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

Macros
#define	ERRORS_TO_CP1252 1

#define	ERRORS_TO_ISO8859_1 1

#define	NBC 0xFFFF + 1

#define	STRICT_RFC3629 0

Functions
FL_EXPORT int	fl_access (const char *f, int mode)

FL_EXPORT int	fl_chmod (const char *f, int mode)

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

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

FL_EXPORT char *	fl_getcwd (char *buf, int maxlen)

FL_EXPORT char *	fl_getenv (const char *name)

FL_EXPORT char	fl_make_path (const char *path)

FL_EXPORT void	fl_make_path_for_file (const char *path)

FL_EXPORT int	fl_mkdir (const char *f, int mode)

FL_EXPORT unsigned int	fl_nonspacing (unsigned int ucs)
	returns true if the character is non-spacing. More...

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

FL_EXPORT int	fl_rename (const char f, const char t)

FL_EXPORT int	fl_rmdir (const char *f)

FL_EXPORT int	fl_stat (const char path, struct stat buffer)

FL_EXPORT int	fl_system (const char *f)

FL_EXPORT int	fl_tolower (unsigned int ucs)
	return the Unicode lower case value of `ucs`

FL_EXPORT int	fl_toupper (unsigned int ucs)
	return the Unicode upper case value of `ucs`

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

FL_EXPORT int	fl_unlink (const char *f)

FL_EXPORT char *	fl_utf2mbcs (const char *s)
	converts UTF8 to a local multi-byte character string.

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

FL_EXPORT int	fl_utf8bytes (unsigned ucs)
	Return the number of bytes needed to encode the given UCS4 character in UTF8. More...

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

FL_EXPORT int	fl_utf8encode (unsigned ucs, char *buf)

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

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

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

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

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

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

FL_EXPORT int	fl_utf8locale ()

FL_EXPORT int	fl_utf8test (const char *src, unsigned len)

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

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

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

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

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

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

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

FL_EXPORT int	fl_utf_tolower (const unsigned char str, int len, char buf)
	converts the str string to the lower case equivalent into buf. More...

FL_EXPORT int	fl_utf_toupper (const unsigned char str, int len, char buf)
	converts the str string to the upper case equivalent into buf. More...

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

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

Detailed Description

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

Macro Definition Documentation

#define ERRORS_TO_CP1252 1

Set to 1 to turn bad UTF8 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.

#define ERRORS_TO_ISO8859_1 1

Set to 1 to turn bad UTF8 bytes into ISO-8859-1. If this is to 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.

#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

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 under the MSWindows 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().

unsigned int fl_nonspacing ( unsigned int ucs )

returns true if the character is non-spacing.

Todo:: explain what non-spacing means.

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

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

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

Parameters

f	the UTF-8 encoded filename
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().

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.

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.

int fl_utf8bytes ( unsigned ucs )

Return the number of bytes needed to encode the given UCS4 character in UTF8.

Parameters

[in] ucs UCS4 encoded character

Returns: number of bytes required

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

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 is 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 utf8 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.

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.

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.

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.

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.

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 utf8 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 algorithim can handle the pointer moving. Do not use this to scan strings, use fl_utf8decode() instead.

int fl_utf8len ( char c )

return 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 UTF8 sequences.

See Also: fl_utf8len1

int fl_utf8len1 ( char c )

Return 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 UTF8 sequence, albeit ignoring invalid codes.

See Also: fl_utf8len

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.

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.

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.

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 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 CP1512 on Windows).

src points at the UTF-8, 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.

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).

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.

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

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

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

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 utf8 strings to compare
n	the maximum number of utf8 characters to compare

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

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

converts the str string to the lower case equivalent into buf.

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

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

converts the str string to the upper case equivalent into buf.

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

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.

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

Function Documentation