libc++: support newlib's ctype

[jfb]

Summary

Newlib supports ctype differently from other platforms, this patch teaches libc++ about yet another platform that does ctype differently.

[jfb]

@jroelofs points out this bug that @danalbert filed:
http://llvm.org/bugs/show_bug.cgi?id=21506

Should I wait for this mythical classic_table, or go ahead with more ctype stew?

[jroelofs]

LGTM for now.

The "right" fix is something like this: http://lists.cs.uiuc.edu/pipermail/cfe-commits/Week-of-Mon-20141208/119787.html

include/__locale

#elif defined(_WIN32)
     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;
 #elif defined(__APPLE__) || defined(__FreeBSD__) || defined(__EMSCRIPTEN__) || defined(__NetBSD__) || defined(__ANDROID__)
-#ifdef __APPLE__
+# ifdef __APPLE__
     typedef __uint32_t mask;
-#elif defined(__FreeBSD__)
+# elif defined(__FreeBSD__)
     typedef unsigned long mask;
-#elif defined(__EMSCRIPTEN__) ||  defined(__NetBSD__)
+# elif defined(__EMSCRIPTEN__) ||  defined(__NetBSD__)
     typedef unsigned short mask;
-#elif defined(__ANDROID__)
+# elif defined(__ANDROID__)
     typedef unsigned char mask;
-#endif
+# 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;
#elif defined(__sun__) || defined(_AIX)
     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;
-#else  // __GLIBC__ || _WIN32 || __APPLE__ || __FreeBSD__ || __EMSCRIPTEN__ || __sun__
+#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;
+#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;
-#endif  // __GLIBC__ || _WIN32 || __APPLE__ || __FreeBSD__
+#endif
     static const mask alnum  = alpha | digit;
     static const mask graph  = alnum | punct;
 
     _LIBCPP_ALWAYS_INLINE ctype_base() {}
 };
 
 template <class _CharT> class _LIBCPP_TYPE_VIS_ONLY ctype;
 

src/locale.cpp

 #elif __sun__
     return __ctype_mask;
 #elif defined(_LIBCPP_MSVCRT) || defined(__MINGW32__)
     return _ctype+1; // internal ctype mask table defined in msvcrt.dll
 // This is assumed to be safe, which is a nonsense assumption because we're
 // going to end up dereferencing it later...
 #elif defined(__EMSCRIPTEN__)
     return *__ctype_b_loc();
+#elif defined(_NEWLIB_VERSION)
+    // Newlib has a 257-entry table in ctype_.c, where (char)0 starts at [1].
+    return _ctype_ + 1;
 #elif defined(_AIX)
     return (const unsigned int *)__lc_ctype_ptr->obj->mask;
 #elif defined(__ANDROID__)
     return reinterpret_cast<const unsigned char*>(_ctype_) + 1;
 #else
     // Platform not supported: abort so the person doing the port knows what to
     // fix
 # warning  ctype<char>::classic_table() is not implemented