[libc++] Keep __regex_word in sync with ctype_base

[miyuki]

Summary

The class ctype_base in the header <locale> contains masks for
character classification functions, which are kept in sync with
platform's C library, hence it contains many special cases.
The value of the bit mask regex_word in the header <regex> must not
clash with those bit masks.

Currently the default case (i.e. unknown platform/C library) is
handled incorrectly: the __regex_word clashes with ctype_base::punct.

To avoid replicating the whole list of platforms in <regex> this patch
defines regex_word in <locale>, so that it is always kept in sync
with other masks.

[ldionne]

I looked at it and I don't think this is an ABI break. Because of the way __regex_word is used (it's never passed through an ABI boundary, instead we use "w". Also this doesn't impact Apple platforms, so I'm personally fine with it.

[atanasyan]

libcxx/trunk/include/__locale

412

This change breaks building on mips: https://bugs.llvm.org/show_bug.cgi?id=43011
Maybe this change fix the problem, but I'm not an expert in libc++:

static const mask __regex_word = static_cast<mask>(_ISbit(15));

[mclow.lists]

libcxx/trunk/include/__locale

412

Personally, I would lose the _ISbit call as well; just say 1 << 15 or 0x8000
We don't use _ISbit for the other constants, and we don't use it anywhere else in libc++.

[miyuki]

libcxx/trunk/include/__locale

412

_ISbit is endian-dependent, see https://reviews.llvm.org/D17132

libcxx/trunk/include/__locale

#if defined(__GLIBC__)
     static const mask cntrl  = _IScntrl;
     static const mask upper  = _ISupper;
     static const mask lower  = _ISlower;
     static const mask alpha  = _ISalpha;
     static const mask digit  = _ISdigit;
     static const mask punct  = _ISpunct;
     static const mask xdigit = _ISxdigit;
     static const mask blank  = _ISblank;
+#if defined(__mips__)
+    static const mask __regex_word = static_cast<char_class_type>(_ISbit(15));
+#else
+    static const mask __regex_word = 0x80;
+#endif
 #elif defined(_LIBCPP_MSVCRT_LIKE)
     typedef unsigned short mask;
     static const mask space  = _SPACE;
     static const mask print  = _BLANK|_PUNCT|_ALPHA|_DIGIT;
     static const mask cntrl  = _CONTROL;
     static const mask upper  = _UPPER;
     static const mask lower  = _LOWER;
     static const mask alpha  = _ALPHA;
     static const mask digit  = _DIGIT;
     static const mask punct  = _PUNCT;
     static const mask xdigit = _HEX;
     static const mask blank  = _BLANK;
+    static const mask __regex_word = 0x80;
 # define _LIBCPP_CTYPE_MASK_IS_COMPOSITE_PRINT
 #elif defined(__APPLE__) || defined(__FreeBSD__) || defined(__EMSCRIPTEN__) || defined(__NetBSD__)
 # ifdef __APPLE__
     typedef __uint32_t mask;
 # elif defined(__FreeBSD__)
     typedef unsigned long mask;
 # elif defined(__EMSCRIPTEN__) || defined(__NetBSD__)
     typedef unsigned short mask;
 # endif
     static const mask space  = _CTYPE_S;
     static const mask print  = _CTYPE_R;
     static const mask cntrl  = _CTYPE_C;
     static const mask upper  = _CTYPE_U;
     static const mask lower  = _CTYPE_L;
     static const mask alpha  = _CTYPE_A;
     static const mask digit  = _CTYPE_D;
     static const mask punct  = _CTYPE_P;
     static const mask xdigit = _CTYPE_X;
 
 # if defined(__NetBSD__)
     static const mask blank  = _CTYPE_BL;
+    // NetBSD defines classes up to 0x2000
+    // see sys/ctype_bits.h, _CTYPE_Q
+    static const mask __regex_word = 0x8000;
 # else
     static const mask blank  = _CTYPE_B;
+    static const mask __regex_word = 0x80;
 # endif
 #elif defined(__sun__) || defined(_AIX)
     typedef unsigned int mask;
     static const mask space  = _ISSPACE;
     static const mask print  = _ISPRINT;
     static const mask cntrl  = _ISCNTRL;
     static const mask upper  = _ISUPPER;
     static const mask lower  = _ISLOWER;
     static const mask alpha  = _ISALPHA;
     static const mask digit  = _ISDIGIT;
     static const mask punct  = _ISPUNCT;
     static const mask xdigit = _ISXDIGIT;
     static const mask blank  = _ISBLANK;
+    static const mask __regex_word = 0x80;
 #elif defined(_NEWLIB_VERSION)
     // Same type as Newlib's _ctype_ array in newlib/libc/include/ctype.h.
     typedef char mask;
     static const mask space  = _S;
     static const mask print  = _P | _U | _L | _N | _B;
     static const mask cntrl  = _C;
     static const mask upper  = _U;
     static const mask lower  = _L;
     static const mask alpha  = _U | _L;
     static const mask digit  = _N;
     static const mask punct  = _P;
     static const mask xdigit = _X | _N;
     static const mask blank  = _B;
+    static const mask __regex_word = 0x80;
 # define _LIBCPP_CTYPE_MASK_IS_COMPOSITE_PRINT
 # define _LIBCPP_CTYPE_MASK_IS_COMPOSITE_ALPHA
 # define _LIBCPP_CTYPE_MASK_IS_COMPOSITE_XDIGIT
 #else
     typedef unsigned long mask;
     static const mask space  = 1<<0;
     static const mask print  = 1<<1;
     static const mask cntrl  = 1<<2;
     static const mask upper  = 1<<3;
     static const mask lower  = 1<<4;
     static const mask alpha  = 1<<5;
     static const mask digit  = 1<<6;
     static const mask punct  = 1<<7;
     static const mask xdigit = 1<<8;
     static const mask blank  = 1<<9;
+    static const mask __regex_word = 1<<10;
 #endif
     static const mask alnum  = alpha | digit;
     static const mask graph  = alnum | punct;
 
     _LIBCPP_INLINE_VISIBILITY ctype_base() {}
 };
 
 template <class _CharT> class _LIBCPP_TEMPLATE_VIS ctype;

libcxx/trunk/include/regex

 struct _LIBCPP_TEMPLATE_VIS regex_traits
 {
 public:
     typedef _CharT                  char_type;
     typedef basic_string<char_type> string_type;
     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<char_class_type>(_ISbit(15));
-#elif defined(__NetBSD__)
-    // NetBSD defines classes up to 0x2000
-    // see sys/ctype_bits.h, _CTYPE_Q
-    static const char_class_type __regex_word = 0x8000;
-#else
-    static const char_class_type __regex_word = 0x80;
-#endif
-
+    static const char_class_type __regex_word = ctype_base::__regex_word;
 private:
     locale __loc_;
     const ctype<char_type>* __ct_;
     const collate<char_type>* __col_;
 
 public:
     regex_traits();