#include <unicode.hpp>

Public Member Functions
template<typename IteratorType >
auto	decode_codepoint (IteratorType &it, const IteratorType &end) -> std::optional< codepoint_type >

template<char UnicodePrefix, typename IteratorType >
requires fly::UnicodePrefixCharacter< UnicodePrefix > auto	escape_codepoint (IteratorType &it, const IteratorType &end) -> std::optional< string_type >

template<typename IteratorType >
auto	unescape_codepoint (IteratorType &it, const IteratorType &end) -> std::optional< string_type >

template<char UnicodePrefix>
requires fly::UnicodePrefixCharacter< UnicodePrefix > auto	escape_codepoint (codepoint_type codepoint) -> string_type

template<char UnicodePrefix, typename IteratorType >
requires fly::UnicodePrefixCharacter< UnicodePrefix > auto	unescape_codepoint (IteratorType &it, const IteratorType &end) -> codepoint_type

template<typename IteratorType >
requires fly::SizeOfTypeIs< CharType, 1 > auto	codepoint_from_string (IteratorType &it, const IteratorType &end) -> codepoint_type

template<typename IteratorType >
requires fly::SizeOfTypeIs< CharType, 2 > auto	codepoint_from_string (IteratorType &it, const IteratorType &end) -> codepoint_type

template<typename IteratorType >
requires fly::SizeOfTypeIs< CharType, 4 > auto	codepoint_from_string (IteratorType &it, const IteratorType &end) -> codepoint_type

template<typename OutputIteratorType >
requires fly::SizeOfTypeIs< CharType, 1 > void	codepoint_to_string (codepoint_type codepoint, OutputIteratorType out)

template<typename OutputIteratorType >
requires fly::SizeOfTypeIs< CharType, 2 > void	codepoint_to_string (codepoint_type codepoint, OutputIteratorType out)

template<typename OutputIteratorType >
requires fly::SizeOfTypeIs< CharType, 4 > void	codepoint_to_string (codepoint_type codepoint, OutputIteratorType out)

template<typename IteratorType >
auto	next_encoded_byte (IteratorType &it, const IteratorType &end) -> codepoint_type

Static Public Member Functions
template<typename IteratorType >
static bool	validate_encoding (IteratorType &it, const IteratorType &end)

template<typename DesiredStringType >
static std::optional< DesiredStringType >	convert_encoding (view_type value)

template<typename DesiredStringType , typename OutputIteratorType >
static bool	convert_encoding_into (view_type value, OutputIteratorType out)

template<typename IteratorType >
static std::optional< codepoint_type >	decode_codepoint (IteratorType &it, const IteratorType &end)

static std::optional< string_type >	encode_codepoint (codepoint_type codepoint)

template<char UnicodePrefix = 'U', typename IteratorType >
requires static fly::UnicodePrefixCharacter< UnicodePrefix > std::optional< string_type >	escape_codepoint (IteratorType &it, const IteratorType &end)

template<typename IteratorType >
static std::optional< string_type >	unescape_codepoint (IteratorType &it, const IteratorType &end)

Detailed Description

template<fly::StandardCharacter CharType>
class fly::detail::BasicUnicode< CharType >

Helper class for decoding and encoding Unicode codepoints in a std::basic_string. The assumed Unicode encoding depends on the template type character type:

1. char - UTF-8
2. wchar_t - UTF-16 on Windows, UTF-32 on Linux and macOS
3. char8_t - UTF-8
4. char16_t - UTF-16
5. char32_t - UTF-32

Author: Timothy Flynn (trfly.nosp@m.nn89.nosp@m.@pm.m.nosp@m.e)

Version: June 6, 2020

Member Function Documentation

◆ convert_encoding()

template<fly::StandardCharacter CharType>

template<typename DesiredStringType >

std::optional< DesiredStringType > fly::detail::BasicUnicode< CharType >::convert_encoding ( view_type value )

inlinestatic

Convert the Unicode encoding of a string to another encoding.

Template Parameters

DesiredStringType The type of string to convert to.

Parameters

value The encoded Unicode string to convert.

Returns: If successful, a copy of the source string with the desired encoding. Otherwise, an uninitialized value.

◆ convert_encoding_into()

template<fly::StandardCharacter CharType>

template<typename DesiredStringType , typename OutputIteratorType >

bool fly::detail::BasicUnicode< CharType >::convert_encoding_into	(	view_type	value,
		OutputIteratorType	out
	)

static

Convert the Unicode encoding of a string to another encoding, inserting the result into the provided output iterator.

Template Parameters

DesiredStringType	The type of string to convert to.
OutputIteratorType	The type of the output iterator to insert the result into.

Parameters

it	Pointer to the beginning of the encoded Unicode string.
end	Pointer to the end of the encoded Unicode string.
out	The output iterator to insert the result into.

Returns: Whether the conversion was successful.

◆ decode_codepoint()

template<fly::StandardCharacter CharType>

template<typename IteratorType >

static std::optional<codepoint_type> fly::detail::BasicUnicode< CharType >::decode_codepoint	(	IteratorType &	it,
		const IteratorType &	end
	)

static

Decode a single Unicode codepoint, starting at the character pointed to by the provided iterator. If successful, after invoking this method, that iterator will point at the first character after the Unicode codepoint in the source string.

Template Parameters

IteratorType The type of the encoded Unicode codepoint's iterator.

Parameters

it	Pointer to the beginning of the encoded Unicode codepoint.
end	Pointer to the end of the encoded Unicode codepoint.

Returns: If successful, the decoded Unicode codepoint. Otherwise, an uninitialized value.

◆ encode_codepoint()

template<fly::StandardCharacter CharType>

auto fly::detail::BasicUnicode< CharType >::encode_codepoint ( codepoint_type codepoint )

static

Encode a single Unicode codepoint.

Returns: The Unicode codepoint to encode.; If successful, a string containing the encoded Unicode codepoint. Otherwise, an uninitialized value.

◆ escape_codepoint()

template<fly::StandardCharacter CharType>

template<char UnicodePrefix = 'U', typename IteratorType >

requires static fly::UnicodePrefixCharacter<UnicodePrefix> std::optional<string_type> fly::detail::BasicUnicode< CharType >::escape_codepoint	(	IteratorType &	it,
		const IteratorType &	end
	)

static

Escape a single Unicode codepoint, starting at the character pointed to by the provided iterator. If successful, after invoking this method, that iterator will point at the first character after the Unicode codepoint in the source string.

If the Unicode codepoint is an ASCII, non-control character (i.e. codepoints in the range [U+0020, U+007E]), that character is not escaped.

If the Unicode codepoint is non-ASCII or a control character (i.e. codepoints in the range [U+0000, U+001F] or [U+007F, U+10FFFF]), the codepoint is encoded as follows, taking into consideration the provided Unicode prefix character:

1. If the Unicode codepoint is in the range [U+0000, U+001F] or [U+007F, U+FFFF],
   regardless of the prefix character, the encoding will be of the form \unnnn.
2. If the codepoint is in the range [U+10000, U+10FFFF], and the prefix character is 'u',
   the encoding will be a surrogate pair of the form \unnnn\unnnn.
3. If the codepoint is in the range [U+10000, U+10FFFF], and the prefix character is 'U',
   the encoding will of the form \Unnnnnnnn.

Template Parameters

UnicodePrefix	The Unicode prefix character ('u' or 'U').
IteratorType	The type of the encoded Unicode codepoint's iterator.

Parameters

it	Pointer to the beginning of the encoded Unicode codepoint.
end	Pointer to the end of the encoded Unicode codepoint.

Returns: If successful, a string containing the escaped Unicode codepoint. Otherwise, an uninitialized value.

◆ unescape_codepoint()

template<fly::StandardCharacter CharType>

template<typename IteratorType >

static std::optional<string_type> fly::detail::BasicUnicode< CharType >::unescape_codepoint	(	IteratorType &	it,
		const IteratorType &	end
	)

static

Unescape a single Unicode codepoint, starting at the character pointed to by provided iterator. If successful, after invoking this method, that iterator will point at the first character after the escaped sequence in the source string.

Accepts escaped sequences of the following forms:

1. \unnnn for Unicode codepoints in the range [U+0000, U+FFFF].
2. \unnnn\unnnn surrogate pairs for Unicode codepoints in the range [U+10000, U+10FFFF].
3. \Unnnnnnnn for all Unicode codepoints.

Template Parameters

IteratorType The type of the escaped Unicode string's iterator.

Parameters

it	Pointer to the beginning of the escaped character sequence.
end	Pointer to the end of the escaped character sequence.

Returns: If successful, a string containing the unescaped Unicode codepoint. Otherwise, an uninitialized value.

◆ validate_encoding()

template<fly::StandardCharacter CharType>

template<typename IteratorType >

bool fly::detail::BasicUnicode< CharType >::validate_encoding	(	IteratorType &	it,
		const IteratorType &	end
	)

static

Validate that a string is strictly Unicode compliant.

Template Parameters

IteratorType The type of the encoded Unicode string's iterator.

Parameters

it	Pointer to the beginning of the encoded Unicode string.
end	Pointer to the end of the encoded Unicode string.

Returns: True if the string is Unicode compliant.

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

fly/types/string/detail/unicode.hpp

Public Member Functions

Static Public Member Functions

Detailed Description

template<fly::StandardCharacter CharType> class fly::detail::BasicUnicode< CharType >

Member Function Documentation

◆ convert_encoding()

◆ convert_encoding_into()

◆ decode_codepoint()

◆ encode_codepoint()

◆ escape_codepoint()

◆ unescape_codepoint()

◆ validate_encoding()

template<fly::StandardCharacter CharType>
class fly::detail::BasicUnicode< CharType >