AuroraMiddleware/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2024-11-24 14:00:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

Set width of JUNGSEONG/JONGSEONG characters from UD7B0 to UD7FB to 0 [BZ #26120]

Browse Source 
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
This commit is contained in:
Mike FABIAN 2020-06-16 08:29:40 +02:00
parent 1d21fb1061
commit 6e540caa21
10 changed files with 18 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
localedata/charmaps/UTF-8
View File

@ -48920,6 +48920,8 @@ WIDTH
<UABE8> 0
<UABED> 0
<UAC00>...<UD7A3> 2
<UD7B0>...<UD7C6> 0
<UD7CB>...<UD7FB> 0
<UF900>...<UFA6D> 2
<UFA70>...<UFAD9> 2
<UFB1E> 0

2
localedata/locales/i18n_ctype
View File

@ -26,7 +26,7 @@ fax ""
language ""
territory "Earth"
revision "13.0.0"
date "2020-04-14"
date "2020-06-25"
category "i18n:2012";LC_CTYPE
END LC_IDENTIFICATION

2
localedata/locales/tr_TR
View File

@ -43,7 +43,7 @@ fax ""
language "Turkish"
territory "Turkey"
revision "1.0"
date "2020-04-14"
date "2020-06-25"
category "i18n:2012";LC_IDENTIFICATION
category "i18n:2012";LC_CTYPE

2
localedata/locales/translit_circle
View File

@ -9,7 +9,7 @@ comment_char %
% otherwise be governed by that license.
% Transliterations of encircled characters.
% Generated automatically from UnicodeData.txt by gen_translit_circle.py on 2020-04-14 for Unicode 13.0.0.
% Generated automatically from UnicodeData.txt by gen_translit_circle.py on 2020-06-25 for Unicode 13.0.0.
LC_CTYPE

2
localedata/locales/translit_cjk_compat
View File

@ -9,7 +9,7 @@ comment_char %
% otherwise be governed by that license.
% Transliterations of CJK compatibility characters.
% Generated automatically from UnicodeData.txt by gen_translit_cjk_compat.py on 2020-04-14 for Unicode 13.0.0.
% Generated automatically from UnicodeData.txt by gen_translit_cjk_compat.py on 2020-06-25 for Unicode 13.0.0.
LC_CTYPE

2
localedata/locales/translit_combining
View File

@ -10,7 +10,7 @@ comment_char %
% Transliterations that remove all combining characters (accents,
% pronounciation marks, etc.).
% Generated automatically from UnicodeData.txt by gen_translit_combining.py on 2020-04-14 for Unicode 13.0.0.
% Generated automatically from UnicodeData.txt by gen_translit_combining.py on 2020-06-25 for Unicode 13.0.0.
LC_CTYPE

2
localedata/locales/translit_compat
View File

@ -9,7 +9,7 @@ comment_char %
% otherwise be governed by that license.
% Transliterations of compatibility characters and ligatures.
% Generated automatically from UnicodeData.txt by gen_translit_compat.py on 2020-04-14 for Unicode 13.0.0.
% Generated automatically from UnicodeData.txt by gen_translit_compat.py on 2020-06-25 for Unicode 13.0.0.
LC_CTYPE

2
localedata/locales/translit_font
View File

@ -9,7 +9,7 @@ comment_char %
% otherwise be governed by that license.
% Transliterations of font equivalents.
% Generated automatically from UnicodeData.txt by gen_translit_font.py on 2020-04-14 for Unicode 13.0.0.
% Generated automatically from UnicodeData.txt by gen_translit_font.py on 2020-06-25 for Unicode 13.0.0.
LC_CTYPE

2
localedata/locales/translit_fraction
View File

@ -9,7 +9,7 @@ comment_char %
% otherwise be governed by that license.
% Transliterations of fractions.
% Generated automatically from UnicodeData.txt by gen_translit_fraction.py on 2020-04-14 for Unicode 13.0.0.
% Generated automatically from UnicodeData.txt by gen_translit_fraction.py on 2020-06-25 for Unicode 13.0.0.
% The replacements have been surrounded with spaces, because fractions are
% often preceded by a decimal number and followed by a unit or a math symbol.

9
localedata/unicode-gen/utf8_gen.py
View File

@ -258,7 +258,13 @@ def process_width(outfile, ulines, elines, plines):
if key in width_dict:
del width_dict[key] # default width is 1
for key in list(range(0x1160, 0x1200)):
width_dict[key] = 0
# Hangul jungseong and jongseong:
if key in unicode_utils.UNICODE_ATTRIBUTES:
width_dict[key] = 0
for key in list(range(0xD7B0, 0xD800)):
# Hangul jungseong and jongseong:
if key in unicode_utils.UNICODE_ATTRIBUTES:
width_dict[key] = 0
for key in list(range(0x3248, 0x3250)):
# These are “A” which means we can decide whether to treat them
# as “W” or “N” based on context:
@ -327,6 +333,7 @@ if __name__ == "__main__":
help='The Unicode version of the input files used.')
ARGS = PARSER.parse_args()
unicode_utils.fill_attributes(ARGS.unicode_data_file)
with open(ARGS.unicode_data_file, mode='r') as UNIDATA_FILE:
UNICODE_DATA_LINES = UNIDATA_FILE.readlines()
with open(ARGS.east_asian_with_file, mode='r') as EAST_ASIAN_WIDTH_FILE: