aboutsummaryrefslogtreecommitdiff
path: root/newlib
diff options
context:
space:
mode:
authorThomas Wolff <towo@towo.net>2020-10-07 18:35:54 +0200
committerCorinna Vinschen <corinna@vinschen.de>2020-10-13 13:52:07 +0200
commit1ed2fe0f03f4c8f9cb663c36720e786a229bcabe (patch)
tree69ac9e2332a69d44b5c06750307986826bfc12d3 /newlib
parent2031b48c93512e644d18d7ed71263fe27ca1eac6 (diff)
downloadnewlib-1ed2fe0f03f4c8f9cb663c36720e786a229bcabe.zip
newlib-1ed2fe0f03f4c8f9cb663c36720e786a229bcabe.tar.gz
newlib-1ed2fe0f03f4c8f9cb663c36720e786a229bcabe.tar.bz2
drop ambiguous-wide behaviour from Unicode CJK locales
Diffstat (limited to 'newlib')
-rw-r--r--newlib/libc/locale/locale.c18
1 files changed, 5 insertions, 13 deletions
diff --git a/newlib/libc/locale/locale.c b/newlib/libc/locale/locale.c
index 2c452ba..9686427 100644
--- a/newlib/libc/locale/locale.c
+++ b/newlib/libc/locale/locale.c
@@ -78,12 +78,9 @@ This implementation also supports the modifiers <<"cjknarrow">> and
<<"cjkwide">>, which affect how the functions <<wcwidth>> and <<wcswidth>>
handle characters from the "CJK Ambiguous Width" category of characters
described at http://www.unicode.org/reports/tr11/#Ambiguous.
-These characters have a width of 1 for singlebyte charsets and a width of 2
-for multibyte charsets other than UTF-8.
-For UTF-8, their width depends on the language specifier:
-it is 2 for <<"zh">> (Chinese), <<"ja">> (Japanese), and <<"ko">> (Korean),
-and 1 for everything else. Specifying <<"cjknarrow">> or <<"cjkwide">>
-forces a width of 1 or 2, respectively, independent of charset and language.
+These characters have a width of 1 for singlebyte charsets and UTF-8,
+and a width of 2 for multibyte charsets other than UTF-8. Specifying
+<<"cjknarrow">> or <<"cjkwide">> forces a width of 1 or 2, respectively.
This implementation also supports the modifier <<"cjksingle">>
to enforce single-width character properties.
@@ -903,17 +900,12 @@ restart:
/* Determine the width for the "CJK Ambiguous Width" category of
characters. This is used in wcwidth(). Assume single width for
single-byte charsets, and double width for multi-byte charsets
- other than UTF-8. For UTF-8, use double width for the East Asian
- languages ("ja", "ko", "zh"), and single width for everything else.
+ other than UTF-8. For UTF-8, use single width.
Single width can also be forced with the "@cjknarrow" modifier.
Double width can also be forced with the "@cjkwide" modifier.
*/
loc->cjk_lang = cjkwide ||
- (!cjknarrow && mbc_max > 1
- && (charset[0] != 'U'
- || strncmp (locale, "ja", 2) == 0
- || strncmp (locale, "ko", 2) == 0
- || strncmp (locale, "zh", 2) == 0));
+ (!cjknarrow && mbc_max > 1 && charset[0] != 'U');
if (cjksingle)
loc->cjk_lang = -1; /* Disable CJK dual-width */
#ifdef __HAVE_LOCALE_INFO__