Locale modifier @cjkwide to adjust ambiguous-width in non-CJK locales

Locale modifier @cjkwide makes Unicode "ambiguous width" characters
wide.  So ambiguous width characters can be enforced to have width 2
even in non-CJK locales. This gives e.g. users of "Powerline symbols"
the opportunity to adjust their width to the desired behaviour (and the
behaviour apparently expected by some tools) without having to set a CJK
locale and without losing consistence of terminal character width with
wcwidth/wcswidth locale width.

1 files changed, 23 insertions, 16 deletions

diff --git a/newlib/libc/locale/locale.c b/newlib/libc/locale/locale.c
index baa5451a6..557982d6e 100644
--- a/newlib/libc/locale/locale.c
+++ b/newlib/libc/locale/locale.c
@@ -74,15 +74,16 @@ Cygwin additionally supports locales from the file
 (<<"">> is also accepted; if given, the settings are read from the
 corresponding LC_* environment variables and $LANG according to POSIX rules.)
 
-This implementation also supports the modifier <<"cjknarrow">>, which
-affects 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:
+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">> forces a width of 1,
-independent of charset and language.
+and 1 for everything else. Specifying <<"cjknarrow">> or <<"cjkwide">>
+forces a width of 1 or 2, respectively, independent of charset and language.
 
 If you use <<NULL>> as the <[locale]> argument, <<setlocale>> returns a
 pointer to the string representing the current locale.  The acceptable
@@ -480,6 +481,7 @@ __loadlocale (struct __locale_t *loc, int category, const char *new_locale)
   wctomb_p l_wctomb;
   mbtowc_p l_mbtowc;
   int cjknarrow = 0;
+  int cjkwide = 0;
 
   /* Avoid doing everything twice if nothing has changed.
 
@@ -593,11 +595,13 @@ restart:
   if (c && c[0] == '@')
     {
       /* Modifier */
-      /* Only one modifier is recognized right now.  "cjknarrow" is used
-         to modify the behaviour of wcwidth() for East Asian languages.
+      /* Modifiers "cjknarrow" or "cjkwide" are recognized to modify the
+         behaviour of wcwidth() and wcswidth() for East Asian languages.
          For details see the comment at the end of this function. */
       if (!strcmp (c + 1, "cjknarrow"))
 	cjknarrow = 1;
+      else if (!strcmp (c + 1, "cjkwide"))
+	cjkwide = 1;
     }
   /* We only support this subset of charsets. */
   switch (charset[0])
@@ -894,12 +898,15 @@ restart:
          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.
-         Single width can also be forced with the "@cjknarrow" modifier. */
-      loc->cjk_lang = !cjknarrow && mbc_max > 1
-		      && (charset[0] != 'U'
-			  || strncmp (locale, "ja", 2) == 0
-			  || strncmp (locale, "ko", 2) == 0
-			  || strncmp (locale, "zh", 2) == 0);
+         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));
 #ifdef __HAVE_LOCALE_INFO__
       ret = __ctype_load_locale (loc, locale, (void *) l_wctomb, charset,
 				 mbc_max);