#include <simdutf.h>

Inheritance diagram for simdutf::implementation:

Public Member Functions
virtual std::string	name () const

virtual std::string	description () const

bool	supported_by_runtime_system () const

virtual simdutf_warn_unused bool	validate_utf8 (const char *buf, size_t len) const noexcept=0

virtual simdutf_warn_unused result	validate_utf8_with_errors (const char *buf, size_t len) const noexcept=0

virtual simdutf_warn_unused bool	validate_utf16le (const char16_t *buf, size_t len) const noexcept=0

virtual simdutf_warn_unused bool	validate_utf16be (const char16_t *buf, size_t len) const noexcept=0

virtual simdutf_warn_unused result	validate_utf16le_with_errors (const char16_t *buf, size_t len) const noexcept=0

virtual simdutf_warn_unused result	validate_utf16be_with_errors (const char16_t *buf, size_t len) const noexcept=0

virtual void	to_well_formed_utf16le (const char16_t input, size_t len, char16_t output) const noexcept=0

virtual void	to_well_formed_utf16be (const char16_t input, size_t len, char16_t output) const noexcept=0

virtual simdutf_warn_unused size_t	convert_utf8_to_utf16le (const char input, size_t length, char16_t utf16_output) const noexcept=0

virtual simdutf_warn_unused size_t	convert_utf8_to_utf16be (const char input, size_t length, char16_t utf16_output) const noexcept=0

virtual simdutf_warn_unused result	convert_utf8_to_utf16le_with_errors (const char input, size_t length, char16_t utf16_output) const noexcept=0

virtual simdutf_warn_unused result	convert_utf8_to_utf16be_with_errors (const char input, size_t length, char16_t utf16_output) const noexcept=0

virtual simdutf_warn_unused result	utf8_length_from_utf16le_with_replacement (const char16_t *input, size_t length) const noexcept=0

virtual simdutf_warn_unused result	utf8_length_from_utf16be_with_replacement (const char16_t *input, size_t length) const noexcept=0

virtual simdutf_warn_unused size_t	convert_valid_utf8_to_utf16le (const char input, size_t length, char16_t utf16_buffer) const noexcept=0

virtual simdutf_warn_unused size_t	convert_valid_utf8_to_utf16be (const char input, size_t length, char16_t utf16_buffer) const noexcept=0

virtual simdutf_warn_unused size_t	utf16_length_from_utf8 (const char *input, size_t length) const noexcept=0

virtual simdutf_warn_unused size_t	convert_utf16le_to_utf8 (const char16_t input, size_t length, char utf8_buffer) const noexcept=0

virtual simdutf_warn_unused size_t	convert_utf16be_to_utf8 (const char16_t input, size_t length, char utf8_buffer) const noexcept=0

virtual simdutf_warn_unused result	convert_utf16le_to_utf8_with_errors (const char16_t input, size_t length, char utf8_buffer) const noexcept=0

virtual simdutf_warn_unused result	convert_utf16be_to_utf8_with_errors (const char16_t input, size_t length, char utf8_buffer) const noexcept=0

virtual simdutf_warn_unused size_t	convert_valid_utf16le_to_utf8 (const char16_t input, size_t length, char utf8_buffer) const noexcept=0

virtual simdutf_warn_unused size_t	convert_valid_utf16be_to_utf8 (const char16_t input, size_t length, char utf8_buffer) const noexcept=0

virtual simdutf_warn_unused size_t	utf8_length_from_utf16le (const char16_t *input, size_t length) const noexcept=0

virtual simdutf_warn_unused size_t	utf8_length_from_utf16be (const char16_t *input, size_t length) const noexcept=0

virtual void	change_endianness_utf16 (const char16_t input, size_t length, char16_t output) const noexcept=0

virtual simdutf_warn_unused size_t	count_utf16le (const char16_t *input, size_t length) const noexcept=0

virtual simdutf_warn_unused size_t	count_utf16be (const char16_t *input, size_t length) const noexcept=0

virtual simdutf_warn_unused size_t	count_utf8 (const char *input, size_t length) const noexcept=0

Private Member Functions
virtual uint32_t	required_instruction_sets () const

simdutf_really_inline	implementation (const char name, const char description, uint32_t required_instruction_sets)

Private Attributes
const char *	_name

const char *	_description

const uint32_t	_required_instruction_sets

Detailed Description

An implementation of simdutf for a particular CPU architecture.

Also used to maintain the currently active implementation. The active implementation is automatically initialized on first use to the most advanced implementation supported by the host.

Constructor & Destructor Documentation

◆ implementation()

simdutf_really_inline simdutf::implementation::implementation	(	const char *	name,
		const char *	description,
		uint32_t	required_instruction_sets
	)

inlineprivate

Construct an implementation with the given name and description. For subclasses.

Member Function Documentation

◆ change_endianness_utf16()

virtual void simdutf::implementation::change_endianness_utf16	(	const char16_t *	input,
		size_t	length,
		char16_t *	output
	)		const

pure virtualnoexcept

Change the endianness of the input. Can be used to go from UTF-16LE to UTF-16BE or from UTF-16BE to UTF-16LE.

This function does not validate the input.

This function is not BOM-aware.

Parameters

input	the UTF-16 string to process
length	the length of the string in 2-byte code units (char16_t)
output	the pointer to a buffer that can hold the conversion result

Implemented in simdutf::internal::unsupported_implementation, simdutf::internal::detect_best_supported_implementation_on_first_use, and simdutf::fallback::implementation.

◆ convert_utf16be_to_utf8()

virtual simdutf_warn_unused size_t simdutf::implementation::convert_utf16be_to_utf8	(	const char16_t *	input,
		size_t	length,
		char *	utf8_buffer
	)		const

pure virtualnoexcept

Convert possibly broken UTF-16BE string into UTF-8 string.

During the conversion also validation of the input string is done. This function is suitable to work with inputs from untrusted sources.

This function is not BOM-aware.

Parameters

input	the UTF-16BE string to convert
length	the length of the string in 2-byte code units (char16_t)
utf8_buffer	the pointer to buffer that can hold conversion result

Returns: number of written code units; 0 if input is not a valid UTF-16BE string

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ convert_utf16be_to_utf8_with_errors()

virtual simdutf_warn_unused result simdutf::implementation::convert_utf16be_to_utf8_with_errors	(	const char16_t *	input,
		size_t	length,
		char *	utf8_buffer
	)		const

pure virtualnoexcept

Convert possibly broken UTF-16BE string into UTF-8 string and stop on error.

During the conversion also validation of the input string is done. This function is suitable to work with inputs from untrusted sources.

This function is not BOM-aware.

Parameters

input	the UTF-16BE string to convert
length	the length of the string in 2-byte code units (char16_t)
utf8_buffer	the pointer to buffer that can hold conversion result

Returns: a result pair struct (of type simdutf::result containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char written if successful.

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ convert_utf16le_to_utf8()

virtual simdutf_warn_unused size_t simdutf::implementation::convert_utf16le_to_utf8	(	const char16_t *	input,
		size_t	length,
		char *	utf8_buffer
	)		const

pure virtualnoexcept

Convert possibly broken UTF-16LE string into UTF-8 string.

During the conversion also validation of the input string is done. This function is suitable to work with inputs from untrusted sources.

This function is not BOM-aware.

Parameters

input	the UTF-16LE string to convert
length	the length of the string in 2-byte code units (char16_t)
utf8_buffer	the pointer to buffer that can hold conversion result

Returns: number of written code units; 0 if input is not a valid UTF-16LE string

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ convert_utf16le_to_utf8_with_errors()

virtual simdutf_warn_unused result simdutf::implementation::convert_utf16le_to_utf8_with_errors	(	const char16_t *	input,
		size_t	length,
		char *	utf8_buffer
	)		const

pure virtualnoexcept

Convert possibly broken UTF-16LE string into UTF-8 string and stop on error.

During the conversion also validation of the input string is done. This function is suitable to work with inputs from untrusted sources.

This function is not BOM-aware.

Parameters

input	the UTF-16LE string to convert
length	the length of the string in 2-byte code units (char16_t)
utf8_buffer	the pointer to buffer that can hold conversion result

Returns: a result pair struct (of type simdutf::result containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of char written if successful.

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ convert_utf8_to_utf16be()

virtual simdutf_warn_unused size_t simdutf::implementation::convert_utf8_to_utf16be	(	const char *	input,
		size_t	length,
		char16_t *	utf16_output
	)		const

pure virtualnoexcept

Convert possibly broken UTF-8 string into UTF-16BE string.

During the conversion also validation of the input string is done. This function is suitable to work with inputs from untrusted sources.

Parameters

input	the UTF-8 string to convert
length	the length of the string in bytes
utf16_buffer	the pointer to buffer that can hold conversion result

Returns: the number of written char16_t; 0 if the input was not valid UTF-8 string

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ convert_utf8_to_utf16be_with_errors()

virtual simdutf_warn_unused result simdutf::implementation::convert_utf8_to_utf16be_with_errors	(	const char *	input,
		size_t	length,
		char16_t *	utf16_output
	)		const

pure virtualnoexcept

Convert possibly broken UTF-8 string into UTF-16BE string and stop on error.

During the conversion also validation of the input string is done. This function is suitable to work with inputs from untrusted sources.

Parameters

input	the UTF-8 string to convert
length	the length of the string in bytes
utf16_buffer	the pointer to buffer that can hold conversion result

Returns: a result pair struct (of type simdutf::result containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of code units validated if successful.

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ convert_utf8_to_utf16le()

virtual simdutf_warn_unused size_t simdutf::implementation::convert_utf8_to_utf16le	(	const char *	input,
		size_t	length,
		char16_t *	utf16_output
	)		const

pure virtualnoexcept

Convert possibly broken UTF-8 string into UTF-16LE string.

During the conversion also validation of the input string is done. This function is suitable to work with inputs from untrusted sources.

Parameters

input	the UTF-8 string to convert
length	the length of the string in bytes
utf16_buffer	the pointer to buffer that can hold conversion result

Returns: the number of written char16_t; 0 if the input was not valid UTF-8 string

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ convert_utf8_to_utf16le_with_errors()

virtual simdutf_warn_unused result simdutf::implementation::convert_utf8_to_utf16le_with_errors	(	const char *	input,
		size_t	length,
		char16_t *	utf16_output
	)		const

pure virtualnoexcept

Convert possibly broken UTF-8 string into UTF-16LE string and stop on error.

During the conversion also validation of the input string is done. This function is suitable to work with inputs from untrusted sources.

Parameters

input	the UTF-8 string to convert
length	the length of the string in bytes
utf16_buffer	the pointer to buffer that can hold conversion result

Returns: a result pair struct (of type simdutf::result containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of code units validated if successful.

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ convert_valid_utf16be_to_utf8()

virtual simdutf_warn_unused size_t simdutf::implementation::convert_valid_utf16be_to_utf8	(	const char16_t *	input,
		size_t	length,
		char *	utf8_buffer
	)		const

pure virtualnoexcept

Convert valid UTF-16BE string into UTF-8 string.

This function assumes that the input string is valid UTF-16BE.

This function is not BOM-aware.

Parameters

input	the UTF-16BE string to convert
length	the length of the string in 2-byte code units (char16_t)
utf8_buffer	the pointer to a buffer that can hold the conversion result

Returns: number of written code units; 0 if conversion is not possible

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ convert_valid_utf16le_to_utf8()

virtual simdutf_warn_unused size_t simdutf::implementation::convert_valid_utf16le_to_utf8	(	const char16_t *	input,
		size_t	length,
		char *	utf8_buffer
	)		const

pure virtualnoexcept

Convert valid UTF-16LE string into UTF-8 string.

This function assumes that the input string is valid UTF-16LE.

This function is not BOM-aware.

Parameters

input	the UTF-16LE string to convert
length	the length of the string in 2-byte code units (char16_t)
utf8_buffer	the pointer to a buffer that can hold the conversion result

Returns: number of written code units; 0 if conversion is not possible

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ convert_valid_utf8_to_utf16be()

virtual simdutf_warn_unused size_t simdutf::implementation::convert_valid_utf8_to_utf16be	(	const char *	input,
		size_t	length,
		char16_t *	utf16_buffer
	)		const

pure virtualnoexcept

Convert valid UTF-8 string into UTF-16BE string.

This function assumes that the input string is valid UTF-8.

Parameters

input	the UTF-8 string to convert
length	the length of the string in bytes
utf16_buffer	the pointer to buffer that can hold conversion result

Returns: the number of written char16_t

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ convert_valid_utf8_to_utf16le()

virtual simdutf_warn_unused size_t simdutf::implementation::convert_valid_utf8_to_utf16le	(	const char *	input,
		size_t	length,
		char16_t *	utf16_buffer
	)		const

pure virtualnoexcept

Convert valid UTF-8 string into UTF-16LE string.

This function assumes that the input string is valid UTF-8.

Parameters

input	the UTF-8 string to convert
length	the length of the string in bytes
utf16_buffer	the pointer to buffer that can hold conversion result

Returns: the number of written char16_t

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ count_utf16be()

virtual simdutf_warn_unused size_t simdutf::implementation::count_utf16be	(	const char16_t *	input,
		size_t	length
	)		const

pure virtualnoexcept

Count the number of code points (characters) in the string assuming that it is valid.

This function assumes that the input string is valid UTF-16BE. It is acceptable to pass invalid UTF-16 strings but in such cases the result is implementation defined.

This function is not BOM-aware.

Parameters

input	the UTF-16BE string to process
length	the length of the string in 2-byte code units (char16_t)

Returns: number of code points

Implemented in simdutf::internal::unsupported_implementation, simdutf::internal::detect_best_supported_implementation_on_first_use, and simdutf::fallback::implementation.

◆ count_utf16le()

virtual simdutf_warn_unused size_t simdutf::implementation::count_utf16le	(	const char16_t *	input,
		size_t	length
	)		const

pure virtualnoexcept

Count the number of code points (characters) in the string assuming that it is valid.

This function assumes that the input string is valid UTF-16LE. It is acceptable to pass invalid UTF-16 strings but in such cases the result is implementation defined.

This function is not BOM-aware.

Parameters

input	the UTF-16LE string to process
length	the length of the string in 2-byte code units (char16_t)

Returns: number of code points

Implemented in simdutf::internal::unsupported_implementation, simdutf::internal::detect_best_supported_implementation_on_first_use, and simdutf::fallback::implementation.

◆ count_utf8()

virtual simdutf_warn_unused size_t simdutf::implementation::count_utf8	(	const char *	input,
		size_t	length
	)		const

pure virtualnoexcept

Count the number of code points (characters) in the string assuming that it is valid.

This function assumes that the input string is valid UTF-8. It is acceptable to pass invalid UTF-8 strings but in such cases the result is implementation defined.

Parameters

input	the UTF-8 string to process
length	the length of the string in bytes

Returns: number of code points

Implemented in simdutf::internal::unsupported_implementation, simdutf::internal::detect_best_supported_implementation_on_first_use, and simdutf::fallback::implementation.

◆ description()

virtual std::string simdutf::implementation::description ( ) const

inlinevirtual

The description of this implementation.

const implementation *impl = simdutf::active_implementation;
cout << "simdutf is optimized for " << impl->name() << "(" <<

impl->description() << ")" << endl;

Returns: the name of the implementation, e.g. "haswell", "westmere", "arm64"

Reimplemented in simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ name()

virtual std::string simdutf::implementation::name ( ) const

inlinevirtual

The name of this implementation.

const implementation *impl = simdutf::active_implementation;
cout << "simdutf is optimized for " << impl->name() << "(" <<

impl->description() << ")" << endl;

Returns: the name of the implementation, e.g. "haswell", "westmere", "arm64"

Reimplemented in simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ required_instruction_sets()

virtual uint32_t simdutf::implementation::required_instruction_sets ( ) const

inlineprivatevirtual

For internal implementation use

The instruction sets this implementation is compiled against.

Returns: a mask of all required internal::instruction_set:: values

Reimplemented in simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ supported_by_runtime_system()

bool simdutf::implementation::supported_by_runtime_system ( ) const

The instruction sets this implementation is compiled against and the current CPU match. This function may poll the current CPU/system and should therefore not be called too often if performance is a concern.

Returns: true if the implementation can be safely used on the current system (determined at runtime)

◆ to_well_formed_utf16be()

virtual void simdutf::implementation::to_well_formed_utf16be	(	const char16_t *	input,
		size_t	len,
		char16_t *	output
	)		const

pure virtualnoexcept

Copies the UTF-16BE string while replacing mismatched surrogates with the Unicode replacement character U+FFFD. We allow the input and output to be the same buffer so that the correction is done in-place.

Overridden by each implementation.

Parameters

input	the UTF-16BE string to correct.
len	the length of the string in number of 2-byte code units (char16_t).
output	the output buffer.

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ to_well_formed_utf16le()

virtual void simdutf::implementation::to_well_formed_utf16le	(	const char16_t *	input,
		size_t	len,
		char16_t *	output
	)		const

pure virtualnoexcept

Copies the UTF-16LE string while replacing mismatched surrogates with the Unicode replacement character U+FFFD. We allow the input and output to be the same buffer so that the correction is done in-place.

Overridden by each implementation.

Parameters

input	the UTF-16LE string to correct.
len	the length of the string in number of 2-byte code units (char16_t).
output	the output buffer.

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ utf16_length_from_utf8()

virtual simdutf_warn_unused size_t simdutf::implementation::utf16_length_from_utf8	(	const char *	input,
		size_t	length
	)		const

pure virtualnoexcept

Compute the number of 2-byte code units that this UTF-8 string would require in UTF-16LE format.

This function does not validate the input. It is acceptable to pass invalid UTF-8 strings but in such cases the result is implementation defined.

Parameters

input	the UTF-8 string to process
length	the length of the string in bytes

Returns: the number of char16_t code units required to encode the UTF-8 string as UTF-16LE

Implemented in simdutf::internal::unsupported_implementation, simdutf::internal::detect_best_supported_implementation_on_first_use, and simdutf::fallback::implementation.

◆ utf8_length_from_utf16be()

virtual simdutf_warn_unused size_t simdutf::implementation::utf8_length_from_utf16be	(	const char16_t *	input,
		size_t	length
	)		const

pure virtualnoexcept

Compute the number of bytes that this UTF-16BE string would require in UTF-8 format.

This function does not validate the input. It is acceptable to pass invalid UTF-16 strings but in such cases the result is implementation defined.

This function is not BOM-aware.

Parameters

input	the UTF-16BE string to convert
length	the length of the string in 2-byte code units (char16_t)

Returns: the number of bytes required to encode the UTF-16BE string as UTF-8

Implemented in simdutf::internal::unsupported_implementation, simdutf::internal::detect_best_supported_implementation_on_first_use, and simdutf::fallback::implementation.

◆ utf8_length_from_utf16be_with_replacement()

virtual simdutf_warn_unused result simdutf::implementation::utf8_length_from_utf16be_with_replacement	(	const char16_t *	input,
		size_t	length
	)		const

pure virtualnoexcept

Compute the number of bytes that this UTF-16BE string would require in UTF-8 format even when the UTF-16BE content contains mismatched surrogates that have to be replaced by the replacement character (0xFFFD).

Parameters

input	the UTF-16BE string to convert
length	the length of the string in 2-byte code units (char16_t)

Returns: a result pair struct (of type simdutf::result containing the two fields error and count) where the count is the number of bytes required to encode the UTF-16BE string as UTF-8, and the error code is either SUCCESS or SURROGATE. The count is correct regardless of the error field. When SURROGATE is returned, it does not indicate an error in the case of this function: it indicates that at least one surrogate has been encountered: the surrogates may be matched or not (thus this function does not validate). If the returned error code is SUCCESS, then the input contains no surrogate, is in the Basic Multilingual Plane, and is necessarily valid.

Implemented in simdutf::internal::unsupported_implementation, simdutf::internal::detect_best_supported_implementation_on_first_use, and simdutf::fallback::implementation.

◆ utf8_length_from_utf16le()

virtual simdutf_warn_unused size_t simdutf::implementation::utf8_length_from_utf16le	(	const char16_t *	input,
		size_t	length
	)		const

pure virtualnoexcept

Compute the number of bytes that this UTF-16LE string would require in UTF-8 format.

This function does not validate the input. It is acceptable to pass invalid UTF-16 strings but in such cases the result is implementation defined.

This function is not BOM-aware.

Parameters

input	the UTF-16LE string to convert
length	the length of the string in 2-byte code units (char16_t)

Returns: the number of bytes required to encode the UTF-16LE string as UTF-8

Implemented in simdutf::internal::unsupported_implementation, simdutf::internal::detect_best_supported_implementation_on_first_use, and simdutf::fallback::implementation.

◆ utf8_length_from_utf16le_with_replacement()

virtual simdutf_warn_unused result simdutf::implementation::utf8_length_from_utf16le_with_replacement	(	const char16_t *	input,
		size_t	length
	)		const

pure virtualnoexcept

Compute the number of bytes that this UTF-16LE string would require in UTF-8 format even when the UTF-16LE content contains mismatched surrogates that have to be replaced by the replacement character (0xFFFD).

Parameters

input	the UTF-16LE string to convert
length	the length of the string in 2-byte code units (char16_t)

Returns: a result pair struct (of type simdutf::result containing the two fields error and count) where the count is the number of bytes required to encode the UTF-16LE string as UTF-8, and the error code is either SUCCESS or SURROGATE. The count is correct regardless of the error field. When SURROGATE is returned, it does not indicate an error in the case of this function: it indicates that at least one surrogate has been encountered: the surrogates may be matched or not (thus this function does not validate). If the returned error code is SUCCESS, then the input contains no surrogate, is in the Basic Multilingual Plane, and is necessarily valid.

Implemented in simdutf::internal::unsupported_implementation, simdutf::internal::detect_best_supported_implementation_on_first_use, and simdutf::fallback::implementation.

◆ validate_utf16be()

virtual simdutf_warn_unused bool simdutf::implementation::validate_utf16be	(	const char16_t *	buf,
		size_t	len
	)		const

pure virtualnoexcept

Validate the UTF-16BE string. This function may be best when you expect the input to be almost always valid. Otherwise, consider using validate_utf16be_with_errors.

Overridden by each implementation.

This function is not BOM-aware.

Parameters

buf	the UTF-16BE string to validate.
len	the length of the string in number of 2-byte code units (char16_t).

Returns: true if and only if the string is valid UTF-16BE.

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ validate_utf16be_with_errors()

virtual simdutf_warn_unused result simdutf::implementation::validate_utf16be_with_errors	(	const char16_t *	buf,
		size_t	len
	)		const

pure virtualnoexcept

Validate the UTF-16BE string and stop on error. It might be faster than validate_utf16be when an error is expected to occur early.

Overridden by each implementation.

This function is not BOM-aware.

Parameters

buf	the UTF-16BE string to validate.
len	the length of the string in number of 2-byte code units (char16_t).

Returns: a result pair struct (of type simdutf::result containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of code units validated if successful.

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ validate_utf16le()

virtual simdutf_warn_unused bool simdutf::implementation::validate_utf16le	(	const char16_t *	buf,
		size_t	len
	)		const

pure virtualnoexcept

Validate the UTF-16LE string.This function may be best when you expect the input to be almost always valid. Otherwise, consider using validate_utf16le_with_errors.

Overridden by each implementation.

This function is not BOM-aware.

Parameters

buf	the UTF-16LE string to validate.
len	the length of the string in number of 2-byte code units (char16_t).

Returns: true if and only if the string is valid UTF-16LE.

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ validate_utf16le_with_errors()

virtual simdutf_warn_unused result simdutf::implementation::validate_utf16le_with_errors	(	const char16_t *	buf,
		size_t	len
	)		const

pure virtualnoexcept

Validate the UTF-16LE string and stop on error. It might be faster than validate_utf16le when an error is expected to occur early.

Overridden by each implementation.

This function is not BOM-aware.

Parameters

buf	the UTF-16LE string to validate.
len	the length of the string in number of 2-byte code units (char16_t).

Returns: a result pair struct (of type simdutf::result containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of code units validated if successful.

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ validate_utf8()

virtual simdutf_warn_unused bool simdutf::implementation::validate_utf8	(	const char *	buf,
		size_t	len
	)		const

pure virtualnoexcept

Validate the UTF-8 string.

Overridden by each implementation.

Parameters

buf	the UTF-8 string to validate.
len	the length of the string in bytes.

Returns: true if and only if the string is valid UTF-8.

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

◆ validate_utf8_with_errors()

virtual simdutf_warn_unused result simdutf::implementation::validate_utf8_with_errors	(	const char *	buf,
		size_t	len
	)		const

pure virtualnoexcept

Validate the UTF-8 string and stop on errors.

Overridden by each implementation.

Parameters

buf	the UTF-8 string to validate.
len	the length of the string in bytes.

Returns: a result pair struct (of type simdutf::result containing the two fields error and count) with an error code and either position of the error (in the input in code units) if any, or the number of code units validated if successful.

Implemented in simdutf::internal::unsupported_implementation, simdutf::fallback::implementation, and simdutf::internal::detect_best_supported_implementation_on_first_use.

Member Data Documentation

◆ _description

const char* simdutf::implementation::_description

private

The description of this implementation.

◆ _name

const char* simdutf::implementation::_name

private

The name of this implementation.

◆ _required_instruction_sets

const uint32_t simdutf::implementation::_required_instruction_sets

private

Instruction sets required for this implementation.

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

/mbsim-env/openmbv/mbxmlutils/mbxmlutilshelper/simdutf.h
/mbsim-env/openmbv/mbxmlutils/mbxmlutilshelper/simdutf.cpp

Public Member Functions

Private Member Functions

Private Attributes

Detailed Description

Constructor & Destructor Documentation

◆ implementation()

Member Function Documentation

◆ change_endianness_utf16()

◆ convert_utf16be_to_utf8()

◆ convert_utf16be_to_utf8_with_errors()

◆ convert_utf16le_to_utf8()

◆ convert_utf16le_to_utf8_with_errors()

◆ convert_utf8_to_utf16be()

◆ convert_utf8_to_utf16be_with_errors()

◆ convert_utf8_to_utf16le()

◆ convert_utf8_to_utf16le_with_errors()

◆ convert_valid_utf16be_to_utf8()

◆ convert_valid_utf16le_to_utf8()

◆ convert_valid_utf8_to_utf16be()

◆ convert_valid_utf8_to_utf16le()

◆ count_utf16be()

◆ count_utf16le()

◆ count_utf8()

◆ description()

◆ name()

◆ required_instruction_sets()

◆ supported_by_runtime_system()

◆ to_well_formed_utf16be()

◆ to_well_formed_utf16le()

◆ utf16_length_from_utf8()

◆ utf8_length_from_utf16be()

◆ utf8_length_from_utf16be_with_replacement()

◆ utf8_length_from_utf16le()

◆ utf8_length_from_utf16le_with_replacement()

◆ validate_utf16be()

◆ validate_utf16be_with_errors()

◆ validate_utf16le()

◆ validate_utf16le_with_errors()

◆ validate_utf8()

◆ validate_utf8_with_errors()

Member Data Documentation

◆ _description

◆ _name

◆ _required_instruction_sets