Fix for non-UTF-8 wide charsets (Solaris patch 050-CR7065478)

McDutchie · McDutchie · commit e03c010c4da2 · 2021-01-09T00:45:51.000Z
This upstreams a Solaris patch: https://github.com/oracle/solaris-userland/blob/master/components/ksh93/patches/050-CR7065478.patch src/lib/libast/comp/setlocale.c: - Add wide_wctomb() wrapper for wctomb(3). It changes an invalid character (wctomb returns -1) to a single byte with length 1. - set_ctype(): Use wide_wctomb() instead of wctomb(3) as the conversion discipline function (ast.mb_conv). Effectively this means there are no invalid characters. Perhaps this is necessary for compatibility with ASCII. Sadly, no public info available.
diff --git a/src/lib/libast/comp/setlocale.c b/src/lib/libast/comp/setlocale.c
@@ -2217,6 +2217,23 @@ iswalpha(wchar_t c)
 
 typedef int (*Isw_f)(wchar_t);
 
+static int
+wide_wctomb(char* u, wchar_t w)
+{
+	int size = 0;
+
+	if (u)
+	{
+		size = wctomb(u, w);
+		if (size < 0)
+		{
+			*u = (char)(w & 0xff);
+			size = 1;
+		}
+	}
+	return size;
+}
+
 /*
  * called when LC_CTYPE initialized or changes
  */
@@ -2261,7 +2278,7 @@ set_ctype(Lc_category_t* cp)
 	{
 		if (!(ast.mb_width = wcwidth))
 			ast.mb_width = default_wcwidth;
-		ast.mb_conv = wctomb;
+		ast.mb_conv = wide_wctomb;
 #ifdef mb_state
 		{
 			/*
