Adapt collation in several locales to the new iso14651_t1_common file

[BZ #22550] - es_ES locale (and other es_* locales): collation should
treat ñ as a primary different character, sync the collation
for Spanish with CLDR
[BZ #21547] - Tibetan script collation broken (Dzongkha and Tibetan)

	* localedata/Makefile: Add new test files.
	* localedata/lv_LV.UTF-8.in: Adapt test file to new collation order.
	* localedata/sv_SE.ISO-8859-1.in: Adapt test file to new collation order.
	* localedata/uk_UA.UTF-8.in: Adapt test file to new collation order.
	* localedata/am_ET.UTF-8.in: New test file.
	* localedata/az_AZ.UTF-8.in: Likewise.
	* localedata/be_BY.UTF-8.in: Likewise.
	* localedata/ber_DZ.UTF-8.in: Likewise.
	* localedata/ber_MA.UTF-8.in: Likewise.
	* localedata/bg_BG.UTF-8.in: Likewise.
	* localedata/br_FR.UTF-8.in: Likewise.
	* localedata/cmn_TW.UTF-8.in: Likewise.
	* localedata/crh_UA.UTF-8.in: Likewise.
	* localedata/csb_PL.UTF-8.in: Likewise.
	* localedata/cv_RU.UTF-8.in: Likewise.
	* localedata/cy_GB.UTF-8.in: Likewise.
	* localedata/dz_BT.UTF-8.in: Likewise.
	* localedata/eo.UTF-8.in: Likewise.
	* localedata/es_ES.UTF-8.in: Likewise.
	* localedata/fa_IR.UTF-8.in: Likewise.
	* localedata/fi_FI.UTF-8.in: Likewise.
	* localedata/fil_PH.UTF-8.in: Likewise.
	* localedata/fur_IT.UTF-8.in: Likewise.
	* localedata/gez_ER.UTF-8@abegede.in: Likewise.
	* localedata/ha_NG.UTF-8.in: Likewise.
	* localedata/ig_NG.UTF-8.in: Likewise.
	* localedata/ik_CA.UTF-8.in: Likewise.
	* localedata/kk_KZ.UTF-8.in: Likewise.
	* localedata/ku_TR.UTF-8.in: Likewise.
	* localedata/ky_KG.UTF-8.in: Likewise.
	* localedata/ln_CD.UTF-8.in: Likewise.
	* localedata/mi_NZ.UTF-8.in: Likewise.
	* localedata/ml_IN.UTF-8.in: Likewise.
	* localedata/mn_MN.UTF-8.in: Likewise.
	* localedata/mr_IN.UTF-8.in: Likewise.
	* localedata/mt_MT.UTF-8.in: Likewise.
	* localedata/nb_NO.UTF-8.in: Likewise.
	* localedata/om_KE.UTF-8.in: Likewise.
	* localedata/os_RU.UTF-8.in: Likewise.
	* localedata/ps_AF.UTF-8.in: Likewise.
	* localedata/ro_RO.UTF-8.in: Likewise.
	* localedata/ru_RU.UTF-8.in: Likewise.
	* localedata/sc_IT.UTF-8.in: Likewise.
	* localedata/se_NO.UTF-8.in: Likewise.
	* localedata/sq_AL.UTF-8.in: Likewise.
	* localedata/sv_SE.UTF-8.in: Likewise.
	* localedata/szl_PL.UTF-8.in: Likewise.
	* localedata/tg_TJ.UTF-8.in: Likewise.
	* localedata/tk_TM.UTF-8.in: Likewise.
	* localedata/tt_RU.UTF-8.in: Likewise.
	* localedata/tt_RU.UTF-8@iqtelif.in: Likewise.
	* localedata/ug_CN.UTF-8.in: Likewise.
	* localedata/uz_UZ.UTF-8.in: Likewise.
	* localedata/vi_VN.UTF-8.in: Likewise.
	* localedata/yi_US.UTF-8.in: Likewise.
	* localedata/yo_NG.UTF-8.in: Likewise.
	* localedata/zh_CN.UTF-8.in: Likewise.
	* localedata/locales/am_ET: Adapt collation rules to new iso14651_t1_common
        file and fix bugs in the collation.
	* localedata/locales/az_AZ: Likewise.
	* localedata/locales/be_BY: Likewise.
	* localedata/locales/ber_DZ: Likewise.
	* localedata/locales/ber_MA: Likewise.
	* localedata/locales/bg_BG: Likewise.
	* localedata/locales/br_FR: Likewise.
	* localedata/locales/br_FR@euro: Likewise.
	* localedata/locales/ca_ES: Likewise.
	* localedata/locales/cns11643_stroke: Likewise.
	* localedata/locales/crh_UA: Likewise.
	* localedata/locales/cs_CZ: Likewise.
	* localedata/locales/csb_PL: Likewise.
	* localedata/locales/cv_RU: Likewise.
	* localedata/locales/cy_GB: Likewise.
	* localedata/locales/da_DK: Likewise.
	* localedata/locales/dz_BT: Likewise.
	* localedata/locales/en_CA: Likewise.
	* localedata/locales/eo: Likewise.
	* localedata/locales/es_CU: Likewise.
	* localedata/locales/es_EC: Likewise.
	* localedata/locales/es_ES: Likewise.
	* localedata/locales/es_US: Likewise.
	* localedata/locales/et_EE: Likewise.
	* localedata/locales/fa_IR: Likewise.
	* localedata/locales/fi_FI: Likewise.
	* localedata/locales/fil_PH: Likewise.
	* localedata/locales/fur_IT: Likewise.
	* localedata/locales/gez_ER@abegede: Likewise.
	* localedata/locales/ha_NG: Likewise.
	* localedata/locales/hr_HR: Likewise.
	* localedata/locales/hsb_DE: Likewise.
	* localedata/locales/hu_HU: Likewise.
	* localedata/locales/ig_NG: Likewise.
	* localedata/locales/ik_CA: Likewise.
	* localedata/locales/is_IS: Likewise.
	* localedata/locales/iso14651_t1_pinyin: Likewise.
	* localedata/locales/kk_KZ: Likewise.
	* localedata/locales/ku_TR: Likewise.
	* localedata/locales/ky_KG: Likewise.
	* localedata/locales/ln_CD: Likewise.
	* localedata/locales/lt_LT: Likewise.
	* localedata/locales/lv_LV: Likewise.
	* localedata/locales/mi_NZ: Likewise.
	* localedata/locales/ml_IN: Likewise.
	* localedata/locales/mn_MN: Likewise.
	* localedata/locales/mr_IN: Likewise.
	* localedata/locales/mt_MT: Likewise.
	* localedata/locales/nb_NO: Likewise.
	* localedata/locales/om_KE: Likewise.
	* localedata/locales/os_RU: Likewise.
	* localedata/locales/pl_PL: Likewise.
	* localedata/locales/ps_AF: Likewise.
	* localedata/locales/ro_RO: Likewise.
	* localedata/locales/ru_RU: Likewise.
	* localedata/locales/ru_UA: Likewise.
	* localedata/locales/sc_IT: Likewise.
	* localedata/locales/se_NO: Likewise.
	* localedata/locales/si_LK: Likewise.
	* localedata/locales/sq_AL: Likewise.
	* localedata/locales/sv_FI: Likewise.
	* localedata/locales/sv_FI@euro: Likewise.
	* localedata/locales/sv_SE: Likewise.
	* localedata/locales/szl_PL: Likewise.
	* localedata/locales/tg_TJ: Likewise.
	* localedata/locales/ti_ER: Likewise.
	* localedata/locales/tk_TM: Likewise.
	* localedata/locales/tl_PH: Likewise.
	* localedata/locales/tr_TR: Likewise.
	* localedata/locales/tt_RU: Likewise.
	* localedata/locales/tt_RU@iqtelif: Likewise.
	* localedata/locales/ug_CN: Likewise.
	* localedata/locales/uk_UA: Likewise.
	* localedata/locales/uz_UZ: Likewise.
	* localedata/locales/uz_UZ@cyrillic: Likewise.
	* localedata/locales/vi_VN: Likewise.
	* localedata/locales/yi_US: Likewise.
	* localedata/locales/yo_NG: Likewise.

1 files changed, 83 insertions, 44 deletions

diff --git a/localedata/locales/uz_UZ b/localedata/locales/uz_UZ
index c5afbf7..2dae80c 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