AuroraMiddleware/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2024-11-21 12:30:06 +00:00
Code Issues Packages Projects Releases Wiki Activity
master
glibc/localedata/locales/uz_UZ
Mike FABIAN 5176a830e7 localedata: Use consistent values for grouping and mon_grouping 
Resolves: BZ # 31205

Adapt test cases in test-grouping_iterator.c
2024-01-25 11:41:02 +01:00

366 lines
11 KiB
Plaintext
Raw Permalink Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

comment_char %
escape_char /
% This file is part of the GNU C Library and contains locale data.
% The Free Software Foundation does not claim any copyright interest
% in the locale data contained in this file. The foregoing does not
% affect the license of the GNU C Library as a whole. It does not
% exempt you from the conditions of the license if your use would
% otherwise be governed by that license.
% Uzbek (latin) language locale for Uzbekistan
% Source: Bobir Ismailov
% Contact: Bobir Ismailov, Pablo Saratxaga, Mashrab Kuvatov
% Email: bobir_is@yahoo.com, pablo@mandrakesoft.com, kmashrab@uni-bremen.de
% Tel:
% Fax:
% Language: uz
% Territory: UZ
% Revision: 0.5
% Date: 2003-06-27
% Users: general
% Charset: UTF-8
% History:
% 2002-09-09 Mashrab Kuvatov <kmashrab@uni-bremen.de>
% LC_TIME-day: Changed the first letter of all day names to upper case.
% LC_TIME-mon: Changed the first letter of all month names to upper case.
% Fixed a typo. September is not Senyabr, but Sentyabr.
% LC_TIME-abmon: Corrected "Yav" (Yanvar) to "Yan".
%
% 2003-02-24 Mashrab Kuvatov <kmashrab@uni-bremen.de>
% Changed charset to UTF-8
%
% ?????????? Pablo Saratxaga <pablo@mandrakesoft.com>
% LC_CTYPE: Added transliteration from cyrillic to latin.
% LC_COLLATE: Added reodering definition.
LC_IDENTIFICATION
title "Uzbek (latin) locale for Uzbekistan"
source "Bobir Ismailov"
address ""
contact "Bobir Ismailov, Pablo Saratxaga, Mashrab Kuvatov"
email "bobir_is@yahoo.com, pablo@mandrakesoft.com, kmashrab@uni-bremen.de"
tel ""
fax ""
language "Uzbek"
territory "Uzbekistan"
revision "0.5"
date "2003-06-27"
category "i18n:2012";LC_IDENTIFICATION
category "i18n:2012";LC_CTYPE
category "i18n:2012";LC_COLLATE
category "i18n:2012";LC_TIME
category "i18n:2012";LC_NUMERIC
category "i18n:2012";LC_MONETARY
category "i18n:2012";LC_MESSAGES
category "i18n:2012";LC_PAPER
category "i18n:2012";LC_NAME
category "i18n:2012";LC_ADDRESS
category "i18n:2012";LC_TELEPHONE
category "i18n:2012";LC_MEASUREMENT
END LC_IDENTIFICATION
LC_CTYPE
copy "i18n"
translit_start
include "translit_combining";""
% cyrillic -> latin
% lower case letters
<U0430> "<U0061>" % a= -> a
<U0431> "<U0062>" % b= -> b
<U0432> "<U0076>" % v= -> v
<U0433> "<U0067>" % g= -> g
<U0434> "<U0064>" % d= -> d
<U0435> "<U0065>" % e= -> e (ye also, but context dependent)
<U0451> "<U0079><U006F>" % io -> yo
<U0436> "<U006A>" % z% -> j
<U0437> "<U007A>" % z= -> z
<U0438> "<U0069>" % i= -> i
<U0439> "<U0079>" % j= -> y
<U043A> "<U006B>" % k= -> k
<U043B> "<U006C>" % l= -> l
<U043C> "<U006D>" % m= -> m
<U043D> "<U006E>" % n= -> n
<U043E> "<U006F>" % o= -> o
<U043F> "<U0070>" % p= -> p
<U0440> "<U0072>" % r= -> r
<U0441> "<U0073>" % s= -> s
<U0442> "<U0074>" % t= -> t
<U0443> "<U0075>" % u= -> u
<U0444> "<U0066>" % f= -> f
<U0445> "<U0078>" % h= -> x
<U0446> "<U0074><U0073>" % c= -> ts
<U0447> "<U0063><U0068>" % c% -> ch
<U0448> "<U0073><U0068>" % s% -> sh
<U0449> "<U0073><U0068>" % shcha -> sh
<U044A> "<U0027>" % hard sign= -> '
<U044B> "<U0069>" % yeru -> 1
<U044C> "" % soft sign omitted. not in latin-uzbek alphabet. stupid, but it is a fact.
<U044D> "<U0065>" % je= -> e
<U044E> "<U0079><U0075>" % ju -> yu
<U044F> "<U0079><U0061>" % ja -> ya
<U045E> "<U006F><U0027>" % v% -> o'
<U049B> "<U0071>" % k,= -> q
<U0493> "<U0067><U0027>" % g-= -> g'
<U04B3> "<U0068>" % h,= -> h
% upper case letters
<U0410> "<U0041>" % a= -> a
<U0411> "<U0042>" % b= -> b
<U0412> "<U0056>" % v= -> v
<U0413> "<U0047>" % g= -> g
<U0414> "<U0044>" % d= -> d
<U0415> "<U0045>" % e= -> e (ye also, but context dependent)
<U0401> "<U0059><U006F>" % io -> yo
<U0416> "<U004A>" % z% -> j
<U0417> "<U005A>" % z= -> z
<U0418> "<U0049>" % i= -> i
<U0419> "<U0059>" % j= -> y
<U041A> "<U004B>" % k= -> k
<U041B> "<U004C>" % l= -> l
<U041C> "<U004D>" % m= -> m
<U041D> "<U004E>" % n= -> n
<U041E> "<U004F>" % o= -> o
<U041F> "<U0050>" % p= -> p
<U0420> "<U0052>" % r= -> r
<U0421> "<U0053>" % s= -> s
<U0422> "<U0054>" % t= -> t
<U0423> "<U0055>" % u= -> u
<U0424> "<U0046>" % f= -> f
<U0425> "<U0058>" % h= -> x
<U0426> "<U0054><U0073>" % c= -> ts
<U0427> "<U0043><U0068>" % c% -> ch
<U0428> "<U0053><U0068>" % s% -> sh
<U0429> "<U0053><U0068>" % shcha -> sh
<U042A> "<U0027>" % hard sign= -> '
<U042B> "<U0049>" % yeru -> i
<U042C> "" % soft sign omitted. not in latin-uzbek alphabet. stupid, but it is a fact.
<U042D> "<U0045>" % je -> e
<U042E> "<U0059><U0075>" % ju -> yu
<U042F> "<U0059><U0061>" % ja -> ya
<U040E> "<U004F><U0027>" % v% -> o'
<U049A> "<U0051>" % k,= -> q
<U0492> "<U0047><U0027>" % g-= -> g'
<U04B2> "<U0048>" % h,= -> h
% various punctuation
<U02BB> "<U0027>" % ‘ -> '
translit_end
END LC_CTYPE
LC_COLLATE
copy "iso14651_t1"
% CLDR collation rules for Uzbek:
% (see: https://unicode.org/cldr/trac/browser/trunk/common/collation/uz.xml)
%
% <collations>
% <collation type="standard"><cr><![CDATA[
% # The following letters sort after z, see
% # https://en.wikipedia.org/wiki/Uzbek_alphabet#Alphabetical_order
% # Native speaker+linguists say that
% # the digraph ⟨ng⟩ and the symbol ⟨ʼ⟩ are not considered separate letters.
% #
% # Reset between the last z-like letter and ezh.
% #
% # U+02BB ʻ MODIFIER LETTER TURNED COMMA is hard to type, so make
% # equivalent contractions with U+2018 ‘ LEFT SINGLE QUOTATION MARK
% # and U+0027 APOSTROPHE.
% # (https://en.wikipedia.org/wiki/Uzbek_alphabet#Distinct_characters)
% # Remember that a pair of apostrophes encodes just one of them.
% &[before 1]ʒ<oʻ=o‘=o''<<<Oʻ=O‘=O''
% <gʻ=g‘=g''<<<Gʻ=G‘=G''
% <sh<<<Sh<<<SH
% <ch<<<Ch<<<CH
% ]]></cr></collation>
% </collations>
%
% And CLDR also lists the following
% index characters:
% (see: https://unicode.org/cldr/trac/browser/trunk/common/main/uz.xml)
%
% <exemplarCharacters type="index">[A B D E F G H I J K L M N O P Q R S T U V X Y Z {Oʻ} {Gʻ} {Sh} {Ch}]</exemplarCharacters>
%
collating-symbol <g'-digraph>
collating-symbol <o'-digraph>
collating-element <g-turned-comma> from "g<U02BB>"
collating-element <G-turned-comma> from "G<U02BB>"
collating-element <o-turned-comma> from "o<U02BB>"
collating-element <O-turned-comma> from "O<U02BB>"
% Unfortunately we cannot use “left single quotation mark” because
% it fails when creating the uz_UZ.iso88591 locale. In UTF-8 it works
% but in ISO-8859-1 one gets error messages that it uses the same
% encoding as “turned comma”
% collating-element <g-left-single-quotation-mark> from "g<U2018>"
% collating-element <G-left-single-quotation-mark> from "G<U2018>"
% collating-element <o-left-single-quotation-mark> from "o<U2018>"
% collating-element <O-left-single-quotation-mark> from "O<U2018>"
collating-element <g-double-apostrophe> from "g''"
collating-element <G-double-apostrophe> from "G''"
collating-element <o-double-apostrophe> from "o''"
collating-element <O-double-apostrophe> from "O''"
collating-symbol <sh-digraph>
collating-element <sh> from "sh"
collating-element <sH> from "sH"
collating-element <Sh> from "Sh"
collating-element <SH> from "SH"
collating-symbol <ch-digraph>
collating-element <ch> from "ch"
collating-element <cH> from "cH"
collating-element <Ch> from "Ch"
collating-element <CH> from "CH"
reorder-after <AFTER-Z>
<o'-digraph>
<g'-digraph>
<sh-digraph>
<ch-digraph>
<o-turned-comma> <o'-digraph>;"<BASE><BASE>";"<MIN><MIN>";<VRNT1>
<O-turned-comma> <o'-digraph>;"<BASE><BASE>";"<CAP><MIN>";<VRNT1>
% <o-left-single-quotation-mark> <o'-digraph>;"<BASE><BASE>";"<MIN><MIN>";<VRNT2>
% <O-left-single-quotation-mark> <o'-digraph>;"<BASE><BASE>";"<CAP><MIN>";<VRNT2>
<o-double-apostrophe> <o'-digraph>;"<BASE><BASE>";"<MIN><MIN>";<VRNT3>
<O-double-apostrophe> <o'-digraph>;"<BASE><BASE>";"<CAP><MIN>";<VRNT3>
<g-turned-comma> <g'-digraph>;"<BASE><BASE>";"<MIN><MIN>";<VRNT1>
<G-turned-comma> <g'-digraph>;"<BASE><BASE>";"<CAP><MIN>";<VRNT1>
% <g-left-single-quotation-mark> <g'-digraph>;"<BASE><BASE>";"<MIN><MIN>";<VRNT2>
% <G-left-single-quotation-mark> <g'-digraph>;"<BASE><BASE>";"<CAP><MIN>";<VRNT2>
<g-double-apostrophe> <g'-digraph>;"<BASE><BASE>";"<MIN><MIN>";<VRNT3>
<G-double-apostrophe> <g'-digraph>;"<BASE><BASE>";"<CAP><MIN>";<VRNT3>
<sh> <sh-digraph>;"<BASE><BASE>";"<MIN><MIN>";IGNORE
<sH> <sh-digraph>;"<BASE><BASE>";"<MIN><CAP>";IGNORE
<Sh> <sh-digraph>;"<BASE><BASE>";"<CAP><MIN>";IGNORE
<SH> <sh-digraph>;"<BASE><BASE>";"<CAP><CAP>";IGNORE
<ch> <ch-digraph>;"<BASE><BASE>";"<MIN><MIN>";IGNORE
<cH> <ch-digraph>;"<BASE><BASE>";"<MIN><CAP>";IGNORE
<Ch> <ch-digraph>;"<BASE><BASE>";"<CAP><MIN>";IGNORE
<CH> <ch-digraph>;"<BASE><BASE>";"<CAP><CAP>";IGNORE
reorder-end
END LC_COLLATE
LC_MONETARY
int_curr_symbol "UZS "
currency_symbol "soʻm"
mon_decimal_point "."
mon_thousands_sep ","
mon_grouping 3
positive_sign ""
negative_sign "-"
int_frac_digits 2
frac_digits 2
p_cs_precedes 1
p_sep_by_space 0
n_cs_precedes 1
n_sep_by_space 0
p_sign_posn 1
n_sign_posn 1
END LC_MONETARY
LC_NUMERIC
decimal_point ","
thousands_sep " "
grouping 3
END LC_NUMERIC
LC_TIME
abday "Yak";"Du";/
"Se";"Cho";/
"Pay";"Ju";/
"Sha"
day "Yakshanba";/
"Dushanba";/
"Seshanba";/
"Chorshanba";/
"Payshanba";/
"Juma";/
"Shanba"
abmon "Yan";"Fev";/
"Mar";"Apr";/
"May";"Iyn";/
"Iyl";"Avg";/
"Sen";"Okt";/
"Noy";"Dek"
mon "Yanvar";/
"Fevral";/
"Mart";/
"Aprel";/
"May";/
"Iyun";/
"Iyul";/
"Avgust";/
"Sentabr";/
"Oktabr";/
"Noyabr";/
"Dekabr"
d_t_fmt "%T, %d %B, %Y yil, %A"
d_fmt "%d//%m//%y"
t_fmt "%T"
am_pm "";""
t_fmt_ampm ""
date_fmt "%d %B, %Y yil, %A"
week 7;19971130;1
first_weekday 2
END LC_TIME
LC_MESSAGES
% Note: "No" is "yo‘q" which conflicts with English "yes".
% This is why "jo‘q" & "jJ" is also accepted as "no".
yesexpr "^[+1hHҲҳ]"
noexpr "^[-0nNyYjJЙй]"
yesstr "ha"
nostr "yo‘q"
END LC_MESSAGES
LC_PAPER
copy "i18n"
END LC_PAPER
LC_TELEPHONE
% FIXME: todo
tel_int_fmt "+%c %a %l"
int_prefix "998"
int_select "00"
END LC_TELEPHONE
LC_MEASUREMENT
copy "i18n"
END LC_MEASUREMENT
LC_NAME
name_fmt "%d%t%f%t%g%t%m"
name_gen "Hurmatli"
name_mr "Janob"
name_mrs "Xonim"
% FIXME: what is miss ?
name_miss ""
% FIXME: what is ms ?
name_ms ""
END LC_NAME
LC_ADDRESS
% format: %C%N%S%N%T%N%s %h%N%f%N%b%N%d%N%e %r%N%a%N%z
% but %S seems not recognized yet ? so %C%N%T%N%s %h%N%f%N%b%N%d%N%e %r%N%a%N%z
% is used.
postal_fmt "%C%N%T%N%s %h%N%f%N%b%N%d%N%e %r%N%a%N%z"
country_name "Oʻzbekiston"
country_post "UZ" % ??
country_ab2 "UZ"
country_ab3 "UZB"
country_num 860
% FIXME: ISBN number?
%country_isbn ""
country_car "UZ"
lang_name "o‘zbek"
lang_ab "uz"
lang_term "uzb"
lang_lib "uzb"
END LC_ADDRESS
Reference in New Issue View Git Blame Copy Permalink