libunibreak 5.1
|
Implementation of the word breaking algorithm as described in Unicode Standard Annex 29. More...
#include <assert.h>
#include <stddef.h>
#include <string.h>
#include "unibreakdef.h"
#include "wordbreak.h"
#include "wordbreakdata.c"
#include "emojidef.h"
Macros | |
#define | IS_WB3ab(cls) |
Functions | |
void | init_wordbreak (void) |
Initializes the wordbreak internals. | |
static enum WordBreakClass | get_char_wb_class (utf32_t ch, const struct WordBreakProperties *wbp, size_t len) |
Gets the word breaking class of a character. | |
static void | set_brks_to (const void *s, char *brks, size_t posStart, size_t posEnd, size_t len, char brkType, get_next_char_t get_next_char) |
Sets the word break types to a specific value in a range. | |
static void | set_wordbreaks (const void *s, size_t len, const char *lang, char *brks, get_next_char_t get_next_char) |
Sets the word breaking information for a generic input string. | |
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. | |
Implementation of the word breaking algorithm as described in Unicode Standard Annex 29.
#define IS_WB3ab | ( | cls | ) |
|
static |
Gets the word breaking class of a character.
ch | character to check |
wbp | pointer to the wbp breaking properties array |
len | size of the wbp array in number of items |
WBP_Any
otherwise void init_wordbreak | ( | void | ) |
Initializes the wordbreak internals.
It currently does nothing, but it may in the future.
|
static |
Sets the word break types to a specific value in a range.
It sets the inside chars to WORDBREAK_INSIDEACHAR and the rest to brkType. Assumes brks is initialized - all the cells with WORDBREAK_NOBREAK are cells that we really don't want to break after.
[in] | s | input string |
[out] | brks | breaks array to fill |
[in] | posStart | start position |
[in] | posEnd | end position (exclusive) |
[in] | len | length of the string |
[in] | brkType | breaks type to use |
[in] | get_next_char | function to get the next UTF-32 character |
|
static |
Sets the word breaking information for a generic input string.
[in] | s | input string |
[in] | len | length of the input |
[in] | lang | language of the input (reserved for future use) |
[out] | brks | pointer to the output breaking data, containing WORDBREAK_BREAK, WORDBREAK_NOBREAK, or WORDBREAK_INSIDEACHAR |
[in] | get_next_char | function to get the next UTF-32 character |
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 (reserved for future use) |
[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 (reserved for future use) |
[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 (reserved for future use) |
[out] | brks | pointer to the output breaking data, containing WORDBREAK_BREAK, WORDBREAK_NOBREAK, or WORDBREAK_INSIDEACHAR |