1comment_char % 2escape_char / 3 4% This file is part of the GNU C Library and contains locale data. 5% The Free Software Foundation does not claim any copyright interest 6% in the locale data contained in this file. The foregoing does not 7% affect the license of the GNU C Library as a whole. It does not 8% exempt you from the conditions of the license if your use would 9% otherwise be governed by that license. 10 11% Uzbek (latin) language locale for Uzbekistan 12% Source: Bobir Ismailov 13% Contact: Bobir Ismailov, Pablo Saratxaga, Mashrab Kuvatov 14% Email: bobir_is@yahoo.com, pablo@mandrakesoft.com, kmashrab@uni-bremen.de 15% Tel: 16% Fax: 17% Language: uz 18% Territory: UZ 19% Revision: 0.5 20% Date: 2003-06-27 21% Users: general 22% Charset: UTF-8 23% History: 24% 2002-09-09 Mashrab Kuvatov <kmashrab@uni-bremen.de> 25% LC_TIME-day: Changed the first letter of all day names to upper case. 26% LC_TIME-mon: Changed the first letter of all month names to upper case. 27% Fixed a typo. September is not Senyabr, but Sentyabr. 28% LC_TIME-abmon: Corrected "Yav" (Yanvar) to "Yan". 29% 30% 2003-02-24 Mashrab Kuvatov <kmashrab@uni-bremen.de> 31% Changed charset to UTF-8 32% 33% ?????????? Pablo Saratxaga <pablo@mandrakesoft.com> 34% LC_CTYPE: Added transliteration from cyrillic to latin. 35% LC_COLLATE: Added reodering definition. 36 37LC_IDENTIFICATION 38title "Uzbek (latin) locale for Uzbekistan" 39source "Bobir Ismailov" 40address "" 41contact "Bobir Ismailov, Pablo Saratxaga, Mashrab Kuvatov" 42email "bobir_is@yahoo.com, pablo@mandrakesoft.com, kmashrab@uni-bremen.de" 43tel "" 44fax "" 45language "Uzbek" 46territory "Uzbekistan" 47revision "0.5" 48date "2003-06-27" 49 50category "i18n:2012";LC_IDENTIFICATION 51category "i18n:2012";LC_CTYPE 52category "i18n:2012";LC_COLLATE 53category "i18n:2012";LC_TIME 54category "i18n:2012";LC_NUMERIC 55category "i18n:2012";LC_MONETARY 56category "i18n:2012";LC_MESSAGES 57category "i18n:2012";LC_PAPER 58category "i18n:2012";LC_NAME 59category "i18n:2012";LC_ADDRESS 60category "i18n:2012";LC_TELEPHONE 61category "i18n:2012";LC_MEASUREMENT 62END LC_IDENTIFICATION 63 64LC_CTYPE 65copy "i18n" 66 67translit_start 68include "translit_combining";"" 69 70% cyrillic -> latin 71% lower case letters 72 73<U0430> "<U0061>" % a= -> a 74<U0431> "<U0062>" % b= -> b 75<U0432> "<U0076>" % v= -> v 76<U0433> "<U0067>" % g= -> g 77<U0434> "<U0064>" % d= -> d 78<U0435> "<U0065>" % e= -> e (ye also, but context dependent) 79<U0451> "<U0079><U006F>" % io -> yo 80<U0436> "<U006A>" % z% -> j 81<U0437> "<U007A>" % z= -> z 82<U0438> "<U0069>" % i= -> i 83<U0439> "<U0079>" % j= -> y 84<U043A> "<U006B>" % k= -> k 85<U043B> "<U006C>" % l= -> l 86<U043C> "<U006D>" % m= -> m 87<U043D> "<U006E>" % n= -> n 88<U043E> "<U006F>" % o= -> o 89<U043F> "<U0070>" % p= -> p 90<U0440> "<U0072>" % r= -> r 91<U0441> "<U0073>" % s= -> s 92<U0442> "<U0074>" % t= -> t 93<U0443> "<U0075>" % u= -> u 94<U0444> "<U0066>" % f= -> f 95<U0445> "<U0078>" % h= -> x 96<U0446> "<U0074><U0073>" % c= -> ts 97<U0447> "<U0063><U0068>" % c% -> ch 98<U0448> "<U0073><U0068>" % s% -> sh 99<U0449> "<U0073><U0068>" % shcha -> sh 100<U044A> "<U0027>" % hard sign= -> ' 101<U044B> "<U0069>" % yeru -> 1 102<U044C> "" % soft sign omitted. not in latin-uzbek alphabet. stupid, but it is a fact. 103<U044D> "<U0065>" % je= -> e 104<U044E> "<U0079><U0075>" % ju -> yu 105<U044F> "<U0079><U0061>" % ja -> ya 106<U045E> "<U006F><U0027>" % v% -> o' 107<U049B> "<U0071>" % k,= -> q 108<U0493> "<U0067><U0027>" % g-= -> g' 109<U04B3> "<U0068>" % h,= -> h 110 111% upper case letters 112 113<U0410> "<U0041>" % a= -> a 114<U0411> "<U0042>" % b= -> b 115<U0412> "<U0056>" % v= -> v 116<U0413> "<U0047>" % g= -> g 117<U0414> "<U0044>" % d= -> d 118<U0415> "<U0045>" % e= -> e (ye also, but context dependent) 119<U0401> "<U0059><U006F>" % io -> yo 120<U0416> "<U004A>" % z% -> j 121<U0417> "<U005A>" % z= -> z 122<U0418> "<U0049>" % i= -> i 123<U0419> "<U0059>" % j= -> y 124<U041A> "<U004B>" % k= -> k 125<U041B> "<U004C>" % l= -> l 126<U041C> "<U004D>" % m= -> m 127<U041D> "<U004E>" % n= -> n 128<U041E> "<U004F>" % o= -> o 129<U041F> "<U0050>" % p= -> p 130<U0420> "<U0052>" % r= -> r 131<U0421> "<U0053>" % s= -> s 132<U0422> "<U0054>" % t= -> t 133<U0423> "<U0055>" % u= -> u 134<U0424> "<U0046>" % f= -> f 135<U0425> "<U0058>" % h= -> x 136<U0426> "<U0054><U0073>" % c= -> ts 137<U0427> "<U0043><U0068>" % c% -> ch 138<U0428> "<U0053><U0068>" % s% -> sh 139<U0429> "<U0053><U0068>" % shcha -> sh 140<U042A> "<U0027>" % hard sign= -> ' 141<U042B> "<U0049>" % yeru -> i 142<U042C> "" % soft sign omitted. not in latin-uzbek alphabet. stupid, but it is a fact. 143<U042D> "<U0045>" % je -> e 144<U042E> "<U0059><U0075>" % ju -> yu 145<U042F> "<U0059><U0061>" % ja -> ya 146<U040E> "<U004F><U0027>" % v% -> o' 147<U049A> "<U0051>" % k,= -> q 148<U0492> "<U0047><U0027>" % g-= -> g' 149<U04B2> "<U0048>" % h,= -> h 150 151% various punctuation 152<U02BB> "<U0027>" % ‘ -> ' 153translit_end 154END LC_CTYPE 155 156LC_COLLATE 157copy "iso14651_t1" 158% CLDR collation rules for Uzbek: 159% (see: https://unicode.org/cldr/trac/browser/trunk/common/collation/uz.xml) 160% 161% <collations> 162% <collation type="standard"><cr><![CDATA[ 163% # The following letters sort after z, see 164% # https://en.wikipedia.org/wiki/Uzbek_alphabet#Alphabetical_order 165% # Native speaker+linguists say that 166% # the digraph ⟨ng⟩ and the symbol ⟨ʼ⟩ are not considered separate letters. 167% # 168% # Reset between the last z-like letter and ezh. 169% # 170% # U+02BB ʻ MODIFIER LETTER TURNED COMMA is hard to type, so make 171% # equivalent contractions with U+2018 ‘ LEFT SINGLE QUOTATION MARK 172% # and U+0027 APOSTROPHE. 173% # (https://en.wikipedia.org/wiki/Uzbek_alphabet#Distinct_characters) 174% # Remember that a pair of apostrophes encodes just one of them. 175% &[before 1]ʒ<oʻ=o‘=o''<<<Oʻ=O‘=O'' 176% <gʻ=g‘=g''<<<Gʻ=G‘=G'' 177% <sh<<<Sh<<<SH 178% <ch<<<Ch<<<CH 179% ]]></cr></collation> 180% </collations> 181% 182% And CLDR also lists the following 183% index characters: 184% (see: https://unicode.org/cldr/trac/browser/trunk/common/main/uz.xml) 185% 186% <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> 187% 188 189collating-symbol <g'-digraph> 190collating-symbol <o'-digraph> 191collating-element <g-turned-comma> from "g<U02BB>" 192collating-element <G-turned-comma> from "G<U02BB>" 193collating-element <o-turned-comma> from "o<U02BB>" 194collating-element <O-turned-comma> from "O<U02BB>" 195% Unfortunately we cannot use “left single quotation mark” because 196% it fails when creating the uz_UZ.iso88591 locale. In UTF-8 it works 197% but in ISO-8859-1 one gets error messages that it uses the same 198% encoding as “turned comma” 199% collating-element <g-left-single-quotation-mark> from "g<U2018>" 200% collating-element <G-left-single-quotation-mark> from "G<U2018>" 201% collating-element <o-left-single-quotation-mark> from "o<U2018>" 202% collating-element <O-left-single-quotation-mark> from "O<U2018>" 203collating-element <g-double-apostrophe> from "g''" 204collating-element <G-double-apostrophe> from "G''" 205collating-element <o-double-apostrophe> from "o''" 206collating-element <O-double-apostrophe> from "O''" 207collating-symbol <sh-digraph> 208collating-element <sh> from "sh" 209collating-element <sH> from "sH" 210collating-element <Sh> from "Sh" 211collating-element <SH> from "SH" 212collating-symbol <ch-digraph> 213collating-element <ch> from "ch" 214collating-element <cH> from "cH" 215collating-element <Ch> from "Ch" 216collating-element <CH> from "CH" 217 218reorder-after <AFTER-Z> 219<o'-digraph> 220<g'-digraph> 221<sh-digraph> 222<ch-digraph> 223 224<o-turned-comma> <o'-digraph>;"<BASE><BASE>";"<MIN><MIN>";<VRNT1> 225<O-turned-comma> <o'-digraph>;"<BASE><BASE>";"<CAP><MIN>";<VRNT1> 226% <o-left-single-quotation-mark> <o'-digraph>;"<BASE><BASE>";"<MIN><MIN>";<VRNT2> 227% <O-left-single-quotation-mark> <o'-digraph>;"<BASE><BASE>";"<CAP><MIN>";<VRNT2> 228<o-double-apostrophe> <o'-digraph>;"<BASE><BASE>";"<MIN><MIN>";<VRNT3> 229<O-double-apostrophe> <o'-digraph>;"<BASE><BASE>";"<CAP><MIN>";<VRNT3> 230<g-turned-comma> <g'-digraph>;"<BASE><BASE>";"<MIN><MIN>";<VRNT1> 231<G-turned-comma> <g'-digraph>;"<BASE><BASE>";"<CAP><MIN>";<VRNT1> 232% <g-left-single-quotation-mark> <g'-digraph>;"<BASE><BASE>";"<MIN><MIN>";<VRNT2> 233% <G-left-single-quotation-mark> <g'-digraph>;"<BASE><BASE>";"<CAP><MIN>";<VRNT2> 234<g-double-apostrophe> <g'-digraph>;"<BASE><BASE>";"<MIN><MIN>";<VRNT3> 235<G-double-apostrophe> <g'-digraph>;"<BASE><BASE>";"<CAP><MIN>";<VRNT3> 236<sh> <sh-digraph>;"<BASE><BASE>";"<MIN><MIN>";IGNORE 237<sH> <sh-digraph>;"<BASE><BASE>";"<MIN><CAP>";IGNORE 238<Sh> <sh-digraph>;"<BASE><BASE>";"<CAP><MIN>";IGNORE 239<SH> <sh-digraph>;"<BASE><BASE>";"<CAP><CAP>";IGNORE 240<ch> <ch-digraph>;"<BASE><BASE>";"<MIN><MIN>";IGNORE 241<cH> <ch-digraph>;"<BASE><BASE>";"<MIN><CAP>";IGNORE 242<Ch> <ch-digraph>;"<BASE><BASE>";"<CAP><MIN>";IGNORE 243<CH> <ch-digraph>;"<BASE><BASE>";"<CAP><CAP>";IGNORE 244 245reorder-end 246 247END LC_COLLATE 248 249LC_MONETARY 250int_curr_symbol "UZS " 251currency_symbol "so<U02BB>m" 252mon_decimal_point "." 253mon_thousands_sep "," 254mon_grouping 3;3 255positive_sign "" 256negative_sign "-" 257int_frac_digits 2 258frac_digits 2 259p_cs_precedes 1 260p_sep_by_space 0 261n_cs_precedes 1 262n_sep_by_space 0 263p_sign_posn 1 264n_sign_posn 1 265END LC_MONETARY 266 267LC_NUMERIC 268decimal_point "." 269thousands_sep "," 270grouping 3;3 271END LC_NUMERIC 272 273LC_TIME 274abday "Yak";"Du";/ 275 "Se";"Cho";/ 276 "Pay";"Ju";/ 277 "Sha" 278day "Yakshanba";/ 279 "Dushanba";/ 280 "Seshanba";/ 281 "Chorshanba";/ 282 "Payshanba";/ 283 "Juma";/ 284 "Shanba" 285abmon "Yan";"Fev";/ 286 "Mar";"Apr";/ 287 "May";"Iyn";/ 288 "Iyl";"Avg";/ 289 "Sen";"Okt";/ 290 "Noy";"Dek" 291mon "Yanvar";/ 292 "Fevral";/ 293 "Mart";/ 294 "Aprel";/ 295 "May";/ 296 "Iyun";/ 297 "Iyul";/ 298 "Avgust";/ 299 "Sentabr";/ 300 "Oktabr";/ 301 "Noyabr";/ 302 "Dekabr" 303d_t_fmt "%T, %d %B, %Y yil, %A" 304d_fmt "%d//%m//%y" 305t_fmt "%T" 306am_pm "";"" 307t_fmt_ampm "" 308date_fmt "%d %B, %Y yil, %A" 309week 7;19971130;1 310first_weekday 2 311END LC_TIME 312 313LC_MESSAGES 314% Note: "No" is "yo‘q" which conflicts with English "yes". 315% This is why "jo‘q" & "jJ" is also accepted as "no". 316yesexpr "^[+1hH<U04B2><U04B3>]" 317noexpr "^[-0nNyYjJ<U0419><U0439>]" 318yesstr "ha" 319nostr "yo<U2018>q" 320END LC_MESSAGES 321 322LC_PAPER 323copy "i18n" 324END LC_PAPER 325 326LC_TELEPHONE 327% FIXME: todo 328tel_int_fmt "+%c %a %l" 329int_prefix "998" 330int_select "00" 331END LC_TELEPHONE 332 333LC_MEASUREMENT 334copy "i18n" 335END LC_MEASUREMENT 336 337LC_NAME 338name_fmt "%d%t%f%t%g%t%m" 339name_gen "Hurmatli" 340name_mr "Janob" 341name_mrs "Xonim" 342% FIXME: what is miss ? 343name_miss "" 344% FIXME: what is ms ? 345name_ms "" 346END LC_NAME 347 348LC_ADDRESS 349% format: %C%N%S%N%T%N%s %h%N%f%N%b%N%d%N%e %r%N%a%N%z 350% 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 351% is used. 352postal_fmt "%C%N%T%N%s %h%N%f%N%b%N%d%N%e %r%N%a%N%z" 353country_name "O<U02BB>zbekiston" 354country_post "UZ" % ?? 355country_ab2 "UZ" 356country_ab3 "UZB" 357country_num 860 358% FIXME: ISBN number? 359%country_isbn "" 360country_car "UZ" 361lang_name "o<U2018>zbek" 362lang_ab "uz" 363lang_term "uzb" 364lang_lib "uzb" 365END LC_ADDRESS 366