added row attributes to hocr output

Author: zdenop

api/baseapi.cpp

@@ -1415,6 +1415,7 @@ char* TessBaseAPI::GetHOCRText(struct ETEXT_DESC* monitor, int page_number) {
 
   int lcnt = 1, bcnt = 1, pcnt = 1, wcnt = 1;
   int page_id = page_number + 1;  // hOCR uses 1-based page numbers.
+  float row_height, descenders, ascenders;  // row attributes
   bool font_info = false;
   GetBoolVariable("hocr_font_info", &font_info);
 
@@ -1480,7 +1481,12 @@ char* TessBaseAPI::GetHOCRText(struct ETEXT_DESC* monitor, int page_number) {
       AddBoxTohOCR(res_it, RIL_PARA, &hocr_str);
     }
     if (res_it->IsAtBeginningOf(RIL_TEXTLINE)) {
+      int fontsize;
       hocr_str.add_str_int("\n     <span class='ocr_line' id='line_", page_id);
+      res_it->RowAttributes(&row_height, &descenders, &ascenders);
+      hocr_str.add_str_int("' size='", row_height);
+      hocr_str.add_str_int("' descenders='", descenders * -1);
+      hocr_str.add_str_int("' ascenders='", ascenders);
       hocr_str.add_str_int("_", lcnt);
       AddBoxTohOCR(res_it, RIL_TEXTLINE, &hocr_str);
     }

ccmain/ltrresultiterator.cpp

@@ -145,6 +145,15 @@ float LTRResultIterator::Confidence(PageIteratorLevel level) const {
   return 0.0f;
 }
 
+void LTRResultIterator::RowAttributes(float* row_height,
+                                      float* descenders,
+                                      float* ascenders) const {
+    *row_height = it_->row()->row->x_height() + it_->row()-> row->ascenders()
+                  - it_->row()->row->descenders();
+    *descenders = it_->row()->row->descenders();
+    *ascenders = it_->row()->row->ascenders();
+}
+
 // Returns the font attributes of the current word. If iterating at a higher
 // level object than words, eg textlines, then this will return the
 // attributes of the first word in that textline.

ccmain/ltrresultiterator.h

@@ -91,6 +91,11 @@ class TESS_API LTRResultIterator : public PageIterator {
   // The number should be interpreted as a percent probability. (0.0f-100.0f)
   float Confidence(PageIteratorLevel level) const;
 
+  // Returns the attributes of the current row.
+  void RowAttributes(float* row_height,
+                     float* descenders,
+                     float* ascenders) const;
+
   // ============= Functions that refer to words only ============.
 
   // Returns the font attributes of the current word. If iterating at a higher