[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Emacs-diffs] Changes to emacs/lisp/international/mule.el [lexbind]
|
From: |
Miles Bader |
|
Subject: |
[Emacs-diffs] Changes to emacs/lisp/international/mule.el [lexbind] |
|
Date: |
Tue, 14 Oct 2003 19:39:32 -0400 |
Index: emacs/lisp/international/mule.el
diff -c emacs/lisp/international/mule.el:1.147.2.2
emacs/lisp/international/mule.el:1.147.2.3
*** emacs/lisp/international/mule.el:1.147.2.2 Fri Apr 4 01:20:22 2003
--- emacs/lisp/international/mule.el Tue Oct 14 19:39:23 2003
***************
*** 372,378 ****
(setq split (split-char trans)
charset (car split)))
(cond ((eq charset 'ascii)
! char)
((eq charset 'latin-iso8859-1)
(+ (nth 1 split) 128))
((eq charset 'mule-unicode-0100-24ff)
--- 372,378 ----
(setq split (split-char trans)
charset (car split)))
(cond ((eq charset 'ascii)
! (or trans char))
((eq charset 'latin-iso8859-1)
(+ (nth 1 split) 128))
((eq charset 'mule-unicode-0100-24ff)
***************
*** 817,822 ****
--- 817,827 ----
The value is a symbol whose name is the `MIME-charset' parameter of
the coding system.
+ o mime-text-unsuitable
+
+ A non-nil value means the `mime-charset' property names a charset
+ which is unsuitable for the top-level media type \"text\".
+
o valid-codes (meaningful only for a coding system based on CCL)
The value is a list to indicate valid byte ranges of the encoded
***************
*** 1116,1121 ****
--- 1121,1134 ----
first eol)))
first))
+ (defun autoload-coding-system (symbol form)
+ "Define SYMBOL as a coding-system that is defined on demand.
+
+ FROM is a form to evaluate to define the coding-system."
+ (put symbol 'coding-system-define-form form)
+ (setq coding-system-alist (cons (list (symbol-name symbol))
+ coding-system-alist)))
+
(defun set-buffer-file-coding-system (coding-system &optional force)
"Set the file coding-system of the current buffer to CODING-SYSTEM.
This means that when you save the buffer, it will be converted
***************
*** 1126,1132 ****
leaves the end-of-line conversion unspecified, FORCE controls what to
do. If FORCE is nil, get the unspecified aspect (or aspects) from the
buffer's previous `buffer-file-coding-system' value (if it is
! specified there). Otherwise, levae it unspecified.
This marks the buffer modified so that the succeeding \\[save-buffer]
surely saves the buffer with CODING-SYSTEM. From a program, if you
--- 1139,1145 ----
leaves the end-of-line conversion unspecified, FORCE controls what to
do. If FORCE is nil, get the unspecified aspect (or aspects) from the
buffer's previous `buffer-file-coding-system' value (if it is
! specified there). Otherwise, leave it unspecified.
This marks the buffer modified so that the succeeding \\[save-buffer]
surely saves the buffer with CODING-SYSTEM. From a program, if you
***************
*** 1318,1425 ****
;;; X selections
! (defvar non-standard-icccm-encodings-alist
'(("ISO8859-15" . latin-iso8859-15)
("ISO8859-14" . latin-iso8859-14)
("KOI8-R" . koi8-r)
("BIG5-0" . big5))
! "Alist of font charset names defined by XLFD.
! The cdr of each element is the corresponding Emacs charset or coding system.")
;; Functions to support "Non-Standard Character Set Encodings" defined
;; by the COMPOUND-TEXT spec.
! ;; We support that by converting the leading sequence of the
! ;; ``extended segment'' to the corresponding ISO-2022 sequences (if
! ;; the leading sequence names an Emacs charset), or decode the segment
! ;; (if it names a coding system). Encoding does the reverse.
;; This function also supports "The UTF-8 encoding" described in the
;; section 7 of the documentation fo COMPOUND-TEXT distributed with
;; XFree86.
(defun ctext-post-read-conversion (len)
"Decode LEN characters encoded as Compound Text with Extended Segments."
- (buffer-disable-undo) ; minimize consing due to insertions and
deletions
- (narrow-to-region (point) (+ (point) len))
(save-match-data
! (let ((pt (point-marker))
! (oldpt (point-marker))
! (newpt (make-marker))
! (modified-p (buffer-modified-p))
! (case-fold-search nil)
! ;; We need multibyte conversion of "TO" type because the
! ;; buffer may be multibyte, and, in that case, the pattern
! ;; must contain eight-bit-control/graphic characters.
! (pattern (string-to-multibyte
"\\(\e\\)%/[0-4]\\([\200-\377][\200-\377]\\)\\([^\002]+\\)\002\\|\e%G[^\e]+\e%@"))
! last-coding-system-used
! encoding textlen chset)
! (while (re-search-forward pattern nil 'move)
! (set-marker newpt (point))
! (set-marker pt (match-beginning 0))
! (if (= (preceding-char) ?@)
! ;; We found embedded utf-8 sequence.
! (progn
! (delete-char -3) ; delete ESC % @ at the tail
! (goto-char pt)
! (delete-char 3) ; delete ESC % G at the head
! (if (> pt oldpt)
! (decode-coding-region oldpt pt 'ctext-no-compositions))
! (decode-coding-region pt newpt 'mule-utf-8)
! (goto-char newpt)
! (set-marker oldpt newpt))
! (setq encoding (match-string 3))
! (setq textlen (- (+ (* (- (aref (match-string 2) 0) 128) 128)
! (- (aref (match-string 2) 1) 128))
! (1+ (length encoding))))
! (setq
! chset (cdr (assoc-ignore-case encoding
! non-standard-icccm-encodings-alist)))
! (cond ((null chset)
! ;; This charset is not supported--leave this extended
! ;; segment unaltered and skip over it.
! (goto-char (+ (point) textlen)))
! ((charsetp chset)
! ;; If it's a charset, replace the leading escape sequence
! ;; with a standard ISO-2022 sequence. We will decode all
! ;; such segments later, in one go, when we exit the loop
! ;; or find an extended segment that names a coding
! ;; system, not a charset.
! (replace-match
! (concat "\\1"
! (if (= 0 (charset-iso-graphic-plane chset))
! ;; GL charsets
! (if (= 1 (charset-dimension chset)) "(" "$(")
! ;; GR charsets
! (if (= 96 (charset-chars chset))
! "-"
! (if (= 1 (charset-dimension chset)) ")" "$)")))
! (string (charset-iso-final-char chset)))
! t)
! (goto-char (+ (point) textlen)))
! ((coding-system-p chset)
! ;; If it's a coding system, we need to decode the segment
! ;; right away. But first, decode what we've skipped
! ;; across until now.
! (when (> pt oldpt)
! (decode-coding-region oldpt pt 'ctext-no-compositions))
! (delete-region pt newpt)
! (set-marker newpt (+ newpt textlen))
! (decode-coding-region pt newpt chset)
! (goto-char newpt)
! (set-marker oldpt newpt)))))
! ;; Decode what's left.
! (when (> (point) oldpt)
! (decode-coding-region oldpt (point) 'ctext-no-compositions))
! ;; This buffer started as unibyte, because the string we get from
! ;; the X selection is a unibyte string. We must now make it
! ;; multibyte, so that the decoded text is inserted as multibyte
! ;; into its buffer.
! (set-buffer-multibyte t)
! (set-buffer-modified-p modified-p)
! (- (point-max) (point-min)))))
;; If you add charsets here, be sure to modify the regexp used by
;; ctext-pre-write-conversion to look up non-standard charsets.
! (defvar non-standard-designations-alist
'(("$(0" . (big5 "big5-0" 2))
("$(1" . (big5 "big5-0" 2))
;; The following are actually standard; generating extended
--- 1331,1429 ----
;;; X selections
! (defvar ctext-non-standard-encodings-alist
'(("ISO8859-15" . latin-iso8859-15)
("ISO8859-14" . latin-iso8859-14)
("KOI8-R" . koi8-r)
("BIG5-0" . big5))
! "Alist of non-standard encoding names vs Emacs coding systems.
! This alist is used to decode an extened segment of a compound text.")
!
! (defvar ctext-non-standard-encodings-regexp
! (string-to-multibyte
! (concat
! ;; For non-standard encodings.
! "\\(\e%/[0-4][\200-\377][\200-\377]\\([^\002]+\\)\002\\)"
! "\\|"
! ;; For UTF-8 encoding.
! "\\(address@hidden)")))
;; Functions to support "Non-Standard Character Set Encodings" defined
;; by the COMPOUND-TEXT spec.
! ;; We support that by decoding the whole data by `ctext' which just
! ;; pertains byte sequences belonging to ``extended segment'', then
! ;; decoding those byte sequences one by one in Lisp.
;; This function also supports "The UTF-8 encoding" described in the
;; section 7 of the documentation fo COMPOUND-TEXT distributed with
;; XFree86.
(defun ctext-post-read-conversion (len)
"Decode LEN characters encoded as Compound Text with Extended Segments."
(save-match-data
! (save-restriction
! (let ((case-fold-search nil)
! (in-workbuf (string= (buffer-name) " *code-converting-work*"))
! last-coding-system-used
! pos bytes)
! (or in-workbuf
! (narrow-to-region (point) (+ (point) len)))
! (decode-coding-region (point-min) (point-max) 'ctext)
! (if in-workbuf
! (set-buffer-multibyte t))
! (while (re-search-forward ctext-non-standard-encodings-regexp
! nil 'move)
! (setq pos (match-beginning 0))
! (if (match-beginning 1)
! ;; ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES--
! (let* ((M (char-after (+ pos 4)))
! (L (char-after (+ pos 5)))
! (encoding (match-string 2))
! (coding (or (cdr (assoc-ignore-case
! encoding
! ctext-non-standard-encodings-alist))
! (coding-system-p
! (intern (downcase encoding))))))
! (setq bytes (- (+ (* (- M 128) 128) (- L 128))
! (- (point) (+ pos 6))))
! (when coding
! (delete-region pos (point))
! (forward-char bytes)
! (decode-coding-region (- (point) bytes) (point) coding)))
! ;; ESC % G --UTF-8-BYTES-- ESC % @
! (setq bytes (- (point) pos))
! (decode-coding-region (- (point) bytes) (point) 'utf-8))))
! (goto-char (point-min))
! (- (point-max) (point)))))
!
! ;; From X registry 2001/06/01
! ;; 20. NON-STANDARD CHARACTER SET ENCODINGS
!
! ;; See Section 6 of the Compound Text standard.
!
! ;; Name Reference
! ;; ---- ---------
! ;; "DEC.CNS11643.1986-2" [53]
! ;; CNS11643 2-plane using the recommended
! ;; internal representation scheme
! ;; "DEC.DTSCS.1990-2" [54]
! ;; DEC Taiwan Supplemental Character Set
! ;; "fujitsu.u90x03" [87]
! ;; "ILA" [62]
! ;; registry prefix
! ;; "IPSYS" [59]
! ;; registry prefix
! ;; "omron_UDC" [45]
! ;; omron User Defined Charset
! ;; "omron_UDC_ja" [45]
! ;; omron User Defined Charset for Japanese
! ;; "omron_UDC_zh" [45]
! ;; omron User Defined Charset for Chinese(Main land)
! ;; "omron_UDC_tw" [45]
! ;; omron User Defined Charset for Chinese(Taiwan)
;; If you add charsets here, be sure to modify the regexp used by
;; ctext-pre-write-conversion to look up non-standard charsets.
! (defvar ctext-non-standard-designations-alist
'(("$(0" . (big5 "big5-0" 2))
("$(1" . (big5 "big5-0" 2))
;; The following are actually standard; generating extended
***************
*** 1451,1494 ****
"Encode characters between FROM and TO as Compound Text w/Extended Segments.
If FROM is a string, or if the current buffer is not the one set up for us
! by run_pre_post_conversion_on_str, generate a new temp buffer, insert the
text, and convert it in the temporary buffer. Otherwise, convert in-place."
- (cond ((and (string= (buffer-name) " *code-converting-work*")
- (not (stringp from)))
- ; Minimize consing due to subsequent insertions and deletions.
- (buffer-disable-undo)
- (narrow-to-region from to))
- (t
- (let ((buf (current-buffer)))
- (set-buffer (generate-new-buffer " *temp"))
- (buffer-disable-undo)
- (if (stringp from)
- (insert from)
- (insert-buffer-substring buf from to))
- (setq from (point-min) to (point-max)))))
- (encode-coding-region from to 'ctext-no-compositions)
- ;; Replace ISO-2022 charset designations with extended segments, for
- ;; those charsets that are not part of the official X registry.
(save-match-data
! (goto-char (point-min))
! (let ((newpt (make-marker))
! (case-fold-search nil)
! pt desig encode-info encoding chset noctets textlen)
! (set-buffer-multibyte nil)
! ;; The regexp below finds the leading sequences for big5.
(while (re-search-forward "\e\\(\$([01]\\)" nil 'move)
! (setq desig (match-string 1)
! pt (point-marker)
! encode-info (cdr (assoc desig non-standard-designations-alist))
encoding (car encode-info)
chset (cadr encode-info)
noctets (car (cddr encode-info)))
(skip-chars-forward "^\e")
- (set-marker newpt (point))
(cond
((eq encoding t) ; only the leading sequence needs to be changed
! (setq textlen (+ (- newpt pt) (length chset) 1))
! ;; Generate the ICCCM control sequence for an extended segment.
(replace-match (format "\e%%/%d%c%c%s"
noctets
(+ (/ textlen 128) 128)
--- 1455,1501 ----
"Encode characters between FROM and TO as Compound Text w/Extended Segments.
If FROM is a string, or if the current buffer is not the one set up for us
! by encode-coding-string, generate a new temp buffer, insert the
text, and convert it in the temporary buffer. Otherwise, convert in-place."
(save-match-data
! ;; Setup a working buffer if necessary.
! (cond ((stringp from)
! (let ((buf (current-buffer)))
! (set-buffer (generate-new-buffer " *temp"))
! (set-buffer-multibyte (multibyte-string-p from))
! (insert from)))
! ((not (string= (buffer-name) " *code-converting-work*"))
! (let ((buf (current-buffer))
! (multibyte enable-multibyte-characters))
! (set-buffer (generate-new-buffer " *temp"))
! (set-buffer-multibyte multibyte)
! (insert-buffer-substring buf from to))))
!
! ;; Now we can encode the whole buffer.
! (let ((case-fold-search nil)
! last-coding-system-used
! pos posend desig encode-info encoding chset noctets textlen)
! (goto-char (point-min))
! ;; At first encode the whole buffer.
! (encode-coding-region (point-min) (point-max) 'ctext-no-compositions)
! ;; Then replace ISO-2022 charset designations with extended
! ;; segments, for those charsets that are not part of the
! ;; official X registry. The regexp below finds the leading
! ;; sequences for big5.
(while (re-search-forward "\e\\(\$([01]\\)" nil 'move)
! (setq pos (match-beginning 0)
! posend (point)
! desig (match-string 1)
! encode-info (cdr (assoc desig
! ctext-non-standard-designations-alist))
encoding (car encode-info)
chset (cadr encode-info)
noctets (car (cddr encode-info)))
(skip-chars-forward "^\e")
(cond
((eq encoding t) ; only the leading sequence needs to be changed
! (setq textlen (+ (- (point) posend) (length chset) 1))
! ;; Generate the control sequence for an extended segment.
(replace-match (format "\e%%/%d%c%c%s"
noctets
(+ (/ textlen 128) 128)
***************
*** 1496,1515 ****
chset)
t t))
((coding-system-p encoding) ; need to recode the entire segment...
! (set-marker pt (match-beginning 0))
! (decode-coding-region pt newpt 'ctext-no-compositions)
! (set-buffer-multibyte t)
! (encode-coding-region pt newpt encoding)
! (set-buffer-multibyte nil)
! (setq textlen (+ (- newpt pt) (length chset) 1))
! (goto-char pt)
! (insert (format "\e%%/%d%c%c%s"
! noctets
! (+ (/ textlen 128) 128)
! (+ (% textlen 128) 128)
! chset))))
! (goto-char newpt))))
! (set-buffer-multibyte t)
;; Must return nil, as build_annotations_2 expects that.
nil)
--- 1503,1519 ----
chset)
t t))
((coding-system-p encoding) ; need to recode the entire segment...
! (decode-coding-region pos (point) 'ctext-no-compositions)
! (encode-coding-region pos (point) encoding)
! (setq textlen (+ (- (point) pos) (length chset) 1))
! (save-excursion
! (goto-char pos)
! (insert (format "\e%%/%d%c%c%s"
! noctets
! (+ (/ textlen 128) 128)
! (+ (% textlen 128) 128)
! chset))))))
! (goto-char (point-min))))
;; Must return nil, as build_annotations_2 expects that.
nil)
***************
*** 1550,1563 ****
sgml-html-meta-auto-coding-function)
"A list of functions which attempt to determine a coding system.
! Each function in this list should be written to operate on the current
! buffer, but should not modify it in any way. It should take one
! argument SIZE, past which it should not search. If a function
! succeeds in determining a coding system, it should return that coding
! system. Otherwise, it should return nil.
! Any `coding:' tags present have a higher priority than the
! functions in this list."
:group 'files
:group 'mule
:type '(repeat function))
--- 1554,1571 ----
sgml-html-meta-auto-coding-function)
"A list of functions which attempt to determine a coding system.
! Each function in this list should be written to operate on the
! current buffer, but should not modify it in any way. The buffer
! will contain undecoded text of parts of the file. Each function
! should take one argument, SIZE, which says how many
! characters (starting from point) it should look at.
!
! If one of these functions succeeds in determining a coding
! system, it should return that coding system. Otherwise, it
! should return nil.
! If a file has a `coding:' tag, that takes precedence over these
! functions, so they won't be called at all."
:group 'files
:group 'mule
:type '(repeat function))
***************
*** 1696,1703 ****
(setq set-auto-coding-function 'set-auto-coding)
! (defun after-insert-file-set-buffer-file-coding-system (inserted)
! "Set `buffer-file-coding-system' of current buffer after text is inserted."
(if last-coding-system-used
(let ((coding-system
(find-new-buffer-file-coding-system last-coding-system-used))
--- 1704,1715 ----
(setq set-auto-coding-function 'set-auto-coding)
! (defun after-insert-file-set-coding (inserted)
! "Set `buffer-file-coding-system' of current buffer after text is inserted.
! INSERTED is the number of characters that were inserted, as figured
! in the situation before this function. Return the number of characters
! inserted, as figured in the situation after. The two numbers can be
! different if the buffer has become unibyte."
(if last-coding-system-used
(let ((coding-system
(find-new-buffer-file-coding-system last-coding-system-used))
***************
*** 1713,1727 ****
(= (buffer-size) inserted))
;; For coding systems no-conversion and raw-text...,
;; edit the buffer as unibyte.
! (let ((pos-byte (position-bytes (+ (point) inserted))))
(set-buffer-multibyte nil)
! (setq inserted (- pos-byte (position-bytes (point))))))
(set-buffer-modified-p modified-p))))
inserted)
- (add-hook 'after-insert-file-functions
- 'after-insert-file-set-buffer-file-coding-system)
-
;; The coding-spec and eol-type of coding-system returned is decided
;; independently in the following order.
;; 1. That of buffer-file-coding-system locally bound.
--- 1725,1736 ----
(= (buffer-size) inserted))
;; For coding systems no-conversion and raw-text...,
;; edit the buffer as unibyte.
! (let ((pos-marker (copy-marker (+ (point) inserted))))
(set-buffer-multibyte nil)
! (setq inserted (- pos-marker (point)))))
(set-buffer-modified-p modified-p))))
inserted)
;; The coding-spec and eol-type of coding-system returned is decided
;; independently in the following order.
;; 1. That of buffer-file-coding-system locally bound.
***************
*** 1851,1859 ****
(setq coding (funcall set-auto-coding-function
filename (- (point-max) (point-min)))))
(or coding
! (setq coding (find-operation-coding-system
! 'insert-file-contents
! filename visit beg end replace)))
(if (coding-system-p coding)
(or enable-multibyte-characters
(setq coding
--- 1860,1868 ----
(setq coding (funcall set-auto-coding-function
filename (- (point-max) (point-min)))))
(or coding
! (setq coding (car (find-operation-coding-system
! 'insert-file-contents
! filename visit beg end replace))))
(if (coding-system-p coding)
(or enable-multibyte-characters
(setq coding
***************
*** 2045,2051 ****
(defun sgml-xml-auto-coding-function (size)
"Determine whether the buffer is XML, and if so, its encoding.
This function is intended to be added to `auto-coding-functions'."
! (when (re-search-forward "\\`[[:space:]\n]*<\\?xml" nil t)
(let ((end (save-excursion
;; This is a hack.
(re-search-forward "\"\\s-*\\?>" size t))))
--- 2054,2061 ----
(defun sgml-xml-auto-coding-function (size)
"Determine whether the buffer is XML, and if so, its encoding.
This function is intended to be added to `auto-coding-functions'."
! (setq size (+ (point) size))
! (when (re-search-forward "\\`[[:space:]\n]*<\\?xml" size t)
(let ((end (save-excursion
;; This is a hack.
(re-search-forward "\"\\s-*\\?>" size t))))
***************
*** 2062,2068 ****
(defun sgml-html-meta-auto-coding-function (size)
"If the buffer has an HTML meta tag, use it to determine encoding.
This function is intended to be added to `auto-coding-functions'."
! (setq size (min size
;; Only search forward 10 lines
(save-excursion
(forward-line 10)
--- 2072,2078 ----
(defun sgml-html-meta-auto-coding-function (size)
"If the buffer has an HTML meta tag, use it to determine encoding.
This function is intended to be added to `auto-coding-functions'."
! (setq size (min (+ (point) size)
;; Only search forward 10 lines
(save-excursion
(forward-line 10)
***************
*** 2079,2082 ****
--- 2089,2093 ----
;;;
(provide 'mule)
+ ;;; arch-tag: 9aebaa6e-0e8a-40a9-b857-cb5d04a39e7c
;;; mule.el ends here
| [Prev in Thread] |
Current Thread |
[Next in Thread] |
- [Emacs-diffs] Changes to emacs/lisp/international/mule.el [lexbind],
Miles Bader <=