Replace more PointerVector by std::vector for src/training

Signed-off-by: Stefan Weil <[email protected]>

src/ccutil/genericvector.h

@@ -401,27 +401,6 @@ class PointerVector : public GenericVector<T *> {
     GenericVector<T *>::truncate(size);
   }
 
-  // Compact the vector by deleting elements for which delete_cb returns
-  // true. delete_cb is a permanent callback and will be deleted.
-  void compact(std::function<bool(const T *)> delete_cb) {
-    int new_size = 0;
-    int old_index = 0;
-    // Until the callback returns true, the elements stay the same.
-    while (old_index < GenericVector<T *>::size_used_ &&
-           !delete_cb(GenericVector<T *>::data_[old_index++])) {
-      ++new_size;
-    }
-    // Now just copy anything else that gets false from delete_cb.
-    for (; old_index < GenericVector<T *>::size_used_; ++old_index) {
-      if (!delete_cb(GenericVector<T *>::data_[old_index])) {
-        GenericVector<T *>::data_[new_size++] = GenericVector<T *>::data_[old_index];
-      } else {
-        delete GenericVector<T *>::data_[old_index];
-      }
-    }
-    GenericVector<T *>::size_used_ = new_size;
-  }
-
   // Clear the array, calling the clear callback function if any.
   // All the owned callbacks are also deleted.
   // If you don't want the callbacks to be deleted, before calling clear, set

src/training/common/trainingsampleset.cpp

@@ -82,12 +82,15 @@ TrainingSampleSet::TrainingSampleSet(const FontInfoTable &font_table)
     , fontinfo_table_(font_table) {}
 
 TrainingSampleSet::~TrainingSampleSet() {
+  for (auto sample : samples_) {
+    delete sample;
+  }
   delete font_class_array_;
 }
 
 // Writes to the given file. Returns false in case of error.
 bool TrainingSampleSet::Serialize(FILE *fp) const {
-  if (!samples_.Serialize(fp))
+  if (!tesseract::Serialize(fp, samples_))
     return false;
   if (!unicharset_.save_to_file(fp))
     return false;
@@ -106,7 +109,7 @@ bool TrainingSampleSet::Serialize(FILE *fp) const {
 // Reads from the given file. Returns false in case of error.
 // If swap is true, assumes a big/little-endian swap is needed.
 bool TrainingSampleSet::DeSerialize(bool swap, FILE *fp) {
-  if (!samples_.DeSerialize(swap, fp))
+  if (!tesseract::DeSerialize(swap, fp, samples_))
     return false;
   num_raw_samples_ = samples_.size();
   if (!unicharset_.load_from_file(fp))
@@ -498,17 +501,26 @@ void TrainingSampleSet::KillSample(TrainingSample *sample) {
 // Deletes all samples with zero features marked by KillSample.
 void TrainingSampleSet::DeleteDeadSamples() {
   using namespace std::placeholders; // for _1
-  samples_.compact(std::bind(&TrainingSampleSet::DeleteableSample, this, _1));
+  auto old_it = samples_.begin();
+  for (; old_it < samples_.end(); ++old_it) {
+    if (*old_it == nullptr || (*old_it)->class_id() < 0) {
+      break;
+    }
+  }
+  auto new_it = old_it;
+  for (; old_it < samples_.end(); ++old_it) {
+    if (*old_it == nullptr || (*old_it)->class_id() < 0) {
+      delete *old_it;
+    } else {
+      *new_it = *old_it;
+      ++new_it;
+    }
+  }
+  samples_.resize(new_it - samples_.begin() + 1);
   num_raw_samples_ = samples_.size();
   // Samples must be re-organized now we have deleted a few.
 }
 
-// Callback function returns true if the given sample is to be deleted, due
-// to having a negative classid.
-bool TrainingSampleSet::DeleteableSample(const TrainingSample *sample) {
-  return sample == nullptr || sample->class_id() < 0;
-}
-
 // Construct an array to access the samples by font,class pair.
 void TrainingSampleSet::OrganizeByFontAndClass() {
   // Font indexes are sparse, so we used a map to compact them, so we can

src/training/common/trainingsampleset.h

@@ -172,10 +172,6 @@ class TrainingSampleSet {
   // must be called after as the samples have been renumbered.
   void DeleteDeadSamples();
 
-  // Callback function returns true if the given sample is to be deleted, due
-  // to having a negative classid.
-  bool DeleteableSample(const TrainingSample *sample);
-
   // Construct an array to access the samples by font,class pair.
   void OrganizeByFontAndClass();
 
@@ -254,7 +250,7 @@ class TrainingSampleSet {
     std::vector<FontClassDistance> distance_cache;
   };
 
-  PointerVector<TrainingSample> samples_;
+  std::vector<TrainingSample *> samples_;
   // Number of samples before replication/randomization.
   int num_raw_samples_;
   // Character set we are training for.