glibc/glibc-c-utf8-locale.patch
Carlos O'Donell 72195d4485 locale: Fix C.UTF-8 ranges.
The ellipsis range support only allows <Uxxxx> or <Uxxxxxxxx> as
valid unicode code points, otherwise it treats it as a symbol and
since we don't define the symbol the entire range is unused.
2019-08-16 10:07:58 -04:00

287 lines
8.9 KiB
Diff

Short description: Add C.UTF-8 support.
Author(s): Fedora glibc team <glibc@lists.fedoraproject.org>
Origin: PATCH
Upstream status: not-submitted
This patch needs to upstream as part of Carlos O'Donell
<carlos@redhat.com>'s work on enabling upstream C.UTF-8 support. This
work is currently blocked on cleaning up the test results to prove that
full code-point sorting is working as intended.
Note that this patch does not provide full code-point sorting as
expected.
This patch needs to upstream as soon as possible since it would be nice
to have this in F29 and fixed.
From 2eda7b462b415105f5a05c1323372d4e39d46439 Mon Sep 17 00:00:00 2001
From: Mike FABIAN <mfabian@redhat.com>
Date: Mon, 10 Aug 2015 15:58:12 +0200
Subject: [PATCH] Add a C.UTF-8 locale
---
localedata/SUPPORTED | 1 +
localedata/locales/C | 238 +++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 239 insertions(+)
create mode 100644 localedata/locales/C
diff --git a/localedata/SUPPORTED b/localedata/SUPPORTED
index 8ca023e..2a78391 100644
--- a/localedata/SUPPORTED
+++ b/localedata/SUPPORTED
@@ -1,6 +1,7 @@
# This file names the currently supported and somewhat tested locales.
# If you have any additions please file a glibc bug report.
SUPPORTED-LOCALES=\
+C.UTF-8/UTF-8 \
aa_DJ.UTF-8/UTF-8 \
aa_DJ/ISO-8859-1 \
aa_ER/UTF-8 \
diff --git a/localedata/locales/C b/localedata/locales/C
new file mode 100644
index 0000000..fdf460e
--- /dev/null
+++ b/localedata/locales/C
@@ -0,0 +1,238 @@
+escape_char /
+comment_char %
+% Locale for C locale in UTF-8
+
+LC_IDENTIFICATION
+title "C locale"
+source ""
+address ""
+contact ""
+email "mfabian@redhat.com"
+tel ""
+fax ""
+language "C"
+territory ""
+revision "1.0"
+date "2015-08-10"
+%
+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";""
+translit_end
+
+END LC_CTYPE
+
+LC_COLLATE
+order_start forward
+<U0000>
+..
+<UFFFF>
+<U00010000>
+..
+<U0001FFFF>
+<U00020000>
+..
+<U0002FFFF>
+<U000E0000>
+..
+<U000EFFFF>
+<U000F0000>
+..
+<U000FFFFF>
+<U00100000>
+..
+<U0010FFFF>
+UNDEFINED
+order_end
+END LC_COLLATE
+
+LC_MONETARY
+% This is the 14652 i18n fdcc-set definition for
+% the LC_MONETARY category
+% (except for the int_curr_symbol and currency_symbol, they are empty in
+% the 14652 i18n fdcc-set definition and also empty in
+% glibc/locale/C-monetary.c. But localedef complains in that case).
+%
+% Using "USD" for int_curr_symbol. But maybe "XXX" would be better?
+% XXX is "No currency" (https://en.wikipedia.org/wiki/ISO_4217)
+int_curr_symbol "<U0055><U0053><U0044><U0020>"
+% Using "$" for currency_symbol. But maybe <U00A4> would be better?
+% U+00A4 is the "generic currency symbol"
+% (https://en.wikipedia.org/wiki/Currency_sign_%28typography%29)
+currency_symbol "<U0024>"
+mon_decimal_point "<U002E>"
+mon_thousands_sep ""
+mon_grouping -1
+positive_sign ""
+negative_sign "<U002D>"
+int_frac_digits -1
+frac_digits -1
+p_cs_precedes -1
+int_p_sep_by_space -1
+p_sep_by_space -1
+n_cs_precedes -1
+int_n_sep_by_space -1
+n_sep_by_space -1
+p_sign_posn -1
+n_sign_posn -1
+%
+END LC_MONETARY
+
+LC_NUMERIC
+% This is the POSIX Locale definition for
+% the LC_NUMERIC category.
+%
+decimal_point "<U002E>"
+thousands_sep ""
+grouping -1
+END LC_NUMERIC
+
+LC_TIME
+% This is the POSIX Locale definition for
+% the LC_TIME category.
+%
+% Abbreviated weekday names (%a)
+abday "<U0053><U0075><U006E>";"<U004D><U006F><U006E>";/
+ "<U0054><U0075><U0065>";"<U0057><U0065><U0064>";/
+ "<U0054><U0068><U0075>";"<U0046><U0072><U0069>";/
+ "<U0053><U0061><U0074>"
+
+% Full weekday names (%A)
+day "<U0053><U0075><U006E><U0064><U0061><U0079>";/
+ "<U004D><U006F><U006E><U0064><U0061><U0079>";/
+ "<U0054><U0075><U0065><U0073><U0064><U0061><U0079>";/
+ "<U0057><U0065><U0064><U006E><U0065><U0073><U0064><U0061><U0079>";/
+ "<U0054><U0068><U0075><U0072><U0073><U0064><U0061><U0079>";/
+ "<U0046><U0072><U0069><U0064><U0061><U0079>";/
+ "<U0053><U0061><U0074><U0075><U0072><U0064><U0061><U0079>"
+
+% Abbreviated month names (%b)
+abmon "<U004A><U0061><U006E>";"<U0046><U0065><U0062>";/
+ "<U004D><U0061><U0072>";"<U0041><U0070><U0072>";/
+ "<U004D><U0061><U0079>";"<U004A><U0075><U006E>";/
+ "<U004A><U0075><U006C>";"<U0041><U0075><U0067>";/
+ "<U0053><U0065><U0070>";"<U004F><U0063><U0074>";/
+ "<U004E><U006F><U0076>";"<U0044><U0065><U0063>"
+
+% Full month names (%B)
+mon "<U004A><U0061><U006E><U0075><U0061><U0072><U0079>";/
+ "<U0046><U0065><U0062><U0072><U0075><U0061><U0072><U0079>";/
+ "<U004D><U0061><U0072><U0063><U0068>";/
+ "<U0041><U0070><U0072><U0069><U006C>";/
+ "<U004D><U0061><U0079>";/
+ "<U004A><U0075><U006E><U0065>";/
+ "<U004A><U0075><U006C><U0079>";/
+ "<U0041><U0075><U0067><U0075><U0073><U0074>";/
+ "<U0053><U0065><U0070><U0074><U0065><U006D><U0062><U0065><U0072>";/
+ "<U004F><U0063><U0074><U006F><U0062><U0065><U0072>";/
+ "<U004E><U006F><U0076><U0065><U006D><U0062><U0065><U0072>";/
+ "<U0044><U0065><U0063><U0065><U006D><U0062><U0065><U0072>"
+
+% Week description, consists of three fields:
+% 1. Number of days in a week.
+% 2. Gregorian date that is a first weekday (19971130 for Sunday, 19971201 for Monday).
+% 3. The weekday number to be contained in the first week of the year.
+%
+% ISO 8601 conforming applications should use the values 7, 19971201 (a
+% Monday), and 4 (Thursday), respectively.
+week 7;19971201;4
+first_weekday 1
+first_workday 1
+
+% Appropriate date and time representation (%c)
+% "%a %b %e %H:%M:%S %Y"
+d_t_fmt "<U0025><U0061><U0020><U0025><U0062><U0020><U0025><U0065><U0020><U0025><U0048><U003A><U0025><U004D><U003A><U0025><U0053><U0020><U0025><U0059>"
+
+% Appropriate date representation (%x)
+% "%m/%d/%y"
+d_fmt "<U0025><U006D><U002F><U0025><U0064><U002F><U0025><U0079>"
+
+% Appropriate time representation (%X)
+% "%H:%M:%S"
+t_fmt "<U0025><U0048><U003A><U0025><U004D><U003A><U0025><U0053>"
+
+% Appropriate AM/PM time representation (%r)
+% "%I:%M:%S %p"
+t_fmt_ampm "<U0025><U0049><U003A><U0025><U004D><U003A><U0025><U0053><U0020><U0025><U0070>"
+
+% Equivalent of AM/PM (%p) "AM"/"PM"
+%
+am_pm "<U0041><U004D>";"<U0050><U004D>"
+
+% Appropriate date representation (date(1)) "%a %b %e %H:%M:%S %Z %Y"
+date_fmt "<U0025><U0061><U0020><U0025><U0062><U0020><U0025><U0065><U0020><U0025><U0048><U003A><U0025><U004D><U003A><U0025><U0053><U0020><U0025><U005A><U0020><U0025><U0059>"
+END LC_TIME
+
+LC_MESSAGES
+% This is the POSIX Locale definition for
+% the LC_NUMERIC category.
+%
+yesexpr "<U005E><U005B><U0079><U0059><U005D>"
+noexpr "<U005E><U005B><U006E><U004E><U005D>"
+yesstr "<U0059><U0065><U0073>"
+nostr "<U004E><U006F>"
+END LC_MESSAGES
+
+LC_PAPER
+% This is the ISO/IEC 14652 "i18n" definition for
+% the LC_PAPER category.
+% (A4 paper, this is also used in the built in C/POSIX
+% locale in glibc/locale/C-paper.c)
+height 297
+width 210
+END LC_PAPER
+
+LC_NAME
+% This is the ISO/IEC 14652 "i18n" definition for
+% the LC_NAME category.
+% "%p%t%g%t%m%t%f"
+% (also used in the built in C/POSIX locale in glibc/locale/C-name.c)
+name_fmt "<U0025><U0070><U0025><U0074><U0025><U0067><U0025><U0074>/
+<U0025><U006D><U0025><U0074><U0025><U0066>"
+END LC_NAME
+
+LC_ADDRESS
+% This is the ISO/IEC 14652 "i18n" definition for
+% the LC_ADDRESS category.
+% "%a%N%f%N%d%N%b%N%s %h %e %r%N%C-%z %T%N%c%N"
+% (also used in the built in C/POSIX locale in glibc/locale/C-address.c)
+postal_fmt "<U0025><U0061><U0025><U004E><U0025><U0066><U0025><U004E>/
+<U0025><U0064><U0025><U004E><U0025><U0062><U0025><U004E><U0025><U0073>/
+<U0020><U0025><U0068><U0020><U0025><U0065><U0020><U0025><U0072><U0025>/
+<U004E><U0025><U0043><U002D><U0025><U007A><U0020><U0025><U0054><U0025>/
+<U004E><U0025><U0063><U0025><U004E>"
+END LC_ADDRESS
+
+LC_TELEPHONE
+% This is the ISO/IEC 14652 "i18n" definition for
+% the LC_TELEPHONE category.
+% "+%c %a %l"
+tel_int_fmt "<U002B><U0025><U0063><U0020><U0025><U0061><U0020><U0025>/
+<U006C>"
+% (also used in the built in C/POSIX locale in glibc/locale/C-telephone.c)
+END LC_TELEPHONE
+
+LC_MEASUREMENT
+% This is the ISO/IEC 14652 "i18n" definition for
+% the LC_MEASUREMENT category.
+% (same as in the built in C/POSIX locale in glibc/locale/C-measurement.c)
+%metric
+measurement 1
+END LC_MEASUREMENT
+
--
2.4.3