mirror of
https://sourceware.org/git/glibc.git
synced 2024-12-25 04:01:10 +00:00
8dc8be75d2
The commit does the following things: * Move non-transliteration Unicode generated data to i18n_ctype. * Copy the i18n_ctype data into i18n and add transliteration. In the future, any locale which needs Unicode LC_CTYPE data can also just use `copy i18n_ctype` and get the base character classes and maps without transliteration. Tested by compiling all the locales and my prototype C.UTF-8 which uses it. Signed-off-by: Carlos O'Donell <carlos@redhat.com>
416 lines
14 KiB
Plaintext
416 lines
14 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.
|
|
|
|
LC_IDENTIFICATION
|
|
title ""
|
|
source ""
|
|
address ""
|
|
contact ""
|
|
email ""
|
|
tel ""
|
|
fax ""
|
|
language ""
|
|
territory ""
|
|
revision ""
|
|
date "2017-06-20"
|
|
|
|
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
|
|
END LC_IDENTIFICATION
|
|
|
|
LC_CTYPE
|
|
|
|
copy "i18n_ctype"
|
|
|
|
translit_start
|
|
|
|
include "translit_neutral";""
|
|
|
|
default_missing <U003F>
|
|
|
|
translit_end
|
|
|
|
END LC_CTYPE
|
|
|
|
LC_COLLATE
|
|
|
|
% Case collating symbols
|
|
collating-symbol <RES-1>
|
|
collating-symbol <BLK>
|
|
collating-symbol <MIN> % SMALL
|
|
collating-symbol <WIDE> % WIDE
|
|
collating-symbol <COMPAT>
|
|
collating-symbol <FONT>
|
|
collating-symbol <CIRCLE>
|
|
collating-symbol <RES-2>
|
|
collating-symbol <CAP> % CAPITAL
|
|
collating-symbol <WIDECAP>
|
|
collating-symbol <COMPATCAP>
|
|
collating-symbol <FONTCAP>
|
|
collating-symbol <CIRCLECAP>
|
|
collating-symbol <HIRA-SMALL>
|
|
collating-symbol <HIRA>
|
|
collating-symbol <SMALL>
|
|
collating-symbol <SMALL-NARROW>
|
|
collating-symbol <KATA>
|
|
collating-symbol <NARROW>
|
|
collating-symbol <CIRCLE-KATA>
|
|
collating-symbol <MNN>
|
|
collating-symbol <MNS>
|
|
collating-symbol <VERTICAL>
|
|
% Arabic forms
|
|
collating-symbol <AINI>
|
|
collating-symbol <AMED>
|
|
collating-symbol <AFIN>
|
|
collating-symbol <AISO>
|
|
%
|
|
collating-symbol <NOBREAK>
|
|
collating-symbol <SQUARED>
|
|
collating-symbol <SQUAREDCAP>
|
|
collating-symbol <FRACTION>
|
|
collating-symbol <BLANK>
|
|
collating-symbol <CAPITAL-SMALL>
|
|
collating-symbol <SMALL-CAPITAL>
|
|
collating-symbol <BOTH>
|
|
% accents
|
|
collating-symbol <LOWLINE> % LOW LINE
|
|
collating-symbol <MACRO> % MACRON
|
|
collating-symbol <OBLIK> % STROKE
|
|
collating-symbol <AIGUT> % ACUTE ACCENT
|
|
collating-symbol <GRAVE> % GRAVE ACCENT
|
|
collating-symbol <BREVE> % BREVE
|
|
collating-symbol <CIRCF> % CIRCUMFLEX ACCENT
|
|
collating-symbol <CARON> % CARON
|
|
collating-symbol <CRCLE> % RING ABOVE
|
|
collating-symbol <TREMA> % DIAERESIS
|
|
collating-symbol <2AIGU> % DOUBLE ACUTE ACCENT
|
|
collating-symbol <TILDE> % TILDE
|
|
collating-symbol <POINT> % DOT ABOVE
|
|
collating-symbol <CEDIL> % CEDILLA
|
|
collating-symbol <OGONK> % OGONEK
|
|
collating-symbol <OVERLINE> % OVERLINE
|
|
collating-symbol <CROOK> % HOOK ABOVE
|
|
collating-symbol <TONOS> % VERTICAL LINE ABOVE
|
|
collating-symbol <D030E> % DOUBLE VERTICAL LINE ABOVE
|
|
collating-symbol <2GRAV> % DOUBLE GRAVE ACCENT
|
|
collating-symbol <D0310> % CANDRABINDU
|
|
collating-symbol <BREVR> % INVERTED BREVE
|
|
collating-symbol <D0312> % TURNED COMMA ABOVE
|
|
collating-symbol <PSILI> % COMMA ABOVE
|
|
collating-symbol <DASIA> % REVERSED COMMA ABOVE
|
|
collating-symbol <D0315> % COMMA ABOVE RIGHT
|
|
collating-symbol <D0316> % GRAVE ACCENT BELOW
|
|
collating-symbol <D0317> % ACUTE ACCENT BELOW
|
|
collating-symbol <D0318> % LEFT TACK BELOW
|
|
collating-symbol <D0319> % RIGHT TACK BELOW
|
|
collating-symbol <D031A> % LEFT ANGLE ABOVE
|
|
collating-symbol <HORNU> % HORN
|
|
collating-symbol <D031C> % LEFT HALF RING BELOW
|
|
collating-symbol <D031D> % UP TACK BELOW
|
|
collating-symbol <D031E> % DOWN TACK BELOW
|
|
collating-symbol <D031F> % PLUS SIGN BELOW
|
|
collating-symbol <D0320> % MINUS SIGN BELOW
|
|
collating-symbol <PALCR> % PALATALIZED HOOK BELOW
|
|
collating-symbol <RETCR> % RETROFLEX HOOK BELOW
|
|
collating-symbol <POINS> % DOT BELOW
|
|
collating-symbol <TREMS> % DIAERESIS BELOW
|
|
collating-symbol <CRCLS> % RING BELOW
|
|
collating-symbol <COMMS> % COMMA BELOW
|
|
collating-symbol <D0329> % VERTICAL LINE BELOW
|
|
collating-symbol <D032A> % BRIDGE BELOW
|
|
collating-symbol <D032B> % INVERTED DOUBLE ARCH BELOW
|
|
collating-symbol <D032C> % CARON BELOW
|
|
collating-symbol <CIRCS> % CIRCUMFLEX ACCENT BELOW
|
|
collating-symbol <BREVS> % BREVE BELOW
|
|
collating-symbol <D032F> % INVERTED BREVE BELOW
|
|
collating-symbol <TILDS> % TILDE BELOW
|
|
collating-symbol <MACRS> % MACRON BELOW
|
|
collating-symbol <D0333> % DOUBLE LOW LINE
|
|
collating-symbol <TILDX> % TILDE OVERLAY
|
|
collating-symbol <BARRE> % SHORT STROKE OVERLAY
|
|
collating-symbol <D0336> % LONG STROKE OVERLAY
|
|
collating-symbol <D0337> % SHORT SOLIDUS OVERLAY
|
|
collating-symbol <CRCL2> % RIGHT HALF RING BELOW
|
|
collating-symbol <D033A> % INVERTED BRIDGE BELOW
|
|
collating-symbol <D033B> % SQUARE BELOW
|
|
collating-symbol <D033C> % SEAGULL BELOW
|
|
collating-symbol <D033D> % X ABOVE
|
|
collating-symbol <D033E> % VERTICAL TILDE
|
|
collating-symbol <D033F> % DOUBLE OVERLINE
|
|
collating-symbol <PERIS> % GREEK PERISPOMENI
|
|
collating-symbol <YPOGE> % GREEK YPOGEGRAMMENI
|
|
collating-symbol <D0360> % DOUBLE TILDE
|
|
collating-symbol <D0361> % DOUBLE INVERTED BREVE
|
|
collating-symbol <DFE20> % LIGATURE LEFT HALF
|
|
collating-symbol <DFE21> % LIGATURE RIGHT HALF
|
|
collating-symbol <DFE22> % DOUBLE TILDE LEFT HALF
|
|
collating-symbol <DFE23> % DOUBLE TILDE RIGHT HALF
|
|
collating-symbol <D0483> % CYRILLIC TITLO
|
|
collating-symbol <D0484> % CYRILLIC PALATALIZATION
|
|
collating-symbol <D0485> % CYRILLIC DASIA PNEUMATA
|
|
collating-symbol <D0486> % CYRILLIC PSILI PNEUMATA
|
|
collating-symbol <SHEVA> % HEBREW POINT SHEVA
|
|
collating-symbol <HTFSG> % HEBREW POINT HATAF SEGOL
|
|
collating-symbol <HTFPT> % HEBREW POINT HATAF PATAH
|
|
collating-symbol <HTFQM> % HEBREW POINT HATAF QAMATS
|
|
collating-symbol <HIRIQ> % HEBREW POINT HIRIQ
|
|
collating-symbol <TSERE> % HEBREW POINT TSERE
|
|
collating-symbol <SEGOL> % HEBREW POINT SEGOL
|
|
collating-symbol <PATAH> % HEBREW POINT PATAH
|
|
collating-symbol <QAMAT> % HEBREW POINT QAMATS
|
|
collating-symbol <HOLAM> % HEBREW POINT HOLAM
|
|
collating-symbol <QUBUT> % HEBREW POINT QUBUTS
|
|
collating-symbol <DAGES> % HEBREW POINT DAGESH OR MAPIQ
|
|
collating-symbol <RAPHE> % HEBREW POINT RAFE
|
|
collating-symbol <SHINP> % HEBREW POINT SHIN DOT
|
|
collating-symbol <SINPT> % HEBREW POINT SIN DOT
|
|
collating-symbol <VARIKA> % HEBREW POINT JUDEO-SPANISH VARIKA
|
|
collating-symbol <FATHATAN> % ARABIC FATHATAN
|
|
collating-symbol <DAMMATAN> % ARABIC DAMMATAN
|
|
collating-symbol <KASRATAN> % ARABIC KASRATAN
|
|
collating-symbol <FATHA> % ARABIC FATHA
|
|
collating-symbol <DAMMA> % ARABIC DAMMA
|
|
collating-symbol <KASRA> % ARABIC KASRA
|
|
collating-symbol <SHADDA> % ARABIC SHADDA
|
|
collating-symbol <SUKUN> % ARABIC SUKUN
|
|
collating-symbol <SUPERALEF> % ARABIC LETTER SUPERSCRIPT ALEF
|
|
collating-symbol <D06D6> % ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA
|
|
collating-symbol <D06D7> % ARABIC SMALL HIGH LIGATURE QAF WITH LAM WITH ALEF MAKSURA
|
|
collating-symbol <D06D8> % ARABIC SMALL HIGH MEEM INITIAL FORM
|
|
collating-symbol <D06D9> % ARABIC SMALL HIGH LAM ALEF
|
|
collating-symbol <D06DA> % ARABIC SMALL HIGH JEEM
|
|
collating-symbol <D06DB> % ARABIC SMALL HIGH THREE DOTS
|
|
collating-symbol <D06DC> % ARABIC SMALL HIGH SEEN
|
|
collating-symbol <D06E1> % ARABIC SMALL HIGH DOTLESS HEAD OF KHAH
|
|
collating-symbol <D06E2> % ARABIC SMALL HIGH MEEM ISOLATED FORM
|
|
collating-symbol <D06E3> % ARABIC SMALL LOW SEEN
|
|
collating-symbol <AMADD> % ARABIC SMALL HIGH MADDA
|
|
collating-symbol <D06E7> % ARABIC SMALL HIGH YEH
|
|
collating-symbol <D06E8> % ARABIC SMALL HIGH NOON
|
|
collating-symbol <D06ED> % ARABIC SMALL LOW MEEM
|
|
collating-symbol <D093C> % DEVANAGARI SIGN NUKTA
|
|
collating-symbol <D0951> % DEVANAGARI STRESS SIGN UDATTA
|
|
collating-symbol <D0952> % DEVANAGARI STRESS SIGN ANUDATTA
|
|
collating-symbol <D0953> % DEVANAGARI GRAVE ACCENT
|
|
collating-symbol <D0954> % DEVANAGARI ACUTE ACCENT
|
|
collating-symbol <D09BC> % BENGALI SIGN NUKTA
|
|
collating-symbol <D0A3C> % GURMUKHI SIGN NUKTA
|
|
collating-symbol <D0ABC> % GUJARATI SIGN NUKTA
|
|
collating-symbol <D0B3C> % ORIYA SIGN NUKTA
|
|
collating-symbol <D0E48> % THAI CHARACTER MAI EK
|
|
collating-symbol <D0E49> % THAI CHARACTER MAI THO
|
|
collating-symbol <D0E4A> % THAI CHARACTER MAI TRI
|
|
collating-symbol <D0E4B> % THAI CHARACTER MAI CHATTAWA
|
|
collating-symbol <D0EC8> % LAO TONE MAI EK
|
|
collating-symbol <D0EC9> % LAO TONE MAI THO
|
|
collating-symbol <D0ECA> % LAO TONE MAI TI
|
|
collating-symbol <D0ECB> % LAO TONE MAI CATAWA
|
|
collating-symbol <D0F39> % TIBETAN MARK TSA -PHRU
|
|
collating-symbol <D0F3E> % TIBETAN SIGN YAR TSHES
|
|
collating-symbol <D0F3F> % TIBETAN SIGN MAR TSHES
|
|
collating-symbol <D302A> % IDEOGRAPHIC LEVEL TONE MARK
|
|
collating-symbol <D302B> % IDEOGRAPHIC RISING TONE MARK
|
|
collating-symbol <D302C> % IDEOGRAPHIC DEPARTING TONE MARK
|
|
collating-symbol <D302D> % IDEOGRAPHIC ENTERING TONE MARK
|
|
collating-symbol <D302E> % HANGUL SINGLE DOT TONE MARK
|
|
collating-symbol <D302F> % HANGUL DOUBLE DOT TONE MARK
|
|
collating-symbol <KNVCE> % KATAKANA-HIRAGANA VOICED SOUND MARK
|
|
collating-symbol <KNSMV> % KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
|
|
collating-symbol <D20D0> % LEFT HARPOON ABOVE
|
|
collating-symbol <D20D1> % RIGHT HARPOON ABOVE
|
|
collating-symbol <D20D2> % LONG VERTICAL LINE OVERLAY
|
|
collating-symbol <D20D3> % SHORT VERTICAL LINE OVERLAY
|
|
collating-symbol <D20D4> % ANTICLOCKWISE ARROW ABOVE
|
|
collating-symbol <D20D5> % CLOCKWISE ARROW ABOVE
|
|
collating-symbol <D20D6> % LEFT ARROW ABOVE
|
|
collating-symbol <D20D7> % RIGHT ARROW ABOVE
|
|
collating-symbol <D20D8> % RING OVERLAY
|
|
collating-symbol <D20D9> % CLOCKWISE RING OVERLAY
|
|
collating-symbol <D20DA> % ANTICLOCKWISE RING OVERLAY
|
|
collating-symbol <D20DB> % THREE DOTS ABOVE
|
|
collating-symbol <D20DC> % FOUR DOTS ABOVE
|
|
collating-symbol <D20DD> % ENCLOSING CIRCLE
|
|
collating-symbol <D20DE> % ENCLOSING SQUARE
|
|
collating-symbol <D20DF> % ENCLOSING DIAMOND
|
|
collating-symbol <D20E0> % ENCLOSING CIRCLE BACKSLASH
|
|
collating-symbol <D20E1> % LEFT RIGHT ARROW ABOVE
|
|
collating-symbol <NEGATIVE>
|
|
collating-symbol <SANSSERIF>
|
|
collating-symbol <NEGSANSSERIF>
|
|
collating-symbol <ARABIC>
|
|
collating-symbol <EXTARABIC>
|
|
collating-symbol <NAGAR>
|
|
collating-symbol <BENGL>
|
|
collating-symbol <BENGALINUMERATOR>
|
|
collating-symbol <GURMU>
|
|
collating-symbol <GUJAR>
|
|
collating-symbol <ORIYA>
|
|
collating-symbol <TAMIL>
|
|
collating-symbol <TELGU>
|
|
collating-symbol <KNNDA>
|
|
collating-symbol <MALAY>
|
|
collating-symbol <SINHALA>
|
|
collating-symbol <THAII>
|
|
collating-symbol <LAAOO>
|
|
collating-symbol <BODKA>
|
|
collating-symbol <CJKVS>
|
|
collating-symbol <S0200>..<S1100> % 0x0200..0x1100
|
|
|
|
collating-symbol <S4E00>..<S9FA5> % Symbols for Han
|
|
|
|
collating-symbol <SAC00>..<SD7A3> % Symbols for Hangul
|
|
|
|
collating-symbol <SFA0E>..<SFA29> % Symbols for Compatibility Han
|
|
|
|
% equivalences
|
|
symbol-equivalence <NONE> <BLANK>
|
|
symbol-equivalence <CAPITAL> <CAP>
|
|
symbol-equivalence <MACRON> <MACRO>
|
|
symbol-equivalence <STROKE> <OBLIK>
|
|
symbol-equivalence <ACUTE> <AIGUT>
|
|
symbol-equivalence <CIRCUMFLEX> <CIRCF>
|
|
symbol-equivalence <RING> <CRCLE>
|
|
symbol-equivalence <DIAERESIS> <TREMA>
|
|
symbol-equivalence <DOT> <POINT>
|
|
symbol-equivalence <CEDILLA> <CEDIL>
|
|
symbol-equivalence <OGONEK> <OGONK>
|
|
symbol-equivalence <HOOK> <CROOK>
|
|
symbol-equivalence <HORN> <HORNU>
|
|
symbol-equivalence <DOT-BELOW> <POINS>
|
|
|
|
% Copy the template from ISO/IEC 14651
|
|
copy "iso14651_t1"
|
|
|
|
END LC_COLLATE
|
|
|
|
LC_MONETARY
|
|
% This is the 14652 i18n fdcc-set definition for
|
|
% the LC_MONETARY category.
|
|
%
|
|
int_curr_symbol "<U0058><U0044><U0052><U0020>"
|
|
currency_symbol "<U00A4>"
|
|
mon_decimal_point "<U002C>"
|
|
mon_thousands_sep ""
|
|
mon_grouping -1
|
|
positive_sign ""
|
|
negative_sign "<U002D>"
|
|
int_frac_digits -1
|
|
frac_digits -1
|
|
p_cs_precedes -1
|
|
p_sep_by_space -1
|
|
n_cs_precedes -1
|
|
n_sep_by_space -1
|
|
p_sign_posn -1
|
|
n_sign_posn -1
|
|
%
|
|
END LC_MONETARY
|
|
|
|
LC_NUMERIC
|
|
% This is the 14652 i18n fdcc-set definition for
|
|
% the LC_NUMERIC category.
|
|
%
|
|
decimal_point "<U002C>"
|
|
thousands_sep ""
|
|
grouping -1
|
|
%
|
|
END LC_NUMERIC
|
|
|
|
LC_TIME
|
|
% This is the ISO/IEC 14652 "i18n" definition for
|
|
% the LC_TIME category.
|
|
%
|
|
% Weekday and week numbering according to ISO 8601
|
|
abday "<U0031>";"<U0032>";"<U0033>";"<U0034>";"<U0035>";"<U0036>";"<U0037>"
|
|
day "<U0031>";"<U0032>";"<U0033>";"<U0034>";"<U0035>";"<U0036>";"<U0037>"
|
|
week 7;19971201;4
|
|
first_weekday 1
|
|
first_workday 1
|
|
abmon "<U0030><U0031>";"<U0030><U0032>";"<U0030><U0033>";"<U0030><U0034>";/
|
|
"<U0030><U0035>";"<U0030><U0036>";"<U0030><U0037>";"<U0030><U0038>";/
|
|
"<U0030><U0039>";"<U0031><U0030>";"<U0031><U0031>";"<U0031><U0032>"
|
|
mon "<U0030><U0031>";"<U0030><U0032>";"<U0030><U0033>";"<U0030><U0034>";/
|
|
"<U0030><U0035>";"<U0030><U0036>";"<U0030><U0037>";"<U0030><U0038>";/
|
|
"<U0030><U0039>";"<U0031><U0030>";"<U0031><U0031>";"<U0031><U0032>"
|
|
am_pm "";""
|
|
% Date formats following ISO 8601
|
|
% Appropriate date and time representation (%c)
|
|
% "%F %T"
|
|
d_t_fmt "<U0025><U0046><U0020><U0025><U0054>"
|
|
%
|
|
% Appropriate date representation (%x) "%F"
|
|
d_fmt "<U0025><U0046>"
|
|
%
|
|
% Appropriate time representation (%X) "%T"
|
|
t_fmt "<U0025><U0054>"
|
|
t_fmt_ampm ""
|
|
%
|
|
% 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 ISO/IEC 14652 "i18n" definition for
|
|
% the LC_MESSAGES category.
|
|
%
|
|
yesexpr "<U005E><U005B><U002B><U0031><U005D>"
|
|
noexpr "<U005E><U005B><U002D><U0030><U005D>"
|
|
END LC_MESSAGES
|
|
|
|
LC_PAPER
|
|
% This is the ISO/IEC 14652 "i18n" definition for
|
|
% the LC_PAPER category.
|
|
%
|
|
height 297
|
|
width 210
|
|
END LC_PAPER
|
|
|
|
LC_NAME
|
|
% This is the ISO/IEC 14652 "i18n" definition for
|
|
% the LC_NAME category.
|
|
%
|
|
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.
|
|
%
|
|
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.
|
|
%
|
|
tel_int_fmt "<U002B><U0025><U0063><U0020><U0025><U0061><U0025><U0074><U0025>/
|
|
<U006C>"
|
|
END LC_TELEPHONE
|
|
|
|
LC_MEASUREMENT
|
|
% This is the ISO/IEC 14652 "i18n" definition for
|
|
% the LC_MEASUREMENT category. It indicates metric.
|
|
measurement 1
|
|
END LC_MEASUREMENT
|