include/libu8/u8ctype.h File Reference

These functions and macros interrogate and transform unicode points. More...

Data Structures
struct	U8_DECOMPOSITION
	struct U8_DECOMPOSITION indicates a mapping between a single Unicode codepoint and an equivalent Unicode sequence. More...
struct	U8_CHARINFO_TABLE
	struct U8_CHARINFO_TABLE is used to store additional character info not provided by the statically defined tables. More...
Defines
#define	u8_isalpha(c)   ((c>=0) && ((u8_getcharinfo(c)) < 6))
	Returns 1 if its argument is an alphabetic unicode point.
#define	u8_islower(c)   ((c>=0) && ((u8_getcharinfo(c)) == U8_LOWER_LETTER))
	Returns 1 if its argument is a lower-case alphabetic unicode point.
#define	u8_isupper(c)
	Returns 1 if its argument is an upper-case alphabetic unicode point.
#define	u8_ismodifier(c)   ((c>=0) && ((u8_getcharinfo(c)) == U8_MODIFIER_LETTER))
	Returns 1 if its argument is modifier unicode point.
#define	u8_isdigit(c)   ((c>=0) && ((u8_getcharinfo(c)) == U8_NUMBER))
	Returns 1 if its argument is numeric digit unicode point.
#define	u8_ispunct(c)
	Returns 1 if its argument is a punctuation character.
#define	u8_isprint(c)
	Returns 1 if its argument is a printing character (letter,digit,punct)
#define	u8_isspace(c)   ((c>=0) && ((u8_getcharinfo(c)) == U8_SEPARATOR))
	Returns 1 if its argument is whitespace unicode point.
#define	u8_ishspace(c)
	Returns 1 if its argument is horizontal whitespace unicode point.
#define	u8_isvspace(c)
	Returns 1 if its argument is horizontal whitespace unicode point.
#define	u8_isctrl(c)   ((c>=0) && ((c<0x20) || ((c>0x7e) && (c<0x9f))))
	Returns 1 if its argument is a standard control character.
#define	u8_isalnum(c)   ((c>=0) && (((u8_getcharinfo(c)) < 6) || (u8_isdigit(c))))
	Returns 1 if its argument is an alphanumeric unicode point.
#define	u8_isxdigit(c)   ((c>=0) && ((c<128) && (isxdigit(c))))
	Returns 1 if its argument is an ASCII hex digit.
#define	u8_isodigit(c)   ((c>=0) && ((c<128) && (isdigit(c)) && (c<'8')))
	Returns 1 if its argument is an ASCII octal digit.
#define	u8_toupper(c)
	Returns a non-lowercase version of a unicode code point.
#define	u8_tolower(c)
	Returns a non-uppercase version of a unicode code point.
#define	u8_digit_weight(c)   ((u8_isdigit(c)) ? ((c<0x10000) ? (u8_getchardata(c)) : (u8_lookup_chardata(c))) : (0))
	Returns the numeric weight of a numeric unicode code point.
Typedefs
typedef struct U8_DECOMPOSITION	U8_DECOMPOSITION
	struct U8_DECOMPOSITION indicates a mapping between a single Unicode codepoint and an equivalent Unicode sequence.
Functions
U8_EXPORT int	u8_entity2code (u8_string name)
	Converts an XML entity name into the corresponding code point.
U8_EXPORT u8_string	u8_code2entity (int code)
	Converts a code point into an XML entity name.
U8_EXPORT int	u8_parse_entity (u8_byte *entity, u8_byte **endp)
	Parses a unicode entity name from a string, recording the endpoint.
U8_EXPORT void	u8_set_charinfo (int n, unsigned char *info, short *data)
	Sets the character information for a particular code point.

---

Detailed Description

These functions and macros interrogate and transform unicode points.

They include standard character predicates (u8_isspace, u8_ispunct, etc) as well as function/macros for changing case and converting to and from XML character entities.

---

Define Documentation

#define u8_digit_weight

(

c

)

((u8_isdigit(c)) ? ((c<0x10000) ? (u8_getchardata(c)) : (u8_lookup_chardata(c))) : (0))

Returns the numeric weight of a numeric unicode code point.

#define u8_isalnum

(

c

)

((c>=0) && (((u8_getcharinfo(c)) < 6) || (u8_isdigit(c))))

Returns 1 if its argument is an alphanumeric unicode point.

#define u8_isalpha

(

c

)

((c>=0) && ((u8_getcharinfo(c)) < 6))

Returns 1 if its argument is an alphabetic unicode point.

#define u8_isctrl

(

c

)

((c>=0) && ((c<0x20) || ((c>0x7e) && (c<0x9f))))

Returns 1 if its argument is a standard control character.

#define u8_isdigit

(

c

)

((c>=0) && ((u8_getcharinfo(c)) == U8_NUMBER))

Returns 1 if its argument is numeric digit unicode point.

#define u8_ishspace

(

c

)

Value:

((c>=0) &&                                      \
   ((c==' ')||(c=='\t')||(c==0x1680)||(c==0x180e)|| \
    ((c>=0x2000)&&(c<0x200b))))

Returns 1 if its argument is horizontal whitespace unicode point.

#define u8_islower

(

c

)

((c>=0) && ((u8_getcharinfo(c)) == U8_LOWER_LETTER))

Returns 1 if its argument is a lower-case alphabetic unicode point.

#define u8_ismodifier

(

c

)

((c>=0) && ((u8_getcharinfo(c)) == U8_MODIFIER_LETTER))

Returns 1 if its argument is modifier unicode point.

#define u8_isodigit

(

c

)

((c>=0) && ((c<128) && (isdigit(c)) && (c<'8')))

Returns 1 if its argument is an ASCII octal digit.

#define u8_ispunct

(

c

)

Value:

((c>=0) &&                                         \
   (((u8_getcharinfo(c)) == U8_GLUE_PUNCTUATION)  || \
    ((u8_getcharinfo(c)) == U8_BREAK_PUNCTUATION) || \
    ((u8_getcharinfo(c)) == U8_SYMBOL)            || \
    ((u8_getcharinfo(c)) == U8_MARK)))

Returns 1 if its argument is a punctuation character.

#define u8_isspace

(

c

)

((c>=0) && ((u8_getcharinfo(c)) == U8_SEPARATOR))

Returns 1 if its argument is whitespace unicode point.

#define u8_isupper

(

c

)

Value:

((c>=0) && \
   (((u8_getcharinfo(c)) == U8_UPPER_LETTER) || \
    ((u8_getcharinfo(c)) == U8_TITLE_LETTER)))

Returns 1 if its argument is an upper-case alphabetic unicode point.

#define u8_isvspace

(

c

)

Value:

((c>=0) &&                                      \
   ((c=='\n')||(c=='\r')||(c==0x0c)||(c==0x0b)||  \
    (c==0x1C)||(c==0x1D)||(c==0x1E)||(c==0x1F)||  \
    (c==0x85)||(c==0x2029)))

Returns 1 if its argument is horizontal whitespace unicode point.

#define u8_isxdigit

(

c

)

((c>=0) && ((c<128) && (isxdigit(c))))

Returns 1 if its argument is an ASCII hex digit.

#define u8_tolower

(

c

)

Value:

((u8_isupper(c)) ? \
   ((c<0x10000) ? (c+(u8_getchardata(c))) : (u8_lookup_chardata(c))) : \
   (c))

Returns a non-uppercase version of a unicode code point.

#define u8_toupper

(

c

)

Value:

((u8_islower(c)) ? \
   ((c<0x10000) ? (c+(u8_getchardata(c))) : (u8_lookup_chardata(c))) : \
   (c))

Returns a non-lowercase version of a unicode code point.

---

Function Documentation

U8_EXPORT u8_string u8_code2entity

(

int

code

)

Converts a code point into an XML entity name.

This falls back to hex codes if neccessary.

Parameters:

code	a unicode code point

Returns:

a mallocd utf-8 (ASCII) name.

U8_EXPORT int u8_entity2code

(

u8_string

name

)

Converts an XML entity name into the corresponding code point.

This returns -1 for unrecognized or invalid entity names.

Parameters:

name	a utf-8 (ASCII) name.

Returns:

a unicode code point or -1 on error.

U8_EXPORT int u8_parse_entity	(	u8_byte *	entity,
		u8_byte **	endp
	)

Parses a unicode entity name from a string, recording the endpoint.

This is handed a pointer to a UTF-8 string (entity) just after the entity escape character ampersand ('&'). It parses an entity name, returning the corresponding code and storing the end of the entity (after the trailing semicolon (';')) in endp. If endp is NULL, the end result is not stored.

Parameters:

entity	a pointer into a UTF-8 string
endp	a pointer to a location to store the end of the entity

Returns:

a unicode code point

U8_EXPORT void u8_set_charinfo	(	int	n,
		unsigned char *	info,
		short *	data
	)

Sets the character information for a particular code point.

Parameters:

n	a Unicode code point
info	a string describing information about the character
data	a pointer to a short vector of data about the character

Returns:

void