From 5a21aaff468ec3f0337117707cda4254cbef8de7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mattias=20Engdeg=C3=A5rd?= <mattiase@acm.org>
Date: Tue, 11 Feb 2020 13:23:10 +0100
Subject: [PATCH] rx: Use longest match for all-string 'or' forms (bug#37659)

Revert to the Emacs 26 semantics that always gave the longest match
for rx 'or' forms with only string arguments.  This guarantee was
never well documented, but it is useful and people likely have come to
rely on it.  For example, prior to this change,

 (rx (or ">" ">="))

matched ">" even if the text contained ">=".

* lisp/emacs-lisp/rx.el (rx--translate-or): Don't tell regexp-opt to
preserve the matching order.
* doc/lispref/searching.texi (Rx Constructs): Document the
longest-match guarantee for all-string 'or' forms.
* test/lisp/emacs-lisp/rx-tests.el (rx-or): Update test.
---
 doc/lispref/searching.texi       | 5 ++++-
 lisp/emacs-lisp/rx.el            | 2 +-
 test/lisp/emacs-lisp/rx-tests.el | 2 +-
 3 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/doc/lispref/searching.texi b/doc/lispref/searching.texi
index 3d7ea932863..5f4509a8b43 100644
--- a/doc/lispref/searching.texi
+++ b/doc/lispref/searching.texi
@@ -1080,7 +1080,10 @@ Corresponding string regexp: @samp{@var{A}@var{B}@dots{}}
 @cindex @code{or} in rx
 @itemx @code{(| @var{rx}@dots{})}
 @cindex @code{|} in rx
-Match exactly one of the @var{rx}s, trying from left to right.
+Match exactly one of the @var{rx}s.
+If all arguments are string literals, the longest possible match
+will always be used.  Otherwise, either the longest match or the
+first (in left-to-right order) will be used.
 Without arguments, the expression will not match anything at all.@*
 Corresponding string regexp: @samp{@var{A}\|@var{B}\|@dots{}}.
 
diff --git a/lisp/emacs-lisp/rx.el b/lisp/emacs-lisp/rx.el
index 03af053c91e..b4cab5715da 100644
--- a/lisp/emacs-lisp/rx.el
+++ b/lisp/emacs-lisp/rx.el
@@ -290,7 +290,7 @@ Return (REGEXP . PRECEDENCE)."
    ((null (cdr body))              ; Single item.
     (rx--translate (car body)))
    ((rx--every #'stringp body)     ; All strings.
-    (cons (list (regexp-opt body nil t))
+    (cons (list (regexp-opt body nil))
           t))
    ((rx--every #'rx--charset-p body)  ; All charsets.
     (rx--translate-union nil body))
diff --git a/test/lisp/emacs-lisp/rx-tests.el b/test/lisp/emacs-lisp/rx-tests.el
index e19e626527b..a6c172adfe7 100644
--- a/test/lisp/emacs-lisp/rx-tests.el
+++ b/test/lisp/emacs-lisp/rx-tests.el
@@ -43,7 +43,7 @@
   (should (equal (rx (or "ab" (| "c" nonl) "de"))
                  "ab\\|c\\|.\\|de"))
   (should (equal (rx (or "ab" "abc" "a"))
-                 "\\(?:ab\\|abc\\|a\\)"))
+                 "\\(?:a\\(?:bc?\\)?\\)"))
   (should (equal (rx (| nonl "a") (| "b" blank))
                  "\\(?:.\\|a\\)\\(?:b\\|[[:blank:]]\\)"))
   (should (equal (rx (|))