localedata: Add brh_PK locale for Brahui language [BZ #33952]

Add locale data for Brahui (brh), a Dravidian language spoken by
approximately 2.8 million people (2023 Pakistan Census) primarily in
Balochistan, Pakistan.  Brahui is the only Dravidian language written
in the Perso-Arabic (Nastaliq) script.

The ISO 639-3 code brh is added to iso-639.def.  Brahui has no ISO
639-1 or ISO 639-2 code, so the three-letter code is used for both the
terminology and bibliographic fields, as is already done for other
639-3-only entries such as brx (Bodo).

Locale content follows CLDR locale brh, for which the submitter is the
contributing native speaker.

Changes since v3:
  - iso-639.def: place Brahui before Braj, restoring alphabetical
    order by English language name.
  - LC_TIME: add first_weekday 1 and first_workday 2.  The previous
    value of 7 selected Saturday, which does not match CLDR territory
    data for PK (firstDay = sun); ur_PK and sd_PK both use 1.
  - LC_TIME: reorder d_t_fmt and date_fmt so the date precedes the
    time, matching the CLDR brh date-time combination pattern and the
    shape used by sd_PK, and use U+060C ARABIC COMMA as the separator,
    which is the comma in the CLDR brh punctuation exemplar set.
  - LC_TIME: abday repeats the full day names, as Brahui has no
    distinct abbreviated forms; CLDR brh gives identical values at the
    abbreviated and wide widths, and ur_PK, pa_PK and fa_IR do the
    same.
  - LC_TIME: am_pm now matches the CLDR brh day-period values.
  - LC_MONETARY: n_sep_by_space 1, matching p_sep_by_space, so that
    positive and negative amounts are spaced alike.
  - LC_MESSAGES: yesexpr accepts U+062C and U+0647, and noexpr accepts
    U+0627, since these initials occur in attested spellings of the
    affirmative and negative words.
  - LC_CTYPE: add transliterations for U+06C1 and U+06B7.
  - LC_TELEPHONE: use the "+%c %a %l" form.
  - LC_IDENTIFICATION: record CLDR as the source; bump revision.

Signed-off-by: Hammad Mengal <hammadalo99@gmail.com>

Reviewed-by: Mike FABIAN <mfabian@redhat.com>
This commit is contained in:
Hammad Mengal
2026-07-28 09:00:36 +02:00
committed by Mike FABIAN
parent fdc90dbb52
commit 18b8719d1e
3 changed files with 237 additions and 0 deletions
+1
View File
@@ -77,6 +77,7 @@ DEFINE_LANGUAGE_CODE ("Bislama", bi, bis, bis)
DEFINE_LANGUAGE_CODE3 ("Blin; Bilin", byn, byn)
DEFINE_LANGUAGE_CODE3 ("Bodo", brx, brx)
DEFINE_LANGUAGE_CODE ("Bosnian", bs, bos, bos)
DEFINE_LANGUAGE_CODE3 ("Brahui", brh, brh)
DEFINE_LANGUAGE_CODE3 ("Braj", bra, bra)
DEFINE_LANGUAGE_CODE ("Breton", br, bre, bre)
DEFINE_LANGUAGE_CODE3 ("Buginese", bug, bug)
+1
View File
@@ -74,6 +74,7 @@ bo_IN/UTF-8 \
br_FR.UTF-8/UTF-8 \
br_FR/ISO-8859-1 \
br_FR@euro/ISO-8859-15 \
brh_PK/UTF-8 \
brx_IN/UTF-8 \
bs_BA.UTF-8/UTF-8 \
bs_BA/ISO-8859-2 \
+235
View File
@@ -0,0 +1,235 @@
comment_char %
escape_char /
% This file is part of the GNU C Library and contains locale data.
% The Free Software Foundation does not claim any copyright interest
% in the locale data contained in this file. The foregoing does not
% affect the license of the GNU C Library as a whole. It does not
% exempt you from the conditions of the license if your use would
% otherwise be governed by that license.
% Brahui Language Locale for Pakistan
% Source: Unicode CLDR (locale brh)
% Contact: Hammad Mengal
% Email: hammadalo99@gmail.com
% Language: brh
% Territory: PK
% Revision: 0.4
% Date: 2026-07-19
% Users: general
LC_IDENTIFICATION
title "Brahui Language Locale for Pakistan"
source "Unicode CLDR"
address ""
contact "Hammad Mengal"
email "hammadalo99@gmail.com"
tel ""
fax ""
language "Brahui"
territory "Pakistan"
revision "0.4"
date "2026-07-19"
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";""
% Maddah above -> Alef with madda above
<U0653> "<U0622>"
% Farsi yeh -> yeh
<U06CC> "<U064A>"
% Heh goal -> heh
<U06C1> "<U0647>"
% Lam with three dots above -> lam
<U06B7> "<U0644>"
translit_end
END LC_CTYPE
LC_COLLATE
% Brahui uses the Arabic-Urdu based Nastaliq script with one additional
% letter not found in standard Urdu: ڷ (Lam with Three Dots Above),
% representing a retroflex lateral.The tailoring below states the
% Brahui rule explicitly rather than relying on that default.
copy "iso14651_t1"
reorder-after <S0644> % Lam
<S06B7> % ڷ Lam with Three Dots Above - Brahui retroflex lateral
reorder-end
END LC_COLLATE
LC_MONETARY
int_curr_symbol "PKR "
currency_symbol "Rs"
mon_decimal_point "."
mon_thousands_sep ","
mon_grouping 3
positive_sign ""
negative_sign "-"
int_frac_digits 2
frac_digits 2
p_cs_precedes 1
p_sep_by_space 1
n_cs_precedes 1
n_sep_by_space 1
p_sign_posn 2
n_sign_posn 1
END LC_MONETARY
LC_NUMERIC
% Brahui uses Western (Latin) digits, not Eastern Arabic-Indic digits.
decimal_point "."
thousands_sep ","
grouping 3
END LC_NUMERIC
LC_TIME
% Brahui day names follow the Persian/Dari ordinal convention
% (yak-shanbeh, do-shanbeh, ...).
% The two elements are written with a space, matching CLDR brh.
% Brahui has no distinct abday names, so abday repeats the
% full forms. ur_PK, pa_PK and fa_IR do the same.
abday "یک شنبہ";/
"دو شنبہ";/
"سہ شنبہ";/
"چار شنبہ";/
"پنچ شنبہ";/
"جمعہ";/
"شنبہ"
day "یک شنبہ";/
"دو شنبہ";/
"سہ شنبہ";/
"چار شنبہ";/
"پنچ شنبہ";/
"جمعہ";/
"شنبہ"
abmon "جنوری";/
"فروری";/
"مارچ";/
"اپریل";/
"مئی";/
"جون";/
"جولائی";/
"اگست";/
"ستمبر";/
"اکتوبر";/
"نومبر";/
"دسمبر"
mon "جنوری";/
"فروری";/
"مارچ";/
"اپریل";/
"مئی";/
"جون";/
"جولائی";/
"اگست";/
"ستمبر";/
"اکتوبر";/
"نومبر";/
"دسمبر"
% Date and time format. The date precedes the time, matching the CLDR
% brh date-time combination pattern, and runs weekday, day, month,
% year, as in the CLDR brh full date pattern. The separator before the
% time is U+060C ARABIC COMMA, which is the comma in the CLDR brh
% punctuation exemplar set. Same shape as sd_PK.
d_t_fmt "%A %d %B %Y<U060C> %H:%M:%S"
% Date and time format for date(1)
date_fmt "%A %d %B %Y<U060C> %H:%M:%S %Z"
% date Format. standard in Pakistan
d_fmt "%d//%m//%Y"
% time format 24 hour
t_fmt "%H:%M:%S"
am_pm "AM";"PM"
% time format 12 hour
t_fmt_ampm "%I:%M:%S %p"
% Calender rtl
cal_direction 3
first_weekday 1
first_workday 2
week 7;19971130;1
END LC_TIME
LC_MESSAGES
% Brahui yes/no expressions
% ہ = ہان (Brahui: yes) - U+06C1 Heh Goal
% آ = آخہ (Brahui: no)
% yesexpr also accepts:
% ه U+0647 ARABIC LETTER HEH, since both spellings of the initial
% letter of ہان are in use
% ب U+0628, the initial of بلکل (bilkul, "absolutely"), a common
% affirmative
% yesexpr matches: + 1 y Y ج(U+062C) ہ(U+06C1) ه(U+0647) ب(U+0628)
% noexpr matches: - 0 n N آ(U+0622) ا(U+0627) ن(U+0646)
yesexpr "^[+1yYجہهب]"
noexpr "^[-0nNآان]"
yesstr "ہان"
nostr "آخہ"
END LC_MESSAGES
LC_PAPER
copy "i18n"
END LC_PAPER
LC_MEASUREMENT
copy "i18n"
END LC_MEASUREMENT
LC_NAME
% Brahui name formatting
% Western order: salutation, given name, middle name, family name
name_fmt "%d%t%g%t%m%t%f"
name_gen "جواننگا"
name_mr "خواجہ"
name_mrs "گودی"
name_miss "بی بی"
name_ms "بی بی"
END LC_NAME
LC_ADDRESS
% Brahui address format for Pakistan
postal_fmt "%a%N%f%N%d%N%b%N%h %s %e %r%N%T %z%N%c%N"
country_name "پاکستان"
country_ab2 "PK"
country_ab3 "PAK"
country_num 586
country_car "PK"
% Brahui has no ISO 639-1 (two-letter) code, so lang_ab is omitted,
% following the ckb_IQ precedent. brh is an ISO 639-3 code.
lang_name "براہوئی"
lang_term "brh"
lang_lib "brh"
END LC_ADDRESS
LC_TELEPHONE
tel_int_fmt "+%c %a %l"
int_prefix "92"
int_select "00"
END LC_TELEPHONE