Fix 'expand-file-name' during startup on MS-Windows

* src/w32.c (w32_init_file_name_codepage): New function, resets
file_name_codepage and w32_ansi_code_page to undo the values
recorded during dumping.
(codepage_for_filenames): Fix an embarrassing typo.  Ignore the
cached value of file-name encoding if it is nil, i.e. not
initialized yet.  Actually cache the last used file-name encoding
to avoid calling APIs when not necessary.

* src/w32.h (w32_init_file_name_codepage): Add prototype.

* src/w32term.c (syms_of_w32term): Set the value of
w32_unicode_filenames according to the OS version.  This avoids
resetting it during startup, which then causes temacs to run with
the incorrect value.

* src/emacs.c (main): Call w32_init_file_name_codepage early
during the startup.

* src/fileio.c (Fexpand_file_name) [WINDOWSNT]: Update 'newdir'
after converting $HOME to a UTF-8 string, so that 'newdirlim' is
consistent with it.  (Bug#25038)

* lisp/international/mule-cmds.el (set-locale-environment): Set
'default-file-name-coding-system' to the ANSI codepage even in
non-interactive sessions.

* lisp/files.el (directory-abbrev-alist, abbreviated-home-dir):
Doc fix.
(abbreviate-file-name): Decode 'abbreviated-home-dir' if it is a
unibyte string.

* doc/lispref/files.texi (Directory Names): Index
'directory-abbrev-alist'.

8 files changed, 64 insertions, 23 deletions

diff --git a/doc/lispref/files.texi b/doc/lispref/files.texi
index 544992d4ba5..85c80d76f73 100644
--- a/doc/lispref/files.texi
+++ b/doc/lispref/files.texi
@@ -2151,6 +2151,7 @@ function:
 
 @cindex file name abbreviations
 @cindex abbreviated file names
+@vindex directory-abbrev-alist
 @defun abbreviate-file-name filename
 @anchor{abbreviate-file-name}
 This function returns an abbreviated form of @var{filename}.  It
diff --git a/lisp/files.el b/lisp/files.el
index fa630731b8d..45646b186af 100644
--- a/lisp/files.el
+++ b/lisp/files.el
@@ -51,20 +51,21 @@ when it has unsaved changes."
   nil
   "Alist of abbreviations for file directories.
 A list of elements of the form (FROM . TO), each meaning to replace
-FROM with TO when it appears in a directory name.  This replacement is
-done when setting up the default directory of a newly visited file.
+a match for FROM with TO when a directory name matches FROM.  This
+replacement is done when setting up the default directory of a
+newly visited file buffer.
 
-FROM is matched against directory names anchored at the first
-character, so it should start with a \"\\\\\\=`\", or, if directory
-names cannot have embedded newlines, with a \"^\".
+FROM is a regexp that is matched against directory names anchored at
+the first character, so it should start with a \"\\\\\\=`\", or, if
+directory names cannot have embedded newlines, with a \"^\".
 
 FROM and TO should be equivalent names, which refer to the
-same directory.  Do not use `~' in the TO strings;
-they should be ordinary absolute directory names.
+same directory.  TO should be an absolute directory name.
+Do not use `~' in the TO strings.
 
 Use this feature when you have directories which you normally refer to
 via absolute symbolic links.  Make TO the name of the link, and FROM
-the name it is linked to."
+a regexp matching the name it is linked to."
   :type '(repeat (cons :format "%v"
 		       :value ("\\`" . "")
 		       (regexp :tag "From")
@@ -1736,7 +1737,8 @@ Choose the buffer's name using `generate-new-buffer-name'."
 (make-obsolete-variable 'automount-dir-prefix 'directory-abbrev-alist "24.3")
 
 (defvar abbreviated-home-dir nil
-  "The user's homedir abbreviated according to `directory-abbrev-alist'.")
+  "Regexp matching the user's homedir at the beginning of file name.
+The value includes abbreviation according to `directory-abbrev-alist'.")
 
 (defun abbreviate-file-name (filename)
   "Return a version of FILENAME shortened using `directory-abbrev-alist'.
@@ -1770,8 +1772,23 @@ home directory is a root directory) and removes automounter prefixes
       (or abbreviated-home-dir
 	  (setq abbreviated-home-dir
 		(let ((abbreviated-home-dir "$foo"))
-		  (concat "\\`" (abbreviate-file-name (expand-file-name "~"))
-			  "\\(/\\|\\'\\)"))))
+                  (setq abbreviated-home-dir
+                        (concat "\\`"
+                                (abbreviate-file-name (expand-file-name "~"))
+                                "\\(/\\|\\'\\)"))
+                  ;; Depending on whether default-directory does or
+                  ;; doesn't include non-ASCII characters, the value
+                  ;; of abbreviated-home-dir could be multibyte or
+                  ;; unibyte.  In the latter case, we need to decode
+                  ;; it.  Note that this function is called for the
+                  ;; first time (from startup.el) when
+                  ;; locale-coding-system is already set up.
+                  (if (multibyte-string-p abbreviated-home-dir)
+                      abbreviated-home-dir
+                    (decode-coding-string abbreviated-home-dir
+                                          (if (eq system-type 'windows-nt)
+                                              'utf-8
+                                            locale-coding-system))))))
 
       ;; If FILENAME starts with the abbreviated homedir,
       ;; make it start with `~' instead.
diff --git a/lisp/international/mule-cmds.el b/lisp/international/mule-cmds.el
index 5008fd5f27b..1ec7456c9e1 100644
--- a/lisp/international/mule-cmds.el
+++ b/lisp/international/mule-cmds.el
@@ -2704,10 +2704,12 @@ See also `locale-charset-language-names', `locale-language-names',
     ;; terminal-coding-system with the ANSI or console codepage.
     (when (and (eq system-type 'windows-nt)
                (boundp 'w32-ansi-code-page))
-      (let* ((code-page-coding
-              (intern (format "cp%d" (if noninteractive
-                                         (w32-get-console-codepage)
-                                       w32-ansi-code-page))))
+      (let* ((ansi-code-page-coding
+              (intern (format "cp%d" w32-ansi-code-page)))
+             (code-page-coding
+              (if noninteractive
+                  (intern (format "cp%d" (w32-get-console-codepage)))
+                ansi-code-page-coding))
              (output-coding
               (if noninteractive
                   (intern (format "cp%d" (w32-get-console-output-codepage)))
@@ -2717,7 +2719,7 @@ See also `locale-charset-language-names', `locale-language-names',
 	  (unless frame (setq locale-coding-system code-page-coding))
 	  (set-keyboard-coding-system code-page-coding frame)
 	  (set-terminal-coding-system output-coding frame)
-	  (setq default-file-name-coding-system code-page-coding))))
+	  (setq default-file-name-coding-system ansi-code-page-coding))))
 
     (when (eq system-type 'darwin)
       ;; On Darwin, file names are always encoded in utf-8, no matter
diff --git a/src/emacs.c b/src/emacs.c
index ce30ae741b2..16cf6cc0e4d 100644
--- a/src/emacs.c
+++ b/src/emacs.c
@@ -716,6 +716,9 @@ main (int argc, char **argv)
      to have non-stub implementations of APIs we need to convert file
      names between UTF-8 and the system's ANSI codepage.  */
   maybe_load_unicows_dll ();
+  /* Initialize the codepage for file names, needed to decode
+     non-ASCII file names during startup.  */
+  w32_init_file_name_codepage ();
 #endif
   /* This has to be done before module_init is called below, so that
      the latter could use the thread ID of the main thread.  */
diff --git a/src/fileio.c b/src/fileio.c
index c3b2be7c5f7..d94805f316b 100644
--- a/src/fileio.c
+++ b/src/fileio.c
@@ -1063,8 +1063,6 @@ filesystem tree, not (expand-file-name ".."  dirname).  */)
 	  if (!(newdir = egetenv ("HOME")))
 	    newdir = newdirlim = "";
 	  nm++;
-	  /* `egetenv' may return a unibyte string, which will bite us since
-	     we expect the directory to be multibyte.  */
 #ifdef WINDOWSNT
 	  if (newdir[0])
 	    {
@@ -1072,11 +1070,14 @@ filesystem tree, not (expand-file-name ".."  dirname).  */)
 
 	      filename_from_ansi (newdir, newdir_utf8);
 	      tem = make_unibyte_string (newdir_utf8, strlen (newdir_utf8));
+	      newdir = SSDATA (tem);
 	    }
 	  else
 #endif
 	    tem = build_string (newdir);
 	  newdirlim = newdir + SBYTES (tem);
+	  /* `egetenv' may return a unibyte string, which will bite us
+	     if we expect the directory to be multibyte.  */
 	  if (multibyte && !STRING_MULTIBYTE (tem))
 	    {
 	      hdir = DECODE_FILE (tem);
@@ -1105,8 +1106,7 @@ filesystem tree, not (expand-file-name ".."  dirname).  */)
 
 	      newdir = pw->pw_dir;
 	      /* `getpwnam' may return a unibyte string, which will
-		 bite us since we expect the directory to be
-		 multibyte.  */
+		 bite us when we expect the directory to be multibyte.  */
 	      tem = make_unibyte_string (newdir, strlen (newdir));
 	      newdirlim = newdir + SBYTES (tem);
 	      if (multibyte && !STRING_MULTIBYTE (tem))
diff --git a/src/w32.c b/src/w32.c
index 793bc0f28d0..7c57693cf3d 100644
--- a/src/w32.c
+++ b/src/w32.c
@@ -1493,6 +1493,16 @@ w32_valid_pointer_p (void *p, int size)
 /* Current codepage for encoding file names.  */
 static int file_name_codepage;
 
+/* Initialize the codepage used for decoding file names.  This is
+   needed to undo the value recorded during dumping, which might not
+   be correct when we run the dumped Emacs.  */
+void
+w32_init_file_name_codepage (void)
+{
+  file_name_codepage = CP_ACP;
+  w32_ansi_code_page = CP_ACP;
+}
+
 /* Produce a Windows ANSI codepage suitable for encoding file names.
    Return the information about that codepage in CP_INFO.  */
 int
@@ -1509,12 +1519,13 @@ codepage_for_filenames (CPINFO *cp_info)
   if (NILP (current_encoding))
     current_encoding = Vdefault_file_name_coding_system;
 
-  if (!EQ (last_file_name_encoding, current_encoding))
+  if (!EQ (last_file_name_encoding, current_encoding)
+      || NILP (last_file_name_encoding))
     {
       /* Default to the current ANSI codepage.  */
       file_name_codepage = w32_ansi_code_page;
 
-      if (NILP (current_encoding))
+      if (!NILP (current_encoding))
 	{
 	  char *cpname = SSDATA (SYMBOL_NAME (current_encoding));
 	  char *cp = NULL, *end;
@@ -1543,6 +1554,9 @@ codepage_for_filenames (CPINFO *cp_info)
 	  if (!GetCPInfo (file_name_codepage, &cp))
 	    emacs_abort ();
 	}
+
+      /* Cache the new value.  */
+      last_file_name_encoding = current_encoding;
     }
   if (cp_info)
     *cp_info = cp;
diff --git a/src/w32.h b/src/w32.h
index 42a1c423ce7..08b88f5f5a0 100644
--- a/src/w32.h
+++ b/src/w32.h
@@ -195,6 +195,7 @@ extern int  filename_from_ansi (const char *, char *);
 extern int  filename_to_ansi (const char *, char *);
 extern int  filename_from_utf16 (const wchar_t *, char *);
 extern int  filename_to_utf16 (const char *, wchar_t *);
+extern void w32_init_file_name_codepage (void);
 extern int  codepage_for_filenames (CPINFO *);
 extern Lisp_Object ansi_encode_filename (Lisp_Object);
 extern int  w32_copy_file (const char *, const char *, int, int, int);
diff --git a/src/w32term.c b/src/w32term.c
index 51743f8f94d..7b74ae03ad0 100644
--- a/src/w32term.c
+++ b/src/w32term.c
@@ -7157,7 +7157,10 @@ specified by `file-name-coding-system'.
 This variable is set to non-nil by default when Emacs runs on Windows
 systems of the NT family, including W2K, XP, Vista, Windows 7 and
 Windows 8.  It is set to nil on Windows 9X.  */);
-  w32_unicode_filenames = 0;
+  if (os_subtype == OS_9X)
+    w32_unicode_filenames = 0;
+  else
+    w32_unicode_filenames = 1;
 
 
   /* FIXME: The following variable will be (hopefully) removed