utf8.hpp File Reference

#include <join/utils.hpp>
#include <algorithm>
#include <cstring>
#include <cstddef>
#include <cstdint>

Include dependency graph for utf8.hpp:

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

Go to the source code of this file.

Classes
struct	join::utf8::details::SequenceTable
	UTF-8 well-formed multibyte sequences indexed by lead byte. More...
struct	join::utf8::details::OrderTable
	rank of UTF-8 bytes in UTF-16 code unit order. More...

Namespaces
namespace	join
namespace	join::utf8
namespace	join::utf8::details

Functions
uint32_t	join::utf8::details::sequenceLength (const uint8_t *cur, const uint8_t *end) noexcept
	get the length of a multibyte sequence.
int	join::utf8::details::validateMixed (const uint8_t *cur, const uint8_t *end) noexcept
	validate UTF-8 input that may contain multibyte sequences.
int	join::utf8::decode (const char *&cur, const char *end, uint32_t &codepoint) noexcept
	decode one codepoint from UTF-8.
size_t	join::utf8::encode (uint32_t codepoint, char *out) noexcept
	encode one codepoint to UTF-8.
int	join::utf8::validate (const char *first, const char *last) noexcept
	validate UTF-8 input.
int	join::utf8::compareUtf16Order (const char *first1, const char *last1, const char *first2, const char *last2) noexcept
	compare two UTF-8 inputs in UTF-16 code unit order.

Variables
constexpr SequenceTable	join::utf8::details::sequenceLookup {}
	UTF-8 multibyte sequences lookup table.
constexpr OrderTable	join::utf8::details::orderLookup {}
	UTF-16 code unit order lookup table.
constexpr uint64_t	join::utf8::details::highBits = 0x8080808080808080ULL
	mask of the high bit of each byte of a 64 bits word.