Fix sorting order for Ukrainian locale (BZ 17293)

In the introduction for the official orthography rules for Ukrainian
language (http://spelling.ulif.org.ua/peredmova.htm) there's a note
that only apostrophe does not affect order of the words when sorting.
As could be seen from the official alphabet the soft sign
(U+044C/U+042C) has its hard position and thus affects the order and
also letters "е" and "є" (CYR-IE: U+0435/U+0415 and UKR-IE:
U+0454/U+0404) have their own positions and should have separate place
when sorting.
This also corresponds to official Unicode collation chart for these
letters: http://unicode.org/charts/collation/chart_Cyrillic.html

5 files changed, 76 insertions, 73 deletions

diff --git a/ChangeLog b/ChangeLog
index eb02973..81ce22e 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+2015-05-26  Andriy Rysin  <arysin@gmail.com>
+
+	[BZ #17293]
+	* uk_UA: Fix sorting order for Ukrainian locale
+
 2015-05-26  Marko Myllynen  <myllynen@redhat.com>
 
 	* stdlib/monetary.h: Fix comment.
diff --git a/NEWS b/NEWS
index d50560a..4aff69d 100644
--- a/NEWS
+++ b/NEWS
@@ -11,15 +11,15 @@ Version 2.22
 
   438, 4719, 6792, 13028, 13064, 14094, 14841, 14906, 15319, 15467, 15790,
   15969, 16159, 16339, 16351, 16352, 16512, 16560, 16704, 16783, 16850,
-  17053, 17090, 17195, 17269, 17523, 17542, 17569, 17581, 17588, 17596,
-  17620, 17621, 17628, 17631, 17692, 17711, 17715, 17776, 17779, 17792,
-  17836, 17912, 17916, 17930, 17932, 17944, 17949, 17964, 17965, 17967,
-  17969, 17978, 17987, 17991, 17996, 17998, 17999, 18007, 18019, 18020,
-  18029, 18030, 18032, 18036, 18038, 18039, 18042, 18043, 18046, 18047,
-  18049, 18068, 18080, 18093, 18100, 18104, 18110, 18111, 18125, 18128,
-  18138, 18185, 18196, 18197, 18206, 18210, 18211, 18217, 18220, 18221,
-  18234, 18244, 18247, 18287, 18319, 18333, 18346, 18397, 18409, 18410,
-  18412, 18418, 18434, 18444.
+  17053, 17090, 17195, 17269, 17293, 17523, 17542, 17569, 17581, 17588,
+  17596, 17620, 17621, 17628, 17631, 17692, 17711, 17715, 17776, 17779,
+  17792, 17836, 17912, 17916, 17930, 17932, 17944, 17949, 17964, 17965,
+  17967, 17969, 17978, 17987, 17991, 17996, 17998, 17999, 18007, 18019,
+  18020, 18029, 18030, 18032, 18036, 18038, 18039, 18042, 18043, 18046,
+  18047, 18049, 18068, 18080, 18093, 18100, 18104, 18110, 18111, 18125,
+  18128, 18138, 18185, 18196, 18197, 18206, 18210, 18211, 18217, 18220,
+  18221, 18234, 18244, 18247, 18287, 18319, 18333, 18346, 18397, 18409,
+  18410, 18412, 18418, 18434, 18444.
 
 * Cache information can be queried via sysconf() function on s390 e.g. with
   _SC_LEVEL1_ICACHE_SIZE as argument.
diff --git a/localedata/Makefile b/localedata/Makefile
index 305c87f..ebf6ac9 100644
--- a/localedata/Makefile
+++ b/localedata/Makefile
@@ -37,7 +37,7 @@ test-srcs := collate-test xfrm-test tst-fmon tst-rpmatch tst-trans \
 	     tst-ctype tst-langinfo tst-langinfo-static tst-numeric
 test-input := de_DE.ISO-8859-1 en_US.ISO-8859-1 da_DK.ISO-8859-1 \
 	      hr_HR.ISO-8859-2 sv_SE.ISO-8859-1 tr_TR.UTF-8 fr_FR.UTF-8 \
-	      si_LK.UTF-8
+	      si_LK.UTF-8 uk_UA.UTF-8
 test-input-data = $(addsuffix .in, $(basename $(test-input)))
 test-output := $(foreach s, .out .xout, \
 			 $(addsuffix $s, $(basename $(test-input))))
@@ -106,7 +106,7 @@ LOCALES := de_DE.ISO-8859-1 de_DE.UTF-8 en_US.ANSI_X3.4-1968 \
 	   hr_HR.ISO-8859-2 sv_SE.ISO-8859-1 ja_JP.SJIS fr_FR.ISO-8859-1 \
 	   nb_NO.ISO-8859-1 nn_NO.ISO-8859-1 tr_TR.UTF-8 cs_CZ.UTF-8 \
 	   zh_TW.EUC-TW fa_IR.UTF-8 fr_FR.UTF-8 ja_JP.UTF-8 si_LK.UTF-8 \
-	   tr_TR.ISO-8859-9 en_GB.UTF-8
+	   tr_TR.ISO-8859-9 en_GB.UTF-8 uk_UA.UTF-8
 include ../gen-locales.mk
 endif
 
diff --git a/localedata/locales/uk_UA b/localedata/locales/uk_UA
index d9194b8..511f004 100644
--- a/localedata/locales/uk_UA
+++ b/localedata/locales/uk_UA
@@ -340,70 +340,14 @@ copy "<U0069><U0073><U006F><U0031><U0034><U0036><U0035><U0031><U005F><U0074><U00
 % Ukrainian ghe is missing in iso14651_t1
 collating-symbol <UKR-GHE>
 
-% Soft sign and apostrophe must be ignored during sorting because they are
-% just signs, not real letters.
+% Apostrophe must be ignored during sorting because it's just a sign, not a
+% real letter.
 % ( "<U006E><U0060>"=="<U006E>", "<U0027><U0079><U0061>"=="<U0079><U0061>", etc. )
 %
 % Apostrophe already ignored by iso14651_t1.
 %
-% Soft sign '<U044C>' may follow only this set of nine characters [<U0432><U0434><U0437><U043B><U043D><U0440><U0441><U0442><U0446>].
-% It only softens pronunciation of these characters so it's should not impact
-% sorting.
-
-
-collating-symbol <V+SS>
-collating-element <V-SS> from "<U0412><U042C>"
-collating-element <V-ss> from "<U0412><U044C>"
-collating-element <v-SS> from "<U0432><U042C>"
-collating-element <v-ss> from "<U0432><U044C>"
-
-collating-symbol <D+SS>
-collating-element <D-SS> from "<U0414><U042C>"
-collating-element <D-ss> from "<U0414><U044C>"
-collating-element <d-SS> from "<U0434><U042C>"
-collating-element <d-ss> from "<U0434><U044C>"
-
-collating-symbol <Z+SS>
-collating-element <Z-SS> from "<U0417><U042C>"
-collating-element <Z-ss> from "<U0417><U044C>"
-collating-element <z-SS> from "<U0437><U042C>"
-collating-element <z-ss> from "<U0437><U044C>"
-
-collating-symbol <L+SS>
-collating-element <L-SS> from "<U041B><U042C>"
-collating-element <L-ss> from "<U041B><U044C>"
-collating-element <l-SS> from "<U043B><U042C>"
-collating-element <l-ss> from "<U043B><U044C>"
-
-collating-symbol <N+SS>
-collating-element <N-SS> from "<U041D><U042C>"
-collating-element <N-ss> from "<U041D><U044C>"
-collating-element <n-SS> from "<U043D><U042C>"
-collating-element <n-ss> from "<U043D><U044C>"
-
-collating-symbol <R+SS>
-collating-element <R-SS> from "<U0420><U042C>"
-collating-element <R-ss> from "<U0420><U044C>"
-collating-element <r-SS> from "<U0440><U042C>"
-collating-element <r-ss> from "<U0440><U044C>"
-
-collating-symbol <S+SS>
-collating-element <S-SS> from "<U0421><U042C>"
-collating-element <S-ss> from "<U0421><U044C>"
-collating-element <s-SS> from "<U0441><U042C>"
-collating-element <s-ss> from "<U0441><U044C>"
-
-collating-symbol <T+SS>
-collating-element <T-SS> from "<U0422><U042C>"
-collating-element <T-ss> from "<U0422><U044C>"
-collating-element <t-SS> from "<U0442><U042C>"
-collating-element <t-ss> from "<U0442><U044C>"
-
-collating-symbol <TSE+SS>
-collating-element <TS-SS> from "<U0426><U042C>"
-collating-element <TS-ss> from "<U0426><U044C>"
-collating-element <ts-SS> from "<U0446><U042C>"
-collating-element <ts-ss> from "<U0446><U044C>"
+% In the official alphabet the soft sign is a letter and has a hard position in
+% the order.
 
 
 collating-symbol <CAP-MIN>
@@ -489,11 +433,9 @@ reorder-after <U0434>
 <U0455> "<U003C><U0043><U0059><U0052><U002D><U0044><U0045><U003E><U003C><U0043><U0059><U0052><U002D><U005A><U0045><U003E>";"<U003C><U004C><U0049><U0047><U003E><U003C><U004C><U0049><U0047><U003E>";"<U003C><U004D><U0049><U004E><U003E><U003C><U004D><U0049><U004E><U003E>";IGNORE % CYR-DZE
 
 reorder-after <U0435>
-<U0454> <CYR-IE>;<UKR-IE>;<MIN>;IGNORE
 <U0451> <CYR-IE>;<CYR-IO>;<MIN>;IGNORE
 <U044D> <CYR-IE>;<CYR-E>;<MIN>;IGNORE
 reorder-after <U0415>
-<U0404> <CYR-IE>;<UKR-IE>;<CAP>;IGNORE
 <U0401> <CYR-IE>;<CYR-IO>;<CAP>;IGNORE
 <U042D> <CYR-IE>;<CYR-E>;<CAP>;IGNORE
 
diff --git a/localedata/uk_UA.in b/localedata/uk_UA.in
new file mode 100644
index 0000000..ff4d284
--- /dev/null
+++ b/localedata/uk_UA.in
@@ -0,0 +1,56 @@
+01010
+Абажур
+абажур
+абажур-10
+брама
+вермішель
+грати
+Граття
+граття
+ґрати
+ебонітовий
+експорт
+експосол
+екс-посол
+експоцентр
+експрацівник
+екс-працівник
+еластичність
+електрика
+ельбор
+елюент
+епатаж
+євгеніка
+Європа
+єдність
+Жмих
+жмих
+зоря
+и
+і
+ї
+й
+Карпати
+криниця
+лебідь
+місяцевий
+місяць
+наразі
+обапіл
+об'їзд
+об’їзд
+обʼїзд
+образ
+опір
+право
+сонце
+тарган
+упродовж
+фантастика
+центр
+чухатися
+ш
+щ
+ь
+ю
+я