Use libcxx's default rune table with the Musl C library.

[vkalintiris]

Summary

Also, there are no exported character type tables from Musl so we have to
Fallback to the standard functions. This reduces the number of libcxx's
test-suite failures down to ~130 for MIPS. Most of the remaining failures
come from the atomics (due to the lack of 8-byte atomic-ops in MIPS32) and
thread tests.

[vkalintiris]

@dalias: Can you take a correctness-look at this patch?

include/__locale

411–415 ↗

(On Diff #40926)

Which typedef should we choose for mask?

[jroelofs]

LGTM

include/__locale

411–415 ↗

(On Diff #40926)

If you're using libcxx's table, you should use typedef unsigned long mask.

libcxx/trunk/include/__config

 
 // CloudABI is intended for running networked services. Processes do not
 // have standard input and output channels.
 #ifdef __CloudABI__
 #define _LIBCPP_HAS_NO_STDIN
 #define _LIBCPP_HAS_NO_STDOUT
 #endif
 
-#if defined(__ANDROID__) || defined(__CloudABI__)
+#if defined(__ANDROID__) || defined(__CloudABI__) || defined(_LIBCPP_HAS_MUSL_LIBC)
 #define _LIBCPP_PROVIDES_DEFAULT_RUNE_TABLE
 #endif
 
 // Thread-unsafe functions such as strtok(), mbtowc() and localtime()
 // are not available.
 #ifdef __CloudABI__
 #define _LIBCPP_HAS_NO_THREAD_UNSAFE_C_FUNCTIONS
 #endif

libcxx/trunk/include/__locale

#elif defined(_WIN32)
     static const mask xdigit = _HEX;
     static const mask blank  = _BLANK;
 # 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__) || defined(_LIBCPP_HAS_MUSL_LIBC)
+# 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;
#elif defined(_NEWLIB_VERSION)
     static const mask digit  = _N;
     static const mask punct  = _P;
     static const mask xdigit = _X | _N;
     static const mask blank  = _B;
 # define _LIBCPP_CTYPE_MASK_IS_COMPOSITE_PRINT
 # define _LIBCPP_CTYPE_MASK_IS_COMPOSITE_ALPHA
 # define _LIBCPP_CTYPE_MASK_IS_COMPOSITE_XDIGIT
 #else
-#if defined(_LIBCPP_HAS_MUSL_LIBC)
-    typedef unsigned short mask;
-#else
     typedef unsigned long mask;
-#endif
     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;

 
 #ifdef _CACHED_RUNES
     static const size_t table_size = _CACHED_RUNES;
 #else
     static const size_t table_size = 256;  // FIXME: Don't hardcode this.
 #endif
     _LIBCPP_ALWAYS_INLINE const mask* table() const  _NOEXCEPT {return __tab_;}
     static const mask* classic_table()  _NOEXCEPT;
-#if defined(__GLIBC__) || defined(__EMSCRIPTEN__) || defined(_LIBCPP_HAS_MUSL_LIBC)
+#if defined(__GLIBC__) || defined(__EMSCRIPTEN__)
     static const int* __classic_upper_table() _NOEXCEPT;
     static const int* __classic_lower_table() _NOEXCEPT;
 #endif
 #if defined(__NetBSD__)
     static const short* __classic_upper_table() _NOEXCEPT;
     static const short* __classic_lower_table() _NOEXCEPT;
 #endif
 

libcxx/trunk/src/locale.cpp

 }
 
 wchar_t
 ctype<wchar_t>::do_toupper(char_type c) const
 {
 #ifdef _LIBCPP_HAS_DEFAULTRUNELOCALE
     return isascii(c) ? _DefaultRuneLocale.__mapupper[c] : c;
 #elif defined(__GLIBC__) || defined(__EMSCRIPTEN__) || \
-      defined(__NetBSD__) || defined(_LIBCPP_HAS_MUSL_LIBC)
+      defined(__NetBSD__)
     return isascii(c) ? ctype<char>::__classic_upper_table()[c] : c;
 #else
     return (isascii(c) && iswlower_l(c, _LIBCPP_GET_C_LOCALE)) ? c-L'a'+L'A' : c;
 #endif
 }
 
 const wchar_t*
 ctype<wchar_t>::do_toupper(char_type* low, const char_type* high) const
 {
     for (; low != high; ++low)
 #ifdef _LIBCPP_HAS_DEFAULTRUNELOCALE
         *low = isascii(*low) ? _DefaultRuneLocale.__mapupper[*low] : *low;
 #elif defined(__GLIBC__) || defined(__EMSCRIPTEN__) || \
-      defined(__NetBSD__) || defined(_LIBCPP_HAS_MUSL_LIBC)
+      defined(__NetBSD__)
         *low = isascii(*low) ? ctype<char>::__classic_upper_table()[*low]
                              : *low;
 #else
         *low = (isascii(*low) && islower_l(*low, _LIBCPP_GET_C_LOCALE)) ? (*low-L'a'+L'A') : *low;
 #endif
     return low;
 }
 
 wchar_t
 ctype<wchar_t>::do_tolower(char_type c) const
 {
 #ifdef _LIBCPP_HAS_DEFAULTRUNELOCALE
     return isascii(c) ? _DefaultRuneLocale.__maplower[c] : c;
 #elif defined(__GLIBC__) || defined(__EMSCRIPTEN__) || \
-      defined(__NetBSD__) || defined(_LIBCPP_HAS_MUSL_LIBC)
+      defined(__NetBSD__)
     return isascii(c) ? ctype<char>::__classic_lower_table()[c] : c;
 #else
     return (isascii(c) && isupper_l(c, _LIBCPP_GET_C_LOCALE)) ? c-L'A'+'a' : c;
 #endif
 }
 
 const wchar_t*
 ctype<wchar_t>::do_tolower(char_type* low, const char_type* high) const
 {
     for (; low != high; ++low)
 #ifdef _LIBCPP_HAS_DEFAULTRUNELOCALE
         *low = isascii(*low) ? _DefaultRuneLocale.__maplower[*low] : *low;
 #elif defined(__GLIBC__) || defined(__EMSCRIPTEN__) || \
-      defined(__NetBSD__) || defined(_LIBCPP_HAS_MUSL_LIBC)
+      defined(__NetBSD__)
         *low = isascii(*low) ? ctype<char>::__classic_lower_table()[*low]
                              : *low;
 #else
         *low = (isascii(*low) && isupper_l(*low, _LIBCPP_GET_C_LOCALE)) ? *low-L'A'+L'a' : *low;
 #endif
     return low;
 }
 

 char
 ctype<char>::do_toupper(char_type c) const
 {
 #ifdef _LIBCPP_HAS_DEFAULTRUNELOCALE
     return isascii(c) ?
       static_cast<char>(_DefaultRuneLocale.__mapupper[static_cast<ptrdiff_t>(c)]) : c;
 #elif defined(__NetBSD__)
     return static_cast<char>(__classic_upper_table()[static_cast<unsigned char>(c)]);
-#elif defined(__GLIBC__) || defined(__EMSCRIPTEN__) || defined(_LIBCPP_HAS_MUSL_LIBC)
+#elif defined(__GLIBC__) || defined(__EMSCRIPTEN__)
     return isascii(c) ?
       static_cast<char>(__classic_upper_table()[static_cast<unsigned char>(c)]) : c;
 #else
     return (isascii(c) && islower_l(c, _LIBCPP_GET_C_LOCALE)) ? c-'a'+'A' : c;
 #endif
 }
 
 const char*
 ctype<char>::do_toupper(char_type* low, const char_type* high) const
 {
     for (; low != high; ++low)
 #ifdef _LIBCPP_HAS_DEFAULTRUNELOCALE
         *low = isascii(*low) ?
           static_cast<char>(_DefaultRuneLocale.__mapupper[static_cast<ptrdiff_t>(*low)]) : *low;
 #elif defined(__NetBSD__)
         *low = static_cast<char>(__classic_upper_table()[static_cast<unsigned char>(*low)]);
-#elif defined(__GLIBC__) || defined(__EMSCRIPTEN__) || defined(_LIBCPP_HAS_MUSL_LIBC)
+#elif defined(__GLIBC__) || defined(__EMSCRIPTEN__)
         *low = isascii(*low) ?
           static_cast<char>(__classic_upper_table()[static_cast<size_t>(*low)]) : *low;
 #else
         *low = (isascii(*low) && islower_l(*low, _LIBCPP_GET_C_LOCALE)) ? *low-'a'+'A' : *low;
 #endif
     return low;
 }
 
 char
 ctype<char>::do_tolower(char_type c) const
 {
 #ifdef _LIBCPP_HAS_DEFAULTRUNELOCALE
     return isascii(c) ?
       static_cast<char>(_DefaultRuneLocale.__maplower[static_cast<ptrdiff_t>(c)]) : c;
 #elif defined(__NetBSD__)
     return static_cast<char>(__classic_lower_table()[static_cast<unsigned char>(c)]);
-#elif defined(__GLIBC__) || defined(__EMSCRIPTEN__) || defined(_LIBCPP_HAS_MUSL_LIBC)
+#elif defined(__GLIBC__) || defined(__EMSCRIPTEN__)
     return isascii(c) ?
       static_cast<char>(__classic_lower_table()[static_cast<size_t>(c)]) : c;
 #else
     return (isascii(c) && isupper_l(c, _LIBCPP_GET_C_LOCALE)) ? c-'A'+'a' : c;
 #endif
 }
 
 const char*
 ctype<char>::do_tolower(char_type* low, const char_type* high) const
 {
     for (; low != high; ++low)
 #ifdef _LIBCPP_HAS_DEFAULTRUNELOCALE
         *low = isascii(*low) ? static_cast<char>(_DefaultRuneLocale.__maplower[static_cast<ptrdiff_t>(*low)]) : *low;
 #elif defined(__NetBSD__)
         *low = static_cast<char>(__classic_lower_table()[static_cast<unsigned char>(*low)]);
-#elif defined(__GLIBC__) || defined(__EMSCRIPTEN__) || defined(_LIBCPP_HAS_MUSL_LIBC)
+#elif defined(__GLIBC__) || defined(__EMSCRIPTEN__)
         *low = isascii(*low) ? static_cast<char>(__classic_lower_table()[static_cast<size_t>(*low)]) : *low;
 #else
         *low = (isascii(*low) && isupper_l(*low, _LIBCPP_GET_C_LOCALE)) ? *low-'A'+'a' : *low;
 #endif
     return low;
 }
 
 char
ctype<char>::do_narrow(const char_type* low, const char_type* high, char dfault, char* dest) const
     for (; low != high; ++low, ++dest)
         if (isascii(*low))
             *dest = *low;
         else
             *dest = dfault;
     return low;
 }
 
-#if defined(__EMSCRIPTEN__) || defined(_LIBCPP_HAS_MUSL_LIBC)
+#if defined(__EMSCRIPTEN__)
 extern "C" const unsigned short ** __ctype_b_loc();
 extern "C" const int ** __ctype_tolower_loc();
 extern "C" const int ** __ctype_toupper_loc();
 #endif
 
 #ifdef _LIBCPP_PROVIDES_DEFAULT_RUNE_TABLE
 const ctype<char>::mask*
 ctype<char>::classic_table()  _NOEXCEPT

 #elif defined(__GLIBC__)
     return _LIBCPP_GET_C_LOCALE->__ctype_b;
 #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__) || defined(_LIBCPP_HAS_MUSL_LIBC)
+#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;
 #else
     // Platform not supported: abort so the person doing the port knows what to

 }
 
 const short*
 ctype<char>::__classic_upper_table() _NOEXCEPT
 {
     return _C_toupper_tab_ + 1;
 }
 
-#elif defined(__EMSCRIPTEN__) || defined(_LIBCPP_HAS_MUSL_LIBC)
+#elif defined(__EMSCRIPTEN__)
 const int*
 ctype<char>::__classic_lower_table() _NOEXCEPT
 {
     return *__ctype_tolower_loc();
 }
 
 const int*
 ctype<char>::__classic_upper_table() _NOEXCEPT
 {
     return *__ctype_toupper_loc();
 }
-#endif // __GLIBC__ || __NETBSD__ || __EMSCRIPTEN__ || defined(_LIBCPP_HAS_MUSL_LIBC)
+#endif // __GLIBC__ || __NETBSD__ || __EMSCRIPTEN__
 
 // template <> class ctype_byname<char>
 
 ctype_byname<char>::ctype_byname(const char* name, size_t refs)
     : ctype<char>(0, false, refs),
       __l(newlocale(LC_ALL_MASK, name, 0))
 {
 #ifndef _LIBCPP_NO_EXCEPTIONS