Rendering/hash map changes part 2

training/boxchar.cpp

@@ -73,7 +73,6 @@ void BoxChar::PrepareToWrite(vector<BoxChar*>* boxes) {
   if (rtl_rules) {
     ReorderRTLText(boxes);
   }
-  tprintf("Rtl = %d ,vertical=%d\n", rtl_rules, vertical_rules);
 }
 
 // Inserts newline (tab) characters into the vector at newline positions.
@@ -291,13 +290,19 @@ const int kMaxLineLength = 1024;
 /* static */
 void BoxChar::WriteTesseractBoxFile(const string& filename, int height,
                                     const vector<BoxChar*>& boxes) {
+  string output = GetTesseractBoxStr(height, boxes);
+  File::WriteStringToFileOrDie(output, filename);
+}
+
+/* static */
+string BoxChar::GetTesseractBoxStr(int height, const vector<BoxChar*>& boxes) {
   string output;
   char buffer[kMaxLineLength];
   for (int i = 0; i < boxes.size(); ++i) {
     const Box* box = boxes[i]->box_;
     if (box == NULL) {
       tprintf("Error: Call PrepareToWrite before WriteTesseractBoxFile!!\n");
-      return;
+      return "";
     }
     int nbytes =
         snprintf(buffer, kMaxLineLength, "%s %d %d %d %d %d\n",
@@ -305,6 +310,7 @@ void BoxChar::WriteTesseractBoxFile(const string& filename, int height,
                  box->x + box->w, height - box->y, boxes[i]->page_);
     output.append(buffer, nbytes);
   }
-  File::WriteStringToFileOrDie(output, filename);
+  return output;
 }
+
 }  // namespace tesseract

training/boxchar.h

@@ -100,6 +100,9 @@ class BoxChar {
   // is needed to convert to tesseract coordinates.
   static void WriteTesseractBoxFile(const string& name, int height,
                                     const vector<BoxChar*>& boxes);
+  // Gets the tesseract box file as a string from the vector of boxes.
+  // The image height is needed to convert to tesseract coordinates.
+  static string GetTesseractBoxStr(int height, const vector<BoxChar*>& boxes);
 
  private:
   string ch_;

training/cntraining.cpp

@@ -160,13 +160,18 @@ int main(int argc, char *argv[]) {
   // reduce the min samples:
   // Config.MinSamples = 0.5 / num_fonts;
   pCharList = CharList;
+  // The norm protos will count the source protos, so we keep them here in
+  // freeable_protos, so they can be freed later.
+  GenericVector<LIST> freeable_protos;
   iterate(pCharList) {
     //Cluster
-    if (Clusterer)
-       FreeClusterer(Clusterer);
     CharSample = (LABELEDLIST)first_node(pCharList);
     Clusterer =
       SetUpForClustering(FeatureDefs, CharSample, PROGRAM_FEATURE_TYPE);
+    if (Clusterer == NULL) {  // To avoid a SIGSEGV
+      fprintf(stderr, "Error: NULL clusterer!\n");
+      return 1;
+    }
     float SavedMinSamples = Config.MinSamples;
     // To disable the tendency to produce a single cluster for all fonts,
     // make MagicSamples an impossible to achieve number:
@@ -185,21 +190,21 @@ int main(int argc, char *argv[]) {
     }
     Config.MinSamples = SavedMinSamples;
     AddToNormProtosList(&NormProtoList, ProtoList, CharSample->Label);
+    freeable_protos.push_back(ProtoList);
+    FreeClusterer(Clusterer);
   }
   FreeTrainingSamples(CharList);
-  if (Clusterer == NULL) { // To avoid a SIGSEGV
-    fprintf(stderr, "Error: NULL clusterer!\n");
-    return 1;
-  }
-  WriteNormProtos(FLAGS_D.c_str(), NormProtoList, Clusterer);
+  int desc_index = ShortNameToFeatureType(FeatureDefs, PROGRAM_FEATURE_TYPE);
+  WriteNormProtos(FLAGS_D.c_str(), NormProtoList,
+                  FeatureDefs.FeatureDesc[desc_index]);
   FreeNormProtoList(NormProtoList);
-  FreeProtoList(&ProtoList);
-  FreeClusterer(Clusterer);
+  for (int i = 0; i < freeable_protos.size(); ++i) {
+    FreeProtoList(&freeable_protos[i]);
+  }
   printf ("\n");
   return 0;
 }  // main
 
-
 /*----------------------------------------------------------------------------
               Private Code
 ----------------------------------------------------------------------------*/
@@ -211,16 +216,13 @@ int main(int argc, char *argv[]) {
 * of the samples.
 * @param Directory  directory to place sample files into
 * @param LabeledProtoList List of labeled protos
-* @param Clusterer The CLUSTERER to use
+* @param feature_desc Description of the features
 * @return none
 * @note Exceptions: none
 * @note History: Fri Aug 18 16:17:06 1989, DSJ, Created.
 */
-void WriteNormProtos (
-     const char  *Directory,
-     LIST  LabeledProtoList,
-     CLUSTERER *Clusterer)
-{
+void WriteNormProtos(const char *Directory, LIST LabeledProtoList,
+                     const FEATURE_DESC_STRUCT *feature_desc) {
   FILE    *File;
   STRING Filename;
   LABELEDLIST LabeledProto;
@@ -235,8 +237,8 @@ void WriteNormProtos (
   Filename += "normproto";
   printf ("\nWriting %s ...", Filename.string());
   File = Efopen (Filename.string(), "wb");
-  fprintf(File,"%0d\n",Clusterer->SampleSize);
-  WriteParamDesc(File,Clusterer->SampleSize,Clusterer->ParamDesc);
+  fprintf(File, "%0d\n", feature_desc->NumParams);
+  WriteParamDesc(File, feature_desc->NumParams, feature_desc->ParamDesc);
   iterate(LabeledProtoList)
   {
     LabeledProto = (LABELEDLIST) first_node (LabeledProtoList);
@@ -251,7 +253,7 @@ void WriteNormProtos (
       exit(1);
     }
     fprintf(File, "\n%s %d\n", LabeledProto->Label, N);
-    WriteProtos(File, Clusterer->SampleSize, LabeledProto->List, true, false);
+    WriteProtos(File, feature_desc->NumParams, LabeledProto->List, true, false);
   }
   fclose (File);
 

training/pango_font_info.cpp

@@ -127,7 +127,7 @@ string PangoFontInfo::DescriptionName() const {
 /* static */
 void PangoFontInfo::SoftInitFontConfig() {
   if (fonts_dir_.empty()) {
-    HardInitFontConfig(FLAGS_fonts_dir, FLAGS_fontconfig_tmpdir);
+    HardInitFontConfig(FLAGS_fonts_dir.c_str(), FLAGS_fontconfig_tmpdir.c_str());
   }
 }