From 478bbf7c80e71ff84f0e4e1363bf86e93d9c51c3 Mon Sep 17 00:00:00 2001 From: Mattias Engdegård Date: Fri, 15 Feb 2019 19:27:48 +0100 Subject: Prevent over-eager rx character range condensation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit `rx' incorrectly considers character ranges between ASCII and raw bytes to cover all codes in-between, which includes all non-ASCII Unicode chars. This causes (any "\000-\377" ?Å) to be simplified to (any "\000-\377"), which is not at all the same thing: [\000-\377] really means [\000-\177\200-\377] (Bug#34492). * lisp/emacs-lisp/rx.el (rx-any-condense-range): Split ranges going from ASCII to raw bytes. * test/lisp/emacs-lisp/rx-tests.el (rx-char-any-raw-byte): Add test case. * etc/NEWS: Mention the overall change (Bug#33205). --- test/lisp/emacs-lisp/rx-tests.el | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'test/lisp/emacs-lisp') diff --git a/test/lisp/emacs-lisp/rx-tests.el b/test/lisp/emacs-lisp/rx-tests.el index f15e1016f7c..e14feda347f 100644 --- a/test/lisp/emacs-lisp/rx-tests.el +++ b/test/lisp/emacs-lisp/rx-tests.el @@ -53,7 +53,11 @@ ;; Range of raw characters, multibyte. (should (equal (string-match-p (rx (any "Å\211\326-\377\177")) "XY\355\177\327") - 2))) + 2)) + ;; Split range; \177-\377ÿ should not be optimised to \177-\377. + (should (equal (string-match-p (rx (any "\177-\377" ?ÿ)) + "ÿA\310B") + 0))) (ert-deftest rx-pcase () (should (equal (pcase "a 1 2 3 1 1 b" -- cgit v1.2.3