(eval-when-compile (require 'cl))
(require 'mail-prsvr)
(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)
(coding-system-equal . equal)
(annotationp . ignore)
(set-buffer-file-coding-system . ignore)
(make-char
. (lambda (charset int)
(int-to-char int)))
(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 &optional inplace)
"Replace characters in STRING from FROM to TO.
Unless optional argument INPLACE is non-nil, return a new string."
(let ((string (if inplace string (copy-sequence string)))
(len (length string))
(idx 0))
(while (< idx len)
(when (= (aref string idx) from)
(aset string idx to))
(setq idx (1+ idx)))
string)))
(string-as-unibyte . identity)
(string-make-unibyte . identity)
(string-as-multibyte . identity)
(multibyte-string-p . ignore)
(insert-byte . insert-char)
(multibyte-char-to-unibyte . identity))))
(eval-and-compile
(cond
((fboundp 'replace-in-string)
(defalias 'mm-replace-in-string 'replace-in-string))
((fboundp 'replace-regexp-in-string)
(defun mm-replace-in-string (string regexp newtext &optional literal)
"Replace all matches for REGEXP with NEWTEXT in STRING.
If LITERAL is non-nil, insert NEWTEXT literally. Return a new
string containing the replacements.
This is a compatibility function for different Emacsen."
(replace-regexp-in-string regexp newtext string nil literal)))
(t
(defun mm-replace-in-string (string regexp newtext &optional literal)
"Replace all matches for REGEXP with NEWTEXT in STRING.
If LITERAL is non-nil, insert NEWTEXT literally. Return a new
string containing the replacements.
This is a compatibility function for different Emacsen."
(let ((start 0) tail)
(while (string-match regexp string start)
(setq tail (- (length string) (match-end 0)))
(setq string (replace-match newtext nil literal string))
(setq start (- (length string) tail))))
string))))
(defalias 'mm-string-to-multibyte
(cond
((featurep 'xemacs)
'identity)
((fboundp 'string-to-multibyte)
'string-to-multibyte)
(t
(lambda (string)
"Return a multibyte string with the same individual chars as string."
(mapconcat
(lambda (ch) (mm-string-as-multibyte (char-to-string ch)))
string "")))))
(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))))
mm-mime-mule-charset-alist)))))))
(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 (cs)
"Return non-nil if CS is a symbol naming a coding system.
In XEmacs, also return non-nil if CS is a coding system object.
If CS is available, return CS itself in Emacs, and return a coding
system object in XEmacs."
(if (fboundp 'find-coding-system)
(and cs (find-coding-system cs))
(if (fboundp 'coding-system-p)
(when (coding-system-p cs)
cs)
(car (memq cs (mm-get-coding-system-list))))))
(defun mm-codepage-setup (number &optional alias)
"Create a coding system cpNUMBER.
The coding system is created using `codepage-setup'. If ALIAS is
non-nil, an alias is created and added to
`mm-charset-synonym-alist'. If ALIAS is a string, it's used as
the alias. Else windows-NUMBER is used."
(interactive
(let ((completion-ignore-case t)
(candidates (cp-supported-codepages)))
(list (completing-read "Setup DOS Codepage: (default 437) " candidates
nil t nil nil "437"))))
(when alias
(setq alias (if (stringp alias)
(intern alias)
(intern (format "windows-%s" number)))))
(let* ((cp (intern (format "cp%s" number))))
(unless (mm-coding-system-p cp)
(codepage-setup number))
(when (and alias
(mm-coding-system-p cp))
(add-to-list 'mm-charset-synonym-alist (cons alias cp)))))
(defvar mm-charset-synonym-alist
`(
,@(unless (mm-coding-system-p 'x-ctext)
'((x-ctext . ctext)))
,@(unless (mm-coding-system-p 'iso-8859-15)
'((iso-8859-15 . iso-8859-1)))
,@(unless (mm-coding-system-p 'big5-hkscs)
'((big5-hkscs . big5)))
,@(when (and (not (mm-coding-system-p 'unicode))
(mm-coding-system-p 'utf-16-le))
'((unicode . utf-16-le)))
,@(unless (mm-coding-system-p 'ks_c_5601-1987)
(if (mm-coding-system-p 'cp949)
'((ks_c_5601-1987 . cp949))
'((ks_c_5601-1987 . euc-kr))))
,@(when (and (not (mm-coding-system-p 'windows-31j))
(mm-coding-system-p 'cp932))
'((windows-31j . cp932)))
)
"A mapping from unknown or invalid charset names to the real charset names.
See `mm-codepage-iso-8859-list' and `mm-codepage-ibm-list'.")
(defcustom mm-codepage-iso-8859-list
(list 1250 '(1252 . 1) '(1254 . 9) '(1255 . 8)) "A list of Windows codepage numbers and iso-8859 charset numbers.
If an element is a number corresponding to a supported windows
codepage, appropriate entries to `mm-charset-synonym-alist' are
added by `mm-setup-codepage-iso-8859'. An element may also be a
cons cell where the car is a codepage number and the cdr is the
corresponding number of an iso-8859 charset."
:type '(list (set :inline t
(const 1250 :tag "Central and East European")
(const (1252 . 1) :tag "West European")
(const (1254 . 9) :tag "Turkish")
(const (1255 . 8) :tag "Hebrew"))
(repeat :inline t
:tag "Other options"
(choice
(integer :tag "Windows codepage number")
(cons (integer :tag "Windows codepage number")
(integer :tag "iso-8859 charset number")))))
:version "22.1" :group 'mime)
(defcustom mm-codepage-ibm-list
(list 437 860 861 862 863 865 852 850 855 866 857 864 869 874) "List of IBM codepage numbers.
The codepage mappings slighly differ between IBM and other vendors.
See \"ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/IBM/README.TXT\".
If an element is a number corresponding to a supported windows
codepage, appropriate entries to `mm-charset-synonym-alist' are
added by `mm-setup-codepage-ibm'."
:type '(list (set :inline t
(const 437 :tag "US etc.")
(const 860 :tag "Portugal")
(const 861 :tag "Iceland")
(const 862 :tag "Israel")
(const 863 :tag "Canadian French")
(const 865 :tag "Nordic")
(const 852)
(const 850 :tag "Latin 1")
(const 855 :tag "Cyrillic")
(const 866 :tag "Cyrillic - Russian")
(const 857 :tag "Turkish")
(const 864 :tag "Arabic")
(const 869 :tag "Greek")
(const 874 :tag "Thai"))
(repeat :inline t
:tag "Other options"
(integer :tag "Codepage number")))
:version "22.1" :group 'mime)
(defun mm-setup-codepage-iso-8859 (&optional list)
"Add appropriate entries to `mm-charset-synonym-alist'.
Unless LIST is given, `mm-codepage-iso-8859-list' is used."
(unless list
(setq list mm-codepage-iso-8859-list))
(dolist (i list)
(let (cp windows iso)
(if (consp i)
(setq cp (intern (format "cp%d" (car i)))
windows (intern (format "windows-%d" (car i)))
iso (intern (format "iso-8859-%d" (cdr i))))
(setq cp (intern (format "cp%d" i))
windows (intern (format "windows-%d" i))))
(unless (mm-coding-system-p windows)
(if (mm-coding-system-p cp)
(add-to-list 'mm-charset-synonym-alist (cons windows cp))
(add-to-list 'mm-charset-synonym-alist (cons windows iso)))))))
(defun mm-setup-codepage-ibm (&optional list)
"Add appropriate entries to `mm-charset-synonym-alist'.
Unless LIST is given, `mm-codepage-ibm-list' is used."
(unless list
(setq list mm-codepage-ibm-list))
(dolist (number list)
(let ((ibm (intern (format "ibm%d" number)))
(cp (intern (format "cp%d" number))))
(when (and (not (mm-coding-system-p ibm))
(mm-coding-system-p cp))
(add-to-list 'mm-charset-synonym-alist (cons ibm cp))))))
(mm-setup-codepage-iso-8859)
(mm-setup-codepage-ibm)
(defcustom mm-charset-override-alist
`((iso-8859-1 . windows-1252))
"A mapping from undesired charset names to their replacement.
You may add pairs like (iso-8859-1 . windows-1252) here,
i.e. treat iso-8859-1 as windows-1252. windows-1252 is a
superset of iso-8859-1."
:type '(list (set :inline t
(const (iso-8859-1 . windows-1252))
(const (undecided . windows-1252)))
(repeat :inline t
:tag "Other options"
(cons (symbol :tag "From charset")
(symbol :tag "To charset"))))
:version "22.1" :group 'mime)
(defcustom mm-charset-eval-alist
(if (featurep 'xemacs)
nil '( (windows-1250 . (mm-codepage-setup 1250 t))
(windows-1251 . (mm-codepage-setup 1251 t))
(windows-1253 . (mm-codepage-setup 1253 t))
(windows-1257 . (mm-codepage-setup 1257 t))))
"An alist of (CHARSET . FORM) pairs.
If an article is encoded in an unknown CHARSET, FORM is
evaluated. This allows to load additional libraries providing
charsets on demand. If supported by your Emacs version, you
could use `autoload-coding-system' here."
:version "22.1" :type '(list (set :inline t
(const (windows-1250 . (mm-codepage-setup 1250 t)))
(const (windows-1251 . (mm-codepage-setup 1251 t)))
(const (windows-1253 . (mm-codepage-setup 1253 t)))
(const (windows-1257 . (mm-codepage-setup 1257 t)))
(const (cp850 . (mm-codepage-setup 850 nil))))
(repeat :inline t
:tag "Other options"
(cons (symbol :tag "charset")
(symbol :tag "form"))))
:group 'mime)
(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 'utf-8-emacs) (if (memq system-type '(windows-nt ms-dos ms-windows))
(if (mm-coding-system-p 'utf-8-emacs-dos)
'utf-8-emacs-dos mm-binary-coding-system)
'utf-8-emacs))
((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.")
(defvar mm-mime-mule-charset-alist
`((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 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 latin-jisx0201 japanese-jisx0208 japanese-jisx0208-1978)
(euc-kr korean-ksc5601)
(gb2312 chinese-gb2312)
(big5 chinese-big5-1 chinese-big5-2)
(tibetan tibetan)
(thai-tis620 thai-tis620)
(windows-1251 cyrillic-iso8859-5)
(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)
(iso-2022-int-1 latin-iso8859-1 greek-iso8859-7
latin-jisx0201 japanese-jisx0208-1978
chinese-gb2312 japanese-jisx0208
korean-ksc5601 japanese-jisx0212
chinese-cns11643-1 chinese-cns11643-2)
(iso-2022-int-1 latin-iso8859-1 latin-iso8859-2
cyrillic-iso8859-5 greek-iso8859-7
latin-jisx0201 japanese-jisx0208-1978
chinese-gb2312 japanese-jisx0208
korean-ksc5601 japanese-jisx0212
chinese-cns11643-1 chinese-cns11643-2
chinese-cns11643-3 chinese-cns11643-4
chinese-cns11643-5 chinese-cns11643-6
chinese-cns11643-7)
(iso-2022-jp-3 latin-jisx0201 japanese-jisx0208-1978 japanese-jisx0208
japanese-jisx0213-1 japanese-jisx0213-2)
(shift_jis latin-jisx0201 katakana-jisx0201 japanese-jisx0208)
,(cond ((fboundp 'unicode-precedence-list)
(cons 'utf-8 (delq 'ascii (mapcar 'charset-name
(unicode-precedence-list)))))
((or (not (fboundp 'charsetp)) (charsetp 'unicode-a)
(not (mm-coding-system-p 'mule-utf-8)))
'(utf-8 unicode-a unicode-b unicode-c unicode-d unicode-e))
(t (append '(utf-8)
(delete 'ascii
(coding-system-get 'mule-utf-8 'safe-charsets))))))
"Alist of MIME-charset/MULE-charsets.")
(defun mm-enrich-utf-8-by-mule-ucs ()
"Make the `utf-8' MIME charset usable by the Mule-UCS package.
This function will run when the `un-define' module is loaded under
XEmacs, and fill the `utf-8' entry in `mm-mime-mule-charset-alist'
with Mule charsets. It is completely useless for Emacs."
(when (boundp 'unicode-basic-translation-charset-order-list)
(condition-case nil
(let ((val (delq
'ascii
(copy-sequence
(symbol-value
'unicode-basic-translation-charset-order-list))))
(elem (assq 'utf-8 mm-mime-mule-charset-alist)))
(if elem
(setcdr elem val)
(setq mm-mime-mule-charset-alist
(nconc mm-mime-mule-charset-alist
(list (cons 'utf-8 val))))))
(error))))
(if (featurep 'xemacs)
(eval-after-load "un-define" '(mm-enrich-utf-8-by-mule-ucs))
(when (and (fboundp 'coding-system-list)
(fboundp 'sort-coding-systems))
(let ((css (sort-coding-systems (coding-system-list 'base-only)))
cs mime mule alist)
(while css
(setq cs (pop css)
mime (or (coding-system-get cs :mime-charset) (coding-system-get cs 'mime-charset)))
(when (and mime
(not (eq t (setq mule
(coding-system-get cs 'safe-charsets))))
(not (assq mime alist)))
(push (cons mime (delq 'ascii mule)) alist)))
(setq mm-mime-mule-charset-alist (nreverse alist)))))
(defvar mm-hack-charsets '(iso-8859-15 iso-2022-jp-2)
"A list of special charsets.
Valid elements include:
`iso-8859-15' convert ISO-8859-1, -9 to ISO-8859-15 if ISO-8859-15 exists.
`iso-2022-jp-2' convert ISO-2022-jp to ISO-2022-jp-2 if ISO-2022-jp-2 exists."
)
(defvar mm-iso-8859-15-compatible
'((iso-8859-1 "\xA4\xA6\xA8\xB4\xB8\xBC\xBD\xBE")
(iso-8859-9 "\xA4\xA6\xA8\xB4\xB8\xBC\xBD\xBE\xD0\xDD\xDE\xF0\xFD\xFE"))
"ISO-8859-15 exchangeable coding systems and inconvertible characters.")
(defvar mm-iso-8859-x-to-15-table
(and (fboundp 'coding-system-p)
(mm-coding-system-p 'iso-8859-15)
(mapcar
(lambda (cs)
(if (mm-coding-system-p (car cs))
(let ((c (string-to-char
(decode-coding-string "\341" (car cs)))))
(cons (char-charset c)
(cons
(- (string-to-char
(decode-coding-string "\341" 'iso-8859-15)) c)
(string-to-list (decode-coding-string (car (cdr cs))
(car cs))))))
'(gnus-charset 0)))
mm-iso-8859-15-compatible))
"A table of the difference character between ISO-8859-X and ISO-8859-15.")
(defcustom mm-coding-system-priorities
(if (boundp 'current-language-environment)
(let ((lang (symbol-value 'current-language-environment)))
(cond ((string= lang "Japanese")
'(iso-8859-1 iso-2022-jp iso-2022-jp-2 shift_jis utf-8)))))
"Preferred coding systems for encoding outgoing messages.
More than one suitable coding system may be found for some text.
By default, the coding system with the highest priority is used
to encode outgoing messages (see `sort-coding-systems'). If this
variable is set, it overrides the default priority."
:version "21.2"
:type '(repeat (symbol :tag "Coding system"))
:group 'mime)
(defvar mm-use-find-coding-systems-region
(fboundp 'find-coding-systems-region)
"Use `find-coding-systems-region' to find proper coding systems.
Setting it to nil is useful on Emacsen supporting Unicode if sending
mail with multiple parts is preferred to sending a Unicode one.")
(defun mm-mule-charset-to-mime-charset (charset)
"Return the MIME charset corresponding to the given Mule CHARSET."
(if (and (fboundp 'find-coding-systems-for-charsets)
(fboundp 'sort-coding-systems))
(let ((css (sort (sort-coding-systems
(find-coding-systems-for-charsets (list charset)))
'mm-sort-coding-systems-predicate))
cs mime)
(while (and (not mime)
css)
(when (setq cs (pop css))
(setq mime (or (coding-system-get cs :mime-charset)
(coding-system-get cs 'mime-charset)))))
mime)
(let ((alist (mapcar (lambda (cs)
(assq cs mm-mime-mule-charset-alist))
(sort (mapcar 'car mm-mime-mule-charset-alist)
'mm-sort-coding-systems-predicate)))
out)
(while alist
(when (memq charset (cdar alist))
(setq out (caar alist)
alist nil))
(pop alist))
out)))
(defun mm-charset-to-coding-system (charset &optional lbt
allow-override)
"Return coding-system corresponding to CHARSET.
CHARSET is a symbol naming a MIME charset.
If optional argument LBT (`unix', `dos' or `mac') is specified, it is
used as the line break code type of the coding system.
If ALLOW-OVERRIDE is given, use `mm-charset-override-alist' to
map undesired charset names to their replacement. This should
only be used for decoding, not for encoding."
(when (stringp charset)
(setq charset (intern (downcase charset))))
(when lbt
(setq charset (intern (format "%s-%s" charset lbt))))
(cond
((null charset)
charset)
((or (null (mm-get-coding-system-list))
(not (fboundp 'coding-system-get)))
charset)
((and allow-override
(let ((cs (cdr (assq charset mm-charset-override-alist))))
(and cs (mm-coding-system-p cs) cs))))
((eq charset 'us-ascii)
'ascii)
((and (mm-coding-system-p charset)
)
charset)
((let* ((el (assq charset mm-charset-eval-alist))
(cs (car el))
(form (cdr el)))
(and cs
form
(prog2
(condition-case nil (eval form) (error nil))
(mm-coding-system-p cs)
(message "Added charset `%s' via `mm-charset-eval-alist'" cs))
cs)))
((let ((cs (cdr (assq charset mm-charset-synonym-alist))))
(and cs
(mm-coding-system-p cs)
cs)))
((let (cs)
(dolist (c (mm-get-coding-system-list))
(if (and (null cs)
(eq charset (or (coding-system-get c :mime-charset)
(coding-system-get c 'mime-charset))))
(setq cs c)))
(unless cs
(if (fboundp 'gnus-message)
(gnus-message 7 "Unknown charset: %s" charset)
(message "Unknown charset: %s" charset)))
cs))))
(defsubst mm-replace-chars-in-string (string from to)
(mm-subst-char-in-string from to string))
(eval-and-compile
(defvar mm-emacs-mule (and (not (featurep 'xemacs))
(boundp 'default-enable-multibyte-characters)
default-enable-multibyte-characters
(fboundp 'set-buffer-multibyte))
"True in Emacs with Mule.")
(if mm-emacs-mule
(defun 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."
(set-buffer-multibyte 'to))
(defalias 'mm-enable-multibyte 'ignore))
(if mm-emacs-mule
(defun mm-disable-multibyte ()
"Unset the multibyte flag of in the current buffer.
This is a no-op in XEmacs."
(set-buffer-multibyte nil))
(defalias 'mm-disable-multibyte 'ignore)))
(defun mm-preferred-coding-system (charset)
(or (get-charset-property charset 'preferred-coding-system)
(get-charset-property charset 'prefered-coding-system)))
(defsubst mm-guess-charset ()
"Guess Mule charset from the language environment."
(or
mail-parse-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-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)
(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
(mm-guess-charset))))))
(defun mm-mime-charset (charset)
"Return the MIME charset corresponding to the given Mule CHARSET."
(if (eq charset 'unknown)
(error "The message contains non-printable characters, please use attachment"))
(if (and (fboundp 'coding-system-get) (fboundp 'get-charset-property))
(or
(and (mm-preferred-coding-system charset)
(or (coding-system-get
(mm-preferred-coding-system charset) :mime-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))
(mm-mule-charset-to-mime-charset charset)))
(if (fboundp 'delete-dups)
(defalias 'mm-delete-duplicates 'delete-dups)
(defun mm-delete-duplicates (list)
"Destructively remove `equal' duplicates from LIST.
Store the result in LIST and return it. LIST must be a proper list.
Of several `equal' occurrences of an element in LIST, the first
one is kept.
This is a compatibility function for Emacsen without `delete-dups'."
(let ((tail list))
(while tail
(setcdr tail (delete (car tail) (cdr tail)))
(setq tail (cdr tail))))
list))
(eval-and-compile
(if (and (not (featurep 'xemacs))
(boundp 'enable-multibyte-characters))
(defun mm-multibyte-p ()
"Non-nil if multibyte is enabled in the current buffer."
enable-multibyte-characters)
(defun mm-multibyte-p () (featurep 'mule))))
(defun mm-default-multibyte-p ()
"Return non-nil if the session is multibyte.
This affects whether coding conversion should be attempted generally."
(if (featurep 'mule)
(if (boundp 'default-enable-multibyte-characters)
default-enable-multibyte-characters
t)))
(defun mm-iso-8859-x-to-15-region (&optional b e)
(if (fboundp 'char-charset)
(let (charset item c inconvertible)
(save-restriction
(if e (narrow-to-region b e))
(goto-char (point-min))
(skip-chars-forward "\0-\177")
(while (not (eobp))
(cond
((not (setq item (assq (char-charset (setq c (char-after)))
mm-iso-8859-x-to-15-table)))
(forward-char))
((memq c (cdr (cdr item)))
(setq inconvertible t)
(forward-char))
(t
(insert-before-markers (prog1 (+ c (car (cdr item)))
(delete-char 1)))))
(skip-chars-forward "\0-\177")))
(not inconvertible))))
(defun mm-sort-coding-systems-predicate (a b)
(let ((priorities
(mapcar (lambda (cs)
(and (setq cs (mm-coding-system-p cs))
(coding-system-base cs)))
mm-coding-system-priorities)))
(and (setq a (mm-coding-system-p a))
(if (setq b (mm-coding-system-p b))
(> (length (memq (coding-system-base a) priorities))
(length (memq (coding-system-base b) priorities)))
t))))
(eval-when-compile
(autoload 'latin-unity-massage-name "latin-unity")
(autoload 'latin-unity-maybe-remap "latin-unity")
(autoload 'latin-unity-representations-feasible-region "latin-unity")
(autoload 'latin-unity-representations-present-region "latin-unity")
(defvar latin-unity-coding-systems)
(defvar latin-unity-ucs-list))
(defun mm-xemacs-find-mime-charset-1 (begin end)
"Determine which MIME charset to use to send region as message.
This uses the XEmacs-specific latin-unity package to better handle the
case where identical characters from diverse ISO-8859-? character sets
can be encoded using a single one of the corresponding coding systems.
It treats `mm-coding-system-priorities' as the list of preferred
coding systems; a useful example setting for this list in Western
Europe would be '(iso-8859-1 iso-8859-15 utf-8), which would default
to the very standard Latin 1 coding system, and only move to coding
systems that are less supported as is necessary to encode the
characters that exist in the buffer.
Latin Unity doesn't know about those non-ASCII Roman characters that
are available in various East Asian character sets. As such, its
behavior if you have a JIS 0212 LATIN SMALL LETTER A WITH ACUTE in a
buffer and it can otherwise be encoded as Latin 1, won't be ideal.
But this is very much a corner case, so don't worry about it."
(let ((systems mm-coding-system-priorities) csets psets curset)
(when (and (not (featurep 'latin-unity)) (locate-library "latin-unity"))
(ignore-errors (require 'latin-unity)))
(if (featurep 'latin-unity)
(progn
(setq csets (latin-unity-representations-feasible-region begin end)
psets (latin-unity-representations-present-region begin end))
(catch 'done
(dolist (curset systems)
(setq curset (latin-unity-massage-name 'buffer-default curset))
(if (memq curset latin-unity-ucs-list)
(throw 'done (list curset)))
(unless (memq curset latin-unity-coding-systems)
(throw 'done nil))
(if (latin-unity-maybe-remap begin end curset csets psets t)
(throw 'done (list curset))))
nil))
nil)))
(defmacro mm-xemacs-find-mime-charset (begin end)
(when (featurep 'xemacs)
`(and (featurep 'mule) (mm-xemacs-find-mime-charset-1 ,begin ,end))))
(defun mm-find-mime-charset-region (b e &optional hack-charsets)
"Return the MIME charsets needed to encode the region between B and E.
nil means ASCII, a single-element list represents an appropriate MIME
charset, and a longer list means no appropriate charset."
(let (charsets)
(or (and (mm-multibyte-p)
mm-use-find-coding-systems-region
(let ((systems (find-coding-systems-region b e)))
(when mm-coding-system-priorities
(setq systems
(sort systems 'mm-sort-coding-systems-predicate)))
(setq systems (delq 'compound-text systems))
(unless (equal systems '(undecided))
(while systems
(let* ((head (pop systems))
(cs (or (coding-system-get head :mime-charset)
(coding-system-get head 'mime-charset))))
(if (and cs
(not (string-match "^[Xx]-" (symbol-name cs)))
(not (string-match "utf-16" (symbol-name cs))))
(setq systems nil
charsets (list cs))))))
charsets))
(setq charsets (mm-xemacs-find-mime-charset b e))
(setq charsets
(mm-delete-duplicates
(mapcar 'mm-mime-charset
(delq 'ascii
(mm-find-charset-region b e))))))
(if (and (> (length charsets) 1)
(memq 'iso-8859-15 charsets)
(memq 'iso-8859-15 hack-charsets)
(save-excursion (mm-iso-8859-x-to-15-region b e)))
(mapcar (lambda (x) (setq charsets (delq (car x) charsets)))
mm-iso-8859-15-compatible))
(if (and (memq 'iso-2022-jp-2 charsets)
(memq 'iso-2022-jp-2 hack-charsets))
(setq charsets (delq 'iso-2022-jp charsets)))
(if (and (featurep 'xemacs)
(> (length charsets) 1)
(mm-coding-system-p 'utf-8))
(let ((mm-coding-system-priorities
(cons 'utf-8 mm-coding-system-priorities)))
(setq charsets
(mm-delete-duplicates
(mapcar 'mm-mime-charset
(delq 'ascii
(mm-find-charset-region b e)))))))
charsets))
(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-multibyte-buffer (&rest forms)
"Create a temporary buffer, and evaluate FORMS there like `progn'.
Use multibyte mode for this."
`(let ((default-enable-multibyte-characters t))
(with-temp-buffer ,@forms)))
(put 'mm-with-multibyte-buffer 'lisp-indent-function 0)
(put 'mm-with-multibyte-buffer 'edebug-form-spec '(body))
(defmacro mm-with-unibyte-current-buffer (&rest forms)
"Evaluate FORMS with current buffer temporarily made unibyte.
Also bind `default-enable-multibyte-characters' to nil.
Equivalent to `progn' in XEmacs
NOTE: Use this macro with caution in multibyte buffers (it is not
worth using this macro in unibyte buffers of course). Use of
`(set-buffer-multibyte t)', which is run finally, is generally
harmful since it is likely to modify existing data in the buffer.
For instance, it converts \"\\300\\255\" into \"\\255\" in
Emacs 23 (unicode)."
(let ((multibyte (make-symbol "multibyte"))
(buffer (make-symbol "buffer")))
`(if mm-emacs-mule
(let ((,multibyte enable-multibyte-characters)
(,buffer (current-buffer)))
(unwind-protect
(let (default-enable-multibyte-characters)
(set-buffer-multibyte nil)
,@forms)
(set-buffer ,buffer)
(set-buffer-multibyte ,multibyte)))
(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 (&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))
(defmacro mm-with-multibyte (&rest forms)
"Eval the FORMS with the default value of `enable-multibyte-characters' t."
`(let ((default-enable-multibyte-characters t))
,@forms))
(put 'mm-with-multibyte 'lisp-indent-function 0)
(put 'mm-with-multibyte '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))
(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
(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)
(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', 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)
(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))
(ffh (if (boundp 'find-file-hook)
'find-file-hook
'find-file-hooks))
(val (symbol-value ffh)))
(set ffh nil)
(unwind-protect
(insert-file-contents filename visit beg end replace)
(set ffh val))))
(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)))
(write-region start end filename t 'no-message)
(message "Appended to %s" 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)))
(if (and (fboundp 'make-temp-file)
(ignore-errors
(let ((def (symbol-function 'make-temp-file)))
(and (byte-code-function-p def)
(setq def (if (fboundp 'compiled-function-arglist)
(eval (list 'compiled-function-arglist def))
(aref def 0)))
(>= (length def) 4)
(eq (nth 3 def) 'suffix)))))
(defalias 'mm-make-temp-file 'make-temp-file)
(defun mm-make-temp-file (prefix &optional dir-flag suffix)
"Create a temporary file.
The returned file name (created by appending some random characters at the end
of PREFIX, and expanding against `temporary-file-directory' if necessary),
is guaranteed to point to a newly created empty file.
You can then use `write-region' to write new data into the file.
If DIR-FLAG is non-nil, create a new empty directory instead of a file.
If SUFFIX is non-nil, add that at the end of the file name."
(let ((umask (default-file-modes))
file)
(unwind-protect
(progn
(set-default-file-modes 448)
(while (condition-case err
(progn
(setq file
(make-temp-name
(expand-file-name
prefix
(if (fboundp 'temp-directory)
(temp-directory)
temporary-file-directory))))
(if suffix
(setq file (concat file suffix)))
(if dir-flag
(make-directory file)
(gmm-write-region "" nil file nil 'silent
nil 'excl))
nil)
(file-already-exists t)
(file-error (or (and (or (featurep 'xemacs)
(= emacs-major-version 20))
(file-exists-p file))
(signal (car err) (cdr err)))))
nil)
file)
(set-default-file-modes umask)))))
(defun mm-image-load-path (&optional package)
(let (dir result)
(dolist (path load-path (nreverse result))
(when (and path
(file-directory-p
(setq dir (concat (file-name-directory
(directory-file-name path))
"etc/images/" (or package "gnus/")))))
(push dir result))
(push path result))))
(if (fboundp 'detect-coding-region)
(defun mm-detect-coding-region (start end)
"Like `detect-coding-region' except returning the best one."
(let ((coding-systems
(detect-coding-region start end)))
(or (car-safe coding-systems)
coding-systems)))
(defun mm-detect-coding-region (start end)
(let ((point (point)))
(goto-char start)
(skip-chars-forward "\0-\177" end)
(prog1
(if (eq (point) end) 'ascii (mm-guess-charset))
(goto-char point)))))
(if (fboundp 'coding-system-get)
(defun mm-detect-mime-charset-region (start end)
"Detect MIME charset of the text in the region between START and END."
(let ((cs (mm-detect-coding-region start end)))
(or (coding-system-get cs :mime-charset)
(coding-system-get cs 'mime-charset))))
(defun mm-detect-mime-charset-region (start end)
"Detect MIME charset of the text in the region between START and END."
(let ((cs (mm-detect-coding-region start end)))
cs)))
(provide 'mm-util)