Handle raw bytes, and LF in ranges, in rx `any' argument strings

* lisp/emacs-lisp/rx.el (rx-check-any-string): Rewrite to handle raw bytes
in unibyte strings and accept LF as range endpoints (Bug#33205).
* test/lisp/emacs-lisp/rx-tests.el: Add tests for the above.

diff --git a/lisp/emacs-lisp/rx.el b/lisp/emacs-lisp/rx.el
index 1230df4f15d2609c067dec76bea9a94914164977..1cae22f870a7e1d02b4830f7810ddf1a08210ff8 100644 (file)
--- a/lisp/emacs-lisp/rx.el
+++ b/lisp/emacs-lisp/rx.el
@@ -449,28 +449,35 @@ Only both edges of each range is checked."
 
 
 (defun rx-check-any-string (str)
-  "Check string argument STR for Rx `any'."
-  (let ((i 0)
-       c1 c2 l)
-    (if (= 0 (length str))
-       (error "String arg for Rx `any' must not be empty"))
-    (while (string-match ".-." str i)
-      ;; string before range: convert it to characters
-      (if (< i (match-beginning 0))
-         (setq l (nconc
-                  l
-                  (append (substring str i (match-beginning 0)) nil))))
-      ;; range
-      (setq i (match-end 0)
-           c1 (aref str (match-beginning 0))
-           c2 (aref str (1- i)))
-      (cond
-       ((< c1 c2) (setq l (nconc l (list (cons c1 c2)))))
-       ((= c1 c2) (setq l (nconc l (list c1))))))
-    ;; rest?
-    (if (< i (length str))
-       (setq l (nconc l (append (substring str i) nil))))
-    l))
+  "Turn the `any' argument string STR into a list of characters.
+The original order is not preserved.  Ranges, \"A-Z\", become pairs, (?A . ?Z)."
+  (let ((decode-char
+         ;; Make sure raw bytes are decoded as such, to avoid confusion with
+         ;; U+0080..U+00FF.
+         (if (multibyte-string-p str)
+             #'identity
+           (lambda (c) (if (<= #x80 c #xff)
+                           (+ c #x3fff00)
+                         c))))
+        (len (length str))
+        (i 0)
+        (ret nil))
+    (if (= 0 len)
+        (error "String arg for Rx `any' must not be empty"))
+    (while (< i len)
+      (cond ((and (< i (- len 2))
+                  (= (aref str (+ i 1)) ?-))
+             ;; Range.
+             (let ((start (funcall decode-char (aref str i)))
+                   (end   (funcall decode-char (aref str (+ i 2)))))
+               (cond ((< start end) (push (cons start end) ret))
+                     ((= start end) (push start ret)))
+               (setq i (+ i 3))))
+            (t
+             ;; Single character.
+             (push (funcall decode-char (aref str i)) ret)
+             (setq i (+ i 1)))))
+    ret))
 
 
 (defun rx-check-any (arg)

diff --git a/test/lisp/emacs-lisp/rx-tests.el b/test/lisp/emacs-lisp/rx-tests.el
index d15e3d77199d21148996a652844de23487f5d7a0..8b3ce6cb01fe55f665c4032913263f80f9de3b25 100644 (file)
--- a/test/lisp/emacs-lisp/rx-tests.el
+++ b/test/lisp/emacs-lisp/rx-tests.el
@@ -33,6 +33,28 @@
                                   (number-sequence ?< ?\])
                                   (number-sequence ?- ?:))))))
 
+(ert-deftest rx-char-any-range-nl ()
+  "Test character alternatives with LF as a range endpoint."
+  (should (equal (rx (any "\n-\r"))
+                 "[\n-\r]"))
+  (should (equal (rx (any "\a-\n"))
+                 "[\a-\n]")))
+
+(ert-deftest rx-char-any-raw-byte ()
+  "Test raw bytes in character alternatives."
+  ;; Separate raw characters.
+  (should (equal (string-match-p (rx (any "\326A\333B"))
+                                 "X\326\333")
+                 1))
+  ;; Range of raw characters, unibyte.
+  (should (equal (string-match-p (rx (any "\200-\377"))
+                                 "ÿA\310B")
+                 2))
+  ;; Range of raw characters, multibyte.
+  (should (equal (string-match-p (rx (any "Å\211\326-\377\177"))
+                                 "XY\355\177\327")
+                 2)))
+
 (ert-deftest rx-pcase ()
   (should (equal (pcase "a 1 2 3 1 1 b"
                    ((rx (let u (+ digit)) space