Commit | Line | Data |
---|---|---|
a8581027 | 1 | ;;; format.el --- read and save files in multiple formats |
b578f267 | 2 | |
c84cf2bf | 3 | ;; Copyright (c) 1994, 1995, 1997 Free Software Foundation |
029894b9 | 4 | |
7865eac6 | 5 | ;; Author: Boris Goldowsky <boris@gnu.ai.mit.edu> |
029894b9 BG |
6 | |
7 | ;; This file is part of GNU Emacs. | |
8 | ||
9 | ;; GNU Emacs is free software; you can redistribute it and/or modify | |
10 | ;; it under the terms of the GNU General Public License as published by | |
11 | ;; the Free Software Foundation; either version 2, or (at your option) | |
12 | ;; any later version. | |
b578f267 | 13 | |
029894b9 BG |
14 | ;; GNU Emacs is distributed in the hope that it will be useful, |
15 | ;; but WITHOUT ANY WARRANTY; without even the implied warranty of | |
16 | ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
17 | ;; GNU General Public License for more details. | |
b578f267 | 18 | |
029894b9 | 19 | ;; You should have received a copy of the GNU General Public License |
b578f267 EN |
20 | ;; along with GNU Emacs; see the file COPYING. If not, write to the |
21 | ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330, | |
22 | ;; Boston, MA 02111-1307, USA. | |
029894b9 BG |
23 | |
24 | ;;; Commentary: | |
b578f267 EN |
25 | |
26 | ;; This file defines a unified mechanism for saving & loading files stored | |
27 | ;; in different formats. `format-alist' contains information that directs | |
029894b9 BG |
28 | ;; Emacs to call an encoding or decoding function when reading or writing |
29 | ;; files that match certain conditions. | |
30 | ;; | |
b578f267 EN |
31 | ;; When a file is visited, its format is determined by matching the |
32 | ;; beginning of the file against regular expressions stored in | |
33 | ;; `format-alist'. If this fails, you can manually translate the buffer | |
34 | ;; using `format-decode-buffer'. In either case, the formats used are | |
35 | ;; listed in the variable `buffer-file-format', and become the default | |
36 | ;; format for saving the buffer. To save a buffer in a different format, | |
37 | ;; change this variable, or use `format-write-file'. | |
029894b9 BG |
38 | ;; |
39 | ;; Auto-save files are normally created in the same format as the visited | |
b578f267 EN |
40 | ;; file, but the variable `auto-save-file-format' can be set to a |
41 | ;; particularly fast or otherwise preferred format to be used for | |
42 | ;; auto-saving (or nil to do no encoding on auto-save files, but then you | |
43 | ;; risk losing any text-properties in the buffer). | |
029894b9 | 44 | ;; |
b578f267 EN |
45 | ;; You can manually translate a buffer into or out of a particular format |
46 | ;; with the functions `format-encode-buffer' and `format-decode-buffer'. | |
47 | ;; To translate just the region use the functions `format-encode-region' | |
48 | ;; and `format-decode-region'. | |
029894b9 | 49 | ;; |
b578f267 EN |
50 | ;; You can define a new format by writing the encoding and decoding |
51 | ;; functions, and adding an entry to `format-alist'. See enriched.el for | |
52 | ;; an example of how to implement a file format. There are various | |
53 | ;; functions defined in this file that may be useful for writing the | |
54 | ;; encoding and decoding functions: | |
55 | ;; * `format-annotate-region' and `format-deannotate-region' allow a | |
56 | ;; single alist of information to be used for encoding and decoding. | |
57 | ;; The alist defines a correspondence between strings in the file | |
58 | ;; ("annotations") and text-properties in the buffer. | |
029894b9 BG |
59 | ;; * `format-replace-strings' is similarly useful for doing simple |
60 | ;; string->string translations in a reversible manner. | |
61 | ||
b578f267 EN |
62 | ;;; Code: |
63 | ||
029894b9 BG |
64 | (put 'buffer-file-format 'permanent-local t) |
65 | ||
4c8a3b19 | 66 | (defvar format-alist |
c84cf2bf RS |
67 | '((compressed "compressed" |
68 | "^\037\213" ; magic number for gzip | |
69 | "gunzip -f" "gzip -f" t nil) | |
70 | (text/enriched "Extended MIME text/enriched format." | |
029894b9 BG |
71 | "Content-[Tt]ype:[ \t]*text/enriched" |
72 | enriched-decode enriched-encode t enriched-mode) | |
c84cf2bf | 73 | (plain "ISO 8859-1 standard format, no text properties." |
029894b9 BG |
74 | ;; Plain only exists so that there is an obvious neutral choice in |
75 | ;; the completion list. | |
c84cf2bf RS |
76 | nil nil nil nil nil) |
77 | (ibm "IBM Code Page 850 (DOS)" | |
78 | "1\\(^\\)" | |
79 | "recode ibm-ps:latin1" "recode latin1:ibm-pc" t nil) | |
80 | (mac "Apple Macintosh" | |
81 | "1\\(^\\)" | |
82 | "recode mac:latin1" "recode latin1:mac" t nil) | |
83 | (hp "HP Roman8" | |
84 | "1\\(^\\)" | |
85 | "recode roman8:latin1" "recode latin1:roman8" t nil) | |
86 | (TeX "TeX (encoding)" | |
87 | "1\\(^\\)" | |
88 | iso-tex2iso iso-iso2tex t nil) | |
89 | (gtex "German TeX (encoding)" | |
90 | "1\\(^\\)" | |
91 | iso-gtex2iso iso-iso2gtex t nil) | |
92 | (html "HTML (encoding)" | |
93 | "1\\(^\\)" | |
94 | "recode html:latin1" "recode latin1:html" t nil) | |
95 | (rot13 "rot13" | |
96 | "1\\(^\\)" | |
97 | "tr a-mn-z n-za-m" "tr a-mn-z n-za-m" t nil) | |
98 | (duden "Duden Ersatzdarstellung" | |
99 | "1\\(^\\)" | |
100 | "diac" iso-iso2duden t nil) | |
101 | (de646 "German ASCII (ISO 646)" | |
102 | "1\\(^\\)" | |
103 | "recode iso646-ge:latin1" "recode latin1:iso646-ge" t nil) | |
104 | (denet "net German" | |
105 | "1\\(^\\)" | |
106 | iso-german iso-cvt-read-only t nil) | |
107 | (esnet "net Spanish" | |
108 | "1\\(^\\)" | |
109 | iso-spanish iso-cvt-read-onlyt nil)) | |
029894b9 BG |
110 | "List of information about understood file formats. |
111 | Elements are of the form \(NAME DOC-STR REGEXP FROM-FN TO-FN MODIFY MODE-FN). | |
112 | NAME is a symbol, which is stored in `buffer-file-format'. | |
113 | DOC-STR should be a single line providing more information about the | |
114 | format. It is currently unused, but in the future will be shown to | |
115 | the user if they ask for more information. | |
116 | REGEXP is a regular expression to match against the beginning of the file; | |
117 | it should match only files in that format. | |
118 | FROM-FN is called to decode files in that format; it gets two args, BEGIN | |
119 | and END, and can make any modifications it likes, returning the new | |
120 | end. It must make sure that the beginning of the file no longer | |
121 | matches REGEXP, or else it will get called again. | |
d1abb42f RS |
122 | TO-FN is called to encode a region into that format; it is passed three |
123 | arguments: BEGIN, END, and BUFFER. BUFFER is the original buffer that | |
124 | the data being written came from, which the function could use, for | |
125 | example, to find the values of local variables. TO-FN should either | |
126 | return a list of annotations like `write-region-annotate-functions', | |
127 | or modify the region and return the new end. | |
128 | MODIFY, if non-nil, means the TO-FN wants to modify the region. If nil, | |
129 | TO-FN will not make any changes but will instead return a list of | |
130 | annotations. | |
029894b9 BG |
131 | MODE-FN, if specified, is called when visiting a file with that format.") |
132 | ||
133 | ;;; Basic Functions (called from Lisp) | |
134 | ||
c84cf2bf RS |
135 | (defun format-encode-run-method (method from to &optional buffer) |
136 | "Translate using function or shell script METHOD the text from FROM to TO. | |
137 | If METHOD is a string, it is a shell command; | |
138 | otherwise, it should be a Lisp function. | |
139 | BUFFER should be the buffer that the output originally came from." | |
140 | (if (stringp method) | |
141 | (save-current-buffer | |
142 | (set-buffer buffer) | |
143 | (shell-command-on-region from to method t) | |
144 | (point)) | |
145 | (funcall method from to buffer))) | |
146 | ||
147 | (defun format-decode-run-method (method from to &optional buffer) | |
148 | "Decode using function or shell script METHOD the text from FROM to TO. | |
149 | If METHOD is a string, it is a shell command; | |
150 | otherwise, it should be a Lisp function." | |
151 | (if (stringp method) | |
152 | (progn | |
153 | (shell-command-on-region from to method t) | |
154 | (point)) | |
155 | (funcall method from to))) | |
156 | ||
d1abb42f | 157 | (defun format-annotate-function (format from to orig-buf) |
029894b9 BG |
158 | "Returns annotations for writing region as FORMAT. |
159 | FORMAT is a symbol naming one of the formats defined in `format-alist', | |
160 | it must be a single symbol, not a list like `buffer-file-format'. | |
d1abb42f RS |
161 | FROM and TO delimit the region to be operated on in the current buffer. |
162 | ORIG-BUF is the original buffer that the data came from. | |
029894b9 BG |
163 | This function works like a function on `write-region-annotate-functions': |
164 | it either returns a list of annotations, or returns with a different buffer | |
165 | current, which contains the modified text to write. | |
166 | ||
167 | For most purposes, consider using `format-encode-region' instead." | |
168 | ;; This function is called by write-region (actually build-annotations) | |
169 | ;; for each element of buffer-file-format. | |
170 | (let* ((info (assq format format-alist)) | |
171 | (to-fn (nth 4 info)) | |
172 | (modify (nth 5 info))) | |
173 | (if to-fn | |
174 | (if modify | |
175 | ;; To-function wants to modify region. Copy to safe place. | |
176 | (let ((copy-buf (get-buffer-create " *Format Temp*"))) | |
177 | (copy-to-buffer copy-buf from to) | |
178 | (set-buffer copy-buf) | |
179 | (format-insert-annotations write-region-annotations-so-far from) | |
c84cf2bf | 180 | (format-encode-run-method to-fn (point-min) (point-max) orig-buf) |
029894b9 BG |
181 | nil) |
182 | ;; Otherwise just call function, it will return annotations. | |
d1abb42f | 183 | (funcall to-fn from to orig-buf))))) |
029894b9 BG |
184 | |
185 | (defun format-decode (format length &optional visit-flag) | |
186 | ;; This function is called by insert-file-contents whenever a file is read. | |
187 | "Decode text from any known FORMAT. | |
188 | FORMAT is a symbol appearing in `format-alist' or a list of such symbols, | |
189 | or nil, in which case this function tries to guess the format of the data by | |
190 | matching against the regular expressions in `format-alist'. After a match is | |
191 | found and the region decoded, the alist is searched again from the beginning | |
192 | for another match. | |
193 | ||
194 | Second arg LENGTH is the number of characters following point to operate on. | |
195 | If optional third arg VISIT-FLAG is true, set `buffer-file-format' | |
196 | to the list of formats used, and call any mode functions defined for those | |
197 | formats. | |
198 | ||
199 | Returns the new length of the decoded region. | |
200 | ||
201 | For most purposes, consider using `format-decode-region' instead." | |
202 | (let ((mod (buffer-modified-p)) | |
203 | (begin (point)) | |
204 | (end (+ (point) length))) | |
205 | (if (null format) | |
206 | ;; Figure out which format it is in, remember list in `format'. | |
207 | (let ((try format-alist)) | |
208 | (while try | |
209 | (let* ((f (car try)) | |
210 | (regexp (nth 2 f)) | |
211 | (p (point))) | |
212 | (if (and regexp (looking-at regexp) | |
213 | (< (match-end 0) (+ begin length))) | |
214 | (progn | |
215 | (setq format (cons (car f) format)) | |
216 | ;; Decode it | |
c84cf2bf RS |
217 | (if (nth 3 f) |
218 | (setq end (format-decode-run-method (nth 3 f) begin end))) | |
029894b9 BG |
219 | ;; Call visit function if required |
220 | (if (and visit-flag (nth 6 f)) (funcall (nth 6 f) 1)) | |
221 | ;; Safeguard against either of the functions changing pt. | |
222 | (goto-char p) | |
223 | ;; Rewind list to look for another format | |
224 | (setq try format-alist)) | |
225 | (setq try (cdr try)))))) | |
226 | ;; Deal with given format(s) | |
227 | (or (listp format) (setq format (list format))) | |
228 | (let ((do format) f) | |
229 | (while do | |
230 | (or (setq f (assq (car do) format-alist)) | |
231 | (error "Unknown format" (car do))) | |
232 | ;; Decode: | |
c84cf2bf RS |
233 | (if (nth 3 f) |
234 | (setq end (format-decode-run-method (nth 3 f) begin end))) | |
029894b9 BG |
235 | ;; Call visit function if required |
236 | (if (and visit-flag (nth 6 f)) (funcall (nth 6 f) 1)) | |
237 | (setq do (cdr do))))) | |
238 | (if visit-flag | |
239 | (setq buffer-file-format format)) | |
240 | (set-buffer-modified-p mod) | |
241 | ;; Return new length of region | |
242 | (- end begin))) | |
243 | ||
244 | ;;; | |
245 | ;;; Interactive functions & entry points | |
246 | ;;; | |
247 | ||
248 | (defun format-decode-buffer (&optional format) | |
249 | "Translate the buffer from some FORMAT. | |
250 | If the format is not specified, this function attempts to guess. | |
251 | `buffer-file-format' is set to the format used, and any mode-functions | |
252 | for the format are called." | |
253 | (interactive | |
254 | (list (format-read "Translate buffer from format (default: guess): "))) | |
255 | (save-excursion | |
256 | (goto-char (point-min)) | |
257 | (format-decode format (buffer-size) t))) | |
258 | ||
259 | (defun format-decode-region (from to &optional format) | |
260 | "Decode the region from some format. | |
261 | Arg FORMAT is optional; if omitted the format will be determined by looking | |
262 | for identifying regular expressions at the beginning of the region." | |
263 | (interactive | |
264 | (list (region-beginning) (region-end) | |
265 | (format-read "Translate region from format (default: guess): "))) | |
266 | (save-excursion | |
267 | (goto-char from) | |
268 | (format-decode format (- to from) nil))) | |
269 | ||
270 | (defun format-encode-buffer (&optional format) | |
271 | "Translate the buffer into FORMAT. | |
272 | FORMAT defaults to `buffer-file-format'. It is a symbol naming one of the | |
273 | formats defined in `format-alist', or a list of such symbols." | |
274 | (interactive | |
275 | (list (format-read (format "Translate buffer to format (default %s): " | |
276 | buffer-file-format)))) | |
277 | (format-encode-region (point-min) (point-max) format)) | |
278 | ||
279 | (defun format-encode-region (beg end &optional format) | |
280 | "Translate the region into some FORMAT. | |
281 | FORMAT defaults to `buffer-file-format', it is a symbol naming | |
282 | one of the formats defined in `format-alist', or a list of such symbols." | |
283 | (interactive | |
284 | (list (region-beginning) (region-end) | |
285 | (format-read (format "Translate region to format (default %s): " | |
286 | buffer-file-format)))) | |
287 | (if (null format) (setq format buffer-file-format)) | |
288 | (if (symbolp format) (setq format (list format))) | |
289 | (save-excursion | |
290 | (goto-char end) | |
291 | (let ((cur-buf (current-buffer)) | |
292 | (end (point-marker))) | |
293 | (while format | |
294 | (let* ((info (assq (car format) format-alist)) | |
295 | (to-fn (nth 4 info)) | |
296 | (modify (nth 5 info)) | |
297 | result) | |
298 | (if to-fn | |
299 | (if modify | |
c84cf2bf RS |
300 | (setq end (format-encode-run-method to-fn beg end |
301 | (current-buffer))) | |
d1abb42f RS |
302 | (format-insert-annotations |
303 | (funcall to-fn beg end (current-buffer))))) | |
029894b9 BG |
304 | (setq format (cdr format))))))) |
305 | ||
306 | (defun format-write-file (filename format) | |
307 | "Write current buffer into a FILE using some FORMAT. | |
308 | Makes buffer visit that file and sets the format as the default for future | |
309 | saves. If the buffer is already visiting a file, you can specify a directory | |
310 | name as FILE, to write a file of the same old name in that directory." | |
311 | (interactive | |
312 | ;; Same interactive spec as write-file, plus format question. | |
313 | (let* ((file (if buffer-file-name | |
314 | (read-file-name "Write file: " | |
315 | nil nil nil nil) | |
316 | (read-file-name "Write file: " | |
317 | (cdr (assq 'default-directory | |
318 | (buffer-local-variables))) | |
319 | nil nil (buffer-name)))) | |
320 | (fmt (format-read (format "Write file `%s' in format: " | |
321 | (file-name-nondirectory file))))) | |
322 | (list file fmt))) | |
323 | (setq buffer-file-format format) | |
324 | (write-file filename)) | |
325 | ||
ce6af52b KH |
326 | (defun format-find-file (filename format) |
327 | "Find the file FILE using data format FORMAT. | |
328 | If FORMAT is nil then do not do any format conversion." | |
329 | (interactive | |
330 | ;; Same interactive spec as write-file, plus format question. | |
331 | (let* ((file (read-file-name "Find file: ")) | |
332 | (fmt (format-read (format "Read file `%s' in format: " | |
333 | (file-name-nondirectory file))))) | |
334 | (list file fmt))) | |
335 | (let ((format-alist nil)) | |
336 | (find-file filename)) | |
337 | (if format | |
338 | (format-decode-buffer format))) | |
339 | ||
340 | (defun format-insert-file (filename format &optional beg end) | |
341 | "Insert the contents of file FILE using data format FORMAT. | |
342 | If FORMAT is nil then do not do any format conversion. | |
343 | The optional third and fourth arguments BEG and END specify | |
344 | the part of the file to read. | |
345 | ||
346 | The return value is like the value of `insert-file-contents': | |
347 | a list (ABSOLUTE-FILE-NAME . SIZE)." | |
348 | (interactive | |
349 | ;; Same interactive spec as write-file, plus format question. | |
350 | (let* ((file (read-file-name "Find file: ")) | |
351 | (fmt (format-read (format "Read file `%s' in format: " | |
352 | (file-name-nondirectory file))))) | |
353 | (list file fmt))) | |
354 | (let (value size) | |
355 | (let ((format-alist nil)) | |
356 | (setq value (insert-file-contents filename nil beg end)) | |
357 | (setq size (nth 1 value))) | |
358 | (if format | |
c84cf2bf | 359 | (setq size (format-decode format size) |
ce6af52b KH |
360 | value (cons (car value) size))) |
361 | value)) | |
362 | ||
029894b9 BG |
363 | (defun format-read (&optional prompt) |
364 | "Read and return the name of a format. | |
365 | Return value is a list, like `buffer-file-format'; it may be nil. | |
366 | Formats are defined in `format-alist'. Optional arg is the PROMPT to use." | |
367 | (let* ((table (mapcar (lambda (x) (list (symbol-name (car x)))) | |
368 | format-alist)) | |
369 | (ans (completing-read (or prompt "Format: ") table nil t))) | |
370 | (if (not (equal "" ans)) (list (intern ans))))) | |
371 | ||
372 | ||
373 | ;;; | |
374 | ;;; Below are some functions that may be useful in writing encoding and | |
375 | ;;; decoding functions for use in format-alist. | |
376 | ;;; | |
377 | ||
378 | (defun format-replace-strings (alist &optional reverse beg end) | |
379 | "Do multiple replacements on the buffer. | |
380 | ALIST is a list of (from . to) pairs, which should be proper arguments to | |
381 | `search-forward' and `replace-match' respectively. | |
382 | Optional 2nd arg REVERSE, if non-nil, means the pairs are (to . from), so that | |
383 | you can use the same list in both directions if it contains only literal | |
384 | strings. | |
385 | Optional args BEGIN and END specify a region of the buffer to operate on." | |
386 | (save-excursion | |
387 | (save-restriction | |
388 | (or beg (setq beg (point-min))) | |
389 | (if end (narrow-to-region (point-min) end)) | |
390 | (while alist | |
391 | (let ((from (if reverse (cdr (car alist)) (car (car alist)))) | |
392 | (to (if reverse (car (cdr alist)) (cdr (car alist))))) | |
393 | (goto-char beg) | |
394 | (while (search-forward from nil t) | |
395 | (goto-char (match-beginning 0)) | |
396 | (insert to) | |
397 | (set-text-properties (- (point) (length to)) (point) | |
398 | (text-properties-at (point))) | |
399 | (delete-region (point) (+ (point) (- (match-end 0) | |
400 | (match-beginning 0))))) | |
401 | (setq alist (cdr alist))))))) | |
402 | ||
403 | ;;; Some list-manipulation functions that we need. | |
404 | ||
405 | (defun format-delq-cons (cons list) | |
406 | "Remove the given CONS from LIST by side effect, | |
407 | and return the new LIST. Since CONS could be the first element | |
408 | of LIST, write `\(setq foo \(format-delq-cons element foo))' to be sure of | |
409 | changing the value of `foo'." | |
410 | (if (eq cons list) | |
411 | (cdr list) | |
412 | (let ((p list)) | |
413 | (while (not (eq (cdr p) cons)) | |
414 | (if (null p) (error "format-delq-cons: not an element.")) | |
415 | (setq p (cdr p))) | |
416 | ;; Now (cdr p) is the cons to delete | |
417 | (setcdr p (cdr cons)) | |
418 | list))) | |
419 | ||
420 | (defun format-make-relatively-unique (a b) | |
421 | "Delete common elements of lists A and B, return as pair. | |
422 | Compares using `equal'." | |
423 | (let* ((acopy (copy-sequence a)) | |
424 | (bcopy (copy-sequence b)) | |
425 | (tail acopy)) | |
426 | (while tail | |
427 | (let ((dup (member (car tail) bcopy)) | |
428 | (next (cdr tail))) | |
429 | (if dup (setq acopy (format-delq-cons tail acopy) | |
430 | bcopy (format-delq-cons dup bcopy))) | |
431 | (setq tail next))) | |
432 | (cons acopy bcopy))) | |
433 | ||
434 | (defun format-common-tail (a b) | |
435 | "Given two lists that have a common tail, return it. | |
436 | Compares with `equal', and returns the part of A that is equal to the | |
437 | equivalent part of B. If even the last items of the two are not equal, | |
438 | returns nil." | |
439 | (let ((la (length a)) | |
440 | (lb (length b))) | |
441 | ;; Make sure they are the same length | |
442 | (if (> la lb) | |
443 | (setq a (nthcdr (- la lb) a)) | |
444 | (setq b (nthcdr (- lb la) b)))) | |
445 | (while (not (equal a b)) | |
446 | (setq a (cdr a) | |
447 | b (cdr b))) | |
448 | a) | |
449 | ||
450 | (defun format-reorder (items order) | |
451 | "Arrange ITEMS to following partial ORDER. | |
452 | Elements of ITEMS equal to elements of ORDER will be rearranged to follow the | |
453 | ORDER. Unmatched items will go last." | |
454 | (if order | |
455 | (let ((item (member (car order) items))) | |
456 | (if item | |
457 | (cons (car item) | |
458 | (format-reorder (format-delq-cons item items) | |
459 | (cdr order))) | |
460 | (format-reorder items (cdr order)))) | |
461 | items)) | |
462 | ||
463 | (put 'face 'format-list-valued t) ; These text-properties take values | |
464 | (put 'unknown 'format-list-valued t) ; that are lists, the elements of which | |
465 | ; should be considered separately. | |
466 | ; See format-deannotate-region and | |
467 | ; format-annotate-region. | |
468 | ||
469 | ;;; | |
470 | ;;; Decoding | |
471 | ;;; | |
472 | ||
473 | (defun format-deannotate-region (from to translations next-fn) | |
474 | "Translate annotations in the region into text properties. | |
475 | This sets text properties between FROM to TO as directed by the | |
476 | TRANSLATIONS and NEXT-FN arguments. | |
477 | ||
478 | NEXT-FN is a function that searches forward from point for an annotation. | |
479 | It should return a list of 4 elements: \(BEGIN END NAME POSITIVE). BEGIN and | |
480 | END are buffer positions bounding the annotation, NAME is the name searched | |
481 | for in TRANSLATIONS, and POSITIVE should be non-nil if this annotation marks | |
482 | the beginning of a region with some property, or nil if it ends the region. | |
483 | NEXT-FN should return nil if there are no annotations after point. | |
484 | ||
485 | The basic format of the TRANSLATIONS argument is described in the | |
486 | documentation for the `format-annotate-region' function. There are some | |
487 | additional things to keep in mind for decoding, though: | |
488 | ||
489 | When an annotation is found, the TRANSLATIONS list is searched for a | |
490 | text-property name and value that corresponds to that annotation. If the | |
491 | text-property has several annotations associated with it, it will be used only | |
492 | if the other annotations are also in effect at that point. The first match | |
493 | found whose annotations are all present is used. | |
494 | ||
495 | The text property thus determined is set to the value over the region between | |
496 | the opening and closing annotations. However, if the text-property name has a | |
497 | non-nil `format-list-valued' property, then the value will be consed onto the | |
498 | surrounding value of the property, rather than replacing that value. | |
499 | ||
500 | There are some special symbols that can be used in the \"property\" slot of | |
501 | the TRANSLATIONS list: PARAMETER and FUNCTION \(spelled in uppercase). | |
502 | Annotations listed under the pseudo-property PARAMETER are considered to be | |
503 | arguments of the immediately surrounding annotation; the text between the | |
504 | opening and closing parameter annotations is deleted from the buffer but saved | |
505 | as a string. The surrounding annotation should be listed under the | |
506 | pseudo-property FUNCTION. Instead of inserting a text-property for this | |
507 | annotation, the function listed in the VALUE slot is called to make whatever | |
508 | changes are appropriate. The function's first two arguments are the START and | |
509 | END locations, and the rest of the arguments are any PARAMETERs found in that | |
510 | region. | |
511 | ||
512 | Any annotations that are found by NEXT-FN but not defined by TRANSLATIONS | |
513 | are saved as values of the `unknown' text-property \(which is list-valued). | |
514 | The TRANSLATIONS list should usually contain an entry of the form | |
515 | \(unknown \(nil format-annotate-value)) | |
516 | to write these unknown annotations back into the file." | |
517 | (save-excursion | |
518 | (save-restriction | |
519 | (narrow-to-region (point-min) to) | |
520 | (goto-char from) | |
521 | (let (next open-ans todo loc unknown-ans) | |
522 | (while (setq next (funcall next-fn)) | |
523 | (let* ((loc (nth 0 next)) | |
524 | (end (nth 1 next)) | |
525 | (name (nth 2 next)) | |
526 | (positive (nth 3 next)) | |
527 | (found nil)) | |
528 | ||
529 | ;; Delete the annotation | |
530 | (delete-region loc end) | |
531 | (if positive | |
532 | ;; Positive annotations are stacked, remembering location | |
533 | (setq open-ans (cons (list name loc) open-ans)) | |
534 | ;; It is a negative annotation: | |
535 | ;; Close the top annotation & add its text property. | |
536 | ;; If the file's nesting is messed up, the close might not match | |
537 | ;; the top thing on the open-annotations stack. | |
538 | ;; If no matching annotation is open, just ignore the close. | |
539 | (if (not (assoc name open-ans)) | |
540 | (message "Extra closing annotation (%s) in file" name) | |
541 | ;; If one is open, but not on the top of the stack, close | |
542 | ;; the things in between as well. Set `found' when the real | |
fa1f61e5 | 543 | ;; one is closed. |
029894b9 BG |
544 | (while (not found) |
545 | (let* ((top (car open-ans)) ; first on stack: should match. | |
546 | (top-name (car top)) | |
547 | (start (car (cdr top))) ; location of start | |
548 | (params (cdr (cdr top))) ; parameters | |
549 | (aalist translations) | |
550 | (matched nil)) | |
551 | (if (equal name top-name) | |
552 | (setq found t) | |
553 | (message "Improper nesting in file.")) | |
554 | ;; Look through property names in TRANSLATIONS | |
555 | (while aalist | |
556 | (let ((prop (car (car aalist))) | |
557 | (alist (cdr (car aalist)))) | |
558 | ;; And look through values for each property | |
559 | (while alist | |
560 | (let ((value (car (car alist))) | |
561 | (ans (cdr (car alist)))) | |
562 | (if (member top-name ans) | |
563 | ;; This annotation is listed, but still have to | |
564 | ;; check if multiple annotations are satisfied | |
565 | (if (member 'nil (mapcar | |
566 | (lambda (r) | |
567 | (assoc r open-ans)) | |
568 | ans)) | |
569 | nil ; multiple ans not satisfied | |
059a4a90 RS |
570 | ;; Yes, all set. |
571 | ;; If there are multiple annotations going | |
572 | ;; into one text property, adjust the | |
573 | ;; begin points of the other annotations | |
574 | ;; so that we don't get double marking. | |
575 | (let ((to-reset ans) | |
576 | this-one) | |
577 | (while to-reset | |
578 | (setq this-one | |
579 | (assoc (car to-reset) | |
580 | (cdr open-ans))) | |
581 | (if this-one | |
2df566e6 | 582 | (setcar (cdr this-one) loc)) |
059a4a90 RS |
583 | (setq to-reset (cdr to-reset)))) |
584 | ;; Set loop variables to nil so loop | |
029894b9 BG |
585 | ;; will exit. |
586 | (setq alist nil aalist nil matched t | |
587 | ;; pop annotation off stack. | |
588 | open-ans (cdr open-ans)) | |
589 | (cond | |
590 | ;; Check for pseudo-properties | |
591 | ((eq prop 'PARAMETER) | |
592 | ;; This is a parameter of the top open ann: | |
593 | ;; delete text and use as arg. | |
594 | (if open-ans | |
595 | ;; (If nothing open, discard). | |
596 | (setq open-ans | |
597 | (cons (append (car open-ans) | |
598 | (list | |
599 | (buffer-substring | |
600 | start loc))) | |
601 | (cdr open-ans)))) | |
602 | (delete-region start loc)) | |
603 | ((eq prop 'FUNCTION) | |
604 | ;; Not a property, but a function to call. | |
605 | (let ((rtn (apply value start loc params))) | |
606 | (if rtn (setq todo (cons rtn todo))))) | |
607 | (t | |
608 | ;; Normal property/value pair | |
609 | (setq todo | |
610 | (cons (list start loc prop value) | |
611 | todo))))))) | |
612 | (setq alist (cdr alist)))) | |
613 | (setq aalist (cdr aalist))) | |
614 | (if matched | |
615 | nil | |
616 | ;; Didn't find any match for the annotation: | |
617 | ;; Store as value of text-property `unknown'. | |
618 | (setq open-ans (cdr open-ans)) | |
619 | (setq todo (cons (list start loc 'unknown top-name) | |
620 | todo)) | |
621 | (setq unknown-ans (cons name unknown-ans))))))))) | |
622 | ||
623 | ;; Once entire file has been scanned, add the properties. | |
624 | (while todo | |
625 | (let* ((item (car todo)) | |
626 | (from (nth 0 item)) | |
627 | (to (nth 1 item)) | |
628 | (prop (nth 2 item)) | |
629 | (val (nth 3 item))) | |
630 | ||
631 | (put-text-property | |
632 | from to prop | |
633 | (cond ((numberp val) ; add to ambient value if numeric | |
634 | (+ val (or (get-text-property from prop) 0))) | |
635 | ((get prop 'format-list-valued) ; value gets consed onto | |
636 | ; list-valued properties | |
637 | (let ((prev (get-text-property from prop))) | |
638 | (cons val (if (listp prev) prev (list prev))))) | |
639 | (t val)))) ; normally, just set to val. | |
640 | (setq todo (cdr todo))) | |
641 | ||
642 | (if unknown-ans | |
643 | (message "Unknown annotations: %s" unknown-ans)))))) | |
644 | ||
645 | ;;; | |
646 | ;;; Encoding | |
647 | ;;; | |
648 | ||
649 | (defun format-insert-annotations (list &optional offset) | |
650 | "Apply list of annotations to buffer as `write-region' would. | |
651 | Inserts each element of the given LIST of buffer annotations at its | |
652 | appropriate place. Use second arg OFFSET if the annotations' locations are | |
653 | not relative to the beginning of the buffer: annotations will be inserted | |
654 | at their location-OFFSET+1 \(ie, the offset is treated as the character number | |
655 | of the first character in the buffer)." | |
656 | (if (not offset) | |
657 | (setq offset 0) | |
658 | (setq offset (1- offset))) | |
659 | (let ((l (reverse list))) | |
660 | (while l | |
661 | (goto-char (- (car (car l)) offset)) | |
662 | (insert (cdr (car l))) | |
663 | (setq l (cdr l))))) | |
664 | ||
665 | (defun format-annotate-value (old new) | |
666 | "Return OLD and NEW as a \(close . open) annotation pair. | |
667 | Useful as a default function for TRANSLATIONS alist when the value of the text | |
668 | property is the name of the annotation that you want to use, as it is for the | |
669 | `unknown' text property." | |
670 | (cons (if old (list old)) | |
671 | (if new (list new)))) | |
672 | ||
673 | (defun format-annotate-region (from to trans format-fn ignore) | |
674 | "Generate annotations for text properties in the region. | |
675 | Searches for changes between FROM and TO, and describes them with a list of | |
676 | annotations as defined by alist TRANSLATIONS and FORMAT-FN. IGNORE lists text | |
677 | properties not to consider; any text properties that are neither ignored nor | |
678 | listed in TRANSLATIONS are warned about. | |
679 | If you actually want to modify the region, give the return value of this | |
680 | function to `format-insert-annotations'. | |
681 | ||
682 | Format of the TRANSLATIONS argument: | |
683 | ||
684 | Each element is a list whose car is a PROPERTY, and the following | |
685 | elements are VALUES of that property followed by the names of zero or more | |
686 | ANNOTATIONS. Whenever the property takes on that value, the annotations | |
687 | \(as formatted by FORMAT-FN) are inserted into the file. | |
688 | When the property stops having that value, the matching negated annotation | |
689 | will be inserted \(it may actually be closed earlier and reopened, if | |
690 | necessary, to keep proper nesting). | |
691 | ||
692 | If the property's value is a list, then each element of the list is dealt with | |
693 | separately. | |
694 | ||
695 | If a VALUE is numeric, then it is assumed that there is a single annotation | |
696 | and each occurrence of it increments the value of the property by that number. | |
697 | Thus, given the entry \(left-margin \(4 \"indent\")), if the left margin | |
698 | changes from 4 to 12, two <indent> annotations will be generated. | |
699 | ||
700 | If the VALUE is nil, then instead of annotations, a function should be | |
701 | specified. This function is used as a default: it is called for all | |
702 | transitions not explicitly listed in the table. The function is called with | |
703 | two arguments, the OLD and NEW values of the property. It should return | |
704 | lists of annotations like `format-annotate-location' does. | |
705 | ||
706 | The same structure can be used in reverse for reading files." | |
707 | (let ((all-ans nil) ; All annotations - becomes return value | |
708 | (open-ans nil) ; Annotations not yet closed | |
709 | (loc nil) ; Current location | |
710 | (not-found nil)) ; Properties that couldn't be saved | |
711 | (while (or (null loc) | |
712 | (and (setq loc (next-property-change loc nil to)) | |
713 | (< loc to))) | |
714 | (or loc (setq loc from)) | |
715 | (let* ((ans (format-annotate-location loc (= loc from) ignore trans)) | |
716 | (neg-ans (format-reorder (aref ans 0) open-ans)) | |
717 | (pos-ans (aref ans 1)) | |
718 | (ignored (aref ans 2))) | |
719 | (setq not-found (append ignored not-found) | |
720 | ignore (append ignored ignore)) | |
721 | ;; First do the negative (closing) annotations | |
722 | (while neg-ans | |
723 | ;; Check if it's missing. This can happen (eg, a numeric property | |
724 | ;; going negative can generate closing annotations before there are | |
725 | ;; any open). Warn user & ignore. | |
726 | (if (not (member (car neg-ans) open-ans)) | |
727 | (message "Can't close %s: not open." (car neg-ans)) | |
728 | (while (not (equal (car neg-ans) (car open-ans))) | |
729 | ;; To close anno. N, need to first close ans 1 to N-1, | |
730 | ;; remembering to re-open them later. | |
731 | (setq pos-ans (cons (car open-ans) pos-ans)) | |
732 | (setq all-ans | |
733 | (cons (cons loc (funcall format-fn (car open-ans) nil)) | |
734 | all-ans)) | |
735 | (setq open-ans (cdr open-ans))) | |
736 | ;; Now remove the one we're really interested in from open list. | |
737 | (setq open-ans (cdr open-ans)) | |
738 | ;; And put the closing annotation here. | |
739 | (setq all-ans | |
740 | (cons (cons loc (funcall format-fn (car neg-ans) nil)) | |
741 | all-ans))) | |
742 | (setq neg-ans (cdr neg-ans))) | |
743 | ;; Now deal with positive (opening) annotations | |
744 | (let ((p pos-ans)) | |
745 | (while pos-ans | |
746 | (setq open-ans (cons (car pos-ans) open-ans)) | |
747 | (setq all-ans | |
748 | (cons (cons loc (funcall format-fn (car pos-ans) t)) | |
749 | all-ans)) | |
750 | (setq pos-ans (cdr pos-ans)))))) | |
751 | ||
752 | ;; Close any annotations still open | |
753 | (while open-ans | |
754 | (setq all-ans | |
755 | (cons (cons to (funcall format-fn (car open-ans) nil)) | |
756 | all-ans)) | |
757 | (setq open-ans (cdr open-ans))) | |
758 | (if not-found | |
759 | (message "These text properties could not be saved:\n %s" | |
760 | not-found)) | |
761 | (nreverse all-ans))) | |
762 | ||
763 | ;;; Internal functions for format-annotate-region. | |
764 | ||
765 | (defun format-annotate-location (loc all ignore trans) | |
766 | "Return annotation(s) needed at LOCATION. | |
767 | This includes any properties that change between LOC-1 and LOC. | |
768 | If ALL is true, don't look at previous location, but generate annotations for | |
769 | all non-nil properties. | |
770 | Third argument IGNORE is a list of text-properties not to consider. | |
771 | ||
772 | Return value is a vector of 3 elements: | |
773 | 1. List of names of the annotations to close | |
774 | 2. List of the names of annotations to open. | |
775 | 3. List of properties that were ignored or couldn't be annotated." | |
776 | (let* ((prev-loc (1- loc)) | |
777 | (before-plist (if all nil (text-properties-at prev-loc))) | |
778 | (after-plist (text-properties-at loc)) | |
779 | p negatives positives prop props not-found) | |
780 | ;; make list of all property names involved | |
781 | (setq p before-plist) | |
782 | (while p | |
783 | (if (not (memq (car p) props)) | |
784 | (setq props (cons (car p) props))) | |
785 | (setq p (cdr (cdr p)))) | |
786 | (setq p after-plist) | |
787 | (while p | |
788 | (if (not (memq (car p) props)) | |
789 | (setq props (cons (car p) props))) | |
790 | (setq p (cdr (cdr p)))) | |
791 | ||
792 | (while props | |
793 | (setq prop (car props) | |
794 | props (cdr props)) | |
795 | (if (memq prop ignore) | |
796 | nil ; If it's been ignored before, ignore it now. | |
797 | (let ((before (if all nil (car (cdr (memq prop before-plist))))) | |
798 | (after (car (cdr (memq prop after-plist))))) | |
799 | (if (equal before after) | |
800 | nil ; no change; ignore | |
801 | (let ((result (format-annotate-single-property-change | |
802 | prop before after trans))) | |
803 | (if (not result) | |
804 | (setq not-found (cons prop not-found)) | |
805 | (setq negatives (nconc negatives (car result)) | |
806 | positives (nconc positives (cdr result))))))))) | |
807 | (vector negatives positives not-found))) | |
808 | ||
809 | (defun format-annotate-single-property-change (prop old new trans) | |
810 | "Return annotations for PROPERTY changing from OLD to NEW. | |
811 | These are searched for in the TRANSLATIONS alist. | |
812 | If NEW does not appear in the list, but there is a default function, then that | |
813 | function is called. | |
814 | Annotations to open and to close are returned as a dotted pair." | |
815 | (let ((prop-alist (cdr (assoc prop trans))) | |
816 | default) | |
817 | (if (not prop-alist) | |
818 | nil | |
819 | ;; If property is numeric, nil means 0 | |
820 | (cond ((and (numberp old) (null new)) | |
821 | (setq new 0)) | |
822 | ((and (numberp new) (null old)) | |
823 | (setq old 0))) | |
824 | ;; If either old or new is a list, have to treat both that way. | |
825 | (if (or (consp old) (consp new)) | |
826 | (let* ((old (if (listp old) old (list old))) | |
827 | (new (if (listp new) new (list new))) | |
828 | (tail (format-common-tail old new)) | |
829 | close open) | |
830 | (while old | |
831 | (setq close | |
832 | (append (car (format-annotate-atomic-property-change | |
833 | prop-alist (car old) nil)) | |
834 | close) | |
835 | old (cdr old))) | |
836 | (while new | |
837 | (setq open | |
838 | (append (cdr (format-annotate-atomic-property-change | |
839 | prop-alist nil (car new))) | |
840 | open) | |
841 | new (cdr new))) | |
842 | (format-make-relatively-unique close open)) | |
843 | (format-annotate-atomic-property-change prop-alist old new))))) | |
844 | ||
845 | (defun format-annotate-atomic-property-change (prop-alist old new) | |
846 | "Internal function annotate a single property change. | |
fa1f61e5 | 847 | PROP-ALIST is the relevant segment of a TRANSLATIONS list. |
029894b9 BG |
848 | OLD and NEW are the values." |
849 | (cond | |
850 | ;; Numerical annotation - use difference | |
851 | ((and (numberp old) (numberp new)) | |
852 | (let* ((entry (progn | |
853 | (while (and (car (car prop-alist)) | |
854 | (not (numberp (car (car prop-alist))))) | |
855 | (setq prop-alist (cdr prop-alist))) | |
856 | (car prop-alist))) | |
857 | (increment (car (car prop-alist))) | |
858 | (n (ceiling (/ (float (- new old)) (float increment)))) | |
859 | (anno (car (cdr (car prop-alist))))) | |
860 | (if (> n 0) | |
861 | (cons nil (make-list n anno)) | |
862 | (cons (make-list (- n) anno) nil)))) | |
863 | ||
864 | ;; Standard annotation | |
865 | (t (let ((close (and old (cdr (assoc old prop-alist)))) | |
866 | (open (and new (cdr (assoc new prop-alist))))) | |
867 | (if (or close open) | |
868 | (format-make-relatively-unique close open) | |
869 | ;; Call "Default" function, if any | |
870 | (let ((default (assq nil prop-alist))) | |
871 | (if default | |
872 | (funcall (car (cdr default)) old new)))))))) | |
873 | ||
c84cf2bf | 874 | (provide 'format) |
029894b9 | 875 | ;; format.el ends here |