thingatpt.el 13.1 KB
Newer Older
Richard M. Stallman's avatar
Richard M. Stallman committed
1 2
;;; thingatpt.el --- Get the `thing' at point

3
;; Copyright (C) 1991,92,93,94,95,96,97,1998 Free Software Foundation, Inc.
Richard M. Stallman's avatar
Richard M. Stallman committed
4 5

;; Author: Mike Williams <mikew@gopher.dosli.govt.nz>
Richard M. Stallman's avatar
Richard M. Stallman committed
6
;; Keywords: extensions, matching, mouse
Richard M. Stallman's avatar
Richard M. Stallman committed
7 8 9 10 11 12 13 14 15 16 17 18 19 20
;; 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
21
;;; Commentary:
Erik Naggum's avatar
Erik Naggum committed
22

23 24
;; 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
25
;; its beginning and end positions in the buffer.
Richard M. Stallman's avatar
Richard M. Stallman committed
26 27
;;
;; The function bounds-of-thing-at-point finds the beginning and end
28
;; positions by moving first forward to the end of the "thing", and then
Richard M. Stallman's avatar
Richard M. Stallman committed
29
;; backwards to the beginning.  By default, it uses the corresponding
30
;; forward-"thing" operator (eg. forward-word, forward-line).
Richard M. Stallman's avatar
Richard M. Stallman committed
31 32
;;
;; Special cases are allowed for using properties associated with the named
33
;; "thing": 
Richard M. Stallman's avatar
Richard M. Stallman committed
34
;;
35
;;   forward-op		Function to call to skip forward over a "thing" (or
Richard M. Stallman's avatar
Richard M. Stallman committed
36 37
;;                      with a negative argument, backward).
;;                      
38 39
;;   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
40 41 42 43 44 45
;;
;; 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
46
;;; Code:
Richard M. Stallman's avatar
Richard M. Stallman committed
47 48 49

(provide 'thingatpt)

Erik Naggum's avatar
Erik Naggum committed
50
;; Basic movement
Richard M. Stallman's avatar
Richard M. Stallman committed
51 52

;;;###autoload
53
(defun forward-thing (thing &optional n)
Richard M. Stallman's avatar
Richard M. Stallman committed
54
  "Move forward to the end of the next THING."
55 56
  (let ((forward-op (or (get thing 'forward-op)
			(intern-soft (format "forward-%s" thing)))))
Richard M. Stallman's avatar
Richard M. Stallman committed
57
    (if (fboundp forward-op)
58 59
	(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
60

Erik Naggum's avatar
Erik Naggum committed
61
;; General routines
Richard M. Stallman's avatar
Richard M. Stallman committed
62 63

;;;###autoload
64 65 66 67 68 69 70 71 72 73 74
(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."
75 76 77 78 79 80 81
  (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 
82 83 84
			 (funcall 
			  (or (get thing 'end-op) 
			      (function (lambda () (forward-thing thing 1)))))
85 86 87 88 89
			 (point)))
		  (beg (progn 
			 (funcall 
			  (or (get thing 'beginning-op) 
			      (function (lambda () (forward-thing thing -1)))))
90
			 (point))))
91 92 93 94 95 96
	      (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 
97 98 99
			   (funcall 
			    (or (get thing 'end-op) 
				(function (lambda () (forward-thing thing 1)))))
100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124
			   (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
125 126

;;;###autoload
127 128 129 130 131 132 133 134
(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."
135 136 137 138 139
  (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
140

Erik Naggum's avatar
Erik Naggum committed
141
;; Go to beginning/end
Richard M. Stallman's avatar
Richard M. Stallman committed
142

143 144 145
(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
146 147
    (goto-char (car bounds))))

148 149 150
(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
151 152
    (goto-char (cdr bounds))))

Erik Naggum's avatar
Erik Naggum committed
153
;;  Special cases 
Richard M. Stallman's avatar
Richard M. Stallman committed
154

Erik Naggum's avatar
Erik Naggum committed
155
;;  Lines 
156 157 158 159 160 161 162

;; 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
163
;;  Sexps 
Richard M. Stallman's avatar
Richard M. Stallman committed
164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179

(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)

180 181 182 183 184 185 186 187 188
(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
189
;;  Lists 
Richard M. Stallman's avatar
Richard M. Stallman committed
190 191 192 193

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

194
;;  Filenames and URLs
Richard M. Stallman's avatar
Richard M. Stallman committed
195

196
(defvar thing-at-point-file-name-chars "~/A-Za-z0-9---_.${}#%,:"
Richard M. Stallman's avatar
Richard M. Stallman committed
197 198 199
  "Characters allowable in filenames.")

(put 'filename 'end-op    
200
     '(lambda () (skip-chars-forward thing-at-point-file-name-chars)))
Richard M. Stallman's avatar
Richard M. Stallman committed
201
(put 'filename 'beginning-op
202 203
     '(lambda () (skip-chars-backward thing-at-point-file-name-chars)))

204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243
(defvar thing-at-point-url-path-regexp
  "[^]\t\n \"'()<>[^`{}]*[^]\t\n \"'()<>[^`{}.,;]+"
  "A regular expression probably matching the host, path or e-mail part of a URL.")

(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''.")

(defvar thing-at-point-url-regexp
  (concat
   "\\(https?://\\|ftp://\\|gopher://\\|telnet://\\|wais://\\|file:/\\|s?news:\\|mailto:\\)"
   thing-at-point-url-path-regexp)
  "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.
244 245 246 247 248 249

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."

250 251 252 253 254 255 256 257 258 259 260 261
  (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
262
	  (while (string-match "[ \t\n\r]+" url)
263
	    (setq url (replace-match "" t t url)))
264 265 266 267 268 269 270
	  (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)))
271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309
	  (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)))))

310 311 312 313 314 315
(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"))))))
316
(put 'url 'beginning-op
317 318 319 320 321
     (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
322

Erik Naggum's avatar
Erik Naggum committed
323
;;  Whitespace 
Richard M. Stallman's avatar
Richard M. Stallman committed
324

325
(defun forward-whitespace (arg)
Richard M. Stallman's avatar
Richard M. Stallman committed
326
  (interactive "p")
327
  (if (natnump arg) 
328
      (re-search-forward "[ \t]+\\|\n" nil 'move arg)
329
    (while (< arg 0)
330
      (if (re-search-backward "[ \t]+\\|\n" nil 'move)
Richard M. Stallman's avatar
Richard M. Stallman committed
331 332
	  (or (eq (char-after (match-beginning 0)) 10)
	      (skip-chars-backward " \t")))
333
      (setq arg (1+ arg)))))
Richard M. Stallman's avatar
Richard M. Stallman committed
334

Erik Naggum's avatar
Erik Naggum committed
335
;;  Buffer 
Richard M. Stallman's avatar
Richard M. Stallman committed
336

337 338
(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
339

Erik Naggum's avatar
Erik Naggum committed
340
;;  Symbols 
Richard M. Stallman's avatar
Richard M. Stallman committed
341

342
(defun forward-symbol (arg)
Richard M. Stallman's avatar
Richard M. Stallman committed
343
  (interactive "p")
344
  (if (natnump arg) 
345
      (re-search-forward "\\(\\sw\\|\\s_\\)+" nil 'move arg)
346
    (while (< arg 0)
347
      (if (re-search-backward "\\(\\sw\\|\\s_\\)+" nil 'move)
Richard M. Stallman's avatar
Richard M. Stallman committed
348
	  (skip-syntax-backward "w_"))
349
      (setq arg (1+ arg)))))
Richard M. Stallman's avatar
Richard M. Stallman committed
350

Erik Naggum's avatar
Erik Naggum committed
351
;;  Syntax blocks 
352 353 354 355 356 357 358 359 360 361 362

(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
363
;;  Aliases 
Richard M. Stallman's avatar
Richard M. Stallman committed
364 365 366 367

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

368 369 370 371
(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
372 373
	 (more-left 
	  (condition-case nil
374
	      (progn (read-from-string (substring str (cdr read-data)))
Richard M. Stallman's avatar
Richard M. Stallman committed
375 376 377 378 379 380
		     t)
	    (end-of-file nil))))
    (if more-left
	(error "Can't read whole string")
      (car read-data))))

381
(defun form-at-point (&optional thing pred) 
Richard M. Stallman's avatar
Richard M. Stallman committed
382
  (let ((sexp (condition-case nil 
383
		  (read-from-whole-string (thing-at-point (or thing 'sexp)))
Richard M. Stallman's avatar
Richard M. Stallman committed
384
		(error nil))))
385
    (if (or (not pred) (funcall pred sexp)) sexp)))
Richard M. Stallman's avatar
Richard M. Stallman committed
386 387 388 389 390 391 392

(defun sexp-at-point ()   (form-at-point 'sexp))
(defun symbol-at-point () (form-at-point 'sexp 'symbolp))
(defun number-at-point () (form-at-point 'sexp 'numberp))
(defun list-at-point ()   (form-at-point 'list 'listp))

;; thingatpt.el ends here.