Fix regex bug with ^\W. Thanks to Tim Shen for the patch. Reviewed as https://reviews.llvm.org/D37955

git-svn-id: https://llvm.org/svn/llvm-project/libcxx/trunk@316095 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 47 insertions, 12 deletions

diff --git a/include/regex b/include/regex
index dfc97c58a..bd7201204 100644
--- a/include/regex
+++ b/include/regex
@@ -2409,17 +2409,28 @@ __bracket_expression<_CharT, _Traits>::__exec(__state& __s) const
                 goto __exit;
             }
         }
-        if (!__neg_chars_.empty())
+        // set of "__found" chars =
+        //   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.
         {
-            for (size_t __i = 0; __i < __neg_chars_.size(); ++__i)
-            {
-                if (__ch == __neg_chars_[__i])
-                    goto __is_neg_char;
-            }
+          const bool __in_neg_mask = (__neg_mask_ == 0) ||
+              __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))
+          {
             __found = true;
             goto __exit;
+          }
         }
-__is_neg_char:
         if (!__ranges_.empty())
         {
             string_type __s2 = __collate_ ?
@@ -2451,11 +2462,6 @@ __is_neg_char:
             __found = true;
             goto __exit;
         }
-        if (__neg_mask_ && !__traits_.isctype(__ch, __neg_mask_))
-        {
-            __found = true;
-            goto __exit;
-        }
     }
     else
         __found = __negate_;  // force reject
diff --git a/test/std/re/re.alg/re.alg.search/invert_neg_word_search.pass.cpp b/test/std/re/re.alg/re.alg.search/invert_neg_word_search.pass.cpp
new file mode 100644
index 000000000..dd17d3519
--- /dev/null
+++ b/test/std/re/re.alg/re.alg.search/invert_neg_word_search.pass.cpp
@@ -0,0 +1,29 @@
+//===----------------------------------------------------------------------===//
+//
+//                     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>
+
+// template <class BidirectionalIterator, class Allocator, class charT, class traits>
+//     bool
+//     regex_search(BidirectionalIterator first, BidirectionalIterator last,
+//                  match_results<BidirectionalIterator, Allocator>& m,
+//                  const basic_regex<charT, traits>& e,
+//                  regex_constants::match_flag_type flags = regex_constants::match_default);
+
+#include <regex>
+#include <cassert>
+#include "test_macros.h"
+
+// PR34310
+int main()
+{
+  assert(std::regex_search("HelloWorld", std::regex("[^\\W]")));
+  assert(std::regex_search("_", std::regex("[^\\W]")));
+  return 0;
+}