tec/org-mode
tec
/
org-mode
forked from mirrors/org-mode
1
0
Fork 0
Code Pull Requests Releases Activity

Work around regexp size limitation for large number of link targets 

* lisp/ol.el (org-target-link-regexp-limit): New constant defining
maximum regexp limit where `org-target-link-regexp' is still safe to
use without triggering "Regexp too long" error.
(org-target-link-regexps): New variable holding a series of shorter
regexps to be used instead of too long single
`org-target-link-regexp'.
(org--re-list-search-forward): New function like `re-search-forward',
but accepting a list of regexps.
(org--re-list-looking-at): New function like `looking-at', but
accepting a list of regexps.
(org-update-radio-target-regexp): When `org-target-link-regexp' is too
long, set `org-target-link-regexps', partitioning the link target list
into smaller regexps.
* lisp/org-element.el (org-element-link-parser):
(org-element--object-lex):
* lisp/org.el (org-activate-target-links): Use
`org--re-list-search-forward' and `org--re-list-looking-at' when
`org-target-link-regexps' is non-nil.
* testing/lisp/test-org-element.el (test-org-element/link-parser): Add
tests.

Reported-by: Rudolf Adamkovič <salutis@me.com>
Link: https://list.orgmode.org/orgmode/m2lenax5m6.fsf@me.com/
This commit is contained in:
Ihor Radchenko 2024-02-19 12:19:34 +03:00
parent dd4d05a159
commit 341a01a07d
No known key found for this signature in database
GPG Key ID: 6470762A7DA11D8B
4 changed files with 100 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

71
lisp/ol.el
View File

@ -52,6 +52,7 @@
(declare-function org-do-occur "org" (regexp &optional cleanup))
(declare-function org-element-at-point "org-element" (&optional pom cached-only))
(declare-function org-element-cache-refresh "org-element" (pos))
(declare-function org-element-cache-reset "org-element" (&optional all no-persistence))
(declare-function org-element-context "org-element" (&optional element))
(declare-function org-element-lineage "org-element-ast" (datum &optional types with-self))
(declare-function org-element-link-parser "org-element" ())
@ -532,6 +533,16 @@ links more efficient."
(defvar-local org-target-link-regexp nil
"Regular expression matching radio targets in plain text.")
(defconst org-target-link-regexp-limit (ash 2 10)
"Maximum allowed length of regexp.
The number should generally be ~order of magnitude smaller than
MAX_BUF_SIZE in src/regex-emacs.c. The number of regexp-emacs.c is
for processed regexp, which appears to be larger compared to the
original string length.")
(defvar-local org-target-link-regexps nil
"List of regular expressions matching radio targets in plain text.
This list is non-nil, when a single regexp would be too long to match
all the possible targets, exceeding Emacs' regexp length limit.")
(defvar org-link-types-re nil
"Matches a link that has a url-like prefix like \"http:\".")
@ -2170,6 +2181,34 @@ This command can be called in any mode to insert a link in Org syntax."
(org-load-modules-maybe)
(org-run-like-in-org-mode 'org-insert-link))
(defun org--re-list-search-forward (regexp-list &optional bound noerror count)
"Like `re-search-forward', but REGEXP-LIST is a list of regexps.
BOUND, NOERROR, and COUNT are passed to `re-search-forward'."
(let (result (min-found most-positive-fixnum)
(pos-found nil)
(min-found-data nil)
(tail regexp-list))
(while tail
(setq result (save-excursion (re-search-forward (pop tail) bound t count)))
(when (and result (< result min-found))
(setq min-found result
pos-found (match-end 0)
min-found-data (match-data))))
(if (= most-positive-fixnum min-found)
(pcase noerror
(`t nil)
(_ (re-search-forward (car regexp-list) bound noerror count)))
(set-match-data min-found-data)
(goto-char pos-found))))
(defun org--re-list-looking-at (regexp-list &optional inhibit-modify)
"Like `looking-at', but REGEXP-LIST is a list of regexps.
INHIBIT-MODIFY is passed to `looking-at'."
(catch :found
(while regexp-list
(when (looking-at (pop regexp-list) inhibit-modify)
(throw :found t)))))
;;;###autoload
(defun org-update-radio-target-regexp ()
"Find all radio targets in this file and update the regular expression.
@ -2207,6 +2246,30 @@ Also refresh fontification if needed."
targets
"\\|")
after-re)))
(setq org-target-link-regexps nil)
(let (current-length sub-targets)
(when (<= org-target-link-regexp-limit (length org-target-link-regexp))
(while (or targets sub-targets)
(when (and sub-targets
(or (not targets)
(>= (+ current-length (length (car targets)))
org-target-link-regexp-limit)))
(push (concat before-re
(mapconcat
(lambda (x)
(replace-regexp-in-string
" +" "\\s-+" (regexp-quote x) t t))
(nreverse sub-targets)
"\\|")
after-re)
org-target-link-regexps)
(setq current-length nil
sub-targets nil))
(unless current-length
(setq current-length (+ (length before-re) (length after-re))))
(when targets (push (pop targets) sub-targets))
(cl-incf current-length (length (car sub-targets))))
(setq org-target-link-regexps (nreverse org-target-link-regexps))))
(unless (equal old-regexp org-target-link-regexp)
;; Clean-up cache.
(let ((regexp (cond ((not old-regexp) org-target-link-regexp)
@ -2222,9 +2285,11 @@ Also refresh fontification if needed."
after-re)))))
(when (and (featurep 'org-element)
(not (bound-and-true-p org-mode-loading)))
(org-with-point-at 1
(while (re-search-forward regexp nil t)
(org-element-cache-refresh (match-beginning 1))))))
(if org-target-link-regexps
(org-element-cache-reset)
(org-with-point-at 1
(while (re-search-forward regexp nil t)
(org-element-cache-refresh (match-beginning 1)))))))
;; Re fontify buffer.
(when (memq 'radio org-highlight-links)
(org-restart-font-lock)))))

16
lisp/org-element.el
View File

@ -3848,7 +3848,9 @@ Assume point is at the beginning of the link."
;; Type 1: Text targeted from a radio target.
((and org-target-link-regexp
(save-excursion (or (bolp) (backward-char))
(looking-at org-target-link-regexp)))
(if org-target-link-regexps
(org--re-list-looking-at org-target-link-regexps)
(looking-at org-target-link-regexp))))
(setq type "radio")
(setq format 'plain)
(setq link-end (match-end 1))
@ -5221,7 +5223,10 @@ to an appropriate container (e.g., a paragraph)."
((not (memq 'link restriction)) nil)
((progn
(unless (bolp) (forward-char -1))
(not (re-search-forward org-target-link-regexp nil t)))
(not
(if org-target-link-regexps
(org--re-list-search-forward org-target-link-regexps nil t)
(re-search-forward org-target-link-regexp nil t))))
nil)
;; Since we moved backward, we do not want to
;; match again an hypothetical 1-character long
@ -5230,8 +5235,11 @@ to an appropriate container (e.g., a paragraph)."
;; beginning of line, we prevent this here.
((and (= start (1+ (line-beginning-position)))
(= start (match-end 1)))
(and (re-search-forward org-target-link-regexp nil t)
(1+ (match-beginning 1))))
(and
(if org-target-link-regexps
(org--re-list-search-forward org-target-link-regexps nil t)
(re-search-forward org-target-link-regexp nil t))
(1+ (match-beginning 1))))
(t (1+ (match-beginning 1))))))
found)
(save-excursion

4
lisp/org.el
View File

@ -5710,7 +5710,9 @@ by a #."
;; `org-target-link-regexp' matches one character before the
;; actual target.
(unless (bolp) (forward-char -1))
(when (re-search-forward org-target-link-regexp limit t)
(when (if org-target-link-regexps
(org--re-list-search-forward org-target-link-regexps limit t)
(re-search-forward org-target-link-regexp limit t))
(org-remove-flyspell-overlays-in (match-beginning 1) (match-end 1))
(add-text-properties (match-beginning 1) (match-end 1)
(list 'mouse-face 'highlight

17
testing/lisp/test-org-element.el
View File

@ -2387,6 +2387,23 @@ e^{i\\pi}+1=0
(org-element-property
:type
(org-element-map (org-element-parse-buffer) 'link #'identity nil t)))))
(should
(equal
"radio"
(org-test-with-temp-text "<<<radio>>><<<radio2>>><<<foo>>>A radio link"
(org-update-radio-target-regexp)
(org-element-property
:type
(org-element-map (org-element-parse-buffer) 'link #'identity nil t)))))
(should
(equal
"radio"
(let ((org-target-link-regexp-limit 9))
(org-test-with-temp-text "<<<radio>>><<<radio2>>><<<foo>>>A radio link"
(org-update-radio-target-regexp)
(org-element-property
:type
(org-element-map (org-element-parse-buffer) 'link #'identity nil t))))))
;; Pathological case: radio target of length 1 at beginning of line
;; not followed by spaces.
(should