From: Mattias Engdegård Date: Wed, 9 Oct 2019 08:22:10 +0000 (+0200) Subject: Use [^z-a] for matching any character (anychar/anything) in rx X-Git-Tag: emacs-27.0.90~1007 X-Git-Url: http://git.eshelyaron.com/gitweb/?a=commitdiff_plain;h=6331d23de3a861de2374be2c03b42e3a2f150792;p=emacs.git Use [^z-a] for matching any character (anychar/anything) in rx * lisp/emacs-lisp/rx.el (rx--translate-symbol): * test/lisp/emacs-lisp/rx-tests.el (rx-any, rx-atoms): Use [^z-a] instead of ".\\|\n" for anychar. The new expression is faster (about 2×) and does not allocate regexp stack space. For example, (0+ anychar) now matches strings of any size (bug#37659). --- diff --git a/lisp/emacs-lisp/rx.el b/lisp/emacs-lisp/rx.el index cf02df239fe..87b3133b7f5 100644 --- a/lisp/emacs-lisp/rx.el +++ b/lisp/emacs-lisp/rx.el @@ -136,7 +136,7 @@ Each entry is: ;; Use `list' instead of a quoted list to wrap the strings here, ;; since the return value may be mutated. ((or 'nonl 'not-newline 'any) (cons (list ".") t)) - ((or 'anychar 'anything) (rx--translate-form '(or nonl "\n"))) + ((or 'anychar 'anything) (cons (list "[^z-a]") t)) ('unmatchable (rx--empty)) ((or 'bol 'line-start) (cons (list "^") 'lseq)) ((or 'eol 'line-end) (cons (list "$") 'rseq)) diff --git a/test/lisp/emacs-lisp/rx-tests.el b/test/lisp/emacs-lisp/rx-tests.el index 903b191c98e..ef2541d83af 100644 --- a/test/lisp/emacs-lisp/rx-tests.el +++ b/test/lisp/emacs-lisp/rx-tests.el @@ -126,9 +126,9 @@ (should (equal (rx (not (any "!a" "0-8" digit nonascii))) "[^!0-8a[:digit:][:nonascii:]]")) (should (equal (rx (any) (not (any))) - "\\`a\\`\\(?:.\\|\n\\)")) + "\\`a\\`[^z-a]")) (should (equal (rx (any "") (not (any ""))) - "\\`a\\`\\(?:.\\|\n\\)"))) + "\\`a\\`[^z-a]"))) (ert-deftest rx-pcase () (should (equal (pcase "a 1 2 3 1 1 b" @@ -185,7 +185,7 @@ (ert-deftest rx-atoms () (should (equal (rx anychar anything) - "\\(?:.\\|\n\\)\\(?:.\\|\n\\)")) + "[^z-a][^z-a]")) (should (equal (rx unmatchable) "\\`a\\`")) (should (equal (rx line-start not-newline nonl any line-end)