#include <unicharset.h>

Public Types
enum	Direction { U_LEFT_TO_RIGHT = 0, U_RIGHT_TO_LEFT = 1, U_EUROPEAN_NUMBER = 2, U_EUROPEAN_NUMBER_SEPARATOR = 3, U_EUROPEAN_NUMBER_TERMINATOR = 4, U_ARABIC_NUMBER = 5, U_COMMON_NUMBER_SEPARATOR = 6, U_BLOCK_SEPARATOR = 7, U_SEGMENT_SEPARATOR = 8, U_WHITE_SPACE_NEUTRAL = 9, U_OTHER_NEUTRAL = 10, U_LEFT_TO_RIGHT_EMBEDDING = 11, U_LEFT_TO_RIGHT_OVERRIDE = 12, U_RIGHT_TO_LEFT_ARABIC = 13, U_RIGHT_TO_LEFT_EMBEDDING = 14, U_RIGHT_TO_LEFT_OVERRIDE = 15, U_POP_DIRECTIONAL_FORMAT = 16, U_DIR_NON_SPACING_MARK = 17, U_BOUNDARY_NEUTRAL = 18, U_CHAR_DIRECTION_COUNT }

Public Member Functions
	UNICHARSET ()

	~UNICHARSET ()

UNICHAR_ID	unichar_to_id (const char *const unichar_repr) const

UNICHAR_ID	unichar_to_id (const char *const unichar_repr, int length) const

int	step (const char *str) const

bool	encodable_string (const char str, int first_bad_position) const

bool	encode_string (const char str, bool give_up_on_failure, GenericVector< UNICHAR_ID > encoding, GenericVector< char > lengths, int encoded_length) const

const char *	id_to_unichar (UNICHAR_ID id) const

const char *	id_to_unichar_ext (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, OldUncleanUnichars old_style)

void	unichar_insert (const char *const unichar_repr)

void	unichar_insert_backwards_compatible (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	save_to_file (tesseract::TFile *file) const

bool	save_to_string (STRING *str) const

bool	load_from_inmemory_file (const char *const memory, int mem_size, bool skip_fragments)

bool	load_from_inmemory_file (const char *const memory, int mem_size)

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)

bool	load_from_file (tesseract::TFile *file, bool skip_fragments)

void	post_load_setup ()

bool	major_right_to_left () const

void	set_black_and_whitelist (const char blacklist, const char whitelist, const char *unblacklist)

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)

void	set_direction (UNICHAR_ID unichar_id, UNICHARSET::Direction value)

void	set_mirror (UNICHAR_ID unichar_id, UNICHAR_ID mirror)

void	set_normed (UNICHAR_ID unichar_id, const char *normed)

void	set_normed_ids (UNICHAR_ID unichar_id)

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	get_isprivate (UNICHAR_ID unichar_id) const

bool	top_bottom_useful () const

void	set_ranges_empty ()

void	SetPropertiesFromOther (const UNICHARSET &src)

void	PartialSetPropertiesFromOther (int start_index, const UNICHARSET &src)

void	ExpandRangesFromOther (const UNICHARSET &src)

void	CopyFrom (const UNICHARSET &src)

void	AppendOtherUnicharset (const UNICHARSET &src)

bool	SizesDistinct (UNICHAR_ID id1, UNICHAR_ID id2) 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)

void	get_width_stats (UNICHAR_ID unichar_id, float width, float width_sd) const

void	set_width_stats (UNICHAR_ID unichar_id, float width, float width_sd)

void	get_bearing_stats (UNICHAR_ID unichar_id, float bearing, float bearing_sd) const

void	set_bearing_stats (UNICHAR_ID unichar_id, float bearing, float bearing_sd)

void	get_advance_stats (UNICHAR_ID unichar_id, float advance, float advance_sd) const

void	set_advance_stats (UNICHAR_ID unichar_id, float advance, float advance_sd)

bool	PropertiesIncomplete (UNICHAR_ID unichar_id) const

bool	IsSpaceDelimited (UNICHAR_ID unichar_id) const

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

Direction	get_direction (UNICHAR_ID unichar_id) const

UNICHAR_ID	get_mirror (UNICHAR_ID unichar_id) const

UNICHAR_ID	to_lower (UNICHAR_ID unichar_id) const

UNICHAR_ID	to_upper (UNICHAR_ID unichar_id) const

bool	has_special_codes () const

bool	AnyRepeatedUnicodes () 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

const char *	get_normed_unichar (UNICHAR_ID unichar_id) const

const GenericVector< UNICHAR_ID > &	normed_ids (UNICHAR_ID unichar_id) 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	thai_sid () const

int	hangul_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)

static string	CleanupString (const char *utf8_str)

static string	CleanupString (const char *utf8_str, int length)

Static Public Attributes
static TESS_API const char *	kCustomLigatures [][2]

static TESS_API const char *	kSpecialUnicharCodes [SPECIAL_UNICHAR_CODES_COUNT]

Detailed Description

Definition at line 146 of file unicharset.h.

Member Enumeration Documentation

◆ Direction

enum UNICHARSET::Direction

Enumerator
U_LEFT_TO_RIGHT
U_RIGHT_TO_LEFT
U_EUROPEAN_NUMBER
U_EUROPEAN_NUMBER_SEPARATOR
U_EUROPEAN_NUMBER_TERMINATOR
U_ARABIC_NUMBER
U_COMMON_NUMBER_SEPARATOR
U_BLOCK_SEPARATOR
U_SEGMENT_SEPARATOR
U_WHITE_SPACE_NEUTRAL
U_OTHER_NEUTRAL
U_LEFT_TO_RIGHT_EMBEDDING
U_LEFT_TO_RIGHT_OVERRIDE
U_RIGHT_TO_LEFT_ARABIC
U_RIGHT_TO_LEFT_EMBEDDING
U_RIGHT_TO_LEFT_OVERRIDE
U_POP_DIRECTIONAL_FORMAT
U_DIR_NON_SPACING_MARK
U_BOUNDARY_NEUTRAL
U_CHAR_DIRECTION_COUNT

Definition at line 157 of file unicharset.h.

                  {
       U_LEFT_TO_RIGHT               = 0,
       U_RIGHT_TO_LEFT               = 1,
       U_EUROPEAN_NUMBER             = 2,
       U_EUROPEAN_NUMBER_SEPARATOR   = 3,
       U_EUROPEAN_NUMBER_TERMINATOR  = 4,
       U_ARABIC_NUMBER               = 5,
       U_COMMON_NUMBER_SEPARATOR     = 6,
       U_BLOCK_SEPARATOR             = 7,
       U_SEGMENT_SEPARATOR           = 8,
       U_WHITE_SPACE_NEUTRAL         = 9,
       U_OTHER_NEUTRAL               = 10,
       U_LEFT_TO_RIGHT_EMBEDDING     = 11,
       U_LEFT_TO_RIGHT_OVERRIDE      = 12,
       U_RIGHT_TO_LEFT_ARABIC        = 13,
       U_RIGHT_TO_LEFT_EMBEDDING     = 14,
       U_RIGHT_TO_LEFT_OVERRIDE      = 15,
       U_POP_DIRECTIONAL_FORMAT      = 16,
       U_DIR_NON_SPACING_MARK        = 17,
       U_BOUNDARY_NEUTRAL            = 18,
       U_CHAR_DIRECTION_COUNT
   };

Constructor & Destructor Documentation

◆ UNICHARSET()

UNICHARSET::UNICHARSET ( )

Definition at line 172 of file unicharset.cpp.

                        :
     unichars(NULL),
     ids(),
     size_used(0),
     size_reserved(0),
     script_table(NULL),
     script_table_size_used(0),
     null_script("NULL") {
   clear();
   for (int i = 0; i < SPECIAL_UNICHAR_CODES_COUNT; ++i) {
     unichar_insert(kSpecialUnicharCodes[i]);
     if (i == UNICHAR_JOINED)
       set_isngram(i, true);
   }
 }

◆ ~UNICHARSET()

UNICHARSET::~UNICHARSET ( )

Definition at line 188 of file unicharset.cpp.

                         {
   clear();
 }

Member Function Documentation

◆ add_script()

int UNICHARSET::add_script ( const char * script )

Definition at line 1028 of file unicharset.cpp.

                                              {
   for (int i = 0; i < script_table_size_used; ++i) {
     if (strcmp(script, script_table[i]) == 0)
       return i;
   }
   if (script_table_size_reserved == 0) {
     script_table_size_reserved = 8;
     script_table = new char*[script_table_size_reserved];
   } else if (script_table_size_used >= script_table_size_reserved) {
     assert(script_table_size_used == script_table_size_reserved);
     script_table_size_reserved += script_table_size_reserved;
     char** new_script_table = new char*[script_table_size_reserved];
     memcpy(new_script_table, script_table,
            script_table_size_used * sizeof(char*));
     delete[] script_table;
     script_table = new_script_table;
   }
   script_table[script_table_size_used] = new char[strlen(script) + 1];
   strcpy(script_table[script_table_size_used], script);
   return script_table_size_used++;
 }

◆ AnyRepeatedUnicodes()

bool UNICHARSET::AnyRepeatedUnicodes ( ) const

Definition at line 1015 of file unicharset.cpp.

                                            {
   int start_id = 0;
   if (has_special_codes()) start_id = SPECIAL_UNICHAR_CODES_COUNT;
   for (int id = start_id; id < size_used; ++id) {
     // Convert to unicodes.
     std::vector<char32> unicodes = UNICHAR::UTF8ToUTF32(get_normed_unichar(id));
     for (int u = 1; u < unicodes.size(); ++u) {
       if (unicodes[u - 1] == unicodes[u]) return true;
     }
   }
   return false;
 }

◆ AppendOtherUnicharset()

void UNICHARSET::AppendOtherUnicharset ( const UNICHARSET & src )

Definition at line 461 of file unicharset.cpp.

                                                             {
   int initial_used = size_used;
   for (int ch = 0; ch < src.size_used; ++ch) {
     const UNICHAR_PROPERTIES& src_props = src.unichars[ch].properties;
     const char* utf8 = src.id_to_unichar(ch);
     int id = size_used;
     if (contains_unichar(utf8)) {
       id = unichar_to_id(utf8);
       // Just expand current ranges.
       unichars[id].properties.ExpandRangesFrom(src_props);
     } else {
       unichar_insert_backwards_compatible(utf8);
       unichars[id].properties.SetRangesEmpty();
     }
   }
   // Set properties, including mirror and other_case, WITHOUT reordering
   // the unicharset.
   PartialSetPropertiesFromOther(initial_used, src);
 }

◆ CleanupString() [1/2]

static string UNICHARSET::CleanupString ( const char * utf8_str )

inlinestatic

Definition at line 241 of file unicharset.h.

                                                     {
     return CleanupString(utf8_str, strlen(utf8_str));
   }

◆ CleanupString() [2/2]

string UNICHARSET::CleanupString	(	const char *	utf8_str,
		int	length
	)

static

Definition at line 1118 of file unicharset.cpp.

                                                                  {
   string result;
   result.reserve(length);
   char ch;
   while ((ch = *utf8_str) != '\0' && --length >= 0) {
     int key_index = 0;
     const char* key;
     while ((key = kCleanupMaps[key_index][0]) != nullptr) {
       int match = 0;
       while (key[match] != '\0' && key[match] == utf8_str[match]) ++match;
       if (key[match] == '\0') {
         utf8_str += match;
         break;
       }
       ++key_index;
     }
     if (key == nullptr) {
       result.push_back(ch);
       ++utf8_str;
     } else {
       result.append(kCleanupMaps[key_index][1]);
     }
   }
   return result;
 }

◆ clear()

void UNICHARSET::clear ( )

inline

Definition at line 303 of file unicharset.h.

                {
     if (script_table != NULL) {
       for (int i = 0; i < script_table_size_used; ++i)
         delete[] script_table[i];
       delete[] script_table;
       script_table = NULL;
       script_table_size_used = 0;
     }
     if (unichars != NULL) {
       delete_pointers_in_unichars();
       delete[] unichars;
       unichars = NULL;
     }
     script_table_size_reserved = 0;
     size_reserved = 0;
     size_used = 0;
     ids.clear();
     top_bottom_set_ = false;
     script_has_upper_lower_ = false;
     script_has_xheight_ = false;
     old_style_included_ = false;
     null_sid_ = 0;
     common_sid_ = 0;
     latin_sid_ = 0;
     cyrillic_sid_ = 0;
     greek_sid_ = 0;
     han_sid_ = 0;
     hiragana_sid_ = 0;
     katakana_sid_ = 0;
     thai_sid_ = 0;
     hangul_sid_ = 0;
     default_sid_ = 0;
   }

◆ common_sid()

int UNICHARSET::common_sid ( ) const

inline

Definition at line 883 of file unicharset.h.

883 { return common_sid_; }

◆ contains_unichar() [1/2]

bool UNICHARSET::contains_unichar ( const char *const unichar_repr ) const

Definition at line 668 of file unicharset.cpp.

                                                                       {
   string cleaned =
       old_style_included_ ? unichar_repr : CleanupString(unichar_repr);
   return ids.contains(cleaned.data(), cleaned.size());
 }

◆ contains_unichar() [2/2]

bool UNICHARSET::contains_unichar	(	const char *const	unichar_repr,
		int	length
	)		const

Definition at line 674 of file unicharset.cpp.

                                                     {
   if (length == 0) {
     return false;
   }
   string cleaned(unichar_repr, length);
   if (!old_style_included_) cleaned = CleanupString(unichar_repr, length);
   return ids.contains(cleaned.data(), cleaned.size());
 }

◆ contains_unichar_id()

bool UNICHARSET::contains_unichar_id ( UNICHAR_ID unichar_id ) const

inline

Definition at line 279 of file unicharset.h.

                                                         {
     return unichar_id != INVALID_UNICHAR_ID && unichar_id < size_used &&
         unichar_id >= 0;
   }

◆ CopyFrom()

void UNICHARSET::CopyFrom ( const UNICHARSET & src )

Definition at line 445 of file unicharset.cpp.

                                                {
   clear();
   for (int ch = 0; ch < src.size_used; ++ch) {
     const UNICHAR_PROPERTIES& src_props = src.unichars[ch].properties;
     const char* utf8 = src.id_to_unichar(ch);
     unichar_insert_backwards_compatible(utf8);
     unichars[ch].properties.ExpandRangesFrom(src_props);
   }
   // Set properties, including mirror and other_case, WITHOUT reordering
   // the unicharset.
   PartialSetPropertiesFromOther(0, src);
 }

◆ cyrillic_sid()

int UNICHARSET::cyrillic_sid ( ) const

inline

Definition at line 885 of file unicharset.h.

885 { return cyrillic_sid_; }

◆ debug_str() [1/2]

STRING UNICHARSET::debug_str ( UNICHAR_ID id ) const

Definition at line 340 of file unicharset.cpp.

                                                 {
   if (id == INVALID_UNICHAR_ID) return STRING(id_to_unichar(id));
   const CHAR_FRAGMENT *fragment = this->get_fragment(id);
   if (fragment) {
     return fragment->to_string();
   }
   const char* str = id_to_unichar(id);
   STRING result = debug_utf8_str(str);
   // Append a for lower alpha, A for upper alpha, and x if alpha but neither.
   if (get_isalpha(id)) {
     if (get_islower(id))
       result += "a";
     else if (get_isupper(id))
       result += "A";
     else
       result += "x";
   }
   // Append 0 if a digit.
   if (get_isdigit(id)) {
     result += "0";
   }
   // Append p is a punctuation symbol.
   if (get_ispunctuation(id)) {
     result += "p";
   }
   return result;
 }

◆ debug_str() [2/2]

STRING UNICHARSET::debug_str ( const char * unichar_repr ) const

inline

Definition at line 249 of file unicharset.h.

                                                     {
     return debug_str(unichar_to_id(unichar_repr));
   }

◆ debug_utf8_str()

STRING UNICHARSET::debug_utf8_str ( const char * str )

static

Definition at line 316 of file unicharset.cpp.

                                                  {
   STRING result = str;
   result += " [";
   int step = 1;
   // Chop into unicodes and code each as hex.
   for (int i = 0; str[i] != '\0'; i += step) {
     char hex[sizeof(int) * 2 + 1];
     step = UNICHAR::utf8_step(str + i);
     if (step == 0) {
       step = 1;
       sprintf(hex, "%x", str[i]);
     } else {
       UNICHAR ch(str + i, step);
       sprintf(hex, "%x", ch.first_uni());
     }
     result += hex;
     result += " ";
   }
   result += "]";
   return result;
 }

◆ default_sid()

int UNICHARSET::default_sid ( ) const

inline

Definition at line 892 of file unicharset.h.

892 { return default_sid_; }

◆ delete_pointers_in_unichars()

void UNICHARSET::delete_pointers_in_unichars ( )

inline

Definition at line 293 of file unicharset.h.

                                      {
     for (int i = 0; i < size_used; ++i) {
       if (unichars[i].properties.fragment != NULL) {
         delete unichars[i].properties.fragment;
         unichars[i].properties.fragment = NULL;
       }
     }
   }

◆ encodable_string()

bool UNICHARSET::encodable_string	(	const char *	str,
		int *	first_bad_position
	)		const

Definition at line 241 of file unicharset.cpp.

                                                                  {
   GenericVector<UNICHAR_ID> encoding;
   return encode_string(str, true, &encoding, NULL, first_bad_position);
 }

◆ encode_string()

bool UNICHARSET::encode_string	(	const char *	str,
		bool	give_up_on_failure,
		GenericVector< UNICHAR_ID > *	encoding,
		GenericVector< char > *	lengths,
		int *	encoded_length
	)		const

Definition at line 256 of file unicharset.cpp.

                                                           {
   GenericVector<UNICHAR_ID> working_encoding;
   GenericVector<char> working_lengths;
   GenericVector<char> best_lengths;
   encoding->truncate(0);  // Just in case str is empty.
   int str_length = strlen(str);
   int str_pos = 0;
   bool perfect = true;
   while (str_pos < str_length) {
     encode_string(str, str_pos, str_length, &working_encoding, &working_lengths,
                   &str_pos, encoding, &best_lengths);
     if (str_pos < str_length) {
       // This is a non-match. Skip one utf-8 character.
       perfect = false;
       if (give_up_on_failure) break;
       int step = UNICHAR::utf8_step(str + str_pos);
       if (step == 0) step = 1;
       encoding->push_back(INVALID_UNICHAR_ID);
       best_lengths.push_back(step);
       str_pos += step;
       working_encoding = *encoding;
       working_lengths = best_lengths;
     }
   }
   if (lengths != NULL) *lengths = best_lengths;
   if (encoded_length != NULL) *encoded_length = str_pos;
   return perfect;
 }

◆ eq()

bool UNICHARSET::eq	(	UNICHAR_ID	unichar_id,
		const char *const	unichar_repr
	)		const

Definition at line 684 of file unicharset.cpp.

                                                           {
   return strcmp(this->id_to_unichar(unichar_id), unichar_repr) == 0;
 }

◆ ExpandRangesFromOther()

void UNICHARSET::ExpandRangesFromOther ( const UNICHARSET & src )

Definition at line 432 of file unicharset.cpp.

                                                             {
   for (int ch = 0; ch < size_used; ++ch) {
     const char* utf8 = id_to_unichar(ch);
     UNICHAR_PROPERTIES properties;
     if (src.GetStrProperties(utf8, &properties)) {
       // Expand just the ranges from properties.
       unichars[ch].properties.ExpandRangesFrom(properties);
     }
   }
 }

◆ get_advance_stats()

void UNICHARSET::get_advance_stats	(	UNICHAR_ID	unichar_id,
		float *	advance,
		float *	advance_sd
	)		const

inline

Definition at line 629 of file unicharset.h.

                                                                   {
     if (INVALID_UNICHAR_ID == unichar_id) {
       *advance = *advance_sd = 0;
       return;
     }
     ASSERT_HOST(contains_unichar_id(unichar_id));
     *advance = unichars[unichar_id].properties.advance;
     *advance_sd = unichars[unichar_id].properties.advance_sd;
   }

◆ get_bearing_stats()

void UNICHARSET::get_bearing_stats	(	UNICHAR_ID	unichar_id,
		float *	bearing,
		float *	bearing_sd
	)		const

inline

Definition at line 612 of file unicharset.h.

                                                                   {
     if (INVALID_UNICHAR_ID == unichar_id) {
       *bearing = *bearing_sd = 0.0f;
       return;
     }
     ASSERT_HOST(contains_unichar_id(unichar_id));
     *bearing = unichars[unichar_id].properties.bearing;
     *bearing_sd = unichars[unichar_id].properties.bearing_sd;
   }

◆ get_chartype() [1/2]

char UNICHARSET::get_chartype ( UNICHAR_ID unichar_id ) const

Definition at line 614 of file unicharset.cpp.

                                                  {
   if (this->get_isupper(id)) return 'A';
   if (this->get_islower(id)) return 'a';
   if (this->get_isalpha(id)) return 'x';
   if (this->get_isdigit(id)) return '0';
   if (this->get_ispunctuation(id)) return 'p';
   return 0;
 }

◆ get_chartype() [2/2]

char UNICHARSET::get_chartype ( const char *const unichar_repr ) const

inline

Definition at line 770 of file unicharset.h.

                                                           {
     return get_chartype(unichar_to_id(unichar_repr));
   }

◆ get_direction()

Direction UNICHARSET::get_direction ( UNICHAR_ID unichar_id ) const

inline

Definition at line 689 of file unicharset.h.

                                                        {
      if (INVALID_UNICHAR_ID == unichar_id) return UNICHARSET::U_OTHER_NEUTRAL;
      ASSERT_HOST(contains_unichar_id(unichar_id));
      return unichars[unichar_id].properties.direction;
    }

◆ get_enabled()

bool UNICHARSET::get_enabled ( UNICHAR_ID unichar_id ) const

inline

Definition at line 877 of file unicharset.h.

                                                 {
     return unichars[unichar_id].properties.enabled;
   }

◆ get_fragment() [1/2]

const CHAR_FRAGMENT* UNICHARSET::get_fragment ( UNICHAR_ID unichar_id ) const

inline

Definition at line 733 of file unicharset.h.

                                                                  {
     if (INVALID_UNICHAR_ID == unichar_id) return NULL;
     ASSERT_HOST(contains_unichar_id(unichar_id));
     return unichars[unichar_id].properties.fragment;
   }

◆ get_fragment() [2/2]

const CHAR_FRAGMENT* UNICHARSET::get_fragment ( const char *const unichar_repr ) const

inline

Definition at line 783 of file unicharset.h.

                                                                           {
     if (unichar_repr == NULL || unichar_repr[0] == '\0' ||
         !ids.contains(unichar_repr, false)) {
       return NULL;
     }
     return get_fragment(unichar_to_id(unichar_repr));
   }

◆ get_isalpha() [1/3]

bool UNICHARSET::get_isalpha ( UNICHAR_ID unichar_id ) const

inline

Definition at line 490 of file unicharset.h.

                                                 {
     if (INVALID_UNICHAR_ID == unichar_id) return false;
     ASSERT_HOST(contains_unichar_id(unichar_id));
     return unichars[unichar_id].properties.isalpha;
   }

◆ get_isalpha() [2/3]

bool UNICHARSET::get_isalpha ( const char *const unichar_repr ) const

inline

Definition at line 740 of file unicharset.h.

                                                          {
     return get_isalpha(unichar_to_id(unichar_repr));
   }

◆ get_isalpha() [3/3]

bool UNICHARSET::get_isalpha	(	const char *const	unichar_repr,
		int	length
	)		const

inline

Definition at line 793 of file unicharset.h.

                                  {
     return get_isalpha(unichar_to_id(unichar_repr, length));
   }

◆ get_isdigit() [1/3]

bool UNICHARSET::get_isdigit ( UNICHAR_ID unichar_id ) const

inline

Definition at line 511 of file unicharset.h.

                                                 {
     if (INVALID_UNICHAR_ID == unichar_id) return false;
     ASSERT_HOST(contains_unichar_id(unichar_id));
     return unichars[unichar_id].properties.isdigit;
   }

◆ get_isdigit() [2/3]

bool UNICHARSET::get_isdigit ( const char *const unichar_repr ) const

inline

Definition at line 755 of file unicharset.h.

                                                          {
     return get_isdigit(unichar_to_id(unichar_repr));
   }

◆ get_isdigit() [3/3]

bool UNICHARSET::get_isdigit	(	const char *const	unichar_repr,
		int	length
	)		const

inline

Definition at line 814 of file unicharset.h.

                                  {
     return get_isdigit(unichar_to_id(unichar_repr, length));
   }

◆ get_islower() [1/3]

bool UNICHARSET::get_islower ( UNICHAR_ID unichar_id ) const

inline

Definition at line 497 of file unicharset.h.

                                                 {
     if (INVALID_UNICHAR_ID == unichar_id) return false;
     ASSERT_HOST(contains_unichar_id(unichar_id));
     return unichars[unichar_id].properties.islower;
   }

◆ get_islower() [2/3]

bool UNICHARSET::get_islower ( const char *const unichar_repr ) const

inline

Definition at line 745 of file unicharset.h.

                                                          {
     return get_islower(unichar_to_id(unichar_repr));
   }

◆ get_islower() [3/3]

bool UNICHARSET::get_islower	(	const char *const	unichar_repr,
		int	length
	)		const

inline

Definition at line 800 of file unicharset.h.

                                  {
     return get_islower(unichar_to_id(unichar_repr, length));
   }

◆ get_isngram()

bool UNICHARSET::get_isngram ( UNICHAR_ID unichar_id ) const

inline

Definition at line 525 of file unicharset.h.

                                                 {
     if (INVALID_UNICHAR_ID == unichar_id) return false;
     ASSERT_HOST(contains_unichar_id(unichar_id));
     return unichars[unichar_id].properties.isngram;
   }

◆ get_isprivate()

bool UNICHARSET::get_isprivate ( UNICHAR_ID unichar_id ) const

Definition at line 385 of file unicharset.cpp.

                                                           {
   UNICHAR uc(id_to_unichar(unichar_id), -1);
   int uni = uc.first_uni();
   return (uni >= 0xE000 && uni <= 0xF8FF);
 }

◆ get_ispunctuation() [1/3]

bool UNICHARSET::get_ispunctuation ( UNICHAR_ID unichar_id ) const

inline

Definition at line 518 of file unicharset.h.

                                                       {
     if (INVALID_UNICHAR_ID == unichar_id) return false;
     ASSERT_HOST(contains_unichar_id(unichar_id));
     return unichars[unichar_id].properties.ispunctuation;
   }

◆ get_ispunctuation() [2/3]

bool UNICHARSET::get_ispunctuation ( const char *const unichar_repr ) const

inline

Definition at line 760 of file unicharset.h.

                                                                {
     return get_ispunctuation(unichar_to_id(unichar_repr));
   }

◆ get_ispunctuation() [3/3]

bool UNICHARSET::get_ispunctuation	(	const char *const	unichar_repr,
		int	length
	)		const

inline

Definition at line 821 of file unicharset.h.

                                             {
     return get_ispunctuation(unichar_to_id(unichar_repr, length));
   }

◆ get_isupper() [1/3]

bool UNICHARSET::get_isupper ( UNICHAR_ID unichar_id ) const

inline

Definition at line 504 of file unicharset.h.

                                                 {
     if (INVALID_UNICHAR_ID == unichar_id) return false;
     ASSERT_HOST(contains_unichar_id(unichar_id));
     return unichars[unichar_id].properties.isupper;
   }

◆ get_isupper() [2/3]

bool UNICHARSET::get_isupper ( const char *const unichar_repr ) const

inline

Definition at line 750 of file unicharset.h.

                                                          {
     return get_isupper(unichar_to_id(unichar_repr));
   }

◆ get_isupper() [3/3]

bool UNICHARSET::get_isupper	(	const char *const	unichar_repr,
		int	length
	)		const

inline

Definition at line 807 of file unicharset.h.

                                  {
     return get_isupper(unichar_to_id(unichar_repr, length));
   }

◆ get_mirror()

UNICHAR_ID UNICHARSET::get_mirror ( UNICHAR_ID unichar_id ) const

inline

Definition at line 696 of file unicharset.h.

                                                      {
     if (INVALID_UNICHAR_ID == unichar_id) return INVALID_UNICHAR_ID;
     ASSERT_HOST(contains_unichar_id(unichar_id));
     return unichars[unichar_id].properties.mirror;
   }

◆ get_normed_unichar()

const char* UNICHARSET::get_normed_unichar ( UNICHAR_ID unichar_id ) const

inline

Definition at line 827 of file unicharset.h.

                                                               {
     if (unichar_id == UNICHAR_SPACE) return " ";
     return unichars[unichar_id].properties.normed.string();
   }

◆ get_other_case()

UNICHAR_ID UNICHARSET::get_other_case ( UNICHAR_ID unichar_id ) const

inline

Definition at line 682 of file unicharset.h.

                                                          {
     if (INVALID_UNICHAR_ID == unichar_id) return INVALID_UNICHAR_ID;
     ASSERT_HOST(contains_unichar_id(unichar_id));
     return unichars[unichar_id].properties.other_case;
   }

◆ get_properties() [1/2]

unsigned int UNICHARSET::get_properties ( UNICHAR_ID unichar_id ) const

Definition at line 599 of file unicharset.cpp.

                                                            {
   unsigned int properties = 0;
   if (this->get_isalpha(id))
     properties |= ISALPHA_MASK;
   if (this->get_islower(id))
     properties |= ISLOWER_MASK;
   if (this->get_isupper(id))
     properties |= ISUPPER_MASK;
   if (this->get_isdigit(id))
     properties |= ISDIGIT_MASK;
   if (this->get_ispunctuation(id))
     properties |= ISPUNCTUATION_MASK;
   return properties;
 }

◆ get_properties() [2/2]

unsigned int UNICHARSET::get_properties ( const char *const unichar_repr ) const

inline

Definition at line 766 of file unicharset.h.

                                                                     {
     return get_properties(unichar_to_id(unichar_repr));
   }

◆ get_script() [1/3]

int UNICHARSET::get_script ( UNICHAR_ID unichar_id ) const

inline

Definition at line 662 of file unicharset.h.

                                               {
     if (INVALID_UNICHAR_ID == unichar_id) return null_sid_;
     ASSERT_HOST(contains_unichar_id(unichar_id));
     return unichars[unichar_id].properties.script_id;
   }

◆ get_script() [2/3]

int UNICHARSET::get_script ( const char *const unichar_repr ) const

inline

Definition at line 777 of file unicharset.h.

                                                        {
     return get_script(unichar_to_id(unichar_repr));
   }

◆ get_script() [3/3]

int UNICHARSET::get_script	(	const char *const	unichar_repr,
		int	length
	)		const

inline

Definition at line 842 of file unicharset.h.

                                    {
     return get_script(unichar_to_id(unichar_repr, length));
   }

◆ get_script_from_script_id()

const char* UNICHARSET::get_script_from_script_id ( int id ) const

inline

Definition at line 853 of file unicharset.h.

                                                       {
     if (id >= script_table_size_used || id < 0)
       return null_script;
     return script_table[id];
   }

◆ get_script_id_from_name()

int UNICHARSET::get_script_id_from_name ( const char * script_name ) const

Definition at line 1107 of file unicharset.cpp.

                                                                      {
   for (int i = 0; i < script_table_size_used; ++i) {
     if (strcmp(script_name, script_table[i]) == 0)
       return i;
   }
   return 0;  // 0 is always the null_script
 }

◆ get_script_table_size()

int UNICHARSET::get_script_table_size ( ) const

inline

Definition at line 848 of file unicharset.h.

                                     {
     return script_table_size_used;
   }

◆ get_top_bottom()

void UNICHARSET::get_top_bottom	(	UNICHAR_ID	unichar_id,
		int *	min_bottom,
		int *	max_bottom,
		int *	min_top,
		int *	max_top
	)		const

inline

Definition at line 567 of file unicharset.h.

                                                         {
     if (INVALID_UNICHAR_ID == unichar_id) {
       *min_bottom = *min_top = 0;
       *max_bottom = *max_top = 256;  // kBlnCellHeight
       return;
     }
     ASSERT_HOST(contains_unichar_id(unichar_id));
     *min_bottom = unichars[unichar_id].properties.min_bottom;
     *max_bottom = unichars[unichar_id].properties.max_bottom;
     *min_top = unichars[unichar_id].properties.min_top;
     *max_top = unichars[unichar_id].properties.max_top;
   }

◆ get_width_stats()

void UNICHARSET::get_width_stats	(	UNICHAR_ID	unichar_id,
		float *	width,
		float *	width_sd
	)		const

inline

Definition at line 595 of file unicharset.h.

                                                             {
     if (INVALID_UNICHAR_ID == unichar_id) {
       *width = 0.0f;
       *width_sd = 0.0f;;
       return;
     }
     ASSERT_HOST(contains_unichar_id(unichar_id));
     *width = unichars[unichar_id].properties.width;
     *width_sd = unichars[unichar_id].properties.width_sd;
   }

◆ greek_sid()

int UNICHARSET::greek_sid ( ) const

inline

Definition at line 886 of file unicharset.h.

886 { return greek_sid_; }

◆ han_sid()

int UNICHARSET::han_sid ( ) const

inline

Definition at line 887 of file unicharset.h.

887 { return han_sid_; }

◆ hangul_sid()

int UNICHARSET::hangul_sid ( ) const

inline

Definition at line 891 of file unicharset.h.

891 { return hangul_sid_; }

◆ has_special_codes()

bool UNICHARSET::has_special_codes ( ) const

inline

Definition at line 721 of file unicharset.h.

                                  {
     return get_fragment(UNICHAR_BROKEN) != NULL &&
         strcmp(id_to_unichar(UNICHAR_BROKEN),
                kSpecialUnicharCodes[UNICHAR_BROKEN]) == 0;
   }

◆ hiragana_sid()

int UNICHARSET::hiragana_sid ( ) const

inline

Definition at line 888 of file unicharset.h.

888 { return hiragana_sid_; }

◆ id_to_unichar()

const char * UNICHARSET::id_to_unichar ( UNICHAR_ID id ) const

Definition at line 288 of file unicharset.cpp.

                                                          {
   if (id == INVALID_UNICHAR_ID) {
     return INVALID_UNICHAR;
   }
   ASSERT_HOST(id < this->size());
   return unichars[id].representation;
 }

◆ id_to_unichar_ext()

const char * UNICHARSET::id_to_unichar_ext ( UNICHAR_ID id ) const

Definition at line 296 of file unicharset.cpp.

                                                              {
   if (id == INVALID_UNICHAR_ID) {
     return INVALID_UNICHAR;
   }
   ASSERT_HOST(id < this->size());
   // Resolve from the kCustomLigatures table if this is a private encoding.
   if (get_isprivate(id)) {
     const char* ch = id_to_unichar(id);
     for (int i = 0; kCustomLigatures[i][0] != NULL; ++i) {
       if (!strcmp(ch, kCustomLigatures[i][1])) {
         return kCustomLigatures[i][0];
       }
     }
   }
   // Otherwise return the stored representation.
   return unichars[id].representation;
 }

◆ is_null_script()

bool UNICHARSET::is_null_script ( const char * script ) const

inline

Definition at line 867 of file unicharset.h.

                                                 {
     return script == null_script;
   }

◆ IsSpaceDelimited()

bool UNICHARSET::IsSpaceDelimited ( UNICHAR_ID unichar_id ) const

inline

Definition at line 651 of file unicharset.h.

                                                      {
     if (INVALID_UNICHAR_ID == unichar_id) return true;
     int script_id = get_script(unichar_id);
     return script_id != han_sid_ && script_id != thai_sid_ &&
            script_id != hangul_sid_ && script_id != hiragana_sid_ &&
            script_id != katakana_sid_;
   }

◆ katakana_sid()

int UNICHARSET::katakana_sid ( ) const

inline

Definition at line 889 of file unicharset.h.

889 { return katakana_sid_; }

◆ latin_sid()

int UNICHARSET::latin_sid ( ) const

inline

Definition at line 884 of file unicharset.h.

884 { return latin_sid_; }

◆ load_from_file() [1/5]

bool UNICHARSET::load_from_file	(	const char *const	filename,
		bool	skip_fragments
	)

inline

Definition at line 387 of file unicharset.h.

                                                                        {
     FILE* file = fopen(filename, "rb");
     if (file == NULL) return false;
     bool result = load_from_file(file, skip_fragments);
     fclose(file);
     return result;
   }

◆ load_from_file() [2/5]

bool UNICHARSET::load_from_file ( const char *const filename )

inline

Definition at line 395 of file unicharset.h.

                                                   {
     return load_from_file(filename, false);
   }

◆ load_from_file() [3/5]

bool UNICHARSET::load_from_file	(	FILE *	file,
		bool	skip_fragments
	)

Definition at line 772 of file unicharset.cpp.

                                                                {
   LocalFilePointer lfp(file);
   TessResultCallback2<char *, char *, int> *fgets_cb =
       NewPermanentTessCallback(&lfp, &LocalFilePointer::fgets);
   bool success = load_via_fgets(fgets_cb, skip_fragments);
   delete fgets_cb;
   return success;
 }

◆ load_from_file() [4/5]

bool UNICHARSET::load_from_file ( FILE * file )

inline

Definition at line 402 of file unicharset.h.

402 { return load_from_file(file, false); }

UNICHARSET::load_from_file

bool load_from_file(const char *const filename, bool skip_fragments)

Definition: unicharset.h:387

◆ load_from_file() [5/5]

bool UNICHARSET::load_from_file	(	tesseract::TFile *	file,
		bool	skip_fragments
	)

Definition at line 781 of file unicharset.cpp.

                                                                          {
   TessResultCallback2<char *, char *, int> *fgets_cb =
       NewPermanentTessCallback(file, &tesseract::TFile::FGets);
   bool success = load_via_fgets(fgets_cb, skip_fragments);
   delete fgets_cb;
   return success;
 }

◆ load_from_inmemory_file() [1/2]

bool UNICHARSET::load_from_inmemory_file	(	const char *const	memory,
		int	mem_size,
		bool	skip_fragments
	)

Definition at line 752 of file unicharset.cpp.

                                                            {
   InMemoryFilePointer mem_fp(memory, mem_size);
   TessResultCallback2<char *, char *, int> *fgets_cb =
       NewPermanentTessCallback(&mem_fp, &InMemoryFilePointer::fgets);
   bool success = load_via_fgets(fgets_cb, skip_fragments);
   delete fgets_cb;
   return success;
 }

◆ load_from_inmemory_file() [2/2]

bool UNICHARSET::load_from_inmemory_file	(	const char *const	memory,
		int	mem_size
	)

inline

Definition at line 380 of file unicharset.h.

                                                                        {
     return load_from_inmemory_file(memory, mem_size, false);
   }

◆ major_right_to_left()

bool UNICHARSET::major_right_to_left ( ) const

Definition at line 960 of file unicharset.cpp.

                                            {
   int ltr_count = 0;
   int rtl_count = 0;
   for (int id = 0; id < size_used; ++id) {
     int dir = get_direction(id);
     if (dir == UNICHARSET::U_LEFT_TO_RIGHT) ltr_count++;
     if (dir == UNICHARSET::U_RIGHT_TO_LEFT ||
         dir == UNICHARSET::U_RIGHT_TO_LEFT_ARABIC ||
         dir == UNICHARSET::U_ARABIC_NUMBER) rtl_count++;
   }
   return rtl_count > ltr_count;
 }

◆ normed_ids()

const GenericVector<UNICHAR_ID>& UNICHARSET::normed_ids ( UNICHAR_ID unichar_id ) const

inline

Definition at line 834 of file unicharset.h.

                                                                            {
     return unichars[unichar_id].properties.normed_ids;
   }

◆ null_sid()

int UNICHARSET::null_sid ( ) const

inline

Definition at line 882 of file unicharset.h.

882 { return null_sid_; }

◆ PartialSetPropertiesFromOther()

void UNICHARSET::PartialSetPropertiesFromOther	(	int	start_index,
		const UNICHARSET &	src
	)

Definition at line 402 of file unicharset.cpp.

                                                                       {
   for (int ch = start_index; ch < size_used; ++ch) {
     const char* utf8 = id_to_unichar(ch);
     UNICHAR_PROPERTIES properties;
     if (src.GetStrProperties(utf8, &properties)) {
       // Setup the script_id, other_case, and mirror properly.
       const char* script = src.get_script_from_script_id(properties.script_id);
       properties.script_id = add_script(script);
       const char* other_case = src.id_to_unichar(properties.other_case);
       if (contains_unichar(other_case)) {
         properties.other_case = unichar_to_id(other_case);
       } else {
         properties.other_case = ch;
       }
       const char* mirror_str = src.id_to_unichar(properties.mirror);
       if (contains_unichar(mirror_str)) {
         properties.mirror = unichar_to_id(mirror_str);
       } else {
         properties.mirror = ch;
       }
       unichars[ch].properties.CopyFrom(properties);
       set_normed_ids(ch);
     }
   }
 }

◆ post_load_setup()

void UNICHARSET::post_load_setup ( )

Definition at line 894 of file unicharset.cpp.

                                  {
   // Number of alpha chars with the case property minus those without,
   // in order to determine that half the alpha chars have case.
   int net_case_alphas = 0;
   int x_height_alphas = 0;
   int cap_height_alphas = 0;
   top_bottom_set_ = false;
   for (UNICHAR_ID id = 0; id < size_used; ++id) {
     int min_bottom = 0;
     int max_bottom = MAX_UINT8;
     int min_top = 0;
     int max_top = MAX_UINT8;
     get_top_bottom(id, &min_bottom, &max_bottom, &min_top, &max_top);
     if (min_top > 0)
       top_bottom_set_ = true;
     if (get_isalpha(id)) {
       if (get_islower(id) || get_isupper(id))
         ++net_case_alphas;
       else
         --net_case_alphas;
       if (min_top < kMeanlineThreshold && max_top < kMeanlineThreshold)
         ++x_height_alphas;
       else if (min_top > kMeanlineThreshold && max_top > kMeanlineThreshold)
         ++cap_height_alphas;
     }
     set_normed_ids(id);
   }
 
   script_has_upper_lower_ = net_case_alphas > 0;
   script_has_xheight_ = script_has_upper_lower_ ||
       (x_height_alphas > cap_height_alphas * kMinXHeightFraction &&
        cap_height_alphas > x_height_alphas * kMinCapHeightFraction);
 
   null_sid_ = get_script_id_from_name(null_script);
   ASSERT_HOST(null_sid_ == 0);
   common_sid_ = get_script_id_from_name("Common");
   latin_sid_ = get_script_id_from_name("Latin");
   cyrillic_sid_ = get_script_id_from_name("Cyrillic");
   greek_sid_ = get_script_id_from_name("Greek");
   han_sid_ = get_script_id_from_name("Han");
   hiragana_sid_ = get_script_id_from_name("Hiragana");
   katakana_sid_ = get_script_id_from_name("Katakana");
   thai_sid_ = get_script_id_from_name("Thai");
   hangul_sid_ = get_script_id_from_name("Hangul");
 
   // Compute default script. Use the highest-counting alpha script, that is
   // not the common script, as that still contains some "alphas".
   int* script_counts = new int[script_table_size_used];
   memset(script_counts, 0, sizeof(*script_counts) * script_table_size_used);
   for (int id = 0; id < size_used; ++id) {
     if (get_isalpha(id)) {
       ++script_counts[get_script(id)];
     }
   }
   default_sid_ = 0;
   for (int s = 1; s < script_table_size_used; ++s) {
     if (script_counts[s] > script_counts[default_sid_] && s != common_sid_)
       default_sid_ = s;
   }
   delete [] script_counts;
 }

◆ PropertiesIncomplete()

bool UNICHARSET::PropertiesIncomplete ( UNICHAR_ID unichar_id ) const

inline

Definition at line 645 of file unicharset.h.

                                                          {
     return unichars[unichar_id].properties.AnyRangeEmpty();
   }

◆ reserve()

void UNICHARSET::reserve ( int unichars_number )

Definition at line 192 of file unicharset.cpp.

                                             {
   if (unichars_number > size_reserved) {
     UNICHAR_SLOT* unichars_new = new UNICHAR_SLOT[unichars_number];
     for (int i = 0; i < size_used; ++i)
       unichars_new[i] = unichars[i];
     for (int j = size_used; j < unichars_number; ++j) {
       unichars_new[j].properties.script_id = add_script(null_script);
     }
     delete[] unichars;
     unichars = unichars_new;
     size_reserved = unichars_number;
   }
 }

◆ save_to_file() [1/3]

bool UNICHARSET::save_to_file ( const char *const filename ) const

inline

Definition at line 347 of file unicharset.h.

                                                        {
     FILE* file = fopen(filename, "w+b");
     if (file == NULL) return false;
     bool result = save_to_file(file);
     fclose(file);
     return result;
   }

◆ save_to_file() [2/3]

bool UNICHARSET::save_to_file ( FILE * file ) const

inline

Definition at line 357 of file unicharset.h.

                                       {
     STRING str;
     if (!save_to_string(&str)) return false;
     if (fwrite(&str[0], str.length(), 1, file) != 1) return false;
     return true;
   }

◆ save_to_file() [3/3]

bool UNICHARSET::save_to_file ( tesseract::TFile * file ) const

inline

Definition at line 363 of file unicharset.h.

                                                 {
     STRING str;
     if (!save_to_string(&str)) return false;
     if (file->FWrite(&str[0], str.length(), 1) != 1) return false;
     return true;
   }

◆ save_to_string()

bool UNICHARSET::save_to_string ( STRING * str ) const

Definition at line 689 of file unicharset.cpp.

                                                  {
   const int kFileBufSize = 1024;
   char buffer[kFileBufSize + 1];
   snprintf(buffer, kFileBufSize, "%d\n", this->size());
   *str = buffer;
   for (UNICHAR_ID id = 0; id < this->size(); ++id) {
     int min_bottom, max_bottom, min_top, max_top;
     get_top_bottom(id, &min_bottom, &max_bottom, &min_top, &max_top);
     float width, width_sd;
     get_width_stats(id, &width, &width_sd);
     float bearing, bearing_sd;
     get_bearing_stats(id, &bearing, &bearing_sd);
     float advance, advance_sd;
     get_advance_stats(id, &advance, &advance_sd);
     unsigned int properties = this->get_properties(id);
     if (strcmp(this->id_to_unichar(id), " ") == 0) {
       snprintf(buffer, kFileBufSize, "%s %x %s %d\n", "NULL", properties,
               this->get_script_from_script_id(this->get_script(id)),
               this->get_other_case(id));
     } else {
       snprintf(buffer, kFileBufSize,
               "%s %x %d,%d,%d,%d,%g,%g,%g,%g,%g,%g %s %d %d %d %s\t# %s\n",
               this->id_to_unichar(id), properties,
               min_bottom, max_bottom, min_top, max_top, width, width_sd,
               bearing, bearing_sd, advance, advance_sd,
               this->get_script_from_script_id(this->get_script(id)),
               this->get_other_case(id), this->get_direction(id),
               this->get_mirror(id), this->get_normed_unichar(id),
               this->debug_str(id).string());
     }
     *str += buffer;
   }
   return true;
 }

◆ script_has_upper_lower()

bool UNICHARSET::script_has_upper_lower ( ) const

inline

Definition at line 895 of file unicharset.h.

                                       {
     return script_has_upper_lower_;
   }

◆ script_has_xheight()

bool UNICHARSET::script_has_xheight ( ) const

inline

Definition at line 902 of file unicharset.h.

                                   {
     return script_has_xheight_;
   }

◆ set_advance_stats()

void UNICHARSET::set_advance_stats	(	UNICHAR_ID	unichar_id,
		float	advance,
		float	advance_sd
	)

inline

Definition at line 639 of file unicharset.h.

                                                           {
     unichars[unichar_id].properties.advance = advance;
     unichars[unichar_id].properties.advance_sd = advance_sd;
   }

◆ set_bearing_stats()

void UNICHARSET::set_bearing_stats	(	UNICHAR_ID	unichar_id,
		float	bearing,
		float	bearing_sd
	)

inline

Definition at line 622 of file unicharset.h.

                                                           {
     unichars[unichar_id].properties.bearing = bearing;
     unichars[unichar_id].properties.bearing_sd = bearing_sd;
   }

◆ set_black_and_whitelist()

void UNICHARSET::set_black_and_whitelist	(	const char *	blacklist,
		const char *	whitelist,
		const char *	unblacklist
	)

Definition at line 977 of file unicharset.cpp.

                                                                   {
   bool def_enabled = whitelist == NULL || whitelist[0] == '\0';
   // Set everything to default
   for (int ch = 0; ch < size_used; ++ch)
     unichars[ch].properties.enabled = def_enabled;
   if (!def_enabled) {
     // Enable the whitelist.
     GenericVector<UNICHAR_ID> encoding;
     encode_string(whitelist, false, &encoding, NULL, NULL);
     for (int i = 0; i < encoding.size(); ++i) {
       if (encoding[i] != INVALID_UNICHAR_ID)
         unichars[encoding[i]].properties.enabled = true;
     }
   }
   if (blacklist != NULL && blacklist[0] != '\0') {
     // Disable the blacklist.
     GenericVector<UNICHAR_ID> encoding;
     encode_string(blacklist, false, &encoding, NULL, NULL);
     for (int i = 0; i < encoding.size(); ++i) {
       if (encoding[i] != INVALID_UNICHAR_ID)
         unichars[encoding[i]].properties.enabled = false;
     }
   }
   if (unblacklist != NULL && unblacklist[0] != '\0') {
     // Re-enable the unblacklist.
     GenericVector<UNICHAR_ID> encoding;
     encode_string(unblacklist, false, &encoding, NULL, NULL);
     for (int i = 0; i < encoding.size(); ++i) {
       if (encoding[i] != INVALID_UNICHAR_ID)
         unichars[encoding[i]].properties.enabled = true;
     }
   }
 }

◆ set_direction()

void UNICHARSET::set_direction	(	UNICHAR_ID	unichar_id,
		UNICHARSET::Direction	value
	)

inline

Definition at line 471 of file unicharset.h.

                                                                        {
     unichars[unichar_id].properties.direction = value;
   }

◆ set_isalpha()

void UNICHARSET::set_isalpha	(	UNICHAR_ID	unichar_id,
		bool	value
	)

inline

Definition at line 430 of file unicharset.h.

                                                       {
     unichars[unichar_id].properties.isalpha = value;
   }

◆ set_isdigit()

void UNICHARSET::set_isdigit	(	UNICHAR_ID	unichar_id,
		bool	value
	)

inline

Definition at line 445 of file unicharset.h.

                                                       {
     unichars[unichar_id].properties.isdigit = value;
   }

◆ set_islower()

void UNICHARSET::set_islower	(	UNICHAR_ID	unichar_id,
		bool	value
	)

inline

Definition at line 435 of file unicharset.h.

                                                       {
     unichars[unichar_id].properties.islower = value;
   }

◆ set_isngram()

void UNICHARSET::set_isngram	(	UNICHAR_ID	unichar_id,
		bool	value
	)

inline

Definition at line 455 of file unicharset.h.

                                                       {
     unichars[unichar_id].properties.isngram = value;
   }

◆ set_ispunctuation()

void UNICHARSET::set_ispunctuation	(	UNICHAR_ID	unichar_id,
		bool	value
	)

inline

Definition at line 450 of file unicharset.h.

                                                             {
     unichars[unichar_id].properties.ispunctuation = value;
   }

◆ set_isupper()

void UNICHARSET::set_isupper	(	UNICHAR_ID	unichar_id,
		bool	value
	)

inline

Definition at line 440 of file unicharset.h.

                                                       {
     unichars[unichar_id].properties.isupper = value;
   }

◆ set_mirror()

void UNICHARSET::set_mirror	(	UNICHAR_ID	unichar_id,
		UNICHAR_ID	mirror
	)

inline

Definition at line 476 of file unicharset.h.

                                                             {
     unichars[unichar_id].properties.mirror = mirror;
   }

◆ set_normed()

void UNICHARSET::set_normed	(	UNICHAR_ID	unichar_id,
		const char *	normed
	)

inline

Definition at line 481 of file unicharset.h.

                                                              {
     unichars[unichar_id].properties.normed = normed;
     unichars[unichar_id].properties.normed_ids.truncate(0);
   }

◆ set_normed_ids()

void UNICHARSET::set_normed_ids ( UNICHAR_ID unichar_id )

Definition at line 370 of file unicharset.cpp.

                                                      {
   unichars[unichar_id].properties.normed_ids.truncate(0);
   if (unichar_id == UNICHAR_SPACE && id_to_unichar(unichar_id)[0] == ' ') {
     unichars[unichar_id].properties.normed_ids.push_back(UNICHAR_SPACE);
   } else if (!encode_string(unichars[unichar_id].properties.normed.string(),
                             true, &unichars[unichar_id].properties.normed_ids,
                             NULL, NULL)) {
     unichars[unichar_id].properties.normed_ids.truncate(0);
     unichars[unichar_id].properties.normed_ids.push_back(unichar_id);
   }
 }

◆ set_other_case()

void UNICHARSET::set_other_case	(	UNICHAR_ID	unichar_id,
		UNICHAR_ID	other_case
	)

inline

Definition at line 466 of file unicharset.h.

                                                                     {
     unichars[unichar_id].properties.other_case = other_case;
   }

◆ set_ranges_empty()

void UNICHARSET::set_ranges_empty ( )

Definition at line 393 of file unicharset.cpp.

                                   {
   for (int id = 0; id < size_used; ++id) {
     unichars[id].properties.SetRangesEmpty();
   }
 }

◆ set_script()

void UNICHARSET::set_script	(	UNICHAR_ID	unichar_id,
		const char *	value
	)

inline

Definition at line 461 of file unicharset.h.

                                                             {
     unichars[unichar_id].properties.script_id = add_script(value);
   }

◆ set_top_bottom()

void UNICHARSET::set_top_bottom	(	UNICHAR_ID	unichar_id,
		int	min_bottom,
		int	max_bottom,
		int	min_top,
		int	max_top
	)

inline

Definition at line 581 of file unicharset.h.

                                                 {
     unichars[unichar_id].properties.min_bottom =
         static_cast<uinT8>(ClipToRange(min_bottom, 0, MAX_UINT8));
     unichars[unichar_id].properties.max_bottom =
         static_cast<uinT8>(ClipToRange(max_bottom, 0, MAX_UINT8));
     unichars[unichar_id].properties.min_top =
         static_cast<uinT8>(ClipToRange(min_top, 0, MAX_UINT8));
     unichars[unichar_id].properties.max_top =
         static_cast<uinT8>(ClipToRange(max_top, 0, MAX_UINT8));
   }

◆ set_width_stats()

void UNICHARSET::set_width_stats	(	UNICHAR_ID	unichar_id,
		float	width,
		float	width_sd
	)

inline

Definition at line 606 of file unicharset.h.

                                                                            {
     unichars[unichar_id].properties.width = width;
     unichars[unichar_id].properties.width_sd = width_sd;
   }

◆ SetPropertiesFromOther()

void UNICHARSET::SetPropertiesFromOther ( const UNICHARSET & src )

inline

Definition at line 544 of file unicharset.h.

                                                      {
     PartialSetPropertiesFromOther(0, src);
   }

◆ size()

int UNICHARSET::size ( ) const

inline

Definition at line 338 of file unicharset.h.

                    {
     return size_used;
   }

◆ SizesDistinct()

bool UNICHARSET::SizesDistinct	(	UNICHAR_ID	id1,
		UNICHAR_ID	id2
	)		const

Definition at line 483 of file unicharset.cpp.

                                                                    {
   int overlap = MIN(unichars[id1].properties.max_top,
                     unichars[id2].properties.max_top) -
                 MAX(unichars[id1].properties.min_top,
                     unichars[id2].properties.min_top);
   return overlap <= 0;
 }

◆ step()

int UNICHARSET::step ( const char * str ) const

Definition at line 230 of file unicharset.cpp.

                                           {
   GenericVector<UNICHAR_ID> encoding;
   GenericVector<char> lengths;
   encode_string(str, true, &encoding, &lengths, NULL);
   if (encoding.empty() || encoding[0] == INVALID_UNICHAR_ID) return 0;
   return lengths[0];
 }

◆ thai_sid()

int UNICHARSET::thai_sid ( ) const

inline

Definition at line 890 of file unicharset.h.

890 { return thai_sid_; }

◆ to_lower()

UNICHAR_ID UNICHARSET::to_lower ( UNICHAR_ID unichar_id ) const

inline

Definition at line 703 of file unicharset.h.

                                                    {
     if (INVALID_UNICHAR_ID == unichar_id) return INVALID_UNICHAR_ID;
     ASSERT_HOST(contains_unichar_id(unichar_id));
     if (unichars[unichar_id].properties.islower) return unichar_id;
     return unichars[unichar_id].properties.other_case;
   }

◆ to_upper()

UNICHAR_ID UNICHARSET::to_upper ( UNICHAR_ID unichar_id ) const

inline

Definition at line 711 of file unicharset.h.

                                                    {
     if (INVALID_UNICHAR_ID == unichar_id) return INVALID_UNICHAR_ID;
     ASSERT_HOST(contains_unichar_id(unichar_id));
     if (unichars[unichar_id].properties.isupper) return unichar_id;
     return unichars[unichar_id].properties.other_case;
   }

◆ top_bottom_useful()

bool UNICHARSET::top_bottom_useful ( ) const

inline

Definition at line 536 of file unicharset.h.

                                  {
     return top_bottom_set_;
   }

◆ unichar_insert() [1/2]

void UNICHARSET::unichar_insert	(	const char *const	unichar_repr,
		OldUncleanUnichars	old_style
	)

Definition at line 623 of file unicharset.cpp.

                                                               {
   if (old_style == OldUncleanUnichars::kTrue) old_style_included_ = true;
   string cleaned =
       old_style_included_ ? unichar_repr : CleanupString(unichar_repr);
   if (!cleaned.empty() && !ids.contains(cleaned.data(), cleaned.size())) {
     const char* str = cleaned.c_str();
     GenericVector<int> encoding;
     if (!old_style_included_ &&
         encode_string(str, true, &encoding, nullptr, nullptr))
       return;
     if (size_used == size_reserved) {
       if (size_used == 0)
         reserve(8);
       else
         reserve(2 * size_used);
     }
     int index = 0;
     do {
       if (index > UNICHAR_LEN) {
         fprintf(stderr, "Utf8 buffer too big, size>%d for %s\n", UNICHAR_LEN,
                 unichar_repr);
         return;
       }
       unichars[size_used].representation[index++] = *str++;
     } while (*str != '\0');
     unichars[size_used].representation[index] = '\0';
     this->set_script(size_used, null_script);
     // If the given unichar_repr represents a fragmented character, set
     // fragment property to a pointer to CHAR_FRAGMENT class instance with
     // information parsed from the unichar representation. Use the script
     // of the base unichar for the fragmented character if possible.
     CHAR_FRAGMENT* frag =
         CHAR_FRAGMENT::parse_from_string(unichars[size_used].representation);
     this->unichars[size_used].properties.fragment = frag;
     if (frag != NULL && this->contains_unichar(frag->get_unichar())) {
       this->unichars[size_used].properties.script_id =
         this->get_script(frag->get_unichar());
     }
     this->unichars[size_used].properties.enabled = true;
     ids.insert(unichars[size_used].representation, size_used);
     ++size_used;
   }
 }

◆ unichar_insert() [2/2]

void UNICHARSET::unichar_insert ( const char *const unichar_repr )

inline

Definition at line 259 of file unicharset.h.

                                                       {
     unichar_insert(unichar_repr, OldUncleanUnichars::kFalse);
   }

◆ unichar_insert_backwards_compatible()

void UNICHARSET::unichar_insert_backwards_compatible ( const char *const unichar_repr )

inline

Definition at line 264 of file unicharset.h.

                                                                            {
     string cleaned = CleanupString(unichar_repr);
     if (cleaned != unichar_repr) {
       unichar_insert(unichar_repr, OldUncleanUnichars::kTrue);
     } else {
       int old_size = size();
       unichar_insert(unichar_repr, OldUncleanUnichars::kFalse);
       if (size() == old_size) {
         unichar_insert(unichar_repr, OldUncleanUnichars::kTrue);
       }
     }
   }

◆ unichar_to_id() [1/2]

UNICHAR_ID UNICHARSET::unichar_to_id ( const char *const unichar_repr ) const

Definition at line 207 of file unicharset.cpp.

                                                               {
   string cleaned =
       old_style_included_ ? unichar_repr : CleanupString(unichar_repr);
   return ids.contains(cleaned.data(), cleaned.size())
              ? ids.unichar_to_id(cleaned.data(), cleaned.size())
              : INVALID_UNICHAR_ID;
 }

◆ unichar_to_id() [2/2]

UNICHAR_ID UNICHARSET::unichar_to_id	(	const char *const	unichar_repr,
		int	length
	)		const

Definition at line 215 of file unicharset.cpp.

                                                        {
   assert(length > 0 && length <= UNICHAR_LEN);
   string cleaned(unichar_repr, length);
   if (!old_style_included_) cleaned = CleanupString(unichar_repr, length);
   return ids.contains(cleaned.data(), cleaned.size())
              ? ids.unichar_to_id(cleaned.data(), cleaned.size())
              : INVALID_UNICHAR_ID;
 }

Member Data Documentation

◆ kCustomLigatures

const char * UNICHARSET::kCustomLigatures

static

Initial value:

= {
  {"ct", "\uE003"},  
  {"ſh", "\uE006"},  
  {"ſi", "\uE007"},  
  {"ſl", "\uE008"},  
  {"ſſ", "\uE009"},  
  {NULL, NULL}
}

Definition at line 151 of file unicharset.h.

◆ kSpecialUnicharCodes

const char * UNICHARSET::kSpecialUnicharCodes

static

Initial value:

= {
    " ",
    "Joined",
    "|Broken|0|1"
}

Definition at line 154 of file unicharset.h.

The documentation for this class was generated from the following files:

/home/stweil/src/github/tesseract-ocr/tesseract/ccutil/unicharset.h
/home/stweil/src/github/tesseract-ocr/tesseract/ccutil/unicharset.cpp

Public Types

Public Member Functions

Static Public Member Functions

Static Public Attributes

Detailed Description

Member Enumeration Documentation

◆ Direction

Constructor & Destructor Documentation

◆ UNICHARSET()

◆ ~UNICHARSET()

Member Function Documentation

◆ add_script()

◆ AnyRepeatedUnicodes()

◆ AppendOtherUnicharset()

◆ CleanupString() [1/2]

◆ CleanupString() [2/2]

◆ clear()

◆ common_sid()

◆ contains_unichar() [1/2]

◆ contains_unichar() [2/2]

◆ contains_unichar_id()

◆ CopyFrom()

◆ cyrillic_sid()

◆ debug_str() [1/2]

◆ debug_str() [2/2]

◆ debug_utf8_str()

◆ default_sid()

◆ delete_pointers_in_unichars()

◆ encodable_string()

◆ encode_string()

◆ eq()

◆ ExpandRangesFromOther()

◆ get_advance_stats()

◆ get_bearing_stats()

◆ get_chartype() [1/2]

◆ get_chartype() [2/2]

◆ get_direction()

◆ get_enabled()

◆ get_fragment() [1/2]

◆ get_fragment() [2/2]

◆ get_isalpha() [1/3]

◆ get_isalpha() [2/3]

◆ get_isalpha() [3/3]

◆ get_isdigit() [1/3]

◆ get_isdigit() [2/3]

◆ get_isdigit() [3/3]

◆ get_islower() [1/3]

◆ get_islower() [2/3]

◆ get_islower() [3/3]

◆ get_isngram()

◆ get_isprivate()

◆ get_ispunctuation() [1/3]

◆ get_ispunctuation() [2/3]

◆ get_ispunctuation() [3/3]

◆ get_isupper() [1/3]

◆ get_isupper() [2/3]

◆ get_isupper() [3/3]

◆ get_mirror()

◆ get_normed_unichar()

◆ get_other_case()

◆ get_properties() [1/2]

◆ get_properties() [2/2]

◆ get_script() [1/3]

◆ get_script() [2/3]

◆ get_script() [3/3]

◆ get_script_from_script_id()

◆ get_script_id_from_name()

◆ get_script_table_size()

◆ get_top_bottom()

◆ get_width_stats()

◆ greek_sid()

◆ han_sid()

◆ hangul_sid()

◆ has_special_codes()

◆ hiragana_sid()

◆ id_to_unichar()

◆ id_to_unichar_ext()

◆ is_null_script()

◆ IsSpaceDelimited()

◆ katakana_sid()