diff mbox series

[2/4] : C++ P1423R3 char8_t remediation: Update feature test macro, add deleted operators, update u8path

Message ID 05f9b7ab-b89a-4348-e758-e7ef9077261a@honermann.net
State New
Headers show
Series : C++ P1423R3 char8_t remediation implementation | expand

Commit Message

Tom Honermann Sept. 15, 2019, 7:39 p.m. UTC 
This patch increments the __cpp_lib_char8_t feature test macro, adds 
deleted operator<< overloads for basic_ostream, and modifies u8path to 
accept sequences of char8_t for both the C++17 implementation of 
std::filesystem, and the filesystem TS implementation.

The implementation mechanism used for u8path differs between the C++17 
and filesystem TS implementations.  The changes to the former take 
advantage of C++17 'if constexpr'.  The changes to the latter retain 
C++11 compatibility and rely on tag dispatching.

libstdc++-v3/ChangeLog:

2019-09-15  Tom Honermann  <tom@honermann.net>

      * libstdc++-v3/include/bits/c++config: Bumped the value of the
        __cpp_lib_char8_t feature test macro.
      * libstdc++-v3/include/bits/fs_path.h (u8path): Modified u8path to
        accept sequences of char8_t.
      * libstdc++-v3/include/experimental/bits/fs_path.h (u8path):
        Modified u8path to accept sequences of char8_t.
      * libstdc++-v3/include/std/ostream: Added deleted overloads of
        wchar_t, char8_t, char16_t, and char32_t for ordinary and wide
        formatted character and string inserters.

Tom.

Comments

Tom Honermann Sept. 16, 2019, 2:33 a.m. UTC | #1 
A revised patch is attached that adds proper preprocessor conditionals 
around the deleted ostream inserters.  Apparently I had previously 
implemented a quick hack for testing purposes, neglected to add a FIXME 
comment, and then forgot about the hack.  Shame on me.

Tom.

On 9/15/19 3:39 PM, Tom Honermann wrote:
> This patch increments the __cpp_lib_char8_t feature test macro, adds 
> deleted operator<< overloads for basic_ostream, and modifies u8path to 
> accept sequences of char8_t for both the C++17 implementation of 
> std::filesystem, and the filesystem TS implementation.
> 
> The implementation mechanism used for u8path differs between the C++17 
> and filesystem TS implementations.  The changes to the former take 
> advantage of C++17 'if constexpr'.  The changes to the latter retain 
> C++11 compatibility and rely on tag dispatching.
> 
> libstdc++-v3/ChangeLog:
> 
> 2019-09-15  Tom Honermann  <tom@honermann.net>
> 
>       * libstdc++-v3/include/bits/c++config: Bumped the value of the
>         __cpp_lib_char8_t feature test macro.
>       * libstdc++-v3/include/bits/fs_path.h (u8path): Modified u8path to
>         accept sequences of char8_t.
>       * libstdc++-v3/include/experimental/bits/fs_path.h (u8path):
>         Modified u8path to accept sequences of char8_t.
>       * libstdc++-v3/include/std/ostream: Added deleted overloads of
>         wchar_t, char8_t, char16_t, and char32_t for ordinary and wide
>         formatted character and string inserters.
> 
> Tom.
diff mbox series

Patch

diff --git a/libstdc++-v3/include/bits/c++config b/libstdc++-v3/include/bits/c++config
index c8e099aaadd..5bcf32d95ef 100644
--- a/libstdc++-v3/include/bits/c++config
+++ b/libstdc++-v3/include/bits/c++config
@@ -620,7 +620,7 @@  namespace std
 # endif
 #endif
 #ifdef _GLIBCXX_USE_CHAR8_T
-# define __cpp_lib_char8_t 201811L
+# define __cpp_lib_char8_t 201907L
 #endif
 
 /* Define if __float128 is supported on this host. */
diff --git a/libstdc++-v3/include/bits/fs_path.h b/libstdc++-v3/include/bits/fs_path.h
index 71354515403..f3f539412fc 100644
--- a/libstdc++-v3/include/bits/fs_path.h
+++ b/libstdc++-v3/include/bits/fs_path.h
@@ -153,9 +153,24 @@  namespace __detail
 
   template<typename _Tp,
 	   typename _Iter = decltype(_S_range_begin(std::declval<_Tp>())),
-	   typename _Val = typename std::iterator_traits<_Iter>::value_type>
+	   typename _Val = typename std::iterator_traits<_Iter>::value_type,
+	   typename _UnqualVal = std::remove_const_t<_Val>>
     using __value_type_is_char
-      = std::enable_if_t<std::is_same_v<std::remove_const_t<_Val>, char>>;
+      = std::enable_if_t<std::is_same_v<_UnqualVal, char>,
+			 _UnqualVal>;
+
+  template<typename _Tp,
+	   typename _Iter = decltype(_S_range_begin(std::declval<_Tp>())),
+	   typename _Val = typename std::iterator_traits<_Iter>::value_type,
+	   typename _UnqualVal = std::remove_const_t<_Val>>
+    using __value_type_is_char_or_char8_t
+      = std::enable_if_t<__or_v<
+			   std::is_same<_UnqualVal, char>
+#ifdef _GLIBCXX_USE_CHAR8_T
+			   ,std::is_same<_UnqualVal, char8_t>
+#endif
+			   >,
+			 _UnqualVal>;
 
   // @} group filesystem-detail
 } // namespace __detail
@@ -639,29 +654,41 @@  namespace __detail
   /// Create a path from a UTF-8-encoded sequence of char
   template<typename _InputIterator,
 	   typename _Require = __detail::_Path<_InputIterator, _InputIterator>,
-	   typename _Require2 = __detail::__value_type_is_char<_InputIterator>>
+	   typename _CharT =
+	     __detail::__value_type_is_char_or_char8_t<_InputIterator>>
     inline path
     u8path(_InputIterator __first, _InputIterator __last)
     {
 #ifdef _GLIBCXX_FILESYSTEM_IS_WINDOWS
-      // XXX This assumes native wide encoding is UTF-16.
-      std::codecvt_utf8_utf16<path::value_type> __cvt;
-      path::string_type __tmp;
-      if constexpr (is_pointer_v<_InputIterator>)
+#ifdef _GLIBCXX_USE_CHAR8_T
+      if constexpr (is_same_v<_CharT, char8_t>)
 	{
-	  if (__str_codecvt_in_all(__first, __last, __tmp, __cvt))
-	    return path{ __tmp };
+	  return path{ __first, __last };
 	}
       else
 	{
-	  const std::string __u8str{__first, __last};
-	  const char* const __ptr = __u8str.data();
-	  if (__str_codecvt_in_all(__ptr, __ptr + __u8str.size(), __tmp, __cvt))
-	    return path{ __tmp };
+#endif
+	  // XXX This assumes native wide encoding is UTF-16.
+	  std::codecvt_utf8_utf16<path::value_type> __cvt;
+	  path::string_type __tmp;
+	  if constexpr (is_pointer_v<_InputIterator>)
+	    {
+	      if (__str_codecvt_in_all(__first, __last, __tmp, __cvt))
+		return path{ __tmp };
+	    }
+	  else
+	    {
+	      const std::string __u8str{__first, __last};
+	      const char* const __ptr = __u8str.data();
+	      if (__str_codecvt_in_all(__ptr, __ptr + __u8str.size(), __tmp, __cvt))
+		return path{ __tmp };
+	    }
+	  _GLIBCXX_THROW_OR_ABORT(filesystem_error(
+	      "Cannot convert character sequence",
+	      std::make_error_code(errc::illegal_byte_sequence)));
+#ifdef _GLIBCXX_USE_CHAR8_T
 	}
-      _GLIBCXX_THROW_OR_ABORT(filesystem_error(
-	    "Cannot convert character sequence",
-	    std::make_error_code(errc::illegal_byte_sequence)));
+#endif
 #else
       // This assumes native normal encoding is UTF-8.
       return path{ __first, __last };
@@ -671,21 +698,32 @@  namespace __detail
   /// Create a path from a UTF-8-encoded sequence of char
   template<typename _Source,
 	   typename _Require = __detail::_Path<_Source>,
-	   typename _Require2 = __detail::__value_type_is_char<_Source>>
+	   typename _CharT = __detail::__value_type_is_char_or_char8_t<_Source>>
     inline path
     u8path(const _Source& __source)
     {
 #ifdef _GLIBCXX_FILESYSTEM_IS_WINDOWS
-      if constexpr (is_convertible_v<const _Source&, std::string_view>)
+#ifdef _GLIBCXX_USE_CHAR8_T
+      if constexpr (is_same_v<_CharT, char8_t>)
 	{
-	  const std::string_view __s = __source;
-	  return filesystem::u8path(__s.data(), __s.data() + __s.size());
+	  return path{ __source };
 	}
       else
 	{
-	  std::string __s = path::_S_string_from_iter(__source);
-	  return filesystem::u8path(__s.data(), __s.data() + __s.size());
+#endif
+	  if constexpr (is_convertible_v<const _Source&, std::string_view>)
+	    {
+	      const std::string_view __s = __source;
+	      return filesystem::u8path(__s.data(), __s.data() + __s.size());
+	    }
+	  else
+	    {
+	      std::string __s = path::_S_string_from_iter(__source);
+	      return filesystem::u8path(__s.data(), __s.data() + __s.size());
+	    }
+#ifdef _GLIBCXX_USE_CHAR8_T
 	}
+#endif
 #else
       return path{ __source };
 #endif
diff --git a/libstdc++-v3/include/experimental/bits/fs_path.h b/libstdc++-v3/include/experimental/bits/fs_path.h
index 3f9a69514a1..7a8cd8d20de 100644
--- a/libstdc++-v3/include/experimental/bits/fs_path.h
+++ b/libstdc++-v3/include/experimental/bits/fs_path.h
@@ -169,10 +169,23 @@  namespace __detail
 
   template<typename _Tp,
 	   typename _Iter = decltype(_S_range_begin(std::declval<_Tp>())),
-	   typename _Val = typename std::iterator_traits<_Iter>::value_type>
+	   typename _Val = typename std::iterator_traits<_Iter>::value_type,
+	   typename _UnqualVal = typename std::remove_const<_Val>::type>
     using __value_type_is_char = typename std::enable_if<
-      std::is_same<typename std::remove_const<_Val>::type, char>::value
-      >::type;
+      std::is_same<_UnqualVal, char>::value,
+      _UnqualVal>::type;
+
+  template<typename _Tp,
+	   typename _Iter = decltype(_S_range_begin(std::declval<_Tp>())),
+	   typename _Val = typename std::iterator_traits<_Iter>::value_type,
+	   typename _UnqualVal = typename std::remove_const<_Val>::type>
+    using __value_type_is_char_or_char8_t = typename std::enable_if<
+      __or_<
+	std::is_same<_UnqualVal, char>
+#ifdef _GLIBCXX_USE_CHAR8_T
+	,std::is_same<_UnqualVal, char8_t>
+#endif
+      >::value, _UnqualVal>::type;
 
   // @} group filesystem-ts-detail
 } // namespace __detail
@@ -592,13 +605,11 @@  namespace __detail
     }
 
   /// Create a path from a UTF-8-encoded sequence of char
-  template<typename _InputIterator,
-	   typename _Require = __detail::_Path<_InputIterator, _InputIterator>,
-	   typename _Require2 = __detail::__value_type_is_char<_InputIterator>>
+#ifdef _GLIBCXX_FILESYSTEM_IS_WINDOWS
+  template<typename _InputIterator>
     inline path
-    u8path(_InputIterator __first, _InputIterator __last)
+    __u8path(_InputIterator __first, _InputIterator __last, char)
     {
-#ifdef _GLIBCXX_FILESYSTEM_IS_WINDOWS
       // XXX This assumes native wide encoding is UTF-16.
       std::codecvt_utf8_utf16<path::value_type> __cvt;
       path::string_type __tmp;
@@ -609,21 +620,61 @@  namespace __detail
       _GLIBCXX_THROW_OR_ABORT(filesystem_error(
 	    "Cannot convert character sequence",
 	    std::make_error_code(errc::illegal_byte_sequence)));
+    }
+
+#ifdef _GLIBCXX_USE_CHAR8_T
+  template<typename _InputIterator>
+    inline path
+    __u8path(_InputIterator __first, _InputIterator __last, char8_t)
+    {
+      return path{ __first, __last };
+    }
+#endif // _GLIBCXX_USE_CHAR8_T
+#endif // _GLIBCXX_FILESYSTEM_IS_WINDOWS
+
+  template<typename _InputIterator,
+	   typename _Require = __detail::_Path<_InputIterator, _InputIterator>,
+	   typename _CharT =
+	     __detail::__value_type_is_char_or_char8_t<_InputIterator>>
+    inline path
+    u8path(_InputIterator __first, _InputIterator __last)
+    {
+#ifdef _GLIBCXX_FILESYSTEM_IS_WINDOWS
+      return __u8path(__first, __last, _CharT{});
 #else
       return path{ __first, __last };
 #endif
     }
 
   /// Create a path from a UTF-8-encoded sequence of char
+#ifdef _GLIBCXX_FILESYSTEM_IS_WINDOWS
+  template<typename _Source>
+    inline path
+    __u8path(const _Source& __source, char)
+    {
+      std::string __s = path::_S_string_from_iter(__source);
+      return filesystem::u8path(__s.data(), __s.data() + __s.size());
+    }
+
+#ifdef _GLIBCXX_USE_CHAR8_T
+  template<typename _Source>
+    inline path
+    __u8path(const _Source& __source, char8_t)
+    {
+      return path{ __source };
+    }
+#endif // _GLIBCXX_USE_CHAR8_T
+#endif // _GLIBCXX_FILESYSTEM_IS_WINDOWS
+
   template<typename _Source,
 	   typename _Require = __detail::_Path<_Source>,
-	   typename _Require2 = __detail::__value_type_is_char<_Source>>
+	   typename _CharT =
+	     __detail::__value_type_is_char_or_char8_t<_Source>>
     inline path
     u8path(const _Source& __source)
     {
 #ifdef _GLIBCXX_FILESYSTEM_IS_WINDOWS
-      std::string __s = path::_S_string_from_iter(__source);
-      return filesystem::u8path(__s.data(), __s.data() + __s.size());
+      return __u8path(__source, _CharT{});
 #else
       return path{ __source };
 #endif
diff --git a/libstdc++-v3/include/std/ostream b/libstdc++-v3/include/std/ostream
index 2541d978886..94308d5de04 100644
--- a/libstdc++-v3/include/std/ostream
+++ b/libstdc++-v3/include/std/ostream
@@ -527,6 +527,39 @@  _GLIBCXX_BEGIN_NAMESPACE_VERSION
     inline basic_ostream<char, _Traits>&
     operator<<(basic_ostream<char, _Traits>& __out, unsigned char __c)
     { return (__out << static_cast<char>(__c)); }
+
+#ifdef _GLIBCXX_USE_CHAR8_T
+  // The following deleted overloads prevent formatting character values as
+  // numeric values.
+
+  template<class _Traits>
+    basic_ostream<char, _Traits>&
+    operator<<(basic_ostream<char, _Traits>&, wchar_t) = delete;
+
+  template<class _Traits>
+    basic_ostream<char, _Traits>&
+    operator<<(basic_ostream<char, _Traits>&, char8_t) = delete;
+
+  template<class _Traits>
+    basic_ostream<char, _Traits>&
+    operator<<(basic_ostream<char, _Traits>&, char16_t) = delete;
+
+  template<class _Traits>
+    basic_ostream<char, _Traits>&
+    operator<<(basic_ostream<char, _Traits>&, char32_t) = delete;
+
+  template<class _Traits>
+    basic_ostream<wchar_t, _Traits>&
+    operator<<(basic_ostream<wchar_t, _Traits>&, char8_t) = delete;
+
+  template<class _Traits>
+    basic_ostream<wchar_t, _Traits>&
+    operator<<(basic_ostream<wchar_t, _Traits>&, char16_t) = delete;
+
+  template<class _Traits>
+    basic_ostream<wchar_t, _Traits>&
+    operator<<(basic_ostream<wchar_t, _Traits>&, char32_t) = delete;
+#endif // _GLIBCXX_USE_CHAR8_T
   //@}
 
   //@{
@@ -582,6 +615,39 @@  _GLIBCXX_BEGIN_NAMESPACE_VERSION
     inline basic_ostream<char, _Traits> &
     operator<<(basic_ostream<char, _Traits>& __out, const unsigned char* __s)
     { return (__out << reinterpret_cast<const char*>(__s)); }
+
+#ifdef _GLIBCXX_USE_CHAR8_T
+   // The following deleted overloads prevent formatting strings as
+   // pointer values.
+
+  template<class _Traits>
+    basic_ostream<char, _Traits>&
+    operator<<(basic_ostream<char, _Traits>&, const wchar_t*) = delete;
+
+  template<class _Traits>
+    basic_ostream<char, _Traits>&
+    operator<<(basic_ostream<char, _Traits>&, const char8_t*) = delete;
+
+  template<class _Traits>
+    basic_ostream<char, _Traits>&
+    operator<<(basic_ostream<char, _Traits>&, const char16_t*) = delete;
+
+  template<class _Traits>
+    basic_ostream<char, _Traits>&
+    operator<<(basic_ostream<char, _Traits>&, const char32_t*) = delete;
+
+  template<class _Traits>
+    basic_ostream<wchar_t, _Traits>&
+    operator<<(basic_ostream<wchar_t, _Traits>&, const char8_t*) = delete;
+
+  template<class _Traits>
+    basic_ostream<wchar_t, _Traits>&
+    operator<<(basic_ostream<wchar_t, _Traits>&, const char16_t*) = delete;
+
+  template<class _Traits>
+    basic_ostream<wchar_t, _Traits>&
+    operator<<(basic_ostream<wchar_t, _Traits>&, const char32_t*) = delete;
+#endif // _GLIBCXX_USE_CHAR8_T
   //@}
 
   // Standard basic_ostream manipulators