libunibreak 5.1
|
Implementation of the line breaking algorithm as described in Unicode Standard Annex 14. More...
#include <assert.h>
#include <stddef.h>
#include <string.h>
#include "linebreak.h"
#include "linebreakdef.h"
Macros | |
#define | LINEBREAK_UNDEFINED -1 |
Special value used internally to indicate an undefined break result. | |
#define | LINEBREAK_INDEX_SIZE 40 |
Size of the second-level index to the line breaking properties. | |
#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 | |
static __inline int | ends_with (const char *str, const char *suffix, unsigned suffixLen) |
Checks whether the str ends with suffix, which has length suffix_len. | |
void | init_linebreak (void) |
Does nothing. | |
static const struct LineBreakProperties * | get_lb_prop_lang (const char *lang) |
Gets the language-specific line breaking properties. | |
static enum LineBreakClass | get_char_lb_class (utf32_t ch, const struct LineBreakProperties *lbp) |
Gets the line breaking class of a character from a line breaking properties array. | |
static enum LineBreakClass | get_char_lb_class_default (utf32_t ch) |
Gets the line breaking class of a character from the default line breaking properties array. | |
static enum LineBreakClass | get_char_lb_class_lang (utf32_t ch, const struct LineBreakProperties *lbpLang) |
Gets the line breaking class of a character for a specific language. | |
static enum LineBreakClass | resolve_lb_class (enum LineBreakClass lbc, const char *lang) |
Resolves the line breaking class for certain ambiguous or complicated characters. | |
static void | treat_first_char (struct LineBreakContext *lbpCtx) |
Treats specially for the first character in a line. | |
static int | get_lb_result_simple (struct LineBreakContext *lbpCtx) |
Tries telling the line break opportunity by simple rules. | |
static int | get_lb_result_lookup (struct LineBreakContext *lbpCtx) |
Tells the line break opportunity by table lookup. | |
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. | |
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. | |
Variables | |
static enum BreakAction | baTable [LBP_CB][LBP_CB] |
Break action pair table. | |
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 |
Enumeration of break actions.
They are used in the break action pair table baTable.
|
static |
Checks whether the str ends with suffix, which has length suffix_len.
str | string whose ending is to be checked |
suffix | string to check |
suffixLen | length of suffix |
|
static |
Gets the line breaking class of a character from a line breaking properties array.
ch | character to check |
lbp | pointer to the line breaking properties array |
LBP_XX
otherwise
|
static |
Gets the line breaking class of a character from the default line breaking properties array.
ch | character to check |
LBP_XX
otherwise
|
static |
Gets the line breaking class of a character for a specific language.
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.
ch | character to check |
lbpLang | pointer to the language-specific line breaking properties array |
LBP_XX
otherwise
|
static |
Gets the language-specific line breaking properties.
lang | language of the text |
NULL
otherwise
|
static |
Tells the line break opportunity by table lookup.
[in,out] | lbpCtx | pointer to the line breaking context |
|
static |
Tries telling the line break opportunity by simple rules.
[in,out] | lbpCtx | pointer to the line breaking context |
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 |
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 |
|
static |
Resolves the line breaking class for certain ambiguous or complicated characters.
They are treated in a simplistic way in this implementation.
lbc | line breaking class to resolve |
lang | language of the text |
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 |
|
static |
Treats specially for the first character in a line.
[in,out] | lbpCtx | pointer to the line breaking context |
|
static |
Break action pair table.
This is a direct mapping of Table 2 of Unicode Standard Annex 14, Revision 37, except for the following: