[libc++] Mostly Implement P1885R12: <text_encoding>

libcxx/docs/FeatureTestMacroTable.rst

@@ -522,7 +522,7 @@ Status
     ---------------------------------------------------------- -----------------
     ``__cpp_lib_submdspan``                                    *unimplemented*
     ---------------------------------------------------------- -----------------
-    ``__cpp_lib_text_encoding``                                *unimplemented*
+    ``__cpp_lib_text_encoding``                                ``202306L``
     ---------------------------------------------------------- -----------------
     ``__cpp_lib_to_chars``                                     *unimplemented*
     ---------------------------------------------------------- -----------------

libcxx/docs/Status/Cxx2cPapers.csv

@@ -13,7 +13,7 @@
 "`P2013R5 <https://wg21.link/P2013R5>`__","Freestanding Language: Optional ``::operator new``","2023-06 (Varna)","","","`#105370 <https://github.com/llvm/llvm-project/issues/105370>`__",""
 "`P2363R5 <https://wg21.link/P2363R5>`__","Extending associative containers with the remaining heterogeneous overloads","2023-06 (Varna)","","","`#105371 <https://github.com/llvm/llvm-project/issues/105371>`__",""
 "`P1901R2 <https://wg21.link/P1901R2>`__","Enabling the Use of ``weak_ptr`` as Keys in Unordered Associative Containers","2023-06 (Varna)","","","`#105372 <https://github.com/llvm/llvm-project/issues/105372>`__",""
-"`P1885R12 <https://wg21.link/P1885R12>`__","Naming Text Encodings to Demystify Them","2023-06 (Varna)","","","`#105373 <https://github.com/llvm/llvm-project/issues/105373>`__",""
+"`P1885R12 <https://wg21.link/P1885R12>`__","Naming Text Encodings to Demystify Them","2023-06 (Varna)","|Partial|","22","`#105373 <https://github.com/llvm/llvm-project/issues/105373>`__",""
 "`P0792R14 <https://wg21.link/P0792R14>`__","``function_ref``: a type-erased callable reference","2023-06 (Varna)","","","`#105376 <https://github.com/llvm/llvm-project/issues/105376>`__",""
 "`P2874R2 <https://wg21.link/P2874R2>`__","P2874R2: Mandating Annex D Require No More","2023-06 (Varna)","|Complete|","12","`#105377 <https://github.com/llvm/llvm-project/issues/105377>`__",""
 "`P2757R3 <https://wg21.link/P2757R3>`__","Type-checking format args","2023-06 (Varna)","","","`#105378 <https://github.com/llvm/llvm-project/issues/105378>`__",""
@@ -79,7 +79,7 @@
 "`P3136R1 <https://wg21.link/P3136R1>`__","Retiring niebloids","2024-11 (Wrocław)","|Complete|","14","`#118133 <https://github.com/llvm/llvm-project/issues/118133>`__",""
 "`P3138R5 <https://wg21.link/P3138R5>`__","``views::cache_latest``","2024-11 (Wrocław)","","","`#118134 <https://github.com/llvm/llvm-project/issues/118134>`__",""
 "`P3379R0 <https://wg21.link/P3379R0>`__","Constrain ``std::expected`` equality operators","2024-11 (Wrocław)","|Complete|","21","`#118135 <https://github.com/llvm/llvm-project/issues/118135>`__",""
-"`P2862R1 <https://wg21.link/P2862R1>`__","``text_encoding::name()`` should never return null values","2024-11 (Wrocław)","","","`#118371 <https://github.com/llvm/llvm-project/issues/118371>`__",""
+"`P2862R1 <https://wg21.link/P2862R1>`__","``text_encoding::name()`` should never return null values","2024-11 (Wrocław)","|Complete|","22","`#118371 <https://github.com/llvm/llvm-project/issues/118371>`__",""
 "`P2897R7 <https://wg21.link/P2897R7>`__","``aligned_accessor``: An ``mdspan`` accessor expressing pointer over-alignment","2024-11 (Wrocław)","|Complete|","21","`#118372 <https://github.com/llvm/llvm-project/issues/118372>`__",""
 "`P3355R2 <https://wg21.link/P3355R2>`__","Fix ``submdspan`` for C++26","2024-11 (Wrocław)","","","`#118373 <https://github.com/llvm/llvm-project/issues/118373>`__",""
 "`P3222R0 <https://wg21.link/P3222R0>`__","Fix C++26 by adding transposed special cases for P2642 layouts","2024-11 (Wrocław)","","","`#118374 <https://github.com/llvm/llvm-project/issues/118374>`__",""

libcxx/include/CMakeLists.txt

@@ -768,6 +768,7 @@ set(files
   __system_error/error_condition.h
   __system_error/system_error.h
   __system_error/throw_system_error.h
+  __text_encoding/te_impl.h
   __thread/formatter.h
   __thread/id.h
   __thread/jthread.h
@@ -1078,6 +1079,7 @@ set(files
   strstream
   syncstream
   system_error
+  text_encoding
   tgmath.h
   thread
   tuple

libcxx/include/__configuration/availability.h

@@ -84,6 +84,9 @@
 // in all versions of the library are available.
 #if !_LIBCPP_HAS_VENDOR_AVAILABILITY_ANNOTATIONS
 
+#  define _LIBCPP_INTRODUCED_IN_LLVM_22 1
+#  define _LIBCPP_INTRODUCED_IN_LLVM_22_ATTRIBUTE /* nothing */
+
 #  define _LIBCPP_INTRODUCED_IN_LLVM_21 1
 #  define _LIBCPP_INTRODUCED_IN_LLVM_21_ATTRIBUTE /* nothing */
 
@@ -112,6 +115,10 @@
 
 // clang-format off
 
+// LLVM 22 
+#  define _LIBCPP_INTRODUCED_IN_LLVM_22 0
+#  define _LIBCPP_INTRODUCED_IN_LLVM_22_ATTRIBUTE __attribute__((unavailable))
+
 // LLVM 21
 // TODO: Fill this in
 #  define _LIBCPP_INTRODUCED_IN_LLVM_21 0
@@ -317,6 +324,10 @@
 #define _LIBCPP_AVAILABILITY_HAS_BAD_FUNCTION_CALL_GOOD_WHAT_MESSAGE _LIBCPP_INTRODUCED_IN_LLVM_21
 // No attribute, since we've had bad_function_call::what() in the headers before
 
+// Controls whether the internal implementation for text_encoding::environment() -> te_impl::__environment() is available
+#define _LIBCPP_AVAILABILITY_HAS_TE_ENVIRONMENT _LIBCPP_INTRODUCED_IN_LLVM_22
+#define _LIBCPP_AVAILABILITY_TE_ENVIRONMENT _LIBCPP_INTRODUCED_IN_LLVM_22_ATTRIBUTE
+
 // Define availability attributes that depend on both
 // _LIBCPP_HAS_EXCEPTIONS and _LIBCPP_HAS_RTTI.
 #if !_LIBCPP_HAS_EXCEPTIONS || !_LIBCPP_HAS_RTTI

libcxx/include/__locale_dir/locale_base_api.h

@@ -142,6 +142,7 @@
 #    include <__cstddef/size_t.h>
 #    include <__utility/forward.h>
 #    include <ctype.h>
+#    include <langinfo.h>
 #    include <string.h>
 #    include <time.h>
 #    if _LIBCPP_HAS_WIDE_CHARACTERS
@@ -160,6 +161,7 @@ namespace __locale {
 #    define _LIBCPP_MESSAGES_MASK LC_MESSAGES_MASK
 #    define _LIBCPP_ALL_MASK LC_ALL_MASK
 #    define _LIBCPP_LC_ALL LC_ALL
+#    define _LIBCPP_NL_CODESET CODESET
 
 using __locale_t _LIBCPP_NODEBUG = locale_t;
 
@@ -283,7 +285,12 @@ __mbsrtowcs(wchar_t* __dest, const char** __src, size_t __len, mbstate_t* __ps,
   return __libcpp_mbsrtowcs_l(__dest, __src, __len, __ps, __loc);
 }
 #      endif // _LIBCPP_HAS_WIDE_CHARACTERS
-#    endif   // _LIBCPP_BUILDING_LIBRARY
+
+inline _LIBCPP_HIDE_FROM_ABI const char* __nl_langinfo_l(decltype(_LIBCPP_NL_CODESET) __item, __locale_t __loc) {
+  return ::nl_langinfo_l(__item, __loc);
+}
+
+#    endif // _LIBCPP_BUILDING_LIBRARY
 
 _LIBCPP_DIAGNOSTIC_PUSH
 _LIBCPP_CLANG_DIAGNOSTIC_IGNORED("-Wgcc-compat")

libcxx/include/__locale_dir/support/bsd_like.h

@@ -15,6 +15,7 @@
 #include <__utility/forward.h>
 #include <clocale> // std::lconv
 #include <ctype.h>
+#include <langinfo.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -46,6 +47,7 @@ namespace __locale {
 #define _LIBCPP_MESSAGES_MASK LC_MESSAGES_MASK
 #define _LIBCPP_ALL_MASK LC_ALL_MASK
 #define _LIBCPP_LC_ALL LC_ALL
+#define _LIBCPP_NL_CODESET CODESET
 
 using __locale_t _LIBCPP_NODEBUG = ::locale_t;
 #if defined(_LIBCPP_BUILDING_LIBRARY)
@@ -193,7 +195,11 @@ __mbsrtowcs(wchar_t* __dest, const char** __src, size_t __len, mbstate_t* __ps,
   return ::mbsrtowcs_l(__dest, __src, __len, __ps, __loc);
 }
 #  endif // _LIBCPP_HAS_WIDE_CHARACTERS
-#endif   // _LIBCPP_BUILDING_LIBRARY
+
+inline _LIBCPP_HIDE_FROM_ABI const char* __nl_langinfo_l(decltype(_LIBCPP_NL_CODESET) __item, __locale_t __loc) {
+  return ::nl_langinfo_l(__item, __loc);
+}
+#endif // _LIBCPP_BUILDING_LIBRARY
 
 _LIBCPP_DIAGNOSTIC_PUSH
 _LIBCPP_CLANG_DIAGNOSTIC_IGNORED("-Wgcc-compat")

libcxx/include/__locale_dir/support/linux.h

@@ -17,6 +17,7 @@
 #include <cstdio>
 #include <cstdlib>
 #include <ctype.h>
+#include <langinfo.h>
 #include <stdarg.h>
 #include <string.h>
 #include <time.h>
@@ -57,6 +58,7 @@ struct __locale_guard {
 #define _LIBCPP_MESSAGES_MASK LC_MESSAGES_MASK
 #define _LIBCPP_ALL_MASK LC_ALL_MASK
 #define _LIBCPP_LC_ALL LC_ALL
+#define _LIBCPP_NL_CODESET CODESET
 
 using __locale_t _LIBCPP_NODEBUG = ::locale_t;
 
@@ -234,7 +236,14 @@ __mbsrtowcs(wchar_t* __dest, const char** __src, size_t __len, mbstate_t* __ps,
   return std::mbsrtowcs(__dest, __src, __len, __ps);
 }
 #  endif // _LIBCPP_HAS_WIDE_CHARACTERS
-#endif   // _LIBCPP_BUILDING_LIBRARY
+
+// TODO: Android has langinfo.h but not nl_langinfo_l
+#  ifndef __ANDROID__
+inline _LIBCPP_HIDE_FROM_ABI const char* __nl_langinfo_l(decltype(_LIBCPP_NL_CODESET) __item, __locale_t __loc) {
+  return ::nl_langinfo_l(__item, __loc);
+}
+#  endif
+#endif // _LIBCPP_BUILDING_LIBRARY
 
 #ifndef _LIBCPP_COMPILER_GCC // GCC complains that this can't be always_inline due to C-style varargs
 _LIBCPP_HIDE_FROM_ABI