Index: source/data/translit/az_Cyrl_az_BGN.txt |
diff --git a/source/data/translit/Azerbaijani_Latin_BGN.txt b/source/data/translit/az_Cyrl_az_BGN.txt |
similarity index 52% |
rename from source/data/translit/Azerbaijani_Latin_BGN.txt |
rename to source/data/translit/az_Cyrl_az_BGN.txt |
index 500fdc13a0729cd7069513a098b8b9d4c17c3d83..8b5be34576f2cc9b4a8d594122ee813c19c9cccc 100644 |
--- a/source/data/translit/Azerbaijani_Latin_BGN.txt |
+++ b/source/data/translit/az_Cyrl_az_BGN.txt |
@@ -1,14 +1,43 @@ |
-# *************************************************************************** |
-# * |
-# * Copyright (C) 2004-2015, International Business Machines |
-# * Corporation; Unicode, Inc.; and others. All Rights Reserved. |
-# * |
-# *************************************************************************** |
-# File: Azerbaijani_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: az_Cyrl_az_BGN.txt |
+# Generated from CLDR |
+# |
+ |
+# |
+######################################################################## |
+# BGN/PCGN 1993 Agreement |
+# |
+# Azerbaijani is the official language of Azerbaijan. In 1991, the |
+# Azerbaijani government adopted a Roman alphabet to replace the |
+# existing Cyrillic alphabet. The Azerbaijani Cyrillic alphabet |
+# contains nine letters not present in the Russian alphabet: |
+# Ғғ, Әә, Јј, Ҝҝ, Өө, Үү, Һһ, Ҹҹ, and ’. Four obsolete letters |
+# Йй, Ээ, Юю and Яя are also given. |
+# |
+# The Azerbaijani Alphabet as defined by the BGN (Page 13): |
+# |
+# АБВГҒДЕӘЖЗИЫЈКҜЛМНОӨПРСТУҮФХҺЧҸШЙЭЮЯ |
+# абвгғдеәжзиыјкҝлмноөпрстуүфхһчҹш’йэюя |
+# |
+# Originally prepared by Michael Everson <everson@evertype.com> |
+######################################################################## |
+# |
+# MINIMAL FILTER: AzerbaijaniCyrl-Latin |
# |
:: [АБВГҒДЕӘЖЗИЫКҜЛМНОӨПРСТУҮФХҺЧҸШЙЭЮЯабвгғдеәжзиыкҝлмноөпрстуүфхһчҹш’йэюя] ; |
:: NFD (NFC) ; |
+# |
+# |
+######################################################################## |
+# |
+######################################################################## |
+# |
+# Define All Transformation Variables |
+# |
+######################################################################## |
+# |
$prime = ’ ; |
$wordBoundary = [^[:L:][:M:][:N:]] ; |
$upperConsonants = [БВГҒДЖЗЈКҜЛМНПРСТФХҺЧҸШЙ] ; |
@@ -18,6 +47,20 @@ $upperVowels = [АЕӘИЫОӨУҮЭЮЯ] ; |
$lowerVowels = [аеәиыоөуүэюя] ; |
$vowels = [$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 |
+# |
+# |
+# |
+######################################################################## |
+# |
+######################################################################## |
+# |
+# Start of Alphabetic Transformations |
+# |
+######################################################################## |
А → A ; # CYRILLIC CAPITAL LETTER A |
а → a ; # CYRILLIC SMALL LETTER A |
Б → B ; # CYRILLIC CAPITAL LETTER BE |
@@ -32,8 +75,33 @@ $lower = [$lowerConsonants $lowerVowels] ; |
д → d ; # CYRILLIC SMALL LETTER DE |
Е → E ; # CYRILLIC CAPITAL LETTER DE |
е → e ; # CYRILLIC SMALL LETTER DE |
+# |
+######################################################################## |
+# |
+# BGN Page 14 Note 1 |
+# |
+# The special letter Ə ə, known as schwa, should be reproduced in that |
+# form whenever encountered. In those instances when it cannot be |
+# reproduced, however, the letter Ä ä may be substituted for it. |
+# |
+######################################################################## |
+# |
Ә → Ə; # CYRILLIC CAPITAL LETTER SCHWA |
ә → ə; # CYRILLIC SMALL LETTER SCHWA |
+# |
+# |
+# Alternative rule when schwa is not available. To apply uncomment the |
+# following by removing the '#' mark at the start of the line and insert |
+# before the two rule lines above. |
+# |
+# Ә → Ä; # CYRILLIC CAPITAL LETTER SCHWA |
+# ә → ä; # CYRILLIC SMALL LETTER SCHWA |
+# |
+######################################################################## |
+# |
+# End BGN Page 14 Note 1 |
+# |
+######################################################################## |
Ж → J ; # CYRILLIC CAPITAL LETTER ZHE |
ж → j ; # CYRILLIC SMALL LETTER ZHE |
З → Z ; # CYRILLIC CAPITAL LETTER ZE |
@@ -82,6 +150,25 @@ $lower = [$lowerConsonants $lowerVowels] ; |
ҹ → c ; # CYRILLIC SMALL LETTER CHE WITH VERTICAL STROKE |
Ш → Ş ; # CYRILLIC CAPITAL LETTER SHA |
ш → ş ; # CYRILLIC SMALL LETTER SHA |
+# |
+######################################################################## |
+# |
+# BGN Page 13 Rule 33, maps the symbol onto itself and |
+# is ignored here for computational efficiency. |
+# |
+# $prime → $prime ; # RIGHT SINGLE QUOTATION MARK |
+# |
+######################################################################## |
+# |
+######################################################################## |
+# |
+# BGN Page 14 Note 2: |
+# |
+# The obsolete characters й, э, ю, and я should be romanized ẏ, ė, |
+# yu\u0307, and yȧ. |
+# |
+######################################################################## |
+# |
Й → Ẏ ; # CYRILLIC CAPITAL LETTER HARD SIGN |
й → ẏ ; # CYRILLIC SMALL LETTER HARD SIGN |
Э → Ė ; # CYRILLIC CAPITAL LETTER SOFT SIGN |
@@ -92,3 +179,11 @@ $lower = [$lowerConsonants $lowerVowels] ; |
Я} $lower → Yȧ ; # CYRILLIC CAPITAL LETTER YA |
Я → YȦ ; # CYRILLIC CAPITAL LETTER YA |
я → yȧ ; # CYRILLIC SMALL LETTER YA |
+# |
+# |
+######################################################################## |
+# |
+# End BGN Page 14 Note 2. |
+# |
+######################################################################## |
+ |