Skip to content

<regex>: Repair character class escapes outside character class definitions #5160

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 3 commits into from
Dec 5, 2024
Merged

<regex>: Repair character class escapes outside character class definitions #5160

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
78a790d
`<regex>`: Repair character class escapes outside character class def…
muellerj2 Dec 2, 2024
84d631e
Fix U+03C7 GREEK SMALL LETTER CHI and update comments.
StephanTLavavej Dec 3, 2024
b3dfac4
Comment nitpicks.
StephanTLavavej Dec 3, 2024
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
17 changes: 12 additions & 5 deletions stl/inc/regex
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1710,7 +1710,7 @@ private:
bool _OctalDigits();
void _Do_ex_class(_Meta_type);
bool _CharacterClassEscape(bool);
_Prs_ret _ClassEscape(bool);
_Prs_ret _ClassEscape2();
_Prs_ret _ClassAtom();
void _ClassRanges();
void _CharacterClass();
Expand Down Expand Up @@ -4017,22 +4017,29 @@ bool _Parser<_FwdIt, _Elem, _RxTraits>::_CharacterClassEscape(bool _Addit) { //
return false;
}

const bool _Negated = _Traits.isctype(_Char, _RxTraits::_Ch_upper);
if (_Addit) {
_Nfa._Add_class();
// GH-992: Outside character class definitions, _Cls completely defines the character class
// so negating _Cls and negating the entire character class are equivalent.
// Since the former negation is defective, do the latter instead.
if (_Negated) {
_Nfa._Negate();
}
}

_Nfa._Add_named_class(_Cls, _Traits.isctype(_Char, _RxTraits::_Ch_upper));
_Nfa._Add_named_class(_Cls, _Negated && !_Addit);
_Next();
return true;
}

template <class _FwdIt, class _Elem, class _RxTraits>
_Prs_ret _Parser<_FwdIt, _Elem, _RxTraits>::_ClassEscape(bool _Addit) { // check for class escape
_Prs_ret _Parser<_FwdIt, _Elem, _RxTraits>::_ClassEscape2() { // check for class escape
if ((_L_flags & _L_esc_bsl) && _Char == _Esc_bsl) { // handle escape backslash if allowed
_Val = _Esc_bsl;
_Next();
return _Prs_chr;
} else if ((_L_flags & _L_esc_wsd) && _CharacterClassEscape(_Addit)) {
} else if ((_L_flags & _L_esc_wsd) && _CharacterClassEscape(false)) {
return _Prs_set;
} else if (_DecimalDigits(regex_constants::error_escape)) { // check for invalid value
if (_Val != 0) {
Expand All @@ -4049,7 +4056,7 @@ _Prs_ret _Parser<_FwdIt, _Elem, _RxTraits>::_ClassAtom() { // check for class at
if (_Mchar == _Meta_esc) { // check for valid escape sequence
_Next();
if (_L_flags & _L_grp_esc) {
return _ClassEscape(false);
return _ClassEscape2();
} else if ((_L_flags & _L_esc_ffn && _Do_ffn(_Char))
|| (_L_flags & _L_esc_ffnx && _Do_ffnx(_Char))) { // advance to next character
_Next();
Expand Down
11 changes: 11 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 @@ -629,6 +629,16 @@ void test_gh_5058() {
}
}

void test_gh_5160() {
// GH-5160 fixed mishandled negated character class escapes
// outside character class definitions
const test_wregex neg_regex(&g_regexTester, LR"(Y\S*Z)");
neg_regex.should_search_match(L"xxxYxx\x0078xxxZxxx", L"Yxx\x0078xxxZ"); // U+0078 LATIN SMALL LETTER X
neg_regex.should_search_match(L"xxxYxx\x03C7xxxZxxx", L"Yxx\x03C7xxxZ"); // U+03C7 GREEK SMALL LETTER CHI
neg_regex.should_search_fail(L"xxxYxx xxxZxxx");
neg_regex.should_search_fail(L"xxxYxx\x2009xxxZxxx"); // U+2009 THIN SPACE
}

int main() {
test_dev10_449367_case_insensitivity_should_work();
test_dev11_462743_regex_collate_should_not_disable_regex_icase();
Expand Down Expand Up @@ -657,6 +667,7 @@ int main() {
test_VSO_226914_word_boundaries();
test_gh_993();
test_gh_5058();
test_gh_5160();

return g_regexTester.result();
}