[libc++] Add an option to disable wide character support in libc++

Some embedded platforms do not wish to support the C library functionality
for handling wchar_t because they have no use for it. It makes sense for
libc++ to work properly on those platforms, so this commit adds a carve-out
of functionality for wchar_t.

Unfortunately, unlike some other carve-outs (e.g. random device), this
patch touches several parts of the library. However, despite the wide
impact of this patch, I still think it is important to support this
configuration since it makes it much simpler to port libc++ to some
embedded platforms.

Differential Revision: https://reviews.llvm.org/D111265

Author: ldionne

libcxx/CMakeLists.txt

@@ -120,6 +120,12 @@ option(LIBCXX_ENABLE_UNICODE
   "Whether to include support for Unicode in the library. Disabling Unicode can
    be useful when porting to platforms that don't support UTF-8 encoding (e.g.
    embedded)." ON)
+option(LIBCXX_ENABLE_WIDE_CHARACTERS
+  "Whether to include support for wide characters in the library. Disabling
+   wide character support can be useful when porting to platforms that don't
+   support the C functionality for wide characters. When wide characters are
+   not supported, several parts of the library will be disabled, notably the
+   wide character specializations of std::basic_string." ON)
 option(LIBCXX_ENABLE_VENDOR_AVAILABILITY_ANNOTATIONS
   "Whether to turn on vendor availability annotations on declarations that depend
    on definitions in a shared library. By default, we assume that we're not building
@@ -893,6 +899,7 @@ config_define_if_not(LIBCXX_ENABLE_FILESYSTEM _LIBCPP_HAS_NO_FILESYSTEM_LIBRARY)
 config_define_if_not(LIBCXX_ENABLE_RANDOM_DEVICE _LIBCPP_HAS_NO_RANDOM_DEVICE)
 config_define_if_not(LIBCXX_ENABLE_LOCALIZATION _LIBCPP_HAS_NO_LOCALIZATION)
 config_define_if_not(LIBCXX_ENABLE_UNICODE _LIBCPP_HAS_NO_UNICODE)
+config_define_if_not(LIBCXX_ENABLE_WIDE_CHARACTERS _LIBCPP_HAS_NO_WIDE_CHARACTERS)
 config_define_if_not(LIBCXX_ENABLE_VENDOR_AVAILABILITY_ANNOTATIONS _LIBCPP_HAS_NO_VENDOR_AVAILABILITY_ANNOTATIONS)
 # Incomplete features get their own specific disabling flags. This makes it
 # easier to grep for target specific flags once the feature is complete.

libcxx/cmake/caches/Generic-no-wide-characters.cmake

@@ -0,0 +1 @@
+set(LIBCXX_ENABLE_WIDE_CHARACTERS OFF CACHE BOOL "")

libcxx/docs/BuildingLibcxx.rst

@@ -251,6 +251,15 @@ libc++ specific options
    This option can be used to enable or disable the filesystem components on
    platforms that may not support them. For example on Windows when using MSVC.
 
+.. option:: LIBCXX_ENABLE_WIDE_CHARACTERS:BOOL
+
+   **Default**: ``ON``
+
+   This option can be used to disable support for ``wchar_t`` in the library. It also
+   allows the library to work on top of a C Standard Library that does not provide
+   support for ``wchar_t``. This is especially useful in embedded settings where
+   C Standard Libraries don't always provide all the usual bells and whistles.
+
 .. option:: LIBCXX_ENABLE_INCOMPLETE_FEATURES:BOOL
 
   **Default**: ``ON``

libcxx/docs/ReleaseNotes.rst

@@ -49,7 +49,9 @@ New Features
 API Changes
 -----------
 
-- ...
+- Support for building libc++ on top of a C Standard Library that does not support ``wchar_t`` was
+  added. This is useful for building libc++ in an embedded setting, and it adds itself to the various
+  freestanding-friendly options provided by libc++.
 
 Build System Changes
 --------------------

libcxx/include/CMakeLists.txt

@@ -211,6 +211,7 @@ set(files
   __iterator/wrap_iter.h
   __libcpp_version
   __locale
+  __mbstate_t.h
   __memory/addressof.h
   __memory/allocation_guard.h
   __memory/allocator_arg_t.h

libcxx/include/__algorithm/sort.h

@@ -463,7 +463,9 @@ __sort(_Tp** __first, _Tp** __last, __less<_Tp*>&)
 }
 
 _LIBCPP_EXTERN_TEMPLATE(_LIBCPP_FUNC_VIS void __sort<__less<char>&, char*>(char*, char*, __less<char>&))
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 _LIBCPP_EXTERN_TEMPLATE(_LIBCPP_FUNC_VIS void __sort<__less<wchar_t>&, wchar_t*>(wchar_t*, wchar_t*, __less<wchar_t>&))
+#endif
 _LIBCPP_EXTERN_TEMPLATE(_LIBCPP_FUNC_VIS void __sort<__less<signed char>&, signed char*>(signed char*, signed char*, __less<signed char>&))
 _LIBCPP_EXTERN_TEMPLATE(_LIBCPP_FUNC_VIS void __sort<__less<unsigned char>&, unsigned char*>(unsigned char*, unsigned char*, __less<unsigned char>&))
 _LIBCPP_EXTERN_TEMPLATE(_LIBCPP_FUNC_VIS void __sort<__less<short>&, short*>(short*, short*, __less<short>&))
@@ -479,7 +481,9 @@ _LIBCPP_EXTERN_TEMPLATE(_LIBCPP_FUNC_VIS void __sort<__less<double>&, double*>(d
 _LIBCPP_EXTERN_TEMPLATE(_LIBCPP_FUNC_VIS void __sort<__less<long double>&, long double*>(long double*, long double*, __less<long double>&))
 
 _LIBCPP_EXTERN_TEMPLATE(_LIBCPP_FUNC_VIS bool __insertion_sort_incomplete<__less<char>&, char*>(char*, char*, __less<char>&))
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 _LIBCPP_EXTERN_TEMPLATE(_LIBCPP_FUNC_VIS bool __insertion_sort_incomplete<__less<wchar_t>&, wchar_t*>(wchar_t*, wchar_t*, __less<wchar_t>&))
+#endif
 _LIBCPP_EXTERN_TEMPLATE(_LIBCPP_FUNC_VIS bool __insertion_sort_incomplete<__less<signed char>&, signed char*>(signed char*, signed char*, __less<signed char>&))
 _LIBCPP_EXTERN_TEMPLATE(_LIBCPP_FUNC_VIS bool __insertion_sort_incomplete<__less<unsigned char>&, unsigned char*>(unsigned char*, unsigned char*, __less<unsigned char>&))
 _LIBCPP_EXTERN_TEMPLATE(_LIBCPP_FUNC_VIS bool __insertion_sort_incomplete<__less<short>&, short*>(short*, short*, __less<short>&))

libcxx/include/__bsd_locale_fallbacks.h

@@ -30,6 +30,7 @@ decltype(MB_CUR_MAX) __libcpp_mb_cur_max_l(locale_t __l)
     return MB_CUR_MAX;
 }
 
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 inline _LIBCPP_INLINE_VISIBILITY
 wint_t __libcpp_btowc_l(int __c, locale_t __l)
 {
@@ -88,6 +89,7 @@ size_t __libcpp_mbrlen_l(const char *__s, size_t __n, mbstate_t *__ps, locale_t
     __libcpp_locale_guard __current(__l);
     return mbrlen(__s, __n, __ps);
 }
+#endif // _LIBCPP_HAS_NO_WIDE_CHARACTERS
 
 inline _LIBCPP_INLINE_VISIBILITY
 lconv *__libcpp_localeconv_l(locale_t __l)
@@ -96,13 +98,15 @@ lconv *__libcpp_localeconv_l(locale_t __l)
     return localeconv();
 }
 
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 inline _LIBCPP_INLINE_VISIBILITY
 size_t __libcpp_mbsrtowcs_l(wchar_t *__dest, const char **__src, size_t __len,
                      mbstate_t *__ps, locale_t __l)
 {
     __libcpp_locale_guard __current(__l);
     return mbsrtowcs(__dest, __src, __len, __ps);
 }
+#endif
 
 inline
 int __libcpp_snprintf_l(char *__s, size_t __n, locale_t __l, const char *__format, ...) {

libcxx/include/__config

@@ -1241,6 +1241,16 @@ extern "C" _LIBCPP_FUNC_VIS void __sanitizer_annotate_contiguous_container(
 #define _LIBCPP_PREFERRED_NAME(x)
 #endif
 
+// We often repeat things just for handling wide characters in the library.
+// When wide characters are disabled, it can be useful to have a quick way of
+// disabling it without having to resort to #if-#endif, which has a larger
+// impact on readability.
+#if defined(_LIBCPP_HAS_NO_WIDE_CHARACTERS)
+# define _LIBCPP_IF_WIDE_CHARACTERS(...)
+#else
+# define _LIBCPP_IF_WIDE_CHARACTERS(...) __VA_ARGS__
+#endif
+
 #if defined(_LIBCPP_ABI_MICROSOFT) && \
     (defined(_LIBCPP_COMPILER_MSVC) || __has_declspec_attribute(empty_bases))
 #  define _LIBCPP_DECLSPEC_EMPTY_BASES __declspec(empty_bases)

libcxx/include/__config_site.in

@@ -30,6 +30,7 @@
 #cmakedefine _LIBCPP_HAS_PARALLEL_ALGORITHMS
 #cmakedefine _LIBCPP_HAS_NO_RANDOM_DEVICE
 #cmakedefine _LIBCPP_HAS_NO_LOCALIZATION
+#cmakedefine _LIBCPP_HAS_NO_WIDE_CHARACTERS
 #cmakedefine _LIBCPP_HAS_NO_INCOMPLETE_FORMAT
 #cmakedefine _LIBCPP_HAS_NO_INCOMPLETE_RANGES
 

libcxx/include/__format/format_context.h

@@ -146,8 +146,9 @@ class _LIBCPP_TEMPLATE_VIS _LIBCPP_AVAILABILITY_FORMAT basic_format_context {
 // (such as a span<charT>) and polymorphic reallocation. - end note]
 
 using format_context = basic_format_context<back_insert_iterator<string>, char>;
-using wformat_context =
-    basic_format_context<back_insert_iterator<wstring>, wchar_t>;
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
+using wformat_context = basic_format_context<back_insert_iterator<wstring>, wchar_t>;
+#endif
 
 #endif // !defined(_LIBCPP_HAS_NO_CONCEPTS)
 

libcxx/include/__format/format_parse_context.h

@@ -96,7 +96,9 @@ class _LIBCPP_TEMPLATE_VIS _LIBCPP_AVAILABILITY_FORMAT basic_format_parse_contex
 };
 
 using format_parse_context = basic_format_parse_context<char>;
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 using wformat_parse_context = basic_format_parse_context<wchar_t>;
+#endif
 
 #endif // !defined(_LIBCPP_HAS_NO_CONCEPTS)
 

libcxx/include/__format/formatter_bool.h

@@ -85,11 +85,13 @@ struct _LIBCPP_TEMPLATE_VIS __bool_strings<char> {
   static constexpr string_view __false{"false"};
 };
 
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 template <>
 struct _LIBCPP_TEMPLATE_VIS __bool_strings<wchar_t> {
   static constexpr wstring_view __true{L"true"};
   static constexpr wstring_view __false{L"false"};
 };
+#endif
 
 template <class _CharT>
 using __formatter_bool = __formatter_integral<__parser_bool<_CharT>>;

libcxx/include/__format/formatter_char.h

@@ -78,6 +78,7 @@ template <>
 struct _LIBCPP_TEMPLATE_VIS _LIBCPP_AVAILABILITY_FORMAT formatter<char, char>
     : public __format_spec::__formatter_char<char> {};
 
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 template <>
 struct _LIBCPP_TEMPLATE_VIS _LIBCPP_AVAILABILITY_FORMAT formatter<char, wchar_t>
     : public __format_spec::__formatter_char<wchar_t> {
@@ -93,7 +94,7 @@ template <>
 struct _LIBCPP_TEMPLATE_VIS _LIBCPP_AVAILABILITY_FORMAT
     formatter<wchar_t, wchar_t>
     : public __format_spec::__formatter_char<wchar_t> {};
-
+#endif // _LIBCPP_HAS_NO_WIDE_CHARACTERS
 #endif // !defined(_LIBCPP_HAS_NO_CONCEPTS)
 
 #endif //_LIBCPP_STD_VER > 17

libcxx/include/__functional/hash.h

@@ -561,6 +561,7 @@ _LIBCPP_SUPPRESS_DEPRECATED_POP
 
 #endif // _LIBCPP_HAS_NO_UNICODE_CHARS
 
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 _LIBCPP_SUPPRESS_DEPRECATED_PUSH
 template <>
 struct _LIBCPP_TEMPLATE_VIS hash<wchar_t>
@@ -576,6 +577,7 @@ _LIBCPP_SUPPRESS_DEPRECATED_POP
     _LIBCPP_INLINE_VISIBILITY
     size_t operator()(wchar_t __v) const _NOEXCEPT {return static_cast<size_t>(__v);}
 };
+#endif // _LIBCPP_HAS_NO_WIDE_CHARACTERS
 
 _LIBCPP_SUPPRESS_DEPRECATED_PUSH
 template <>

libcxx/include/__locale

@@ -338,7 +338,9 @@ collate<_CharT>::do_hash(const char_type* __lo, const char_type* __hi) const
 }
 
 _LIBCPP_EXTERN_TEMPLATE_EVEN_IN_DEBUG_MODE(class _LIBCPP_EXTERN_TEMPLATE_TYPE_VIS collate<char>)
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 _LIBCPP_EXTERN_TEMPLATE_EVEN_IN_DEBUG_MODE(class _LIBCPP_EXTERN_TEMPLATE_TYPE_VIS collate<wchar_t>)
+#endif
 
 // template <class CharT> class collate_byname;
 
@@ -363,6 +365,7 @@ protected:
     virtual string_type do_transform(const char_type* __lo, const char_type* __hi) const;
 };
 
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 template <>
 class _LIBCPP_TYPE_VIS collate_byname<wchar_t>
     : public collate<wchar_t>
@@ -382,6 +385,7 @@ protected:
                            const char_type* __lo2, const char_type* __hi2) const;
     virtual string_type do_transform(const char_type* __lo, const char_type* __hi) const;
 };
+#endif
 
 template <class _CharT, class _Traits, class _Allocator>
 bool
@@ -516,6 +520,7 @@ public:
 
 template <class _CharT> class _LIBCPP_TEMPLATE_VIS ctype;
 
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 template <>
 class _LIBCPP_TYPE_VIS ctype<wchar_t>
     : public locale::facet,
@@ -617,6 +622,7 @@ protected:
     virtual char do_narrow(char_type, char __dfault) const;
     virtual const char_type* do_narrow(const char_type* __low, const char_type* __high, char __dfault, char* __dest) const;
 };
+#endif // _LIBCPP_HAS_NO_WIDE_CHARACTERS
 
 template <>
 class _LIBCPP_TYPE_VIS ctype<char>
@@ -761,6 +767,7 @@ protected:
     virtual const char_type* do_tolower(char_type* __low, const char_type* __high) const;
 };
 
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 template <>
 class _LIBCPP_TYPE_VIS ctype_byname<wchar_t>
     : public ctype<wchar_t>
@@ -786,6 +793,7 @@ protected:
     virtual char do_narrow(char_type, char __dfault) const;
     virtual const char_type* do_narrow(const char_type* __low, const char_type* __high, char __dfault, char* __dest) const;
 };
+#endif // _LIBCPP_HAS_NO_WIDE_CHARACTERS
 
 template <class _CharT>
 inline _LIBCPP_INLINE_VISIBILITY
@@ -992,6 +1000,7 @@ protected:
 
 // template <> class codecvt<wchar_t, char, mbstate_t>
 
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 template <>
 class _LIBCPP_TYPE_VIS codecvt<wchar_t, char, mbstate_t>
     : public locale::facet,
@@ -1072,6 +1081,7 @@ protected:
     virtual int do_length(state_type&, const extern_type* __frm, const extern_type* __end, size_t __mx) const;
     virtual int do_max_length() const  _NOEXCEPT;
 };
+#endif // _LIBCPP_HAS_NO_WIDE_CHARACTERS
 
 // template <> class codecvt<char16_t, char, mbstate_t> // deprecated in C++20
 
@@ -1450,7 +1460,9 @@ codecvt_byname<_InternT, _ExternT, _StateT>::~codecvt_byname()
 _LIBCPP_SUPPRESS_DEPRECATED_POP
 
 _LIBCPP_EXTERN_TEMPLATE_EVEN_IN_DEBUG_MODE(class _LIBCPP_EXTERN_TEMPLATE_TYPE_VIS codecvt_byname<char, char, mbstate_t>)
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 _LIBCPP_EXTERN_TEMPLATE_EVEN_IN_DEBUG_MODE(class _LIBCPP_EXTERN_TEMPLATE_TYPE_VIS codecvt_byname<wchar_t, char, mbstate_t>)
+#endif
 _LIBCPP_EXTERN_TEMPLATE_EVEN_IN_DEBUG_MODE(class _LIBCPP_DEPRECATED_IN_CXX20 _LIBCPP_EXTERN_TEMPLATE_TYPE_VIS codecvt_byname<char16_t, char, mbstate_t>) // deprecated in C++20
 _LIBCPP_EXTERN_TEMPLATE_EVEN_IN_DEBUG_MODE(class _LIBCPP_DEPRECATED_IN_CXX20 _LIBCPP_EXTERN_TEMPLATE_TYPE_VIS codecvt_byname<char32_t, char, mbstate_t>) // deprecated in C++20
 #ifndef _LIBCPP_HAS_NO_CHAR8_T
@@ -1681,6 +1693,7 @@ protected:
     string __grouping_;
 };
 
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 template <>
 class _LIBCPP_TYPE_VIS numpunct<wchar_t>
     : public locale::facet
@@ -1711,6 +1724,7 @@ protected:
     char_type __thousands_sep_;
     string __grouping_;
 };
+#endif // _LIBCPP_HAS_NO_WIDE_CHARACTERS
 
 // template <class charT> class numpunct_byname
 
@@ -1734,6 +1748,7 @@ private:
     void __init(const char*);
 };
 
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 template <>
 class _LIBCPP_TYPE_VIS numpunct_byname<wchar_t>
 : public numpunct<wchar_t>
@@ -1751,6 +1766,7 @@ protected:
 private:
     void __init(const char*);
 };
+#endif // _LIBCPP_HAS_NO_WIDE_CHARACTERS
 
 _LIBCPP_END_NAMESPACE_STD
 

libcxx/include/__mbstate_t.h

@@ -0,0 +1,44 @@
+// -*- C++ -*-
+//===----------------------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef _LIBCPP___MBSTATE_T_H
+#define _LIBCPP___MBSTATE_T_H
+
+#include <__config>
+
+#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
+#pragma GCC system_header
+#endif
+
+// TODO(ldionne):
+// The goal of this header is to provide mbstate_t without having to pull in
+// <wchar.h> or <uchar.h>. This is necessary because we need that type even
+// when we don't have (or try to provide) support for wchar_t, because several
+// types like std::fpos are defined in terms of mbstate_t.
+//
+// This is a gruesome hack, but I don't know how to make it cleaner for
+// the time being.
+
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
+#   include <wchar.h> // for mbstate_t
+#elif __has_include(<bits/types/mbstate_t.h>)
+#   include <bits/types/mbstate_t.h> // works on most Unixes
+#elif __has_include(<sys/_types/_mbstate_t.h>)
+#   include <sys/_types/_mbstate_t.h> // works on Darwin
+#else
+#   error "The library was configured without support for wide-characters, but we don't know how to get the definition of mbstate_t without <wchar.h> on your platform."
+#endif
+
+_LIBCPP_BEGIN_NAMESPACE_STD
+
+using ::mbstate_t _LIBCPP_USING_IF_EXISTS;
+
+_LIBCPP_END_NAMESPACE_STD
+
+#endif // _LIBCPP___MBSTATE_T_H

libcxx/include/__string

@@ -23,8 +23,12 @@
 #include <cstdio>      // for EOF
 #include <cstdint>     // for uint_least16_t
 #include <cstring>     // for memcpy
-#include <cwchar>      // for wmemcpy
 #include <type_traits> // for __libcpp_is_constant_evaluated
+#include <iosfwd>      // for streampos & friends
+
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
+#   include <cwchar> // for wmemcpy
+#endif
 
 #include <__debug>
 
@@ -423,6 +427,7 @@ char_traits<char>::find(const char_type* __s, size_t __n, const char_type& __a)
 
 // char_traits<wchar_t>
 
+#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 template <>
 struct _LIBCPP_TEMPLATE_VIS char_traits<wchar_t>
 {
@@ -539,6 +544,7 @@ char_traits<wchar_t>::find(const char_type* __s, size_t __n, const char_type& __
     return nullptr;
 #endif
 }
+#endif // _LIBCPP_HAS_NO_WIDE_CHARACTERS
 
 template <class _Traits>
 _LIBCPP_INLINE_VISIBILITY