Tesseract 3.01
|
#include <unicharset.h>
Classes | |
struct | UNICHAR_PROPERTIES |
struct | UNICHAR_SLOT |
Public Member Functions | |
UNICHARSET () | |
~UNICHARSET () | |
const UNICHAR_ID | unichar_to_id (const char *const unichar_repr) const |
const UNICHAR_ID | unichar_to_id (const char *const unichar_repr, int length) const |
int | step (const char *str) const |
const char *const | id_to_unichar (UNICHAR_ID id) const |
STRING | debug_str (UNICHAR_ID id) const |
STRING | debug_str (const char *unichar_repr) const |
void | unichar_insert (const char *const unichar_repr) |
bool | contains_unichar_id (UNICHAR_ID unichar_id) const |
bool | contains_unichar (const char *const unichar_repr) const |
bool | contains_unichar (const char *const unichar_repr, int length) const |
bool | eq (UNICHAR_ID unichar_id, const char *const unichar_repr) const |
void | delete_pointers_in_unichars () |
void | clear () |
int | size () const |
void | reserve (int unichars_number) |
bool | save_to_file (const char *const filename) const |
bool | save_to_file (FILE *file) const |
bool | load_from_file (const char *const filename, bool skip_fragments) |
bool | load_from_file (const char *const filename) |
bool | load_from_file (FILE *file, bool skip_fragments) |
bool | load_from_file (FILE *file) |
void | post_load_setup () |
bool | any_right_to_left () const |
void | set_black_and_whitelist (const char *blacklist, const char *whitelist) |
void | set_isalpha (UNICHAR_ID unichar_id, bool value) |
void | set_islower (UNICHAR_ID unichar_id, bool value) |
void | set_isupper (UNICHAR_ID unichar_id, bool value) |
void | set_isdigit (UNICHAR_ID unichar_id, bool value) |
void | set_ispunctuation (UNICHAR_ID unichar_id, bool value) |
void | set_isngram (UNICHAR_ID unichar_id, bool value) |
void | set_script (UNICHAR_ID unichar_id, const char *value) |
void | set_other_case (UNICHAR_ID unichar_id, UNICHAR_ID other_case) |
bool | get_isalpha (UNICHAR_ID unichar_id) const |
bool | get_islower (UNICHAR_ID unichar_id) const |
bool | get_isupper (UNICHAR_ID unichar_id) const |
bool | get_isdigit (UNICHAR_ID unichar_id) const |
bool | get_ispunctuation (UNICHAR_ID unichar_id) const |
bool | get_isngram (UNICHAR_ID unichar_id) const |
bool | top_bottom_useful () const |
void | get_top_bottom (UNICHAR_ID unichar_id, int *min_bottom, int *max_bottom, int *min_top, int *max_top) const |
void | set_top_bottom (UNICHAR_ID unichar_id, int min_bottom, int max_bottom, int min_top, int max_top) |
int | get_script (UNICHAR_ID unichar_id) const |
unsigned int | get_properties (UNICHAR_ID unichar_id) const |
char | get_chartype (UNICHAR_ID unichar_id) const |
UNICHAR_ID | get_other_case (UNICHAR_ID unichar_id) const |
UNICHAR_ID | to_lower (UNICHAR_ID unichar_id) const |
UNICHAR_ID | to_upper (UNICHAR_ID unichar_id) const |
const CHAR_FRAGMENT * | get_fragment (UNICHAR_ID unichar_id) const |
bool | get_isalpha (const char *const unichar_repr) const |
bool | get_islower (const char *const unichar_repr) const |
bool | get_isupper (const char *const unichar_repr) const |
bool | get_isdigit (const char *const unichar_repr) const |
bool | get_ispunctuation (const char *const unichar_repr) const |
unsigned int | get_properties (const char *const unichar_repr) const |
char | get_chartype (const char *const unichar_repr) const |
int | get_script (const char *const unichar_repr) const |
const CHAR_FRAGMENT * | get_fragment (const char *const unichar_repr) const |
bool | get_isalpha (const char *const unichar_repr, int length) const |
bool | get_islower (const char *const unichar_repr, int length) const |
bool | get_isupper (const char *const unichar_repr, int length) const |
bool | get_isdigit (const char *const unichar_repr, int length) const |
bool | get_ispunctuation (const char *const unichar_repr, int length) const |
int | get_script (const char *const unichar_repr, int length) const |
int | get_script_table_size () const |
const char * | get_script_from_script_id (int id) const |
int | get_script_id_from_name (const char *script_name) const |
bool | is_null_script (const char *script) const |
int | add_script (const char *script) |
bool | get_enabled (UNICHAR_ID unichar_id) const |
int | null_sid () const |
int | common_sid () const |
int | latin_sid () const |
int | cyrillic_sid () const |
int | greek_sid () const |
int | han_sid () const |
int | hiragana_sid () const |
int | katakana_sid () const |
int | default_sid () const |
bool | script_has_upper_lower () const |
bool | script_has_xheight () const |
Static Public Member Functions | |
static STRING | debug_utf8_str (const char *str) |
UNICHARSET::UNICHARSET | ( | ) |
UNICHARSET::~UNICHARSET | ( | ) |
int UNICHARSET::add_script | ( | const char * | script | ) |
bool UNICHARSET::any_right_to_left | ( | ) | const |
void UNICHARSET::clear | ( | ) | [inline] |
int UNICHARSET::common_sid | ( | ) | const [inline] |
bool UNICHARSET::contains_unichar | ( | const char *const | unichar_repr, |
int | length | ||
) | const |
bool UNICHARSET::contains_unichar | ( | const char *const | unichar_repr | ) | const |
bool UNICHARSET::contains_unichar_id | ( | UNICHAR_ID | unichar_id | ) | const [inline] |
int UNICHARSET::cyrillic_sid | ( | ) | const [inline] |
STRING UNICHARSET::debug_str | ( | UNICHAR_ID | id | ) | const |
STRING UNICHARSET::debug_str | ( | const char * | unichar_repr | ) | const [inline] |
STRING UNICHARSET::debug_utf8_str | ( | const char * | str | ) | [static] |
int UNICHARSET::default_sid | ( | ) | const [inline] |
void UNICHARSET::delete_pointers_in_unichars | ( | ) | [inline] |
bool UNICHARSET::eq | ( | UNICHAR_ID | unichar_id, |
const char *const | unichar_repr | ||
) | const |
char UNICHARSET::get_chartype | ( | UNICHAR_ID | unichar_id | ) | const |
char UNICHARSET::get_chartype | ( | const char *const | unichar_repr | ) | const [inline] |
bool UNICHARSET::get_enabled | ( | UNICHAR_ID | unichar_id | ) | const [inline] |
const CHAR_FRAGMENT* UNICHARSET::get_fragment | ( | UNICHAR_ID | unichar_id | ) | const [inline] |
const CHAR_FRAGMENT* UNICHARSET::get_fragment | ( | const char *const | unichar_repr | ) | const [inline] |
bool UNICHARSET::get_isalpha | ( | UNICHAR_ID | unichar_id | ) | const [inline] |
bool UNICHARSET::get_isalpha | ( | const char *const | unichar_repr | ) | const [inline] |
bool UNICHARSET::get_isalpha | ( | const char *const | unichar_repr, |
int | length | ||
) | const [inline] |
bool UNICHARSET::get_isdigit | ( | UNICHAR_ID | unichar_id | ) | const [inline] |
bool UNICHARSET::get_isdigit | ( | const char *const | unichar_repr | ) | const [inline] |
bool UNICHARSET::get_isdigit | ( | const char *const | unichar_repr, |
int | length | ||
) | const [inline] |
bool UNICHARSET::get_islower | ( | UNICHAR_ID | unichar_id | ) | const [inline] |
bool UNICHARSET::get_islower | ( | const char *const | unichar_repr | ) | const [inline] |
bool UNICHARSET::get_islower | ( | const char *const | unichar_repr, |
int | length | ||
) | const [inline] |
bool UNICHARSET::get_isngram | ( | UNICHAR_ID | unichar_id | ) | const [inline] |
bool UNICHARSET::get_ispunctuation | ( | const char *const | unichar_repr, |
int | length | ||
) | const [inline] |
bool UNICHARSET::get_ispunctuation | ( | UNICHAR_ID | unichar_id | ) | const [inline] |
bool UNICHARSET::get_ispunctuation | ( | const char *const | unichar_repr | ) | const [inline] |
bool UNICHARSET::get_isupper | ( | UNICHAR_ID | unichar_id | ) | const [inline] |
bool UNICHARSET::get_isupper | ( | const char *const | unichar_repr | ) | const [inline] |
bool UNICHARSET::get_isupper | ( | const char *const | unichar_repr, |
int | length | ||
) | const [inline] |
UNICHAR_ID UNICHARSET::get_other_case | ( | UNICHAR_ID | unichar_id | ) | const [inline] |
unsigned int UNICHARSET::get_properties | ( | UNICHAR_ID | unichar_id | ) | const |
unsigned int UNICHARSET::get_properties | ( | const char *const | unichar_repr | ) | const [inline] |
int UNICHARSET::get_script | ( | const char *const | unichar_repr, |
int | length | ||
) | const [inline] |
int UNICHARSET::get_script | ( | UNICHAR_ID | unichar_id | ) | const [inline] |
int UNICHARSET::get_script | ( | const char *const | unichar_repr | ) | const [inline] |
const char* UNICHARSET::get_script_from_script_id | ( | int | id | ) | const [inline] |
int UNICHARSET::get_script_id_from_name | ( | const char * | script_name | ) | const |
int UNICHARSET::get_script_table_size | ( | ) | const [inline] |
void UNICHARSET::get_top_bottom | ( | UNICHAR_ID | unichar_id, |
int * | min_bottom, | ||
int * | max_bottom, | ||
int * | min_top, | ||
int * | max_top | ||
) | const [inline] |
int UNICHARSET::greek_sid | ( | ) | const [inline] |
int UNICHARSET::han_sid | ( | ) | const [inline] |
int UNICHARSET::hiragana_sid | ( | ) | const [inline] |
const char *const UNICHARSET::id_to_unichar | ( | UNICHAR_ID | id | ) | const |
bool UNICHARSET::is_null_script | ( | const char * | script | ) | const [inline] |
int UNICHARSET::katakana_sid | ( | ) | const [inline] |
int UNICHARSET::latin_sid | ( | ) | const [inline] |
bool UNICHARSET::load_from_file | ( | const char *const | filename, |
bool | skip_fragments | ||
) | [inline] |
bool UNICHARSET::load_from_file | ( | const char *const | filename | ) | [inline] |
bool UNICHARSET::load_from_file | ( | FILE * | file, |
bool | skip_fragments | ||
) |
bool UNICHARSET::load_from_file | ( | FILE * | file | ) | [inline] |
int UNICHARSET::null_sid | ( | ) | const [inline] |
void UNICHARSET::post_load_setup | ( | ) |
void UNICHARSET::reserve | ( | int | unichars_number | ) |
bool UNICHARSET::save_to_file | ( | const char *const | filename | ) | const [inline] |
bool UNICHARSET::save_to_file | ( | FILE * | file | ) | const |
bool UNICHARSET::script_has_upper_lower | ( | ) | const [inline] |
bool UNICHARSET::script_has_xheight | ( | ) | const [inline] |
void UNICHARSET::set_black_and_whitelist | ( | const char * | blacklist, |
const char * | whitelist | ||
) |
void UNICHARSET::set_isalpha | ( | UNICHAR_ID | unichar_id, |
bool | value | ||
) | [inline] |
void UNICHARSET::set_isdigit | ( | UNICHAR_ID | unichar_id, |
bool | value | ||
) | [inline] |
void UNICHARSET::set_islower | ( | UNICHAR_ID | unichar_id, |
bool | value | ||
) | [inline] |
void UNICHARSET::set_isngram | ( | UNICHAR_ID | unichar_id, |
bool | value | ||
) | [inline] |
void UNICHARSET::set_ispunctuation | ( | UNICHAR_ID | unichar_id, |
bool | value | ||
) | [inline] |
void UNICHARSET::set_isupper | ( | UNICHAR_ID | unichar_id, |
bool | value | ||
) | [inline] |
void UNICHARSET::set_other_case | ( | UNICHAR_ID | unichar_id, |
UNICHAR_ID | other_case | ||
) | [inline] |
void UNICHARSET::set_script | ( | UNICHAR_ID | unichar_id, |
const char * | value | ||
) | [inline] |
void UNICHARSET::set_top_bottom | ( | UNICHAR_ID | unichar_id, |
int | min_bottom, | ||
int | max_bottom, | ||
int | min_top, | ||
int | max_top | ||
) | [inline] |
int UNICHARSET::size | ( | ) | const [inline] |
int UNICHARSET::step | ( | const char * | str | ) | const |
UNICHAR_ID UNICHARSET::to_lower | ( | UNICHAR_ID | unichar_id | ) | const [inline] |
UNICHAR_ID UNICHARSET::to_upper | ( | UNICHAR_ID | unichar_id | ) | const [inline] |
bool UNICHARSET::top_bottom_useful | ( | ) | const [inline] |
void UNICHARSET::unichar_insert | ( | const char *const | unichar_repr | ) |
const UNICHAR_ID UNICHARSET::unichar_to_id | ( | const char *const | unichar_repr | ) | const |
const UNICHAR_ID UNICHARSET::unichar_to_id | ( | const char *const | unichar_repr, |
int | length | ||
) | const |