thingatpt.el 13.7 KB
Newer Older
1
;;; thingatpt.el --- get the `thing' at point
Richard M. Stallman's avatar
Richard M. Stallman committed
2

3 4
;; Copyright (C) 1991,92,93,94,95,96,97,1998,2000
;;  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 15 16 17 18 19 20 21 22
;; 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
;; the Free Software Foundation; either version 2, or (at your option)
;; 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 39
;;                      with a negative argument, backward).
;;                      
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)
Richard M. Stallman's avatar
Richard M. Stallman committed
56
  "Move forward to the end of the 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 70 71 72 73 74 75 76
(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',
`word', `sentence', `whitespace', `line', `page' and others.

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 83
  (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.
	    (let ((end (progn 
84 85 86
			 (funcall 
			  (or (get thing 'end-op) 
			      (function (lambda () (forward-thing thing 1)))))
87 88 89 90 91
			 (point)))
		  (beg (progn 
			 (funcall 
			  (or (get thing 'beginning-op) 
			      (function (lambda () (forward-thing thing -1)))))
92
			 (point))))
93 94 95 96 97 98
	      (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
			 (progn 
99 100 101
			   (funcall 
			    (or (get thing 'end-op) 
				(function (lambda () (forward-thing thing 1)))))
102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126
			   (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.
		(let ((beg (progn 
			     (funcall 
			      (or (get thing 'beginning-op) 
				  (function (lambda () (forward-thing thing -1)))))
			     (point)))
		      (end (progn 
			     (funcall 
			      (or (get thing 'end-op) 
				  (function (lambda () (forward-thing thing 1)))))
			     (point)))
		      (real-beg
		       (progn 
			 (funcall 
			  (or (get thing 'beginning-op) 
			      (function (lambda () (forward-thing thing -1)))))
			 (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
127 128

;;;###autoload
129 130 131 132 133 134 135 136
(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',
`word', `sentence', `whitespace', `line', `page' and others.

See the file `thingatpt.el' for documentation on how to define
a symbol as a valid THING."
137 138 139 140 141
  (if (get thing 'thing-at-point)
      (funcall (get thing 'thing-at-point))
    (let ((bounds (bounds-of-thing-at-point thing)))
      (if bounds 
	  (buffer-substring (car bounds) (cdr bounds))))))
Richard M. Stallman's avatar
Richard M. Stallman committed
142

Erik Naggum's avatar
Erik Naggum committed
143
;; Go to beginning/end
Richard M. Stallman's avatar
Richard M. Stallman committed
144

145 146 147
(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
148 149
    (goto-char (car bounds))))

150 151 152
(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
153 154
    (goto-char (cdr bounds))))

Erik Naggum's avatar
Erik Naggum committed
155
;;  Special cases 
Richard M. Stallman's avatar
Richard M. Stallman committed
156

Erik Naggum's avatar
Erik Naggum committed
157
;;  Lines 
158 159 160 161 162 163 164

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

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

Erik Naggum's avatar
Erik Naggum committed
165
;;  Sexps 
Richard M. Stallman's avatar
Richard M. Stallman committed
166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181

(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)

182 183 184 185 186 187 188 189 190
(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)

Erik Naggum's avatar
Erik Naggum committed
191
;;  Lists 
Richard M. Stallman's avatar
Richard M. Stallman committed
192 193 194 195

(put 'list 'end-op (function (lambda () (up-list 1))))
(put 'list 'beginning-op 'backward-sexp)

196
;;  Filenames and URLs
Richard M. Stallman's avatar
Richard M. Stallman committed
197

198
(defvar thing-at-point-file-name-chars "~/A-Za-z0-9---_.${}#%,:"
Richard M. Stallman's avatar
Richard M. Stallman committed
199 200 201
  "Characters allowable in filenames.")

(put 'filename 'end-op    
202
     (lambda () (skip-chars-forward thing-at-point-file-name-chars)))
Richard M. Stallman's avatar
Richard M. Stallman committed
203
(put 'filename 'beginning-op
204
     (lambda () (skip-chars-backward thing-at-point-file-name-chars)))
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''.")

216 217 218 219 220 221 222 223 224 225 226 227
(defvar thing-at-point-uri-schemes
  ;; Officials from http://www.iana.org/assignments/uri-schemes
  '("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:"
  ;; Compatibility
    "snews:")
  "Uniform Resource Identifier (URI) Schemes")

228
(defvar thing-at-point-url-regexp
229 230
  (concat "\\<\\(" (mapconcat 'identity thing-at-point-uri-schemes "\\|") "\\)"
          thing-at-point-url-path-regexp)
231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256
  "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 ()
  (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)))
	(let ((beginning (match-beginning 0))
	      (end (match-end 0)))
	  (cond (strip
		 (setq beginning (+ beginning 5))
		 (setq end (- end 1))))
	  (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.
257 258 259 260 261 262

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."

263 264 265 266 267 268 269 270 271 272 273 274
  (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
275
	  (while (string-match "[ \t\n\r]+" url)
276
	    (setq url (replace-match "" t t url)))
277 278 279 280 281 282 283
	  (and short (setq url (concat (cond ((string-match "@" url)
                                              "mailto:")
					     ;; e.g. ftp.swiss... or ftp-swiss...
                                             ((string-match "^ftp" url)
                                              "ftp://")
                                             (t "http://"))
                                       url)))
284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322
	  (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)))))

323 324 325 326 327 328
(put 'url 'end-op
     (function (lambda ()
		 (let ((bounds (thing-at-point-bounds-of-url-at-point)))
		   (if bounds
		       (goto-char (cdr bounds))
		     (error "No URL here"))))))
329
(put 'url 'beginning-op
330 331 332 333 334
     (function (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
335

Erik Naggum's avatar
Erik Naggum committed
336
;;  Whitespace 
Richard M. Stallman's avatar
Richard M. Stallman committed
337

338
(defun forward-whitespace (arg)
Richard M. Stallman's avatar
Richard M. Stallman committed
339
  (interactive "p")
340
  (if (natnump arg) 
341
      (re-search-forward "[ \t]+\\|\n" nil 'move arg)
342
    (while (< arg 0)
343
      (if (re-search-backward "[ \t]+\\|\n" nil 'move)
Richard M. Stallman's avatar
Richard M. Stallman committed
344 345
	  (or (eq (char-after (match-beginning 0)) 10)
	      (skip-chars-backward " \t")))
346
      (setq arg (1+ arg)))))
Richard M. Stallman's avatar
Richard M. Stallman committed
347

Erik Naggum's avatar
Erik Naggum committed
348
;;  Buffer 
Richard M. Stallman's avatar
Richard M. Stallman committed
349

350 351
(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
352

Erik Naggum's avatar
Erik Naggum committed
353
;;  Symbols 
Richard M. Stallman's avatar
Richard M. Stallman committed
354

355
(defun forward-symbol (arg)
Richard M. Stallman's avatar
Richard M. Stallman committed
356
  (interactive "p")
357
  (if (natnump arg) 
358
      (re-search-forward "\\(\\sw\\|\\s_\\)+" nil 'move arg)
359
    (while (< arg 0)
360
      (if (re-search-backward "\\(\\sw\\|\\s_\\)+" nil 'move)
Richard M. Stallman's avatar
Richard M. Stallman committed
361
	  (skip-syntax-backward "w_"))
362
      (setq arg (1+ arg)))))
Richard M. Stallman's avatar
Richard M. Stallman committed
363

Erik Naggum's avatar
Erik Naggum committed
364
;;  Syntax blocks 
365 366 367 368 369 370 371 372 373 374 375

(defun forward-same-syntax (&optional arg)
  (interactive "p")
  (while (< arg 0)
    (skip-syntax-backward 
     (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))))

Erik Naggum's avatar
Erik Naggum committed
376
;;  Aliases 
Richard M. Stallman's avatar
Richard M. Stallman committed
377 378 379 380

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

381 382 383 384
(defun read-from-whole-string (str)
  "Read a lisp expression from STR.
Signal an error if the entire string was not used."
  (let* ((read-data (read-from-string str))
Richard M. Stallman's avatar
Richard M. Stallman committed
385 386
	 (more-left 
	  (condition-case nil
387
	      (progn (read-from-string (substring str (cdr read-data)))
Richard M. Stallman's avatar
Richard M. Stallman committed
388 389 390 391 392 393
		     t)
	    (end-of-file nil))))
    (if more-left
	(error "Can't read whole string")
      (car read-data))))

394
(defun form-at-point (&optional thing pred) 
Richard M. Stallman's avatar
Richard M. Stallman committed
395
  (let ((sexp (condition-case nil 
396
		  (read-from-whole-string (thing-at-point (or thing 'sexp)))
Richard M. Stallman's avatar
Richard M. Stallman committed
397
		(error nil))))
398
    (if (or (not pred) (funcall pred sexp)) sexp)))
Richard M. Stallman's avatar
Richard M. Stallman committed
399

Dave Love's avatar
Dave Love committed
400
;;;###autoload
Richard M. Stallman's avatar
Richard M. Stallman committed
401
(defun sexp-at-point ()   (form-at-point 'sexp))
Dave Love's avatar
Dave Love committed
402
;;;###autoload
Richard M. Stallman's avatar
Richard M. Stallman committed
403
(defun symbol-at-point () (form-at-point 'sexp 'symbolp))
Dave Love's avatar
Dave Love committed
404
;;;###autoload
Richard M. Stallman's avatar
Richard M. Stallman committed
405
(defun number-at-point () (form-at-point 'sexp 'numberp))
Dave Love's avatar
Dave Love committed
406
;;;###autoload
Richard M. Stallman's avatar
Richard M. Stallman committed
407 408
(defun list-at-point ()   (form-at-point 'list 'listp))

409
;;; thingatpt.el ends here