int main (void){
main_setup();
for(;;){
welcome_msg(algo_name);
cmd_interface(cmdlist);
}
}
int main (void){
main_setup();
int_realloc = realloc;
int_free = free;
for(;;){
welcome_msg(algo_name);
cmd_interface(cmdlist);
}
}
int main (void){
main_setup();
shavs_algolist=(hfdesc_t**)algolist;
shavs_algo=(hfdesc_t*)&jh256_desc;
for(;;){
welcome_msg(algo_name);
cmd_interface(cmdlist);
}
}
int main (void){
int8_t r;
main_setup();
calibrateTimer();
for(;;){
welcome_msg(algo_name);
r = cmd_interface(cmdlist);
printf("r = %"PRId8"\n", r);
cli_putstr_P(PSTR("\r\nHello!\r\n"));
}
}
void setup(void) {
int i;
char *p = (char *)MAIN_SETUP_ENTRY;
for (i = 0; i < 8; i++) {
read_sect(p, 1+i);
p += 512;
}
void (*main_setup)(void) = (void (*)())MAIN_SETUP_ENTRY;
main_setup();
}
void init_tesseract_lang_data(const char *arg0,
const char *textbase,
const char *language,
const char *configfile,
int configc,
const char *const *configv) {
FILE *var_file;
static char c_path[MAX_PATH]; //path for c code
// Set the basename, compute the data directory and read C++ configs.
main_setup(arg0, textbase, configc, configv);
debug_window_on.set_value (FALSE);
if (tessedit_write_vars) {
var_file = fopen ("edited.cfg", "w");
if (var_file != NULL) {
print_variables(var_file);
fclose(var_file);
}
}
strcpy (c_path, datadir.string ());
c_path[strlen (c_path) - strlen (m_data_sub_dir.string ())] = '\0';
demodir = c_path;
// Set the language data path prefix
language_data_path_prefix = datadir;
if (language != NULL)
language_data_path_prefix += language;
else
language_data_path_prefix += "eng";
language_data_path_prefix += ".";
// Load the unichar set
STRING unicharpath = language_data_path_prefix;
unicharpath += "unicharset";
if (!unicharset.load_from_file(unicharpath.string())) {
printf("Unable to load unicharset file %s\n", unicharpath.string());
exit(1);
}
if (unicharset.size() > MAX_NUM_CLASSES) {
printf("Error: Size of unicharset is greater than MAX_NUM_CLASSES\n");
exit(1);
}
// Set the white and blacklists (if any)
unicharset.set_black_and_whitelist(tessedit_char_blacklist.string(),
tessedit_char_whitelist.string());
}
void kadnode_loop(void)
{
if (gconf && gconf->is_running == 0) {
conf_check();
main_setup();
// Loop over all sockets and file descriptors
net_loop();
// Export peers if a file is provided
peerfile_export();
main_free();
conf_free();
}
}
// Returns false if a unicharset file for the specified language was not found
// or was invalid.
// This function initializes TessdataManager. After TessdataManager is
// no longer needed, TessdataManager::End() should be called.
//
// This function sets tessedit_oem_mode to the given OcrEngineMode oem, unless
// it is OEM_DEFAULT, in which case the value of the variable will be obtained
// from the language-specific config file (stored in [lang].traineddata), from
// the config files specified on the command line or left as the default
// OEM_TESSERACT_ONLY if none of the configs specify this variable.
bool Tesseract::init_tesseract_lang_data(
const char *arg0, const char *textbase, const char *language,
OcrEngineMode oem, char **configs, int configs_size,
const GenericVector<STRING> *vars_vec,
const GenericVector<STRING> *vars_values,
bool set_only_non_debug_params) {
// Set the basename, compute the data directory.
main_setup(arg0, textbase);
// Set the language data path prefix
lang = language != NULL ? language : "eng";
language_data_path_prefix = datadir;
language_data_path_prefix += lang;
language_data_path_prefix += ".";
// Initialize TessdataManager.
STRING tessdata_path = language_data_path_prefix + kTrainedDataSuffix;
if (!tessdata_manager.Init(tessdata_path.string(),
tessdata_manager_debug_level)) {
return false;
}
// If a language specific config file (lang.config) exists, load it in.
if (tessdata_manager.SeekToStart(TESSDATA_LANG_CONFIG)) {
ParamUtils::ReadParamsFromFp(
tessdata_manager.GetDataFilePtr(),
tessdata_manager.GetEndOffset(TESSDATA_LANG_CONFIG),
SET_PARAM_CONSTRAINT_NONE, this->params());
if (tessdata_manager_debug_level) {
tprintf("Loaded language config file\n");
}
}
SetParamConstraint set_params_constraint = set_only_non_debug_params ?
SET_PARAM_CONSTRAINT_NON_DEBUG_ONLY : SET_PARAM_CONSTRAINT_NONE;
// Load tesseract variables from config files. This is done after loading
// language-specific variables from [lang].traineddata file, so that custom
// config files can override values in [lang].traineddata file.
for (int i = 0; i < configs_size; ++i) {
read_config_file(configs[i], set_params_constraint);
}
// Set params specified in vars_vec (done after setting params from config
// files, so that params in vars_vec can override those from files).
if (vars_vec != NULL && vars_values != NULL) {
for (int i = 0; i < vars_vec->size(); ++i) {
if (!ParamUtils::SetParam((*vars_vec)[i].string(),
(*vars_values)[i].string(),
set_params_constraint, this->params())) {
tprintf("Error setting param %s\n", (*vars_vec)[i].string());
exit(1);
}
}
}
if (((STRING &)tessedit_write_params_to_file).length() > 0) {
FILE *params_file = fopen(tessedit_write_params_to_file.string(), "wb");
if (params_file != NULL) {
ParamUtils::PrintParams(params_file, this->params());
fclose(params_file);
if (tessdata_manager_debug_level > 0) {
tprintf("Wrote parameters to %s\n",
tessedit_write_params_to_file.string());
}
} else {
tprintf("Failed to open %s for writing params.\n",
tessedit_write_params_to_file.string());
}
}
// Determine which ocr engine(s) should be loaded and used for recognition.
if (oem != OEM_DEFAULT) tessedit_ocr_engine_mode.set_value(oem);
if (tessdata_manager_debug_level) {
tprintf("Loading Tesseract/Cube with tessedit_ocr_engine_mode %d\n",
static_cast<int>(tessedit_ocr_engine_mode));
}
// If we are only loading the config file (and so not planning on doing any
// recognition) then there's nothing else do here.
if (tessedit_init_config_only) {
if (tessdata_manager_debug_level) {
tprintf("Returning after loading config file\n");
}
return true;
}
// Load the unicharset
if (!tessdata_manager.SeekToStart(TESSDATA_UNICHARSET) ||
!unicharset.load_from_file(tessdata_manager.GetDataFilePtr())) {
return false;
}
if (unicharset.size() > MAX_NUM_CLASSES) {
tprintf("Error: Size of unicharset is greater than MAX_NUM_CLASSES\n");
return false;
}
if (tessdata_manager_debug_level) tprintf("Loaded unicharset\n");
right_to_left_ = unicharset.major_right_to_left();
// Setup initial unichar ambigs table and read universal ambigs.
UNICHARSET encoder_unicharset;
encoder_unicharset.CopyFrom(unicharset);
unichar_ambigs.InitUnicharAmbigs(unicharset, use_ambigs_for_adaption);
unichar_ambigs.LoadUniversal(encoder_unicharset, &unicharset);
if (!tessedit_ambigs_training &&
tessdata_manager.SeekToStart(TESSDATA_AMBIGS)) {
TFile ambigs_file;
ambigs_file.Open(tessdata_manager.GetDataFilePtr(),
tessdata_manager.GetEndOffset(TESSDATA_AMBIGS) + 1);
unichar_ambigs.LoadUnicharAmbigs(
encoder_unicharset,
&ambigs_file,
ambigs_debug_level, use_ambigs_for_adaption, &unicharset);
if (tessdata_manager_debug_level) tprintf("Loaded ambigs\n");
}
// Load Cube objects if necessary.
if (tessedit_ocr_engine_mode == OEM_CUBE_ONLY) {
ASSERT_HOST(init_cube_objects(false, &tessdata_manager));
if (tessdata_manager_debug_level)
tprintf("Loaded Cube w/out combiner\n");
} else if (tessedit_ocr_engine_mode == OEM_TESSERACT_CUBE_COMBINED) {
ASSERT_HOST(init_cube_objects(true, &tessdata_manager));
if (tessdata_manager_debug_level)
tprintf("Loaded Cube with combiner\n");
}
// Init ParamsModel.
// Load pass1 and pass2 weights (for now these two sets are the same, but in
// the future separate sets of weights can be generated).
for (int p = ParamsModel::PTRAIN_PASS1;
p < ParamsModel::PTRAIN_NUM_PASSES; ++p) {
language_model_->getParamsModel().SetPass(
static_cast<ParamsModel::PassEnum>(p));
if (tessdata_manager.SeekToStart(TESSDATA_PARAMS_MODEL)) {
if (!language_model_->getParamsModel().LoadFromFp(
lang.string(), tessdata_manager.GetDataFilePtr(),
tessdata_manager.GetEndOffset(TESSDATA_PARAMS_MODEL))) {
return false;
}
}
}
if (tessdata_manager_debug_level) language_model_->getParamsModel().Print();
return true;
}
// Returns false if a unicharset file for the specified language was not found
// or was invalid.
// This function initializes TessdataManager. After TessdataManager is
// no longer needed, TessdataManager::End() should be called.
bool Tesseract::init_tesseract_lang_data(
const char *arg0, const char *textbase, const char *language,
char **configs, int configs_size, bool configs_global_only) {
FILE *var_file;
static char c_path[MAX_PATH]; //path for c code
// Set the basename, compute the data directory.
main_setup(arg0, textbase);
debug_window_on.set_value (FALSE);
if (tessedit_write_vars) {
var_file = fopen ("edited.cfg", "w");
if (var_file != NULL) {
print_variables(var_file);
fclose(var_file);
}
}
strcpy (c_path, datadir.string());
c_path[strlen (c_path) - strlen (m_data_sub_dir.string ())] = '\0';
demodir = c_path;
// Set the language data path prefix
lang = language != NULL ? language : "eng";
language_data_path_prefix = datadir;
language_data_path_prefix += lang;
language_data_path_prefix += ".";
// Load tesseract variables from config files.
for (int i = 0; i < configs_size; ++i) {
read_config_file(configs[i], configs_global_only);
}
// Initialize TessdataManager.
STRING tessdata_path = language_data_path_prefix + kTrainedDataSuffix;
tessdata_manager.Init(tessdata_path.string());
// If a language specific config file (lang.config) exists, load it in.
if (tessdata_manager.SeekToStart(TESSDATA_LANG_CONFIG)) {
read_variables_from_fp(tessdata_manager.GetDataFilePtr(),
tessdata_manager.GetEndOffset(TESSDATA_LANG_CONFIG),
false);
if (global_tessdata_manager_debug_level) {
tprintf("Loaded language config file\n");
}
}
// Load the unicharset
if (!tessdata_manager.SeekToStart(TESSDATA_UNICHARSET) ||
!unicharset.load_from_file(tessdata_manager.GetDataFilePtr())) {
return false;
}
if (unicharset.size() > MAX_NUM_CLASSES) {
tprintf("Error: Size of unicharset is greater than MAX_NUM_CLASSES\n");
return false;
}
if (global_tessdata_manager_debug_level) tprintf("Loaded unicharset\n");
if (!global_tessedit_ambigs_training &&
tessdata_manager.SeekToStart(TESSDATA_AMBIGS)) {
unichar_ambigs.LoadUnicharAmbigs(
tessdata_manager.GetDataFilePtr(),
tessdata_manager.GetEndOffset(TESSDATA_AMBIGS),
&unicharset);
if (global_tessdata_manager_debug_level) tprintf("Loaded ambigs\n");
}
return true;
}
// Returns false if a unicharset file for the specified language was not found
// or was invalid.
// This function initializes TessdataManager. After TessdataManager is
// no longer needed, TessdataManager::End() should be called.
//
// This function sets tessedit_oem_mode to the given OcrEngineMode oem, unless
// it is OEM_DEFAULT, in which case the value of the variable will be obtained
// from the language-specific config file (stored in [lang].traineddata), from
// the config files specified on the command line or left as the default
// OEM_TESSERACT_ONLY if none of the configs specify this variable.
bool Tesseract::init_tesseract_lang_data(
const char *arg0, const char *textbase, const char *language,
OcrEngineMode oem, char **configs, int configs_size,
const GenericVector<STRING> *vars_vec,
const GenericVector<STRING> *vars_values,
bool set_only_init_params) {
// Set the basename, compute the data directory.
#if _BUILDASDLL
imagebasename = textbase; /*name of image */
STRING dll_module_name;
#ifdef __MSW32__
dll_module_name = tessedit_module_name;
#endif
if (getpath(arg0, dll_module_name, datadir) < 0)
return false;
#else
main_setup(arg0, textbase);
#endif
// Set the language data path prefix
lang = language != NULL ? language : "eng";
language_data_path_prefix = datadir;
language_data_path_prefix += lang;
language_data_path_prefix += ".";
// Initialize TessdataManager.
STRING tessdata_path = language_data_path_prefix + kTrainedDataSuffix;
if (!tessdata_manager.Init(tessdata_path.string(),
tessdata_manager_debug_level)) {
return false;
}
// If a language specific config file (lang.config) exists, load it in.
if (tessdata_manager.SeekToStart(TESSDATA_LANG_CONFIG)) {
ParamUtils::ReadParamsFromFp(
tessdata_manager.GetDataFilePtr(),
tessdata_manager.GetEndOffset(TESSDATA_LANG_CONFIG),
false, this->params());
if (tessdata_manager_debug_level) {
tprintf("Loaded language config file\n");
}
}
// Load tesseract variables from config files. This is done after loading
// language-specific variables from [lang].traineddata file, so that custom
// config files can override values in [lang].traineddata file.
for (int i = 0; i < configs_size; ++i) {
read_config_file(configs[i], set_only_init_params);
}
// Set params specified in vars_vec (done after setting params from config
// files, so that params in vars_vec can override those from files).
if (vars_vec != NULL && vars_values != NULL) {
for (int i = 0; i < vars_vec->size(); ++i) {
if (!ParamUtils::SetParam((*vars_vec)[i].string(),
(*vars_values)[i].string(),
set_only_init_params, this->params())) {
tprintf("Error setting param %s\n", (*vars_vec)[i].string());
exit(1);
}
}
}
if (((STRING &)tessedit_write_params_to_file).length() > 0) {
FILE *params_file = fopen(tessedit_write_params_to_file.string(), "wb");
if (params_file != NULL) {
ParamUtils::PrintParams(params_file, this->params());
fclose(params_file);
if (tessdata_manager_debug_level > 0) {
tprintf("Wrote parameters to %s\n",
tessedit_write_params_to_file.string());
}
} else {
tprintf("Failed to open %s for writing params.\n",
tessedit_write_params_to_file.string());
}
}
// Determine which ocr engine(s) should be loaded and used for recognition.
if (oem != OEM_DEFAULT) tessedit_ocr_engine_mode.set_value(oem);
if (tessdata_manager_debug_level) {
tprintf("Loading Tesseract/Cube with tessedit_ocr_engine_mode %d\n",
static_cast<int>(tessedit_ocr_engine_mode));
}
// Load the unicharset
if (!tessdata_manager.SeekToStart(TESSDATA_UNICHARSET) ||
!unicharset.load_from_file(tessdata_manager.GetDataFilePtr())) {
return false;
}
if (unicharset.size() > MAX_NUM_CLASSES) {
tprintf("Error: Size of unicharset is greater than MAX_NUM_CLASSES\n");
return false;
}
right_to_left_ = unicharset.any_right_to_left();
if (tessdata_manager_debug_level) tprintf("Loaded unicharset\n");
if (!tessedit_ambigs_training &&
tessdata_manager.SeekToStart(TESSDATA_AMBIGS)) {
unichar_ambigs.LoadUnicharAmbigs(
tessdata_manager.GetDataFilePtr(),
tessdata_manager.GetEndOffset(TESSDATA_AMBIGS),
ambigs_debug_level, use_ambigs_for_adaption, &unicharset);
if (tessdata_manager_debug_level) tprintf("Loaded ambigs\n");
}
// Load Cube objects if necessary.
if (tessedit_ocr_engine_mode == OEM_CUBE_ONLY) {
ASSERT_HOST(init_cube_objects(false, &tessdata_manager));
if (tessdata_manager_debug_level)
tprintf("Loaded Cube w/out combiner\n");
} else if (tessedit_ocr_engine_mode == OEM_TESSERACT_CUBE_COMBINED) {
ASSERT_HOST(init_cube_objects(true, &tessdata_manager));
if (tessdata_manager_debug_level)
tprintf("Loaded Cube with combiner\n");
}
return true;
}
// Returns false if a unicharset file for the specified language was not found
// or was invalid.
// This function initializes TessdataManager. After TessdataManager is
// no longer needed, TessdataManager::End() should be called.
//
// This function sets tessedit_oem_mode to the given OcrEngineMode oem, unless
// it is OEM_DEFAULT, in which case the value of the variable will be obtained
// from the language-specific config file (stored in [lang].traineddata), from
// the config files specified on the command line or left as the default
// OEM_TESSERACT_ONLY if none of the configs specify this variable.
bool Tesseract::init_tesseract_lang_data(
const char *arg0, const char *textbase, const char *language,
OcrEngineMode oem, char **configs, int configs_size,
const GenericVector<STRING> *vars_vec,
const GenericVector<STRING> *vars_values, bool set_only_non_debug_params,
TessdataManager *mgr) {
// Set the basename, compute the data directory.
main_setup(arg0, textbase);
// Set the language data path prefix
lang = language != NULL ? language : "eng";
language_data_path_prefix = datadir;
language_data_path_prefix += lang;
language_data_path_prefix += ".";
// Initialize TessdataManager.
STRING tessdata_path = language_data_path_prefix + kTrainedDataSuffix;
if (!mgr->is_loaded() && !mgr->Init(tessdata_path.string())) {
// Try without tessdata.
m_data_sub_dir.set_value("");
main_setup(arg0, textbase);
language_data_path_prefix = datadir;
language_data_path_prefix += lang;
language_data_path_prefix += ".";
tessdata_path = language_data_path_prefix + kTrainedDataSuffix;
if (!mgr->Init(tessdata_path.string())) {
tprintf("Error opening data file %s\n", tessdata_path.string());
tprintf(
"Please make sure the TESSDATA_PREFIX environment variable is set"
" to your \"tessdata\" directory.\n");
return false;
}
}
if (oem == OEM_DEFAULT) {
// Set the engine mode from availability, which can then be overidden by
// the config file when we read it below.
if (!mgr->IsLSTMAvailable()) {
tessedit_ocr_engine_mode.set_value(OEM_TESSERACT_ONLY);
} else if (!mgr->IsBaseAvailable()) {
tessedit_ocr_engine_mode.set_value(OEM_LSTM_ONLY);
} else {
tessedit_ocr_engine_mode.set_value(OEM_TESSERACT_LSTM_COMBINED);
}
}
// If a language specific config file (lang.config) exists, load it in.
TFile fp;
if (mgr->GetComponent(TESSDATA_LANG_CONFIG, &fp)) {
ParamUtils::ReadParamsFromFp(SET_PARAM_CONSTRAINT_NONE, &fp,
this->params());
}
SetParamConstraint set_params_constraint = set_only_non_debug_params ?
SET_PARAM_CONSTRAINT_NON_DEBUG_ONLY : SET_PARAM_CONSTRAINT_NONE;
// Load tesseract variables from config files. This is done after loading
// language-specific variables from [lang].traineddata file, so that custom
// config files can override values in [lang].traineddata file.
for (int i = 0; i < configs_size; ++i) {
read_config_file(configs[i], set_params_constraint);
}
// Set params specified in vars_vec (done after setting params from config
// files, so that params in vars_vec can override those from files).
if (vars_vec != NULL && vars_values != NULL) {
for (int i = 0; i < vars_vec->size(); ++i) {
if (!ParamUtils::SetParam((*vars_vec)[i].string(),
(*vars_values)[i].string(),
set_params_constraint, this->params())) {
tprintf("Error setting param %s\n", (*vars_vec)[i].string());
exit(1);
}
}
}
if (((STRING &)tessedit_write_params_to_file).length() > 0) {
FILE *params_file = fopen(tessedit_write_params_to_file.string(), "wb");
if (params_file != NULL) {
ParamUtils::PrintParams(params_file, this->params());
fclose(params_file);
} else {
tprintf("Failed to open %s for writing params.\n",
tessedit_write_params_to_file.string());
}
}
// Determine which ocr engine(s) should be loaded and used for recognition.
if (oem != OEM_DEFAULT) tessedit_ocr_engine_mode.set_value(oem);
// If we are only loading the config file (and so not planning on doing any
// recognition) then there's nothing else do here.
if (tessedit_init_config_only) {
return true;
}
// The various OcrEngineMode settings (see publictypes.h) determine which
// engine-specific data files need to be loaded.
// If LSTM_ONLY is requested, the base Tesseract files are *Not* required.
#ifndef ANDROID_BUILD
if (tessedit_ocr_engine_mode == OEM_LSTM_ONLY ||
tessedit_ocr_engine_mode == OEM_TESSERACT_LSTM_COMBINED) {
if (mgr->IsComponentAvailable(TESSDATA_LSTM)) {
lstm_recognizer_ = new LSTMRecognizer;
ASSERT_HOST(
lstm_recognizer_->Load(lstm_use_matrix ? language : nullptr, mgr));
} else {
tprintf("Error: LSTM requested, but not present!! Loading tesseract.\n");
tessedit_ocr_engine_mode.set_value(OEM_TESSERACT_ONLY);
}
}
#endif
// Load the unicharset
if (tessedit_ocr_engine_mode == OEM_LSTM_ONLY) {
// Avoid requiring a unicharset when we aren't running base tesseract.
#ifndef ANDROID_BUILD
unicharset.CopyFrom(lstm_recognizer_->GetUnicharset());
#endif
} else if (!mgr->GetComponent(TESSDATA_UNICHARSET, &fp) ||
!unicharset.load_from_file(&fp, false)) {
return false;
}
if (unicharset.size() > MAX_NUM_CLASSES) {
tprintf("Error: Size of unicharset is greater than MAX_NUM_CLASSES\n");
return false;
}
right_to_left_ = unicharset.major_right_to_left();
// Setup initial unichar ambigs table and read universal ambigs.
UNICHARSET encoder_unicharset;
encoder_unicharset.CopyFrom(unicharset);
unichar_ambigs.InitUnicharAmbigs(unicharset, use_ambigs_for_adaption);
unichar_ambigs.LoadUniversal(encoder_unicharset, &unicharset);
if (!tessedit_ambigs_training && mgr->GetComponent(TESSDATA_AMBIGS, &fp)) {
unichar_ambigs.LoadUnicharAmbigs(encoder_unicharset, &fp,
ambigs_debug_level,
use_ambigs_for_adaption, &unicharset);
}
// Init ParamsModel.
// Load pass1 and pass2 weights (for now these two sets are the same, but in
// the future separate sets of weights can be generated).
for (int p = ParamsModel::PTRAIN_PASS1;
p < ParamsModel::PTRAIN_NUM_PASSES; ++p) {
language_model_->getParamsModel().SetPass(
static_cast<ParamsModel::PassEnum>(p));
if (mgr->GetComponent(TESSDATA_PARAMS_MODEL, &fp)) {
if (!language_model_->getParamsModel().LoadFromFp(lang.string(), &fp)) {
return false;
}
}
}
return true;
}
