From: Stefan Monnier <monnier@iro.umontreal.ca>
Date: Mon, 22 Jan 2024 20:06:24 +0000 (-0500)
Subject: * src/regex-emacs.c (forall_firstchar_1): Improve corner case
X-Git-Url: http://git.eshelyaron.com/gitweb/?a=commitdiff_plain;h=912f8ce2c5372a10bbfefb7967f640cd7a736f4d;p=emacs.git

* src/regex-emacs.c (forall_firstchar_1): Improve corner case

Fixes a "FORALL_FIRSTCHAR: Broken assumption2!!" warning with:

    "^\\(# *\\)\\([^ ]+?\\) *: *\\(.*?\\(?:\n\\1[ \t]+.*?\\)*\\)[[:space:]]*$"

(cherry picked from commit f821ac29e0cf69316d6c721bafe9b749b47a6db3)
---

diff --git a/src/regex-emacs.c b/src/regex-emacs.c
index dfc6c1fd691..0ec0c6eb63f 100644
--- a/src/regex-emacs.c
+++ b/src/regex-emacs.c
@@ -2923,8 +2923,18 @@ forall_firstchar_1 (re_char *p, re_char *pend,
                forward over a subsequent `jump`.  Recognize this pattern
                since that subsequent `jump` is the one that jumps to the
                loop-entry.  */
-	    newp2 = ((re_opcode_t) *newp2 == jump)
-	            ? extract_address (newp2 + 1) : newp2;
+	    if ((re_opcode_t) *newp2 == jump)
+	      {
+	        re_char *p3 = extract_address (newp2 + 1);
+	        /* Only recognize this pattern if one of the two destinations
+	           is going forward, otherwise we'll fall into the pessimistic
+	           "Both destinations go backward" below.
+	           This is important if the `jump` at newp2 is the end of an
+	           outer loop while the `on_failure_jump` is the end of an
+	           inner loop.  */
+	        if (p3 > p_orig || newp1 > p_orig)
+	          newp2 = p3;
+	      }
 
 	  do_twoway_jump:
 	    /* We have to check that both destinations are safe.