X-Git-Url: http://cgit.sxemacs.org/?a=blobdiff_plain;f=lisp%2Fmm-util.el;h=80c182ab2f920e6bb7157024e2628b25fae285ab;hb=59409510d1e17b4f41d10861516412f6546366b3;hp=1634ce3abb71baee7c25e32eff4fac6e71547331;hpb=4e82d566924d807ea0927aa382f7f875e14f33be;p=gnus diff --git a/lisp/mm-util.el b/lisp/mm-util.el index 1634ce3ab..80c182ab2 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) 1998,99 Free Software Foundation, Inc. +;;; mm-util.el --- Utility functions for Mule and low level things +;; Copyright (C) 1998, 1999, 2000, 2001 Free Software Foundation, Inc. ;; Author: Lars Magne Ingebrigtsen ;; MORIOKA Tomohiko @@ -24,47 +24,31 @@ ;;; Code: -(defvar mm-running-xemacs (string-match "XEmacs" emacs-version)) - -(defvar mm-running-ntemacs - (and (not mm-running-xemacs) - (string-match "nt" system-configuration))) - -(defvar mm-binary-coding-system - (if mm-running-xemacs - 'binary 'no-conversion) - "100% binary coding system.") - -(defvar mm-text-coding-system - (cond - ((not (fboundp 'coding-system-p)) nil) - (mm-running-xemacs ;; XEmacs - 'no-conversion) - (mm-running-ntemacs ;; NTEmacs - (and (coding-system-p 'raw-text-dos) 'raw-text-dos)) - ((coding-system-p 'raw-text) 'raw-text) ;; Emacs - (t nil)) - "100% text coding system, for removing ^M.") +(eval-when-compile (require 'cl)) +(require 'mail-prsvr) (defvar mm-mime-mule-charset-alist - '((us-ascii ascii) + `((us-ascii ascii) (iso-8859-1 latin-iso8859-1) (iso-8859-2 latin-iso8859-2) (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-8859-14 latin-iso8859-14) + (iso-8859-15 latin-iso8859-15) (viscii vietnamese-viscii-lower) - (iso-2022-jp-2 japanese-jisx0208) - (iso-2022-jp latin-jisx0201 - japanese-jisx0208-1978) + (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) + (gb2312 chinese-gb2312) + (big5 chinese-big5-1 chinese-big5-2) (tibetan tibetan) (thai-tis620 thai-tis620) (iso-2022-7bit ethiopic arabic-1-column arabic-2-column) @@ -86,17 +70,23 @@ chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6 - chinese-cns11643-7)) + chinese-cns11643-7) + ,(if (or (not (fboundp 'charsetp)) ;; non-Mule case + (not (fboundp 'coding-system-p)) + (charsetp 'unicode-a) + (not (coding-system-p 'mule-utf-8))) + '(utf-8 unicode-a unicode-b unicode-c unicode-d unicode-e) + ;; If we have utf-8 we're in Mule 5+. + (delete 'ascii (coding-system-get 'mule-utf-8 'safe-charsets)))) "Alist of MIME-charset/MULE-charsets.") - (eval-and-compile (mapcar (lambda (elem) (let ((nfunc (intern (format "mm-%s" (car elem))))) (if (fboundp (car elem)) - (fset nfunc (car elem)) - (fset nfunc (cdr 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) @@ -110,8 +100,48 @@ (make-char . (lambda (charset int) (int-to-char int))) - (read-coding-system + (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))) + (string-as-unibyte . identity) + (string-as-multibyte . identity) + (multibyte-string-p . ignore)))) + +(eval-and-compile + (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)))) + +(eval-and-compile + (defalias 'mm-read-coding-system + (cond + ((fboundp 'read-coding-system) + (if (and (featurep 'xemacs) + (<= (string-to-number emacs-version) 21.1)) + (lambda (prompt &optional default-coding-system) + (read-coding-system prompt)) + 'read-coding-system)) + (t (lambda (prompt &optional default-coding-system) "Prompt the user for a coding system." (completing-read prompt (mapcar (lambda (s) (list (symbol-name (car s)))) @@ -123,19 +153,59 @@ (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) + `((big5 . cn-big5) (gb2312 . cn-gb-2312) - (iso-2022-jp-2 . iso-2022-7bit-ss2) + (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.") + +(defvar mm-universal-coding-system mm-auto-save-coding-system + "The universal Coding system.") + ;;; 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 @@ -164,97 +234,214 @@ used as the line break code type of the coding system." ;; ascii ((eq charset 'us-ascii) 'ascii) - ;; Check to see whether we can handle this charset. + ;; 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)) +(defsubst mm-replace-chars-in-string (string from to) + (mm-subst-char-in-string from to string)) (defsubst mm-enable-multibyte () - "Enable multibyte in the current buffer." - (when (and (fboundp 'set-buffer-multibyte) - (default-value 'enable-multibyte-characters)) + "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 () - "Disable multibyte in the current buffer." - (when (fboundp 'set-buffer-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))) + +(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-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))) + ;; Fixme: don't fix that! + 'latin-iso8859-1))) + mail-parse-mule-charset))))))) + (defun mm-mime-charset (charset) "Return the MIME charset corresponding to the MULE CHARSET." - (if (fboundp 'coding-system-get) + (if (eq charset 'unknown) + (error "The message contains non-printable characters, please use attachment")) + (if (and (fboundp 'coding-system-get) (fboundp 'get-charset-property)) ;; This exists in Emacs 20. (or - (and (get-charset-property charset 'prefered-coding-system) + (and (mm-preferred-coding-system charset) (coding-system-get - (get-charset-property charset 'prefered-coding-system) - 'mime-charset)) + (mm-preferred-coding-system charset) 'mime-charset)) (and (eq charset 'ascii) 'us-ascii) - (get-charset-property charset 'prefered-coding-system) + (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-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))))) - (delete-duplicates charsets))) + (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) + (let ((cs (find-coding-systems-region b e))) + (or (memq 'utf-8 cs) (memq 'mule-utf-8 cs)))) + '(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'. -See also `with-temp-file' and `with-output-to-string'." - (let ((temp-buffer (make-symbol "temp-buffer")) - (multibyte (make-symbol "multibyte"))) - `(if (not (boundp 'enable-multibyte-characters)) - (with-temp-buffer ,@forms) - (let ((,multibyte (default-value 'enable-multibyte-characters)) - ,temp-buffer) - (unwind-protect - (progn - (setq-default enable-multibyte-characters nil) - (setq ,temp-buffer - (get-buffer-create (generate-new-buffer-name " *temp*"))) - (unwind-protect - (with-current-buffer ,temp-buffer - (let ((buffer-file-coding-system mm-binary-coding-system) - (coding-system-for-read mm-binary-coding-system) - (coding-system-for-write mm-binary-coding-system)) - ,@forms)) - (and (buffer-name ,temp-buffer) - (kill-buffer ,temp-buffer)))) - (setq-default enable-multibyte-characters ,multibyte)))))) +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 charsets in the region." + "Return a list of Emacs charsets in the region B to E." (cond - ((fboundp 'find-charset-region) - (find-charset-region b e)) - ((not (boundp 'current-language-environment)) + ((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 + control-1)) + 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) @@ -262,28 +449,121 @@ See also `with-temp-file' and `with-output-to-string'." (skip-chars-forward "\0-\177") (if (eobp) '(ascii) - (delq nil (list 'ascii mail-parse-charset)))))) - (t - ;; We are in a unibyte buffer, so we futz around a bit. - (save-excursion - (save-restriction - (narrow-to-region b e) - (goto-char (point-min)) - (let ((entry (assoc (capitalize current-language-environment) - language-info-alist))) - (skip-chars-forward "\0-\177") - (if (eobp) - '(ascii) - (list 'ascii (car (last (assq 'charset entry))))))))))) - -(defun mm-read-charset (prompt) - "Return a charset." - (intern - (completing-read - prompt - (mapcar (lambda (e) (list (symbol-name (car e)))) - mm-mime-mule-charset-alist) - nil t))) + (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 image-file-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)