Represents a single textual unit with Unicode and linguistic properties. More...

#include <rune.hpp>

Public Member Functions
constexpr	Rune () noexcept
	Default constructor (creates null character)
constexpr	Rune (char32_t codepoint) noexcept
	Construct a Rune from a Unicode codepoint.
constexpr	Rune (char32_t codepoint, language::Code lang) noexcept
	Construct a Rune with explicit language information.
	Rune (char32_t codepoint, language::Code lang, std::string phoneme)
	Construct a Rune with phonetic representation.
constexpr	Rune (const Rune &)=default
constexpr	Rune (Rune &&) noexcept=default
constexpr Rune &	operator= (const Rune &)=default
constexpr Rune &	operator= (Rune &&) noexcept=default
	~Rune ()=default
constexpr char32_t	codepoint () const noexcept
	Get the Unicode codepoint.
constexpr language::Code	language () const noexcept
	Get the language code.
constexpr unicode::Category	category () const noexcept
	Get the Unicode category.
constexpr unicode::Script	script () const noexcept
	Get the Unicode script.
const std::string &	phoneme () const noexcept
	Get the phonetic representation.
constexpr void	set_language (language::Code lang) noexcept
	Set the language code.
void	set_phoneme (std::string phoneme)
	Set the phonetic representation.
constexpr bool	is_vowel () const noexcept
	Check if this rune represents a vowel.
constexpr bool	is_consonant () const noexcept
	Check if this rune represents a consonant.
constexpr bool	is_letter () const noexcept
	Check if this rune is a letter.
constexpr bool	is_digit () const noexcept
	Check if this rune is a digit.
constexpr bool	is_whitespace () const noexcept
	Check if this rune is whitespace.
constexpr bool	is_punctuation () const noexcept
	Check if this rune is punctuation.
constexpr bool	is_ascii () const noexcept
	Check if this is an ASCII character.
constexpr bool	is_latin () const noexcept
	Check if this is a Latin script character.
constexpr bool	is_hangul () const noexcept
	Check if this is a Hangul (Korean) character.
constexpr bool	is_hiragana () const noexcept
	Check if this is a Hiragana character.
constexpr bool	is_katakana () const noexcept
	Check if this is a Katakana character.
constexpr bool	is_kanji () const noexcept
	Check if this is a Kanji character.
constexpr bool	is_emoji () const noexcept
	Check if this is an emoji character.
std::string	to_utf8 () const
	Convert to UTF-8 string.
std::u16string	to_utf16 () const
	Convert to UTF-16 string.
constexpr std::u32string	to_utf32 () const
	Convert to UTF-32 string.
constexpr auto	operator<=> (const Rune &other) const noexcept=default
	Three-way comparison operator (C++20)
constexpr bool	operator== (const Rune &other) const noexcept=default
	Equality comparison.

Static Public Member Functions
static Rune	from_utf8 (std::string_view utf8_char)
	Create a Rune from a UTF-8 character.
static Rune	from_utf8 (std::string_view utf8_char, language::Code lang)
	Create a Rune from a UTF-8 character with language hint.
static Rune	from_utf16 (std::u16string_view utf16_char)
	Create a Rune from a UTF-16 character.

Detailed Description

Represents a single textual unit with Unicode and linguistic properties.

The Rune class encapsulates a Unicode codepoint along with its linguistic attributes such as language, category, and phonetic representation. It serves as the fundamental building block for text processing in the rune-caster framework.

C++20 Enhanced: Supports constexpr operations, comprehensive language detection, and modern C++ features for optimal performance.

Definition at line 23 of file rune.hpp.

Constructor & Destructor Documentation

◆ Rune() [1/6]

rune_caster::Rune::Rune ( )

inlineconstexprnoexcept

Default constructor (creates null character)

Definition at line 274 of file rune.hpp.

◆ Rune() [2/6]

rune_caster::Rune::Rune ( char32_t codepoint )

inlineexplicitconstexprnoexcept

Construct a Rune from a Unicode codepoint.

Parameters

codepoint The Unicode codepoint

Definition at line 275 of file rune.hpp.

◆ Rune() [3/6]

rune_caster::Rune::Rune	(	char32_t	codepoint,
		language::Code	lang )

inlineconstexprnoexcept

Construct a Rune with explicit language information.

Parameters

codepoint	The Unicode codepoint
language	The language code

Definition at line 276 of file rune.hpp.

◆ Rune() [4/6]

rune_caster::Rune::Rune	(	char32_t	codepoint,
		language::Code	lang,
		std::string	phoneme )

Construct a Rune with phonetic representation.

Parameters

codepoint	The Unicode codepoint
language	The language code
phoneme	The phonetic representation

Definition at line 10 of file rune.cpp.

◆ Rune() [5/6]

rune_caster::Rune::Rune ( const Rune & )

constexprdefault

◆ Rune() [6/6]

rune_caster::Rune::Rune ( Rune && )

constexprdefaultnoexcept

◆ ~Rune()

rune_caster::Rune::~Rune ( )

default

Member Function Documentation

◆ category()

unicode::Category rune_caster::Rune::category ( ) const

nodiscardconstexprnoexcept

Get the Unicode category.

Returns: The Unicode category

Definition at line 19 of file rune.cpp.

◆ codepoint()

char32_t rune_caster::Rune::codepoint ( ) const

inlinenodiscardconstexprnoexcept

Get the Unicode codepoint.

Returns: The Unicode codepoint

Definition at line 66 of file rune.hpp.

◆ from_utf16()

Rune rune_caster::Rune::from_utf16 ( std::u16string_view utf16_char )

static

Create a Rune from a UTF-16 character.

Parameters

utf16_char UTF-16 encoded character

Returns: Rune object

Exceptions

std::invalid_argument if invalid UTF-16 sequence

Definition at line 200 of file rune.cpp.

◆ from_utf8() [1/2]

Rune rune_caster::Rune::from_utf8 ( std::string_view utf8_char )

static

Create a Rune from a UTF-8 character.

Parameters

utf8_char UTF-8 encoded character (may be multi-byte)

Returns: Rune object

Exceptions

std::invalid_argument if invalid UTF-8 sequence

Definition at line 140 of file rune.cpp.

◆ from_utf8() [2/2]

Rune rune_caster::Rune::from_utf8	(	std::string_view	utf8_char,
		language::Code	lang )

static

Create a Rune from a UTF-8 character with language hint.

Parameters

utf8_char	UTF-8 encoded character
language	Language hint for processing

Returns: Rune object

Exceptions

std::invalid_argument if invalid UTF-8 sequence

Definition at line 194 of file rune.cpp.

◆ is_ascii()

bool rune_caster::Rune::is_ascii ( ) const

nodiscardconstexprnoexcept

Check if this is an ASCII character.

Returns: true if ASCII (0-127), false otherwise

Definition at line 29 of file rune.cpp.

◆ is_consonant()

bool rune_caster::Rune::is_consonant ( ) const

inlinenodiscardconstexprnoexcept

Check if this rune represents a consonant.

Returns: true if consonant, false otherwise

Definition at line 341 of file rune.hpp.

◆ is_digit()

bool rune_caster::Rune::is_digit ( ) const

inlinenodiscardconstexprnoexcept

Check if this rune is a digit.

Returns: true if digit, false otherwise

Definition at line 280 of file rune.hpp.

◆ is_emoji()

bool rune_caster::Rune::is_emoji ( ) const

nodiscardconstexprnoexcept

Check if this is an emoji character.

Returns: true if emoji, false otherwise

Definition at line 71 of file rune.cpp.

◆ is_hangul()

bool rune_caster::Rune::is_hangul ( ) const

nodiscardconstexprnoexcept

Check if this is a Hangul (Korean) character.

Returns: true if Hangul, false otherwise

Definition at line 41 of file rune.cpp.

◆ is_hiragana()

bool rune_caster::Rune::is_hiragana ( ) const

nodiscardconstexprnoexcept

Check if this is a Hiragana character.

Returns: true if Hiragana, false otherwise

Definition at line 50 of file rune.cpp.

◆ is_kanji()

bool rune_caster::Rune::is_kanji ( ) const

nodiscardconstexprnoexcept

Check if this is a Kanji character.

Returns: true if Kanji (CJK Unified Ideographs), false otherwise

Definition at line 62 of file rune.cpp.

◆ is_katakana()

bool rune_caster::Rune::is_katakana ( ) const

nodiscardconstexprnoexcept

Check if this is a Katakana character.

Returns: true if Katakana, false otherwise

Definition at line 55 of file rune.cpp.

◆ is_latin()

bool rune_caster::Rune::is_latin ( ) const

nodiscardconstexprnoexcept

Check if this is a Latin script character.

Returns: true if Latin script, false otherwise

Definition at line 33 of file rune.cpp.

◆ is_letter()

bool rune_caster::Rune::is_letter ( ) const

inlinenodiscardconstexprnoexcept

Check if this rune is a letter.

Returns: true if letter, false otherwise

Definition at line 279 of file rune.hpp.

◆ is_punctuation()

bool rune_caster::Rune::is_punctuation ( ) const

inlinenodiscardconstexprnoexcept

Check if this rune is punctuation.

Returns: true if punctuation, false otherwise

Definition at line 282 of file rune.hpp.

◆ is_vowel()

bool rune_caster::Rune::is_vowel ( ) const

inlinenodiscardconstexprnoexcept

Check if this rune represents a vowel.

Returns: true if vowel, false otherwise

Definition at line 315 of file rune.hpp.

◆ is_whitespace()

bool rune_caster::Rune::is_whitespace ( ) const

inlinenodiscardconstexprnoexcept

Check if this rune is whitespace.

Returns: true if whitespace, false otherwise

Definition at line 281 of file rune.hpp.

◆ language()

language::Code rune_caster::Rune::language ( ) const

inlinenodiscardconstexprnoexcept

Get the language code.

Returns: The language code

Definition at line 72 of file rune.hpp.

◆ operator<=>()

auto rune_caster::Rune::operator<=> ( const Rune & other ) const

nodiscardconstexprdefaultnoexcept

Three-way comparison operator (C++20)

◆ operator=() [1/2]

Rune & rune_caster::Rune::operator= ( const Rune & )

constexprdefault

◆ operator=() [2/2]

Rune & rune_caster::Rune::operator= ( Rune && )

constexprdefaultnoexcept

◆ operator==()

bool rune_caster::Rune::operator== ( const Rune & other ) const

nodiscardconstexprdefaultnoexcept

Equality comparison.

◆ phoneme()

const std::string & rune_caster::Rune::phoneme ( ) const

inlinenodiscardnoexcept

Get the phonetic representation.

Returns: The phonetic representation as a string

Definition at line 90 of file rune.hpp.

◆ script()

unicode::Script rune_caster::Rune::script ( ) const

nodiscardconstexprnoexcept

Get the Unicode script.

Returns: The Unicode script

Definition at line 23 of file rune.cpp.

◆ set_language()

void rune_caster::Rune::set_language ( language::Code lang )

inlineconstexprnoexcept

Set the language code.

Parameters

language The new language code

Definition at line 98 of file rune.hpp.

◆ set_phoneme()

void rune_caster::Rune::set_phoneme ( std::string phoneme )

inline

Set the phonetic representation.

Parameters

phoneme The new phonetic representation

Definition at line 104 of file rune.hpp.

◆ to_utf16()

std::u16string rune_caster::Rune::to_utf16 ( ) const

nodiscard

Convert to UTF-16 string.

Returns: UTF-16 encoded string representation

Definition at line 114 of file rune.cpp.

◆ to_utf32()

std::u32string rune_caster::Rune::to_utf32 ( ) const

nodiscardconstexpr

Convert to UTF-32 string.

Returns: UTF-32 encoded string representation

Definition at line 134 of file rune.cpp.

◆ to_utf8()

std::string rune_caster::Rune::to_utf8 ( ) const

nodiscard

Convert to UTF-8 string.

Returns: UTF-8 encoded string representation

Definition at line 86 of file rune.cpp.

The documentation for this class was generated from the following files:

include/rune_caster/rune.hpp
src/rune/rune.cpp

Public Member Functions

Static Public Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ Rune() [1/6]

◆ Rune() [2/6]

◆ Rune() [3/6]

◆ Rune() [4/6]

◆ Rune() [5/6]

◆ Rune() [6/6]

◆ ~Rune()

Member Function Documentation

◆ category()

◆ codepoint()

◆ from_utf16()

◆ from_utf8() [1/2]

◆ from_utf8() [2/2]

◆ is_ascii()

◆ is_consonant()

◆ is_digit()

◆ is_emoji()

◆ is_hangul()

◆ is_hiragana()

◆ is_kanji()

◆ is_katakana()

◆ is_latin()

◆ is_letter()

◆ is_punctuation()

◆ is_vowel()

◆ is_whitespace()

◆ language()

◆ operator<=>()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ operator==()

◆ phoneme()

◆ script()

◆ set_language()

◆ set_phoneme()

◆ to_utf16()

◆ to_utf32()

◆ to_utf8()