More errors when parsing from corrected XML

src/python/def_classes.py

@@ -402,7 +402,7 @@ class Document:
         
         if 'imgobj' not in self.__dict__.keys():
             self.pdf2imgobj()
-        if 'XML_main' not in self.__dict__.keys():            
+        if 'XML_main_corr' not in self.__dict__.keys():            
             name_tar = self.folder_database + '/' + str(self.year) + '/' + name_outcorrxml + '.tar.gz'
             if os.path.isfile(name_tar):
                 name_xml = './' + str(self.year) + '/' + str(self.id_doc) + suffix_xml + 'corr.xml'
@@ -411,11 +411,17 @@ class Document:
                     #print('Run this')
                     h_xml = utils_proc.get_handlerfile(name_xml, self.folder_database, name_outcorrxml)
                     XML_tree = ET.parse(h_xml)
-                    self.XML_main = XML_tree.getroot()
+                    self.XML_main_corr = XML_tree.getroot()
                 else:
-                    self.pdf2xml(pages = 'all', suffix_xml = suffix_xml, flag_save = 0)   
+                    print('You need to have the tar file to use flag_compute = 0!')
+                    flag_error = 1
+                    return 0, 0, 0, 0, 0, 0, flag_error
+                    #self.pdf2xml(pages = 'all', suffix_xml = suffix_xml, flag_save = 0)   
             else:
-                self.pdf2xml(pages = 'all', suffix_xml = suffix_xml, flag_save = 0)   
+                print('You need to have the tar file to use flag_compute = 0!')
+                flag_error = 1
+                return 0, 0, 0, 0, 0, 0, flag_error
+                #self.pdf2xml(pages = 'all', suffix_xml = suffix_xml, flag_save = 0)   
             ind_abs = np.array([ind_page]).astype(int).reshape((-1,))  
         else:
             #print('Run this')
@@ -425,12 +431,12 @@ class Document:
         #print(ind_abs, type(ind_abs))
         #print(self.XML_main, len(self.imgobj))
         
-        if ind_page > (len(self.XML_main) - 1):
+        if ind_page > (len(self.XML_main_corr) - 1):
             flag_error = 1
             return 0, 0, 0, 0, 0, 0, flag_error
         
         XML_root = ET.Element('pages')
-        XML_root.append(self.XML_main[ind_abs[0]])
+        XML_root.append(self.XML_main_corr[ind_abs[0]])
         imarray = np.array(self.imgobj[ind_page])
         
         bbox_page = np.array(XML_root[0].attrib['bbox'].split(',')).astype(np.float64)