| Index: source/data/translit/kk_kk_Latn_BGN.txt
|
| diff --git a/source/data/translit/Kazakh_Latin_BGN.txt b/source/data/translit/kk_kk_Latn_BGN.txt
|
| similarity index 51%
|
| rename from source/data/translit/Kazakh_Latin_BGN.txt
|
| rename to source/data/translit/kk_kk_Latn_BGN.txt
|
| index ed695acbddaebe9961cbdc903ff269273d19a435..d9ef30e974cbf2112a904c536b8e15c8a6b2c5e0 100644
|
| --- a/source/data/translit/Kazakh_Latin_BGN.txt
|
| +++ b/source/data/translit/kk_kk_Latn_BGN.txt
|
| @@ -1,14 +1,41 @@
|
| -# ***************************************************************************
|
| -# *
|
| -# * Copyright (C) 2004-2015, International Business Machines
|
| -# * Corporation; Unicode, Inc.; and others. All Rights Reserved.
|
| -# *
|
| -# ***************************************************************************
|
| -# File: Kazakh_Latin_BGN.txt
|
| -# Generated from CLDR
|
| +# © 2016 and later: Unicode, Inc. and others.
|
| +# License & terms of use: http://www.unicode.org/copyright.html#License
|
| +#
|
| +# File: kk_kk_Latn_BGN.txt
|
| +# Generated from CLDR
|
| +#
|
| +
|
| +#
|
| +########################################################################
|
| +# BGN/PCGN 1979 System
|
| +#
|
| +# The BGN/PCGN system for Kazakh Cyrillic was designed for use in
|
| +# romanizing names written in the Kazakh Cyrillic alphabet.
|
| +# The Kazakh Cyrillic alphabet contains nine letters not present
|
| +# in the Russian alphabet: Әә, Ғғ, Ққ, Ңң, Өө, Ұұ, Үү, Һһ, and Іі.
|
| +#
|
| +# The Kazakh Cyrillic Alphabet as defined by the BGN (Page 47):
|
| +#
|
| +# АӘБВГҒДЕЁЖЗИЙКҚЛМНҢОӨПРСТУҰҮФХҺЦЧШЩЪЫІЬЭЮЯ
|
| +# аәбвгғдеёжзийкқлмнңоөпрстуұүфхһцчшщъыіьэюя
|
| +#
|
| +# Originally prepared by Michael Everson <everson@evertype.com>
|
| +########################################################################
|
| +#
|
| +# MINIMAL FILTER: KazakhCyrl-Latin
|
| #
|
| :: [АӘБВГҒДЕЁЖЗИЙКҚЛМНҢОӨПРСТУҰҮФХҺЦЧШЩЪЫІЬЭЮЯаәбвгғдеёжзийкқлмнңоөпрстуұүфхһцчшщъыіьэюя] ;
|
| :: NFD (NFC) ;
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +########################################################################
|
| +#
|
| +# Define All Transformation Variables
|
| +#
|
| +########################################################################
|
| +#
|
| $prime = ʹ ;
|
| $doublePrime = ʺ ;
|
| $upperConsonants = [БВГҒДЖЗЙКҚЛМНҢПРСТФХҺЦЧШЩЪЬ] ;
|
| @@ -18,7 +45,22 @@ $upperVowels = [АӘЕЁИОӨУҰҮЫІЭЮЯ] ;
|
| $lowerVowels = [аәеёиоөуұүыіэюя] ;
|
| $vowels = [$upperVowels $lowerVowels] ;
|
| $lower = [$lowerConsonants $lowerVowels] ;
|
| +#
|
| +#
|
| +# Use this $wordBoundary until bug 2034 is fixed in ICU:
|
| +# http://bugs.icu-project.org/cgi-bin/icu-bugs/transliterate?id=2034;expression=boundary;user=guest
|
| +#
|
| $wordBoundary = [^[:L:][:M:][:N:]] ;
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +########################################################################
|
| +#
|
| +# Start of Alphabetic Transformations
|
| +#
|
| +########################################################################
|
| +#
|
| А → A ; # CYRILLIC CAPITAL LETTER A
|
| а → a ; # CYRILLIC SMALL LETTER A
|
| Ә → Ä ; # CYRILLIC CAPITAL LETTER SCHWA
|
| @@ -27,11 +69,33 @@ $wordBoundary = [^[:L:][:M:][:N:]] ;
|
| б → b ; # CYRILLIC SMALL LETTER BE
|
| В → V ; # CYRILLIC CAPITAL LETTER VE
|
| в → v ; # CYRILLIC SMALL LETTER VE
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# BGN Page 48 Rule 1
|
| +#
|
| +# The character sequences гһ, зһ, кһ, нг, сһ and цһ may be romanized
|
| +# g·h, z·h, k·h, n·g, s·h and ts·h in order to differentiate those
|
| +# romanizations from the digraphs gh, zh, kh, ng, sh, and the letter
|
| +# sequence tsh, which are used to render the characters г, ж, х, ң, ш,
|
| +# and the character sequence тш.
|
| +#
|
| +########################################################################
|
| +#
|
| ГҺ → G·H ; # CYRILLIC CAPITAL LETTER GHE
|
| Гһ → G·h ; # CYRILLIC CAPITAL LETTER GHE
|
| гһ → g·h ; # CYRILLIC SMALL LETTER GHE
|
| Г → G ; # CYRILLIC CAPITAL LETTER GHE
|
| г → g ; # CYRILLIC SMALL LETTER GHE
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# End Rule 1
|
| +#
|
| +########################################################################
|
| +#
|
| Ғ} $lower → Gh ; # CYRILLIC CAPITAL LETTER GHE WITH STROKE
|
| Ғ → GH ; # CYRILLIC CAPITAL LETTER GHE WITH STROKE
|
| ғ → gh ; # CYRILLIC SMALL LETTER GHE WITH STROKE
|
| @@ -45,31 +109,85 @@ $wordBoundary = [^[:L:][:M:][:N:]] ;
|
| Ж} $lower → Zh ; # CYRILLIC CAPITAL LETTER ZHE
|
| Ж → ZH ; # CYRILLIC CAPITAL LETTER ZHE
|
| ж → zh ; # CYRILLIC SMALL LETTER ZHE
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# BGN Page 48 Rule 1
|
| +#
|
| +# зһ becomes z·h
|
| +#
|
| +########################################################################
|
| +#
|
| ЗҺ → Z·H ; # CYRILLIC CAPITAL LETTER ZE
|
| Зһ → Z·h ; # CYRILLIC CAPITAL LETTER ZE
|
| зһ → z·h ; # CYRILLIC SMALL LETTER ZE
|
| З → Z ; # CYRILLIC CAPITAL LETTER ZE
|
| з → z ; # CYRILLIC SMALL LETTER ZE
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# End Rule 1
|
| +#
|
| +########################################################################
|
| +#
|
| И → Ī ; # CYRILLIC CAPITAL LETTER I
|
| и → ī ; # CYRILLIC SMALL LETTER I
|
| Й → Y ; # CYRILLIC CAPITAL LETTER I
|
| й → y ; # CYRILLIC SMALL LETTER I
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# BGN Page 48 Rule 1
|
| +#
|
| +# кһ becomes k·h
|
| +#
|
| +########################################################################
|
| +#
|
| КҺ → K·H ; # CYRILLIC CAPITAL LETTER KA
|
| Кһ → K·h ; # CYRILLIC CAPITAL LETTER KA
|
| кһ → k·h ; # CYRILLIC SMALL LETTER KA
|
| К → K ; # CYRILLIC CAPITAL LETTER KA
|
| к → k ; # CYRILLIC SMALL LETTER KA
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# End Rule 1
|
| +#
|
| +########################################################################
|
| +#
|
| Қ → Q ; # CYRILLIC CAPITAL LETTER KA WITH DESCENDER
|
| қ → q ; # CYRILLIC SMALL LETTER KA WITH DESCENDER
|
| Л → L ; # CYRILLIC CAPITAL LETTER EL
|
| л → l ; # CYRILLIC SMALL LETTER EL
|
| М → M ; # CYRILLIC CAPITAL LETTER EM
|
| м → m ; # CYRILLIC SMALL LETTER EM
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# BGN Page 48 Rule 1
|
| +#
|
| +# нг becomes n·g
|
| +#
|
| +########################################################################
|
| +#
|
| НГ → N·G ; # CYRILLIC CAPITAL LETTER EN
|
| Нг → N·g ; # CYRILLIC CAPITAL LETTER EN
|
| нг → n·g ; # CYRILLIC SMALL LETTER EN
|
| Н → N ; # CYRILLIC CAPITAL LETTER EN
|
| н → n ; # CYRILLIC SMALL LETTER EN
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# End Rule 1
|
| +#
|
| +########################################################################
|
| +#
|
| Ң} $lower → Ng ; # CYRILLIC CAPITAL LETTER EN WITH DESCENDER
|
| Ң → NG ; # CYRILLIC CAPITAL LETTER EN WITH DESCENDER
|
| ң → ng ; # CYRILLIC SMALL LETTER EN WITH DESCENDER
|
| @@ -81,11 +199,29 @@ $wordBoundary = [^[:L:][:M:][:N:]] ;
|
| п → p ; # CYRILLIC SMALL LETTER PE
|
| Р → R ; # CYRILLIC CAPITAL LETTER ER
|
| р → r ; # CYRILLIC SMALL LETTER ER
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# BGN Page 48 Rule 1
|
| +#
|
| +# сһ becomes s·h
|
| +#
|
| +########################################################################
|
| +#
|
| СҺ → S·H ; # CYRILLIC CAPITAL LETTER ES
|
| Сһ → S·h ; # CYRILLIC CAPITAL LETTER ES
|
| сһ → s·h ; # CYRILLIC SMALL LETTER ES
|
| С → S ; # CYRILLIC CAPITAL LETTER ES
|
| с → s ; # CYRILLIC SMALL LETTER ES
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# End Rule 1
|
| +#
|
| +########################################################################
|
| +#
|
| Т → T ; # CYRILLIC CAPITAL LETTER TE
|
| т → t ; # CYRILLIC SMALL LETTER TE
|
| У → Ū ; # CYRILLIC CAPITAL LETTER U
|
| @@ -101,15 +237,43 @@ $wordBoundary = [^[:L:][:M:][:N:]] ;
|
| х → kh ; # CYRILLIC SMALL LETTER HA
|
| Һ → H ; # CYRILLIC CAPITAL LETTER SHHA
|
| һ → h ; # CYRILLIC SMALL LETTER SHHA
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# BGN Page 48 Rule 1
|
| +#
|
| +# цһ becomes ts·h
|
| +#
|
| +########################################################################
|
| +#
|
| ЦҺ → TS·H ; # CYRILLIC CAPITAL LETTER GHE
|
| Цһ → Ts·h ; # CYRILLIC CAPITAL LETTER GHE
|
| цһ → ts·h ; # CYRILLIC SMALL LETTER GHE
|
| Ц} $lower → Ts ; # CYRILLIC CAPITAL LETTER TSE
|
| Ц → TS ; # CYRILLIC CAPITAL LETTER TSE
|
| ц → ts ; # CYRILLIC SMALL LETTER TSE
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# End Rule 1
|
| +#
|
| +########################################################################
|
| +#
|
| Ч} $lower → Ch ; # CYRILLIC CAPITAL LETTER CHE
|
| Ч → CH ; # CYRILLIC CAPITAL LETTER CHE
|
| ч → ch ; # CYRILLIC SMALL LETTER CHE
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# Implied rule from BGN Russian-Latin transliteration (Page 94 Note 3.6).
|
| +#
|
| +# шч becomes sh·ch
|
| +#
|
| +########################################################################
|
| +#
|
| ШЧ → SH·CH ; # CYRILLIC CAPITAL LETTER SHA
|
| Шч → Sh·ch ; # CYRILLIC CAPITAL LETTER SHA
|
| шч → sh·ch ; # CYRILLIC SMALL LETTER SHA
|
| @@ -119,10 +283,43 @@ $wordBoundary = [^[:L:][:M:][:N:]] ;
|
| Щ} $lower → Shch ; # CYRILLIC CAPITAL LETTER SHCHA
|
| Щ → SHCH ; # CYRILLIC CAPITAL LETTER SHCHA
|
| щ → shch ; # CYRILLIC SMALL LETTER SHCHA
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# End Implied rule
|
| +#
|
| +########################################################################
|
| +#
|
| Ъ → $doublePrime ; # CYRILLIC CAPITAL LETTER HARD SIGN
|
| ъ → $doublePrime ; # CYRILLIC SMALL LETTER HARD SIGN
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# BGN Page 48 Note 2
|
| +#
|
| +# The character Ыы may be romanized Ɨɨ instead of Yy, if so desired.
|
| +#
|
| +########################################################################
|
| +#
|
| Ы → Y ; # CYRILLIC CAPITAL LETTER YERU
|
| ы → y ; # CYRILLIC SMALL LETTER YERU
|
| +#
|
| +#
|
| +# Alternative rule to implement the option described here. To apply
|
| +# uncomment the following by removing the '#' mark at the start of the
|
| +# line and insert before the two rule lines above.
|
| +#
|
| +#Ы → Ɨ ; # CYRILLIC CAPITAL LETTER YERU
|
| +#ы → ɨ ; # CYRILLIC SMALL LETTER YERU
|
| +#
|
| +########################################################################
|
| +#
|
| +# End BGN Page 48 Note 2
|
| +#
|
| +########################################################################
|
| +#
|
| І → I ; # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
|
| і → i ; # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
|
| Ь → $prime ; # CYRILLIC CAPITAL LETTER SOFT SIGN
|
| @@ -135,3 +332,7 @@ $wordBoundary = [^[:L:][:M:][:N:]] ;
|
| Я} $lower → Ya ; # CYRILLIC CAPITAL LETTER YA
|
| Я → YA ; # CYRILLIC CAPITAL LETTER YA
|
| я → ya ; # CYRILLIC SMALL LETTER YA
|
| +#
|
| +#
|
| +########################################################################
|
| +
|
|
|