X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=lisp%2Fmm-util.el;h=29436800fecca1b27eb3d9ff3e2ac08f51a1bffb;hb=a707b63af25b91cb730c12e65156ca364bf49a44;hp=c8800b0ca79d1cf47622b9908542f2c581256f6a;hpb=baa7cb7f6c13f0609cb29ebefcff7a8fbd0d15e3;p=elisp%2Fgnus.git- diff --git a/lisp/mm-util.el b/lisp/mm-util.el index c8800b0..2943680 100644 --- a/lisp/mm-util.el +++ b/lisp/mm-util.el @@ -1,5 +1,5 @@ -;;; mm-util.el --- Utility functions for MIME things -;; Copyright (C) 1998 Free Software Foundation, Inc. +;;; mm-util.el --- Utility functions for Mule and low level things +;; Copyright (C) 1998, 1999, 2000 Free Software Foundation, Inc. ;; Author: Lars Magne Ingebrigtsen ;; MORIOKA Tomohiko @@ -24,8 +24,8 @@ ;;; Code: -(defvar mm-known-charsets '(iso-8859-1) - "List of known charsets.") +(eval-when-compile (require 'cl)) +(require 'mail-prsvr) (defvar mm-mime-mule-charset-alist '((us-ascii ascii) @@ -34,20 +34,27 @@ (iso-8859-3 latin-iso8859-3) (iso-8859-4 latin-iso8859-4) (iso-8859-5 cyrillic-iso8859-5) - (koi8-r cyrillic-iso8859-5) + ;; Non-mule (X)Emacs uses the last mule-charset for 8bit characters. + ;; The fake mule-charset, gnus-koi8-r, tells Gnus that the default + ;; charset is koi8-r, not iso-8859-5. + (koi8-r cyrillic-iso8859-5 gnus-koi8-r) (iso-8859-6 arabic-iso8859-6) (iso-8859-7 greek-iso8859-7) (iso-8859-8 hebrew-iso8859-8) (iso-8859-9 latin-iso8859-9) - (iso-2022-jp latin-jisx0201 - japanese-jisx0208-1978 japanese-jisx0208) + (viscii vietnamese-viscii-lower) + (iso-2022-jp latin-jisx0201 japanese-jisx0208 japanese-jisx0208-1978) (euc-kr korean-ksc5601) (cn-gb-2312 chinese-gb2312) (cn-big5 chinese-big5-1 chinese-big5-2) + (tibetan tibetan) + (thai-tis620 thai-tis620) + (iso-2022-7bit ethiopic arabic-1-column arabic-2-column) (iso-2022-jp-2 latin-iso8859-1 greek-iso8859-7 latin-jisx0201 japanese-jisx0208-1978 chinese-gb2312 japanese-jisx0208 - korean-ksc5601 japanese-jisx0212) + korean-ksc5601 japanese-jisx0212 + katakana-jisx0201) (iso-2022-int-1 latin-iso8859-1 greek-iso8859-7 latin-jisx0201 japanese-jisx0208-1978 chinese-gb2312 japanese-jisx0208 @@ -61,67 +68,122 @@ chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6 - chinese-cns11643-7)) + chinese-cns11643-7) + (utf-8 unicode-a unicode-b unicode-c unicode-d unicode-e)) "Alist of MIME-charset/MULE-charsets.") +(eval-and-compile + (mapcar + (lambda (elem) + (let ((nfunc (intern (format "mm-%s" (car elem))))) + (if (fboundp (car elem)) + (defalias nfunc (car elem)) + (defalias nfunc (cdr elem))))) + '((decode-coding-string . (lambda (s a) s)) + (encode-coding-string . (lambda (s a) s)) + (encode-coding-region . ignore) + (coding-system-list . ignore) + (decode-coding-region . ignore) + (char-int . identity) + (device-type . ignore) + (coding-system-equal . equal) + (annotationp . ignore) + (set-buffer-file-coding-system . ignore) + (make-char + . (lambda (charset int) + (int-to-char int))) + (read-coding-system + . (lambda (prompt) + "Prompt the user for a coding system." + (completing-read + prompt (mapcar (lambda (s) (list (symbol-name (car s)))) + mm-mime-mule-charset-alist)))) + (read-charset + . (lambda (prompt) + "Return a charset." + (intern + (completing-read + prompt + (mapcar (lambda (e) (list (symbol-name (car e)))) + mm-mime-mule-charset-alist) + nil t)))) + (subst-char-in-string + . (lambda (from to string) ;; stolen (and renamed) from nnheader.el + "Replace characters in STRING from FROM to TO." + (let ((string (substring string 0)) ;Copy string. + (len (length string)) + (idx 0)) + ;; Replace all occurrences of FROM with TO. + (while (< idx len) + (when (= (aref string idx) from) + (aset string idx to)) + (setq idx (1+ idx))) + string))) + ))) (eval-and-compile - (if (fboundp 'decode-coding-string) - (fset 'mm-decode-coding-string 'decode-coding-string) - (fset 'mm-decode-coding-string (lambda (s a) s))) - - (if (fboundp 'encode-coding-string) - (fset 'mm-encode-coding-string 'encode-coding-string) - (fset 'mm-encode-coding-string (lambda (s a) s))) - - (if (fboundp 'encode-coding-region) - (fset 'mm-encode-coding-region 'encode-coding-region) - (fset 'mm-encode-coding-region 'ignore)) - - (if (fboundp 'decode-coding-region) - (fset 'mm-decode-coding-region 'decode-coding-region) - (fset 'mm-decode-coding-region 'ignore)) - - (if (fboundp 'coding-system-list) - (fset 'mm-coding-system-list 'coding-system-list) - (fset 'mm-coding-system-list 'ignore)) - - (if (fboundp 'char-int) - (fset 'mm-char-int 'char-int) - (fset 'mm-char-int 'identity)) - - (if (fboundp 'coding-system-equal) - (fset 'mm-coding-system-equal 'coding-system-equal) - (fset 'mm-coding-system-equal 'equal)) - - (if (fboundp 'read-coding-system) - (fset 'mm-read-coding-system 'read-coding-system) - (defun mm-read-coding-system (prompt) - "Prompt the user for a coding system." - (completing-read - prompt (mapcar (lambda (s) (list (symbol-name (car s)))) - mm-mime-mule-charset-alist))))) - - -(defvar mm-charset-coding-system-alist - (let ((rest - '((us-ascii . iso-8859-1) - (gb2312 . cn-gb-2312) - (iso-2022-jp-2 . iso-2022-7bit-ss2) - (x-ctext . ctext))) - (systems (mm-coding-system-list)) - dest) - (while rest - (let ((pair (car rest))) - (unless (memq (car pair) systems) - (setq dest (cons pair dest)))) - (setq rest (cdr rest))) - dest) - "Charset/coding system alist.") + (defalias 'mm-char-or-char-int-p + (cond + ((fboundp 'char-or-char-int-p) 'char-or-char-int-p) + ((fboundp 'char-valid-p) 'char-valid-p) + (t 'identity)))) + +(defvar mm-coding-system-list nil) +(defun mm-get-coding-system-list () + "Get the coding system list." + (or mm-coding-system-list + (setq mm-coding-system-list (mm-coding-system-list)))) + +(defun mm-coding-system-p (sym) + "Return non-nil if SYM is a coding system." + (or (and (fboundp 'coding-system-p) (coding-system-p sym)) + (memq sym (mm-get-coding-system-list)))) + +(defvar mm-charset-synonym-alist + `((big5 . cn-big5) + (gb2312 . cn-gb-2312) + (cn-gb . cn-gb-2312) + ;; Windows-1252 is actually a superset of Latin-1. See also + ;; `gnus-article-dumbquotes-map'. + ,(unless (mm-coding-system-p 'windows-1252) ; should be defined eventually + '(windows-1252 . iso-8859-1)) + (x-ctext . ctext)) + "A mapping from invalid charset names to the real charset names.") + +(defvar mm-binary-coding-system + (cond + ((mm-coding-system-p 'binary) 'binary) + ((mm-coding-system-p 'no-conversion) 'no-conversion) + (t nil)) + "100% binary coding system.") + +(defvar mm-text-coding-system + (or (if (memq system-type '(windows-nt ms-dos ms-windows)) + (and (mm-coding-system-p 'raw-text-dos) 'raw-text-dos) + (and (mm-coding-system-p 'raw-text) 'raw-text)) + mm-binary-coding-system) + "Text-safe coding system (For removing ^M).") + +(defvar mm-text-coding-system-for-write nil + "Text coding system for write.") + +(defvar mm-auto-save-coding-system + (cond + ((mm-coding-system-p 'emacs-mule) + (if (memq system-type '(windows-nt ms-dos ms-windows)) + (if (mm-coding-system-p 'emacs-mule-dos) + 'emacs-mule-dos mm-binary-coding-system) + 'emacs-mule)) + ((mm-coding-system-p 'escape-quoted) 'escape-quoted) + (t mm-binary-coding-system)) + "Coding system of auto save file.") + +;;; Internal variables: +;;; Functions: (defun mm-mule-charset-to-mime-charset (charset) - "Return the MIME charset corresponding to MULE CHARSET." + "Return the MIME charset corresponding to the given Mule CHARSET." (let ((alist mm-mime-mule-charset-alist) out) (while alist @@ -139,67 +201,344 @@ used as the line break code type of the coding system." (when (stringp charset) (setq charset (intern (downcase charset)))) (setq charset - (or (cdr (assq charset mm-charset-coding-system-alist)) + (or (cdr (assq charset mm-charset-synonym-alist)) charset)) (when lbt (setq charset (intern (format "%s-%s" charset lbt)))) (cond ;; Running in a non-MULE environment. - ((and (null (mm-coding-system-list)) - (memq charset mm-known-charsets)) + ((null (mm-get-coding-system-list)) charset) - ;; Check to see whether we can handle this charset. - ((memq charset (mm-coding-system-list)) + ;; ascii + ((eq charset 'us-ascii) + 'ascii) + ;; Check to see whether we can handle this charset. (This depends + ;; on there being some coding system matching each `mime-charset' + ;; coding sysytem property defined, as there should be.) + ((memq charset (mm-get-coding-system-list)) charset) ;; Nope. (t nil))) -(defun mm-replace-chars-in-string (string from to) - "Replace characters in STRING from FROM to TO." - (let ((string (substring string 0)) ;Copy string. - (len (length string)) - (idx 0)) - ;; Replace all occurrences of FROM with TO. - (while (< idx len) - (when (= (aref string idx) from) - (aset string idx to)) - (setq idx (1+ idx))) - string)) - -(defun mm-enable-multibyte () - "Enable multibyte in the current buffer." - (when (fboundp 'set-buffer-multibyte) +(defsubst mm-replace-chars-in-string (string from to) + (mm-subst-char-in-string from to string)) + +(defsubst mm-enable-multibyte () + "Set the multibyte flag of the current buffer. +Only do this if the default value of `enable-multibyte-characters' is +non-nil. This is a no-op in XEmacs." + (when (and (not (featurep 'xemacs)) + (boundp 'default-enable-multibyte-characters) + default-enable-multibyte-characters + (fboundp 'set-buffer-multibyte)) + (set-buffer-multibyte t))) + +(defsubst mm-disable-multibyte () + "Unset the multibyte flag of in the current buffer. +This is a no-op in XEmacs." + (when (and (not (featurep 'xemacs)) + (fboundp 'set-buffer-multibyte)) + (set-buffer-multibyte nil))) + +(defsubst mm-enable-multibyte-mule4 () + "Enable multibyte in the current buffer. +Only used in Emacs Mule 4." + (when (and (not (featurep 'xemacs)) + (boundp 'default-enable-multibyte-characters) + default-enable-multibyte-characters + (fboundp 'set-buffer-multibyte) + (fboundp 'charsetp) + (not (charsetp 'eight-bit-control))) (set-buffer-multibyte t))) -(defun mm-insert-rfc822-headers (charset encoding) - "Insert text/plain headers with CHARSET and ENCODING." - (insert "MIME-Version: 1.0\n") - (insert "Content-Type: text/plain; charset=\"" - (downcase (symbol-name charset)) "\"\n") - (insert "Content-Transfer-Encoding: " - (downcase (symbol-name encoding)) "\n")) +(defsubst mm-disable-multibyte-mule4 () + "Disable multibyte in the current buffer. +Only used in Emacs Mule 4." + (when (and (not (featurep 'xemacs)) + (fboundp 'set-buffer-multibyte) + (fboundp 'charsetp) + (not (charsetp 'eight-bit-control))) + (set-buffer-multibyte nil))) -(defun mm-content-type-charset (header) - "Return the charset parameter from HEADER." - (when (string-match "charset *= *\"? *\\([-0-9a-zA-Z_]+\\)\"? *$" header) - (intern (downcase (match-string 1 header))))) +(defun mm-preferred-coding-system (charset) + ;; A typo in some Emacs versions. + (or (get-charset-property charset 'prefered-coding-system) + (get-charset-property charset 'preferred-coding-system))) +(defun mm-charset-after (&optional pos) + "Return charset of a character in current buffer at position POS. +If POS is nil, it defauls to the current point. +If POS is out of range, the value is nil. +If the charset is `composition', return the actual one." + (let ((char (char-after pos)) charset) + (if (< (mm-char-int char) 128) + (setq charset 'ascii) + ;; charset-after is fake in some Emacsen. + (setq charset (and (fboundp 'char-charset) (char-charset char))) + (if (eq charset 'composition) + (let ((p (or pos (point)))) + (cadr (find-charset-region p (1+ p)))) + (if (and charset (not (memq charset '(ascii eight-bit-control + eight-bit-graphic)))) + charset + (or + mail-parse-mule-charset ;; cached mule-charset + (progn + (setq mail-parse-mule-charset + (and (boundp 'current-language-environment) + (car (last + (assq 'charset + (assoc current-language-environment + language-info-alist)))))) + (if (or (not mail-parse-mule-charset) + (eq mail-parse-mule-charset 'ascii)) + (setq mail-parse-mule-charset + (or (car (last (assq mail-parse-charset + mm-mime-mule-charset-alist))) + 'latin-iso8859-1))) + mail-parse-mule-charset))))))) -(defun mm-mime-charset (charset b e) - (if (fboundp 'coding-system-get) +(defun mm-mime-charset (charset) + "Return the MIME charset corresponding to the MULE CHARSET." + (if (eq charset 'unknown) + (error "8-bit characters are found in the message, please specify charset.")) + (if (and (fboundp 'coding-system-get) (fboundp 'get-charset-property)) + ;; This exists in Emacs 20. (or - (coding-system-get - (get-charset-property charset 'prefered-coding-system) - 'mime-charset) - (car (memq charset (find-coding-systems-region - (point-min) (point-max))))) + (and (mm-preferred-coding-system charset) + (coding-system-get + (mm-preferred-coding-system charset) 'mime-charset)) + (and (eq charset 'ascii) + 'us-ascii) + (mm-preferred-coding-system charset) + (mm-mule-charset-to-mime-charset charset)) + ;; This is for XEmacs. (mm-mule-charset-to-mime-charset charset))) -(defun mm-multibyte-p () +(defun mm-delete-duplicates (list) + "Simple substitute for CL `delete-duplicates', testing with `equal'." + (let (result head) + (while list + (setq head (car list)) + (setq list (delete head list)) + (setq result (cons head result))) + (nreverse result))) + +(defun mm-find-mime-charset-region (b e) + "Return the MIME charsets needed to encode the region between B and E." + (let ((charsets (mapcar 'mm-mime-charset + (delq 'ascii + (mm-find-charset-region b e))))) + (when (memq 'iso-2022-jp-2 charsets) + (setq charsets (delq 'iso-2022-jp charsets))) + (setq charsets (mm-delete-duplicates charsets)) + (if (and (> (length charsets) 1) + (fboundp 'find-coding-systems-region) + (memq 'utf-8 (find-coding-systems-region b e))) + '(utf-8) + charsets))) + +(defsubst mm-multibyte-p () "Say whether multibyte is enabled." - (and (boundp 'enable-multibyte-characters) - enable-multibyte-characters)) + (if (and (not (featurep 'xemacs)) + (boundp 'enable-multibyte-characters)) + enable-multibyte-characters + (featurep 'mule))) + +(defmacro mm-with-unibyte-buffer (&rest forms) + "Create a temporary buffer, and evaluate FORMS there like `progn'. +Use unibyte mode for this." + `(let (default-enable-multibyte-characters) + (with-temp-buffer ,@forms))) +(put 'mm-with-unibyte-buffer 'lisp-indent-function 0) +(put 'mm-with-unibyte-buffer 'edebug-form-spec '(body)) + +(defmacro mm-with-unibyte-current-buffer (&rest forms) + "Evaluate FORMS with current current buffer temporarily made unibyte. +Also bind `default-enable-multibyte-characters' to nil. +Equivalent to `progn' in XEmacs" + (let ((buffer (make-symbol "buffer"))) + `(if (and (not (featurep 'xemacs)) + (boundp 'enable-multibyte-characters) + enable-multibyte-characters + (fboundp 'set-buffer-multibyte)) + (let ((,buffer (current-buffer))) + (unwind-protect + (let (default-enable-multibyte-characters) + (set-buffer-multibyte nil) + ,@forms) + (set-buffer ,buffer) + (set-buffer-multibyte t))) + (let (default-enable-multibyte-characters) + ,@forms)))) +(put 'mm-with-unibyte-current-buffer 'lisp-indent-function 0) +(put 'mm-with-unibyte-current-buffer 'edebug-form-spec '(body)) + +(defmacro mm-with-unibyte-current-buffer-mule4 (&rest forms) + "Evaluate FORMS there like `progn' in current buffer. +Mule4 only." + (let ((buffer (make-symbol "buffer"))) + `(if (and (not (featurep 'xemacs)) + (boundp 'enable-multibyte-characters) + enable-multibyte-characters + (fboundp 'set-buffer-multibyte) + (fboundp 'charsetp) + (not (charsetp 'eight-bit-control))) ;; For Emacs Mule 4 only. + (let ((,buffer (current-buffer))) + (unwind-protect + (let (default-enable-multibyte-characters) + (set-buffer-multibyte nil) + ,@forms) + (set-buffer ,buffer) + (set-buffer-multibyte t))) + (let (default-enable-multibyte-characters) + ,@forms)))) +(put 'mm-with-unibyte-current-buffer-mule4 'lisp-indent-function 0) +(put 'mm-with-unibyte-current-buffer-mule4 'edebug-form-spec '(body)) + +(defmacro mm-with-unibyte (&rest forms) + "Eval the FORMS with the default value of `enable-multibyte-characters' nil, ." + `(let (default-enable-multibyte-characters) + ,@forms)) +(put 'mm-with-unibyte 'lisp-indent-function 0) +(put 'mm-with-unibyte 'edebug-form-spec '(body)) + +(defun mm-find-charset-region (b e) + "Return a list of Emacs charsets in the region B to E." + (cond + ((and (mm-multibyte-p) + (fboundp 'find-charset-region)) + ;; Remove composition since the base charsets have been included. + ;; Remove eight-bit-*, treat them as ascii. + (let ((css (find-charset-region b e))) + (mapcar (lambda (cs) (setq css (delq cs css))) + '(composition eight-bit-control eight-bit-graphic)) + css)) + (t + ;; We are in a unibyte buffer or XEmacs non-mule, so we futz around a bit. + (save-excursion + (save-restriction + (narrow-to-region b e) + (goto-char (point-min)) + (skip-chars-forward "\0-\177") + (if (eobp) + '(ascii) + (let (charset) + (setq charset + (and (boundp 'current-language-environment) + (car (last (assq 'charset + (assoc current-language-environment + language-info-alist)))))) + (if (eq charset 'ascii) (setq charset nil)) + (or charset + (setq charset + (car (last (assq mail-parse-charset + mm-mime-mule-charset-alist))))) + (list 'ascii (or charset 'latin-iso8859-1))))))))) + +(if (fboundp 'shell-quote-argument) + (defalias 'mm-quote-arg 'shell-quote-argument) + (defun mm-quote-arg (arg) + "Return a version of ARG that is safe to evaluate in a shell." + (let ((pos 0) new-pos accum) + ;; *** bug: we don't handle newline characters properly + (while (setq new-pos (string-match "[]*[;!'`\"$\\& \t{} |()<>]" arg pos)) + (push (substring arg pos new-pos) accum) + (push "\\" accum) + (push (list (aref arg new-pos)) accum) + (setq pos (1+ new-pos))) + (if (= pos 0) + arg + (apply 'concat (nconc (nreverse accum) (list (substring arg pos)))))))) + +(defun mm-auto-mode-alist () + "Return an `auto-mode-alist' with only the .gz (etc) thingies." + (let ((alist auto-mode-alist) + out) + (while alist + (when (listp (cdar alist)) + (push (car alist) out)) + (pop alist)) + (nreverse out))) + +(defvar mm-inhibit-file-name-handlers + '(jka-compr-handler) + "A list of handlers doing (un)compression (etc) thingies.") + +(defun mm-insert-file-contents (filename &optional visit beg end replace + inhibit) + "Like `insert-file-contents', q.v., but only reads in the file. +A buffer may be modified in several ways after reading into the buffer due +to advanced Emacs features, such as file-name-handlers, format decoding, +find-file-hooks, etc. +If INHIBIT is non-nil, inhibit mm-inhibit-file-name-handlers. + This function ensures that none of these modifications will take place." + (let ((format-alist nil) + (auto-mode-alist (if inhibit nil (mm-auto-mode-alist))) + (default-major-mode 'fundamental-mode) + (enable-local-variables nil) + (after-insert-file-functions nil) + (enable-local-eval nil) + (find-file-hooks nil) + (inhibit-file-name-operation (if inhibit + 'insert-file-contents + inhibit-file-name-operation)) + (inhibit-file-name-handlers + (if inhibit + (append mm-inhibit-file-name-handlers + inhibit-file-name-handlers) + inhibit-file-name-handlers))) + (insert-file-contents filename visit beg end replace))) + +(defun mm-append-to-file (start end filename &optional codesys inhibit) + "Append the contents of the region to the end of file FILENAME. +When called from a function, expects three arguments, +START, END and FILENAME. START and END are buffer positions +saying what text to write. +Optional fourth argument specifies the coding system to use when +encoding the file. +If INHIBIT is non-nil, inhibit mm-inhibit-file-name-handlers." + (let ((coding-system-for-write + (or codesys mm-text-coding-system-for-write + mm-text-coding-system)) + (inhibit-file-name-operation (if inhibit + 'append-to-file + inhibit-file-name-operation)) + (inhibit-file-name-handlers + (if inhibit + (append mm-inhibit-file-name-handlers + inhibit-file-name-handlers) + inhibit-file-name-handlers))) + (append-to-file start end filename))) + +(defun mm-write-region (start end filename &optional append visit lockname + coding-system inhibit) + + "Like `write-region'. +If INHIBIT is non-nil, inhibit mm-inhibit-file-name-handlers." + (let ((coding-system-for-write + (or coding-system mm-text-coding-system-for-write + mm-text-coding-system)) + (inhibit-file-name-operation (if inhibit + 'write-region + inhibit-file-name-operation)) + (inhibit-file-name-handlers + (if inhibit + (append mm-inhibit-file-name-handlers + inhibit-file-name-handlers) + inhibit-file-name-handlers))) + (write-region start end filename append visit lockname))) + +(defun mm-image-load-path (&optional package) + (let (dir result) + (dolist (path load-path (nreverse result)) + (if (file-directory-p + (setq dir (concat (file-name-directory + (directory-file-name path)) + "etc/" (or package "gnus/")))) + (push dir result)) + (push path result)))) (provide 'mm-util)