49\u0e32; \u0e2a\u0e34\u0e1a; \u0e2a\u0e34\u0e1a\u0e40\u0e2d\u0e47\u0e14;\n"
|
|
" \u0e2a\u0e34\u0e1a\u0e2a\u0e2d\u0e07; \u0e2a\u0e34\u0e1a\u0e2a\u0e32\u0e21;\n"
|
|
" \u0e2a\u0e34\u0e1a\u0e2a\u0e35\u0e48; \u0e2a\u0e34\u0e1a\u0e2b\u0e49\u0e32;\n"
|
|
" \u0e2a\u0e34\u0e1a\u0e2b\u0e01; \u0e2a\u0e34\u0e1a\u0e40\u0e08\u0e47\u0e14;\n"
|
|
" \u0e2a\u0e34\u0e1a\u0e41\u0e1b\u0e14; \u0e2a\u0e34\u0e1a\u0e40\u0e01\u0e49\u0e32;\n"
|
|
" 20: \u0e22\u0e35\u0e48\u0e2a\u0e34\u0e1a[>%%alt-ones>];\n"
|
|
" 30: \u0e2a\u0e32\u0e21\u0e2a\u0e34\u0e1a[>%%alt-ones>];\n"
|
|
" 40: \u0e2a\u0e35\u0e48\u0e2a\u0e34\u0e1a[>%%alt-ones>];\n"
|
|
" 50: \u0e2b\u0e49\u0e32\u0e2a\u0e34\u0e1a[>%%alt-ones>];\n"
|
|
" 60: \u0e2b\u0e01\u0e2a\u0e34\u0e1a[>%%alt-ones>];\n"
|
|
" 70: \u0e40\u0e08\u0e47\u0e14\u0e2a\u0e34\u0e1a[>%%alt-ones>];\n"
|
|
" 80: \u0e41\u0e1b\u0e14\u0e2a\u0e34\u0e1a[>%%alt-ones>];\n"
|
|
" 90: \u0e40\u0e01\u0e49\u0e32\u0e2a\u0e34\u0e1a[>%%alt-ones>];\n"
|
|
" 100: <<\u0e23\u0e49\u0e2d\u0e22[>>];\n"
|
|
" 1000: <<\u0e1e\u0e31\u0e19[>>];\n"
|
|
" 10000: <<\u0e2b\u0e21\u0e37\u0e48\u0e19[>>];\n"
|
|
" 100000: <<\u0e41\u0e2a\u0e19[>>];\n"
|
|
" 1,000,000: <<\u0e25\u0e49\u0e32\u0e19[>>];\n"
|
|
" 1,000,000,000: <<\u0e1e\u0e31\u0e19\u0e25\u0e49\u0e32\u0e19[>>];\n"
|
|
" 1,000,000,000,000: <<\u0e25\u0e49\u0e32\u0e19\u0e25\u0e49\u0e32\u0e19[>>];\n"
|
|
" 1,000,000,000,000,000: =#,##0=;\n"
|
|
"%%alt-ones:\n"
|
|
" \u0e28\u0e39\u0e19\u0e22\u0e4c;\n"
|
|
" \u0e40\u0e2d\u0e47\u0e14;\n"
|
|
" =%default=;\n";
|
|
}
|
|
}
|