v1::unicode_description Class Reference

#include <hikogui/unicode/unicode_description.hpp>

Public Member Functions
	unicode_description (unicode_description const &)=delete
unicode_description &	operator= (unicode_description const &)=delete
constexpr	unicode_description (unicode_description &&) noexcept=default
constexpr unicode_description &	operator= (unicode_description &&) noexcept=default
constexpr	unicode_description (char32_t code_point, unicode_general_category general_category, unicode_grapheme_cluster_break grapheme_cluster_break, unicode_line_break_class line_break_class, unicode_word_break_property word_break_property, unicode_sentence_break_property sentence_break_property, unicode_east_asian_width east_asian_width, unicode_script script, unicode_bidi_class bidi_class, unicode_bidi_bracket_type bidi_bracket_type, char32_t bidi_mirrored_glyph, unicode_decomposition_type decomposition_type, bool is_canonical_composition, uint8_t canonical_combining_class, uint8_t decomposition_length, uint32_t decomposition_index, uint16_t non_starter_code) noexcept
constexpr char32_t	code_point () const noexcept
	The code point of the description.
constexpr unicode_general_category	general_category () const noexcept
	The general category of this code-point.
constexpr unicode_grapheme_cluster_break	grapheme_cluster_break () const noexcept
	The grapheme cluster break of this code-point.
constexpr bool	is_canonical_composition () const noexcept
constexpr bool	is_combining_mark () const noexcept
constexpr unicode_line_break_class	line_break_class () const noexcept
constexpr unicode_word_break_property	word_break_property () const noexcept
constexpr unicode_sentence_break_property	sentence_break_property () const noexcept
constexpr unicode_east_asian_width	east_asian_width () const noexcept
constexpr unicode_bidi_class	bidi_class () const noexcept
	The bidi class of this code-point This function is used by the bidirectional algorithm to figure out if the code-point represents a character that is written left-to-right or right-to-left.
constexpr unicode_script	script () const noexcept
	Get the script of this character.
constexpr unicode_bidi_bracket_type	bidi_bracket_type () const noexcept
	Get the bidi bracket type.
constexpr char32_t	bidi_mirrored_glyph () const noexcept
	Get the mirrored glyph.
constexpr unicode_decomposition_type	decomposition_type () const noexcept
	This character has a canonical decomposition.
constexpr uint8_t	canonical_combining_class () const noexcept
	Get the combining class.
constexpr std::size_t	decomposition_length () const noexcept
	The number of code-points the decomposed grapheme has.
constexpr std::size_t	decomposition_index () const noexcept
	A multi-use value representing the decomposition of this code-point.
constexpr char32_t	canonical_equivalent () const noexcept
	Get the canonical equivalent of this code-point.
constexpr size_t	non_starter_code () const noexcept
	Get the non-starter-code.

Static Public Member Functions
static constexpr unicode_description	make_unassigned (unicode_description const &other)
static unicode_description const &	find (char32_t code_point) noexcept
	Find a code-point in the global unicode_description table.

Friends
bool	operator== (unicode_description const &lhs, unicode_general_category const &rhs) noexcept
bool	operator== (unicode_description const &lhs, unicode_decomposition_type const &rhs) noexcept
bool	operator== (unicode_description const &lhs, unicode_bidi_bracket_type const &rhs) noexcept
bool	operator== (unicode_description const &lhs, unicode_bidi_class const &rhs) noexcept
bool	operator== (unicode_description const &lhs, unicode_east_asian_width const &rhs) noexcept
bool	operator== (unicode_description const &lhs, unicode_sentence_break_property const &rhs) noexcept
bool	operator== (unicode_description const &lhs, unicode_line_break_class const &rhs) noexcept
bool	operator== (unicode_description const &lhs, unicode_word_break_property const &rhs) noexcept
bool	operator== (unicode_description const &lhs, unicode_grapheme_cluster_break const &rhs) noexcept
bool	operator== (unicode_description const &lhs, char32_t const &rhs) noexcept
bool	is_C (unicode_description const &rhs) noexcept

Detailed Description

Description of a unicode code point.

This class holds information of a unicode code point.

The information is compressed to use bit-fields to reduce memory usage of the unicode database.

Member Function Documentation

bidi_bracket_type()

constexpr unicode_bidi_bracket_type v1::unicode_description::bidi_bracket_type ( ) const

inlineconstexprnoexcept

Get the bidi bracket type.

This function is used by the bidirectional algorithm for mirroring characters when needing to reverse the writing direction.

Returns

n = no-mirror, o = open-bracket, c = close-bracket, m = bidi-mirrored.

bidi_class()

constexpr unicode_bidi_class v1::unicode_description::bidi_class ( ) const

inlineconstexprnoexcept

The bidi class of this code-point This function is used by the bidirectional algorithm to figure out if the code-point represents a character that is written left-to-right or right-to-left.

Returns

the bidi class of this code-point.

bidi_mirrored_glyph()

constexpr char32_t v1::unicode_description::bidi_mirrored_glyph ( ) const

inlineconstexprnoexcept

Get the mirrored glyph.

Returns

The mirrored glyph or U+ffff when there is no mirrored glyph.

canonical_combining_class()

constexpr uint8_t v1::unicode_description::canonical_combining_class ( ) const

inlineconstexprnoexcept

Get the combining class.

The combing class describes how a code-point combines with other code-points. Specifically the value 0 means that the code-point is a starter character, and the numeric value of the combing class determines the order of the the code-points after a starter before trying to look up composition in the composition table.

Returns

The numeric combining class of this code point.

canonical_equivalent()

constexpr char32_t v1::unicode_description::canonical_equivalent ( ) const

inlineconstexprnoexcept

Get the canonical equivalent of this code-point.

The canonical equivalent is the code-point after NFC-normalization. This is equal to canonical decomposition to a single code-point.

Returns

The canonical equivalent code-point or U+ffff if there is not equivalent.

code_point()

constexpr char32_t v1::unicode_description::code_point ( ) const

inlineconstexprnoexcept

The code point of the description.

Returns

The code_point of the description.

decomposition_index()

constexpr std::size_t v1::unicode_description::decomposition_index ( ) const

inlineconstexprnoexcept

A multi-use value representing the decomposition of this code-point.

To compress the data for decomposition:

• For single code-point decomposition the index itself is the code-point value.
• For double code-point decomposition, if it is equal to the composition it points into the composition table, otherwise it points into the decomposition table
• Anything else points into the decomposition table.

See also

decomposition_length

Returns

A code-point value, or a index into the composition table, or an index into the decomposition table.

decomposition_length()

constexpr std::size_t v1::unicode_description::decomposition_length ( ) const

inlineconstexprnoexcept

The number of code-points the decomposed grapheme has.

Return values

0	There is no decomposition
1	Decomposition is a single code-point, the decomposition_index() is the numeric value of the code point.
2	Decomposition is has two code-point. When composition_canonical is set the decomposition_index() points in the composition table. Otherwise the index points into the decomposition table.

Returns

Values 3 and above are the number of code points in the decomposition table pointed to from the decomposition_index().

decomposition_type()

constexpr unicode_decomposition_type v1::unicode_description::decomposition_type ( ) const

inlineconstexprnoexcept

This character has a canonical decomposition.

Returns

When true you can decompose the character canonically.

find()

static unicode_description const & v1::unicode_description::find ( char32_t code_point )

staticnoexcept

Find a code-point in the global unicode_description table.

For any valid unicode code point this function will return a reference to the unicode_description. It may return a unicode_description to the U+fffd 'REPLACEMENT CHARACTER' if the code-point could not be found in the table. Or it may return unicode_description to a single element in a range of code-points, such as for hangul-syllables, or private use areas.

Parameters

code_point

The code point to look up.

Returns

a const reference to the unicode_description entry.

general_category()

constexpr unicode_general_category v1::unicode_description::general_category ( ) const

inlineconstexprnoexcept

The general category of this code-point.

This function is used to determine what kind of code-point this, this allows you to determine if the code-point is a letter, number, punctuation, white-space, etc.

Returns

The general category of this code-point

grapheme_cluster_break()

constexpr unicode_grapheme_cluster_break v1::unicode_description::grapheme_cluster_break ( ) const

inlineconstexprnoexcept

The grapheme cluster break of this code-point.

This function is used to determine where to break a string of code-points into grapheme clusters.

Returns

The grapheme cluster break of this code-point

non_starter_code()

constexpr size_t v1::unicode_description::non_starter_code ( ) const

inlineconstexprnoexcept

Get the non-starter-code.

Instead of using a full 21-bit code-point this 10-bit value is used to compress non-starter characters.

Note

It is undefined-behavior to call this function on a starter-character.

Returns

10 bit code value for a non-starter character.

script()

constexpr unicode_script v1::unicode_description::script ( ) const

inlineconstexprnoexcept

Get the script of this character.

---

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

• hikogui/src/hikogui/unicode/unicode_description.hpp