xentara::utils::string::unicode Namespace Reference

Functions
constexpr auto	isHighSurrogate (char16_t codeUnit) noexcept -> bool
	Determines if a UTF-16 code unit is a high surrogate.
constexpr auto	isLowSurrogate (char16_t codeUnit) noexcept -> bool
	Determines if a UTF-16 code unit is a low surrogate.
constexpr auto	isSurrogate (char16_t codeUnit) noexcept -> bool
	Determines if a UTF-16 code unit is a high or low surrogate.
constexpr auto	combineSurrogates (char16_t high, char16_t low) noexcept -> char32_t
	Combines a high and a low surrogate into a single code point.
constexpr auto	makeSurrogatePair (char32_t codePoint) noexcept -> std::array< char16_t, 2 >
	Splits a code point into high and low surrogates.
constexpr auto	isBmp (char32_t codePoint) noexcept -> bool
	Determines if a code point lies in the basic multilingual plane.
constexpr auto	isOutOfRange (char32_t codePoint) noexcept -> bool
	Determines if a code point is outside the valid range for Unicode scalar values.
constexpr auto	isReserved (char32_t codeUnit) noexcept -> bool
	Determines if a UTF-32 code unit is reserved for a high or a low surrogate.
constexpr auto	isIllegal (char32_t codePoint) noexcept -> bool
	Determines if a code point is not a legal Unicode scalar value.
constexpr auto	replacementCharacter () noexcept -> char32_t
	Returns the replacement character.
constexpr auto	isSingleByteUtf8 (char32_t codePoint) noexcept -> bool
	Determines if a code point encodes to a single UTF-8 code unit.
constexpr auto	isTwoByteUtf8 (char32_t codePoint) noexcept -> bool
	Determines if a code point encodes to a sequence of two UTF-8 code units.
constexpr auto	isThreeByteUtf8 (char32_t codePoint) noexcept -> bool
	Determines if a code point encodes to a sequence of three UTF-8 code units.
constexpr auto	isFourByteUtf8 (char32_t codePoint) noexcept -> bool
	Determines if a code point encodes to a sequence of four UTF-8 code units.
constexpr auto	isTwoByteUtf8OrLess (char32_t codePoint) noexcept -> bool
	Determines if a code point encodes to a sequence of two UTF-8 code units or less.
constexpr auto	isThreeByteUtf8OrLess (char32_t codePoint) noexcept -> bool
	Determines if a code point encodes to a sequence of three UTF-8 code units or less.
constexpr auto	isFourByteUtf8OrLess (char32_t codePoint) noexcept -> bool
	Determines if a code point encodes to a sequence of four UTF-8 code units or less.
constexpr auto	utf8Size (char32_t codePoint) noexcept -> std::size_t
	Determines how many UTF-8 code units are needed to encode a code point.
constexpr auto	utf16Size (char32_t codePoint) noexcept -> std::size_t
	Determines how many UTF-16 code units are needed to encode a code point.

Function Documentation

combineSurrogates()

constexpr auto xentara::utils::string::unicode::combineSurrogates ( char16_t  high, char16_t  low  ) -> char32_t

constexprnoexcept

Combines a high and a low surrogate into a single code point.

Parameters

high	The high surrogate
low	The low surrogate

Returns

the combined code point

isBmp()

constexpr auto xentara::utils::string::unicode::isBmp ( char32_t  codePoint ) -> bool

constexprnoexcept

Determines if a code point lies in the basic multilingual plane.

The basic multilingual plane consists of all code points less than or equal to U+FFFF. These characters can be represented by a single UTF-16 code unit. Characters outside the basic multilingual plane must be split up into high and low surrogates.

Parameters

codePoint

The code point

Returns

true if the code unit is in the basic multilingual plane, and can thus be reporesented by a single UTF-16 code unit.

isFourByteUtf8()

constexpr auto xentara::utils::string::unicode::isFourByteUtf8 ( char32_t  codePoint ) -> bool

constexprnoexcept

Determines if a code point encodes to a sequence of four UTF-8 code units.

isFourByteUtf8OrLess()

constexpr auto xentara::utils::string::unicode::isFourByteUtf8OrLess ( char32_t  codePoint ) -> bool

constexprnoexcept

Determines if a code point encodes to a sequence of four UTF-8 code units or less.

This function can be used insead of isTwoByteUtf8() if it is already known that the code unit is not a three byte sequence or less, e.g. in chained if statements.

Note

No legal Unicode code point encodes to more than four characters, so this function is equivalent to !isOutOfRange().

isHighSurrogate()

constexpr auto xentara::utils::string::unicode::isHighSurrogate ( char16_t  codeUnit ) -> bool

constexprnoexcept

Determines if a UTF-16 code unit is a high surrogate.

Parameters

codeUnit

The code unit

Returns

true if the code unit is a high surrogate

isIllegal()

constexpr auto xentara::utils::string::unicode::isIllegal ( char32_t  codePoint ) -> bool

constexprnoexcept

Determines if a code point is not a legal Unicode scalar value.

Parameters

codePoint

The code point

Returns

true if the code point is a high or low surrogate, or if it is out of range

isLowSurrogate()

constexpr auto xentara::utils::string::unicode::isLowSurrogate ( char16_t  codeUnit ) -> bool

constexprnoexcept

Determines if a UTF-16 code unit is a low surrogate.

Parameters

codeUnit

The code unit

Returns

true if the code unit is a low surrogate

isOutOfRange()

constexpr auto xentara::utils::string::unicode::isOutOfRange ( char32_t  codePoint ) -> bool

constexprnoexcept

Determines if a code point is outside the valid range for Unicode scalar values.

Parameters

codePoint

The code point

Returns

true if the code point is out of range (i.e. greater than U+10FFFF)

isReserved()

constexpr auto xentara::utils::string::unicode::isReserved ( char32_t  codeUnit ) -> bool

constexprnoexcept

Determines if a UTF-32 code unit is reserved for a high or a low surrogate.

Parameters

codeUnit

The code unit

Returns

true if the code unit is a high surrogate or a low surrogate

isSingleByteUtf8()

constexpr auto xentara::utils::string::unicode::isSingleByteUtf8 ( char32_t  codePoint ) -> bool

constexprnoexcept

Determines if a code point encodes to a single UTF-8 code unit.

isSurrogate()

constexpr auto xentara::utils::string::unicode::isSurrogate ( char16_t  codeUnit ) -> bool

constexprnoexcept

Determines if a UTF-16 code unit is a high or low surrogate.

Parameters

codeUnit

The code unit

Returns

true if the code unit is a high surrogate or a low surrogate

isThreeByteUtf8()

constexpr auto xentara::utils::string::unicode::isThreeByteUtf8 ( char32_t  codePoint ) -> bool

constexprnoexcept

Determines if a code point encodes to a sequence of three UTF-8 code units.

isThreeByteUtf8OrLess()

constexpr auto xentara::utils::string::unicode::isThreeByteUtf8OrLess ( char32_t  codePoint ) -> bool

constexprnoexcept

Determines if a code point encodes to a sequence of three UTF-8 code units or less.

This function can be used insead of isTwoByteUtf8() if it is already known that the code unit is not a two byte sequence or less, e.g. in chained if statements.

isTwoByteUtf8()

constexpr auto xentara::utils::string::unicode::isTwoByteUtf8 ( char32_t  codePoint ) -> bool

constexprnoexcept

Determines if a code point encodes to a sequence of two UTF-8 code units.

isTwoByteUtf8OrLess()

constexpr auto xentara::utils::string::unicode::isTwoByteUtf8OrLess ( char32_t  codePoint ) -> bool

constexprnoexcept

Determines if a code point encodes to a sequence of two UTF-8 code units or less.

This function can be used insead of isTwoByteUtf8() if it is already known that the code unit is not a single byte sequence, e.g. in chained if statements.

makeSurrogatePair()

constexpr auto xentara::utils::string::unicode::makeSurrogatePair ( char32_t  codePoint ) -> std::array<char16_t, 2>

constexprnoexcept

Splits a code point into high and low surrogates.

Parameters

codePoint

The code point. Must be between U+10000 and U+10FFFF (supplementary planes).

Returns

The code point's high surrogate followed by the its low surrogate

replacementCharacter()

constexpr auto xentara::utils::string::unicode::replacementCharacter ( ) -> char32_t

constexprnoexcept

Returns the replacement character.

Returns

The Unicode replacement character (U+FFFD)

utf16Size()

constexpr auto xentara::utils::string::unicode::utf16Size ( char32_t  codePoint ) -> std::size_t

constexprnoexcept

Determines how many UTF-16 code units are needed to encode a code point.

Parameters

codePoint

The code point. Must be a legal Unicode scalar value (less than or equal to U+10FFFF, and not a surrogate).

Returns

the number of UTF-16 code units needed to represent the code point. The return value will always be 1 or 2, as all Unicode code points encode to either a single code unit, or a surrogate pair.

utf8Size()

constexpr auto xentara::utils::string::unicode::utf8Size ( char32_t  codePoint ) -> std::size_t

constexprnoexcept

Determines how many UTF-8 code units are needed to encode a code point.

Parameters

codePoint

The code point. Must be a legal Unicode scalar value (less than or equal to U+10FFFF, and not a surrogate).

Returns

the number of UTF-8 code units needed to represent the code point. The return value will always be between 1 and 4, as all Unicode code points encode to between one and four bytes.