[Emacs-diffs] master 478bbf7: Prevent over-eager rx character range condensation

[Mattias Engdegård]

branch: master
commit 478bbf7c80e71ff84f0e4e1363bf86e93d9c51c3
Author: Mattias Engdegård <address@hidden>
Commit: Mattias Engdegård <address@hidden>

    Prevent over-eager rx character range condensation
    
    `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" ?Ã…) 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).
---
 etc/NEWS                         | 8 ++++++++
 lisp/emacs-lisp/rx.el            | 7 +++++++
 test/lisp/emacs-lisp/rx-tests.el | 6 +++++-
 3 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/etc/NEWS b/etc/NEWS
index 70a50c0..0cafbaa 100644
--- a/etc/NEWS
+++ b/etc/NEWS
@@ -1101,6 +1101,14 @@ subexpression.
 When there is no menu for a mode, display the mode name after the
 indicator instead of just the indicator (which is sometimes cryptic).
 
+** rx
+
+---
+*** rx now handles raw bytes in character alternatives correctly,
+when given in a string.  Previously, '(any "\x80-\xff")' would match
+characters U+0080...U+00FF.  Now the expression matches raw bytes in
+the 128...255 range, as expected.
+
 
 * New Modes and Packages in Emacs 27.1
 
diff --git a/lisp/emacs-lisp/rx.el b/lisp/emacs-lisp/rx.el
index b229903..715cd60 100644
--- a/lisp/emacs-lisp/rx.el
+++ b/lisp/emacs-lisp/rx.el
@@ -429,6 +429,13 @@ Only both edges of each range is checked."
     ;; set L list of all ranges
     (mapc (lambda (e) (cond ((stringp e) (push e str))
                            ((numberp e) (push (cons e e) l))
+                            ;; Ranges between ASCII and raw bytes are split,
+                            ;; to prevent accidental inclusion of Unicode
+                            ;; characters later on.
+                            ((and (<= (car e) #x7f)
+                                  (>= (cdr e) #x3fff80))
+                             (push (cons (car e) #x7f) l)
+                             (push (cons #x3fff80 (cdr e)) l))
                            (t (push e l))))
          args)
     ;; condense overlapped ranges in L
diff --git a/test/lisp/emacs-lisp/rx-tests.el b/test/lisp/emacs-lisp/rx-tests.el
index f15e101..e14feda 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 "Ã…\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"