;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
;; Licensed to the Free Software Foundation.
+;; Copyright (C) 2001, 2002 Free Software Foundation, Inc.
;; Keywords: mule, multilingual, character set, coding system
;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
;; Boston, MA 02111-1307, USA.
+;;; Commentary:
+
;;; Code:
-(defconst mule-version "5.0 (AOI)" "\
+(defconst mule-version "5.0 (SAKAKI)" "\
Version number and name of this version of MULE (multilingual environment).")
(defconst mule-version-date "1999.12.7" "\
;; API (Application Program Interface) for charsets.
-;; Return t if OBJ is a quoted symbol
-;; and the symbol is the name of a standard charset.
(defsubst charset-quoted-standard-p (obj)
+ "Return t if OBJ is a quoted symbol, and is the name of a standard charset."
(and (listp obj) (eq (car obj) 'quote)
(symbolp (car-safe (cdr obj)))
(let ((vector (get (car-safe (cdr obj)) 'charset)))
LEADING-CODE-EXT (integer) is the extended leading-code for the
charset. All charsets of less than 0xA0 has the value 0.
ISO-FINAL-CHAR (character) is the final character of the
- corresponding ISO 2022 charset.
+ corresponding ISO 2022 charset. If the charset is not assigned
+ any final character, the value is -1.
ISO-GRAPHIC-PLANE (integer) is the graphic plane to be invoked
while encoding to variants of ISO 2022 coding system, one of the
following: 0/graphic-plane-left(GL), 1/graphic-plane-right(GR).
+ If the charset is not assigned any final character, the value is -1.
REVERSE-CHARSET (integer) is the charset which differs only in
LEFT-TO-RIGHT value from the charset. If there's no such a
charset, the value is -1.
"Set CHARSET's property list to PLIST, and return PLIST."
(aset (charset-info charset) 14 plist))
-(defun make-char (charset &optional c1 c2)
- "Return a character of CHARSET and position codes CODE1 and CODE2.
+(defun make-char (charset &optional code1 code2)
+ "Return a character of CHARSET whose position codes are CODE1 and CODE2.
CODE1 and CODE2 are optional, but if you don't supply
sufficient position codes, return a generic character which stands for
all characters or group of characters in the character set.
-A generic character can be used to index a char table (e.g. syntax-table)."
- (make-char-internal (charset-id charset) c1 c2))
+A generic character can be used to index a char table (e.g. syntax-table).
+
+Such character sets as ascii, eight-bit-control, and eight-bit-graphic
+don't have corresponding generic characters. If CHARSET is one of
+them and you don't supply CODE1, return the character of the smallest
+code in CHARSET.
+
+If CODE1 or CODE2 are invalid (out of range), this function signals an
+error. However, the eighth bit of both CODE1 and CODE2 is zeroed
+before they are used to index CHARSET. Thus you may use, say, the
+actual ISO 8859 character code rather than subtracting 128, as you
+would need to index the corresponding Emacs charset."
+ (make-char-internal (charset-id charset) code1 code2))
(put 'make-char 'byte-compile
- (function
+ (function
(lambda (form)
(let ((charset (nth 1 form)))
(if (charset-quoted-standard-p charset)
(defsubst generic-char-p (char)
"Return t if and only if CHAR is a generic character.
-See also the documentation of make-char."
+See also the documentation of `make-char'."
(and (>= char 0400)
(let ((l (split-char char)))
(and (or (= (nth 1 l) 0) (eq (nth 2 l) 0))
(not (eq (car l) 'composition))))))
+(defun decode-char (ccs code-point &optional restriction)
+ "Return character specified by coded character set CCS and CODE-POINT in it.
+Return nil if such a character is not supported.
+Currently the only supported coded character set is `ucs' (ISO/IEC
+10646: Universal Multi-Octet Coded Character Set), and the result is
+translated through the char table `utf-8-translation-table-for-decode'.
+
+Optional argument RESTRICTION specifies a way to map the pair of CCS
+and CODE-POINT to a character. Currently not supported and just ignored."
+ (cond
+ ((eq ccs 'ucs)
+ (let ((c (cond
+ ((< code-point 160)
+ code-point)
+ ((< code-point 256)
+ (make-char 'latin-iso8859-1 code-point))
+ ((< code-point #x2500)
+ (setq code-point (- code-point #x0100))
+ (make-char 'mule-unicode-0100-24ff
+ (+ (/ code-point 96) 32) (+ (% code-point 96) 32)))
+ ((< code-point #x3400)
+ (setq code-point (- code-point #x2500))
+ (make-char 'mule-unicode-2500-33ff
+ (+ (/ code-point 96) 32) (+ (% code-point 96) 32)))
+ ((and (>= code-point #xe000) (< code-point #x10000))
+ (setq code-point (- code-point #xe000))
+ (make-char 'mule-unicode-e000-ffff
+ (+ (/ code-point 96) 32) (+ (% code-point 96) 32))))))
+ (if (and c (aref utf-8-translation-table-for-decode c))
+ (aref utf-8-translation-table-for-decode c)
+ c)))))
+
+(defun encode-char (char ccs &optional restriction)
+ "Return code-point in coded character set CCS that corresponds to CHAR.
+Return nil if CHAR is not included in CCS.
+Currently the only supported coded character set is `ucs' (ISO/IEC
+10646: Universal Multi-Octet Coded Character Set), and CHAR is first
+translated through the char-table `ucs-mule-to-mule-unicode'.
+
+CHAR should be in one of these charsets:
+ ascii, latin-iso8859-1, mule-unicode-0100-24ff, mule-unicode-2500-33ff,
+ mule-unicode-e000-ffff, eight-bit-control
+Otherwise, return nil.
+
+Optional argument RESTRICTION specifies a way to map CHAR to a
+code-point in CCS. Currently not supported and just ignored."
+ (let* ((split (split-char char))
+ (charset (car split))
+ trans)
+ (cond ((eq ccs 'ucs)
+ (setq trans (aref ucs-mule-to-mule-unicode char))
+ (if trans
+ (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)
+ (+ #x0100 (+ (* (- (nth 1 split) 32) 96)
+ (- (nth 2 split) 32))))
+ ((eq charset 'mule-unicode-2500-33ff)
+ (+ #x2500 (+ (* (- (nth 1 split) 32) 96)
+ (- (nth 2 split) 32))))
+ ((eq charset 'mule-unicode-e000-ffff)
+ (+ #xe000 (+ (* (- (nth 1 split) 32) 96)
+ (- (nth 2 split) 32))))
+ ((eq charset 'eight-bit-control)
+ char))))))
+
\f
-;; Coding system staffs
+;; Coding system stuff
;; Coding system is a symbol that has the property `coding-system'.
;;
;; following format:
;; [TYPE MNEMONIC DOC-STRING PLIST FLAGS]
;; We call this vector as coding-spec. See comments in src/coding.c
-;; for more detail.
+;; for more detail.
(defconst coding-spec-type-idx 0)
(defconst coding-spec-mnemonic-idx 1)
;; o coding-category
;;
;; The value is a coding category the coding system belongs to. The
-;; function `make-coding-system' sets this value automatically
+;; function `make-coding-system' sets this value automatically
;; unless its argument PROPERTIES specifies this property.
;;
;; o alias-coding-systems
;; `base coding system'. The function `make-coding-system' sets this
;; value automatically and `define-coding-system-alias' updates it.
;;
-;; o post-read-conversion
-;;
-;; The value is a function to call after some text is inserted and
-;; decoded by the coding system itself and before any functions in
-;; `after-insert-functions' are called. The arguments to this
-;; function is the same as those of a function in
-;; `after-insert-functions', i.e. LENGTH of a text while putting point
-;; at the head of the text to be decoded
+;; See the documentation of make-coding-system for the meanings of the
+;; following properties.
;;
+;; o post-read-conversion
;; o pre-write-conversion
-;;
-;; The value is a function to call after all functions in
-;; `write-region-annotate-functions' and `buffer-file-format' are
-;; called, and before the text is encoded by the coding system itself.
-;; The arguments to this function is the same as those of a function
-;; in `write-region-annotate-functions', i.e. FROM and TO specifying
-;; region of a text.
-;;
;; o translation-table-for-decode
-;;
-;; The value is a translation table to be applied on decoding. See
-;; the function `make-translation-table' for the format of translation
-;; table.
-;;
;; o translation-table-for-encode
-;;
-;; The value is a translation table to be applied on encoding.
-;;
+;; o safe-chars
;; o safe-charsets
-;;
-;; The value is a list of charsets safely supported by the coding
-;; system. The value t means that all charsets Emacs handles are
-;; supported. Even if some charset is not in this list, it doesn't
-;; mean that the charset can't be encoded in the coding system,
-;; instead, it just means that some other receiver of a text encoded
-;; in the coding system won't be able to handle that charset.
-;;
;; o mime-charset
-;;
-;; The value is a symbol of which name is `MIME-charset' parameter of
-;; the coding system.
-;;
-;; o charset-origin-alist
-;;
-;; The value is a list of this form:
-;; (CHARSET EXTERNAL-CHARSET-NAME ENCODING-FUNCTION).
-;; ENCODING-FUNCTION is a function to encode a character in CHARSET
-;; to the code in EXTERNAL-CHARSET-NAME. The command what-cursor-position
-;; uses this information of the buffer-file-coding-system.
-;; ENCODING-FUNCTION may be a translation table or a symbol whose
-;; property `translation-table' is a translation table. In these case,
-;; the translation table is used to encode the character.
-;;
;; 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
-;; file. Each element of the list is an integer or a cons of integer.
-;; In the former case, the integer value is a valid byte code. In the
-;; latter case, the integers specifies the range of valid byte codes.
-;; Return coding-spec of CODING-SYSTEM
(defsubst coding-system-spec (coding-system)
+ "Return coding-spec of CODING-SYSTEM."
(get (check-coding-system coding-system) 'coding-system))
(defun coding-system-type (coding-system)
(list prop val)))))
(defun coding-system-category (coding-system)
- "Return the coding category of CODING-SYSTEM."
+ "Return the coding category of CODING-SYSTEM.
+See also `coding-category-list'."
(coding-system-get coding-system 'coding-category))
(defun coding-system-base (coding-system)
(and (not (> (downcase c1) (downcase c2)))
(< c1 c2)))))))
-;; Add CODING-SYSTEM to coding-system-list while keeping it sorted.
(defun add-to-coding-system-list (coding-system)
+ "Add CODING-SYSTEM to `coding-system-list' while keeping it sorted."
(if (or (null coding-system-list)
(coding-system-lessp coding-system (car coding-system-list)))
(setq coding-system-list (cons coding-system coding-system-list))
(setcdr tem (cons coding-system (cdr tem))))))
(defun coding-system-list (&optional base-only)
- "Return a list of all existing coding systems.
-If optional arg BASE-ONLY is non-nil, only base coding systems are listed."
+ "Return a list of all existing non-subsidiary coding systems.
+If optional arg BASE-ONLY is non-nil, only base coding systems are listed.
+The value doesn't include subsidiary coding systems which are what
+made from bases and aliases automatically for various end-of-line
+formats (e.g. iso-latin-1-unix, koi8-r-dos)."
(let* ((codings (copy-sequence coding-system-list))
(tail (cons nil codings)))
;; Remove subsidiary coding systems (eol variants) and alias
(setq tail (cdr tail)))))
codings))
-;; Make subsidiary coding systems (eol-type variants) of CODING-SYSTEM.
+(defun map-charset-chars (func charset)
+ "Use FUNC to map over all characters in CHARSET for side effects.
+FUNC is a function of two args, the start and end (inclusive) of a
+character code range. Thus FUNC should iterate over [START, END]."
+ (let* ((dim (charset-dimension charset))
+ (chars (charset-chars charset))
+ (start (if (= chars 94)
+ 33
+ 32)))
+ (if (= dim 1)
+ (funcall func
+ (make-char charset start)
+ (make-char charset (+ start chars -1)))
+ (dotimes (i chars)
+ (funcall func
+ (make-char charset (+ i start) start)
+ (make-char charset (+ i start) (+ start chars -1)))))))
+
+(defun register-char-codings (coding-system safe-chars)
+ "Add entries for CODING-SYSTEM to `char-coding-system-table'.
+If SAFE-CHARS is a char-table, its non-nil entries specify characters
+which CODING-SYSTEM encodes safely. If SAFE-CHARS is t, register
+CODING-SYSTEM as a general one which can encode all characters."
+ (let ((general (char-table-extra-slot char-coding-system-table 0))
+ ;; Charsets which have some members in the table, but not all
+ ;; of them (i.e. not just a generic character):
+ (partials (char-table-extra-slot char-coding-system-table 1)))
+ (if (eq safe-chars t)
+ (or (memq coding-system general)
+ (set-char-table-extra-slot char-coding-system-table 0
+ (cons coding-system general)))
+ (map-char-table
+ (lambda (key val)
+ (if (and (>= key 128) val)
+ (let ((codings (aref char-coding-system-table key))
+ (charset (char-charset key)))
+ (unless (memq coding-system codings)
+ (if (and (generic-char-p key)
+ (memq charset partials))
+ ;; The generic char would clobber individual
+ ;; entries already in the table. First save the
+ ;; separate existing entries for all chars of the
+ ;; charset (with the generic entry added, if
+ ;; necessary).
+ (let (entry existing)
+ (map-charset-chars
+ (lambda (start end)
+ (while (<= start end)
+ (setq entry (aref char-coding-system-table start))
+ (when entry
+ (push (cons
+ start
+ (if (memq coding-system entry)
+ entry
+ (cons coding-system entry)))
+ existing))
+ (setq start (1+ start))))
+ charset)
+ ;; Update the generic entry.
+ (aset char-coding-system-table key
+ (cons coding-system codings))
+ ;; Override with the saved entries.
+ (dolist (elt existing)
+ (aset char-coding-system-table (car elt) (cdr elt))))
+ (aset char-coding-system-table key
+ (cons coding-system codings))
+ (unless (or (memq charset partials)
+ (generic-char-p key))
+ (push charset partials)))))))
+ safe-chars)
+ (set-char-table-extra-slot char-coding-system-table 1 partials))))
+
+
(defun make-subsidiary-coding-system (coding-system)
+ "Make subsidiary coding systems (eol-type variants) of CODING-SYSTEM."
(let ((coding-spec (coding-system-spec coding-system))
(subsidiaries (vector (intern (format "%s-unix" coding-system))
(intern (format "%s-dos" coding-system))
(setq i (1+ i)))
subsidiaries))
+(defun transform-make-coding-system-args (name type &optional doc-string props)
+ "For internal use only.
+Transform XEmacs style args for `make-coding-system' to Emacs style.
+Value is a list of transformed arguments."
+ (let ((mnemonic (string-to-char (or (plist-get props 'mnemonic) "?")))
+ (eol-type (plist-get props 'eol-type))
+ properties tmp)
+ (cond
+ ((eq eol-type 'lf) (setq eol-type 'unix))
+ ((eq eol-type 'crlf) (setq eol-type 'dos))
+ ((eq eol-type 'cr) (setq eol-type 'mac)))
+ (if (setq tmp (plist-get props 'post-read-conversion))
+ (setq properties (plist-put properties 'post-read-conversion tmp)))
+ (if (setq tmp (plist-get props 'pre-write-conversion))
+ (setq properties (plist-put properties 'pre-write-conversion tmp)))
+ (cond
+ ((eq type 'shift-jis)
+ `(,name 1 ,mnemonic ,doc-string () ,properties ,eol-type))
+ ((eq type 'iso2022) ; This is not perfect.
+ (if (plist-get props 'escape-quoted)
+ (error "escape-quoted is not supported: %S"
+ `(,name ,type ,doc-string ,props)))
+ (let ((g0 (plist-get props 'charset-g0))
+ (g1 (plist-get props 'charset-g1))
+ (g2 (plist-get props 'charset-g2))
+ (g3 (plist-get props 'charset-g3))
+ (use-roman
+ (and
+ (eq (cadr (assoc 'latin-jisx0201
+ (plist-get props 'input-charset-conversion)))
+ 'ascii)
+ (eq (cadr (assoc 'ascii
+ (plist-get props 'output-charset-conversion)))
+ 'latin-jisx0201)))
+ (use-oldjis
+ (and
+ (eq (cadr (assoc 'japanese-jisx0208-1978
+ (plist-get props 'input-charset-conversion)))
+ 'japanese-jisx0208)
+ (eq (cadr (assoc 'japanese-jisx0208
+ (plist-get props 'output-charset-conversion)))
+ 'japanese-jisx0208-1978))))
+ (if (charsetp g0)
+ (if (plist-get props 'force-g0-on-output)
+ (setq g0 `(nil ,g0))
+ (setq g0 `(,g0 t))))
+ (if (charsetp g1)
+ (if (plist-get props 'force-g1-on-output)
+ (setq g1 `(nil ,g1))
+ (setq g1 `(,g1 t))))
+ (if (charsetp g2)
+ (if (plist-get props 'force-g2-on-output)
+ (setq g2 `(nil ,g2))
+ (setq g2 `(,g2 t))))
+ (if (charsetp g3)
+ (if (plist-get props 'force-g3-on-output)
+ (setq g3 `(nil ,g3))
+ (setq g3 `(,g3 t))))
+ `(,name 2 ,mnemonic ,doc-string
+ (,g0 ,g1 ,g2 ,g3
+ ,(plist-get props 'short)
+ ,(not (plist-get props 'no-ascii-eol))
+ ,(not (plist-get props 'no-ascii-cntl))
+ ,(plist-get props 'seven)
+ t
+ ,(not (plist-get props 'lock-shift))
+ ,use-roman
+ ,use-oldjis
+ ,(plist-get props 'no-iso6429)
+ nil nil nil nil)
+ ,properties ,eol-type)))
+ ((eq type 'big5)
+ `(,name 3 ,mnemonic ,doc-string () ,properties ,eol-type))
+ ((eq type 'ccl)
+ `(,name 4 ,mnemonic ,doc-string
+ (,(plist-get props 'decode) . ,(plist-get props 'encode))
+ ,properties ,eol-type))
+ (t
+ (error "unsupported XEmacs style make-coding-style arguments: %S"
+ `(,name ,type ,doc-string ,props))))))
+
(defun make-coding-system (coding-system type mnemonic doc-string
&optional
flags
properties
eol-type)
"Define a new coding system CODING-SYSTEM (symbol).
-Remaining arguments are TYPE, MNEMONIC, DOC-STRING, FLAGS (optional),
+Remaining arguments are TYPE, MNEMONIC, DOC-STRING, FLAGS (optional),
and PROPERTIES (optional) which construct a coding-spec of CODING-SYSTEM
in the following format:
[TYPE MNEMONIC DOC-STRING PLIST FLAGS]
TYPE is an integer value indicating the type of the coding system as follows:
0: Emacs internal format,
- 1: Shift-JIS (or MS-Kanji) used mainly on Japanese PC,
+ 1: Shift-JIS (or MS-Kanji) used mainly on Japanese PCs,
2: ISO-2022 including many variants,
- 3: Big5 used mainly on Chinese PC,
+ 3: Big5 used mainly on Chinese PCs,
4: private, CCL programs provide encoding/decoding algorithm,
- 5: Raw-text, which means that text contains random 8-bit codes.
+ 5: Raw-text, which means that text contains random 8-bit codes.
MNEMONIC is a character to be displayed on mode line for the coding system.
DESIGNATION-BOL non-nil means designation sequences should be placed
at beginning of line on output.
SAFE non-nil means convert unsafe characters to `?' on output.
- Unsafe characters are what not specified in SAFE-CHARSET.
+ Characters not specified in the property `safe-charsets' nor
+ `safe-chars' are unsafe.
ACCEPT-LATIN-EXTRA-CODE non-nil means code-detection routine accepts
a code specified in `latin-extra-code-table' (which see) as a valid
code of the coding system.
decoding and encoding. CCL programs should be specified by their
symbols.
-PROPERTIES is an alist of properties vs the corresponding values.
+PROPERTIES is an alist of properties vs the corresponding values. The
+following properties are recognized:
+
+ o post-read-conversion
+
+ The value is a function to call after some text is inserted and
+ decoded by the coding system itself and before any functions in
+ `after-insert-functions' are called. The argument of this
+ function is the same as for a function in
+ `after-insert-file-functions', i.e. LENGTH of the text inserted,
+ with point at the head of the text to be decoded.
+
+ o pre-write-conversion
+
+ The value is a function to call after all functions in
+ `write-region-annotate-functions' and `buffer-file-format' are
+ called, and before the text is encoded by the coding system itself.
+ The arguments to this function are the same as those of a function
+ in `write-region-annotate-functions', i.e. FROM and TO, specifying
+ a region of text.
+
+ o translation-table-for-decode
+
+ The value is a translation table to be applied on decoding. See
+ the function `make-translation-table' for the format of translation
+ table. This is not applicable to type 4 (CCL-based) coding systems.
+
+ o translation-table-for-encode
+
+ The value is a translation table to be applied on encoding. This is
+ not applicable to type 4 (CCL-based) coding systems.
+
+ o safe-chars
+
+ The value is a char table. If a character has non-nil value in it,
+ the character is safely supported by the coding system. This
+ overrides the specification of safe-charsets.
+
+ o safe-charsets
+
+ The value is a list of charsets safely supported by the coding
+ system. The value t means that all charsets Emacs handles are
+ supported. Even if some charset is not in this list, it doesn't
+ mean that the charset can't be encoded in the coding system;
+ it just means that some other receiver of text encoded
+ in the coding system won't be able to handle that charset.
+
+ o mime-charset
+
+ The value is a symbol whose name is the `MIME-charset' parameter of
+ the coding system.
+
+ 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
+ file. Each element of the list is an integer or a cons of integer.
+ In the former case, the integer value is a valid byte code. In the
+ latter case, the integers specify the range of valid byte codes.
+
These properties are set in PLIST, a property list. This function
also sets properties `coding-category' and `alias-coding-systems'
automatically.
The EOL type is detected automatically for the coding system.
And, according to the detected EOL type, one of the coding
systems in the vector is selected. Elements of the vector
- corresponds to Unix-liek EOL, DOS-like EOL, and Mac-like EOL
+ corresponds to Unix-like EOL, DOS-like EOL, and Mac-like EOL
in this order.
Kludgy features for backward compatibility:
2. If PROPERTIES is just a list of character sets, the list is set as
a value of `safe-charsets' in PLIST."
+
+ ;; For compatiblity with XEmacs, we check the type of TYPE. If it
+ ;; is a symbol, perhaps, this function is called with XEmacs-style
+ ;; arguments. Here, try to transform that kind of arguments to
+ ;; Emacs style.
+ (if (symbolp type)
+ (let ((args (transform-make-coding-system-args coding-system type
+ mnemonic doc-string)))
+ (setq coding-system (car args)
+ type (nth 1 args)
+ mnemonic (nth 2 args)
+ doc-string (nth 3 args)
+ flags (nth 4 args)
+ properties (nth 5 args)
+ eol-type (nth 6 args))))
+
;; Set a value of `coding-system' property.
(let ((coding-spec (make-vector 5 nil))
(no-initial-designation t)
(no-alternative-designation t)
+ (accept-latin-extra-code nil)
coding-category)
(if (or (not (integerp type)) (< type 0) (> type 5))
(error "TYPE argument must be 0..5"))
(if (or (not (integerp mnemonic)) (<= mnemonic ? ) (> mnemonic 127))
- (error "MNEMONIC argument must be an ASCII printable character."))
+ (error "MNEMONIC argument must be an ASCII printable character"))
(aset coding-spec coding-spec-type-idx type)
(aset coding-spec coding-spec-mnemonic-idx mnemonic)
(aset coding-spec coding-spec-doc-string-idx
(setq fl (cdr fl) i (1+ i)))
(while (and (< i 32) fl)
(aset vec i (car fl))
+ (if (and (= i 16) ; ACCEPT-LATIN-EXTRA-CODE
+ (car fl))
+ (setq accept-latin-extra-code t))
(setq fl (cdr fl) i (1+ i)))
(aset coding-spec 4 vec)
(setq coding-category
(not (consp (car properties)))))
;; In the old version, the arg PROPERTIES is a list to be
;; set in PLIST as a value of property `safe-charsets'.
- (plist-put plist 'safe-charsets properties)
- ;; In the current version PROPERTIES is a property list.
- ;; Reflect it into PLIST one by one.
- (let ((l properties))
- (while l
- (plist-put plist (car (car l)) (cdr (car l)))
- (setq l (cdr l)))))
+ (setq properties (list (cons 'safe-charsets properties))))
+ ;; In the current version PROPERTIES is a property list.
+ ;; Reflect it into PLIST one by one while handling safe-chars
+ ;; specially.
+ (let ((safe-charsets (cdr (assq 'safe-charsets properties)))
+ (safe-chars (cdr (assq 'safe-chars properties)))
+ (l properties)
+ prop val)
+ ;; If only safe-charsets is specified, make a char-table from
+ ;; it, and store that char-table as the value of `safe-chars'.
+ (if (and (not safe-chars) safe-charsets)
+ (let (charset)
+ (if (eq safe-charsets t)
+ (setq safe-chars t)
+ (setq safe-chars (make-char-table 'safe-chars))
+ (while safe-charsets
+ (setq charset (car safe-charsets)
+ safe-charsets (cdr safe-charsets))
+ (cond ((eq charset 'ascii)) ; just ignore
+ ((eq charset 'eight-bit-control)
+ (let ((i 128))
+ (while (< i 160)
+ (aset safe-chars i t)
+ (setq i (1+ i)))))
+ ((eq charset 'eight-bit-graphic)
+ (let ((i 160))
+ (while (< i 256)
+ (aset safe-chars i t)
+ (setq i (1+ i)))))
+ (t
+ (aset safe-chars (make-char charset) t))))
+ (if accept-latin-extra-code
+ (let ((i 128))
+ (while (< i 160)
+ (if (aref latin-extra-code-table i)
+ (aset safe-chars i t))
+ (setq i (1+ i))))))
+ (setq l (cons (cons 'safe-chars safe-chars) l))))
+ (while l
+ (setq prop (car (car l)) val (cdr (car l)) l (cdr l))
+ (if (eq prop 'safe-chars)
+ (progn
+ (if (and (symbolp val)
+ (get val 'translation-table))
+ (setq safe-chars (get val 'translation-table)))
+ (register-char-codings coding-system safe-chars)
+ (setq val safe-chars)))
+ (plist-put plist prop val)))
;; The property `coding-category' may have been set differently
;; through PROPERTIES.
(setq coding-category (plist-get plist 'coding-category))
(cons coding-system (get coding-category 'coding-systems))))
;; Next, set a value of `eol-type' property.
- (if (and (not eol-type)
- (or (<= type 3) (= type 5)))
+ (if (not eol-type)
;; If EOL-TYPE is nil, set a vector of subsidiary coding
;; systems, each corresponds to a coding system for the detected
;; EOL format.
(if (or (eq coding-category 'coding-category-iso-8-1)
(eq coding-category 'coding-category-iso-8-2))
(let ((esc (intern (concat (symbol-name coding-system) "-with-esc")))
- (doc (format "Same as %s but can handle any charsets by ISO's escape sequences." coding-system)))
+ (doc (format "Same as %s but can handle any charsets by ISO's escape sequences." coding-system))
+ (safe-charsets (assq 'safe-charsets properties))
+ (mime-charset (assq 'mime-charset properties)))
+ (if safe-charsets
+ (setcdr safe-charsets t)
+ (setq properties (cons (cons 'safe-charsets t) properties)))
+ (if mime-charset
+ (setcdr mime-charset nil))
(make-coding-system esc type mnemonic doc
(if (listp (car flags))
(cons (append (car flags) '(t)) (cdr flags))
(cons (list (car flags) t) (cdr flags)))
- properties)
- (coding-system-put esc 'mime-charset nil)
- (coding-system-put esc 'safe-charsets t))))
+ properties))))
coding-system)
(defun define-coding-system-alias (alias coding-system)
"Define ALIAS as an alias for coding system CODING-SYSTEM."
(put alias 'coding-system (coding-system-spec coding-system))
- (nconc (coding-system-get alias 'alias-coding-systems) (list alias))
(add-to-coding-system-list alias)
(setq coding-system-alist (cons (list (symbol-name alias))
coding-system-alist))
(let ((eol-type (coding-system-eol-type coding-system)))
(if (vectorp eol-type)
- (put alias 'eol-type (make-subsidiary-coding-system alias))
+ (progn
+ (nconc (coding-system-get alias 'alias-coding-systems) (list alias))
+ (put alias 'eol-type (make-subsidiary-coding-system alias)))
(put alias 'eol-type eol-type))))
(defun set-buffer-file-coding-system (coding-system &optional force)
`buffer-file-coding-system' directly."
(interactive "zCoding system for visited file (default, nil): \nP")
(check-coding-system coding-system)
- (if (and buffer-file-coding-system (null force))
- (let ((x (coding-system-eol-type buffer-file-coding-system))
- (y (coding-system-eol-type coding-system)))
- (if (and (numberp x) (>= x 0) (<= x 2) (vectorp y))
- (setq coding-system (aref y x))
- (if (and (eq (coding-system-base coding-system) 'undecided)
- (numberp y))
- (setq coding-system (coding-system-change-eol-conversion
- buffer-file-coding-system y))))))
+ (if (and coding-system buffer-file-coding-system (null force))
+ (let ((base (coding-system-base buffer-file-coding-system))
+ (eol (coding-system-eol-type buffer-file-coding-system)))
+ ;; If CODING-SYSTEM doesn't specify text conversion, merge
+ ;; with that of buffer-file-coding-system.
+ (if (eq (coding-system-base coding-system) 'undecided)
+ (setq coding-system (coding-system-change-text-conversion
+ coding-system base)))
+ ;; If CODING-SYSTEM doesn't specify eol conversion, merge with
+ ;; that of buffer-file-coding-system.
+ (if (and (vectorp (coding-system-eol-type coding-system))
+ (numberp eol) (>= eol 0) (<= eol 2))
+ (setq coding-system (coding-system-change-eol-conversion
+ coding-system eol)))))
(setq buffer-file-coding-system coding-system)
(set-buffer-modified-p t)
(force-mode-line-update))
(not (terminal-coding-system)))
(setq coding-system default-terminal-coding-system))
(if coding-system
- (setq default-terminal-coding-system coding-system))
+ (setq default-terminal-coding-system coding-system))
(set-terminal-coding-system-internal coding-system)
(redraw-frame (selected-frame)))
(defun set-keyboard-coding-system (coding-system)
"Set coding system for keyboard input to CODING-SYSTEM.
In addition, this command enables Encoded-kbd minor mode.
-\(If CODING-SYSTEM is nil, Encoded-kbd mode is turned off.)
+\(If CODING-SYSTEM is nil, Encoded-kbd mode is turned off -- see
+`encoded-kbd-mode'.)
For a list of possible values of CODING-SYSTEM, use \\[list-coding-systems].
The default is determined by the selected language environment
or by the previous use of this command."
(if coding-system
(setq default-keyboard-coding-system coding-system))
(set-keyboard-coding-system-internal coding-system)
+ (setq keyboard-coding-system coding-system)
(encoded-kbd-mode (if coding-system 1 0)))
+(defcustom keyboard-coding-system nil
+ "Specify coding system for keyboard input.
+If you set this on a terminal which can't distinguish Meta keys from
+8-bit characters, you will have to use ESC to type Meta characters.
+See Info node `Specify Coding' and Info node `Single-Byte Character Support'.
+
+Setting this variable directly does not take effect;
+use either M-x customize or \\[set-keyboard-coding-system]."
+ :type '(coding-system :tag "Coding system")
+ :link '(info-link "(emacs)Specify Coding")
+ :link '(info-link "(emacs)Single-Byte Character Support")
+ :set (lambda (symbol value)
+ ;; Don't load encoded-kbd-mode unnecessarily.
+ (if (or value (boundp 'encoded-kbd-mode))
+ (set-keyboard-coding-system value)
+ (set-default 'keyboard-coding-system nil))) ; must initialize
+ :version "21.1"
+ :group 'keyboard
+ :group 'mule)
+
(defun set-buffer-process-coding-system (decoding encoding)
"Set coding systems for the process associated with the current buffer.
DECODING is the coding system to be used to decode input from the process,
For a list of possible values of CODING-SYSTEM, use \\[list-coding-systems]."
(interactive
- "zCoding-system for process input: \nzCoding-system for process output: ")
+ "zCoding-system for output from the process: \nzCoding-system for input to the process: ")
(let ((proc (get-buffer-process (current-buffer))))
(if (null proc)
- (error "no process")
+ (error "No process")
(check-coding-system decoding)
(check-coding-system encoding)
(set-process-coding-system proc decoding encoding)))
(setq next-selection-coding-system coding-system))
(defun set-coding-priority (arg)
- "Set priority of coding categories according to LIST.
-LIST is a list of coding categories ordered by priority."
+ "Set priority of coding categories according to ARG.
+ARG is a list of coding categories ordered by priority."
(let ((l arg)
(current-list (copy-sequence coding-category-list)))
;; Check the validity of ARG while deleting coding categories in
(setq coding-category-list (append arg current-list))
(set-coding-priority-internal)))
+;;; 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, and the corresponding Emacs
+charsets or coding systems.")
+
+;; Functions to support "Non-Standard Character Set Encodings" defined
+;; by the ICCCM 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.
+(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)
+ last-coding-system-used
+ encoding textlen chset)
+ (while (re-search-forward
+ "\\(\e\\)%/[0-4]\\([\200-\377][\200-\377]\\)\\([^\002]+\\)\002"
+ nil 'move)
+ (set-marker newpt (point))
+ (set-marker pt (match-beginning 0))
+ (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))
+ ("-V" . (t "iso8859-10" 1))
+ ("-Y" . (t "iso8859-13" 1))
+ ("-_" . (t "iso8859-14" 1))
+ ("-b" . (t "iso8859-15" 1))
+ ("-f" . (t "iso8859-16" 1)))
+ "Alist of ctext control sequences that introduce character sets which
+are not in the list of approved ICCCM encodings, and the corresponding
+coding system, identifier string, and number of octets per encoded
+character.
+
+Each element has the form (CTLSEQ . (ENCODING CHARSET NOCTETS)). CTLSEQ
+is the control sequence (sans the leading ESC) that introduces the character
+set in the text encoded by compound-text. ENCODING is a coding system
+symbol; if it is t, it means that the ctext coding system already encodes
+the text correctly, and only the leading control sequence needs to be altered.
+If ENCODING is a coding system, we need to re-encode the text with that
+coding system. CHARSET is the ICCCM name of the charset we need to put into
+the leading control sequence. NOCTETS is the number of octets (bytes) that
+encode each character in this charset. NOCTETS can be 0 (meaning the number
+of octets per character is variable), 1, 2, 3, or 4.")
+
+(defun ctext-pre-write-conversion (from to)
+ "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 and
+ ;; iso8859-1[03-6] charsets.
+ (while (re-search-forward "\e\\(\$([01]\\|-[VY_bf]\\)" 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\ 2"
+ noctets
+ (+ (/ textlen 128) 128)
+ (+ (% textlen 128) 128)
+ 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\ 2"
+ 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)
+
;;; FILE I/O
-(defvar auto-coding-alist
- '(("\\.\\(arc\\|zip\\|lzh\\|zoo\\|jar\\|tar\\|tgz\\)\\'" . no-conversion)
- ("\\.\\(ARC\\|ZIP\\|LZH\\|ZOO\\|JAR\\|TAR\\|TGZ\\)\\'" . no-conversion))
+(defcustom auto-coding-alist
+ '(("\\.\\(arc\\|zip\\|lzh\\|zoo\\|jar\\|sx[dmicw]\\|tar\\|tgz\\)\\'" . no-conversion)
+ ("\\.\\(gz\\|Z\\|bz\\|bz2\\|gpg\\)\\'" . no-conversion)
+ ("/#[^/]+#\\'" . emacs-mule))
"Alist of filename patterns vs corresponding coding systems.
Each element looks like (REGEXP . CODING-SYSTEM).
A file whose name matches REGEXP is decoded by CODING-SYSTEM on reading.
The settings in this alist take priority over `coding:' tags
in the file (see the function `set-auto-coding')
-and the contents of `file-coding-system-alist'.")
+and the contents of `file-coding-system-alist'."
+ :group 'files
+ :group 'mule
+ :type '(repeat (cons (regexp :tag "File name regexp")
+ (symbol :tag "Coding system"))))
+
+(defcustom auto-coding-regexp-alist
+ '(("^BABYL OPTIONS:[ \t]*-\\*-[ \t]*rmail[ \t]*-\\*-" . no-conversion))
+ "Alist of patterns vs corresponding coding systems.
+Each element looks like (REGEXP . CODING-SYSTEM).
+A file whose first bytes match REGEXP is decoded by CODING-SYSTEM on reading.
+
+The settings in this alist take priority over `coding:' tags
+in the file (see the function `set-auto-coding')
+and the contents of `file-coding-system-alist'."
+ :group 'files
+ :group 'mule
+ :type '(repeat (cons (regexp :tag "Regexp")
+ (symbol :tag "Coding system"))))
+
+;; See the bottom of this file for built-in auto coding functions.
+(defcustom auto-coding-functions '(sgml-xml-auto-coding-function
+ 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))
(defvar set-auto-coding-for-load nil
"Non-nil means look for `load-coding' property instead of `coding'.
These bytes should include at least the first 1k of the file
and the last 3k of the file, but the middle may be omitted.
-It checks FILENAME against the variable `auto-coding-alist'.
-If FILENAME doesn't match any entries in the variable,
-it checks for a `coding:' tag in the first one or two lines following
-point. If no `coding:' tag is found, it checks for local variables
-list in the last 3K bytes out of the SIZE bytes.
+The function checks FILENAME against the variable `auto-coding-alist'.
+If FILENAME doesn't match any entries in the variable, it checks the
+contents of the current buffer following point against
+`auto-coding-regexp-alist'. If no match is found, it checks for a
+`coding:' tag in the first one or two lines following point. If no
+`coding:' tag is found, it checks any local variables list in the last
+3K bytes out of the SIZE bytes. Finally, if none of these methods
+succeed, it checks to see if any function in `auto-coding-functions'
+gives a match.
-The return value is the specified coding system,
-or nil if nothing specified.
+The return value is the specified coding system, or nil if nothing is
+specified.
The variable `set-auto-coding-function' (which see) is set to this
function by default."
- (let ((coding-system (auto-coding-alist-lookup filename)))
-
- (or coding-system
- (let* ((case-fold-search t)
- (head-start (point))
- (head-end (+ head-start (min size 1024)))
- (tail-start (+ head-start (max (- size 3072) 0)))
- (tail-end (+ head-start size))
- coding-system head-found tail-found pos)
- ;; Try a short cut by searching for the string "coding:"
- ;; and for "unibyte:" at the head and tail of SIZE bytes.
- (setq head-found (or (search-forward "coding:" head-end t)
- (search-forward "unibyte:" head-end t)))
- (if (and head-found (> head-found tail-start))
- ;; Head and tail are overlapped.
- (setq tail-found head-found)
- (goto-char tail-start)
- (setq tail-found (or (search-forward "coding:" tail-end t)
- (search-forward "unibyte:" tail-end t))))
-
- ;; At first check the head.
- (when head-found
+ (or (auto-coding-alist-lookup filename)
+ ;; Try using `auto-coding-regexp-alist'.
+ (save-excursion
+ (let ((alist auto-coding-regexp-alist)
+ coding-system)
+ (while (and alist (not coding-system))
+ (let ((regexp (car (car alist))))
+ (when (re-search-forward regexp (+ (point) size) t)
+ (setq coding-system (cdr (car alist)))))
+ (setq alist (cdr alist)))
+ coding-system))
+ (let* ((case-fold-search t)
+ (head-start (point))
+ (head-end (+ head-start (min size 1024)))
+ (tail-start (+ head-start (max (- size 3072) 0)))
+ (tail-end (+ head-start size))
+ coding-system head-found tail-found pos)
+ ;; Try a short cut by searching for the string "coding:"
+ ;; and for "unibyte:" at the head and tail of SIZE bytes.
+ (setq head-found (or (search-forward "coding:" head-end t)
+ (search-forward "unibyte:" head-end t)))
+ (if (and head-found (> head-found tail-start))
+ ;; Head and tail are overlapped.
+ (setq tail-found head-found)
+ (goto-char tail-start)
+ (setq tail-found (or (search-forward "coding:" tail-end t)
+ (search-forward "unibyte:" tail-end t))))
+
+ ;; At first check the head.
+ (when head-found
+ (goto-char head-start)
+ (setq head-end (set-auto-mode-1))
+ (setq head-start (point))
+ (when (and head-end (< head-found head-end))
(goto-char head-start)
- (setq pos (re-search-forward "[\n\r]" head-end t))
- (if (and pos
- (= (char-after head-start) ?#)
- (= (char-after (1+ head-start)) ?!))
- ;; If the file begins with "#!" (exec interpreter magic),
- ;; look for coding frobs in the first two lines. You cannot
- ;; necessarily put them in the first line of such a file
- ;; without screwing up the interpreter invocation.
- (setq pos (search-forward "\n" head-end t)))
- (if pos (setq head-end pos))
- (when (< head-found head-end)
- (goto-char head-start)
- (when (and set-auto-coding-for-load
- (re-search-forward
- "-\\*-\\(.*;\\)?[ \t]*unibyte:[ \t]*\\([^ ;]+\\)"
- head-end t))
- (setq coding-system 'raw-text))
- (when (and (not coding-system)
- (re-search-forward
- "-\\*-\\(.*;\\)?[ \t]*coding:[ \t]*\\([^ ;]+\\)"
- head-end t))
- (setq coding-system (intern (match-string 2)))
- (or (coding-system-p coding-system)
- (setq coding-system nil)))))
-
- ;; If no coding: tag in the head, check the tail.
- (when (and tail-found (not coding-system))
- (goto-char tail-start)
- (search-forward "\n\^L" nil t)
- (if (re-search-forward
- "^\\(.*\\)[ \t]*Local Variables:[ \t]*\\(.*\\)$" tail-end t)
- ;; The prefix is what comes before "local variables:" in its
- ;; line. The suffix is what comes after "local variables:"
- ;; in its line.
- (let* ((prefix (regexp-quote (match-string 1)))
- (suffix (regexp-quote (match-string 2)))
- (re-coding
- (concat
- "^" prefix
- "[ \t]*coding[ \t]*:[ \t]*\\([^ \t]+\\)[ \t]*"
- suffix "$"))
- (re-unibyte
- (concat
- "^" prefix
- "[ \t]*unibyte[ \t]*:[ \t]*\\([^ \t]+\\)[ \t]*"
- suffix "$"))
- (re-end
- (concat "^" prefix "[ \t]*end *:[ \t]*" suffix "$"))
- (pos (point)))
- (re-search-forward re-end tail-end 'move)
- (setq tail-end (point))
- (goto-char pos)
- (when (and set-auto-coding-for-load
- (re-search-forward re-unibyte tail-end t))
- (setq coding-system 'raw-text))
- (when (and (not coding-system)
- (re-search-forward re-coding tail-end t))
- (setq coding-system (intern (match-string 1)))
- (or (coding-system-p coding-system)
- (setq coding-system nil))))))
- coding-system))))
+ (when (and set-auto-coding-for-load
+ (re-search-forward
+ "\\(.*;\\)?[ \t]*unibyte:[ \t]*\\([^ ;]+\\)"
+ head-end t))
+ (setq coding-system 'raw-text))
+ (when (and (not coding-system)
+ (re-search-forward
+ "\\(.*;\\)?[ \t]*coding:[ \t]*\\([^ ;]+\\)"
+ head-end t))
+ (setq coding-system (intern (match-string 2)))
+ (or (coding-system-p coding-system)
+ (setq coding-system nil)))))
+
+ ;; If no coding: tag in the head, check the tail.
+ (when (and tail-found (not coding-system))
+ (goto-char tail-start)
+ (search-forward "\n\^L" nil t)
+ (if (re-search-forward
+ "^\\(.*\\)[ \t]*Local Variables:[ \t]*\\(.*\\)$" tail-end t)
+ ;; The prefix is what comes before "local variables:" in its
+ ;; line. The suffix is what comes after "local variables:"
+ ;; in its line.
+ (let* ((prefix (regexp-quote (match-string 1)))
+ (suffix (regexp-quote (match-string 2)))
+ (re-coding
+ (concat
+ "^" prefix
+ ;; N.B. without the \n below, the regexp can
+ ;; eat newlines.
+ "[ \t]*coding[ \t]*:[ \t]*\\([^ \t\n]+\\)[ \t]*"
+ suffix "$"))
+ (re-unibyte
+ (concat
+ "^" prefix
+ "[ \t]*unibyte[ \t]*:[ \t]*\\([^ \t\n]+\\)[ \t]*"
+ suffix "$"))
+ (re-end
+ (concat "^" prefix "[ \t]*End *:[ \t]*" suffix "$"))
+ (pos (point)))
+ (re-search-forward re-end tail-end 'move)
+ (setq tail-end (point))
+ (goto-char pos)
+ (when (and set-auto-coding-for-load
+ (re-search-forward re-unibyte tail-end t))
+ (setq coding-system 'raw-text))
+ (when (and (not coding-system)
+ (re-search-forward re-coding tail-end t))
+ (setq coding-system (intern (match-string 1)))
+ (or (coding-system-p coding-system)
+ (setq coding-system nil))))))
+ coding-system)
+ ;; Finally, try all the `auto-coding-functions'.
+ (let ((funcs auto-coding-functions)
+ (coding-system nil))
+ (while (and funcs (not coding-system))
+ (setq coding-system (condition-case e
+ (save-excursion
+ (goto-char (point-min))
+ (funcall (pop funcs) size))
+ (error nil))))
+ coding-system)))
(setq set-auto-coding-function 'set-auto-coding)
-;; Set buffer-file-coding-system of the current buffer after some text
-;; is inserted.
(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))
(modified-p (buffer-modified-p)))
(when coding-system
- (set-buffer-file-coding-system coding-system)
+ (set-buffer-file-coding-system coding-system t)
(if (and enable-multibyte-characters
(or (eq coding-system 'no-conversion)
(eq (coding-system-type coding-system) 5))
network-coding-system-alist)))))))
(defun make-translation-table (&rest args)
- "Make a translation table (char table) from arguments.
-Each argument is a list of the form (FROM . TO),
-where FROM is a character to be translated to TO.
+ "Make a translation table from arguments.
+A translation table is a char table intended for character
+translation in CCL programs.
+
+Each argument is a list of elements of the form (FROM . TO), where FROM
+is a character to be translated to TO.
FROM can be a generic character (see `make-char'). In this case, TO is
-a generic character containing the same number of characters, or a
+a generic character containing the same number of characters, or an
ordinary character. If FROM and TO are both generic characters, all
characters belonging to FROM are translated to characters belonging to TO
-without changing their position code(s)."
+without changing their position code(s).
+
+The arguments and forms in each argument are processed in the given
+order, and if a previous form already translates TO to some other
+character, say TO-ALT, FROM is also translated to TO-ALT."
(let ((table (make-char-table 'translation-table))
revlist)
(while args
(defun make-translation-table-from-vector (vec)
"Make translation table from decoding vector VEC.
-VEC is an array of 256 elements to map unibyte codes to multibyte characters.
+VEC is an array of 256 elements to map unibyte codes to multibyte
+characters. Elements may be nil for undefined code points.
See also the variable `nonascii-translation-table'."
(let ((table (make-char-table 'translation-table))
(rev-table (make-char-table 'translation-table))
- (i 0)
ch)
- (while (< i 256)
+ (dotimes (i 256)
(setq ch (aref vec i))
- (aset table i ch)
- (if (>= ch 256)
- (aset rev-table ch i))
- (setq i (1+ i)))
+ (when ch
+ (aset table i ch)
+ (if (>= ch 256)
+ (aset rev-table ch i))))
(set-char-table-extra-slot table 0 rev-table)
table))
(defun define-translation-table (symbol &rest args)
- "Define SYMBOL as a name of translation table made by ARGS.
+ "Define SYMBOL as the name of translation table made by ARGS.
+This sets up information so that the table can be used for
+translations in a CCL program.
-If the first element of ARGS is a char-table of which purpose is
-translation-table, just define SYMBOL as the name of it.
+If the first element of ARGS is a char-table whose purpose is
+`translation-table', just define SYMBOL to name it. (Note that this
+function does not bind SYMBOL.)
-In the other case, ARGS are the same as arguments to the function
+Any other ARGS should be suitable as arguments of the function
`make-translation-table' (which see).
This function sets properties `translation-table' and
-`translation-table-id' of SYMBOL to the created table itself and
-identification number of the table respectively."
+`translation-table-id' of SYMBOL to the created table itself and the
+identification number of the table respectively. It also registers
+the table in `translation-table-vector'."
(let ((table (if (and (char-table-p (car args))
(eq (char-table-subtype (car args))
'translation-table))
(progn ,@body)
(set-category-table current-category-table))))
+(defun define-translation-hash-table (symbol table)
+ "Define SYMBOL as the name of the hash translation TABLE for use in CCL.
+
+Analogous to `define-translation-table', but updates
+`translation-hash-table-vector' and the table is for use in the CCL
+`lookup-integer' and `lookup-character' functions."
+ (unless (and (symbolp symbol)
+ (hash-table-p table))
+ (error "Bad args to define-translation-hash-table"))
+ (let ((len (length translation-hash-table-vector))
+ (id 0)
+ done)
+ (put symbol 'translation-hash-table table)
+ (while (not done)
+ (if (>= id len)
+ (setq translation-hash-table-vector
+ (vconcat translation-hash-table-vector [nil])))
+ (let ((slot (aref translation-hash-table-vector id)))
+ (if (or (not slot)
+ (eq (car slot) symbol))
+ (progn
+ (aset translation-hash-table-vector id (cons symbol table))
+ (setq done t))
+ (setq id (1+ id)))))
+ (put symbol 'translation-hash-table-id id)
+ id))
+
;;; Initialize some variables.
(put 'use-default-ascent 'char-table-extra-slots 0)
(setq ignore-relative-composition
(make-char-table 'ignore-relative-composition))
+
+;;; Built-in auto-coding-functions:
+
+(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")
+ (let ((end (save-excursion
+ ;; This is a hack.
+ (re-search-forward "\"\\s-*\\?>" size t))))
+ (when end
+ (if (re-search-forward "encoding=\"\\(.+?\\)\"" end t)
+ (let* ((match (match-string 1))
+ (sym (intern (downcase match))))
+ (if (coding-system-p sym)
+ sym
+ (message "Warning: unknown coding system \"%s\"" match)
+ nil))
+ 'utf-8)))))
+
+(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)
+ (point))))
+ (when (and (search-forward "<html>" size t)
+ (re-search-forward "<meta\\s-+http-equiv=\"content-type\"\\s-+content=\"text/\\sw+;\\s-*charset=\\(.+?\\)\"" size t))
+ (let* ((match (match-string 1))
+ (sym (intern (downcase match))))
+ (if (coding-system-p sym)
+ sym
+ (message "Warning: unknown coding system \"%s\"" match)
+ nil))))
+
;;;
(provide 'mule)
HCoop / bpt / emacs.git / blobdiff