Skip to content

Commit

Permalink
[libc++] Fix handling of negated character classes in regex
Browse files Browse the repository at this point in the history
Summary:
This commit fixes a regression introduced in r316095, where we don't match
inverted character classes when there's no negated characrers in the []'s.

rdar://problem/43060054

Reviewers: mclow.lists, timshen, EricWF

Subscribers: christof, dexonsmith, cfe-commits

Differential Revision: https://reviews.llvm.org/D50534

llvm-svn: 340609
  • Loading branch information
ldionne committed Aug 24, 2018
1 parent 616ef18 commit 954d4a2
Show file tree
Hide file tree
Showing 3 changed files with 51 additions and 10 deletions.
15 changes: 6 additions & 9 deletions libcxx/include/regex
Original file line number Diff line number Diff line change
Expand Up @@ -2414,20 +2414,17 @@ __bracket_expression<_CharT, _Traits>::__exec(__state& __s) const
goto __exit;
}
}
// set of "__found" chars =
// When there's at least one of __neg_chars_ and __neg_mask_, the set
// of "__found" chars is
// union(complement(union(__neg_chars_, __neg_mask_)),
// other cases...)
//
// __neg_chars_ and __neg_mask_'d better be handled together, as there
// are no short circuit opportunities.
//
// In addition, when __neg_mask_/__neg_chars_ is empty, they should be
// treated as all ones/all chars.
// It doesn't make sense to check this when there are no __neg_chars_
// and no __neg_mask_.
if (!(__neg_mask_ == 0 && __neg_chars_.empty()))
{
const bool __in_neg_mask = (__neg_mask_ == 0) ||
__traits_.isctype(__ch, __neg_mask_);
const bool __in_neg_mask = __traits_.isctype(__ch, __neg_mask_);
const bool __in_neg_chars =
__neg_chars_.empty() ||
std::find(__neg_chars_.begin(), __neg_chars_.end(), __ch) !=
__neg_chars_.end();
if (!(__in_neg_mask || __in_neg_chars))
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,44 @@
//===----------------------------------------------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//

// <regex>
// UNSUPPORTED: c++98, c++03

// Make sure that we correctly match inverted character classes.

#include <cassert>
#include <regex>


int main() {
assert(std::regex_match("X", std::regex("[X]")));
assert(std::regex_match("X", std::regex("[XY]")));
assert(!std::regex_match("X", std::regex("[^X]")));
assert(!std::regex_match("X", std::regex("[^XY]")));

assert(std::regex_match("X", std::regex("[\\S]")));
assert(!std::regex_match("X", std::regex("[^\\S]")));

assert(!std::regex_match("X", std::regex("[\\s]")));
assert(std::regex_match("X", std::regex("[^\\s]")));

assert(std::regex_match("X", std::regex("[\\s\\S]")));
assert(std::regex_match("X", std::regex("[^Y\\s]")));
assert(!std::regex_match("X", std::regex("[^X\\s]")));

assert(std::regex_match("X", std::regex("[\\w]")));
assert(std::regex_match("_", std::regex("[\\w]")));
assert(!std::regex_match("X", std::regex("[^\\w]")));
assert(!std::regex_match("_", std::regex("[^\\w]")));

assert(!std::regex_match("X", std::regex("[\\W]")));
assert(!std::regex_match("_", std::regex("[\\W]")));
assert(std::regex_match("X", std::regex("[^\\W]")));
assert(std::regex_match("_", std::regex("[^\\W]")));
}
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@

#include <regex>
#include <cassert>
#include "test_macros.h"


// PR34310
int main()
Expand Down

0 comments on commit 954d4a2

Please sign in to comment.