| Index: source/data/translit/uk_uk_Latn_BGN.txt
|
| diff --git a/source/data/translit/Ukrainian_Latin_BGN.txt b/source/data/translit/uk_uk_Latn_BGN.txt
|
| similarity index 50%
|
| rename from source/data/translit/Ukrainian_Latin_BGN.txt
|
| rename to source/data/translit/uk_uk_Latn_BGN.txt
|
| index e6349978bdad43dc459dfcb4befcb06d3e381a80..c2da7942049c5700ccb473579034d3168ff71c67 100644
|
| --- a/source/data/translit/Ukrainian_Latin_BGN.txt
|
| +++ b/source/data/translit/uk_uk_Latn_BGN.txt
|
| @@ -1,14 +1,41 @@
|
| -# ***************************************************************************
|
| -# *
|
| -# * Copyright (C) 2004-2015, International Business Machines
|
| -# * Corporation; Unicode, Inc.; and others. All Rights Reserved.
|
| -# *
|
| -# ***************************************************************************
|
| -# File: Ukrainian_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: uk_uk_Latn_BGN.txt
|
| +# Generated from CLDR
|
| +#
|
| +
|
| +#
|
| +########################################################################
|
| +# BGN/PCGN 1979 System
|
| +#
|
| +# The BGN/PCGN system for Ukrainian was designed for use in romanizing
|
| +# names written in the Ukrainian alphabet. The Ukrainian alphabet
|
| +# contains five letters not present in the Russian alphabet:
|
| +# Ґґ, Єє, Іі, Її, and ’.
|
| +#
|
| +# The Ukrainian Alphabet as defined by the BGN (Page 105):
|
| +#
|
| +# АБВГҐДЕЄЖЗИІЇЙКЛМНОПРСТУФХЦЧШЩЮЯЬ
|
| +# абвгґдеєжзиіїйклмнопрстуфхцчшщюяь’
|
| +#
|
| +# Originally prepared by Michael Everson <everson@evertype.com>
|
| +########################################################################
|
| +#
|
| +# MINIMAL FILTER: Ukrainian-Latin
|
| #
|
| :: [АБВГҐДЕЄЖЗИІЇЙКЛМНОПРСТУФХЦЧШЩЮЯЬабвгґдеєжзиіїйклмнопрстуфхцчшщюяь’] ;
|
| :: NFC ;
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +########################################################################
|
| +#
|
| +# Define All Transformation Variables
|
| +#
|
| +########################################################################
|
| +#
|
| $prime = ʹ ;
|
| $doublePrime = ʺ ;
|
| $upperConsonants = [БВГҐДЖЗЙКЛМНПРСТФХЦЧШЩЬ] ;
|
| @@ -18,17 +45,49 @@ $upperVowels = [АЕЄИІЇОУЮЯ] ;
|
| $lowerVowels = [аеєиіїоуюя] ;
|
| $vowels = [$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
|
| Б → B ; # CYRILLIC CAPITAL LETTER BE
|
| б → b ; # CYRILLIC SMALL LETTER BE
|
| В → V ; # CYRILLIC CAPITAL LETTER VE
|
| в → v ; # CYRILLIC SMALL LETTER VE
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# Comment. The BGN gives h as the transliteration for both г and ґ.
|
| +# This is an error: г is h and ґ is g.
|
| +#
|
| +########################################################################
|
| +#
|
| Г → H ; # CYRILLIC CAPITAL LETTER GHE
|
| г → h ; # CYRILLIC SMALL LETTER GHE
|
| Ґ → G ; # CYRILLIC CAPITAL LETTER GHE WITH UPTURN
|
| ґ → g ; # CYRILLIC SMALL LETTER GHE WITH UPTURN
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# End Comment.
|
| +#
|
| +########################################################################
|
| +#
|
| Д → D ; # CYRILLIC CAPITAL LETTER DE
|
| д → d ; # CYRILLIC SMALL LETTER DE
|
| Е → E ; # CYRILLIC CAPITAL LETTER IE
|
| @@ -39,11 +98,33 @@ $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 105 Rule 1
|
| +#
|
| +# The character sequences зг, кг, сг, тс, and цг may be romanized
|
| +# z·h, k·h, s·h, t·s, and ts·h in order to differentiate those
|
| +# romanizations from the digraphs zh, kh, sh, ts, and the letter
|
| +# sequence tsh, which are used to render the characters ж, х, ш, ц
|
| +# and the character sequence тш.
|
| +#
|
| +########################################################################
|
| +#
|
| ЗГ → Z·H ; # CYRILLIC CAPITAL LETTER ZE
|
| Зг → Z·h ; # CYRILLIC CAPITAL LETTER ZE
|
| зг → z·h ; # CYRILLIC SMALL LETTER ZE
|
| З → Z ; # CYRILLIC CAPITAL LETTER ZE
|
| з → z ; # CYRILLIC SMALL LETTER ZE
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# End Rule 1
|
| +#
|
| +########################################################################
|
| +#
|
| И → Y ; # CYRILLIC CAPITAL LETTER I
|
| и → y ; # CYRILLIC SMALL LETTER I
|
| І → I ; # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
|
| @@ -53,11 +134,29 @@ $wordBoundary = [^[:L:][:M:][:N:]] ;
|
| ї → yi ; # CYRILLIC SMALL LETTER YI
|
| Й → Y ; # CYRILLIC CAPITAL LETTER I
|
| й → y ; # CYRILLIC SMALL LETTER I
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# BGN Page 105 Rule 1
|
| +#
|
| +# кг becomes k·h
|
| +#
|
| +########################################################################
|
| +#
|
| КГ → K·H ; # CYRILLIC CAPITAL LETTER KA
|
| Кг → K·h ; # CYRILLIC CAPITAL LETTER KA
|
| кг → k·h ; # CYRILLIC SMALL LETTER KA
|
| К → K ; # CYRILLIC CAPITAL LETTER KA
|
| к → k ; # CYRILLIC SMALL LETTER KA
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# End Rule 1
|
| +#
|
| +########################################################################
|
| +#
|
| Л → L ; # CYRILLIC CAPITAL LETTER EL
|
| л → l ; # CYRILLIC SMALL LETTER EL
|
| М → M ; # CYRILLIC CAPITAL LETTER EM
|
| @@ -70,16 +169,50 @@ $wordBoundary = [^[:L:][:M:][:N:]] ;
|
| п → p ; # CYRILLIC SMALL LETTER PE
|
| Р → R ; # CYRILLIC CAPITAL LETTER ER
|
| р → r ; # CYRILLIC SMALL LETTER ER
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# BGN Page 105 Rule 1
|
| +#
|
| +# сг becomes s·h
|
| +#
|
| +########################################################################
|
| +#
|
| СГ → S·H ; # CYRILLIC CAPITAL LETTER ES
|
| Сг → S·h ; # CYRILLIC CAPITAL LETTER ES
|
| сг → s·h ; # CYRILLIC SMALL LETTER ES
|
| С → S ; # CYRILLIC CAPITAL LETTER ES
|
| с → s ; # CYRILLIC SMALL LETTER ES
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# End Rule 1
|
| +#
|
| +########################################################################
|
| +#
|
| +########################################################################
|
| +#
|
| +# BGN Page 105 Rule 1
|
| +#
|
| +# тс becomes t·s
|
| +#
|
| +########################################################################
|
| +#
|
| ТС → T·S ; # CYRILLIC CAPITAL LETTER TE
|
| Тс → T·s ; # CYRILLIC CAPITAL LETTER TE
|
| тс → t·s ; # CYRILLIC SMALL LETTER TE
|
| Т → T ; # CYRILLIC CAPITAL LETTER TE
|
| т → t ; # CYRILLIC SMALL LETTER TE
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# End Rule 1
|
| +#
|
| +########################################################################
|
| +#
|
| У → U ; # CYRILLIC CAPITAL LETTER U
|
| у → u ; # CYRILLIC SMALL LETTER U
|
| Ф → F ; # CYRILLIC CAPITAL LETTER EF
|
| @@ -87,15 +220,43 @@ $wordBoundary = [^[:L:][:M:][:N:]] ;
|
| Х} $lower → Kh ; # CYRILLIC CAPITAL LETTER HA
|
| Х → KH ; # CYRILLIC CAPITAL LETTER HA
|
| х → kh ; # CYRILLIC SMALL LETTER HA
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# BGN Page 105 Rule 1
|
| +#
|
| +# цг becomes ts·h
|
| +#
|
| +########################################################################
|
| +#
|
| ЦГ → TS·H ; # CYRILLIC CAPITAL LETTER TSE
|
| Цг → Ts·h ; # CYRILLIC CAPITAL LETTER TSE
|
| цг → ts·h ; # CYRILLIC SMALL LETTER TSE
|
| 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
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# BGN Page 94 Rule 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
|
| @@ -105,6 +266,14 @@ $wordBoundary = [^[:L:][:M:][:N:]] ;
|
| Щ} $lower → Shch ; # CYRILLIC CAPITAL LETTER SHCHA
|
| Щ → SHCH ; # CYRILLIC CAPITAL LETTER SHCHA
|
| щ → shch ; # CYRILLIC SMALL LETTER SHCHA
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# End Rule 3.6
|
| +#
|
| +########################################################################
|
| +#
|
| Ю} $lower → Yu ; # CYRILLIC CAPITAL LETTER YU
|
| Ю → YU ; # CYRILLIC CAPITAL LETTER YU
|
| ю → yu ; # CYRILLIC SMALL LETTER YU
|
| @@ -114,3 +283,7 @@ $wordBoundary = [^[:L:][:M:][:N:]] ;
|
| Ь → $prime ; # CYRILLIC CAPITAL LETTER SOFT SIGN
|
| ь → $prime ; # CYRILLIC SMALL LETTER SOFT SIGN
|
| ’ → $doublePrime ; # LEFT SINGLE QUOTATION MARK
|
| +#
|
| +#
|
| +########################################################################
|
| +
|
|
|