1 ;;; mule-diag.el --- Show diagnosis of multilingual environment (Mule)
3 ;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
4 ;; Licensed to the Free Software Foundation.
6 ;; Keywords: multilingual, charset, coding system, fontset, diagnosis, i18n
8 ;; This file is part of GNU Emacs.
10 ;; GNU Emacs is free software; you can redistribute it and/or modify
11 ;; it under the terms of the GNU General Public License as published by
12 ;; the Free Software Foundation; either version 2, or (at your option)
15 ;; GNU Emacs is distributed in the hope that it will be useful,
16 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
17 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
18 ;; GNU General Public License for more details.
20 ;; You should have received a copy of the GNU General Public License
21 ;; along with GNU Emacs; see the file COPYING. If not, write to the
22 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
23 ;; Boston, MA 02111-1307, USA.
25 ;;; General utility function
27 ;; Print all arguments with single space separator in one line.
28 (defun print-list (&rest args
)
33 (setq args
(cdr args
)))
37 ;; Re-order the elements of charset-list.
38 (defun sort-charset-list ()
41 (function (lambda (x y
) (< (charset-id x
) (charset-id y
)))))))
46 (defun list-character-sets (arg)
47 "Display a list of all character sets.
49 The ID-NUM column contains a charset identification number
50 for internal Emacs use.
52 The MULTIBYTE-FORM column contains a format of multibyte sequence
53 of characters in the charset for buffer and string
54 by one to four hexadecimal digits.
55 `xx' stands for any byte in the range 0..127.
56 `XX' stands for any byte in the range 160..255.
58 The D column contains a dimension of this character set.
59 The CH column contains a number of characters in a block of this character set.
60 The FINAL-CHAR column contains an ISO-2022's <final-char> to use for
61 designating this character set in ISO-2022-based coding systems.
63 With prefix arg, the output format gets more cryptic,
64 but still shows the full information."
66 (with-output-to-temp-buffer "*Help*"
67 (with-current-buffer standard-output
69 (list-character-sets-2)
72 (substitute-command-keys
74 (if (display-mouse-p) "\\[help-follow-mouse] or ")
75 "\\[help-follow]:\n")))
76 (insert " on a column title to sort by that title,")
78 (insert "+----DIMENSION\n")
79 (insert " on a charset name to list characters.")
81 (insert "| +--CHARS\n")
82 (let ((columns '(("ID-NUM" . id
) "\t"
83 ("CHARSET-NAME" . name
) "\t\t\t"
84 ("MULTIBYTE-FORM" . id
) "\t"
85 ("D CH FINAL-CHAR" . iso-spec
)))
86 (help-highlight-face 'region
)
88 (substitute-command-keys
89 (concat (if (display-mouse-p) "\\[help-follow-mouse], ")
90 "\\[help-follow]: sort on this column")))
93 (if (stringp (car columns
))
94 (insert (car columns
))
95 (insert (car (car columns
)))
96 (search-backward (car (car columns
)))
97 (help-xref-button 0 'sort-listed-character-sets
100 (goto-char (point-max)))
101 (setq columns
(cdr columns
)))
103 (insert "------\t------------\t\t\t--------------\t- -- ----------\n")
105 ;; Insert body sorted by charset IDs.
106 (list-character-sets-1 'id
)
107 (help-setup-xref (list #'list-character-sets arg
) (interactive-p))))))
110 ;; Sort character set list by SORT-KEY.
112 (defun sort-listed-character-sets (sort-key)
115 (let ((buffer-read-only nil
))
116 (goto-char (point-min))
117 (re-search-forward "[0-9][0-9][0-9]")
119 (delete-region (point) (point-max))
120 (list-character-sets-1 sort-key
)
121 (help-setup-xref (list #'list-character-sets nil
) t
)))))
123 (defun charset-multibyte-form-string (charset)
124 (let ((info (charset-info charset
)))
125 (cond ((eq charset
'ascii
)
127 ((eq charset
'eight-bit-control
)
128 (format "%2X Xx" (aref info
6)))
129 ((eq charset
'eight-bit-graphic
)
132 (let ((str (format "%2X" (aref info
6))))
133 (if (> (aref info
7) 0)
134 (setq str
(format "%s %2X"
136 (setq str
(concat str
" XX"))
137 (if (> (aref info
2) 1)
138 (setq str
(concat str
" XX")))
141 ;; Insert a list of character sets sorted by SORT-KEY. SORT-KEY
142 ;; should be one of `id', `name', and `iso-spec'. If SORT-KEY is nil,
143 ;; it defaults to `id'.
145 (defun list-character-sets-1 (sort-key)
148 (let ((tail (charset-list))
150 (substitute-command-keys
151 (concat (if (display-mouse-p) "\\[help-follow-mouse], ")
152 "\\[help-follow]: show table of this character set")))
153 charset-info-list elt charset info sort-func
)
155 (setq charset
(car tail
) tail
(cdr tail
)
156 info
(charset-info charset
))
158 ;; Generate a list that contains all information to display.
159 (setq charset-info-list
160 (cons (list (charset-id charset
) ; ID-NUM
161 charset
; CHARSET-NAME
162 (charset-multibyte-form-string charset
); MULTIBYTE-FORM
163 (aref info
2) ; DIMENSION
164 (aref info
3) ; CHARS
165 (aref info
8) ; FINAL-CHAR
169 ;; Determine a predicate for `sort' by SORT-KEY.
171 (cond ((eq sort-key
'id
)
172 (function (lambda (x y
) (< (car x
) (car y
)))))
175 (function (lambda (x y
) (string< (nth 1 x
) (nth 1 y
)))))
177 ((eq sort-key
'iso-spec
)
178 ;; Sort by DIMENSION CHARS FINAL-CHAR
181 (or (< (nth 3 x
) (nth 3 y
))
182 (and (= (nth 3 x
) (nth 3 y
))
183 (or (< (nth 4 x
) (nth 4 y
))
184 (and (= (nth 4 x
) (nth 4 y
))
185 (< (nth 5 x
) (nth 5 y
)))))))))
187 (error "Invalid charset sort key: %s" sort-key
))))
189 (setq charset-info-list
(sort charset-info-list sort-func
))
191 ;; Insert information of character sets.
192 (while charset-info-list
193 (setq elt
(car charset-info-list
)
194 charset-info-list
(cdr charset-info-list
))
195 (insert (format "%03d(%02X)" (car elt
) (car elt
))) ; ID-NUM
197 (insert (symbol-name (nth 1 elt
))) ; CHARSET-NAME
198 (search-backward (symbol-name (nth 1 elt
)))
199 (help-xref-button 0 'list-charset-chars
(nth 1 elt
) help-echo
)
200 (goto-char (point-max))
203 (insert (nth 2 elt
)) ; MULTIBYTE-FORM
205 (insert (format "%d %2d " (nth 3 elt
) (nth 4 elt
)) ; DIMENSION and CHARS
206 (if (< (nth 5 elt
) 0) "none" (nth 5 elt
))) ; FINAL-CHAR
210 ;; List all character sets in a form that a program can easily parse.
212 (defun list-character-sets-2 ()
213 (insert "#########################
215 ## Each line corresponds to one charset.
216 ## The following attributes are listed in this order
217 ## separated by a colon `:' in one line.
219 ## CHARSET-SYMBOL-NAME,
220 ## DIMENSION (1 or 2)
222 ## BYTES (of multibyte form: 1, 2, 3, or 4),
223 ## WIDTH (occupied column numbers: 1 or 2),
224 ## DIRECTION (0:left-to-right, 1:right-to-left),
225 ## ISO-FINAL-CHAR (character code of ISO-2022's final character)
226 ## ISO-GRAPHIC-PLANE (ISO-2022's graphic plane, 0:GL, 1:GR)
227 ## DESCRIPTION (describing string of the charset)
229 (let ((l charset-list
)
232 (setq charset
(car l
) l
(cdr l
))
233 (princ (format "%03d:%s:%d:%d:%d:%d:%d:%d:%d:%s\n"
236 (charset-dimension charset
)
237 (charset-chars charset
)
238 (charset-bytes charset
)
239 (charset-width charset
)
240 (charset-direction charset
)
241 (charset-iso-final-char charset
)
242 (charset-iso-graphic-plane charset
)
243 (charset-description charset
))))))
245 (defvar non-iso-charset-alist
247 (ascii vietnamese-viscii-lower vietnamese-viscii-upper
)
248 viet-viscii-nonascii-translation-table
251 (ascii cyrillic-iso8859-5
)
252 cyrillic-koi8-r-nonascii-translation-table
255 (ascii cyrillic-iso8859-5
)
256 cyrillic-alternativnyj-nonascii-translation-table
259 (ascii chinese-big5-1 chinese-big5-2
)
262 ((?
\xA1 ?
\xFE) .
(?
\x40 ?
\x7E ?
\xA1 ?
\xFE))))
264 (ascii katakana-jisx0201 japanese-jisx0208
)
266 ((32 127 ?
\xA1 ?
\xDF)
267 ((?
\x81 ?
\x9F ?
\xE0 ?
\xEF) .
(?
\x40 ?
\x7E ?
\x80 ?
\xFC)))))
268 "Alist of non-ISO charset names vs the corresponding information.
270 Non-ISO charsets are what Emacs can read (or write) by mapping to (or
271 from) some Emacs' charsets that correspond to ISO charsets.
273 Each element has the following format:
274 (NON-ISO-CHARSET CHARSET-LIST TRANSLATION-METHOD [ CODE-RANGE ])
276 NON-ISO-CHARSET is a name (symbol) of the non-ISO charset.
278 CHARSET-LIST is a list of Emacs' charsets into which characters of
279 NON-ISO-CHARSET are mapped.
281 TRANSLATION-METHOD is a translatin table (symbol) to translate a
282 character code of NON-ISO-CHARSET to the corresponding Emacs character
283 code. It can also be a function to call with one argument, a
284 character code in NON-ISO-CHARSET.
286 CODE-RANGE specifies the valid code ranges of NON-ISO-CHARSET.
287 It is a list of RANGEs, where each RANGE is of the form:
288 (FROM1 TO1 FROM2 TO2 ...)
290 ((FROM1-1 TO1-1 FROM1-2 TO1-2 ...) . (FROM2-1 TO2-1 FROM2-2 TO2-2 ...))
291 In the first form, valid codes are between FROM1 and TO1, or FROM2 and
293 The second form is used for 2-byte codes. The car part is the ranges
294 of the first byte, and the cdr part is the ranges of the second byte.")
297 ;; Decode a character that has code CODE in CODEPAGE. Value is a
298 ;; string of decoded character.
300 (defun decode-codepage-char (codepage code
)
301 ;; Each CODEPAGE corresponds to a coding system cpCODEPAGE.
302 (let ((coding-system (intern (format "cp%d" codepage
))))
303 (or (coding-system-p coding-system
)
304 (codepage-setup codepage
))
306 (decode-coding-string (char-to-string code
) coding-system
))))
309 ;; Add DOS codepages to `non-iso-charset-alist'.
311 (let ((tail (cp-supported-codepages))
314 (setq elt
(car tail
) tail
(cdr tail
))
315 ;; Now ELT is (CODEPAGE . CHARSET), where CODEPAGE is a string
316 ;; (e.g. "850"), CHARSET is a charset that characters in CODEPAGE
318 (setq non-iso-charset-alist
319 (cons (list (intern (concat "cp" (car elt
)))
320 (list 'ascii
(cdr elt
))
322 (decode-codepage-char ,(string-to-int (car elt
))
325 non-iso-charset-alist
))))
328 ;; A variable to hold charset input history.
329 (defvar charset-history nil
)
333 (defun read-charset (prompt &optional default-value initial-input
)
334 "Read a character set from the minibuffer, prompting with string PROMPT.
335 It reads an Emacs' character set listed in the variable `charset-list'
336 or a non-ISO character set listed in the variable
337 `non-iso-charset-alist'.
339 Optional arguments are DEFAULT-VALUE and INITIAL-INPUT.
340 DEFAULT-VALUE, if non-nil, is the default value.
341 INITIAL-INPUT, if non-nil, is a string inserted in the minibuffer initially.
342 See the documentation of the function `completing-read' for the
343 detailed meanings of these arguments."
344 (let* ((table (append (mapcar (function (lambda (x) (list (symbol-name x
))))
346 (mapcar (function (lambda (x)
347 (list (symbol-name (car x
)))))
348 non-iso-charset-alist
)))
349 (charset (completing-read prompt table
350 nil t initial-input
'charset-history
352 (if (> (length charset
) 0)
356 ;; List characters of the range MIN and MAX of CHARSET. If dimension
357 ;; of CHARSET is two (i.e. 2-byte charset), ROW is the first byte
358 ;; (block index) of the characters, and MIN and MAX are the second
359 ;; bytes of the characters. If the dimension is one, ROW should be 0.
360 ;; For a non-ISO charset, CHARSET is a translation table (symbol) or a
361 ;; function to get Emacs' character codes that corresponds to the
362 ;; characters to list.
364 (defun list-block-of-chars (charset row min max
)
366 (insert-char ?-
(+ 4 (* 3 16)))
370 (insert (format "%3X" i
))
372 (setq i
(* (/ min
16) 16))
375 (insert (format "\n%3Xx" (/ (+ (* row
256) i
) 16))))
376 (setq ch
(cond ((< i min
)
380 (make-char charset i
)
381 (make-char charset row i
)))
382 ((and (symbolp charset
) (get charset
'translation-table
))
383 (aref (get charset
'translation-table
) i
))
384 (t (funcall charset
(+ (* row
256) i
)))))
385 (if (and (char-table-p charset
)
386 (or (< ch
32) (and (>= ch
127) (<= ch
255))))
387 ;; Don't insert a control code.
389 (indent-to (+ (* (% i
16) 3) 6))
395 ;; List all characters in ISO charset CHARSET.
397 (defun list-iso-charset-chars (charset)
398 (let ((dim (charset-dimension charset
))
399 (chars (charset-chars charset
))
400 (plane (charset-iso-graphic-plane charset
))
402 (insert (format "Characters in the charset %s.\n" charset
))
404 (cond ((eq charset
'eight-bit-control
)
405 (setq min
128 max
159))
406 ((eq charset
'eight-bit-graphic
)
407 (setq min
160 max
255))
410 (setq min
33 max
126)
411 (setq min
32 max
127))
413 (setq min
(+ min
128) max
(+ max
128)))))
416 (list-block-of-chars charset
0 min max
)
419 (list-block-of-chars charset i min max
)
423 ;; List all characters in non-ISO charset CHARSET.
425 (defun list-non-iso-charset-chars (charset)
426 (let* ((slot (assq charset non-iso-charset-alist
))
427 (charsets (nth 1 slot
))
428 (translate-method (nth 2 slot
))
429 (ranges (nth 3 slot
))
432 (error "Unknown external charset: %s" charset
))
433 (insert (format "Characters in non-ISO charset %s.\n" charset
))
434 (insert "They are mapped to: "
435 (mapconcat #'symbol-name charsets
", ")
438 (setq range
(car ranges
) ranges
(cdr ranges
))
439 (if (integerp (car range
))
440 ;; The form of RANGES is (FROM1 TO1 FROM2 TO2 ...).
442 (list-block-of-chars translate-method
443 0 (car range
) (nth 1 range
))
444 (setq range
(nthcdr 2 range
)))
445 ;; The form of RANGES is ((FROM1-1 TO1-1 ...) . (FROM2-1 TO2-1 ...)).
446 (let ((row-range (car range
))
448 col-range col col-max
)
450 (setq row
(car row-range
) row-max
(nth 1 row-range
)
451 row-range
(nthcdr 2 row-range
))
452 (while (< row row-max
)
453 (setq col-range
(cdr range
))
455 (setq col
(car col-range
) col-max
(nth 1 col-range
)
456 col-range
(nthcdr 2 col-range
))
457 (list-block-of-chars translate-method row col col-max
))
458 (setq row
(1+ row
)))))))))
462 (defun list-charset-chars (charset)
463 "Display a list of characters in the specified character set."
464 (interactive (list (read-charset "Character set: ")))
465 (with-output-to-temp-buffer "*Help*"
466 (with-current-buffer standard-output
467 (set-buffer-multibyte t
)
468 (cond ((charsetp charset
)
469 (list-iso-charset-chars charset
))
470 ((assq charset non-iso-charset-alist
)
471 (list-non-iso-charset-chars charset
))
473 (error "Invalid charset %s" charset
))))))
477 (defun describe-character-set (charset)
478 "Display information about character set CHARSET."
479 (interactive (list (let ((non-iso-charset-alist nil
))
480 (read-charset "Charset: "))))
481 (or (charsetp charset
)
482 (error "Invalid charset: %S" charset
))
483 (let ((info (charset-info charset
)))
484 (with-output-to-temp-buffer "*Help*"
486 (set-buffer standard-output
)
487 (insert "Character set: " (symbol-name charset
)
488 (format " (ID:%d)\n\n" (aref info
0)))
489 (insert (aref info
13) "\n\n") ; description
490 (insert "number of contained characters: "
491 (if (= (aref info
2) 1)
492 (format "%d\n" (aref info
3))
493 (format "%dx%d\n" (aref info
3) (aref info
3))))
494 (insert "the final char of ISO2022's desgination sequence: ")
496 (insert (format "`%c'\n" (aref info
8)))
497 (insert "not assigned\n"))
498 (insert (format "width (how many columns on screen): %d\n"
500 (insert (format "internal multibyte sequence: %s\n"
501 (charset-multibyte-form-string charset
)))
502 (let ((coding (plist-get (aref info
14) 'preferred-coding-system
)))
504 (insert (format "prefered coding system: %s\n" coding
))
505 (search-backward (symbol-name coding
))
506 (help-xref-button 0 #'describe-coding-system coding
507 "mouse-2, RET: describe this coding system")))
508 (help-setup-xref (list #'describe-character-set charset
)
513 (defun describe-char-after (&optional pos
)
514 "Display information of in current buffer at position POS.
515 The information includes character code, charset and code points in it,
516 syntax, category, how the character is encoded in a file,
517 which font is being used for displaying the character."
521 (if (>= pos
(point-max))
522 (error "No character at point"))
523 (let* ((char (char-after pos
))
524 (charset (char-charset char
))
525 (composition (find-composition (point) nil nil t
))
526 (composed (if composition
(buffer-substring (car composition
)
527 (nth 1 composition
))))
529 (if (eq charset
'unknown
)
532 ,(format "%s (0%o, %d, 0x%x) -- invalid character code"
534 (single-key-description char
)
535 (char-to-string char
))
539 ,(format "%s (0%o, %d, 0x%x)" (if (< char
256)
540 (single-key-description char
)
541 (char-to-string char
))
544 ,(symbol-name charset
)
545 ,(format "(%s)" (charset-description charset
)))
547 ,(let ((split (split-char char
)))
548 (if (= (charset-dimension charset
) 1)
549 (format "%d" (nth 1 split
))
550 (format "%d %d" (nth 1 split
) (nth 2 split
)))))
552 ,(nth 2 (assq (char-syntax char
) syntax-code-table
)))
554 ,@(let ((category-set (char-category-set char
)))
555 (if (not category-set
)
557 (mapcar #'(lambda (x) (format "%c:%s "
558 x
(category-docstring x
)))
559 (category-set-mnemonics category-set
)))))
561 ,(encoded-string-description
562 (string-as-unibyte (char-to-string char
)) nil
))
564 ,@(let* ((coding buffer-file-coding-system
)
565 (encoded (encode-coding-char char coding
)))
567 (list (encoded-string-description encoded coding
)
568 (format "(encoded by coding system %S)" coding
))
569 (list "not encodable by coding system"
570 (symbol-name coding
)))))
571 ,(if (display-graphic-p (selected-frame))
572 (list "font" (or (internal-char-font (point))
574 (list "terminal code"
575 (let* ((coding (terminal-coding-system))
576 (encoded (encode-coding-char char coding
)))
578 (encoded-string-description encoded coding
)
579 "not encodable")))))))
580 (setq max-width
(apply #'max
(mapcar #'(lambda (x) (length (car x
)))
582 (with-output-to-temp-buffer "*Help*"
584 (set-buffer standard-output
)
585 (let ((formatter (format "%%%ds:" max-width
)))
586 (dolist (elt item-list
)
587 (insert (format formatter
(car elt
)))
588 (dolist (clm (cdr elt
))
589 (when (>= (+ (current-column) (string-width clm
) 1)
592 (indent-to (1+ max-width
)))
596 (insert "\nComposed with the following characerter(s) "
597 (mapconcat (lambda (x) (format "`%c'" x
))
598 (substring composed
1)
600 " to form `" composed
"'")
601 (if (nth 3 composition
)
603 (insert "\nby the rule ("
604 (mapconcat (lambda (x)
605 (format (if (consp x
) "%S" "?%c") x
))
609 "See the variable `reference-point-alist' for the meaning of the rule.\n")))
615 ;; Print information of designation of each graphic register in FLAGS
616 ;; in human readable format. See the documentation of
617 ;; `make-coding-system' for the meaning of FLAGS.
618 (defun print-designation (flags)
619 (let ((graphic-register 0)
621 (while (< graphic-register
4)
622 (setq charset
(aref flags graphic-register
))
626 (cond ((null charset
)
629 "no initial designation, and used by any charsets")
632 charset
(charset-description charset
)))
634 (if (charsetp (car charset
))
635 (format "%s:%s, and also used by the followings:"
637 (charset-description (car charset
)))
638 "no initial designation, and used by the followings:"))
640 "invalid designation information"))))
641 (when (listp charset
)
642 (setq charset
(cdr charset
))
644 (cond ((eq (car charset
) t
)
645 (princ "\tany other charsets\n"))
646 ((charsetp (car charset
))
647 (princ (format "\t%s:%s\n"
649 (charset-description (car charset
)))))
651 "invalid designation information"))
652 (setq charset
(cdr charset
))))
653 (setq graphic-register
(1+ graphic-register
)))))
656 (defun describe-coding-system (coding-system)
657 "Display information about CODING-SYSTEM."
658 (interactive "zDescribe coding system (default, current choices): ")
659 (if (null coding-system
)
660 (describe-current-coding-system)
661 (with-output-to-temp-buffer "*Help*"
662 (print-coding-system-briefly coding-system
'doc-string
)
663 (let ((coding-spec (coding-system-spec coding-system
)))
665 (let ((type (coding-system-type coding-system
))
666 (flags (coding-system-flags coding-system
)))
669 (princ " (do no conversion)"))
671 (princ " (do automatic conversion)"))
673 (princ " (Emacs internal multibyte form)"))
675 (princ " (Shift-JIS, MS-KANJI)"))
677 (princ " (variant of ISO-2022)\n")
678 (princ "Initial designations:\n")
679 (print-designation flags
)
680 (princ "Other Form: \n ")
681 (princ (if (aref flags
4) "short-form" "long-form"))
682 (if (aref flags
5) (princ ", ASCII@EOL"))
683 (if (aref flags
6) (princ ", ASCII@CNTL"))
684 (princ (if (aref flags
7) ", 7-bit" ", 8-bit"))
685 (if (aref flags
8) (princ ", use-locking-shift"))
686 (if (aref flags
9) (princ ", use-single-shift"))
687 (if (aref flags
10) (princ ", use-roman"))
688 (if (aref flags
11) (princ ", use-old-jis"))
689 (if (aref flags
12) (princ ", no-ISO6429"))
690 (if (aref flags
13) (princ ", init-bol"))
691 (if (aref flags
14) (princ ", designation-bol"))
692 (if (aref flags
15) (princ ", convert-unsafe"))
693 (if (aref flags
16) (princ ", accept-latin-extra-code"))
698 (princ " (do conversion by CCL program)"))
700 (princ " (text with random binary characters)"))
701 (t (princ ": invalid coding-system."))))
702 (princ "\nEOL type: ")
703 (let ((eol-type (coding-system-eol-type coding-system
)))
704 (cond ((vectorp eol-type
)
705 (princ "Automatic selection from:\n\t")
708 ((or (null eol-type
) (eq eol-type
0)) (princ "LF\n"))
709 ((eq eol-type
1) (princ "CRLF\n"))
710 ((eq eol-type
2) (princ "CR\n"))
711 (t (princ "invalid\n")))))
712 (let ((postread (coding-system-get coding-system
'post-read-conversion
)))
714 (princ "After decoding a text normally,")
715 (princ " perform post-conversion by the function: ")
719 (let ((prewrite (coding-system-get coding-system
'pre-write-conversion
)))
721 (princ "Before encoding a text normally,")
722 (princ " perform pre-conversion by the function: ")
727 (set-buffer standard-output
)
728 (let ((charsets (coding-system-get coding-system
'safe-charsets
)))
731 (insert "This coding system can encode all charsets.\n")
732 (insert "This coding system encode the following charsets:\n ")
734 (insert " " (symbol-name (car charsets
)))
735 (search-backward (symbol-name (car charsets
)))
736 (help-xref-button 0 #'describe-character-set
(car charsets
))
737 (goto-char (point-max))
738 (setq charsets
(cdr charsets
))))))
739 (help-setup-xref (list #'describe-coding-system coding-system
)
744 (defun describe-current-coding-system-briefly ()
745 "Display coding systems currently used in a brief format in echo area.
747 The format is \"F[..],K[..],T[..],P>[..],P<[..], default F[..],P<[..],P<[..]\",
748 where mnemonics of the following coding systems come in this order
749 at the place of `..':
750 `buffer-file-coding-system' (of the current buffer)
751 eol-type of `buffer-file-coding-system' (of the current buffer)
752 Value returned by `keyboard-coding-system'
753 eol-type of `keyboard-coding-system'
754 Value returned by `terminal-coding-system'.
755 eol-type of `terminal-coding-system'
756 `process-coding-system' for read (of the current buffer, if any)
757 eol-type of `process-coding-system' for read (of the current buffer, if any)
758 `process-coding-system' for write (of the current buffer, if any)
759 eol-type of `process-coding-system' for write (of the current buffer, if any)
760 `default-buffer-file-coding-system'
761 eol-type of `default-buffer-file-coding-system'
762 `default-process-coding-system' for read
763 eol-type of `default-process-coding-system' for read
764 `default-process-coding-system' for write
765 eol-type of `default-process-coding-system'"
767 (let* ((proc (get-buffer-process (current-buffer)))
768 (process-coding-systems (if proc
(process-coding-system proc
))))
770 "F[%c%s],K[%c%s],T[%c%s],P>[%c%s],P<[%c%s], default F[%c%s],P>[%c%s],P<[%c%s]"
771 (coding-system-mnemonic buffer-file-coding-system
)
772 (coding-system-eol-type-mnemonic buffer-file-coding-system
)
773 (coding-system-mnemonic (keyboard-coding-system))
774 (coding-system-eol-type-mnemonic (keyboard-coding-system))
775 (coding-system-mnemonic (terminal-coding-system))
776 (coding-system-eol-type-mnemonic (terminal-coding-system))
777 (coding-system-mnemonic (car process-coding-systems
))
778 (coding-system-eol-type-mnemonic (car process-coding-systems
))
779 (coding-system-mnemonic (cdr process-coding-systems
))
780 (coding-system-eol-type-mnemonic (cdr process-coding-systems
))
781 (coding-system-mnemonic default-buffer-file-coding-system
)
782 (coding-system-eol-type-mnemonic default-buffer-file-coding-system
)
783 (coding-system-mnemonic (car default-process-coding-system
))
784 (coding-system-eol-type-mnemonic (car default-process-coding-system
))
785 (coding-system-mnemonic (cdr default-process-coding-system
))
786 (coding-system-eol-type-mnemonic (cdr default-process-coding-system
))
789 ;; Print symbol name and mnemonic letter of CODING-SYSTEM with `princ'.
790 (defun print-coding-system-briefly (coding-system &optional doc-string
)
791 (if (not coding-system
)
793 (princ (format "%c -- %s"
794 (coding-system-mnemonic coding-system
)
796 (let ((aliases (coding-system-get coding-system
'alias-coding-systems
)))
797 (if (eq coding-system
(car aliases
))
799 (princ (format " %S" (cons 'alias
: (cdr aliases
)))))
800 (if (memq coding-system aliases
)
801 (princ (format " (alias of %s)" (car aliases
))))))
804 (setq doc-string
(coding-system-doc-string coding-system
)))
805 (princ (format " %s\n" doc-string
)))))
808 (defun describe-current-coding-system ()
809 "Display coding systems currently used, in detail."
811 (with-output-to-temp-buffer "*Help*"
812 (let* ((proc (get-buffer-process (current-buffer)))
813 (process-coding-systems (if proc
(process-coding-system proc
))))
814 (princ "Coding system for saving this buffer:\n ")
815 (if (local-variable-p 'buffer-file-coding-system
)
816 (print-coding-system-briefly buffer-file-coding-system
)
817 (princ "Not set locally, use the default.\n"))
818 (princ "Default coding system (for new files):\n ")
819 (print-coding-system-briefly default-buffer-file-coding-system
)
820 (princ "Coding system for keyboard input:\n ")
821 (print-coding-system-briefly (keyboard-coding-system))
822 (princ "Coding system for terminal output:\n ")
823 (print-coding-system-briefly (terminal-coding-system))
824 (when (get-buffer-process (current-buffer))
825 (princ "Coding systems for process I/O:\n")
826 (princ " encoding input to the process: ")
827 (print-coding-system-briefly (cdr process-coding-systems
))
828 (princ " decoding output from the process: ")
829 (print-coding-system-briefly (car process-coding-systems
)))
830 (princ "Defaults for subprocess I/O:\n")
831 (princ " decoding: ")
832 (print-coding-system-briefly (car default-process-coding-system
))
833 (princ " encoding: ")
834 (print-coding-system-briefly (cdr default-process-coding-system
)))
837 (set-buffer standard-output
)
839 (princ "\nPriority order for recognizing coding systems when reading files:\n")
840 (let ((l coding-category-list
)
845 (setq coding
(symbol-value (car l
)))
846 ;; Do not list up the same coding system twice.
847 (when (and coding
(not (memq coding coding-list
)))
848 (setq coding-list
(cons coding coding-list
))
849 (princ (format " %d. %s " i coding
))
850 (setq aliases
(coding-system-get coding
'alias-coding-systems
))
851 (if (eq coding
(car aliases
))
853 (princ (cons 'alias
: (cdr aliases
))))
854 (if (memq coding aliases
)
855 (princ (list 'alias
'of
(car aliases
)))))
860 (princ "\n Other coding systems cannot be distinguished automatically
861 from these, and therefore cannot be recognized automatically
862 with the present coding system priorities.\n\n")
864 (let ((categories '(coding-category-iso-7 coding-category-iso-7-else
))
865 coding-system codings
)
867 (setq coding-system
(symbol-value (car categories
)))
871 (if (and (not (eq x coding-system
))
872 (coding-system-get x
'no-initial-designation
)
873 (let ((flags (coding-system-flags x
)))
874 (not (or (aref flags
10) (aref flags
11)))))
875 (setq codings
(cons x codings
)))))
876 (get (car categories
) 'coding-systems
))
878 (let ((max-col (frame-width))
880 (princ (format " The followings are decoded correctly but recognized as %s:\n " coding-system
))
883 (insert (format " %s" (car codings
)))
884 (when (> (current-column) max-col
)
887 (goto-char (point-max)))
888 (setq codings
(cdr codings
)))
890 (setq categories
(cdr categories
))))
892 (princ "Particular coding systems specified for certain file names:\n")
894 (princ " OPERATION\tTARGET PATTERN\t\tCODING SYSTEM(s)\n")
895 (princ " ---------\t--------------\t\t----------------\n")
896 (let ((func (lambda (operation alist
)
900 (princ "\tnothing specified\n")
903 (prin1 (car (car alist
)))
904 (if (>= (current-column) 40)
907 (princ (cdr (car alist
)))
909 (setq alist
(cdr alist
)))))))
910 (funcall func
"File I/O" file-coding-system-alist
)
911 (funcall func
"Process I/O" process-coding-system-alist
)
912 (funcall func
"Network I/O" network-coding-system-alist
))
915 ;; Print detailed information on CODING-SYSTEM.
916 (defun print-coding-system (coding-system)
917 (let ((type (coding-system-type coding-system
))
918 (eol-type (coding-system-eol-type coding-system
))
919 (flags (coding-system-flags coding-system
))
920 (aliases (coding-system-get coding-system
'alias-coding-systems
)))
921 (if (not (eq (car aliases
) coding-system
))
922 (princ (format "%s (alias of %s)\n" coding-system
(car aliases
)))
923 (princ coding-system
)
924 (setq aliases
(cdr aliases
))
927 (princ (car aliases
))
928 (setq aliases
(cdr aliases
)))
929 (princ (format ":%s:%c:%d:"
931 (coding-system-mnemonic coding-system
)
932 (if (integerp eol-type
) eol-type
3)))
933 (cond ((eq type
2) ; ISO-2022
937 (setq charset
(aref flags idx
))
938 (cond ((null charset
)
946 (princ (car charset
))
947 (setq charset
(cdr charset
))
950 (princ (car charset
))
951 (setq charset
(cdr charset
)))
956 (princ (if (aref flags idx
) 1 0))
959 (princ (if (aref flags idx
) 1 0))))
962 (if (symbolp (car flags
))
963 (princ (format " %s" (car flags
)))
964 (setq i
0 len
(length (car flags
)))
966 (princ (format " %x" (aref (car flags
) i
)))
969 (if (symbolp (cdr flags
))
970 (princ (format "%s" (cdr flags
)))
971 (setq i
0 len
(length (cdr flags
)))
973 (princ (format " %x" (aref (cdr flags
) i
)))
977 (princ (coding-system-doc-string coding-system
))
981 (defun list-coding-systems (&optional arg
)
982 "Display a list of all coding systems.
983 This shows the mnemonic letter, name, and description of each coding system.
985 With prefix arg, the output format gets more cryptic,
986 but still contains full information about each coding system."
988 (with-output-to-temp-buffer "*Help*"
989 (list-coding-systems-1 arg
)))
991 (defun list-coding-systems-1 (arg)
994 ###############################################
995 # List of coding systems in the following format:
996 # MNEMONIC-LETTER -- CODING-SYSTEM-NAME
1000 #########################
1001 ## LIST OF CODING SYSTEMS
1002 ## Each line corresponds to one coding system
1003 ## Format of a line is:
1004 ## NAME[,ALIAS...]:TYPE:MNEMONIC:EOL:FLAGS:POST-READ-CONVERSION
1005 ## :PRE-WRITE-CONVERSION:DOC-STRING,
1007 ## NAME = coding system name
1008 ## ALIAS = alias of the coding system
1009 ## TYPE = nil (no conversion), t (undecided or automatic detection),
1010 ## 0 (EMACS-MULE), 1 (SJIS), 2 (ISO2022), 3 (BIG5), or 4 (CCL)
1011 ## EOL = 0 (LF), 1 (CRLF), 2 (CR), or 3 (Automatic detection)
1014 ## comma (`,') separated data of the followings:
1015 ## G0, G1, G2, G3, SHORT-FORM, ASCII-EOL, ASCII-CNTL, SEVEN,
1016 ## LOCKING-SHIFT, SINGLE-SHIFT, USE-ROMAN, USE-OLDJIS, NO-ISO6429
1017 ## else if TYPE = 4 then
1018 ## comma (`,') separated CCL programs for read and write
1021 ## POST-READ-CONVERSION, PRE-WRITE-CONVERSION = function name to be called
1024 (let ((bases (coding-system-list 'base-only
))
1027 (setq coding-system
(car bases
))
1029 (print-coding-system-briefly coding-system
'doc-string
)
1030 (print-coding-system coding-system
))
1031 (setq bases
(cdr bases
)))))
1034 (defun list-coding-categories ()
1035 "Display a list of all coding categories."
1036 (with-output-to-temp-buffer "*Help*"
1038 ############################
1039 ## LIST OF CODING CATEGORIES (ordered by priority)
1040 ## CATEGORY:CODING-SYSTEM
1043 (let ((l coding-category-list
))
1045 (princ (format "%s:%s\n" (car l
) (symbol-value (car l
))))
1046 (setq l
(cdr l
))))))
1050 ;; Print information of a font in FONTINFO.
1051 (defun describe-font-internal (font-info &optional verbose
)
1052 (print-list "name (opened by):" (aref font-info
0))
1053 (print-list " full name:" (aref font-info
1))
1054 (print-list " size:" (format "%2d" (aref font-info
2)))
1055 (print-list " height:" (format "%2d" (aref font-info
3)))
1056 (print-list " baseline-offset:" (format "%2d" (aref font-info
4)))
1057 (print-list "relative-compose:" (format "%2d" (aref font-info
5))))
1060 (defun describe-font (fontname)
1061 "Display information about fonts which partially match FONTNAME."
1062 (interactive "sFontname (default, current choice for ASCII chars): ")
1063 (or (and window-system
(fboundp 'fontset-list
))
1064 (error "No fontsets being used"))
1065 (when (or (not fontname
) (= (length fontname
) 0))
1066 (setq fontname
(cdr (assq 'font
(frame-parameters))))
1067 (if (query-fontset fontname
)
1069 (nth 1 (assq 'ascii
(aref (fontset-info fontname
) 2))))))
1070 (let ((font-info (font-info fontname
)))
1071 (if (null font-info
)
1072 (message "No matching font")
1073 (with-output-to-temp-buffer "*Help*"
1074 (describe-font-internal font-info
'verbose
)))))
1076 ;; Print information of FONTSET. If optional arg PRINT-FONTS is
1077 ;; non-nil, print also names of all opened fonts for FONTSET. This
1078 ;; function actually INSERT such information in the current buffer.
1079 (defun print-fontset (fontset &optional print-fonts
)
1080 (let ((tail (aref (fontset-info fontset
) 2))
1081 elt chars font-spec opened prev-charset charset from to
)
1083 (insert "Fontset: " fontset
"\n")
1084 (insert "CHARSET or CHAR RANGE")
1086 (insert "FONT NAME\n")
1087 (insert "---------------------")
1089 (insert "---------")
1092 (setq elt
(car tail
) tail
(cdr tail
))
1093 (setq chars
(car elt
) font-spec
(car (cdr elt
)) opened
(cdr (cdr elt
)))
1095 (setq charset chars from nil to nil
)
1096 (if (integerp chars
)
1097 (setq charset
(char-charset chars
) from chars to chars
)
1098 (setq charset
(char-charset (car chars
))
1099 from
(car chars
) to
(cdr chars
))))
1100 (unless (eq charset prev-charset
)
1101 (insert (symbol-name charset
))
1105 (let ((split (split-char from
)))
1106 (if (and (= (charset-dimension charset
) 2)
1107 (= (nth 2 split
) 0))
1109 (make-char charset
(nth 1 split
)
1110 (if (= (charset-chars charset
) 94) 33 32))))
1114 (let ((split (split-char to
)))
1115 (if (and (= (charset-dimension charset
) 2)
1116 (= (nth 2 split
) 0))
1118 (make-char charset
(nth 1 split
)
1119 (if (= (charset-chars charset
) 94) 126 127))))
1122 (if (stringp font-spec
)
1125 (if (string-match "-" (car font-spec
))
1126 (insert "-" (car font-spec
) "-*-")
1127 (insert "-*-" (car font-spec
) "-*-"))
1130 (if (string-match "-" (cdr font-spec
))
1131 (insert (cdr font-spec
))
1132 (insert (cdr font-spec
) "-*"))
1138 (insert "[" (car opened
) "]\n")
1139 (setq opened
(cdr opened
))))
1140 (setq prev-charset charset
)
1144 (defun describe-fontset (fontset)
1145 "Display information of FONTSET.
1146 This shows which font is used for which character(s)."
1148 (if (not (and window-system
(fboundp 'fontset-list
)))
1149 (error "No fontsets being used")
1150 (let ((fontset-list (append
1151 (mapcar 'list
(fontset-list))
1152 (mapcar (lambda (x) (list (cdr x
)))
1153 fontset-alias-alist
)))
1154 (completion-ignore-case t
))
1155 (list (completing-read
1156 "Fontset (default, used by the current frame): "
1157 fontset-list nil t
)))))
1158 (if (= (length fontset
) 0)
1159 (setq fontset
(cdr (assq 'font
(frame-parameters)))))
1160 (if (not (setq fontset
(query-fontset fontset
)))
1161 (error "Current frame is using font, not fontset"))
1162 (with-output-to-temp-buffer "*Help*"
1164 (set-buffer standard-output
)
1165 (print-fontset fontset t
))))
1168 (defun list-fontsets (arg)
1169 "Display a list of all fontsets.
1170 This shows the name, size, and style of each fontset.
1171 With prefix arg, it also list the fonts contained in each fontset;
1172 see the function `describe-fontset' for the format of the list."
1174 (if (not (and window-system
(fboundp 'fontset-list
)))
1175 (error "No fontsets being used")
1176 (with-output-to-temp-buffer "*Help*"
1178 ;; This code is duplicated near the end of mule-diag.
1179 (set-buffer standard-output
)
1181 (sort (fontset-list)
1182 (function (lambda (x y
)
1183 (string< (fontset-plain-name x
)
1184 (fontset-plain-name y
)))))))
1187 (print-fontset (car fontsets
) nil
)
1188 (insert "Fontset: " (car fontsets
) "\n"))
1189 (setq fontsets
(cdr fontsets
))))))))
1192 (defun list-input-methods ()
1193 "Display information about all input methods."
1195 (with-output-to-temp-buffer "*Help*"
1196 (list-input-methods-1)))
1198 (defun list-input-methods-1 ()
1199 (if (not input-method-alist
)
1202 No input method is available, perhaps because you have not yet
1203 installed LEIM (Libraries of Emacs Input Method).
1205 LEIM is available from the same ftp directory as Emacs. For instance,
1206 if there exists an archive file `emacs-20.N.tar.gz', there should also
1207 be a file `leim-20.N.tar.gz'. When you extract this file, LEIM files
1208 are put under the subdirectory `emacs-20.N/leim'. When you install
1209 Emacs again, you should be able to use various input methods."))
1210 (princ "LANGUAGE\n NAME (`TITLE' in mode line)\n")
1211 (princ " SHORT-DESCRIPTION\n------------------------------\n")
1212 (setq input-method-alist
1213 (sort input-method-alist
1214 (function (lambda (x y
) (string< (nth 1 x
) (nth 1 y
))))))
1215 (let ((l input-method-alist
)
1218 (setq elt
(car l
) l
(cdr l
))
1219 (when (not (equal language
(nth 1 elt
)))
1220 (setq language
(nth 1 elt
))
1223 (princ (format " %s (`%s' in mode line)\n %s\n"
1225 (let ((title (nth 3 elt
)))
1226 (if (and (consp title
) (stringp (car title
)))
1229 (let ((description (nth 4 elt
)))
1230 (string-match ".*" description
)
1231 (match-string 0 description
))))))))
1235 ;; Insert a header of a section with SECTION-NUMBER and TITLE.
1236 (defun insert-section (section-number title
)
1237 (insert "########################################\n"
1238 "# Section " (format "%d" section-number
) ". " title
"\n"
1239 "########################################\n\n"))
1243 "Display diagnosis of the multilingual environment (Mule).
1245 This shows various information related to the current multilingual
1246 environment, including lists of input methods, coding systems,
1247 character sets, and fontsets (if Emacs is running under a window
1248 system which uses fontsets)."
1250 (with-output-to-temp-buffer "*Mule-Diagnosis*"
1252 (set-buffer standard-output
)
1253 (insert "###############################################\n"
1254 "### Current Status of Multilingual Features ###\n"
1255 "###############################################\n\n"
1256 "CONTENTS: Section 1. General Information\n"
1257 " Section 2. Display\n"
1258 " Section 3. Input methods\n"
1259 " Section 4. Coding systems\n"
1260 " Section 5. Character sets\n")
1261 (if (and window-system
(fboundp 'fontset-list
))
1262 (insert " Section 6. Fontsets\n"))
1265 (insert-section 1 "General Information")
1266 (insert "Version of this emacs:\n " (emacs-version) "\n\n")
1268 (insert-section 2 "Display")
1270 (insert "Window-system: "
1271 (symbol-name window-system
)
1272 (format "%s" window-system-version
))
1273 (insert "Terminal: " (getenv "TERM")))
1276 (if (eq window-system
'x
)
1277 (let ((font (cdr (assq 'font
(frame-parameters)))))
1278 (insert "The selected frame is using the "
1279 (if (query-fontset font
) "fontset" "font")
1281 (insert "Coding system of the terminal: "
1282 (symbol-name (terminal-coding-system))))
1285 (insert-section 3 "Input methods")
1286 (list-input-methods-1)
1288 (if default-input-method
1289 (insert (format "Default input method: %s\n" default-input-method
))
1290 (insert "No default input method is specified\n"))
1292 (insert-section 4 "Coding systems")
1293 (list-coding-systems-1 t
)
1295 ############################
1296 ## LIST OF CODING CATEGORIES (ordered by priority)
1297 ## CATEGORY:CODING-SYSTEM
1300 (let ((l coding-category-list
))
1302 (princ (format "%s:%s\n" (car l
) (symbol-value (car l
))))
1306 (insert-section 5 "Character sets")
1307 (list-character-sets-2)
1310 (when (and window-system
(fboundp 'fontset-list
))
1311 ;; This code duplicates most of list-fontsets.
1312 (insert-section 6 "Fontsets")
1313 (insert "Fontset-Name\t\t\t\t\t\t WDxHT Style\n")
1314 (insert "------------\t\t\t\t\t\t ----- -----\n")
1315 (let ((fontsets (fontset-list)))
1317 (print-fontset (car fontsets
) t
)
1318 (setq fontsets
(cdr fontsets
)))))
1319 (print-help-return-message))))
1325 (defun dump-charsets ()
1326 "Dump information about all charsets into the file `CHARSETS'.
1327 The file is saved in the directory `data-directory'."
1328 (let ((file (expand-file-name "CHARSETS" data-directory
))
1330 (or (file-writable-p file
)
1331 (error "Can't write to file %s" file
))
1332 (setq buf
(find-file-noselect file
))
1333 (save-window-excursion
1336 (setq buffer-read-only nil
)
1338 (list-character-sets-2)
1339 (insert-buffer-substring "*Help*")
1340 (let (make-backup-files
1341 coding-system-for-write
)
1348 (defun dump-codings ()
1349 "Dump information about all coding systems into the file `CODINGS'.
1350 The file is saved in the directory `data-directory'."
1351 (let ((file (expand-file-name "CODINGS" data-directory
))
1353 (or (file-writable-p file
)
1354 (error "Can't write to file %s" file
))
1355 (setq buf
(find-file-noselect file
))
1356 (save-window-excursion
1359 (setq buffer-read-only nil
)
1361 (list-coding-systems t
)
1362 (insert-buffer-substring "*Help*")
1363 (list-coding-categories)
1364 (insert-buffer-substring "*Help*")
1365 (let (make-backup-files
1366 coding-system-for-write
)
1372 ;;; mule-diag.el ends here