Header file for the word breaking (segmentation) algorithm. More...
#include <stddef.h>
#include "unibreakbase.h"
Go to the source code of this file.
Defines | |
#define | WORDBREAK_BREAK 0 |
Break is allowed. | |
#define | WORDBREAK_NOBREAK 1 |
No break is allowed. | |
#define | WORDBREAK_INSIDEACHAR 2 |
A UTF-8/16 sequence is unfinished. | |
Functions | |
void | init_wordbreak (void) |
Initializes the wordbreak internals. | |
void | set_wordbreaks_utf8 (const utf8_t *s, size_t len, const char *lang, char *brks) |
Sets the word breaking information for a UTF-8 input string. | |
void | set_wordbreaks_utf16 (const utf16_t *s, size_t len, const char *lang, char *brks) |
Sets the word breaking information for a UTF-16 input string. | |
void | set_wordbreaks_utf32 (const utf32_t *s, size_t len, const char *lang, char *brks) |
Sets the word breaking information for a UTF-32 input string. |
Header file for the word breaking (segmentation) algorithm.
#define WORDBREAK_BREAK 0 |
Break is allowed.
#define WORDBREAK_INSIDEACHAR 2 |
A UTF-8/16 sequence is unfinished.
#define WORDBREAK_NOBREAK 1 |
No break is allowed.
void init_wordbreak | ( | void | ) |
Initializes the wordbreak internals.
It currently does nothing, but it may in the future.
void set_wordbreaks_utf16 | ( | const utf16_t * | s, | |
size_t | len, | |||
const char * | lang, | |||
char * | brks | |||
) |
Sets the word breaking information for a UTF-16 input string.
[in] | s | input UTF-16 string |
[in] | len | length of the input |
[in] | lang | language of the input |
[out] | brks | pointer to the output breaking data, containing WORDBREAK_BREAK, WORDBREAK_NOBREAK, or WORDBREAK_INSIDEACHAR |
void set_wordbreaks_utf32 | ( | const utf32_t * | s, | |
size_t | len, | |||
const char * | lang, | |||
char * | brks | |||
) |
Sets the word breaking information for a UTF-32 input string.
[in] | s | input UTF-32 string |
[in] | len | length of the input |
[in] | lang | language of the input |
[out] | brks | pointer to the output breaking data, containing WORDBREAK_BREAK, WORDBREAK_NOBREAK, or WORDBREAK_INSIDEACHAR |
void set_wordbreaks_utf8 | ( | const utf8_t * | s, | |
size_t | len, | |||
const char * | lang, | |||
char * | brks | |||
) |
Sets the word breaking information for a UTF-8 input string.
[in] | s | input UTF-8 string |
[in] | len | length of the input |
[in] | lang | language of the input |
[out] | brks | pointer to the output breaking data, containing WORDBREAK_BREAK, WORDBREAK_NOBREAK, or WORDBREAK_INSIDEACHAR |