From bea6410138c538908bb15639675e9835c66e70bc Mon Sep 17 00:00:00 2001
From: Volodymyr Chernetskyi <volodymyr_chernetskyi@goodyear.com>
Date: Tue, 8 Sep 2026 15:50:03 +0200
Subject: [PATCH] vim-patch:9.2.1046: regex: case-insensitive match fails on
 multi-byte string with re=1 (#41781)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Problem:  With 'regexpengine' set to 1 a case-insensitive match against
          a literal string fails when the string starts with a
          multi-byte character that is longer than a character following
          it, so the two regexp engines disagree (after v9.1.0645).
Solution: In cstrncmp() advance by the length of the character at the
          current position instead of always measuring the first
          character of "s1" (Volodymyr Chernetskyi).

cstrncmp() walks "s1" to find how many characters make up "*n" bytes, so
that it can measure out the same number of characters in "s2". The loop
decremented the remaining byte count by mb_ptr2len(s1), which always
returns the length of the *first* character, rather than the length of
the character at the current position "p".

When the first character is longer than a later one the byte count runs
out too early, the character count comes up short, and MB_STRNICMP2() is
handed a length for "s2" that is too small, so the comparison fails. For
example matching "\cüber" against "Überraschung": "über" is five bytes,
but each iteration subtracts two (the length of "ü"), so the loop runs
three times instead of four.

    :set regexpengine=1
    echo matchstr('Überraschung', '\cüber')

returns an empty string, while 'regexpengine' set to 2 correctly returns
"Über". The default value of 0 uses the NFA engine and is unaffected.

related: vim/vim#14756
closes:  vim/vim#21212

https://github.com/vim/vim/commit/4e5ac0d68a3e35602b63fba7b334baa9dc7cc22e
---
 src/nvim/regexp.c                     | 2 +-
 test/old/testdir/test_regexp_utf8.vim | 6 ++++++
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/src/nvim/regexp.c b/src/nvim/regexp.c
index 3b63c6ec8f..5074e3a8d5 100644
--- a/src/nvim/regexp.c
+++ b/src/nvim/regexp.c
@@ -1759,7 +1759,7 @@ static int cstrncmp(char *s1, char *s2, int *n)
     int n1 = *n;
     // count the number of characters for byte-length of s1
     while (n1 > 0 && *p != NUL) {
-      n1 -= utfc_ptr2len(s1);
+      n1 -= utfc_ptr2len(p);
       MB_PTR_ADV(p);
       n2++;
     }
diff --git a/test/old/testdir/test_regexp_utf8.vim b/test/old/testdir/test_regexp_utf8.vim
index f5ec0b77d2..272d3d535e 100644
--- a/test/old/testdir/test_regexp_utf8.vim
+++ b/test/old/testdir/test_regexp_utf8.vim
@@ -363,6 +363,12 @@ func Run_regexp_ignore_case()
   call assert_equal('iIx', substitute('iIİ', '\c\(\%u0130\)', 'x', 'g'))
   call assert_equal('iIx', substitute('iIİ', '\c\([\u0130]\)', 'x', 'g'))
   call assert_equal('iIx', substitute('iIİ', '\c\([\u012f-\u0131]\)', 'x', 'g'))
+
+  " Ignoring case in a literal string that starts with a character longer
+  " than a following one must still match.
+  call assert_equal('Über', matchstr('Überraschung', '\cüber'))
+  call assert_equal('Ünder', matchstr('Ünderdog', '\cünder'))
+  call assert_equal('αaaa', matchstr('αaaaa', '\cαaaa'))
 endfunc
 
 func Test_regexp_ignore_case()