Skip to content

<regex>: Optimize skip heuristic for searches of patterns with initial dot wildcards #6189

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
StephanTLavavej merged 2 commits into from
Mar 31, 2026
Merged

<regex>: Optimize skip heuristic for searches of patterns with initial dot wildcards #6189

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e7f3100
`<regex>`: Optimize skip heuristic for searches of patterns with init…
muellerj2 Mar 29, 2026
ba5b471
regex_search.cpp: Fix benchmark name to match args.
StephanTLavavej Mar 30, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions benchmarks/src/regex_search.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,5 +47,8 @@ BENCHMARK_CAPTURE(bm_lorem_search, R"(\Bibe)", R"(\Bibe)")->Apply(common_args);
BENCHMARK_CAPTURE(bm_lorem_search, R"((?=....)bibe)", R"((?=....)bibe)")->Apply(common_args);
BENCHMARK_CAPTURE(bm_lorem_search, R"((?=bibe)....)", R"((?=bibe)....)")->Apply(common_args);
BENCHMARK_CAPTURE(bm_lorem_search, R"((?!lorem)bibe)", R"((?!lorem)bibe)")->Apply(common_args);
BENCHMARK_CAPTURE(bm_lorem_search, "(bibe|soda)", "(bibe|soda)")->Apply(common_args);
BENCHMARK_CAPTURE(bm_lorem_search, "(id )?bibe", "(id )?bibe")->Apply(common_args);
BENCHMARK_CAPTURE(bm_lorem_search, ".bibe", ".bibe")->Apply(common_args);

BENCHMARK_MAIN();
11 changes: 10 additions & 1 deletion stl/inc/regex
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5015,13 +5015,22 @@ _It _Matcher3<_Elem, _RxTraits, _It, _Alloc>::_Skip(
return _First;
}

case _N_dot:
{
if (_Recursion_depth >= _Max_recursion_depth) {
return _First;
}

_First = _Skip(++_First, _Last, _Nx->_Next, _Recursion_depth + 1U);
return --_First;
}

case _N_begin:
case _N_endif:
break;

case _N_end:
case _N_none:
case _N_dot:
case _N_back:
case _N_end_rep:
default:
Expand Down
16 changes: 16 additions & 0 deletions tests/std/tests/VSO_0000000_regex_use/test.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2507,6 +2507,21 @@ void test_gh_6181() {
}
}

void test_gh_6189() {
// GH-6189: Optimize skip heuristic for searches of patterns with initial dot wildcards
test_regex re(&g_regexTester, ".abc");
re.should_search_match("dabc", "dabc");
re.should_search_match("dabcdddd", "dabc");
re.should_search_match("ddabc", "dabc");
re.should_search_match("ddabcdddd", "dabc");
re.should_search_match("ddddddddddddddddabcdddddddddddd", "dabc");
re.should_search_match("ddddddddddddddddddddddddabc", "dabc");
re.should_search_match("ddabcddd", "dabc");
re.should_search_fail("abcddddd");
re.should_search_fail("ddddddddddd\nabcdddddddddd");
re.should_search_fail("d");
}

int main() {
test_dev10_449367_case_insensitivity_should_work();
test_dev11_462743_regex_collate_should_not_disable_regex_icase();
Expand Down Expand Up @@ -2572,6 +2587,7 @@ int main() {
test_gh_6118();
test_gh_6147();
test_gh_6181();
test_gh_6189();

return g_regexTester.result();
}