Skip to content

<regex>: Make back-references to unmatched capture groups not match anything in POSIX basic regexes #5376

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
merged 4 commits into from
Apr 10, 2025
Merged

<regex>: Make back-references to unmatched capture groups not match anything in POSIX basic regexes #5376

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3ab9a83
`<regex>`: Make back-references to unmatched capture groups not match…
muellerj2 Mar 28, 2025
1425012
Extract an internal check for the grammars that lack backreferences.
StephanTLavavej Apr 1, 2025
bc1e3d1
Add ECMAScript coverage.
StephanTLavavej Apr 1, 2025
0add804
Merge branch 'main' into regex-fix-unmatched-backreferences-in-basic-…
StephanTLavavej Apr 10, 2025
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
5 changes: 5 additions & 0 deletions stl/inc/regex
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3662,6 +3662,9 @@ bool _Matcher<_BidIt, _Elem, _RxTraits, _It>::_Match_pat(_Node_base* _Nx) { // c

case _N_back:
{ // check back reference
_STL_INTERNAL_CHECK(
(_Sflags & (regex_constants::extended | regex_constants::egrep | regex_constants::awk))
== 0); // these grammars don't have backreferences
_Node_back* _Node = static_cast<_Node_back*>(_Nx);
if (_Tgt_state._Grp_valid[_Node->_Idx]) { // check for match
_It _Res0 = _Tgt_state._Cur;
Expand All @@ -3673,6 +3676,8 @@ bool _Matcher<_BidIt, _Elem, _RxTraits, _It>::_Match_pat(_Node_base* _Nx) { // c
} else {
_Tgt_state._Cur = _Res0;
}
} else if (_Sflags & (regex_constants::basic | regex_constants::grep)) {
_Failed = true;
}
break;
}
Expand Down
18 changes: 18 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 @@ -1440,6 +1440,23 @@ void test_gh_5371() {
g_regexTester.should_match("", R"(\B)");
}

void test_gh_5374() {
// GH-5374: <regex>: Back-references to unmatched capture groups
// should not match in POSIX basic regular expressions
for (syntax_option_type option : {basic, grep}) {
g_regexTester.should_not_match("", R"(\(.\)*\1)", option);
g_regexTester.should_match("", R"(\(.*\)\1)", option);
g_regexTester.should_not_match("bc", R"(\(a\)*b\1c)", option);
g_regexTester.should_match("bc", R"(\(a*\)b\1c)", option);
}

// ECMAScript's behavior is different:
g_regexTester.should_match("", R"((.)*\1)", ECMAScript);
g_regexTester.should_match("", R"((.*)\1)", ECMAScript);
g_regexTester.should_match("bc", R"((a)*b\1c)", ECMAScript);
g_regexTester.should_match("bc", R"((a*)b\1c)", ECMAScript);
}

int main() {
test_dev10_449367_case_insensitivity_should_work();
test_dev11_462743_regex_collate_should_not_disable_regex_icase();
Expand Down Expand Up @@ -1481,6 +1498,7 @@ int main() {
test_gh_5362();
test_gh_5364();
test_gh_5371();
test_gh_5374();

return g_regexTester.result();
}