Do not treat the command line or environment like paths

	* dcrt0.cc (dll_crt0_1), environ.cc (environ_init, getwinenveq,
	build_env), strfuncs.cc (sys_wcstombs, sys_wcstombs_alloc),
	wchar.c (sys_wcstombs, sys_wcstombs_alloc): avoid mis-conversions
	of text that does not, actually, refer to a path or file name

Detailed explanation:

Our WCS -> UTF conversion handles the private Unicode page specially
to allow for otherwise invalid file names. However, this handling makes
no sense for command-lines, nor environment variables, which we would
rather convert verbatim.

As a stop-gap solution, let's just introduce a version of the
sys_wcstombs() function that specifically excludes that file name
conversion magic.

The proper solution is to change sys_wcstombs() to assume that it is not
a path that wants to be converted, and introduce sys_wcstombs_path()
that does, but that is a bigger task which we leave for another patch.

Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>

1 files changed, 34 insertions, 7 deletions

diff --git a/winsup/cygwin/strfuncs.cc b/winsup/cygwin/strfuncs.cc
index e73cd63bc..ad6773823 100644
--- a/winsup/cygwin/strfuncs.cc
+++ b/winsup/cygwin/strfuncs.cc
@@ -409,8 +409,9 @@ __big5_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
        to buffer size, it's a bug in Cygwin and the buffer in the calling
        function should be raised.
 */
-size_t __reg3
-sys_wcstombs (char *dst, size_t len, const wchar_t *src, size_t nwc)
+static size_t __reg3
+sys_wcstombs (char *dst, size_t len, const wchar_t *src, size_t nwc,
+		bool is_path)
 {
   char buf[10];
   char *ptr = dst;
@@ -434,7 +435,7 @@ sys_wcstombs (char *dst, size_t len, const wchar_t *src, size_t nwc)
 	 ASCII area <= 0x7f (only for path names) is transform_chars above.
 	 Reverse functionality for invalid bytes in a multibyte sequence is
 	 in sys_cp_mbstowcs below. */
-      if ((pw & 0xff00) == 0xf000
+      if (is_path && (pw & 0xff00) == 0xf000
 	  && (((cwc = (pw & 0xff)) <= 0x7f && tfx_rev_chars[cwc] >= 0xf000)
 	      || (cwc >= 0x80 && MB_CUR_MAX > 1)))
 	{
@@ -496,6 +497,18 @@ sys_wcstombs (char *dst, size_t len, const wchar_t *src, size_t nwc)
   return n;
 }
 
+size_t __reg3
+sys_wcstombs (char *dst, size_t len, const wchar_t * src, size_t nwc)
+{
+  return sys_wcstombs (dst, len, src, nwc, true);
+}
+
+size_t __reg3
+sys_wcstombs_no_path (char *dst, size_t len, const wchar_t * src, size_t nwc)
+{
+  return sys_wcstombs (dst, len, src, nwc, false);
+}
+
 /* Allocate a buffer big enough for the string, always including the
    terminating '\0'.  The buffer pointer is returned in *dst_p, the return
    value is the number of bytes written to the buffer, as usual.
@@ -506,12 +519,13 @@ sys_wcstombs (char *dst, size_t len, const wchar_t *src, size_t nwc)
    Note that this code is shared by cygserver (which requires it via
    __small_vsprintf) and so when built there plain calloc is the
    only choice.  */
-size_t __reg3
-sys_wcstombs_alloc (char **dst_p, int type, const wchar_t *src, size_t nwc)
+static size_t __reg3
+sys_wcstombs_alloc (char **dst_p, int type, const wchar_t *src, size_t nwc,
+		bool is_path)
 {
   size_t ret;
 
-  ret = sys_wcstombs (NULL, (size_t) -1, src, nwc);
+  ret = sys_wcstombs (NULL, (size_t) -1, src, nwc, is_path);
   if (ret > 0)
     {
       size_t dlen = ret + 1;
@@ -522,11 +536,24 @@ sys_wcstombs_alloc (char **dst_p, int type, const wchar_t *src, size_t nwc)
 	*dst_p = (char *) ccalloc ((cygheap_types) type, dlen, sizeof (char));
       if (!*dst_p)
 	return 0;
-      ret = sys_wcstombs (*dst_p, dlen, src, nwc);
+      ret = sys_wcstombs (*dst_p, dlen, src, nwc, is_path);
     }
   return ret;
 }
 
+size_t __reg3
+sys_wcstombs_alloc (char **dst_p, int type, const wchar_t *src, size_t nwc)
+{
+  return sys_wcstombs_alloc (dst_p, type, src, nwc, true);
+}
+
+size_t __reg3
+sys_wcstombs_alloc_no_path (char **dst_p, int type, const wchar_t *src,
+		size_t nwc)
+{
+  return sys_wcstombs_alloc (dst_p, type, src, nwc, false);
+}
+
 /* sys_cp_mbstowcs is actually most of the time called as sys_mbstowcs with
    a 0 codepage.  If cp is not 0, the codepage is evaluated and used for the
    conversion.  This is so that fhandler_console can switch to an alternate