utf8.cpp File Reference

Basic UTF-8 Conversion functions. More...

#include <utf8/utf8.h>
#include <vector>
#include <cassert>
#include <cstring>

Functions
action	utf8::error_mode (action mode)
	Set error handling mode for this thread.
char32_t	utf8::throw_or_replace (exception::cause err)
std::string	utf8::narrow (const wchar_t *s, size_t nch)
	Conversion from wide character to UTF-8.
std::string	utf8::narrow (const std::wstring &ws)
	Conversion from wide character to UTF-8.
std::string	utf8::narrow (const char32_t *s, size_t nch)
	Conversion from UTF32 to UTF8.
std::string	utf8::narrow (const std::u32string &s)
	Conversion from UTF32 to UTF8.
std::string	utf8::narrow (char32_t r)
	Conversion from UTF32 to UTF8.
std::wstring	utf8::widen (const char *s, size_t nch)
	Conversion from UTF-8 to wide character.
std::wstring	utf8::widen (const std::string &s)
	Conversion from UTF-8 to wide character.
std::u32string	utf8::runes (const char *s, size_t nch)
	Conversion from UTF-8 to UTF-32.
std::u32string	utf8::runes (const std::string &s)
	Converts a string of characters from UTF-8 to UTF-32.
bool	utf8::valid_str (const char *s, size_t nch)
	Verifies if string is a valid UTF-8 string.
char32_t	utf8::next (std::string::const_iterator &ptr, const std::string::const_iterator last)
	Decodes a UTF-8 encoded character and advances iterator to next code point.
char32_t	utf8::next (const char *&ptr)
	Decodes a UTF-8 encoded character and advances pointer to next character.
char32_t	utf8::prev (const char *&ptr)
	Decrements a character pointer to previous UTF-8 character.
char32_t	utf8::prev (std::string::const_iterator &ptr, const std::string::const_iterator first)
	Decrements an iterator to previous UTF-8 character.
size_t	utf8::length (const std::string &s)
	Counts number of characters in an UTF8 encoded string.
size_t	utf8::length (const char *s)
	Counts number of characters in an UTF8 encoded string.
bool	utf8::isblank (char32_t r)
	Check if character is space or tab.
bool	utf8::isspace (char32_t r)
	Check if character is white space.

Detailed Description

Basic UTF-8 Conversion functions.

Function Documentation

error_mode()

action utf8::error_mode

(

action

mode

)

Set error handling mode for this thread.

Parameters

mode	new error handling mode

Returns

previous error handling mode for this thread

length() [1/2]

size_t utf8::length

(

const char *

s

)

Counts number of characters in an UTF8 encoded string.

Parameters

s	UTF8-encoded string

Returns

number of characters in string

Note

Algorithm from http://canonical.org/~kragen/strlen-utf8.html

length() [2/2]

size_t utf8::length

(

const std::string &

s

)

Counts number of characters in an UTF8 encoded string.

Parameters

s	UTF8-encoded string

Returns

number of characters in string

Note

Algorithm from http://canonical.org/~kragen/strlen-utf8.html

next() [1/2]

char32_t utf8::next

(

const char *&

ptr

)

Decodes a UTF-8 encoded character and advances pointer to next character.

Parameters

ptr	Reference to character pointer to be advanced

Returns

decoded character

If the string contains an invalid UTF-8 encoding, the function throws an exception or returns utf8::REPLACEMENT_CHARACTER (0xfffd) depending on error handling mode. In any case, the pointer is advanced to beginning of next character or end of string.

next() [2/2]

char32_t utf8::next	(	std::string::const_iterator &	ptr,
		const std::string::const_iterator	last
	)

Decodes a UTF-8 encoded character and advances iterator to next code point.

Parameters

ptr	Reference to iterator to be advanced
last	Iterator pointing to the end of range

Returns

decoded character

If the iterator points to an invalid UTF-8 encoding or is at end, the function throws an exception or returns utf8::REPLACEMENT_CHARACTER (0xfffd) depending on error handling mode. In any case, the iterator is advanced to beginning of next character or end of string.

prev() [1/2]

char32_t utf8::prev

(

const char *&

ptr

)

Decrements a character pointer to previous UTF-8 character.

Parameters

ptr	Reference to character pointer to be decremented

Returns

previous UTF-8 encoded character

If the string contains an invalid UTF-8 encoding, the function throws an exception or returns utf8::REPLACEMENT_CHARACTER (0xfffd) depending on error handling mode. In this case the pointer remains unchanged.

prev() [2/2]

char32_t utf8::prev	(	std::string::const_iterator &	ptr,
		const std::string::const_iterator	first
	)

Decrements an iterator to previous UTF-8 character.

Parameters

ptr	iterator to be decremented
first	iterator pointing to beginning of string

Returns

previous UTF-8 encoded character

If the string contains an invalid UTF-8 encoding, the function returns REPLACEMENT_CHARACTER (0xfffd) and iterator remains unchanged.

valid_str()

bool utf8::valid_str	(	const char *	s,
		size_t	nch
	)

Verifies if string is a valid UTF-8 string.

Parameters

s	pointer to character string to verify
nch	number of characters to verify or 0 if string is null-terminated

Returns

true if string is a valid UTF-8 encoded string, false otherwise