mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-30 16:50:07 +00:00
355 lines
11 KiB
Plaintext
355 lines
11 KiB
Plaintext
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.
|
||
|
||
% Malayalam language locale for India.
|
||
|
||
LC_IDENTIFICATION
|
||
title "Malayalam language locale for India"
|
||
source "Free Software Foundation of India, Trivandrum"
|
||
address ""
|
||
contact ""
|
||
email "bug-glibc-locales@gnu.org"
|
||
tel ""
|
||
fax ""
|
||
language "Malayalam"
|
||
territory "India"
|
||
revision "0.1"
|
||
date "2003-February-01"
|
||
|
||
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"
|
||
|
||
% Malayalam uses the alternate digits U+0D66..U+0D6F
|
||
outdigit <U0D66>..<U0D6F>
|
||
|
||
% This is used in the scanf family of functions to read Malayalam numbers
|
||
% using "%Id" and such.
|
||
map to_inpunct; /
|
||
(<U0030>,<U0D66>); /
|
||
(<U0031>,<U0D67>); /
|
||
(<U0032>,<U0D68>); /
|
||
(<U0033>,<U0D69>); /
|
||
(<U0034>,<U0D6A>); /
|
||
(<U0035>,<U0D6B>); /
|
||
(<U0036>,<U0D6C>); /
|
||
(<U0037>,<U0D6D>); /
|
||
(<U0038>,<U0D6E>); /
|
||
(<U0039>,<U0D6F>);
|
||
|
||
translit_start
|
||
include "translit_combining";""
|
||
translit_end
|
||
END LC_CTYPE
|
||
%
|
||
%
|
||
LC_COLLATE
|
||
% CLDR collation rules for Malayalam:
|
||
% (see: https://unicode.org/cldr/trac/browser/trunk/common/collation/ml.xml)
|
||
%
|
||
% <collation type="standard" references="Sabdatharavali Malayalam Dictionary 23rd Ed. by Sahithya Pravarthaka Co-operative Society Ltd.">
|
||
% <cr><![CDATA[
|
||
% [reorder Mlym Latn Deva Arab Taml Knda Telu Beng Guru Gujr Orya Sinh] # native speaker's special list
|
||
% #
|
||
% # Avagraha and Visarga are primary ignorables.
|
||
% #
|
||
% &ഃ<<ഽ
|
||
% #
|
||
% # Vowel sign AU ( ൌ) and AU length mark ( ൗ) need to differ
|
||
% # only on secondary level, not primary.
|
||
% #
|
||
% &\u0D4C<<\u0D57
|
||
% #
|
||
% # Pre-5.1 Chillus secondary equal to 5.1 chillus.
|
||
% # Chillus primary equal to their consonant_dead form.
|
||
% #
|
||
% &ക്<<ക്\u200D<<<ൿ
|
||
% &ണ്<<ണ്\u200D<<<ൺ
|
||
% &ന്<<ന്\u200D<<<ൻ
|
||
% &ര്<<ര്\u200D<<<ർ
|
||
% &ല്<<ല്\u200D<<<ൽ
|
||
% &ള്<<ള്\u200D<<<ൾ
|
||
% #
|
||
% # Anuswara primary equal to MA_dead.
|
||
% #
|
||
% &മ്<<ം
|
||
% #
|
||
% # /nta/ is sorted as <NA, Virama, RRA>.
|
||
% #
|
||
% &ന്<<<ൻ്
|
||
% ]]></cr>
|
||
% </collation>
|
||
%
|
||
% And CLDR also lists the following
|
||
% index characters:
|
||
% (see: https://unicode.org/cldr/trac/browser/trunk/common/main/ml.xml)
|
||
%
|
||
% <exemplarCharacters type="index" draft="contributed">[അ ആ ഇ ഈ ഉ ഊ ഋ എ ഏ ഐ ഒ ഓ ഔ ക ഖ ഗ ഘ ങ ച ഛ ജ ഝ ഞ ട ഠ ഡ ഢ ണ ത ഥ ദ ധ ന പ ഫ ബ ഭ മ യ ര ല വ ശ ഷ സ ഹ ള ഴ റ]</exemplarCharacters>
|
||
%
|
||
% The following rules implement the same order for glibc.
|
||
copy "iso14651_t1"
|
||
% &ക്<<ക്\u200D<<<ൿ
|
||
collating-element <e0d15-0d4d> from "<U0D15><U0D4D>"
|
||
collating-symbol <s0d15-0d4d>
|
||
collating-element <e0d15-0d4d-200d> from "<U0D15><U0D4D><U200D>"
|
||
collating-symbol <s0d15-0d4d-200d>
|
||
% &ണ്<<ണ്\u200D<<<ൺ
|
||
collating-element <e0d23-0d4d> from "<U0D23><U0D4D>"
|
||
collating-symbol <s0d23-0d4d>
|
||
collating-element <e0d23-0d4d-200d> from "<U0D23><U0D4D><U200D>"
|
||
collating-symbol <s0d23-0d4d-200d>
|
||
% &ന്<sന്\u200D<<<ൻ
|
||
collating-element <e0d28-0d4d> from "<U0D28><U0D4D>"
|
||
collating-symbol <s0d28-0d4d>
|
||
collating-element <e0d28-0d4d-200d> from "<U0D28><U0D4D><U200D>"
|
||
collating-symbol <s0d28-0d4d-200d>
|
||
% &ര്<<ര്\u200D<<<ർ
|
||
collating-element <e0d30-0d4d> from "<U0D30><U0D4D>"
|
||
collating-symbol <s0d30-0d4d>
|
||
collating-element <e0d30-0d4d-200d> from "<U0D30><U0D4D><U200D>"
|
||
collating-symbol <s0d30-0d4d-200d>
|
||
% &ല്<<ല്\u200D<<<ൽ
|
||
collating-element <e0d32-0d4d> from "<U0D32><U0D4D>"
|
||
collating-symbol <s0d32-0d4d>
|
||
collating-element <e0d32-0d4d-200d> from "<U0D32><U0D4D><U200D>"
|
||
collating-symbol <s0d32-0d4d-200d>
|
||
% &ള്<<ള്\u200D<<<ൾ
|
||
collating-element <e0d33-0d4d> from "<U0D33><U0D4D>"
|
||
collating-symbol <s0d33-0d4d>
|
||
collating-element <e0d33-0d4d-200d> from "<U0D33><U0D4D><U200D>"
|
||
collating-symbol <s0d33-0d4d-200d>
|
||
% #
|
||
% # Anuswara primary equal to MA_dead.
|
||
% #
|
||
% &മ്<<ം
|
||
collating-element <e0d2e-0d4d> from "<U0D2e><U0D4D>"
|
||
collating-symbol <s0d2e-0d4d>
|
||
% #
|
||
% # /nta/ is sorted as <NA, Virama, RRA>.
|
||
% #
|
||
% &ന്<<<ൻ്
|
||
% already defined:
|
||
% collating-element <e0d28-0d4d> from "<U0D28><U0D4D>"
|
||
% already defined:
|
||
% collating-symbol <s0d28-0d4d>
|
||
collating-element <e0d7b-0d4d> from "<U0D7B><U0D4D>"
|
||
collating-symbol <s0d7b-0d4d>
|
||
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
||
% Finished defining collating-elements and collating-symbols
|
||
%
|
||
% One dummy reorder-after statement here to avoid a syntax error
|
||
% because the first rule reordering stuff starts without a reorder-after:
|
||
collating-symbol <dummy>
|
||
reorder-after <AFTER-A>
|
||
<dummy>
|
||
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
||
% # Avagraha and Visarga are primary ignorables.
|
||
% &ഃ<<ഽ
|
||
<U0D03> IGNORE;<VISARGA>;<MIN>;<U0D03> % MALAYALAM SIGN VISARGA
|
||
<U0D3D> IGNORE;<VRNT1>;<MIN>;<U0D3D> % MALAYALAM SIGN AVAGRAHA
|
||
% # Vowel sign AU ( ൌ) and AU length mark ( ൗ) need to differ
|
||
% # only on secondary level, not primary.
|
||
% #
|
||
% &\u0D4C<<\u0D57
|
||
<U0D4C> <S0D4C>;<BASE>;<MIN>;<U0D4C> % MALAYALAM VOWEL SIGN AU
|
||
<U0D57> <S0D4C>;<VRNT1>;<MIN>;<U0D57> % MALAYALAM AU LENGTH MARK
|
||
% &ക്<<ക്\u200D<<<ൿ
|
||
<e0d15-0d4d> "<S0D15><S0D4D>";"<BASE><BASE>";"<MIN><MIN>";IGNORE
|
||
<e0d15-0d4d-200d> "<S0D15><S0D4D>";"<BASE><VRNT1>";"<MIN><MIN>";IGNORE
|
||
<U0D7F> "<S0D15><S0D4D>";"<BASE><VRNT1>";"<COMPAT><COMPAT>";<U0D7F>
|
||
% &ണ്<<ണ്\u200D<<<ൺ
|
||
<e0d23-0d4d> "<S0D23><S0D4D>";"<BASE><BASE>";"<MIN><MIN>";IGNORE
|
||
<e0d23-0d4d-200d> "<S0D23><S0D4D>";"<BASE><VRNT1>";"<MIN><MIN>";IGNORE
|
||
<U0D7A> "<S0D23><S0D4D>";"<BASE><VRNT1>";"<COMPAT><COMPAT>";<U0D7A>
|
||
% &ന്<<ന്\u200D<<<ൻ
|
||
<e0d28-0d4d> "<S0D28><S0D4D>";"<BASE><BASE>";"<MIN><MIN>";IGNORE % ന്
|
||
<e0d28-0d4d-200d> "<S0D28><S0D4D>";"<BASE><VRNT1>";"<MIN><MIN>";IGNORE % ന്
|
||
<U0D7B> "<S0D28><S0D4D>";"<BASE><VRNT1>";"<COMPATCAP><COMPATCAP>";<U0D7B> % ൻ
|
||
% &ര്<<ര്\u200D<<<ർ
|
||
<e0d30-0d4d> "<S0D30><S0D4D>";"<BASE><BASE>";"<MIN><MIN>";IGNORE
|
||
<e0d30-0d4d-200d> "<S0D30><S0D4D>";"<BASE><VRNT1>";"<MIN><MIN>";IGNORE
|
||
<U0D7C> "<S0D30><S0D4D>";"<BASE><VRNT1>";"<COMPAT><COMPAT>";<U0D7C> % ർ
|
||
% &ല്<<ല്\u200D<<<ൽ
|
||
<e0d32-0d4d> "<S0D32><S0D4D>";"<BASE><BASE>";"<MIN><MIN>";IGNORE
|
||
<e0d32-0d4d-200d> "<S0D32><S0D4D>";"<BASE><VRNT1>";"<MIN><MIN>";IGNORE
|
||
<U0D7D> "<S0D32><S0D4D>";"<BASE><VRNT1>";"<COMPAT><COMPAT>";<U0D7D>
|
||
% &ള്<<ള്\u200D<<<ൾ
|
||
<e0d33-0d4d> "<S0D33><S0D4D>";"<BASE><BASE>";"<MIN><MIN>";IGNORE
|
||
<e0d33-0d4d-200d> "<S0D33><S0D4D>";"<BASE><VRNT1>";"<MIN><MIN>";IGNORE
|
||
<U0D7E> "<S0D33><S0D4D>";"<BASE><VRNT1>";"<COMPAT><COMPAT>";<U0D7E>
|
||
% #
|
||
% # Anuswara primary equal to MA_dead.
|
||
% #
|
||
% &മ്<<ം
|
||
<e0d2e-0d4d> "<S0D2E><S0D4D>";"<BASE><BASE>";"<MIN><MIN>";IGNORE % മ്
|
||
<U0D02> "<S0D2E><S0D4D>";"<BASE><VRNT1>";"<MIN><MIN>";IGNORE % MALAYALAM SIGN ANUSVARA
|
||
% #
|
||
% # /nta/ is sorted as <NA, Virama, RRA>.
|
||
% #
|
||
% &ന്<<<ൻ്
|
||
%
|
||
% It looks to me that the above line
|
||
% is a contradiction to the earlier rule: &ന്<<ന്\u200D<<<ൻ
|
||
% I experimented with libicu to see how libicu sorts given these rules.
|
||
% And the end result seems to be the same as if the above two rules had been
|
||
% combined in a rule like this:
|
||
%
|
||
% &ന്<<ന്\u200D<<<ൻ്<<<ൻ
|
||
%
|
||
% So I write the glibc rules to reproduce that behaviour.
|
||
<e0d28-0d4d> "<S0D28><S0D4D>";"<BASE><BASE>";"<MIN><MIN>";<U0D28> % ന്
|
||
<e0d7b-0d4d> "<S0D28><S0D4D>";"<BASE><VRNT1>";"<COMPAT><COMPAT>";<U0D7B> % ൻ്
|
||
|
||
reorder-end
|
||
|
||
END LC_COLLATE
|
||
%
|
||
LC_MONETARY
|
||
copy "hi_IN"
|
||
END LC_MONETARY
|
||
%
|
||
LC_NUMERIC
|
||
% This is the POSIX Locale definition for the LC_NUMERIC category.
|
||
%
|
||
decimal_point "."
|
||
thousands_sep ","
|
||
grouping 3;2
|
||
%
|
||
END LC_NUMERIC
|
||
%
|
||
LC_TIME
|
||
% This is the POSIX Locale definition for the LC_TIME category
|
||
% generated by IBM Basic CountryPack Transformer.
|
||
% These are generated based on XML base Locale definition file
|
||
% for IBM Class for Unicode.
|
||
%
|
||
% Abbreviated weekday names (%a)
|
||
abday "ഞാ";"തി";/
|
||
"ചൊ";"ബു";/
|
||
"വ്യാ";"വെ";/
|
||
"ശ"
|
||
%
|
||
% Full weekday names (%A)
|
||
day "ഞായര്";/
|
||
"തിങ്കള്";/
|
||
"ചൊവ്വ";/
|
||
"ബുധന്";/
|
||
"വ്യാഴം";/
|
||
"വെള്ളി";/
|
||
"ശനി"
|
||
%
|
||
% Abbreviated month names (%b)
|
||
abmon "ജനു";/
|
||
"ഫെബ്രു";/
|
||
"മാർ";/
|
||
"ഏപ്രി";/
|
||
"മേയ്";/
|
||
"ജൂൺ";/
|
||
"ജൂലൈ";/
|
||
"ഓഗ";/
|
||
"സെപ്റ്റം";/
|
||
"ഒക്ടോ";/
|
||
"നവം";/
|
||
"ഡിസം"
|
||
%
|
||
% FULL month names (%B)
|
||
mon "ജനുവരി";/
|
||
"ഫെബ്രുവരി";/
|
||
"മാർച്ച്";/
|
||
"ഏപ്രിൽ";/
|
||
"മേയ്";/
|
||
"ജൂൺ";/
|
||
"ജൂലൈ";/
|
||
"ഓഗസ്റ്റ്";/
|
||
"സെപ്റ്റംബർ";/
|
||
"ഒക്ടോബർ";/
|
||
"നവംബർ";/
|
||
"ഡിസംബർ"
|
||
%
|
||
%
|
||
% Equivalent of AM PM
|
||
am_pm "രാവിലെ";"വൈകു"
|
||
%
|
||
% Appropriate date and time representation
|
||
d_t_fmt "%A %d %B %Y %I:%M:%S %p"
|
||
%
|
||
% Appropriate date and time representation for date(1)
|
||
date_fmt "%A %d %B %Y %I:%M:%S %p %Z"
|
||
%
|
||
% Appropriate date representation
|
||
d_fmt "%-d//%-m//%y"
|
||
%
|
||
% Appropriate time representation
|
||
t_fmt "%I:%M:%S %p %Z"
|
||
%
|
||
% Appropriate 12 h time representation (%r)
|
||
t_fmt_ampm "%I:%M:%S %p %Z"
|
||
%
|
||
week 7;19971130;1
|
||
END LC_TIME
|
||
%
|
||
LC_MESSAGES
|
||
yesexpr "^[+1yYഉ]"
|
||
noexpr "^[-0nNഅ]"
|
||
yesstr "ഉവ്വ്"
|
||
nostr "അല്ല"
|
||
END LC_MESSAGES
|
||
%
|
||
LC_PAPER
|
||
copy "hi_IN"
|
||
END LC_PAPER
|
||
%
|
||
LC_NAME
|
||
% This is the ISO_IEC TR14652 Locale definition for the LC_NAME category
|
||
% generated by IBM Basic CountryPack Transformer.
|
||
%
|
||
%
|
||
name_fmt "%p%t%f%t%g"
|
||
name_gen "ശ്രീ"
|
||
name_mr "ശ്രീമാനു്"
|
||
name_mrs "ശ്രീമതി"
|
||
name_miss "കുമാരി"
|
||
name_ms "ശ്രീമതി"
|
||
END LC_NAME
|
||
LC_ADDRESS
|
||
% This is the ISO_IEC TR14652 Locale definition for the LC_ADDRESS category
|
||
% generated by IBM Basic CountryPack Transformer.
|
||
postal_fmt "%z%c%T%s%b%e%r"
|
||
country_name "ഇന്ത്യ"
|
||
country_ab2 "IN"
|
||
country_ab3 "IND"
|
||
country_num 356
|
||
country_car "IND"
|
||
lang_name "മലയാളം"
|
||
lang_ab "ml"
|
||
lang_term "mal"
|
||
lang_lib "mal"
|
||
END LC_ADDRESS
|
||
%
|
||
LC_TELEPHONE
|
||
copy "hi_IN"
|
||
END LC_TELEPHONE
|
||
%
|
||
LC_MEASUREMENT
|
||
copy "hi_IN"
|
||
END LC_MEASUREMENT
|