utf8.cpp File Reference

Basic UTF-8 Conversion functions. More...

#include <windows.h>
#include <sys/stat.h>
#include <utf8/utf8.h>
#include <vector>
#include <assert.h>

Functions
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 &s)
	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.
std::string	utf8::getcwd ()
	Gets the current working directory.
bool	utf8::splitpath (const std::string &path, char *drive, char *dir, char *fname, char *ext)
	Breaks a path name into components.
bool	utf8::splitpath (const std::string &path, std::string &drive, std::string &dir, std::string &fname, std::string &ext)
	Breaks a path name into components.
bool	utf8::makepath (std::string &path, const std::string &drive, const std::string &dir, const std::string &fname, const std::string &ext)
	Creates a path from UTF-8 encoded components.
std::string	utf8::fullpath (const std::string &relpath)
	Returns the absolute (full) path of a filename.
std::string	utf8::getenv (const std::string &var)
	Retrieves the value of an environment variable.
char **	utf8::get_argv (int *argc)
	Converts wide byte command arguments to an array of pointers to UTF-8 strings.
void	utf8::free_argv (int argc, char **argv)
	Frees the memory allocated by get_argv(int *argc)
std::vector< std::string >	utf8::get_argv ()
	Converts wide byte command arguments to UTF-8 to a vector of UTF-8 strings.
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

free_argv()

void utf8::free_argv	(	int	argc,
		char **	argv
	)

Frees the memory allocated by get_argv(int *argc)

Parameters

argc	number of arguments
argv	array of pointers to arguments

fullpath()

std::string utf8::fullpath

(

const std::string &

relpath

)

Returns the absolute (full) path of a filename.

Parameters

relpath

relative path

get_argv() [1/2]

std::vector< std::string > utf8::get_argv

(

)

Converts wide byte command arguments to UTF-8 to a vector of UTF-8 strings.

Returns

vector of UTF-8 strings. The vector is empty if an error occurred.

get_argv() [2/2]

char ** utf8::get_argv

(

int *

argc

)

Converts wide byte command arguments to an array of pointers to UTF-8 strings.

Parameters

argc	Pointer to an integer that contains number of parameters

Returns

array of pointers to each command line parameter or NULL if an error occurred.

The space allocated for strings and array of pointers should be freed by calling free_utf8argv()

getcwd()

std::string utf8::getcwd

(

)

Gets the current working directory.

Returns

UTF-8 encoded name of working directory

getenv()

std::string utf8::getenv

(

const std::string &

var

)

Retrieves the value of an environment variable.

Parameters

var	name of environment variable

Returns

value of environment variable or an empty string if there is no such environment variable

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

makepath()

bool utf8::makepath	(	std::string &	path,
		const std::string &	drive,
		const std::string &	dir,
		const std::string &	fname,
		const std::string &	ext
	)

Creates a path from UTF-8 encoded components.

Parameters

path	Resulting path (UTF-8 encoded)
drive	drive letter
dir	directory path
fname	filename
ext	extension

Returns

True if successful; false otherwise

If any required syntactic element (colon after drive letter, '\' at end of directory path, colon before extension) is missing, it is automatically added.

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 returns REPLACEMENT_CHARACTER (0xfffd) and advances pointer 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 string contains an invalid UTF-8 encoding, the function returns REPLACEMENT_CHARACTER (0xfffd) and advances pointer 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 returns REPLACEMENT_CHARACTER (0xfffd) and 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.

splitpath() [1/2]

bool utf8::splitpath	(	const std::string &	path,
		char *	drive,
		char *	dir,
		char *	fname,
		char *	ext
	)

Breaks a path name into components.

Parameters

path	UTF-8 encoded full path
drive	drive letter followed by colon (or NULL if not needed)
dir	directory path (or NULL if not needed)
fname	base filename (or NULL if not needed)
ext	file extension including the leading period (.) (or NULL if not needed)

Returns

true if successful, false otherwise Returned strings are converted to UTF-8.

splitpath() [2/2]

bool utf8::splitpath	(	const std::string &	path,
		std::string &	drive,
		std::string &	dir,
		std::string &	fname,
		std::string &	ext
	)

Breaks a path name into components.

Parameters

path	UTF-8 encoded full path
drive	drive letter followed by colon
dir	directory path
fname	base filename
ext	file extension including the leading period (.)

Returned strings are converted to UTF-8.

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