fl global Unicode and UTF-8 handling functions declared in <FL/fl_utf8.h> More...

Macros
#define	ERRORS_TO_CP1252 1
	Set to 1 to turn bad UTF-8 bytes in the 0x80-0x9f range into the Unicode index for Microsoft's CP1252 character set.

#define	ERRORS_TO_ISO8859_1 1
	Set to 1 to turn bad UTF-8 bytes into ISO-8859-1.

#define	NBC 0xFFFF + 1

#define	STRICT_RFC3629 0
	A number of Unicode code points are in fact illegal and should not be produced by a UTF-8 converter.

Functions
int	fl_access (const char *f, int mode)
	Cross-platform function to test a files access() with a UTF-8 encoded name or value.

int	fl_chdir (const char *path)
	Cross-platform function to change the current working directory, given as a UTF-8 encoded string.

int	fl_chmod (const char *f, int mode)
	Cross-platform function to set a files mode() with a UTF-8 encoded name or value.

int	fl_close_fd (int fd)
	Cross-platform function to close a file descriptor.

int	fl_execvp (const char file, char const *argv)

FILE *	fl_fopen (const char f, const char mode)
	Cross-platform function to open files with a UTF-8 encoded name.

char *	fl_getcwd (char *buf, int len)
	Cross-platform function to get the current working directory as a UTF-8 encoded value.

char *	fl_getenv (const char *v)
	Cross-platform function to get environment variables with a UTF-8 encoded name or value.

char	fl_make_path (const char *path)
	Cross-platform function to recursively create a path in the file system.

void	fl_make_path_for_file (const char *path)
	Cross-platform function to create a path for the file in the file system.

int	fl_mkdir (const char *f, int mode)
	Cross-platform function to create a directory with a UTF-8 encoded name.

unsigned int	fl_nonspacing (unsigned int ucs)
	Returns true if the Unicode character `ucs` is non-spacing.

int	fl_open (const char *fname, int oflags,...)
	Cross-platform function to open files with a UTF-8 encoded name.

int	fl_open_ext (const char *fname, int binary, int oflags,...)
	Cross-platform function to open files with a UTF-8 encoded name.

int	fl_putenv (const char *var)
	Cross-platform function to write environment variables with a UTF-8 encoded name or value.

int	fl_rename (const char f, const char n)
	Cross-platform function to rename a filesystem object using UTF-8 encoded names.

int	fl_rmdir (const char *f)
	Cross-platform function to remove a directory with a UTF-8 encoded name.

int	fl_stat (const char f, struct stat b)
	Cross-platform function to stat() a file using a UTF-8 encoded name or value.

int	fl_system (const char *cmd)
	Cross-platform function to run a system command with a UTF-8 encoded string.

int	fl_tolower (unsigned int ucs)
	Returns the Unicode lower case value of `ucs`.

int	fl_toupper (unsigned int ucs)
	Returns the Unicode upper case value of `ucs`.

unsigned	fl_ucs_to_Utf16 (const unsigned ucs, unsigned short *dst, const unsigned dstlen)
	Convert a single 32-bit Unicode codepoint into an array of 16-bit characters.

int	fl_unlink (const char *fname)
	Cross-platform function to unlink() (that is, delete) a file using a UTF-8 encoded filename.

char *	fl_utf2mbcs (const char *s)
	Converts UTF-8 string `s` to a local multi-byte character string.

const char *	fl_utf8back (const char p, const char start, const char *end)
	Move `p` backward until it points to the start of a UTF-8 character.

int	fl_utf8bytes (unsigned ucs)
	Return the number of bytes needed to encode the given UCS4 character in UTF-8.

unsigned	fl_utf8decode (const char p, const char end, int *len)
	Decode a single UTF-8 encoded character starting at p.

int	fl_utf8encode (unsigned ucs, char *buf)
	Write the UTF-8 encoding of ucs into buf and return the number of bytes written.

unsigned	fl_utf8from_mb (char dst, unsigned dstlen, const char src, unsigned srclen)
	Convert a filename from the locale-specific multibyte encoding used by Windows to UTF-8 as used by FLTK.

unsigned	fl_utf8froma (char dst, unsigned dstlen, const char src, unsigned srclen)
	Convert an ISO-8859-1 (ie normal c-string) byte stream to UTF-8.

unsigned	fl_utf8fromwc (char dst, unsigned dstlen, const wchar_t src, unsigned srclen)
	Turn "wide characters" as returned by some system calls (especially on Windows) into UTF-8.

const char *	fl_utf8fwd (const char p, const char start, const char *end)
	Move `p` forward until it points to the start of a UTF-8 character.

int	fl_utf8len (char c)
	Returns the byte length of the UTF-8 sequence with first byte `c`, or -1 if `c` is not valid.

int	fl_utf8len1 (char c)
	Returns the byte length of the UTF-8 sequence with first byte `c`, or 1 if `c` is not valid.

int	fl_utf8locale ()
	Return true if the "locale" seems to indicate that UTF-8 encoding is used.

int	fl_utf8strlen (const char *text, int len)
	Return the length in bytes of a UTF-8 string.

int	fl_utf8test (const char *src, unsigned srclen)
	Examines the first `srclen` bytes in `src` and returns a verdict on whether it is UTF-8 or not.

unsigned	fl_utf8to_mb (const char src, unsigned srclen, char dst, unsigned dstlen)
	Convert the UTF-8 used by FLTK to the locale-specific encoding used for filenames (and sometimes used for data in files).

unsigned	fl_utf8toa (const char src, unsigned srclen, char dst, unsigned dstlen)
	Convert a UTF-8 sequence into an array of 1-byte characters.

unsigned	fl_utf8toUtf16 (const char src, unsigned srclen, unsigned short dst, unsigned dstlen)
	Convert a UTF-8 sequence into an array of 16-bit characters.

unsigned	fl_utf8towc (const char src, unsigned srclen, wchar_t dst, unsigned dstlen)
	Converts a UTF-8 string into a wide character string.

int	fl_utf_nb_char (const unsigned char *buf, int len)
	Returns the number of Unicode chars in the UTF-8 string.

int	fl_utf_strcasecmp (const char s1, const char s2)
	UTF-8 aware strcasecmp - converts to Unicode and tests.

int	fl_utf_strncasecmp (const char s1, const char s2, int n)
	UTF-8 aware strncasecmp - converts to lower case Unicode and tests.

int	fl_utf_tolower (const unsigned char str, int len, char buf)
	Converts the string `str` to its lower case equivalent into buf.

int	fl_utf_toupper (const unsigned char str, int len, char buf)
	Converts the string `str` to its upper case equivalent into buf.

int	fl_wcwidth (const char *src)
	extended wrapper around fl_wcwidth_(unsigned int ucs) function.

int	fl_wcwidth_ (unsigned int ucs)
	Wrapper to adapt Markus Kuhn's implementation of wcwidth() for FLTK.

Detailed Description

fl global Unicode and UTF-8 handling functions declared in <FL/fl_utf8.h>

Macro Definition Documentation

◆ ERRORS_TO_CP1252

#define ERRORS_TO_CP1252 1

Set to 1 to turn bad UTF-8 bytes in the 0x80-0x9f range into the Unicode index for Microsoft's CP1252 character set.

You should also set ERRORS_TO_ISO8859_1. With this a huge amount of more available text (such as all web pages) are correctly converted to Unicode.

◆ ERRORS_TO_ISO8859_1

#define ERRORS_TO_ISO8859_1 1

Set to 1 to turn bad UTF-8 bytes into ISO-8859-1.

If this is zero they are instead turned into the Unicode REPLACEMENT CHARACTER, of value 0xfffd. If this is on fl_utf8decode() will correctly map most (perhaps all) human-readable text that is in ISO-8859-1. This may allow you to completely ignore character sets in your code because virtually everything is either ISO-8859-1 or UTF-8.

◆ STRICT_RFC3629

#define STRICT_RFC3629 0

A number of Unicode code points are in fact illegal and should not be produced by a UTF-8 converter.

Turn this on will replace the bytes in those encodings with errors. If you do this then converting arbitrary 16-bit data to UTF-8 and then back is not an identity, which will probably break a lot of software.

Function Documentation

◆ fl_access()

int fl_access	(	const char *	f,
		int	mode
	)

Cross-platform function to test a files access() with a UTF-8 encoded name or value.

This function is especially useful on the Windows platform where the standard access() function fails with UTF-8 encoded non-ASCII filenames.

Windows defines the mode values 0 for existence, 2 for writable, 4 for readable, and 6 of readable and writable. On other systems, the modes X_OK, W_OK, and R_OK are usually defined as 1, 2, and 4.

Upon successful completion, the value 0 is returned on all platforms.

Parameters

[in]	f	the UTF-8 encoded filename
[in]	mode	the mode to test

Returns: the return value of _waccess() on Windows or access() on other platforms.

◆ fl_chdir()

int fl_chdir ( const char * path )

Cross-platform function to change the current working directory, given as a UTF-8 encoded string.

This function is especially useful on the Windows platform where the standard _wchdir() function needs a path in UTF-16 encoding.

The path is converted to a system specific encoding if necessary and the system specific chdir(converted_path) function is called.

The function returns 0 on success and -1 on error. Depending on the platform, errno may be set if an error occurs.

Note: The possible errno values are platform specific. Refer to the documentation of the platform specific chdir() function.

If the function is not implemented on a particular platform the default implementation returns -1 and errno is not set.

If the path is NULL the function returns -1, but errno is not changed. This is a convenience feature of fl_chdir() as opposed to chdir().

Parameters

[in] path the target directory for chdir (may be NULL)

Returns: 0 if successful, -1 on error (errno may be set)

◆ fl_chmod()

int fl_chmod	(	const char *	f,
		int	mode
	)

Cross-platform function to set a files mode() with a UTF-8 encoded name or value.

This function is especially useful on the Windows platform where the standard chmod() function fails with UTF-8 encoded non-ASCII filenames.

Parameters

[in]	f	the UTF-8 encoded filename
[in]	mode	the mode to set

Returns: the return value of _wchmod() on Windows or chmod() on other platforms.

◆ fl_close_fd()

int fl_close_fd ( int fd )

Cross-platform function to close a file descriptor.

Returns: 0 in case of success, or -1 in case of error.

◆ fl_fopen()

FILE * fl_fopen	(	const char *	f,
		const char *	mode
	)

Cross-platform function to open files with a UTF-8 encoded name.

This function is especially useful on the Windows platform where the standard fopen() function fails with UTF-8 encoded non-ASCII filenames.

Parameters

f	the UTF-8 encoded filename
mode	same as the second argument of the standard fopen() function

Returns: a FILE pointer upon successful completion, or NULL in case of error.

See also: fl_open().

◆ fl_getcwd()

char * fl_getcwd	(	char *	buf,
		int	len
	)

Cross-platform function to get the current working directory as a UTF-8 encoded value.

This function is especially useful on the Windows platform where the standard _wgetcwd() function returns UTF-16 encoded non-ASCII filenames.

If buf is NULL a buffer of size (len+1) is allocated, filled with the current working directory, and returned. In this case the buffer must be released by the caller with free() to prevent memory leaks.

Parameters

[in]	buf	the buffer to populate (may be NULL)
[in]	len	the length of the buffer

Returns: the CWD encoded as UTF-8

◆ fl_getenv()

char * fl_getenv ( const char * v )

Cross-platform function to get environment variables with a UTF-8 encoded name or value.

This function is especially useful on the Windows platform where non-ASCII environment variables are encoded as wide characters. The returned value of the variable is encoded in UTF-8 as well.

On platforms other than Windows this function calls getenv directly. The return value is returned as-is.

The return value is a pointer to an implementation defined buffer:

an internal buffer that is (re)allocated as needed (Windows) or
the string in the environment itself (Unix, Linux, MaOS) or
any other implementation (other platforms). This string must be considered read-only and must not be freed by the caller.

If the resultant string is to be used later it must be copied to a safe place. The next call to fl_getenv() or any other environment changes may overwrite the string.

Note: This function is not thread-safe.

Parameters

[in] v the UTF-8 encoded environment variable

Returns: the environment variable in UTF-8 encoding, or NULL in case of error.

◆ fl_make_path()

char fl_make_path ( const char * path )

Cross-platform function to recursively create a path in the file system.

This function creates a path in the file system by recursively creating all directories.

Parameters

[in] path a Unix style ('/' forward slashes) absolute or relative pathname

Returns: 1 if the path was created, 0 if creating the path failed at some point

◆ fl_make_path_for_file()

void fl_make_path_for_file ( const char * path )

Cross-platform function to create a path for the file in the file system.

This function strips the filename from the given path and creates a path in the file system by recursively creating all directories.

◆ fl_mkdir()

int fl_mkdir	(	const char *	f,
		int	mode
	)

Cross-platform function to create a directory with a UTF-8 encoded name.

This function is especially useful on the Windows platform where the standard _wmkdir() function expects UTF-16 encoded non-ASCII filenames.

Parameters

[in]	f	the UTF-8 encoded filename
[in]	mode	the mode of the directory

Returns: the return value of _wmkdir() on Windows or mkdir() on other platforms.

◆ fl_nonspacing()

unsigned int fl_nonspacing ( unsigned int ucs )

Returns true if the Unicode character ucs is non-spacing.

Non-spacing characters in Unicode are typically combining marks like tilde (~), diaeresis (¨), or other marks that are added to a base character, for instance 'a' (base character) + '¨' (combining mark) = 'ä' (German Umlaut).

◆ fl_open()

int fl_open	(	const char *	fname,
		int	oflags,
			...
	)

Cross-platform function to open files with a UTF-8 encoded name.

This function is especially useful on the Windows platform where the standard open() function fails with UTF-8 encoded non-ASCII filenames.

Parameters

[in]	fname	the UTF-8 encoded filename
[in]	oflags	other arguments are as in the standard open() function

Returns: a file descriptor upon successful completion, or -1 in case of error.

See also: fl_fopen(), fl_open_ext(), fl_close_fd(int fd).

◆ fl_open_ext()

int fl_open_ext	(	const char *	fname,
		int	binary,
		int	oflags,
			...
	)

Cross-platform function to open files with a UTF-8 encoded name.

In comparison with fl_open(), this function allows to control whether the file is opened in binary (a.k.a. untranslated) mode. This is especially useful on the Windows platform where files are by default opened in text (translated) mode.

Parameters

[in]	fname	the UTF-8 encoded filename
[in]	binary	if non-zero, the file is to be accessed in binary (a.k.a. untranslated) mode.
[in]	oflags,...	these arguments are as in the standard open() function. Setting `oflags` to zero opens the file for reading.

Returns: a file descriptor upon successful completion, or -1 in case of error.

◆ fl_putenv()

int fl_putenv ( const char * var )

Cross-platform function to write environment variables with a UTF-8 encoded name or value.

This function is especially useful on the Windows platform where non-ASCII environment variables are encoded as wide characters.

The given argument var must be encoded in UTF-8 in the form "name=value". The 'name' part must conform to platform dependent restrictions on environment variable names.

The string given in var is copied and optionally converted to the required encoding for the platform. On platforms other than Windows this function calls putenv directly.

The return value is zero on success and non-zero in case of error. The value in case of error is platform specific and returned as-is.

Note: The copied string is allocated on the heap and "lost" on some platforms, i.e. calling fl_putenv() to change environment variables frequently may cause memory leaks. There may be an option to avoid this in a future implementation.; This function is not thread-safe.

Parameters

[in] var the UTF-8 encoded environment variable 'name=value'

Returns: 0 on success, non-zero in case of error.

◆ fl_rename()

int fl_rename	(	const char *	f,
		const char *	n
	)

Cross-platform function to rename a filesystem object using UTF-8 encoded names.

This function is especially useful on the Windows platform where the standard _wrename() function expects UTF-16 encoded non-ASCII filenames.

Parameters

[in]	f	the UTF-8 encoded filename to change
[in]	n	the new UTF-8 encoded filename to set

Returns: the return value of _wrename() on Windows or rename() on other platforms.

◆ fl_rmdir()

int fl_rmdir ( const char * f )

Cross-platform function to remove a directory with a UTF-8 encoded name.

This function is especially useful on the Windows platform where the standard _wrmdir() function expects UTF-16 encoded non-ASCII filenames.

Parameters

[in] f the UTF-8 encoded filename to remove

Returns: the return value of _wrmdir() on Windows or rmdir() on other platforms.

◆ fl_stat()

int fl_stat	(	const char *	f,
		struct stat *	b
	)

Cross-platform function to stat() a file using a UTF-8 encoded name or value.

This function is especially useful on the Windows platform where the standard stat() function fails with UTF-8 encoded non-ASCII filenames.

Parameters

[in]	f	the UTF-8 encoded filename
	b	the stat struct to populate

Returns: the return value of _wstat() on Windows or stat() on other platforms.

◆ fl_system()

int fl_system ( const char * cmd )

Cross-platform function to run a system command with a UTF-8 encoded string.

This function is especially useful on the Windows platform where non-ASCII program (file) names must be encoded as wide characters.

On platforms other than Windows this function calls system() directly.

Parameters

[in] cmd the UTF-8 encoded command string

Returns: the return value of _wsystem() on Windows or system() on other platforms.

◆ fl_ucs_to_Utf16()

unsigned fl_ucs_to_Utf16	(	const unsigned	ucs,
		unsigned short *	dst,
		const unsigned	dstlen
	)

Convert a single 32-bit Unicode codepoint into an array of 16-bit characters.

These are used by some system calls, especially on Windows.

ucs is the value to convert.

dst points at an array to write, and dstlen is the number of locations in this array. At most dstlen words will be written, and a 0 terminating word will be added if dstlen is large enough. Thus this function will never overwrite the buffer and will attempt return a zero-terminated string if space permits. If dstlen is zero then dst can be set to NULL and no data is written, but the length is returned.

The return value is the number of 16-bit words that would be written to dst if it is large enough, not counting any terminating zero.

If the return value is greater than dstlen it indicates truncation, you should then allocate a new array of size return+1 and call this again.

Unicode characters in the range 0x10000 to 0x10ffff are converted to "surrogate pairs" which take two words each (in UTF-16 encoding). Typically, setting dstlen to 2 will ensure that any valid Unicode value can be converted, and setting dstlen to 3 or more will allow a NULL terminated sequence to be returned.

◆ fl_unlink()

int fl_unlink ( const char * fname )

Cross-platform function to unlink() (that is, delete) a file using a UTF-8 encoded filename.

This function is especially useful on the Windows platform where the standard function expects UTF-16 encoded non-ASCII filenames.

Parameters

fname the filename to unlink

Returns: the return value of _wunlink() on Windows or unlink() on other platforms.

◆ fl_utf8back()

const char * fl_utf8back	(	const char *	p,
		const char *	start,
		const char *	end
	)

Move p backward until it points to the start of a UTF-8 character.

If it already points at the start of one then it is returned unchanged. Any UTF-8 errors are treated as though each byte of the error is an individual character.

start is the start of the string and is used to limit the backwards search for the start of a UTF-8 character.

end is the end of the string and is assumed to be a break between characters. It is assumed to be greater than p.

If you wish to decrement a UTF-8 pointer, pass p-1 to this.

◆ fl_utf8bytes()

int fl_utf8bytes ( unsigned ucs )

Return the number of bytes needed to encode the given UCS4 character in UTF-8.

Returns number of bytes that utf8encode() will use to encode the character ucs.

Parameters

[in] ucs UCS4 encoded character

Returns: number of bytes required

◆ fl_utf8decode()

unsigned fl_utf8decode	(	const char *	p,
		const char *	end,
		int *	len
	)

Decode a single UTF-8 encoded character starting at p.

The resulting Unicode value (in the range 0-0x10ffff) is returned, and len is set to the number of bytes in the UTF-8 encoding (adding len to p will point at the next character).

If p points at an illegal UTF-8 encoding, including one that would go past end, or where a code uses more bytes than necessary, then *(unsigned char*)p is translated as though it is in the Microsoft CP1252 character set and len is set to 1. Treating errors this way allows this to decode almost any ISO-8859-1 or CP1252 text that has been mistakenly placed where UTF-8 is expected, and has proven very useful.

If you want errors to be converted to error characters (as the standards recommend), adding a test to see if the length is unexpectedly 1 will work:

if (*p & 0x80) {              // what should be a multibyte encoding
  code = fl_utf8decode(p,end,&len);
  if (len<2) code = 0xFFFD;   // Turn errors into REPLACEMENT CHARACTER
} else {                      // handle the 1-byte UTF-8 encoding:
  code = *p;
  len = 1;
}

Direct testing for the 1-byte case (as shown above) will also speed up the scanning of strings where the majority of characters are ASCII.

◆ fl_utf8encode()

int fl_utf8encode	(	unsigned	ucs,
		char *	buf
	)

Write the UTF-8 encoding of ucs into buf and return the number of bytes written.

Up to 4 bytes may be written. If you know that ucs is less than 0x10000 then at most 3 bytes will be written. If you wish to speed this up, remember that anything less than 0x80 is written as a single byte.

If ucs is greater than 0x10ffff this is an illegal character according to RFC 3629. These are converted as though they are 0xFFFD (REPLACEMENT CHARACTER).

RFC 3629 also says many other values for ucs are illegal (in the range 0xd800 to 0xdfff, or ending with 0xfffe or 0xffff). However I encode these as though they are legal, so that utf8encode/fl_utf8decode will be the identity for all codes between 0 and 0x10ffff.

◆ fl_utf8from_mb()

unsigned fl_utf8from_mb	(	char *	dst,
		unsigned	dstlen,
		const char *	src,
		unsigned	srclen
	)

Convert a filename from the locale-specific multibyte encoding used by Windows to UTF-8 as used by FLTK.

Up to dstlen bytes are written to dst, including a null terminator. The return value is the number of bytes that would be written, not counting the null terminator. If greater or equal to dstlen then if you malloc a new array of size n+1 you will have the space needed for the entire string. If dstlen is zero then nothing is written and this call just measures the storage space needed.

On Unix or on Windows when a UTF-8 locale is in effect, this does not change the data. You may also want to check if fl_utf8test() returns non-zero, so that the filesystem can store filenames in UTF-8 encoding regardless of the locale.

◆ fl_utf8froma()

unsigned fl_utf8froma	(	char *	dst,
		unsigned	dstlen,
		const char *	src,
		unsigned	srclen
	)

Convert an ISO-8859-1 (ie normal c-string) byte stream to UTF-8.

It is possible this should convert Microsoft's CP1252 to UTF-8 instead. This would translate the codes in the range 0x80-0x9f to different characters. Currently it does not do this.

Up to dstlen bytes are written to dst, including a null terminator. The return value is the number of bytes that would be written, not counting the null terminator. If greater or equal to dstlen then if you malloc a new array of size n+1 you will have the space needed for the entire string. If dstlen is zero then nothing is written and this call just measures the storage space needed.

srclen is the number of bytes in src to convert.

If the return value equals srclen then this indicates that no conversion is necessary, as only ASCII characters are in the string.

◆ fl_utf8fromwc()

unsigned fl_utf8fromwc	(	char *	dst,
		unsigned	dstlen,
		const wchar_t *	src,
		unsigned	srclen
	)

Turn "wide characters" as returned by some system calls (especially on Windows) into UTF-8.

Up to dstlen bytes are written to dst, including a null terminator. The return value is the number of bytes that would be written, not counting the null terminator. If greater or equal to dstlen then if you malloc a new array of size n+1 you will have the space needed for the entire string. If dstlen is zero then nothing is written and this call just measures the storage space needed.

srclen is the number of words in src to convert. On Windows this is not necessarily the number of characters, due to there possibly being "surrogate pairs" in the UTF-16 encoding used. On Unix wchar_t is 32 bits and each location is a character.

On Unix if a src word is greater than 0x10ffff then this is an illegal character according to RFC 3629. These are converted as though they are 0xFFFD (REPLACEMENT CHARACTER). Characters in the range 0xd800 to 0xdfff, or ending with 0xfffe or 0xffff are also illegal according to RFC 3629. However I encode these as though they are legal, so that fl_utf8towc will return the original data.

On Windows "surrogate pairs" are converted to a single character and UTF-8 encoded (as 4 bytes). Mismatched halves of surrogate pairs are converted as though they are individual characters.

◆ fl_utf8fwd()

const char * fl_utf8fwd	(	const char *	p,
		const char *	start,
		const char *	end
	)

Move p forward until it points to the start of a UTF-8 character.

If it already points at the start of one then it is returned unchanged. Any UTF-8 errors are treated as though each byte of the error is an individual character.

start is the start of the string and is used to limit the backwards search for the start of a UTF-8 character.

end is the end of the string and is assumed to be a break between characters. It is assumed to be greater than p.

This function is for moving a pointer that was jumped to the middle of a string, such as when doing a binary search for a position. You should use either this or fl_utf8back() depending on which direction your algorithm can handle the pointer moving. Do not use this to scan strings, use fl_utf8decode() instead.

◆ fl_utf8len()

int fl_utf8len ( char c )

Returns the byte length of the UTF-8 sequence with first byte c, or -1 if c is not valid.

This function is helpful for finding faulty UTF-8 sequences.

See also: fl_utf8len1

◆ fl_utf8len1()

int fl_utf8len1 ( char c )

Returns the byte length of the UTF-8 sequence with first byte c, or 1 if c is not valid.

This function can be used to scan faulty UTF-8 sequences, albeit ignoring invalid codes.

See also: fl_utf8len

◆ fl_utf8locale()

int fl_utf8locale ( void )

Return true if the "locale" seems to indicate that UTF-8 encoding is used.

If true the fl_utf8to_mb and fl_utf8from_mb don't do anything useful.

It is highly recommended that you change your system so this does return true. On Windows this is done by setting the "codepage" to CP_UTF8. On Unix this is done by setting $LC_CTYPE to a string containing the letters "utf" or "UTF" in it, or by deleting all $LC* and $LANG environment variables. In the future it is likely that all non-Asian Unix systems will return true, due to the compatibility of UTF-8 with ISO-8859-1.

◆ fl_utf8strlen()

int fl_utf8strlen	(	const char *	text,
		int	len
	)

Return the length in bytes of a UTF-8 string.

Parameters

[in]	text	encoded in UTF-8
[in]	len	number of Unicode characters, -1 to test until the end of text

Returns: number of bytes that make up the Unicode string

See also: fl_utf_nb_char(const unsigned char *buf, int len)

◆ fl_utf8test()

int fl_utf8test	(	const char *	src,
		unsigned	srclen
	)

Examines the first srclen bytes in src and returns a verdict on whether it is UTF-8 or not.

Returns 0 if there is any illegal UTF-8 sequences, using the same rules as fl_utf8decode(). Note that some UCS values considered illegal by RFC 3629, such as 0xffff, are considered legal by this.
Returns 1 if there are only single-byte characters (ie no bytes have the high bit set). This is legal UTF-8, but also indicates plain ASCII. It also returns 1 if srclen is zero.
Returns 2 if there are only characters less than 0x800.
Returns 3 if there are only characters less than 0x10000.
Returns 4 if there are characters in the 0x10000 to 0x10ffff range.

Because there are many illegal sequences in UTF-8, it is almost impossible for a string in another encoding to be confused with UTF-8. This is very useful for transitioning Unix to UTF-8 filenames, you can simply test each filename with this to decide if it is UTF-8 or in the locale encoding. My hope is that if this is done we will be able to cleanly transition to a locale-less encoding.

◆ fl_utf8to_mb()

unsigned fl_utf8to_mb	(	const char *	src,
		unsigned	srclen,
		char *	dst,
		unsigned	dstlen
	)

Convert the UTF-8 used by FLTK to the locale-specific encoding used for filenames (and sometimes used for data in files).

Unfortunately due to stupid design you will have to do this as needed for filenames. This is a bug on both Unix and Windows.

Up to dstlen bytes are written to dst, including a null terminator. The return value is the number of bytes that would be written, not counting the null terminator. If greater or equal to dstlen then if you malloc a new array of size n+1 you will have the space needed for the entire string. If dstlen is zero then nothing is written and this call just measures the storage space needed.

If fl_utf8locale() returns true then this does not change the data.

◆ fl_utf8toa()

unsigned fl_utf8toa	(	const char *	src,
		unsigned	srclen,
		char *	dst,
		unsigned	dstlen
	)

Convert a UTF-8 sequence into an array of 1-byte characters.

If the UTF-8 decodes to a character greater than 0xff then it is replaced with '?'.

Errors in the UTF-8 sequence are converted as individual bytes, same as fl_utf8decode() does. This allows ISO-8859-1 text mistakenly identified as UTF-8 to be printed correctly (and possibly CP1252 on Windows).

src points at the UTF-8 sequence, and srclen is the number of bytes to convert.

Up to dstlen bytes are written to dst, including a null terminator. The return value is the number of bytes that would be written, not counting the null terminator. If greater or equal to dstlen then if you malloc a new array of size n+1 you will have the space needed for the entire string. If dstlen is zero then nothing is written and this call just measures the storage space needed.

◆ fl_utf8toUtf16()

unsigned fl_utf8toUtf16	(	const char *	src,
		unsigned	srclen,
		unsigned short *	dst,
		unsigned	dstlen
	)

Convert a UTF-8 sequence into an array of 16-bit characters.

These are used by some system calls, especially on Windows.

src points at the UTF-8, and srclen is the number of bytes to convert.

dst points at an array to write, and dstlen is the number of locations in this array. At most dstlen-1 words will be written there, plus a 0 terminating word. Thus this function will never overwrite the buffer and will always return a zero-terminated string. If dstlen is zero then dst can be null and no data is written, but the length is returned.

The return value is the number of 16-bit words that would be written to dst if it were long enough, not counting the terminating zero. If the return value is greater or equal to dstlen it indicates truncation, you can then allocate a new array of size return+1 and call this again.

Errors in the UTF-8 are converted as though each byte in the erroneous string is in the Microsoft CP1252 encoding. This allows ISO-8859-1 text mistakenly identified as UTF-8 to be printed correctly.

Unicode characters in the range 0x10000 to 0x10ffff are converted to "surrogate pairs" which take two words each (this is called UTF-16 encoding).

◆ fl_utf8towc()

unsigned fl_utf8towc	(	const char *	src,
		unsigned	srclen,
		wchar_t *	dst,
		unsigned	dstlen
	)

Converts a UTF-8 string into a wide character string.

This function generates 32-bit wchar_t (e.g. "ucs4" as it were) except on Windows where it is equivalent to fl_utf8toUtf16 and returns UTF-16.

src points at the UTF-8, and srclen is the number of bytes to convert.

dst points at an array to write, and dstlen is the number of locations in this array. At most dstlen-1 wchar_t will be written there, plus a 0 terminating wchar_t.

The return value is the number of wchar_t that would be written to dst if it were long enough, not counting the terminating zero. If the return value is greater or equal to dstlen it indicates truncation, you can then allocate a new array of size return+1 and call this again.

Notice that sizeof(wchar_t) is 2 on Windows and is 4 on Linux and most other systems. Where wchar_t is 16 bits, Unicode characters in the range 0x10000 to 0x10ffff are converted to "surrogate pairs" which take two words each (this is called UTF-16 encoding). If wchar_t is 32 bits this rather nasty problem is avoided.

Note that Windows includes Cygwin, i.e. compiled with Cygwin's POSIX layer (cygwin1.dll, –enable-cygwin), either native (GDI) or X11.

◆ fl_utf_nb_char()

int fl_utf_nb_char	(	const unsigned char *	buf,
		int	len
	)

Returns the number of Unicode chars in the UTF-8 string.

See also: fl_utf8strlen(const char *text, int len)

◆ fl_utf_strcasecmp()

int fl_utf_strcasecmp	(	const char *	s1,
		const char *	s2
	)

UTF-8 aware strcasecmp - converts to Unicode and tests.

Returns: result of comparison

Return values

0	if the strings are equal
1	if s1 is greater than s2
-1	if s1 is less than s2

◆ fl_utf_strncasecmp()

int fl_utf_strncasecmp	(	const char *	s1,
		const char *	s2,
		int	n
	)

UTF-8 aware strncasecmp - converts to lower case Unicode and tests.

Parameters

s1,s2	the UTF-8 strings to compare
n	the maximum number of UTF-8 characters to compare

Returns: result of comparison

Return values

0	if the strings are equal
>0	if s1 is greater than s2
<0	if s1 is less than s2

◆ fl_utf_tolower()

int fl_utf_tolower	(	const unsigned char *	str,
		int	len,
		char *	buf
	)

Converts the string str to its lower case equivalent into buf.

Warning: to be safe buf length must be at least 3 * len [for 16-bit Unicode]

◆ fl_utf_toupper()

int fl_utf_toupper	(	const unsigned char *	str,
		int	len,
		char *	buf
	)

Converts the string str to its upper case equivalent into buf.

Warning: to be safe buf length must be at least 3 * len [for 16-bit Unicode]

◆ fl_wcwidth()

int fl_wcwidth ( const char * src )

extended wrapper around fl_wcwidth_(unsigned int ucs) function.

Parameters

[in] src pointer to start of UTF-8 byte sequence

Returns: width of character in columns

Depending on build options, this function may map C1 control characters (0x80 to 0x9f) to CP1252, and return the width of that character instead. This is not the same behaviour as fl_wcwidth_(unsigned int ucs) .

Note that other control characters and DEL will still return -1, so if you want different behaviour, you need to test for those characters before calling fl_wcwidth(), and handle them separately.

◆ fl_wcwidth_()

int fl_wcwidth_ ( unsigned int ucs )

Wrapper to adapt Markus Kuhn's implementation of wcwidth() for FLTK.

Parameters

[in] ucs Unicode character value

Returns: width of character in columns

See http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c for Markus Kuhn's original implementation of wcwidth() and wcswidth() (defined in IEEE Std 1002.1-2001) for Unicode.

WARNING: this function returns widths for "raw" Unicode characters. It does not even try to map C1 control characters (0x80 to 0x9F) to CP1252, and C0/C1 control characters and DEL will return -1. You are advised to use fl_width(const char* src) instead.

Macros

Functions

Detailed Description

Macro Definition Documentation

◆ ERRORS_TO_CP1252

◆ ERRORS_TO_ISO8859_1

◆ STRICT_RFC3629

Function Documentation

◆ fl_access()

◆ fl_chdir()

◆ fl_chmod()

◆ fl_close_fd()

◆ fl_fopen()

◆ fl_getcwd()

◆ fl_getenv()

◆ fl_make_path()

◆ fl_make_path_for_file()

◆ fl_mkdir()

◆ fl_nonspacing()

◆ fl_open()

◆ fl_open_ext()

◆ fl_putenv()

◆ fl_rename()

◆ fl_rmdir()

◆ fl_stat()

◆ fl_system()

◆ fl_ucs_to_Utf16()

◆ fl_unlink()

◆ fl_utf8back()

◆ fl_utf8bytes()

◆ fl_utf8decode()

◆ fl_utf8encode()

◆ fl_utf8from_mb()

◆ fl_utf8froma()

◆ fl_utf8fromwc()

◆ fl_utf8fwd()

◆ fl_utf8len()

◆ fl_utf8len1()

◆ fl_utf8locale()

◆ fl_utf8strlen()

◆ fl_utf8test()

◆ fl_utf8to_mb()

◆ fl_utf8toa()

◆ fl_utf8toUtf16()

◆ fl_utf8towc()

◆ fl_utf_nb_char()

◆ fl_utf_strcasecmp()

◆ fl_utf_strncasecmp()

◆ fl_utf_tolower()

◆ fl_utf_toupper()

◆ fl_wcwidth()

◆ fl_wcwidth_()