thingatpt.el 15.5 KB
Newer Older
1
;;; thingatpt.el --- get the `thing' at point
Richard M. Stallman's avatar
Richard M. Stallman committed
2

Glenn Morris's avatar
Glenn Morris committed
3
;; Copyright (C) 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 2000,
Glenn Morris's avatar
Glenn Morris committed
4
;;   2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008 Free Software Foundation, Inc.
Richard M. Stallman's avatar
Richard M. Stallman committed
5 6

;; Author: Mike Williams <mikew@gopher.dosli.govt.nz>
7
;; Maintainer: FSF
Richard M. Stallman's avatar
Richard M. Stallman committed
8
;; Keywords: extensions, matching, mouse
Richard M. Stallman's avatar
Richard M. Stallman committed
9 10 11 12 13 14
;; Created: Thu Mar 28 13:48:23 1991

;; This file is part of GNU Emacs.

;; GNU Emacs is free software; you can redistribute it and/or modify
;; it under the terms of the GNU General Public License as published by
15
;; the Free Software Foundation; either version 3, or (at your option)
Richard M. Stallman's avatar
Richard M. Stallman committed
16 17 18 19 20 21 22
;; any later version.

;; GNU Emacs is distributed in the hope that it will be useful,
;; but WITHOUT ANY WARRANTY; without even the implied warranty of
;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
;; GNU General Public License for more details.

Richard M. Stallman's avatar
Richard M. Stallman committed
23
;;; Commentary:
Erik Naggum's avatar
Erik Naggum committed
24

25 26
;; This file provides routines for getting the "thing" at the location of
;; point, whatever that "thing" happens to be.  The "thing" is defined by
Richard M. Stallman's avatar
Richard M. Stallman committed
27
;; its beginning and end positions in the buffer.
Richard M. Stallman's avatar
Richard M. Stallman committed
28 29
;;
;; The function bounds-of-thing-at-point finds the beginning and end
30
;; positions by moving first forward to the end of the "thing", and then
Richard M. Stallman's avatar
Richard M. Stallman committed
31
;; backwards to the beginning.  By default, it uses the corresponding
32
;; forward-"thing" operator (eg. forward-word, forward-line).
Richard M. Stallman's avatar
Richard M. Stallman committed
33 34
;;
;; Special cases are allowed for using properties associated with the named
35
;; "thing":
Richard M. Stallman's avatar
Richard M. Stallman committed
36
;;
37
;;   forward-op		Function to call to skip forward over a "thing" (or
Richard M. Stallman's avatar
Richard M. Stallman committed
38
;;                      with a negative argument, backward).
39
;;
40 41
;;   beginning-op	Function to call to skip to the beginning of a "thing".
;;   end-op		Function to call to skip to the end of a "thing".
Richard M. Stallman's avatar
Richard M. Stallman committed
42 43 44 45 46 47
;;
;; Reliance on existing operators means that many `things' can be accessed
;; without further code:  eg.
;;     (thing-at-point 'line)
;;     (thing-at-point 'page)

Erik Naggum's avatar
Erik Naggum committed
48
;;; Code:
Richard M. Stallman's avatar
Richard M. Stallman committed
49 50 51

(provide 'thingatpt)

Erik Naggum's avatar
Erik Naggum committed
52
;; Basic movement
Richard M. Stallman's avatar
Richard M. Stallman committed
53 54

;;;###autoload
55
(defun forward-thing (thing &optional n)
56
  "Move forward to the end of the Nth next THING."
57 58
  (let ((forward-op (or (get thing 'forward-op)
			(intern-soft (format "forward-%s" thing)))))
59
    (if (functionp forward-op)
60 61
	(funcall forward-op (or n 1))
      (error "Can't determine how to move over a %s" thing))))
Richard M. Stallman's avatar
Richard M. Stallman committed
62

Erik Naggum's avatar
Erik Naggum committed
63
;; General routines
Richard M. Stallman's avatar
Richard M. Stallman committed
64 65

;;;###autoload
66 67 68 69
(defun bounds-of-thing-at-point (thing)
  "Determine the start and end buffer locations for the THING at point.
THING is a symbol which specifies the kind of syntactic entity you want.
Possibilities include `symbol', `list', `sexp', `defun', `filename', `url',
70
`email', `word', `sentence', `whitespace', `line', `page' and others.
71 72 73 74 75 76

See the file `thingatpt.el' for documentation on how to define
a symbol as a valid THING.

The value is a cons cell (START . END) giving the start and end positions
of the textual entity that was found."
77 78 79 80 81 82
  (if (get thing 'bounds-of-thing-at-point)
      (funcall (get thing 'bounds-of-thing-at-point))
    (let ((orig (point)))
      (condition-case nil
	  (save-excursion
	    ;; Try moving forward, then back.
83 84 85 86 87 88 89
            (funcall ;; First move to end.
             (or (get thing 'end-op)
                 (lambda () (forward-thing thing 1))))
            (funcall ;; Then move to beg.
             (or (get thing 'beginning-op)
                 (lambda () (forward-thing thing -1))))
	    (let ((beg (point)))
90 91 92 93 94
	      (if (not (and beg (> beg orig)))
		  ;; If that brings us all the way back to ORIG,
		  ;; it worked.  But END may not be the real end.
		  ;; So find the real end that corresponds to BEG.
		  (let ((real-end
95 96 97
			 (progn
			   (funcall
			    (or (get thing 'end-op)
98
                                (lambda () (forward-thing thing 1))))
99 100 101 102 103 104
			   (point))))
		    (if (and beg real-end (<= beg orig) (<= orig real-end))
			(cons beg real-end)))
		(goto-char orig)
		;; Try a second time, moving backward first and then forward,
		;; so that we can find a thing that ends at ORIG.
105 106 107 108 109 110 111 112
                (funcall ;; First, move to beg.
                 (or (get thing 'beginning-op)
                     (lambda () (forward-thing thing -1))))
                (funcall ;; Then move to end.
                 (or (get thing 'end-op)
                     (lambda () (forward-thing thing 1))))
		(let ((end (point))
                      (real-beg
113 114 115
		       (progn
			 (funcall
			  (or (get thing 'beginning-op)
116
                              (lambda () (forward-thing thing -1))))
117 118 119 120
			 (point))))
		  (if (and real-beg end (<= real-beg orig) (<= orig end))
		      (cons real-beg end))))))
	(error nil)))))
Richard M. Stallman's avatar
Richard M. Stallman committed
121 122

;;;###autoload
123 124 125 126
(defun thing-at-point (thing)
  "Return the THING at point.
THING is a symbol which specifies the kind of syntactic entity you want.
Possibilities include `symbol', `list', `sexp', `defun', `filename', `url',
127
`email', `word', `sentence', `whitespace', `line', `page' and others.
128 129 130

See the file `thingatpt.el' for documentation on how to define
a symbol as a valid THING."
131 132 133
  (if (get thing 'thing-at-point)
      (funcall (get thing 'thing-at-point))
    (let ((bounds (bounds-of-thing-at-point thing)))
134
      (if bounds
135
	  (buffer-substring (car bounds) (cdr bounds))))))
Richard M. Stallman's avatar
Richard M. Stallman committed
136

Erik Naggum's avatar
Erik Naggum committed
137
;; Go to beginning/end
Richard M. Stallman's avatar
Richard M. Stallman committed
138

139 140 141
(defun beginning-of-thing (thing)
  (let ((bounds (bounds-of-thing-at-point thing)))
    (or bounds (error "No %s here" thing))
Richard M. Stallman's avatar
Richard M. Stallman committed
142 143
    (goto-char (car bounds))))

144 145 146
(defun end-of-thing (thing)
  (let ((bounds (bounds-of-thing-at-point thing)))
    (or bounds (error "No %s here" thing))
Richard M. Stallman's avatar
Richard M. Stallman committed
147 148
    (goto-char (cdr bounds))))

149
;;  Special cases
Richard M. Stallman's avatar
Richard M. Stallman committed
150

151
;;  Lines
152 153 154 155 156

;; bolp will be false when you click on the last line in the buffer
;; and it has no final newline.

(put 'line 'beginning-op
157
     (lambda () (if (bolp) (forward-line -1) (beginning-of-line))))
158

159
;;  Sexps
Richard M. Stallman's avatar
Richard M. Stallman committed
160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175

(defun in-string-p ()
  (let ((orig (point)))
    (save-excursion
      (beginning-of-defun)
      (nth 3 (parse-partial-sexp (point) orig)))))

(defun end-of-sexp ()
  (let ((char-syntax (char-syntax (char-after (point)))))
    (if (or (eq char-syntax ?\))
	    (and (eq char-syntax ?\") (in-string-p)))
	(forward-char 1)
      (forward-sexp 1))))

(put 'sexp 'end-op 'end-of-sexp)

176 177 178 179 180 181 182 183 184
(defun beginning-of-sexp ()
  (let ((char-syntax (char-syntax (char-before (point)))))
    (if (or (eq char-syntax ?\()
	    (and (eq char-syntax ?\") (in-string-p)))
	(forward-char -1)
      (forward-sexp -1))))

(put 'sexp 'beginning-op 'beginning-of-sexp)

185
;;  Lists
Richard M. Stallman's avatar
Richard M. Stallman committed
186

187
(put 'list 'end-op (lambda () (up-list 1)))
Richard M. Stallman's avatar
Richard M. Stallman committed
188 189
(put 'list 'beginning-op 'backward-sexp)

190
;;  Filenames and URLs  www.com/foo%32bar
Richard M. Stallman's avatar
Richard M. Stallman committed
191

192
(defvar thing-at-point-file-name-chars "-~/[:alnum:]_.${}#%,:"
Richard M. Stallman's avatar
Richard M. Stallman committed
193 194
  "Characters allowable in filenames.")

195
(put 'filename 'end-op
196 197 198
     (lambda ()
       (re-search-forward (concat "\\=[" thing-at-point-file-name-chars "]*")
			  nil t)))
Richard M. Stallman's avatar
Richard M. Stallman committed
199
(put 'filename 'beginning-op
200 201 202 203 204
     (lambda ()
       (if (re-search-backward (concat "[^" thing-at-point-file-name-chars "]")
			       nil t)
	   (forward-char)
	 (goto-char (point-min)))))
205

206 207
(defvar thing-at-point-url-path-regexp
  "[^]\t\n \"'()<>[^`{}]*[^]\t\n \"'()<>[^`{}.,;]+"
208
  "A regular expression probably matching the host and filename or e-mail part of a URL.")
209 210 211 212 213 214 215

(defvar thing-at-point-short-url-regexp
  (concat "[-A-Za-z0-9.]+" thing-at-point-url-path-regexp)
  "A regular expression probably matching a URL without an access scheme.
Hostname matching is stricter in this case than for
``thing-at-point-url-regexp''.")

216
(defvar thing-at-point-uri-schemes
217
  ;; Officials from http://www.iana.org/assignments/uri-schemes.html
218 219 220 221 222 223
  '("ftp://" "http://" "gopher://" "mailto:" "news:" "nntp:"
    "telnet://" "wais://" "file:/" "prospero:" "z39.50s:" "z39.50r:"
    "cid:" "mid:" "vemmi:" "service:" "imap:" "nfs:" "acap:" "rtsp:"
    "tip:" "pop:" "data:" "dav:" "opaquelocktoken:" "sip:" "tel:" "fax:"
    "modem:" "ldap:" "https://" "soap.beep:" "soap.beeps:" "urn:" "go:"
    "afs:" "tn3270:" "mailserver:"
224 225 226
    "crid:" "dict:" "dns:" "dtn:" "h323:" "im:" "info:" "ipp:"
    "iris.beep:" "mtqp:" "mupdate:" "pres:" "sips:" "snmp:" "tag:"
    "tftp:" "xmlrpc.beep:" "xmlrpc.beeps:" "xmpp:"
227
  ;; Compatibility
228
    "snews:" "irc:" "mms://" "mmsh://")
229
  "Uniform Resource Identifier (URI) Schemes.")
230

231
(defvar thing-at-point-url-regexp
232 233
  (concat "\\<\\(" (mapconcat 'identity thing-at-point-uri-schemes "\\|") "\\)"
          thing-at-point-url-path-regexp)
234 235 236 237 238 239 240 241 242
  "A regular expression probably matching a complete URL.")

(defvar thing-at-point-markedup-url-regexp
  "<URL:[^>]+>"
  "A regular expression matching a URL marked up per RFC1738.
This may contain whitespace (including newlines) .")

(put 'url 'bounds-of-thing-at-point 'thing-at-point-bounds-of-url-at-point)
(defun thing-at-point-bounds-of-url-at-point ()
243 244 245
  (let ((strip (thing-at-point-looking-at
			 thing-at-point-markedup-url-regexp))) ;; (url "") short
    (if (or strip
246
	    (thing-at-point-looking-at thing-at-point-url-regexp)
247
	    ;; Access scheme omitted?
248 249 250
	    ;; (setq short (thing-at-point-looking-at
	    ;;     	 thing-at-point-short-url-regexp))
            )
251 252
	(let ((beginning (match-beginning 0))
	      (end (match-end 0)))
253 254 255
	  (when strip
            (setq beginning (+ beginning 5))
            (setq end (- end 1)))
256 257 258 259 260
	  (cons beginning end)))))

(put 'url 'thing-at-point 'thing-at-point-url-at-point)
(defun thing-at-point-url-at-point ()
  "Return the URL around or before point.
261 262 263 264 265 266

Search backwards for the start of a URL ending at or after point.  If
no URL found, return nil.  The access scheme will be prepended if
absent: \"mailto:\" if the string contains \"@\", \"ftp://\" if it
starts with \"ftp\" and not \"ftp:/\", or \"http://\" by default."

267 268 269 270 271 272 273 274 275 276 277 278
  (let ((url "") short strip)
    (if (or (setq strip (thing-at-point-looking-at
			 thing-at-point-markedup-url-regexp))
	    (thing-at-point-looking-at thing-at-point-url-regexp)
	    ;; Access scheme omitted?
	    (setq short (thing-at-point-looking-at
			 thing-at-point-short-url-regexp)))
	(progn
	  (setq url (buffer-substring-no-properties (match-beginning 0)
						    (match-end 0)))
	  (and strip (setq url (substring url 5 -1))) ; Drop "<URL:" & ">"
	  ;; strip whitespace
279
	  (while (string-match "[ \t\n\r]+" url)
280
	    (setq url (replace-match "" t t url)))
281 282 283 284
	  (and short (setq url (concat (cond ((string-match "^[a-zA-Z]+:" url)
					       ;; already has a URL scheme.
					       "")
					     ((string-match "@" url)
285 286 287 288 289 290
                                              "mailto:")
					     ;; e.g. ftp.swiss... or ftp-swiss...
                                             ((string-match "^ftp" url)
                                              "ftp://")
                                             (t "http://"))
                                       url)))
291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329
	  (if (string-equal "" url)
	      nil
	    url)))))

;; The normal thingatpt mechanism doesn't work for complex regexps.
;; This should work for almost any regexp wherever we are in the
;; match.  To do a perfect job for any arbitrary regexp would mean
;; testing every position before point.  Regexp searches won't find
;; matches that straddle the start position so we search forwards once
;; and then back repeatedly and then back up a char at a time.

(defun thing-at-point-looking-at (regexp)
  "Return non-nil if point is in or just after a match for REGEXP.
Set the match data from the earliest such match ending at or after
point."
  (save-excursion
    (let ((old-point (point)) match)
      (and (looking-at regexp)
	   (>= (match-end 0) old-point)
	   (setq match (point)))
      ;; Search back repeatedly from end of next match.
      ;; This may fail if next match ends before this match does.
      (re-search-forward regexp nil 'limit)
      (while (and (re-search-backward regexp nil t)
		  (or (> (match-beginning 0) old-point)
		      (and (looking-at regexp)	; Extend match-end past search start
			   (>= (match-end 0) old-point)
			   (setq match (point))))))
      (if (not match) nil
	(goto-char match)
	;; Back up a char at a time in case search skipped
	;; intermediate match straddling search start pos.
	(while (and (not (bobp))
		    (progn (backward-char 1) (looking-at regexp))
		    (>= (match-end 0) old-point)
		    (setq match (point))))
	(goto-char match)
	(looking-at regexp)))))

330
(put 'url 'end-op
331 332 333 334 335
     (lambda ()
       (let ((bounds (thing-at-point-bounds-of-url-at-point)))
         (if bounds
             (goto-char (cdr bounds))
           (error "No URL here")))))
336
(put 'url 'beginning-op
337 338 339 340 341
     (lambda ()
       (let ((bounds (thing-at-point-bounds-of-url-at-point)))
         (if bounds
             (goto-char (car bounds))
           (error "No URL here")))))
Richard M. Stallman's avatar
Richard M. Stallman committed
342

343 344
;;   Email addresses
(defvar thing-at-point-email-regexp
345
  "<?[-+_.~a-zA-Z][-+_.~:a-zA-Z0-9]*@[-.a-zA-Z0-9]+>?"
346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369
  "A regular expression probably matching an email address.
This does not match the real name portion, only the address, optionally
with angle brackets.")

;; Haven't set 'forward-op on 'email nor defined 'forward-email' because
;; not sure they're actually needed, and URL seems to skip them too.
;; Note that (end-of-thing 'email) and (beginning-of-thing 'email)
;; work automagically, though.

(put 'email 'bounds-of-thing-at-point
     (lambda ()
       (let ((thing (thing-at-point-looking-at thing-at-point-email-regexp)))
         (if thing
             (let ((beginning (match-beginning 0))
                   (end (match-end 0)))
               (cons beginning end))))))

(put 'email 'thing-at-point
     (lambda ()
       (let ((boundary-pair (bounds-of-thing-at-point 'email)))
         (if boundary-pair
             (buffer-substring-no-properties
              (car boundary-pair) (cdr boundary-pair))))))

370
;;  Whitespace
Richard M. Stallman's avatar
Richard M. Stallman committed
371

372
(defun forward-whitespace (arg)
Richard M. Stallman's avatar
Richard M. Stallman committed
373
  (interactive "p")
374
  (if (natnump arg)
375
      (re-search-forward "[ \t]+\\|\n" nil 'move arg)
376
    (while (< arg 0)
377
      (if (re-search-backward "[ \t]+\\|\n" nil 'move)
Richard M. Stallman's avatar
Richard M. Stallman committed
378 379
	  (or (eq (char-after (match-beginning 0)) 10)
	      (skip-chars-backward " \t")))
380
      (setq arg (1+ arg)))))
Richard M. Stallman's avatar
Richard M. Stallman committed
381

382
;;  Buffer
Richard M. Stallman's avatar
Richard M. Stallman committed
383

384 385
(put 'buffer 'end-op (lambda () (goto-char (point-max))))
(put 'buffer 'beginning-op (lambda () (goto-char (point-min))))
Richard M. Stallman's avatar
Richard M. Stallman committed
386

387
;;  Symbols
Richard M. Stallman's avatar
Richard M. Stallman committed
388

389
(defun forward-symbol (arg)
Richard M. Stallman's avatar
Richard M. Stallman committed
390
  (interactive "p")
391
  (if (natnump arg)
392
      (re-search-forward "\\(\\sw\\|\\s_\\)+" nil 'move arg)
393
    (while (< arg 0)
394
      (if (re-search-backward "\\(\\sw\\|\\s_\\)+" nil 'move)
Richard M. Stallman's avatar
Richard M. Stallman committed
395
	  (skip-syntax-backward "w_"))
396
      (setq arg (1+ arg)))))
Richard M. Stallman's avatar
Richard M. Stallman committed
397

398
;;  Syntax blocks
399 400 401 402

(defun forward-same-syntax (&optional arg)
  (interactive "p")
  (while (< arg 0)
403
    (skip-syntax-backward
404 405 406 407 408 409
     (char-to-string (char-syntax (char-after (1- (point))))))
    (setq arg (1+ arg)))
  (while (> arg 0)
    (skip-syntax-forward (char-to-string (char-syntax (char-after (point)))))
    (setq arg (1- arg))))

410
;;  Aliases
Richard M. Stallman's avatar
Richard M. Stallman committed
411 412 413 414

(defun word-at-point () (thing-at-point 'word))
(defun sentence-at-point () (thing-at-point 'sentence))

415
(defun read-from-whole-string (str)
416
  "Read a Lisp expression from STR.
417 418
Signal an error if the entire string was not used."
  (let* ((read-data (read-from-string str))
419
	 (more-left
Richard M. Stallman's avatar
Richard M. Stallman committed
420
	  (condition-case nil
Richard M. Stallman's avatar
Richard M. Stallman committed
421
	      ;; The call to `ignore' suppresses a compiler warning.
422
	      (progn (ignore (read-from-string (substring str (cdr read-data))))
Richard M. Stallman's avatar
Richard M. Stallman committed
423 424 425 426 427 428
		     t)
	    (end-of-file nil))))
    (if more-left
	(error "Can't read whole string")
      (car read-data))))

429 430
(defun form-at-point (&optional thing pred)
  (let ((sexp (condition-case nil
431
		  (read-from-whole-string (thing-at-point (or thing 'sexp)))
Richard M. Stallman's avatar
Richard M. Stallman committed
432
		(error nil))))
433
    (if (or (not pred) (funcall pred sexp)) sexp)))
Richard M. Stallman's avatar
Richard M. Stallman committed
434

Dave Love's avatar
Dave Love committed
435
;;;###autoload
Richard M. Stallman's avatar
Richard M. Stallman committed
436
(defun sexp-at-point ()   (form-at-point 'sexp))
Dave Love's avatar
Dave Love committed
437
;;;###autoload
438 439 440
(defun symbol-at-point ()
  (let ((thing (thing-at-point 'symbol)))
    (if thing (intern thing))))
Dave Love's avatar
Dave Love committed
441
;;;###autoload
Richard M. Stallman's avatar
Richard M. Stallman committed
442
(defun number-at-point () (form-at-point 'sexp 'numberp))
Dave Love's avatar
Dave Love committed
443
;;;###autoload
Richard M. Stallman's avatar
Richard M. Stallman committed
444 445
(defun list-at-point ()   (form-at-point 'list 'listp))

446
;; arch-tag: bb65a163-dae2-4055-aedc-fe11f497f698
447
;;; thingatpt.el ends here