charsets.h File Reference

Data Structures
struct	conv_table

Macros
#define	UCS_SPACE   ((unicode_val_T) 0x0020)
#define	UCS_NO_BREAK_SPACE   ((unicode_val_T) 0x00A0)
#define	UCS_SOFT_HYPHEN   ((unicode_val_T) 0x00AD)
#define	UCS_REPLACEMENT_CHARACTER   ((unicode_val_T) 0xFFFD)
#define	UCS_NO_CHAR   ((unicode_val_T) 0xFFFFFFFD)
#define	UCS_ORPHAN_CELL   ((unicode_val_T) 0x20)
#define	NBSP_CHAR   ((unsigned char) 1)
#define	NBSP_CHAR_STRING   "\001"
#define	convert_string   convert_string_elinks
#define	u2cp(u, to)   u2cp_(u, to, NBSP_MODE_HACK)
#define	u2cp_no_nbsp(u, to)   u2cp_(u, to, NBSP_MODE_ASCII)
#define	is_utf16_surrogate(u)   (((u) & 0xFFFFF800) == 0xD800)
#define	is_utf16_high_surrogate(u)   (((u) & 0xFFFFFC00) == 0xD800)
#define	is_utf16_low_surrogate(u)   (((u) & 0xFFFFFC00) == 0xDC00)
#define	join_utf16_surrogates(high, low)   (0x10000 + (((high) - 0xD800L) << 10) + ((low) - 0xDC00))
#define	needs_utf16_surrogates(u)   ((uint32_t) ((u) - 0x10000) < 0x100000)
#define	get_utf16_high_surrogate(u)   (0xD800 + (((u) - 0x10000) >> 10))
#define	get_utf16_low_surrogate(u)   (0xDC00 + ((u) & 0x3FF))

Typedefs
typedef uint32_t	unicode_val_T

Enumerations
enum	convert_string_mode { CSM_DEFAULT , CSM_QUERY , CSM_FORM , CSM_NONE }
enum	nbsp_mode { NBSP_MODE_HACK = 0 , NBSP_MODE_ASCII = 1 }
enum	utf8_step { UTF8_STEP_CHARACTERS , UTF8_STEP_CELLS_FEWER , UTF8_STEP_CELLS_MORE }

Functions
struct conv_table *	get_translation_table (int, int)
const char *	get_entity_string (const char *str, const int strlen, int encoding)
char *	convert_string (struct conv_table *convert_table, const char *chars, int charslen, int cp, enum convert_string_mode mode, int *length, void(*callback)(void *data, char *buf, int buflen), void *callback_data)
int	get_cp_index (const char *)
const char *	get_cp_name (int)
const char *	get_cp_config_name (int)
const char *	get_cp_mime_name (int)
const uint16_t *	get_cp_highhalf (const char *)
int	is_cp_utf8 (int)
void	free_conv_table (void)
char *	encode_utf8 (unicode_val_T)
char *	utf8_prevchar (char *, int, char *)
int	utf8charlen (const char *)
int	utf8_char2cells (const char *, char *)
int	utf8_ptr2cells (const char *, char *)
int	utf8_ptr2chars (char *, char *)
int	utf8_cells2bytes (const char *, int, char *)
char *	utf8_step_forward (char *, char *, int, enum utf8_step, int *)
char *	utf8_step_backward (char *, char *, int, enum utf8_step, int *)
int	codepoint_replacement (unicode_val_T u)
int	unicode_to_cell (unicode_val_T)
unicode_val_T	unicode_fold_label_case (unicode_val_T)
int	strlen_utf8 (char **)
unicode_val_T	utf8_to_unicode (char **, const char *)
unicode_val_T	cp_to_unicode (int, char **, const char *)
unicode_val_T	cp2u (int, unsigned char)
const char *	cp2utf8 (int, int)
const char *	u2cp_ (unicode_val_T, int, enum nbsp_mode)
void	init_charsets_lookup (void)
void	free_charsets_lookup (void)

Macro Definition Documentation

convert_string

#define convert_string   convert_string_elinks

get_utf16_high_surrogate

#define get_utf16_high_surrogate

(

u

)

(0xD800 + (((u) - 0x10000) >> 10))

get_utf16_low_surrogate

#define get_utf16_low_surrogate

(

u

)

(0xDC00 + ((u) & 0x3FF))

is_utf16_high_surrogate

#define is_utf16_high_surrogate

(

u

)

(((u) & 0xFFFFFC00) == 0xD800)

is_utf16_low_surrogate

#define is_utf16_low_surrogate

(

u

)

(((u) & 0xFFFFFC00) == 0xDC00)

is_utf16_surrogate

#define is_utf16_surrogate

(

u

)

(((u) & 0xFFFFF800) == 0xD800)

join_utf16_surrogates

#define join_utf16_surrogates	(		high,
			low
	)		(0x10000 + (((high) - 0xD800L) << 10) + ((low) - 0xDC00))

NBSP_CHAR

#define NBSP_CHAR   ((unsigned char) 1)

NBSP_CHAR_STRING

#define NBSP_CHAR_STRING   "\001"

needs_utf16_surrogates

#define needs_utf16_surrogates

(

u

)

((uint32_t) ((u) - 0x10000) < 0x100000)

u2cp

#define u2cp	(		u,
			to
	)		u2cp_(u, to, NBSP_MODE_HACK)

u2cp_no_nbsp

#define u2cp_no_nbsp	(		u,
			to
	)		u2cp_(u, to, NBSP_MODE_ASCII)

UCS_NO_BREAK_SPACE

#define UCS_NO_BREAK_SPACE   ((unicode_val_T) 0x00A0)

UCS_NO_CHAR

#define UCS_NO_CHAR   ((unicode_val_T) 0xFFFFFFFD)

UCS_ORPHAN_CELL

#define UCS_ORPHAN_CELL   ((unicode_val_T) 0x20)

UCS_REPLACEMENT_CHARACTER

#define UCS_REPLACEMENT_CHARACTER   ((unicode_val_T) 0xFFFD)

UCS_SOFT_HYPHEN

#define UCS_SOFT_HYPHEN   ((unicode_val_T) 0x00AD)

UCS_SPACE

#define UCS_SPACE   ((unicode_val_T) 0x0020)

Typedef Documentation

unicode_val_T

typedef uint32_t unicode_val_T

Enumeration Type Documentation

convert_string_mode

enum convert_string_mode

Enumerator
CSM_DEFAULT
CSM_QUERY
CSM_FORM
CSM_NONE

nbsp_mode

enum nbsp_mode

Enumerator
NBSP_MODE_HACK
NBSP_MODE_ASCII

utf8_step

enum utf8_step

Enumerator
UTF8_STEP_CHARACTERS
UTF8_STEP_CELLS_FEWER
UTF8_STEP_CELLS_MORE

Function Documentation

codepoint_replacement()

int codepoint_replacement

(

unicode_val_T

u

)

convert_string()

char * convert_string	(	struct conv_table *	convert_table,
		const char *	chars,
		int	charslen,
		int	cp,
		enum convert_string_mode	mode,
		int *	length,
		void(*)(void *data, char *buf, int buflen)	callback,
		void *	callback_data
	)

cp2u()

unicode_val_T cp2u	(	int	from,
		unsigned char	c
	)

cp2utf8()

const char * cp2utf8	(	int	from,
		int	c
	)

cp_to_unicode()

unicode_val_T cp_to_unicode	(	int	codepage,
		char **	string,
		const char *	end
	)

encode_utf8()

char * encode_utf8

(

unicode_val_T

u

)

free_charsets_lookup()

void free_charsets_lookup

(

void

)

free_conv_table()

void free_conv_table

(

void

)

get_cp_config_name()

const char * get_cp_config_name

(

int

cp_index

)

get_cp_highhalf()

const uint16_t * get_cp_highhalf

(

const char *

name

)

get_cp_index()

int get_cp_index

(

const char *

name

)

get_cp_mime_name()

const char * get_cp_mime_name

(

int

cp_index

)

get_cp_name()

const char * get_cp_name

(

int

cp_index

)

get_entity_string()

const char * get_entity_string	(	const char *	str,
		const int	strlen,
		int	encoding
	)

get_translation_table()

struct conv_table * get_translation_table	(	int	from,
		int	to
	)

init_charsets_lookup()

void init_charsets_lookup

(

void

)

is_cp_utf8()

int is_cp_utf8

(

int

cp_index

)

strlen_utf8()

int strlen_utf8

(

char **

str

)

u2cp_()

const char * u2cp_	(	unicode_val_T	,
		int	,
		enum	nbsp_mode
	)

unicode_fold_label_case()

unicode_val_T unicode_fold_label_case

(

unicode_val_T

c

)

unicode_to_cell()

int unicode_to_cell

(

unicode_val_T

ucs4

)

utf8_cells2bytes()

int utf8_cells2bytes	(	const char *	string,
		int	max_cells,
		char *	end
	)

utf8_char2cells()

int utf8_char2cells	(	const char *	utf8_char_const,
		char *	end
	)

utf8_prevchar()

char * utf8_prevchar	(	char *	current,
		int	pos,
		char *	start
	)

utf8_ptr2cells()

int utf8_ptr2cells	(	const char *	string,
		char *	end
	)

utf8_ptr2chars()

int utf8_ptr2chars	(	char *	string,
		char *	end
	)

utf8_step_backward()

char * utf8_step_backward	(	char *	string,
		char *	start,
		int	max,
		enum	utf8_step,
		int *	count
	)

utf8_step_forward()

char * utf8_step_forward	(	char *	string,
		char *	end,
		int	max,
		enum	utf8_step,
		int *	count
	)

utf8_to_unicode()

unicode_val_T utf8_to_unicode	(	char **	string,
		const char *	end
	)

utf8charlen()

int utf8charlen

(

const char *

p

)