Single-width display option triggered by @cjksingle locale modifier

From 6813ab6d2699ebc2de783b14eb53ee4c84b8ba22 Mon Sep 17 00:00:00 2001
From: Thomas Wolff <[email protected]>
Date: Mon, 17 Feb 2020 00:00:00 +0100
Subject: [PATCH] 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.
---
 newlib/libc/locale/locale.c  | 13 +++++++++++--
 newlib/libc/string/wcwidth.c |  8 ++++++--
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/newlib/libc/locale/locale.c b/newlib/libc/locale/locale.c
index 4c343e462..698119f89 100644
--- a/newlib/libc/locale/locale.c
+++ b/newlib/libc/locale/locale.c
@@ -85,6 +85,9 @@ 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.
 
+This implementation also supports the modifier <<"cjksingle">> 
+to enforce single-width character properties.
+
 If you use <<NULL>> as the <[locale]> argument, <<setlocale>> returns a
 pointer to the string representing the current locale.  The acceptable
 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;
   wctomb_p l_wctomb;
   mbtowc_p l_mbtowc;
+  int cjksingle = 0;
   int cjknarrow = 0;
   int cjkwide = 0;
 
@@ -594,11 +598,13 @@ restart:
     }
   if (c && c[0] == '@')
     {
-      /* Modifier */
+      /* Modifier "cjksingle" is recognized to enforce single-width mode. */
       /* 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"))
+      if (!strcmp (c + 1, "cjksingle"))
+	cjksingle = 1;
+      else if (!strcmp (c + 1, "cjknarrow"))
 	cjknarrow = 1;
       else if (!strcmp (c + 1, "cjkwide"))
 	cjkwide = 1;
@@ -893,6 +899,7 @@ restart:
       loc->wctomb = l_wctomb;
       loc->mbtowc = l_mbtowc;
       __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
          characters. This is used in wcwidth(). Assume single width for
          single-byte charsets, and double width for multi-byte charsets
@@ -907,6 +914,8 @@ restart:
 			   || strncmp (locale, "ja", 2) == 0
 			   || strncmp (locale, "ko", 2) == 0
 			   || strncmp (locale, "zh", 2) == 0));
+      if (cjksingle)
+	loc->cjk_lang = -1;	/* Disable CJK dual-width */
 #ifdef __HAVE_LOCALE_INFO__
       ret = __ctype_load_locale (loc, locale, (void *) l_wctomb, charset,
 				 mbc_max);
diff --git a/newlib/libc/string/wcwidth.c b/newlib/libc/string/wcwidth.c
index 62e76edc3..8348eefe8 100644
--- a/newlib/libc/string/wcwidth.c
+++ b/newlib/libc/string/wcwidth.c
@@ -197,8 +197,11 @@ __wcwidth (const wint_t ucs)
   if (ucs >= 0xd800 && ucs <= 0xdfff)
     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 */
-  if (__locale_cjk_lang ()
+  if (cjk_lang > 0
       && bisearch(ucs, ambiguous,
 		  sizeof(ambiguous) / sizeof(struct interval) - 1))
     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 */
 
   /* 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))
     return 2;
   else
-- 
2.21.0

From c913a33ec9084fe0e76986662f06970efa82cfe6 Mon Sep 17 00:00:00 2001
From: Thomas Wolff <[email protected]>
Date: Mon, 17 Feb 2020 00:00:00 +0100
Subject: [PATCH] describe new locale modifier @cjksingle for user guide

---
 winsup/doc/setup-locale.xml | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/winsup/doc/setup-locale.xml b/winsup/doc/setup-locale.xml
index 4872ae202..7bb85a833 100644
--- a/winsup/doc/setup-locale.xml
+++ b/winsup/doc/setup-locale.xml
@@ -179,6 +179,17 @@ response with this option; it forces wcwidth/wcswidth to return 2 for the
 ambiguous width characters.
 </para></listitem>
 
+<listitem><para>
+As an alternative preference, CJK single-width may be enforced.
+This feature is a 
+<ulink url="https://gitlab.freedesktop.org/terminal-wg/specifications/issues/9#note_406682">proposal</ulink>
+in the Terminals Working Group Specifications.
+The mintty terminal implements it as an option with proper glyph scaling.
+The locale modifier "@cjksingle" supports consistent locale response 
+with this option; it forces wcwidth/wcswidth to account at most 1 for 
+all characters.
+</para></listitem>
+
 </itemizedlist>
 
 </sect2>
-- 
2.21.0