libs/newlib-cygwin
libs
/
newlib-cygwin
mirror of git://sourceware.org/git/newlib-cygwin.git
4
0
Fork 0
Code Issues Projects Releases Wiki Activity

Locale modifier "@cjksingle" to enforce single-width CJK width. 

This option follows a proposal in the Terminals Working Group Specifications
(https://gitlab.freedesktop.org/terminal-wg/specifications/issues/9#note_406682).
It makes locale width consistent with the corresponding mintty feature.
This commit is contained in:
Thomas Wolff 2020-02-17 00:00:00 +01:00 committed by Corinna Vinschen
parent 40245925ce
commit c8204b1069
2 changed files with 17 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
newlib/libc/locale/locale.c
View File

@ -85,6 +85,9 @@ it is 2 for <<"zh">> (Chinese), <<"ja">> (Japanese), and <<"ko">> (Korean),
and 1 for everything else. Specifying <<"cjknarrow">> or <<"cjkwide">> and 1 for everything else. Specifying <<"cjknarrow">> or <<"cjkwide">>
forces a width of 1 or 2, respectively, independent of charset and language. forces a width of 1 or 2, respectively, independent of charset and language.
This implementation also supports the modifier <<"cjksingle">>
to enforce single-width character properties.
If you use <<NULL>> as the <[locale]> argument, <<setlocale>> returns a If you use <<NULL>> as the <[locale]> argument, <<setlocale>> returns a
pointer to the string representing the current locale. The acceptable pointer to the string representing the current locale. The acceptable
values for <[category]> are defined in `<<locale.h>>' as macros values for <[category]> are defined in `<<locale.h>>' as macros
@ -480,6 +483,7 @@ __loadlocale (struct __locale_t *loc, int category, char *new_locale)
int mbc_max; int mbc_max;
wctomb_p l_wctomb; wctomb_p l_wctomb;
mbtowc_p l_mbtowc; mbtowc_p l_mbtowc;
int cjksingle = 0;
int cjknarrow = 0; int cjknarrow = 0;
int cjkwide = 0; int cjkwide = 0;
@ -594,11 +598,13 @@ restart:
} }
if (c && c[0] == '@') if (c && c[0] == '@')
{ {
/* Modifier */ /* Modifier "cjksingle" is recognized to enforce single-width mode. */
/* Modifiers "cjknarrow" or "cjkwide" are recognized to modify the /* Modifiers "cjknarrow" or "cjkwide" are recognized to modify the
behaviour of wcwidth() and wcswidth() for East Asian languages. behaviour of wcwidth() and wcswidth() for East Asian languages.
For details see the comment at the end of this function. */ For details see the comment at the end of this function. */
if (!strcmp (c + 1, "cjknarrow")) if (!strcmp (c + 1, "cjksingle"))
cjksingle = 1;
else if (!strcmp (c + 1, "cjknarrow"))
cjknarrow = 1; cjknarrow = 1;
else if (!strcmp (c + 1, "cjkwide")) else if (!strcmp (c + 1, "cjkwide"))
cjkwide = 1; cjkwide = 1;
@ -893,6 +899,7 @@ restart:
loc->wctomb = l_wctomb; loc->wctomb = l_wctomb;
loc->mbtowc = l_mbtowc; loc->mbtowc = l_mbtowc;
__set_ctype (loc, charset); __set_ctype (loc, charset);
/* Set CJK width mode (1: ambiguous-wide, 0: normal, -1: disabled). */
/* Determine the width for the "CJK Ambiguous Width" category of /* Determine the width for the "CJK Ambiguous Width" category of
characters. This is used in wcwidth(). Assume single width for characters. This is used in wcwidth(). Assume single width for
single-byte charsets, and double width for multi-byte charsets single-byte charsets, and double width for multi-byte charsets
@ -907,6 +914,8 @@ restart:
|| strncmp (locale, "ja", 2) == 0 || strncmp (locale, "ja", 2) == 0
|| strncmp (locale, "ko", 2) == 0 || strncmp (locale, "ko", 2) == 0
|| strncmp (locale, "zh", 2) == 0)); || strncmp (locale, "zh", 2) == 0));
if (cjksingle)
loc->cjk_lang = -1; /* Disable CJK dual-width */
#ifdef __HAVE_LOCALE_INFO__ #ifdef __HAVE_LOCALE_INFO__
ret = __ctype_load_locale (loc, locale, (void *) l_wctomb, charset, ret = __ctype_load_locale (loc, locale, (void *) l_wctomb, charset,
mbc_max); mbc_max);

8
newlib/libc/string/wcwidth.c
View File

@ -197,8 +197,11 @@ __wcwidth (const wint_t ucs)
if (ucs >= 0xd800 && ucs <= 0xdfff) if (ucs >= 0xd800 && ucs <= 0xdfff)
return -1; return -1;
/* check CJK width mode (1: ambiguous-wide, 0: normal, -1: disabled) */
int cjk_lang = __locale_cjk_lang ();
/* binary search in table of ambiguous characters */ /* binary search in table of ambiguous characters */
if (__locale_cjk_lang () if (cjk_lang > 0
&& bisearch(ucs, ambiguous, && bisearch(ucs, ambiguous,
sizeof(ambiguous) / sizeof(struct interval) - 1)) sizeof(ambiguous) / sizeof(struct interval) - 1))
return 2; return 2;
@ -211,7 +214,8 @@ __wcwidth (const wint_t ucs)
/* if we arrive here, ucs is not a combining or C0/C1 control character */ /* if we arrive here, ucs is not a combining or C0/C1 control character */
/* binary search in table of wide character codes */ /* binary search in table of wide character codes */
if (bisearch(ucs, wide, if (cjk_lang >= 0
&& bisearch(ucs, wide,
sizeof(wide) / sizeof(struct interval) - 1)) sizeof(wide) / sizeof(struct interval) - 1))
return 2; return 2;
else else