Monitor

api/baseapi.cpp

@@ -1397,12 +1397,25 @@ static void AddBoxTohOCR(const PageIterator *it,
  * STL removed from original patch submission and refactored by rays.
  */
 char* TessBaseAPI::GetHOCRText(int page_number) {
+  return GetHOCRText(NULL,page_number);
+}
+
+/**
+ * Make a HTML-formatted string with hOCR markup from the internal
+ * data structures.
+ * page_number is 0-based but will appear in the output as 1-based.
+ * Image name/input_file_ can be set by SetInputName before calling
+ * GetHOCRText
+ * STL removed from original patch submission and refactored by rays.
+ */
+char* TessBaseAPI::GetHOCRText(struct ETEXT_DESC* monitor, int page_number) {
   if (tesseract_ == NULL ||
-      (page_res_ == NULL && Recognize(NULL) < 0))
+      (page_res_ == NULL && Recognize(monitor) < 0))
     return NULL;
 
   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);
 
@@ -1468,7 +1481,12 @@ char* TessBaseAPI::GetHOCRText(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);
     }

api/baseapi.h

@@ -583,6 +583,16 @@ class TESS_API TessBaseAPI {
    */
   char* GetUTF8Text();
 
+  /**
+   * Make a HTML-formatted string with hOCR markup from the internal
+   * data structures.
+   * page_number is 0-based but will appear in the output as 1-based.
+   * monitor can be used to
+   * 	cancel the regocnition
+   * 	receive progress callbacks
+   */
+  char* GetHOCRText(struct ETEXT_DESC* monitor, int page_number);
+
   /**
    * Make a HTML-formatted string with hOCR markup from the internal
    * data structures.

api/capi.cpp

@@ -424,7 +424,7 @@ TESS_API int TESS_CALL TessBaseAPIRecognizeForChopTest(TessBaseAPI* handle, ETEX
 TESS_API BOOL TESS_CALL TessBaseAPIProcessPages(TessBaseAPI* handle, const char* filename, const char* retry_config,
                                                 int timeout_millisec, TessResultRenderer* renderer)
 {
-    if (handle->ProcessPages(filename, retry_config, timeout_millisec, renderer))    
+    if (handle->ProcessPages(filename, retry_config, timeout_millisec, renderer))
         return TRUE;
     else
         return FALSE;
@@ -456,7 +456,7 @@ TESS_API char* TESS_CALL TessBaseAPIGetUTF8Text(TessBaseAPI* handle)
 
 TESS_API char* TESS_CALL TessBaseAPIGetHOCRText(TessBaseAPI* handle, int page_number)
 {
-    return handle->GetHOCRText(page_number);
+    return handle->GetHOCRText(NULL, page_number);
 }
 
 TESS_API char* TESS_CALL TessBaseAPIGetBoxText(TessBaseAPI* handle, int page_number)

ccmain/control.cpp

@@ -224,10 +224,22 @@ bool Tesseract::RecogAllWordsPassN(int pass_n, ETEXT_DESC* monitor,
     if (w > 0) word->prev_word = &(*words)[w - 1];
     if (monitor != NULL) {
       monitor->ocr_alive = TRUE;
-      if (pass_n == 1)
-        monitor->progress = 30 + 50 * w / words->size();
-      else
-        monitor->progress = 80 + 10 * w / words->size();
+      if (pass_n == 1) {
+      //  monitor->progress = 30 + 50 * w / words->size();
+        monitor->progress = 70 * w / words->size();
+        if (monitor->progress_callback != NULL) {
+            TBOX box = pr_it->word()->word->bounding_box();
+            (*monitor->progress_callback)(monitor->progress,
+                                          box.left(), box.right(),
+                                          box.top(), box.bottom());
+        }
+      } else {
+        monitor->progress = 70 + 30 * w / words->size();
+        if (monitor->progress_callback!=NULL) {
+                      (*monitor->progress_callback)(monitor->progress,
+                                                    0, 0, 0, 0);
+        }
+      }
       if (monitor->deadline_exceeded() ||
           (monitor->cancel != NULL && (*monitor->cancel)(monitor->cancel_this,
                                                          words->size()))) {

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

ccutil/ocrclass.h

@@ -101,13 +101,17 @@ typedef struct {                  /*single character */
  * the OCR engine is storing its output to shared memory.
  * During progress, all the buffer info is -1.
  * Progress starts at 0 and increases to 100 during OCR. No other constraint.
+ * Additionally the progress callback contains the bounding box of the word that
+ * is currently being processed.
  * Every progress callback, the OCR engine must set ocr_alive to 1.
  * The HP side will set ocr_alive to 0. Repeated failure to reset
  * to 1 indicates that the OCR engine is dead.
  * If the cancel function is not null then it is called with the number of
  * user words found. If it returns true then operation is cancelled.
  **********************************************************************/
 typedef bool (*CANCEL_FUNC)(void* cancel_this, int words);
+typedef bool (*PROGRESS_FUNC)(int progress,
+                              int left, int right, int top, int bottom);
 
 class ETEXT_DESC {             // output header
  public:
@@ -117,6 +121,7 @@ class ETEXT_DESC {             // output header
   volatile inT8 ocr_alive;     // ocr sets to 1, HP 0
   inT8 err_code;               // for errcode use
   CANCEL_FUNC cancel;          // returns true to cancel
+  PROGRESS_FUNC progress_callback; // called whenever progress increases
   void* cancel_this;           // this or other data for cancel
   struct timeval end_time;     // time to stop. expected to be set only by call
                                // to set_deadline_msecs()