From 7e87bc9c67c393c792a0e6bf82e84d9b00b4b169 Mon Sep 17 00:00:00 2001 From: Daniel Sanders Date: Wed, 17 Feb 2016 13:16:31 +0000 Subject: [PATCH] [libcxx] Fix definition of regex_traits::__regex_word on big-endian glibc systems Summary: On glibc, the bits used for the various character classes is endian dependant (see _ISbit() in ctypes.h) but __regex_word does not account for this and uses a spare bit that isn't spare on big-endian. On big-endian, it overlaps with the bit for graphic characters which causes '-', '@', etc. to be considered a word character. Fixed this by defining the value using _ISbit(15) on MIPS glibc systems. We've restricted this to MIPS for now to avoid the risk of introducing failures in other targets. Fixes PR26476. Reviewers: hans, mclow.lists Subscribers: dsanders, cfe-commits Differential Revision: http://reviews.llvm.org/D17132 git-svn-id: https://llvm.org/svn/llvm-project/libcxx/trunk@261088 91177308-0d34-0410-b5e6-96231b3b80d8 --- include/regex | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/include/regex b/include/regex index f1f3264d3..1139d8fb2 100644 --- a/include/regex +++ b/include/regex @@ -976,7 +976,12 @@ public: typedef locale locale_type; typedef ctype_base::mask char_class_type; +#if defined(__mips__) && defined(__GLIBC__) + static const char_class_type __regex_word = static_cast(_ISbit(15)); +#else static const char_class_type __regex_word = 0x80; +#endif + private: locale __loc_; const ctype* __ct_;