[libcxx-commits] [libcxx] [libc++] Define an internal locale API as a shim on top of the current one (PR #114596)

[Louis Dionne via libcxx-commits]

================
@@ -35,71 +122,163 @@
 #  include <__locale_dir/locale_base_api/bsd_locale_fallbacks.h>
 #endif
 
-#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
-#  pragma GCC system_header
+#include <__cstddef/size_t.h>
+#include <__utility/forward.h>
+#include <ctype.h>
+#include <string.h>
+#include <time.h>
+#if _LIBCPP_HAS_WIDE_CHARACTERS
+#  include <wctype.h>
+#endif
+_LIBCPP_BEGIN_NAMESPACE_STD
+namespace __locale {
+//
+// Locale management
+//
+using __locale_t = locale_t;
+
+#ifndef _LIBCPP_MSVCRT_LIKE
+inline _LIBCPP_HIDE_FROM_ABI __locale_t __uselocale(__locale_t __loc) { return uselocale(__loc); }
+#endif
+
+inline _LIBCPP_HIDE_FROM_ABI __locale_t __newlocale(int __category_mask, const char* __name, __locale_t __loc) {
+  return newlocale(__category_mask, __name, __loc);
+}
+
+inline _LIBCPP_HIDE_FROM_ABI void __freelocale(__locale_t __loc) { freelocale(__loc); }
+
+inline _LIBCPP_HIDE_FROM_ABI lconv* __localeconv(__locale_t& __loc) { return __libcpp_localeconv_l(__loc); }
+
+//
+// Strtonum functions
+//
+inline _LIBCPP_HIDE_FROM_ABI float __strtof(const char* __nptr, char** __endptr, __locale_t __loc) {
+  return strtof_l(__nptr, __endptr, __loc);
+}
+
+inline _LIBCPP_HIDE_FROM_ABI double __strtod(const char* __nptr, char** __endptr, __locale_t __loc) {
+  return strtod_l(__nptr, __endptr, __loc);
+}
+
+inline _LIBCPP_HIDE_FROM_ABI long double __strtold(const char* __nptr, char** __endptr, __locale_t __loc) {
+  return strtold_l(__nptr, __endptr, __loc);
+}
+
+inline _LIBCPP_HIDE_FROM_ABI long long __strtoll(const char* __nptr, char** __endptr, int __base, __locale_t __loc) {
+  return strtoll_l(__nptr, __endptr, __base, __loc);
+}
+
+inline _LIBCPP_HIDE_FROM_ABI unsigned long long
+__strtoull(const char* __nptr, char** __endptr, int __base, __locale_t __loc) {
+  return strtoull_l(__nptr, __endptr, __base, __loc);
+}
+
+//
+// Character manipulation functions
+//
+inline _LIBCPP_HIDE_FROM_ABI int __islower(int __ch, __locale_t __loc) { return islower_l(__ch, __loc); }
+inline _LIBCPP_HIDE_FROM_ABI int __isupper(int __ch, __locale_t __loc) { return isupper_l(__ch, __loc); }
+inline _LIBCPP_HIDE_FROM_ABI int __isdigit(int __ch, __locale_t __loc) { return isdigit_l(__ch, __loc); }
+inline _LIBCPP_HIDE_FROM_ABI int __isxdigit(int __ch, __locale_t __loc) { return isxdigit_l(__ch, __loc); }
+inline _LIBCPP_HIDE_FROM_ABI int __strcoll(const char* __s1, const char* __s2, __locale_t __loc) {
+  return strcoll_l(__s1, __s2, __loc);
+}
+inline _LIBCPP_HIDE_FROM_ABI size_t __strxfrm(char* __dest, const char* __src, size_t __n, __locale_t __loc) {
+  return strxfrm_l(__dest, __src, __n, __loc);
+}
+inline _LIBCPP_HIDE_FROM_ABI int __toupper(int __ch, __locale_t __loc) { return toupper_l(__ch, __loc); }
+inline _LIBCPP_HIDE_FROM_ABI int __tolower(int __ch, __locale_t __loc) { return tolower_l(__ch, __loc); }
+
+#if _LIBCPP_HAS_WIDE_CHARACTERS
+inline _LIBCPP_HIDE_FROM_ABI int __wcscoll(const wchar_t* __s1, const wchar_t* __s2, __locale_t __loc) {
+  return wcscoll_l(__s1, __s2, __loc);
+}
+inline _LIBCPP_HIDE_FROM_ABI size_t __wcsxfrm(wchar_t* __dest, const wchar_t* __src, size_t __n, __locale_t __loc) {
+  return wcsxfrm_l(__dest, __src, __n, __loc);
+}
+inline _LIBCPP_HIDE_FROM_ABI int __iswspace(wint_t __ch, __locale_t __loc) { return iswspace_l(__ch, __loc); }
+inline _LIBCPP_HIDE_FROM_ABI int __iswprint(wint_t __ch, __locale_t __loc) { return iswprint_l(__ch, __loc); }
----------------
ldionne wrote:

Actually, I think it would be better if we tried to simplify this a bit. It looks like `_LIBCPP_WCTYPE_IS_MASK` and `iswupper_l` & friends were introduced in 0081892d335b22f2d3b0b92071f7e7fc9d0172ec. I don't fully understand what's the problem they were working around, but I *think* `iswctype_l` should do the same thing on all platforms that provide it (contrary to the commit message). So instead I'd be curious to try assuming that `iswctype_l` behaves like it does on FreeBSD and Apple, and see what happens in that case. That would allow us to remove many of these `__iswFOO` functions in one go, unconditionally. So, basically, I'd try reverting 0081892d335b22f2d3b0b92071f7e7fc9d0172ec and see what happens with the CI bots.

Alternatively, if that doesn't work out, we could potentially move from `iswctype_l` to `__iswFOO` on all platforms unconditionally.

TLDR I'd like to try simplifying this instead of adding even more complexity by tweaking the locale base API using configuration options, since it's already quite a mess.

https://github.com/llvm/llvm-project/pull/114596