Implementation of the line breaking algorithm as described in Unicode Standard Annex 14. More...

#include <assert.h>
#include <stddef.h>
#include <stdint.h>
#include <string.h>
#include "eastasianwidthdef.h"
#include "linebreak.h"
#include "linebreakdef.h"

Include dependency graph for linebreak.c:

Macros
#define	UB_LB25_OPT_HACK 1
#define	LINEBREAK_UNDEFINED -1
	Special value used internally to indicate an undefined break result.
#define	INVALID_POS ((size_t)-1)
	Special value used internally to mark an invalid position.
#define	ENDS_WITH(str, suffix)

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.
void	lb_init_break_context (struct LineBreakContext lbpCtx, utf32_t ch, const char lang)
	Initializes line breaking context for a given language.
int	lb_process_next_char (struct LineBreakContext *lbpCtx, utf32_t ch)
	Updates LineBreakingContext for the next codepoint and returns the detected break.
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.
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.
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.
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.
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.
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.
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.
int	is_line_breakable (utf32_t char1, utf32_t char2, const char *lang)
	Tells whether a line break can occur between two Unicode characters.

Detailed Description

Implementation of the line breaking algorithm as described in Unicode Standard Annex 14.

Author: Wu Yongwei; Petr Filipsky

Macro Definition Documentation

◆ ENDS_WITH

#define ENDS_WITH	(		str,
			suffix )

Value:

ends_with((str), (suffix), sizeof(suffix) - 1)

◆ INVALID_POS

#define INVALID_POS ((size_t)-1)

Special value used internally to mark an invalid position.

◆ LINEBREAK_UNDEFINED

#define LINEBREAK_UNDEFINED -1

Special value used internally to indicate an undefined break result.

◆ UB_LB25_OPT_HACK

#define UB_LB25_OPT_HACK 1

Enumeration Type Documentation

◆ BreakAction

enum BreakAction

Enumeration of break actions.

They are used in the break action pair table #baTable.

Enumerator
DIR_BRK	Direct break opportunity.
IND_BRK	Indirect break opportunity.
CMI_BRK	Indirect break opportunity for combining marks.
CMP_BRK	Prohibited break for combining marks.
PRH_BRK	Prohibited break.

Function Documentation

◆ init_linebreak()

void init_linebreak ( void )

Does nothing.

This is kept for binary compatibility.

◆ is_line_breakable()

int is_line_breakable	(	utf32_t	char1,
		utf32_t	char2,
		const char *	lang )

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.

Parameters

char1	the first Unicode character
char2	the second Unicode character
lang	language of the input

Returns: one of LINEBREAK_MUSTBREAK, LINEBREAK_ALLOWBREAK, LINEBREAK_NOBREAK, or LINEBREAK_INSIDEACHAR

◆ lb_get_char_class()

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.

Parameters

lbpCtx	pointer to the line breaking context
ch	character to check

Returns: the line breaking class if found; LBP_XX otherwise

◆ lb_init_break_context()

void lb_init_break_context	(	struct LineBreakContext *	lbpCtx,
		utf32_t	ch,
		const char *	lang )

Initializes line breaking context for a given language.

Parameters

[in,out]	lbpCtx	pointer to the line breaking context
[in]	ch	the first character to process
[in]	lang	language of the input

Postcondition: the line breaking context is initialized

◆ lb_process_next_char()

int lb_process_next_char	(	struct LineBreakContext *	lbpCtx,
		utf32_t	ch )

Updates LineBreakingContext for the next codepoint and returns the detected break.

This function is deprecated, as it cannot support fixups, as required by LB25 tailoring (and some more recent rules). See the implementation of set_linebreaks for the fixup logic.

Parameters

[in,out]	lbpCtx	pointer to the line breaking context
[in]	ch	Unicode codepoint

Returns: break result, one of LINEBREAK_MUSTBREAK, LINEBREAK_ALLOWBREAK, and LINEBREAK_NOBREAK

Postcondition: the line breaking context is updated

◆ set_linebreaks()

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):

de (German)
en (English)
es (Spanish)
fr (French)
ja (Japanese)
ko (Korean)
ru (Russian)
zh (Chinese)

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.

Parameters

[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

Returns: The number of entries in brks filled. This is equal to the number of code-points or code-units in the source string, depending on the outputType parameter.

◆ set_linebreaks_utf16()

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.

Parameters

[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

See also: set_linebreaks for a note about lang.

◆ set_linebreaks_utf16_per_code_point()

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.

Parameters

[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

Returns: The number of entries in brks filled. This is equal to the number of code-points in the source string.

See also: set_linebreaks for a note about lang.

◆ set_linebreaks_utf32()

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.

Parameters

[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

See also: set_linebreaks for a note about lang.

◆ set_linebreaks_utf8()

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.

Parameters

[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

See also: set_linebreaks for a note about lang.

◆ set_linebreaks_utf8_per_code_point()

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.

Parameters

[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

Returns: The number of entries in brks filled. This is equal to the number of code-points in the source string.

See also: set_linebreaks for a note about lang.

Macros

Enumerations

Functions

Detailed Description

Macro Definition Documentation

◆ ENDS_WITH

◆ INVALID_POS

◆ LINEBREAK_UNDEFINED

◆ UB_LB25_OPT_HACK

Enumeration Type Documentation

◆ BreakAction

Function Documentation

◆ init_linebreak()

◆ is_line_breakable()

◆ lb_get_char_class()

◆ lb_init_break_context()

◆ lb_process_next_char()

◆ set_linebreaks()

◆ set_linebreaks_utf16()

◆ set_linebreaks_utf16_per_code_point()

◆ set_linebreaks_utf32()

◆ set_linebreaks_utf8()

◆ set_linebreaks_utf8_per_code_point()