This is the complete list of members for tesseract::Dict, including all inherited members.
absolute_garbage(const WERD_CHOICE &word, const UNICHARSET &unicharset) | tesseract::Dict | |
AcceptableChoice(const WERD_CHOICE &best_choice, XHeightConsistencyEnum xheight_consistency) | tesseract::Dict | |
AcceptableResult(WERD_RES *word) const | tesseract::Dict | |
add_document_word(const WERD_CHOICE &best_choice) | tesseract::Dict | |
adjust_word(WERD_CHOICE *word, bool nonword, XHeightConsistencyEnum xheight_consistency, float additional_adjust, bool modify_rating, bool debug) | tesseract::Dict | |
apostrophe_unichar_id_ | tesseract::Dict | private |
append_choices(const char *debug, const BLOB_CHOICE_LIST_VECTOR &char_choices, const BLOB_CHOICE &blob_choice, int char_choice_index, const CHAR_FRAGMENT_INFO *prev_char_frag_info, WERD_CHOICE *word, float certainties[], float *limit, WERD_CHOICE *best_choice, int *attempts_left, void *more_args) | tesseract::Dict | |
bigram_dawg_ | tesseract::Dict | private |
BOOL_VAR_H(load_system_dawg, true, "Load system word dawg.") | tesseract::Dict | |
BOOL_VAR_H(load_freq_dawg, true, "Load frequent word dawg.") | tesseract::Dict | |
BOOL_VAR_H(load_unambig_dawg, true, "Load unambiguous word dawg.") | tesseract::Dict | |
BOOL_VAR_H(load_punc_dawg, true, "Load dawg with punctuation patterns.") | tesseract::Dict | |
BOOL_VAR_H(load_number_dawg, true, "Load dawg with number patterns.") | tesseract::Dict | |
BOOL_VAR_H(load_bigram_dawg, true, "Load dawg with special word bigrams.") | tesseract::Dict | |
BOOL_VAR_H(use_only_first_uft8_step, false, "Use only the first UTF8 step of the given string" " when computing log probabilities.") | tesseract::Dict | |
BOOL_VAR_H(stopper_no_acceptable_choices, false, "Make AcceptableChoice() always return false. Useful" " when there is a need to explore all segmentations") | tesseract::Dict | |
BOOL_VAR_H(segment_nonalphabetic_script, false, "Don't use any alphabetic-specific tricks." "Set to true in the traineddata config file for" " scripts that are cursive or inherently fixed-pitch") | tesseract::Dict | |
BOOL_VAR_H(save_doc_words, 0, "Save Document Words") | tesseract::Dict | |
CallParamsModelClassify(void *path) | tesseract::Dict | inline |
case_ok(const WERD_CHOICE &word, const UNICHARSET &unicharset) const | tesseract::Dict | |
ccutil_ | tesseract::Dict | private |
char_for_dawg(const UNICHARSET &unicharset, UNICHAR_ID ch, const Dawg *dawg) const | tesseract::Dict | inline |
compound_marker(UNICHAR_ID unichar_id) | tesseract::Dict | inline |
copy_hyphen_info(WERD_CHOICE *word) const | tesseract::Dict | inline |
dang_ambigs_table_ | tesseract::Dict | private |
dawg_cache_ | tesseract::Dict | private |
dawg_cache_is_ours_ | tesseract::Dict | private |
dawg_permute_and_select(const BLOB_CHOICE_LIST_VECTOR &char_choices, float rating_limit) | tesseract::Dict | |
dawgs_ | tesseract::Dict | private |
DebugWordChoices() | tesseract::Dict | |
def_letter_is_okay(void *void_dawg_args, const UNICHARSET &unicharset, UNICHAR_ID unichar_id, bool word_end) const | tesseract::Dict | |
def_probability_in_context(const char *lang, const char *context, int context_bytes, const char *character, int character_bytes) | tesseract::Dict | inline |
default_dawgs(DawgPositionVector *anylength_dawgs, bool suppress_patterns) const | tesseract::Dict | |
Dict(CCUtil *image_ptr) | tesseract::Dict | |
document_words_ | tesseract::Dict | private |
double_VAR_H(xheight_penalty_subscripts, 0.125, "Score penalty (0.1 = 10%) added if there are subscripts " "or superscripts in a word, but it is otherwise OK.") | tesseract::Dict | |
double_VAR_H(xheight_penalty_inconsistent, 0.25, "Score penalty (0.1 = 10%) added if an xheight is " "inconsistent.") | tesseract::Dict | |
double_VAR_H(segment_penalty_dict_frequent_word, 1.0, "Score multiplier for word matches which have good case and" "are frequent in the given language (lower is better).") | tesseract::Dict | |
double_VAR_H(segment_penalty_dict_case_ok, 1.1, "Score multiplier for word matches that have good case " "(lower is better).") | tesseract::Dict | |
double_VAR_H(segment_penalty_dict_case_bad, 1.3125, "Default score multiplier for word matches, which may have " "case issues (lower is better).") | tesseract::Dict | |
double_VAR_H(segment_penalty_dict_nonword, 1.25, "Score multiplier for glyph fragment segmentations which " "do not match a dictionary word (lower is better).") | tesseract::Dict | |
double_VAR_H(segment_penalty_garbage, 1.50, "Score multiplier for poorly cased strings that are not in" " the dictionary and generally look like garbage (lower is" " better).") | tesseract::Dict | |
double_VAR_H(certainty_scale, 20.0, "Certainty scaling factor") | tesseract::Dict | |
double_VAR_H(stopper_nondict_certainty_base, -2.50, "Certainty threshold for non-dict words") | tesseract::Dict | |
double_VAR_H(stopper_phase2_certainty_rejection_offset, 1.0, "Reject certainty offset") | tesseract::Dict | |
double_VAR_H(stopper_certainty_per_char, -0.50, "Certainty to add for each dict char above small word size.") | tesseract::Dict | |
double_VAR_H(stopper_allowable_character_badness, 3.0, "Max certaintly variation allowed in a word (in sigma)") | tesseract::Dict | |
double_VAR_H(doc_dict_pending_threshold, 0.0, "Worst certainty for using pending dictionary") | tesseract::Dict | |
double_VAR_H(doc_dict_certainty_threshold, -2.25, "Worst certainty" " for words that can be inserted into the document dictionary") | tesseract::Dict | |
End() | tesseract::Dict | |
EndDangerousAmbigs() | tesseract::Dict | |
equivalent_symbols_ | tesseract::Dict | private |
FinishLoad() | tesseract::Dict | |
fragment_state_okay(UNICHAR_ID curr_unichar_id, float curr_rating, float curr_certainty, const CHAR_FRAGMENT_INFO *prev_char_frag_info, const char *debug, int word_ending, CHAR_FRAGMENT_INFO *char_frag_info) | tesseract::Dict | |
freq_dawg_ | tesseract::Dict | private |
getCCUtil() const | tesseract::Dict | inline |
getCCUtil() | tesseract::Dict | inline |
GetDawg(int index) const | tesseract::Dict | inline |
GetPuncDawg() const | tesseract::Dict | inline |
GetStartingNode(const Dawg *dawg, EDGE_REF edge_ref) | tesseract::Dict | inlinestatic |
GetUnambigDawg() const | tesseract::Dict | inline |
getUnicharAmbigs() const | tesseract::Dict | inline |
getUnicharset() const | tesseract::Dict | inline |
getUnicharset() | tesseract::Dict | inline |
GlobalDawgCache() | tesseract::Dict | static |
go_deeper_dawg_fxn(const char *debug, const BLOB_CHOICE_LIST_VECTOR &char_choices, int char_choice_index, const CHAR_FRAGMENT_INFO *prev_char_frag_info, bool word_ending, WERD_CHOICE *word, float certainties[], float *limit, WERD_CHOICE *best_choice, int *attempts_left, void *void_more_args) | tesseract::Dict | |
go_deeper_fxn_ | tesseract::Dict | |
good_choice(const WERD_CHOICE &choice) | tesseract::Dict | |
has_hyphen_end(UNICHAR_ID unichar_id, bool first_pos) const | tesseract::Dict | inline |
has_hyphen_end(const WERD_CHOICE &word) const | tesseract::Dict | inline |
hyphen_active_dawgs_ | tesseract::Dict | private |
hyphen_base_size() const | tesseract::Dict | inline |
hyphen_unichar_id_ | tesseract::Dict | private |
hyphen_word_ | tesseract::Dict | private |
hyphenated() const | tesseract::Dict | inline |
init_active_dawgs(DawgPositionVector *active_dawgs, bool ambigs_mode) const | tesseract::Dict | |
INT_VAR_H(dawg_debug_level, 0, "Set to 1 for general debug info" ", to 2 for more details, to 3 to see all the debug messages") | tesseract::Dict | |
INT_VAR_H(hyphen_debug_level, 0, "Debug level for hyphenated words.") | tesseract::Dict | |
INT_VAR_H(max_viterbi_list_size, 10, "Maximum size of viterbi list.") | tesseract::Dict | |
INT_VAR_H(stopper_smallword_size, 2, "Size of dict word to be treated as non-dict word") | tesseract::Dict | |
INT_VAR_H(stopper_debug_level, 0, "Stopper debug level") | tesseract::Dict | |
INT_VAR_H(tessedit_truncate_wordchoice_log, 10, "Max words to keep in list") | tesseract::Dict | |
INT_VAR_H(fragments_debug, 0, "Debug character fragments") | tesseract::Dict | |
INT_VAR_H(max_permuter_attempts, 10000, "Maximum number of different" " character choices to consider during permutation." " This limit is especially useful when user patterns" " are specified, since overly generic patterns can result in" " dawg search exploring an overly large number of options.") | tesseract::Dict | |
is_apostrophe(UNICHAR_ID unichar_id) | tesseract::Dict | inline |
IsSpaceDelimitedLang() const | tesseract::Dict | |
last_word_on_line_ | tesseract::Dict | private |
LengthOfShortestAlphaRun(const WERD_CHOICE &WordChoice) const | tesseract::Dict | |
letter_is_okay_ | tesseract::Dict | |
LetterIsOkay(void *void_dawg_args, const UNICHARSET &unicharset, UNICHAR_ID unichar_id, bool word_end) const | tesseract::Dict | inline |
Load(const STRING &lang, TessdataManager *data_file) | tesseract::Dict | |
LoadLSTM(const STRING &lang, TessdataManager *data_file) | tesseract::Dict | |
ngram_probability_in_context(const char *lang, const char *context, int context_bytes, const char *character, int character_bytes) | tesseract::Dict | |
NoDangerousAmbig(WERD_CHOICE *BestChoice, DANGERR *fixpt, bool fix_replaceable, MATRIX *ratings) | tesseract::Dict | |
NumDawgs() const | tesseract::Dict | inline |
output_ambig_words_file_ | tesseract::Dict | private |
params_model_classify_ | tesseract::Dict | |
ParamsModelClassify(const char *lang, void *path) | tesseract::Dict | |
pending_words_ | tesseract::Dict | private |
permute_choices(const char *debug, const BLOB_CHOICE_LIST_VECTOR &char_choices, int char_choice_index, const CHAR_FRAGMENT_INFO *prev_char_frag_info, WERD_CHOICE *word, float certainties[], float *limit, WERD_CHOICE *best_choice, int *attempts_left, void *more_args) | tesseract::Dict | |
probability_in_context_ | tesseract::Dict | |
ProbabilityInContext(const char *context, int context_bytes, const char *character, int character_bytes) | tesseract::Dict | inline |
ProcessPatternEdges(const Dawg *dawg, const DawgPosition &info, UNICHAR_ID unichar_id, bool word_end, DawgArgs *dawg_args, PermuterType *current_permuter) const | tesseract::Dict | |
punc_dawg_ | tesseract::Dict | private |
question_unichar_id_ | tesseract::Dict | private |
reject_offset_ | tesseract::Dict | private |
replace_ambigs_table_ | tesseract::Dict | private |
ReplaceAmbig(int wrong_ngram_begin_index, int wrong_ngram_size, UNICHAR_ID correct_ngram_id, WERD_CHOICE *werd_choice, MATRIX *ratings) | tesseract::Dict | |
reset_hyphen_vars(bool last_word_on_line) | tesseract::Dict | |
ResetDocumentDictionary() | tesseract::Dict | inline |
set_hyphen_word(const WERD_CHOICE &word, const DawgPositionVector &active_dawgs) | tesseract::Dict | |
SettupStopperPass1() | tesseract::Dict | |
SettupStopperPass2() | tesseract::Dict | |
SetupForLoad(DawgCache *dawg_cache) | tesseract::Dict | |
SetWildcardID(UNICHAR_ID id) | tesseract::Dict | inline |
SetWordsegRatingAdjustFactor(float f) | tesseract::Dict | inline |
slash_unichar_id_ | tesseract::Dict | private |
STRING_VAR_H(user_words_file, "", "A filename of user-provided words.") | tesseract::Dict | |
STRING_VAR_H(user_words_suffix, "", "A suffix of user-provided words located in tessdata.") | tesseract::Dict | |
STRING_VAR_H(user_patterns_file, "", "A filename of user-provided patterns.") | tesseract::Dict | |
STRING_VAR_H(user_patterns_suffix, "", "A suffix of user-provided patterns located in tessdata.") | tesseract::Dict | |
STRING_VAR_H(output_ambig_words_file, "", "Output file for ambiguities found in the dictionary") | tesseract::Dict | |
STRING_VAR_H(word_to_debug, "", "Word for which stopper debug information" " should be printed to stdout") | tesseract::Dict | |
STRING_VAR_H(word_to_debug_lengths, "", "Lengths of unichars in word_to_debug") | tesseract::Dict | |
successors_ | tesseract::Dict | private |
unambig_dawg_ | tesseract::Dict | private |
UniformCertainties(const WERD_CHOICE &word) | tesseract::Dict | |
update_best_choice(const WERD_CHOICE &word, WERD_CHOICE *best_choice) | tesseract::Dict | inline |
valid_bigram(const WERD_CHOICE &word1, const WERD_CHOICE &word2) const | tesseract::Dict | |
valid_punctuation(const WERD_CHOICE &word) | tesseract::Dict | |
valid_word(const WERD_CHOICE &word, bool numbers_ok) const | tesseract::Dict | |
valid_word(const WERD_CHOICE &word) const | tesseract::Dict | inline |
valid_word(const char *string) const | tesseract::Dict | inline |
valid_word_or_number(const WERD_CHOICE &word) const | tesseract::Dict | inline |
valid_word_permuter(uint8_t perm, bool numbers_ok) | tesseract::Dict | inlinestatic |
wildcard_unichar_id_ | tesseract::Dict | private |
WildcardID() const | tesseract::Dict | inline |
wordseg_rating_adjust_factor_ | tesseract::Dict | private |
~Dict() | tesseract::Dict |