diff options
Diffstat (limited to 'localedata/locales/uz_UZ')
| -rw-r--r-- | localedata/locales/uz_UZ | 127 |
1 files changed, 83 insertions, 44 deletions
diff --git a/localedata/locales/uz_UZ b/localedata/locales/uz_UZ index c5afbf721c..2dae80c8aa 100644 --- a/localedata/locales/uz_UZ +++ b/localedata/locales/uz_UZ @@ -155,53 +155,92 @@ 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> +% -%% a b c d e f g g' h i j k l m n o o' p q r s t u v x y z -%% cyr: a=, b=, v=, g=, d=, e=, io, z%, z=, i=, j=, k=, l=, m=, n=, o=, -%% p=, r=, s=, t=, u=, f=, h=, c=, c%, s%, sc, =' , y=, je, ju, ja, -%% v%, k,=, g-=, h,= -collating-symbol <g-'-uz> -collating-element <g-'> from "<U0067><U0027>" -collating-element <G-'> from "<U0047><U0027>" -collating-symbol <o-'-uz> -collating-element <o-'> from "<U006F><U0027>" -collating-element <O-'> from "<U004F><U0027>" - -collating-symbol <k,=> -collating-symbol <g-=> -collating-symbol <h,=> - -reorder-after <g> -<g-'-uz> -reorder-after <o> -<o-'-uz> -reorder-after <CYR-YA> -<CYR-OUBRE> -<k,=> -<g-=> -<h,=> - -reorder-after <U0067> -<g-'> <g-'-uz>;<PCL>;<MIN>;IGNORE -reorder-after <U0047> -<G-'> <g-'-uz>;<PCL>;<CAP>;IGNORE - -reorder-after <U006F> -<o-'> <o-'-uz>;<PCL>;<MIN>;IGNORE -reorder-after <U004F> -<O-'> <o-'-uz>;<PCL>;<CAP>;IGNORE +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 <U044F> -<U045E> <CYR-OUBRE>;<PCL>;<MIN>;IGNORE -<U049B> <k,=>;<PCL>;<MIN>;IGNORE -<U0493> <g-=>;<PCL>;<MIN>;IGNORE -<U04B3> <h,=>;<PCL>;<MIN>;IGNORE +reorder-after <AFTER-Z> +<o'-digraph> +<g'-digraph> +<sh-digraph> +<ch-digraph> -reorder-after <U042F> -<U040E> <CYR-OUBRE>;<PCL>;<CAP>;IGNORE -<U049A> <k,=>;<PCL>;<CAP>;IGNORE -<U0492> <g-=>;<PCL>;<CAP>;IGNORE -<U04B2> <h,=>;<PCL>;<CAP>;IGNORE +<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 |