GNU bug report logs - #36398
Lax char-fold search

Previous Next

Full log

View this message in rfc822 format

From: Juri Linkov <juri <at> linkov.net>
To: 36398 <at> debbugs.gnu.org
Subject: bug#36398: Lax char-fold search
Date: Thu, 27 Jun 2019 00:12:08 +0300

[Message part 1 (text/plain, inline)]

Before finishing bug#35689, I'd like to implement the argument LAX of
char-fold-to-regexp, so e.g. during isearch when point is at the beginning
of the word with ligature “fix”, typing three letters ‘f’, ‘i’, ‘x’
will keep point matching on the same word:

[char-fold-to-regexp-lax.patch (text/x-diff, inline)]

diff --git a/lisp/char-fold.el b/lisp/char-fold.el
index 7223ecf738..9d3ea17b41 100644
--- a/lisp/char-fold.el
+++ b/lisp/char-fold.el
@@ -148,12 +148,18 @@ char-fold--make-space-string
                  (make-list n (or (aref char-fold-table ?\s) " ")))))
 
 ;;;###autoload
-(defun char-fold-to-regexp (string &optional _lax from)
+(defun char-fold-to-regexp (string &optional lax from)
   "Return a regexp matching anything that char-folds into STRING.
 Any character in STRING that has an entry in
 `char-fold-table' is replaced with that entry (which is a
 regexp) and other characters are `regexp-quote'd.
 
+When LAX is non-nil, then the final character also matches ligatures
+partially, for instance, the search string \"f\" will match \"fi\",
+so when typing the search string in isearch while the cursor is on
+a ligature, the search won't try to immediately advance to the next
+complete match, but will stay on the partially matched ligature.
+
 If the resulting regexp would be too long for Emacs to handle,
 just return the result of calling `regexp-quote' on STRING.
 
@@ -183,7 +189,11 @@ char-fold-to-regexp
                  ;; Long string.  The regexp would probably be too long.
                  (alist (unless (> end 50)
                           (aref multi-char-table c))))
-             (push (let ((matched-entries nil)
+             (push (if (and lax alist (= (1+ i) end))
+                       (concat "\\(?:" regexp "\\|"
+                               (mapconcat (lambda (entry)
+                                            (cdr entry)) alist "\\|") "\\)")
+                     (let ((matched-entries nil)
                            (max-length 0))
                        (dolist (entry alist)
                          (let* ((suffix (car entry))
@@ -212,7 +222,7 @@ char-fold-to-regexp
                                            (concat suffix-regexp
                                                    (char-fold-to-regexp subs nil length))))
                                        `((0 . ,regexp) . ,matched-entries) "\\|")
-                          "\\)"))))
+                            "\\)")))))
                    out))))
       (setq i (1+ i)))
     (when (> spaces 0)
diff --git a/test/lisp/char-fold-tests.el b/test/lisp/char-fold-tests.el
index 3fde312a13..e9dfd2b733 100644
--- a/test/lisp/char-fold-tests.el
+++ b/test/lisp/char-fold-tests.el
@@ -82,6 +82,14 @@ char-fold--test-search-with-contents
       (set-char-table-extra-slot char-fold-table 0 multi)
       (char-fold--test-match-exactly (car it) (cdr it)))))
 
+(ert-deftest char-fold--test-multi-lax ()
+ (dolist (it '(("f" . "fi") ("f" . "ff")))
+   (with-temp-buffer
+     (insert (cdr it))
+     (goto-char (point-min))
+     (should (search-forward-regexp
+              (char-fold-to-regexp (car it) 'lax) nil 'noerror)))))
+
 (ert-deftest char-fold--test-fold-to-regexp ()
   (let ((char-fold-table (make-char-table 'char-fold-table))
         (multi  (make-char-table 'char-fold-table)))

Previous Next

GNU bug tracking system
Copyright (C) 1999 Darren O. Benham, 1997,2003 nCipher Corporation Ltd, 1994-97 Ian Jackson.