diff options
| -rw-r--r-- | ChangeLog | 5 | ||||
| -rw-r--r-- | configure.ac | 24 | ||||
| -rw-r--r-- | leim/ChangeLog | 4 | ||||
| -rw-r--r-- | leim/Makefile.in | 2 | ||||
| -rw-r--r-- | lisp/ChangeLog | 13 | ||||
| -rw-r--r-- | lisp/Makefile.in | 2 | ||||
| -rw-r--r-- | lisp/loadup.el | 14 | ||||
| -rw-r--r-- | lisp/startup.el | 94 | ||||
| -rw-r--r-- | src/ChangeLog | 31 | ||||
| -rw-r--r-- | src/buffer.c | 9 | ||||
| -rw-r--r-- | src/callproc.c | 6 | ||||
| -rw-r--r-- | src/coding.h | 18 | ||||
| -rw-r--r-- | src/emacs.c | 10 | ||||
| -rw-r--r-- | src/fileio.c | 36 | ||||
| -rw-r--r-- | src/lread.c | 18 | ||||
| -rw-r--r-- | src/xdisp.c | 14 |
16 files changed, 213 insertions, 87 deletions
diff --git a/ChangeLog b/ChangeLog index 85b30977cad..547f5ce1afc 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,8 @@ +2013-11-04 Eli Zaretskii <eliz@gnu.org> + + * configure.ac: Don't disallow builds in non-ASCII directories. + (Bug#15260) + 2013-11-04 Paul Eggert <eggert@cs.ucla.edu> Port to stricter C99 platforms. diff --git a/configure.ac b/configure.ac index 64efdd8bbd6..2540f185078 100644 --- a/configure.ac +++ b/configure.ac @@ -73,30 +73,6 @@ dnl Support for --program-prefix, --program-suffix and dnl --program-transform-name options AC_ARG_PROGRAM -dnl http://debbugs.gnu.org/15260 -dnl I think we have to check, eg, both exec_prefix and bindir, -dnl because the latter by default is not yet expanded, but the user -dnl may have specified a value for it via --bindir. -dnl At first glance, _installing_ in non-ASCII seems ok, but in fact -dnl it is not; see http://debbugs.gnu.org/15260#61 -dnl Note that abs_srcdir and abs_builddir are not yet defined. :( - -dnl "`cd \"$srcdir\"`" is not portable. -dnl See autoconf manual "Shell Substitutions": -dnl "There is just no portable way to use double-quoted strings inside -dnl double-quoted back-quoted expressions (pfew!)." -temp_srcdir=`cd "$srcdir"; pwd` - -for var in "`pwd`" "$temp_srcdir" "$prefix" "$exec_prefix" \ - "$datarootdir" "$bindir" "$datadir" "$sharedstatedir" "$libexecdir"; do - - dnl configure sets LC_ALL=C early on, so this range should work. - case "$var" in - *[[!\ -~]]*) AC_MSG_ERROR([Emacs cannot be built or installed in a directory whose name contains non-ASCII characters: $var]) ;; - esac - -done - dnl It is important that variables on the RHS not be expanded here, dnl hence the single quotes. This is per the GNU coding standards, see dnl (autoconf) Installation Directory Variables diff --git a/leim/ChangeLog b/leim/ChangeLog index 9883995c68b..6b16d71c215 100644 --- a/leim/ChangeLog +++ b/leim/ChangeLog @@ -1,3 +1,7 @@ +2013-11-04 Eli Zaretskii <eliz@gnu.org> + + * Makefile.in (RUN_EMACS): Don't set LC_ALL=C. (Bug#15260) + 2013-11-03 Glenn Morris <rgm@gnu.org> * Makefile.in (abs_srcdir): Remove. diff --git a/leim/Makefile.in b/leim/Makefile.in index c1a79a75d04..a5c05d567ec 100644 --- a/leim/Makefile.in +++ b/leim/Makefile.in @@ -32,7 +32,7 @@ EMACS = ../src/emacs # How to run Emacs. # Prevent any setting of EMACSLOADPATH in user environment causing problems. -RUN_EMACS = unset EMACSLOADPATH; LC_ALL=C "${EMACS}" -batch \ +RUN_EMACS = unset EMACSLOADPATH; "${EMACS}" -batch \ --no-site-file --no-site-lisp MKDIR_P = @MKDIR_P@ diff --git a/lisp/ChangeLog b/lisp/ChangeLog index 4ef439a43c1..965a62668ed 100644 --- a/lisp/ChangeLog +++ b/lisp/ChangeLog @@ -1,3 +1,16 @@ +2013-11-04 Eli Zaretskii <eliz@gnu.org> + + * startup.el (normal-top-level): Move setting eol-mnemonic-unix, + eol-mnemonic-mac, eol-mnemonic-dos, and also setup of the locale + environment and decoding all of the default-directory's to here + from command-line. + (command-line): Decode also argv[0]. + + * loadup.el: Error out if default-directory is a multibyte string + when we are dumping. + + * Makefile.in (emacs): Don't set LC_ALL=C. (Bug#15260) + 2013-11-04 Teodor Zlatanov <tzz@lifelogs.com> * emacs-lisp/package.el (package-menu-mode) diff --git a/lisp/Makefile.in b/lisp/Makefile.in index 7b0206a623d..9733495403c 100644 --- a/lisp/Makefile.in +++ b/lisp/Makefile.in @@ -106,7 +106,7 @@ COMPILE_FIRST = \ # The actual Emacs command run in the targets below. # Prevent any setting of EMACSLOADPATH in user environment causing problems. -emacs = unset EMACSLOADPATH; LC_ALL=C "$(EMACS)" $(EMACSOPT) +emacs = unset EMACSLOADPATH; "$(EMACS)" $(EMACSOPT) # Common command to find subdirectories setwins=subdirs=`find . -type d -print`; \ diff --git a/lisp/loadup.el b/lisp/loadup.el index 27148ceea75..98e3b877144 100644 --- a/lisp/loadup.el +++ b/lisp/loadup.el @@ -286,6 +286,20 @@ ;For other systems, you must edit ../src/Makefile.in. (load "site-load" t) +;; Make sure default-directory is unibyte when dumping. This is +;; because we cannot decode and encode it correctly (since the locale +;; environment is not, and should not be, set up). default-directory +;; is used every time we call expand-file-name, which we do in every +;; file primitive. So the only workable solution to support building +;; in non-ASCII directories is to manipulate unibyte strings in the +;; current locale's encoding. +(if (and (or (equal (nth 3 command-line-args) "dump") + (equal (nth 4 command-line-args) "dump") + (equal (nth 3 command-line-args) "bootstrap") + (equal (nth 4 command-line-args) "bootstrap")) + (multibyte-string-p default-directory)) + (error "default-directory must be unibyte when dumping Emacs!")) + ;; Determine which last version number to use ;; based on the executables that now exist. (if (and (or (equal (nth 3 command-line-args) "dump") diff --git a/lisp/startup.el b/lisp/startup.el index e93c3fa5826..963ee687a3b 100644 --- a/lisp/startup.el +++ b/lisp/startup.el @@ -489,6 +489,63 @@ It is the default value of the variable `top-level'." (if command-line-processed (message "Back to top level.") (setq command-line-processed t) + + ;; Set the default strings to display in mode line for end-of-line + ;; formats that aren't native to this platform. This should be + ;; done before calling set-locale-environment, as the latter might + ;; use these mnemonics. + (cond + ((memq system-type '(ms-dos windows-nt)) + (setq eol-mnemonic-unix "(Unix)" + eol-mnemonic-mac "(Mac)")) + (t ; this is for Unix/GNU/Linux systems + (setq eol-mnemonic-dos "(DOS)" + eol-mnemonic-mac "(Mac)"))) + + (set-locale-environment nil) + ;; Decode all default-directory's (probably, only *scratch* exists + ;; at this point). default-directory of *scratch* is the basis + ;; for many other file-name variables and directory lists, so it + ;; is important to decode it ASAP. + (when locale-coding-system + (save-excursion + (dolist (elt (buffer-list)) + (set-buffer elt) + (if default-directory + (setq default-directory + (decode-coding-string default-directory + locale-coding-system t))))) + + ;; Decode all the important variables and directory lists, now + ;; that we know the locale's encoding. This is because the + ;; values of these variables are until here unibyte undecoded + ;; strings created by build_unibyte_string. data-directory in + ;; particular is used to construct many other standard directory + ;; names, so it must be decoded ASAP. + ;; Note that charset-map-path cannot be decoded here, since we + ;; could then be trapped in infinite recursion below, when we + ;; load subdirs.el, because encoding a directory name might need + ;; to load a charset map, which will want to encode + ;; charset-map-path, which will want to load the same charset + ;; map... So decoding of charset-map-path is delayed until + ;; further down below. + (dolist (pathsym '(load-path exec-path)) + (let ((path (symbol-value pathsym))) + (if (listp path) + (set pathsym (mapcar (lambda (dir) + (decode-coding-string + dir + locale-coding-system t)) + path))))) + (dolist (filesym '(data-directory doc-directory exec-directory + installation-directory + invocation-directory invocation-name + source-directory + shared-game-score-directory)) + (let ((file (symbol-value filesym))) + (if (stringp file) + (set filesym (decode-coding-string file locale-coding-system t)))))) + (let ((dir default-directory)) (with-current-buffer "*Messages*" (messages-buffer-mode) @@ -536,6 +593,16 @@ It is the default value of the variable `top-level'." (setq process-environment (delete (concat "PWD=" pwd) process-environment))))) + ;; Now, that other directories were searched, and any charsets we + ;; need for encoding them are already loaded, we are ready to + ;; decode charset-map-path. + (if (listp charset-map-path) + (setq charset-map-path + (mapcar (lambda (dir) + (decode-coding-string + dir + locale-coding-system t)) + charset-map-path))) (setq default-directory (abbreviate-file-name default-directory)) (let ((old-face-font-rescale-alist face-font-rescale-alist)) (unwind-protect @@ -756,18 +823,6 @@ Amongst another things, it parses the command-line arguments." ;;! ;; Choose a good default value for split-window-keep-point. ;;! (setq split-window-keep-point (> baud-rate 2400)) - ;; Set the default strings to display in mode line for - ;; end-of-line formats that aren't native to this platform. - (cond - ((memq system-type '(ms-dos windows-nt)) - (setq eol-mnemonic-unix "(Unix)" - eol-mnemonic-mac "(Mac)")) - (t ; this is for Unix/GNU/Linux systems - (setq eol-mnemonic-dos "(DOS)" - eol-mnemonic-mac "(Mac)"))) - - (set-locale-environment nil) - ;; Convert preloaded file names in load-history to absolute. (let ((simple-file-name ;; Look for simple.el or simple.elc and use their directory @@ -801,7 +856,7 @@ please check its value") load-history)))) ;; Convert the arguments to Emacs internal representation. - (let ((args (cdr command-line-args))) + (let ((args command-line-args)) (while args (setcar args (decode-coding-string (car args) locale-coding-system t)) @@ -1211,19 +1266,6 @@ the `--debug-init' option to view a complete error backtrace." (setq after-init-time (current-time)) (run-hooks 'after-init-hook) - ;; Decode all default-directory. - (if (and (default-value 'enable-multibyte-characters) locale-coding-system) - (save-excursion - (dolist (elt (buffer-list)) - (set-buffer elt) - (if default-directory - (setq default-directory - (decode-coding-string default-directory - locale-coding-system t)))) - (setq command-line-default-directory - (decode-coding-string command-line-default-directory - locale-coding-system t)))) - ;; If *scratch* exists and init file didn't change its mode, initialize it. (if (get-buffer "*scratch*") (with-current-buffer "*scratch*" diff --git a/src/ChangeLog b/src/ChangeLog index 1c56a7c5996..f6f4dc3ef88 100644 --- a/src/ChangeLog +++ b/src/ChangeLog @@ -1,3 +1,34 @@ +2013-11-04 Eli Zaretskii <eliz@gnu.org> + + * 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 <eggert@cs.ucla.edu> Port to stricter C99 platforms. diff --git a/src/buffer.c b/src/buffer.c index e5a8af93cf0..63198cd1018 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 d4b4a26ec3a..2740779f513 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 0472bec99de..5a921e44950 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 928babb417c..52d2e76dc87 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 a1dcb72b4e4..884af25f9fc 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 b42ac5908e9..618b0cadb53 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 9992fa4776a..382f9e7a8e1 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) |