libunibreak 6.1
|
Implementation of the line breaking algorithm as described in Unicode Standard Annex 14. More...
#include <assert.h>
#include <stddef.h>
#include <string.h>
#include "eastasianwidthdef.h"
#include "linebreak.h"
#include "linebreakdef.h"
Macros | |
#define | LINEBREAK_UNDEFINED -1 |
Special value used internally to indicate an undefined break result. More... | |
#define | LINEBREAK_INDEX_SIZE 40 |
Size of the second-level index to the line breaking properties. More... | |
#define | ENDS_WITH(str, suffix) ends_with((str), (suffix), sizeof(suffix) - 1) |
Enumerations | |
enum | BreakAction { DIR_BRK , IND_BRK , CMI_BRK , CMP_BRK , PRH_BRK } |
Enumeration of break actions. More... | |
Functions | |
void | init_linebreak (void) |
Does nothing. More... | |
void | lb_init_break_context (struct LineBreakContext *lbpCtx, utf32_t ch, const char *lang) |
Initializes line breaking context for a given language. More... | |
int | lb_process_next_char (struct LineBreakContext *lbpCtx, utf32_t ch) |
Updates LineBreakingContext for the next codepoint and returns the detected break. More... | |
enum LineBreakClass | lb_get_char_class (const struct LineBreakContext *lbpCtx, utf32_t ch) |
Gets the line breaking class of a character for a line breaking context. More... | |
size_t | set_linebreaks (const void *s, size_t len, const char *lang, enum BreakOutputType outputType, char *brks, get_next_char_t get_next_char) |
Sets the line breaking information for a generic input string. More... | |
void | set_linebreaks_utf8 (const utf8_t *s, size_t len, const char *lang, char *brks) |
Sets the line breaking information for a UTF-8 input string. More... | |
size_t | set_linebreaks_utf8_per_code_point (const utf8_t *s, size_t len, const char *lang, char *brks) |
Sets the line breaking information for a UTF-8 input string. More... | |
void | set_linebreaks_utf16 (const utf16_t *s, size_t len, const char *lang, char *brks) |
Sets the line breaking information for a UTF-16 input string. More... | |
size_t | set_linebreaks_utf16_per_code_point (const utf16_t *s, size_t len, const char *lang, char *brks) |
Sets the line breaking information for a UTF-16 input string. More... | |
void | set_linebreaks_utf32 (const utf32_t *s, size_t len, const char *lang, char *brks) |
Sets the line breaking information for a UTF-32 input string. More... | |
int | is_line_breakable (utf32_t char1, utf32_t char2, const char *lang) |
Tells whether a line break can occur between two Unicode characters. More... | |
Implementation of the line breaking algorithm as described in Unicode Standard Annex 14.
#define ENDS_WITH | ( | str, | |
suffix | |||
) | ends_with((str), (suffix), sizeof(suffix) - 1) |
#define LINEBREAK_INDEX_SIZE 40 |
Size of the second-level index to the line breaking properties.
#define LINEBREAK_UNDEFINED -1 |
Special value used internally to indicate an undefined break result.
enum BreakAction |
void init_linebreak | ( | void | ) |
Does nothing.
This is kept for binary compatibility.
Tells whether a line break can occur between two Unicode characters.
This is a wrapper function to expose a simple interface. Generally speaking, it is better to use set_linebreaks_utf32 instead, since complicated cases involving combining marks, spaces, etc. cannot be correctly processed.
char1 | the first Unicode character |
char2 | the second Unicode character |
lang | language of the input |
enum LineBreakClass lb_get_char_class | ( | const struct LineBreakContext * | lbpCtx, |
utf32_t | ch | ||
) |
Gets the line breaking class of a character for a line breaking context.
This function will check the language-specific data first, and then the default data if there is no language-specific property available for the character.
lbpCtx | pointer to the line breaking context |
ch | character to check |
LBP_XX
otherwise void lb_init_break_context | ( | struct LineBreakContext * | lbpCtx, |
utf32_t | ch, | ||
const char * | lang | ||
) |
Initializes line breaking context for a given language.
[in,out] | lbpCtx | pointer to the line breaking context |
[in] | ch | the first character to process |
[in] | lang | language of the input |
int lb_process_next_char | ( | struct LineBreakContext * | lbpCtx, |
utf32_t | ch | ||
) |
Updates LineBreakingContext for the next codepoint and returns the detected break.
[in,out] | lbpCtx | pointer to the line breaking context |
[in] | ch | Unicode codepoint |
size_t set_linebreaks | ( | const void * | s, |
size_t | len, | ||
const char * | lang, | ||
enum BreakOutputType | outputType, | ||
char * | brks, | ||
get_next_char_t | get_next_char | ||
) |
Sets the line breaking information for a generic input string.
Currently, this implementation has customization for the following ISO 639-1 language codes (for lang):
In addition, a suffix "-strict"
may be added to indicate strict (as versus normal) line-breaking behaviour. See the Conditional Japanese Starter section of UAX #14 for more details.
[in] | s | input string |
[in] | len | length of the input |
[in] | lang | language of the input |
[in] | outputType | output per code-unit or per code-point |
[out] | brks | pointer to the output breaking data, containing LINEBREAK_MUSTBREAK, LINEBREAK_ALLOWBREAK, LINEBREAK_NOBREAK, or LINEBREAK_INSIDEACHAR |
[in] | get_next_char | function to get the next UTF-32 character |
void set_linebreaks_utf16 | ( | const utf16_t * | s, |
size_t | len, | ||
const char * | lang, | ||
char * | brks | ||
) |
Sets the line 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 LINEBREAK_MUSTBREAK, LINEBREAK_ALLOWBREAK, LINEBREAK_NOBREAK, or LINEBREAK_INSIDEACHAR |
size_t set_linebreaks_utf16_per_code_point | ( | const utf16_t * | s, |
size_t | len, | ||
const char * | lang, | ||
char * | brks | ||
) |
Sets the line 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 LINEBREAK_MUSTBREAK, LINEBREAK_ALLOWBREAK, LINEBREAK_NOBREAK |
void set_linebreaks_utf32 | ( | const utf32_t * | s, |
size_t | len, | ||
const char * | lang, | ||
char * | brks | ||
) |
Sets the line 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 LINEBREAK_MUSTBREAK, LINEBREAK_ALLOWBREAK, LINEBREAK_NOBREAK, or LINEBREAK_INSIDEACHAR |
void set_linebreaks_utf8 | ( | const utf8_t * | s, |
size_t | len, | ||
const char * | lang, | ||
char * | brks | ||
) |
Sets the line 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 LINEBREAK_MUSTBREAK, LINEBREAK_ALLOWBREAK, LINEBREAK_NOBREAK, or LINEBREAK_INSIDEACHAR |
size_t set_linebreaks_utf8_per_code_point | ( | const utf8_t * | s, |
size_t | len, | ||
const char * | lang, | ||
char * | brks | ||
) |
Sets the line 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 LINEBREAK_MUSTBREAK, LINEBREAK_ALLOWBREAK, LINEBREAK_NOBREAK |