mirror/tesseract
1
0
Fork 0
mirror of https://github.com/tesseract-ocr/tesseract.git synced 2024-11-27 20:59:36 +08:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

Replace FontSet struct with vector. It may be improved further (remove pointer?).

Browse Source
This commit is contained in:
Egor Pugin 2021-04-23 02:38:25 +03:00
parent d6cdc521e5
commit 048e63c02b
4 changed files with 24 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
src/ccstruct/fontinfo.cpp
View File

@ -138,7 +138,7 @@ void FontInfoDeleteCallback(FontInfo f) {
f.name = nullptr;
}
void FontSetDeleteCallback(FontSet fs) {
delete[] fs.configs;
delete fs;
}
/*---------------------------------------------------------------------------*/
@ -222,16 +222,18 @@ bool write_spacing_info(FILE *f, const FontInfo &fi) {
return true;
}
bool read_set(TFile *f, FontSet *fs) {
if (!f->DeSerialize(&fs->size)) {
bool read_set(TFile *f, FontSet &fs) {
int size;
if (!f->DeSerialize(&size)) {
return false;
}
fs->configs = new int[fs->size];
return f->DeSerialize(&fs->configs[0], fs->size);
fs->resize(size);
return f->DeSerialize(&(*fs)[0], size);
}
bool write_set(FILE *f, const FontSet &fs) {
return tesseract::Serialize(f, &fs.size) && tesseract::Serialize(f, &fs.configs[0], fs.size);
int size = fs->size();
return tesseract::Serialize(f, &size) && tesseract::Serialize(f, &(*fs)[0], size);
}
} // namespace tesseract.

21
src/ccstruct/fontinfo.h
View File

@ -26,6 +26,7 @@
#include <cstdint> // for uint16_t, uint32_t
#include <cstdio> // for FILE
#include <vector>
namespace tesseract {
@ -151,22 +152,8 @@ struct FontInfo {
// lot of FontSet that differ only by one font. Rather than storing directly
// the FontInfo in the FontSet structure, it's better to share FontInfos among
// FontSets (Classify::fontinfo_table_).
struct FontSet {
int size;
int *configs; // FontInfo ids
bool operator==(const FontSet &rhs) const {
if (size != rhs.size) {
return false;
}
for (int i = 0; i < size; ++i) {
if (configs[i] != rhs.configs[i]) {
return false;
}
}
return true;
}
};
using FontSetBase = std::vector<int>;
using FontSet = FontSetBase *;
// Class that adds a bit of functionality on top of GenericVector to
// implement a table of FontInfo that replaces UniCityTable<FontInfo>.
@ -213,7 +200,7 @@ bool read_info(TFile *f, FontInfo *fi);
bool write_info(FILE *f, const FontInfo &fi);
bool read_spacing_info(TFile *f, FontInfo *fi);
bool write_spacing_info(FILE *f, const FontInfo &fi);
bool read_set(TFile *f, FontSet *fs);
bool read_set(TFile *f, FontSet &fs);
bool write_set(FILE *f, const FontSet &fs);
} // namespace tesseract.

12
src/classify/adaptmatch.cpp
View File

@ -1637,8 +1637,8 @@ void Classify::ComputeCharNormArrays(FEATURE_STRUCT *norm_feature, INT_TEMPLATES
for (int id = 0; id < templates->NumClasses; ++id) {
int font_set_id = templates->Class[id]->font_set_id;
const FontSet &fs = fontset_table_.at(font_set_id);
for (int config = 0; config < fs.size; ++config) {
const Shape &shape = shape_table_->GetShape(fs.configs[config]);
for (int config = 0; config < fs->size(); ++config) {
const Shape &shape = shape_table_->GetShape((*fs)[config]);
for (int c = 0; c < shape.size(); ++c) {
if (char_norm_array[shape[c].unichar_id] < pruner_array[id]) {
pruner_array[id] = char_norm_array[shape[c].unichar_id];
@ -2111,8 +2111,8 @@ int Classify::ClassAndConfigIDToFontOrShapeID(int class_id, int int_result_confi
return kBlankFontinfoId;
}
const FontSet &fs = fontset_table_.at(font_set_id);
ASSERT_HOST(int_result_config >= 0 && int_result_config < fs.size);
return fs.configs[int_result_config];
ASSERT_HOST(int_result_config >= 0 && int_result_config < fs->size());
return (*fs)[int_result_config];
}
// Converts a shape_table_ index to a classifier class_id index (not a
@ -2122,8 +2122,8 @@ int Classify::ShapeIDToClassID(int shape_id) const {
int font_set_id = PreTrainedTemplates->Class[id]->font_set_id;
ASSERT_HOST(font_set_id >= 0);
const FontSet &fs = fontset_table_.at(font_set_id);
for (int config = 0; config < fs.size; ++config) {
if (fs.configs[config] == shape_id) {
for (int config = 0; config < fs->size(); ++config) {
if ((*fs)[config] == shape_id) {
return id;
}
}

14
src/classify/intproto.cpp
View File

@ -506,15 +506,13 @@ INT_TEMPLATES_STRUCT *Classify::CreateIntTemplates(CLASSES FloatProtos,
}
assert(UnusedClassIdIn(IntTemplates, ClassId));
IClass = new INT_CLASS_STRUCT(FClass->NumProtos, FClass->NumConfigs);
FontSet fs;
fs.size = FClass->font_set.size();
fs.configs = new int[fs.size];
for (int i = 0; i < fs.size; ++i) {
fs.configs[i] = FClass->font_set.at(i);
FontSet fs = new FontSetBase{FClass->font_set.size()};
for (int i = 0; i < fs->size(); ++i) {
(*fs)[i] = FClass->font_set.at(i);
}
if (this->fontset_table_.contains(fs)) {
IClass->font_set_id = this->fontset_table_.get_id(fs);
delete[] fs.configs;
delete fs;
} else {
IClass->font_set_id = this->fontset_table_.push_back(fs);
}
@ -854,7 +852,7 @@ INT_TEMPLATES_STRUCT *Classify::ReadIntTemplates(TFile *fp) {
if (version_id >= 5) {
this->fontinfo_table_.read(fp, std::bind(read_spacing_info, _1, _2));
}
this->fontset_table_.read(fp, std::bind(read_set, _1, _2));
this->fontset_table_.read(fp, [](auto *f, auto *fs) { return read_set(f, *fs); } );
}
return (Templates);
@ -952,7 +950,7 @@ void Classify::WriteIntTemplates(FILE *File, INT_TEMPLATES_STRUCT *Templates,
/* first write out the high level struct for the class */
fwrite(&Class->NumProtos, sizeof(Class->NumProtos), 1, File);
fwrite(&Class->NumProtoSets, sizeof(Class->NumProtoSets), 1, File);
ASSERT_HOST(Class->NumConfigs == this->fontset_table_.at(Class->font_set_id).size);
ASSERT_HOST(Class->NumConfigs == this->fontset_table_.at(Class->font_set_id)->size());
fwrite(&Class->NumConfigs, sizeof(Class->NumConfigs), 1, File);
for (j = 0; j < Class->NumConfigs; ++j) {
fwrite(&Class->ConfigLengths[j], sizeof(uint16_t), 1, File);