/usr/include/tesseract/cube_reco_context.h is in libtesseract-dev 3.02.01-6.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 | /**********************************************************************
* File: cube_reco_context.h
* Description: Declaration of the Cube Recognition Context Class
* Author: Ahmad Abdulkader
* Created: 2007
*
* (C) Copyright 2008, Google Inc.
** Licensed under the Apache License, Version 2.0 (the "License");
** you may not use this file except in compliance with the License.
** You may obtain a copy of the License at
** http://www.apache.org/licenses/LICENSE-2.0
** Unless required by applicable law or agreed to in writing, software
** distributed under the License is distributed on an "AS IS" BASIS,
** WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
** See the License for the specific language governing permissions and
** limitations under the License.
*
**********************************************************************/
// The CubeRecoContext class abstracts the Cube OCR Engine. Typically a process
// (or a thread) would create one CubeRecoContext object per language.
// The CubeRecoContext object also provides methods to get and set the
// different attribues of the Cube OCR Engine.
#ifndef CUBE_RECO_CONTEXT_H
#define CUBE_RECO_CONTEXT_H
#include <string>
#include "neural_net.h"
#include "lang_model.h"
#include "classifier_base.h"
#include "feature_base.h"
#include "char_set.h"
#include "word_size_model.h"
#include "char_bigrams.h"
#include "word_unigrams.h"
namespace tesseract {
class Tesseract;
class TessdataManager;
class CubeRecoContext {
public:
// Reading order enum type
enum ReadOrder {
L2R,
R2L
};
// Instantiate using a Tesseract object
CubeRecoContext(Tesseract *tess_obj);
~CubeRecoContext();
// accessor functions
inline const string & Lang() const { return lang_; }
inline CharSet *CharacterSet() const { return char_set_; }
const UNICHARSET *TessUnicharset() const { return tess_unicharset_; }
inline CharClassifier *Classifier() const { return char_classifier_; }
inline WordSizeModel *SizeModel() const { return word_size_model_; }
inline CharBigrams *Bigrams() const { return char_bigrams_; }
inline WordUnigrams *WordUnigramsObj() const { return word_unigrams_; }
inline TuningParams *Params() const { return params_; }
inline LangModel *LangMod() const { return lang_mod_; }
// the reading order of the language
inline ReadOrder ReadingOrder() const {
return ((lang_ == "ara") ? R2L : L2R);
}
// does the language support case
inline bool HasCase() const {
return (lang_ != "ara" && lang_ != "hin");
}
inline bool Cursive() const {
return (lang_ == "ara");
}
inline bool HasItalics() const {
return (lang_ != "ara" && lang_ != "hin" && lang_ != "uk");
}
inline bool Contextual() const {
return (lang_ == "ara");
}
// RecoContext runtime flags accessor functions
inline bool SizeNormalization() const { return size_normalization_; }
inline bool NoisyInput() const { return noisy_input_; }
inline bool OOD() const { return lang_mod_->OOD(); }
inline bool Numeric() const { return lang_mod_->Numeric(); }
inline bool WordList() const { return lang_mod_->WordList(); }
inline bool Punc() const { return lang_mod_->Punc(); }
inline bool CaseSensitive() const {
return char_classifier_->CaseSensitive();
}
inline void SetSizeNormalization(bool size_normalization) {
size_normalization_ = size_normalization;
}
inline void SetNoisyInput(bool noisy_input) {
noisy_input_ = noisy_input;
}
inline void SetOOD(bool ood_enabled) {
lang_mod_->SetOOD(ood_enabled);
}
inline void SetNumeric(bool numeric_enabled) {
lang_mod_->SetNumeric(numeric_enabled);
}
inline void SetWordList(bool word_list_enabled) {
lang_mod_->SetWordList(word_list_enabled);
}
inline void SetPunc(bool punc_enabled) {
lang_mod_->SetPunc(punc_enabled);
}
inline void SetCaseSensitive(bool case_sensitive) {
char_classifier_->SetCaseSensitive(case_sensitive);
}
inline tesseract::Tesseract *TesseractObject() const {
return tess_obj_;
}
// Returns the path of the data files
bool GetDataFilePath(string *path) const;
// Creates a CubeRecoContext object using a tesseract object. Data
// files are loaded via the tessdata_manager, and the tesseract
// unicharset is provided in order to map Cube's unicharset to
// Tesseract's in the case where the two unicharsets differ.
static CubeRecoContext *Create(Tesseract *tess_obj,
TessdataManager *tessdata_manager,
UNICHARSET *tess_unicharset);
private:
bool loaded_;
string lang_;
CharSet *char_set_;
UNICHARSET *tess_unicharset_;
WordSizeModel *word_size_model_;
CharClassifier *char_classifier_;
CharBigrams *char_bigrams_;
WordUnigrams *word_unigrams_;
TuningParams *params_;
LangModel *lang_mod_;
Tesseract *tess_obj_; // CubeRecoContext does not own this pointer
bool size_normalization_;
bool noisy_input_;
// Loads and initialized all the necessary components of a
// CubeRecoContext. See .cpp for more details.
bool Load(TessdataManager *tessdata_manager,
UNICHARSET *tess_unicharset);
};
}
#endif // CUBE_RECO_CONTEXT_H
|