utf8.h File Reference

#include <cctype>
#include <istream>
#include <ostream>
#include "fe/assert.h"

Include dependency graph for utf8.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes
struct	fe::utf8::Char32
	Wrapper for char32_t with an operator<< that writes UTF-8. More...

Namespaces
namespace	fe
namespace	fe::utf8
	UTF-8 helpers for decoding byte streams, encoding char32_t values, and running ASCII-style character classification on char32_t.

Functions
constexpr size_t	fe::utf8::num_bytes (char8_t c) noexcept
	Returns the expected number of bytes for an UTF-8 char sequence by inspecting the first byte.
constexpr char32_t	fe::utf8::append (char32_t c, char8_t b) noexcept
	Append b to c for converting UTF-8 to UTF-32.
constexpr char32_t	fe::utf8::first (char32_t c, char32_t num) noexcept
	Get relevant bits of first UTF-8 byte c of a multi-byte sequence consisting of num bytes.
constexpr char32_t	fe::utf8::min_code_point (size_t num) noexcept
	Minimum Unicode scalar value representable in an UTF-8 sequence of num bytes.
constexpr bool	fe::utf8::is_scalar_value (char32_t c) noexcept
	Is c a valid Unicode scalar value?
constexpr char8_t	fe::utf8::is_valid234 (char8_t c) noexcept
	Is the 2nd, 3rd, or 4th byte of an UTF-8 byte sequence valid?
char32_t	fe::utf8::decode (std::istream &is)
	Decodes the next UTF-8 sequence from is into a single char32_t.
bool	fe::utf8::encode (std::ostream &os, char32_t c32)
	Encodes c32 as UTF-8 and writes the resulting bytes to os.
Wrappers
Safe char32_t-style wrappers for <ctype> functions: Like all other functions from <cctype>, the behavior of std::isalnum is undefined if the argument's value is neither representable as unsigned char nor equal to EOF.
bool	fe::utf8::isalnum (char32_t c) noexcept
bool	fe::utf8::isalpha (char32_t c) noexcept
bool	fe::utf8::isblank (char32_t c) noexcept
bool	fe::utf8::iscntrl (char32_t c) noexcept
bool	fe::utf8::isdigit (char32_t c) noexcept
bool	fe::utf8::isgraph (char32_t c) noexcept
bool	fe::utf8::islower (char32_t c) noexcept
bool	fe::utf8::isprint (char32_t c) noexcept
bool	fe::utf8::ispunct (char32_t c) noexcept
bool	fe::utf8::isspace (char32_t c) noexcept
bool	fe::utf8::isupper (char32_t c) noexcept
bool	fe::utf8::isxdigit (char32_t c) noexcept
bool	fe::utf8::isascii (char32_t c) noexcept
char32_t	fe::utf8::tolower (char32_t c) noexcept
char32_t	fe::utf8::toupper (char32_t c) noexcept
constexpr bool	fe::utf8::isrange (char32_t c, char32_t begin, char32_t finis) noexcept
	Is c within [begin, finis]?
constexpr auto	fe::utf8::isrange (char32_t begin, char32_t finis) noexcept
constexpr bool	fe::utf8::isodigit (char32_t c) noexcept
	Is octal digit?
constexpr bool	fe::utf8::isbdigit (char32_t c) noexcept
	Is binary digit?
any
Build a predicate that checks whether a code point matches any of the given values.
bool	fe::utf8::_any (char32_t c, char32_t d)
template<class... T>
bool	fe::utf8::_any (char32_t c, char32_t d, T... args)
template<class... T>
auto	fe::utf8::any (T... args)

Variables
static constexpr size_t	fe::utf8::Max = 4
	Maximal number of char8_ts of an UTF-8 byte sequence.
static constexpr char32_t	fe::utf8::BOM = 0xfeff
	Byte Order Mark.
static constexpr char32_t	fe::utf8::EoF = (char32_t)std::istream::traits_type::eof()
	End of stream sentinel returned by decode.
static constexpr char32_t	fe::utf8::Null = 0
	U+0000 NULL returned unchanged by decode.
static constexpr char32_t	fe::utf8::Invalid = 0x110000
	Sentinel returned by decode for malformed UTF-8.