[libc++] Fix handling of negated character classes in regex

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

git-svn-id: https://llvm.org/svn/llvm-project/libcxx/trunk@340609 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Louis Dionne
2018-08-24 14:10:28 +00:00
parent 39ad1d12c1
commit cd04d45e3a
3 changed files with 51 additions and 10 deletions

View File

@@ -2414,20 +2414,17 @@ __bracket_expression<_CharT, _Traits>::__exec(__state& __s) const
goto __exit; 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_)), // union(complement(union(__neg_chars_, __neg_mask_)),
// other cases...) // other cases...)
// //
// __neg_chars_ and __neg_mask_'d better be handled together, as there // It doesn't make sense to check this when there are no __neg_chars_
// are no short circuit opportunities. // and no __neg_mask_.
// if (!(__neg_mask_ == 0 && __neg_chars_.empty()))
// In addition, when __neg_mask_/__neg_chars_ is empty, they should be
// treated as all ones/all chars.
{ {
const bool __in_neg_mask = (__neg_mask_ == 0) || const bool __in_neg_mask = __traits_.isctype(__ch, __neg_mask_);
__traits_.isctype(__ch, __neg_mask_);
const bool __in_neg_chars = const bool __in_neg_chars =
__neg_chars_.empty() ||
std::find(__neg_chars_.begin(), __neg_chars_.end(), __ch) != std::find(__neg_chars_.begin(), __neg_chars_.end(), __ch) !=
__neg_chars_.end(); __neg_chars_.end();
if (!(__in_neg_mask || __in_neg_chars)) if (!(__in_neg_mask || __in_neg_chars))

View File

@@ -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]")));
}

View File

@@ -18,7 +18,7 @@
#include <regex> #include <regex>
#include <cassert> #include <cassert>
#include "test_macros.h"
// PR34310 // PR34310
int main() int main()