Add monitor to GetHOCRText

tesseract-ocr · May 17, 2015 · ed6ae9b · ed6ae9b
1 parent 59bcbc7
commit ed6ae9b
Show file tree

Hide file tree

Showing 3 changed files with 25 additions and 3 deletions.
diff --git a/api/baseapi.cpp b/api/baseapi.cpp
@@ -1397,8 +1397,20 @@ 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;

diff --git a/api/baseapi.h b/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.

diff --git a/api/capi.cpp b/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)