Fix bug #15260 with building and installing Emacs in non-ASCII directories.

 src/xdisp.c (message3_nolog, message_with_string): Encode the string
 before writing it to the terminal in a non-interactive session.
 src/lread.c (openp): If both FILENAME and SUFFIX are unibyte, make
 sure we concatenate them into a unibyte string.
 src/fileio.c (make_temp_name): Encode PREFIX, and decode the
 resulting temporary name before returning it to the caller.
 (Fexpand_file_name): If NAME is pure-ASCII and DEFAULT_DIRECTORY
 is a unibyte string, convert NAME to a unibyte string to ensure
 that the result is also a unibyte string.
 src/emacs.c (init_cmdargs): Use build_unibyte_string to make sure we
 create unibyte strings from default paths and directory/file
 names.
 src/coding.h (ENCODE_FILE): Do not attempt to encode a unibyte
 string.
 src/callproc.c (init_callproc): Use build_unibyte_string to make
 sure we create unibyte strings from default paths and
 directory/file names.
 src/buffer.c (init_buffer): Don't store default-directory of
 *scratch* in multibyte form.  The original problem which led to
 that is described in
 http://lists.gnu.org/archive/html/emacs-pretest-bug/2004-11/msg00532.html,
 but it was solved long ago.

 lisp/startup.el (normal-top-level): Move setting eol-mnemonic-unix,
 eol-mnemonic-mac, eol-mnemonic-dos, and also setup of the locale
 environment and decoding all of the default-directory's to here
 from command-line.
 (command-line): Decode also argv[0].
 lisp/loadup.el: Error out if default-directory is a multibyte string
 when we are dumping.
 lisp/Makefile.in (emacs): Don't set LC_ALL=C.

 leim/Makefile.in (RUN_EMACS): Don't set LC_ALL=C.

 configure.ac: Don't disallow builds in non-ASCII directories.

8 files changed, 107 insertions, 35 deletions

diff --git a/src/ChangeLog b/src/ChangeLog
index 1c56a7c599..f6f4dc3ef8 100644
--- a/src/ChangeLog
+++ b/src/ChangeLog
@@ -1,3 +1,34 @@
+2013-11-04  Eli Zaretskii  <[email protected]>
+
+	* xdisp.c (message3_nolog, message_with_string): Encode the string
+	before writing it to the terminal in a non-interactive session.
+
+	* lread.c (openp): If both FILENAME and SUFFIX are unibyte, make
+	sure we concatenate them into a unibyte string.
+
+	* fileio.c (make_temp_name): Encode PREFIX, and decode the
+	resulting temporary name before returning it to the caller.
+	(Fexpand_file_name): If NAME is pure-ASCII and DEFAULT_DIRECTORY
+	is a unibyte string, convert NAME to a unibyte string to ensure
+	that the result is also a unibyte string.
+
+	* emacs.c (init_cmdargs): Use build_unibyte_string to make sure we
+	create unibyte strings from default paths and directory/file
+	names.
+
+	* coding.h (ENCODE_FILE): Do not attempt to encode a unibyte
+	string.
+
+	* callproc.c (init_callproc): Use build_unibyte_string to make
+	sure we create unibyte strings from default paths and
+	directory/file names.
+
+	* buffer.c (init_buffer): Don't store default-directory of
+	8scratch* in multibyte form.  The original problem which led to
+	that is described in
+	http://lists.gnu.org/archive/html/emacs-pretest-bug/2004-11/msg00532.html,
+	but it was solved long ago.  (Bug#15260)
+
 2013-11-04  Paul Eggert  <[email protected]>
 
 	Port to stricter C99 platforms.
diff --git a/src/buffer.c b/src/buffer.c
index e5a8af93cf..63198cd101 100644
--- a/src/buffer.c
+++ b/src/buffer.c
@@ -5349,13 +5349,10 @@ init_buffer (void)
       len++;
     }
 
+  /* At this moment, we still don't know how to decode the directory
+     name.  So, we keep the bytes in unibyte form so that file I/O
+     routines correctly get the original bytes.  */
   bset_directory (current_buffer, make_unibyte_string (pwd, len));
-  if (! NILP (BVAR (&buffer_defaults, enable_multibyte_characters)))
-    /* At this moment, we still don't know how to decode the
-       directory name.  So, we keep the bytes in multibyte form so
-       that ENCODE_FILE correctly gets the original bytes.  */
-    bset_directory
-      (current_buffer, string_to_multibyte (BVAR (current_buffer, directory)));
 
   /* Add /: to the front of the name
      if it would otherwise be treated as magic.  */
diff --git a/src/callproc.c b/src/callproc.c
index d4b4a26ec3..2740779f51 100644
--- a/src/callproc.c
+++ b/src/callproc.c
@@ -1612,14 +1612,14 @@ init_callproc (void)
       Lisp_Object tem, tem1, srcdir;
 
       srcdir = Fexpand_file_name (build_string ("../src/"),
-				  build_string (PATH_DUMPLOADSEARCH));
+				  build_unibyte_string (PATH_DUMPLOADSEARCH));
       tem = Fexpand_file_name (build_string ("GNU"), Vdata_directory);
       tem1 = Ffile_exists_p (tem);
       if (!NILP (Fequal (srcdir, Vinvocation_directory)) || NILP (tem1))
 	{
 	  Lisp_Object newdir;
 	  newdir = Fexpand_file_name (build_string ("../etc/"),
-				      build_string (PATH_DUMPLOADSEARCH));
+				      build_unibyte_string (PATH_DUMPLOADSEARCH));
 	  tem = Fexpand_file_name (build_string ("GNU"), newdir);
 	  tem1 = Ffile_exists_p (tem);
 	  if (!NILP (tem1))
@@ -1646,7 +1646,7 @@ init_callproc (void)
 #ifdef DOS_NT
   Vshared_game_score_directory = Qnil;
 #else
-  Vshared_game_score_directory = build_string (PATH_GAME);
+  Vshared_game_score_directory = build_unibyte_string (PATH_GAME);
   if (NILP (Ffile_accessible_directory_p (Vshared_game_score_directory)))
     Vshared_game_score_directory = Qnil;
 #endif
diff --git a/src/coding.h b/src/coding.h
index 0472bec99d..5a921e4495 100644
--- a/src/coding.h
+++ b/src/coding.h
@@ -670,14 +670,16 @@ struct coding_system
     (code) = (s1 << 8) | s2;				\
   } while (0)
 
-/* Encode the file name NAME using the specified coding system
-   for file names, if any.  */
-#define ENCODE_FILE(name)						   \
-  (! NILP (Vfile_name_coding_system)					   \
-   ? code_convert_string_norecord (name, Vfile_name_coding_system, 1)	   \
-   : (! NILP (Vdefault_file_name_coding_system)				   \
-      ? code_convert_string_norecord (name, Vdefault_file_name_coding_system, 1) \
-      : name))
+/* Encode the file name NAME using the specified coding system for
+   file names, if any.  If NAME is a unibyte string, return NAME.  */
+#define ENCODE_FILE(name)						\
+    (! STRING_MULTIBYTE (name)						\
+     ? name								\
+     : (! NILP (Vfile_name_coding_system)				\
+	? code_convert_string_norecord (name, Vfile_name_coding_system, 1) \
+	: (! NILP (Vdefault_file_name_coding_system)			\
+	   ? code_convert_string_norecord (name, Vdefault_file_name_coding_system, 1) \
+	   : name)))
 
 
 /* Decode the file name NAME using the specified coding system
diff --git a/src/emacs.c b/src/emacs.c
index 928babb417..52d2e76dc8 100644
--- a/src/emacs.c
+++ b/src/emacs.c
@@ -393,7 +393,7 @@ init_cmdargs (int argc, char **argv, int skip_args, char *original_pwd)
   initial_argv = argv;
   initial_argc = argc;
 
-  raw_name = build_string (argv[0]);
+  raw_name = build_unibyte_string (argv[0]);
 
   /* Add /: to the front of the name
      if it would otherwise be treated as magic.  */
@@ -427,7 +427,9 @@ init_cmdargs (int argc, char **argv, int skip_args, char *original_pwd)
     /* Emacs was started with relative path, like ./emacs.
        Make it absolute.  */
     {
-      Lisp_Object odir = original_pwd ? build_string (original_pwd) : Qnil;
+      Lisp_Object odir =
+	original_pwd ? build_unibyte_string (original_pwd) : Qnil;
+
       Vinvocation_directory = Fexpand_file_name (Vinvocation_directory, odir);
     }
 
@@ -2206,7 +2208,7 @@ decode_env_path (const char *evarname, const char *defalt)
       p = strchr (path, SEPCHAR);
       if (!p)
 	p = path + strlen (path);
-      element = (p - path ? make_string (path, p - path)
+      element = (p - path ? make_unibyte_string (path, p - path)
 		 : build_string ("."));
 #ifdef WINDOWSNT
       /* Relative file names in the default path are interpreted as
@@ -2216,7 +2218,7 @@ decode_env_path (const char *evarname, const char *defalt)
 	element = Fexpand_file_name (Fsubstring (element,
 						 make_number (emacs_dir_len),
 						 Qnil),
-				     build_string (emacs_dir));
+				     build_unibyte_string (emacs_dir));
 #endif
 
       /* Add /: to the front of the name
diff --git a/src/fileio.c b/src/fileio.c
index a1dcb72b4e..884af25f9f 100644
--- a/src/fileio.c
+++ b/src/fileio.c
@@ -732,8 +732,8 @@ static unsigned make_temp_name_count, make_temp_name_count_initialized_p;
 Lisp_Object
 make_temp_name (Lisp_Object prefix, bool base64_p)
 {
-  Lisp_Object val;
-  int len, clen;
+  Lisp_Object val, encoded_prefix;
+  int len;
   printmax_t pid;
   char *p, *data;
   char pidbuf[INT_BUFSIZE_BOUND (printmax_t)];
@@ -767,12 +767,11 @@ make_temp_name (Lisp_Object prefix, bool base64_p)
 #endif
     }
 
-  len = SBYTES (prefix); clen = SCHARS (prefix);
-  val = make_uninit_multibyte_string (clen + 3 + pidlen, len + 3 + pidlen);
-  if (!STRING_MULTIBYTE (prefix))
-    STRING_SET_UNIBYTE (val);
+  encoded_prefix = ENCODE_FILE (prefix);
+  len = SBYTES (encoded_prefix);
+  val = make_uninit_string (len + 3 + pidlen);
   data = SSDATA (val);
-  memcpy (data, SSDATA (prefix), len);
+  memcpy (data, SSDATA (encoded_prefix), len);
   p = data + len;
 
   memcpy (p, pidbuf, pidlen);
@@ -810,7 +809,7 @@ make_temp_name (Lisp_Object prefix, bool base64_p)
 	{
 	  /* We want to return only if errno is ENOENT.  */
 	  if (errno == ENOENT)
-	    return val;
+	    return DECODE_FILE (val);
 	  else
 	    /* The error here is dubious, but there is little else we
 	       can do.  The alternatives are to return nil, which is
@@ -987,7 +986,26 @@ filesystem tree, not (expand-file-name ".."  dirname).  */)
   if (multibyte != STRING_MULTIBYTE (default_directory))
     {
       if (multibyte)
-	default_directory = string_to_multibyte (default_directory);
+	{
+	  unsigned char *p = SDATA (name);
+
+	  while (*p && ASCII_BYTE_P (*p))
+	    p++;
+	  if (*p == '\0')
+	    {
+	      /* NAME is a pure ASCII string, and DEFAULT_DIRECTORY is
+		 unibyte.  Do not convert DEFAULT_DIRECTORY to
+		 multibyte; instead, convert NAME to a unibyte string,
+		 so that the result of this function is also a unibyte
+		 string.  This is needed during bootstraping and
+		 dumping, when Emacs cannot decode file names, because
+		 the locale environment is not set up.  */
+	      name = make_unibyte_string (SSDATA (name), SBYTES (name));
+	      multibyte = 0;
+	    }
+	  else
+	    default_directory = string_to_multibyte (default_directory);
+	}
       else
 	{
 	  name = string_to_multibyte (name);
diff --git a/src/lread.c b/src/lread.c
index b42ac5908e..618b0cadb5 100644
--- a/src/lread.c
+++ b/src/lread.c
@@ -1500,7 +1500,8 @@ openp (Lisp_Object path, Lisp_Object str, Lisp_Object suffixes,
       for (tail = NILP (suffixes) ? list1 (empty_unibyte_string) : suffixes;
 	   CONSP (tail); tail = XCDR (tail))
 	{
-	  ptrdiff_t fnlen, lsuffix = SBYTES (XCAR (tail));
+	  Lisp_Object suffix = XCAR (tail);
+	  ptrdiff_t fnlen, lsuffix = SBYTES (suffix);
 	  Lisp_Object handler;
 
 	  /* Concatenate path element/specified name with the suffix.
@@ -1511,7 +1512,7 @@ openp (Lisp_Object path, Lisp_Object str, Lisp_Object suffixes,
 			   ? 2 : 0);
 	  fnlen = SBYTES (filename) - prefixlen;
 	  memcpy (fn, SDATA (filename) + prefixlen, fnlen);
-	  memcpy (fn + fnlen, SDATA (XCAR (tail)), lsuffix + 1);
+	  memcpy (fn + fnlen, SDATA (suffix), lsuffix + 1);
 	  fnlen += lsuffix;
 	  /* Check that the file exists and is not a directory.  */
 	  /* We used to only check for handlers on non-absolute file names:
@@ -1521,7 +1522,18 @@ openp (Lisp_Object path, Lisp_Object str, Lisp_Object suffixes,
 		  handler = Ffind_file_name_handler (filename, Qfile_exists_p);
 	     It's not clear why that was the case and it breaks things like
 	     (load "/bar.el") where the file is actually "/bar.el.gz".  */
-	  string = make_string (fn, fnlen);
+	  /* make_string has its own ideas on when to return a unibyte
+	     string and when a multibyte string, but we know better.
+	     We must have a unibyte string when dumping, since
+	     file-name encoding is shaky at best at that time, and in
+	     particular default-file-name-coding-system is reset
+	     several times during loadup.  We therefore don't want to
+	     encode the file before passing it to file I/O library
+	     functions.  */
+	  if (!STRING_MULTIBYTE (filename) && !STRING_MULTIBYTE (suffix))
+	    string = make_unibyte_string (fn, fnlen);
+	  else
+	    string = make_string (fn, fnlen);
 	  handler = Ffind_file_name_handler (string, Qfile_exists_p);
 	  if ((!NILP (handler) || !NILP (predicate)) && !NATNUMP (predicate))
             {
diff --git a/src/xdisp.c b/src/xdisp.c
index 9992fa4776..382f9e7a8e 100644
--- a/src/xdisp.c
+++ b/src/xdisp.c
@@ -9728,7 +9728,11 @@ message3_nolog (Lisp_Object m)
 	putc ('\n', stderr);
       noninteractive_need_newline = 0;
       if (STRINGP (m))
-	fwrite (SDATA (m), SBYTES (m), 1, stderr);
+	{
+	  Lisp_Object s = ENCODE_SYSTEM (m);
+
+	  fwrite (SDATA (s), SBYTES (s), 1, stderr);
+	}
       if (cursor_in_echo_area == 0)
 	fprintf (stderr, "\n");
       fflush (stderr);
@@ -9803,13 +9807,19 @@ message_with_string (const char *m, Lisp_Object string, int log)
     {
       if (m)
 	{
+	  /* ENCODE_SYSTEM below can GC and/or relocate the Lisp
+	     String whose data pointer might be passed to us in M.  So
+	     we use a local copy.  */
+	  char *fmt = xstrdup (m);
+
 	  if (noninteractive_need_newline)
 	    putc ('\n', stderr);
 	  noninteractive_need_newline = 0;
-	  fprintf (stderr, m, SDATA (string));
+	  fprintf (stderr, fmt, SDATA (ENCODE_SYSTEM (string)));
 	  if (!cursor_in_echo_area)
 	    fprintf (stderr, "\n");
 	  fflush (stderr);
+	  xfree (fmt);
 	}
     }
   else if (INTERACTIVE)