llvm-capstone/libcxx/include/print
Mark de Wever e2953303f4 [libc++][print] Adds stdout functions.
Implements parts of
- P2093R14 Formatted output
- P2539R4  Should the output of std::print to a terminal be
           synchronized with the underlying stream?

Depends on D150044

Reviewed By: #libc, ldionne

Differential Revision: https://reviews.llvm.org/D155262
2023-07-22 11:28:17 +02:00

390 lines
16 KiB
C++

// -*- 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_PRINT
#define _LIBCPP_PRINT
/*
namespace std {
// [print.fun], print functions
template<class... Args>
void print(format_string<Args...> fmt, Args&&... args);
template<class... Args>
void print(FILE* stream, format_string<Args...> fmt, Args&&... args);
template<class... Args>
void println(format_string<Args...> fmt, Args&&... args);
template<class... Args>
void println(FILE* stream, format_string<Args...> fmt, Args&&... args);
void vprint_unicode(string_view fmt, format_args args);
void vprint_unicode(FILE* stream, string_view fmt, format_args args);
void vprint_nonunicode(string_view fmt, format_args args);
void vprint_nonunicode(FILE* stream, string_view fmt, format_args args);
}
*/
#include <__assert> // all public C++ headers provide the assertion handler
#include <__concepts/same_as.h>
#include <__config>
#include <__format/buffer.h>
#include <__format/format_arg_store.h>
#include <__format/format_args.h>
#include <__format/format_context.h>
#include <__format/format_error.h>
#include <__format/format_functions.h>
#include <__format/unicode.h>
#include <__system_error/system_error.h>
#include <__utility/forward.h>
#include <cerrno>
#include <cstdio>
#include <string>
#include <string_view>
#include <version>
#if __has_include(<unistd.h>)
# include <unistd.h>
#endif
#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
# pragma GCC system_header
#endif
_LIBCPP_BEGIN_NAMESPACE_STD
#ifdef _WIN32
_LIBCPP_EXPORTED_FROM_ABI bool __is_windows_terminal(FILE* __stream);
# ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
// A wrapper for WriteConsoleW which is used to write to the Windows
// console. This function is in the dylib to avoid pulling in windows.h
// in the library headers. The function itself uses some private parts
// of the dylib too.
//
// The function does not depend on the language standard used. Guarding
// it with C++23 would fail since the dylib is currently built using C++20.
//
// Note the function is only implemented on the Windows platform.
_LIBCPP_EXPORTED_FROM_ABI void __write_to_windows_console(FILE* __stream, wstring_view __view);
# endif // _LIBCPP_HAS_NO_WIDE_CHARACTERS
#endif // _WIN32
#if _LIBCPP_STD_VER >= 23
# ifndef _LIBCPP_HAS_NO_UNICODE
// This is the code to transcode UTF-8 to UTF-16. This is used on
// Windows for the native Unicode API. The code is modeled to make it
// easier to extend to
//
// P2728R0 Unicode in the Library, Part 1: UTF Transcoding
//
// This paper is still under heavy development so it makes no sense yet
// to strictly follow the paper.
namespace __unicode {
// The names of these concepts are modelled after P2728R0, but the
// implementation is not. char16_t may contain 32-bits so depending on the
// number of bits is an issue.
# ifdef _LIBCPP_SHORT_WCHAR
template <class _Tp>
concept __utf16_code_unit =
same_as<_Tp, char16_t>
# ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
|| same_as<_Tp, wchar_t>
# endif
;
template <class _Tp>
concept __utf32_code_unit = same_as<_Tp, char32_t>;
# else // _LIBCPP_SHORT_WCHAR
template <class _Tp>
concept __utf16_code_unit = same_as<_Tp, char16_t>;
template <class _Tp>
concept __utf32_code_unit =
same_as<_Tp, char32_t>
# ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
|| same_as<_Tp, wchar_t>
# endif
;
# endif // _LIBCPP_SHORT_WCHAR
// Pass by reference since an output_iterator may not be copyable.
template <class _OutIt>
_LIBCPP_HIDE_FROM_ABI constexpr void __encode(_OutIt&, char32_t) = delete;
template <class _OutIt>
requires __utf16_code_unit<iter_value_t<_OutIt>>
_LIBCPP_HIDE_FROM_ABI constexpr void __encode(_OutIt& __out_it, char32_t __value) {
_LIBCPP_ASSERT_UNCATEGORIZED(__is_scalar_value(__value), "an invalid unicode scalar value results in invalid UTF-16");
if (__value < 0x10000) {
*__out_it++ = __value;
return;
}
__value -= 0x10000;
*__out_it++ = 0xd800 + (__value >> 10);
*__out_it++ = 0xdc00 + (__value & 0x3FF);
}
template <class _OutIt>
requires __utf32_code_unit<iter_value_t<_OutIt>>
_LIBCPP_HIDE_FROM_ABI constexpr void __encode(_OutIt& __out_it, char32_t __value) {
_LIBCPP_ASSERT_UNCATEGORIZED(__is_scalar_value(__value), "an invalid unicode scalar value results in invalid UTF-32");
*__out_it++ = __value;
}
template <class _OutIt, input_iterator _InIt>
requires output_iterator<_OutIt, const iter_value_t<_OutIt>&> && (!same_as<iter_value_t<_OutIt>, iter_value_t<_InIt>>)
_LIBCPP_HIDE_FROM_ABI constexpr _OutIt __transcode(_InIt __first, _InIt __last, _OutIt __out_it) {
// The __code_point_view has a basic_string_view interface.
// When transcoding becomes part of the standard we probably want to
// look at smarter algorithms.
// For example, when processing a code point that is encoded in
// 1 to 3 code units in UTF-8, the result will always be encoded
// in 1 code unit in UTF-16 (code points that require 4 code
// units in UTF-8 will require 2 code units in UTF-16).
//
// Note if P2728 is accepted types like int may become valid. In that case
// the __code_point_view should use a span. Libc++ will remove support for
// char_traits<int>.
// TODO PRINT Validate with clang-tidy
// NOLINTNEXTLINE(bugprone-dangling-handle)
basic_string_view<iter_value_t<_InIt>> __data{__first, __last};
__code_point_view<iter_value_t<_InIt>> __view{__data.begin(), __data.end()};
while (!__view.__at_end())
__unicode::__encode(__out_it, __view.__consume().__code_point);
return __out_it;
}
} // namespace __unicode
# endif // _LIBCPP_HAS_NO_UNICODE
namespace __print {
// [print.fun]/2
// Effects: If the ordinary literal encoding ([lex.charset]) is UTF-8, equivalent to:
// vprint_unicode(stream, fmt.str, make_format_args(args...));
// Otherwise, equivalent to:
// vprint_nonunicode(stream, fmt.str, make_format_args(args...));
//
// Based on the compiler and its compilation flags this value is or is
// not true. As mentioned in P2093R14 this only affects Windows. The
// test below could also be done for
// - GCC using __GNUC_EXECUTION_CHARSET_NAME
// https://gcc.gnu.org/onlinedocs/cpp/Common-Predefined-Macros.html
// - Clang using __clang_literal_encoding__
// https://clang.llvm.org/docs/LanguageExtensions.html#builtin-macros
// (note at the time of writing Clang is hard-coded to UTF-8.)
//
# ifdef _LIBCPP_HAS_NO_UNICODE
inline constexpr bool __use_unicode = false;
# elif defined(_MSVC_EXECUTION_CHARACTER_SET)
// This is the same test MSVC STL uses in their implementation of <print>
// See: https://learn.microsoft.com/en-us/windows/win32/intl/code-page-identifiers
inline constexpr bool __use_unicode = _MSVC_EXECUTION_CHARACTER_SET == 65001;
# else
inline constexpr bool __use_unicode = true;
# endif
_LIBCPP_HIDE_FROM_ABI inline bool __is_terminal(FILE* __stream) {
# ifdef _WIN32
return std::__is_windows_terminal(__stream);
# elif __has_include(<unistd.h>)
return isatty(fileno(__stream));
# else
# error "Provide a way to determine whether a FILE* is a terminal"
# endif
}
template <class = void> // TODO PRINT template or availability markup fires too eagerly (http://llvm.org/PR61563).
_LIBCPP_HIDE_FROM_ABI inline void
__vprint_nonunicode(FILE* __stream, string_view __fmt, format_args __args, bool __write_nl) {
_LIBCPP_ASSERT_UNCATEGORIZED(__stream, "__stream is a valid pointer to an output C stream");
string __str = std::vformat(__fmt, __args);
if (__write_nl)
__str.push_back('\n');
size_t __size = fwrite(__str.data(), 1, __str.size(), __stream);
if (__size < __str.size()) {
if (std::feof(__stream))
std::__throw_system_error(EIO, "EOF while writing the formatted output");
std::__throw_system_error(std::ferror(__stream), "failed to write formatted output");
}
}
# ifndef _LIBCPP_HAS_NO_UNICODE
// Note these helper functions are mainly used to aid testing.
// On POSIX systems and Windows the output is no longer considered a
// terminal when the output is redirected. Typically during testing the
// output is redirected to be able to capture it. This makes it hard to
// test this code path.
template <class = void> // TODO PRINT template or availability markup fires too eagerly (http://llvm.org/PR61563).
_LIBCPP_HIDE_FROM_ABI inline void
__vprint_unicode_posix(FILE* __stream, string_view __fmt, format_args __args, bool __write_nl, bool __is_terminal) {
// TODO PRINT Should flush errors throw too?
if (__is_terminal)
std::fflush(__stream);
__print::__vprint_nonunicode(__stream, __fmt, __args, __write_nl);
}
# ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
template <class = void> // TODO PRINT template or availability markup fires too eagerly (http://llvm.org/PR61563).
_LIBCPP_HIDE_FROM_ABI inline void
__vprint_unicode_windows(FILE* __stream, string_view __fmt, format_args __args, bool __write_nl, bool __is_terminal) {
if (!__is_terminal)
return __print::__vprint_nonunicode(__stream, __fmt, __args, __write_nl);
// TODO PRINT Should flush errors throw too?
std::fflush(__stream);
string __str = std::vformat(__fmt, __args);
// UTF-16 uses the same number or less code units than UTF-8.
// However the size of the code unit is 16 bits instead of 8 bits.
//
// The buffer uses the worst-case estimate and should never resize.
// However when the string is large this could lead to OOM. Using a
// smaller size might work, but since the buffer uses a grow factor
// the final size might be larger when the estimate is wrong.
//
// TODO PRINT profile and improve the speed of this code.
__format::__retarget_buffer<wchar_t> __buffer{__str.size()};
__unicode::__transcode(__str.begin(), __str.end(), __buffer.__make_output_iterator());
if (__write_nl)
__buffer.push_back(L'\n');
[[maybe_unused]] wstring_view __view = __buffer.__view();
// The macro _LIBCPP_TESTING_PRINT_WRITE_TO_WINDOWS_CONSOLE_FUNCTION is used to change
// the behavior in the test. This is not part of the public API.
# ifdef _LIBCPP_TESTING_PRINT_WRITE_TO_WINDOWS_CONSOLE_FUNCTION
_LIBCPP_TESTING_PRINT_WRITE_TO_WINDOWS_CONSOLE_FUNCTION(__stream, __view);
# elif defined(_WIN32)
std::__write_to_windows_console(__stream, __view);
# else
std::__throw_runtime_error("No defintion of _LIBCPP_TESTING_PRINT_WRITE_TO_WINDOWS_CONSOLE_FUNCTION and "
"__write_to_windows_console is not available.");
# endif
}
# endif // _LIBCPP_HAS_NO_WIDE_CHARACTERS
template <class = void> // TODO PRINT template or availability markup fires too eagerly (http://llvm.org/PR61563).
_LIBCPP_HIDE_FROM_ABI inline void
__vprint_unicode([[maybe_unused]] FILE* __stream,
[[maybe_unused]] string_view __fmt,
[[maybe_unused]] format_args __args,
[[maybe_unused]] bool __write_nl) {
_LIBCPP_ASSERT_UNCATEGORIZED(__stream, "__stream is a valid pointer to an output C stream");
// [print.fun]
// 7 - Effects: If stream refers to a terminal capable of displaying
// Unicode, writes out to the terminal using the native Unicode
// API; if out contains invalid code units, the behavior is
// undefined and implementations are encouraged to diagnose it.
// Otherwise writes out to stream unchanged. If the native
// Unicode API is used, the function flushes stream before
// writing out.
// 8 - Throws: Any exception thrown by the call to vformat
// ([format.err.report]). system_error if writing to the terminal
// or stream fails. May throw bad_alloc.
// 9 - Recommended practice: If invoking the native Unicode API
// requires transcoding, implementations should substitute
// invalid code units with U+FFFD replacement character per the
// Unicode Standard, Chapter 3.9 U+FFFD Substitution in
// Conversion.
// On non-Windows platforms the Unicode API is the normal file I/O API
// so there the call can be forwarded to the non_unicode API. On
// Windows there is a different API. This API requires transcoding.
# ifndef _WIN32
__print::__vprint_unicode_posix(__stream, __fmt, __args, __write_nl, __print::__is_terminal(__stream));
# elif !defined(_LIBCPP_HAS_NO_WIDE_CHARACTERS)
__print::__vprint_unicode_windows(__stream, __fmt, __args, __write_nl, __print::__is_terminal(__stream));
# else
# error "Windows builds with wchar_t disabled are not supported."
# endif
}
# endif // _LIBCPP_HAS_NO_UNICODE
} // namespace __print
template <class... _Args>
_LIBCPP_HIDE_FROM_ABI void print(FILE* __stream, format_string<_Args...> __fmt, _Args&&... __args) {
# ifndef _LIBCPP_HAS_NO_UNICODE
if constexpr (__print::__use_unicode)
__print::__vprint_unicode(__stream, __fmt.get(), std::make_format_args(__args...), false);
else
__print::__vprint_nonunicode(__stream, __fmt.get(), std::make_format_args(__args...), false);
# else // _LIBCPP_HAS_NO_UNICODE
__print::__vprint_nonunicode(__stream, __fmt.get(), std::make_format_args(__args...), false);
# endif // _LIBCPP_HAS_NO_UNICODE
}
template <class... _Args>
_LIBCPP_HIDE_FROM_ABI void print(format_string<_Args...> __fmt, _Args&&... __args) {
std::print(stdout, __fmt, std::forward<_Args>(__args)...);
}
template <class... _Args>
_LIBCPP_HIDE_FROM_ABI void println(FILE* __stream, format_string<_Args...> __fmt, _Args&&... __args) {
# ifndef _LIBCPP_HAS_NO_UNICODE
// Note the wording in the Standard is inefficient. The output of
// std::format is a std::string which is then copied. This solution
// just appends a newline at the end of the output.
if constexpr (__print::__use_unicode)
__print::__vprint_unicode(__stream, __fmt.get(), std::make_format_args(__args...), true);
else
__print::__vprint_nonunicode(__stream, __fmt.get(), std::make_format_args(__args...), true);
# else // _LIBCPP_HAS_NO_UNICODE
__print::__vprint_nonunicode(__stream, __fmt.get(), std::make_format_args(__args...), true);
# endif // _LIBCPP_HAS_NO_UNICODE
}
template <class... _Args>
_LIBCPP_HIDE_FROM_ABI void println(format_string<_Args...> __fmt, _Args&&... __args) {
std::println(stdout, __fmt, std::forward<_Args>(__args)...);
}
# ifndef _LIBCPP_HAS_NO_UNICODE
template <class = void> // TODO PRINT template or availability markup fires too eagerly (http://llvm.org/PR61563).
_LIBCPP_HIDE_FROM_ABI inline void vprint_unicode(FILE* __stream, string_view __fmt, format_args __args) {
__print::__vprint_unicode(__stream, __fmt, __args, false);
}
template <class = void> // TODO PRINT template or availability markup fires too eagerly (http://llvm.org/PR61563).
_LIBCPP_HIDE_FROM_ABI inline void vprint_unicode(string_view __fmt, format_args __args) {
std::vprint_unicode(stdout, __fmt, __args);
}
# endif // _LIBCPP_HAS_NO_UNICODE
template <class = void> // TODO PRINT template or availability markup fires too eagerly (http://llvm.org/PR61563).
_LIBCPP_HIDE_FROM_ABI inline void vprint_nonunicode(FILE* __stream, string_view __fmt, format_args __args) {
__print::__vprint_nonunicode(__stream, __fmt, __args, false);
}
template <class = void> // TODO PRINT template or availability markup fires too eagerly (http://llvm.org/PR61563).
_LIBCPP_HIDE_FROM_ABI inline void vprint_nonunicode(string_view __fmt, format_args __args) {
std::vprint_nonunicode(stdout, __fmt, __args);
}
#endif // _LIBCPP_STD_VER >= 23
_LIBCPP_END_NAMESPACE_STD
#endif // _LIBCPP_PRINT