Update InitialMarkups.py

InitialMarkups.py

@@ -1093,7 +1093,7 @@ def extract_section_under_header_withoutNot(pdf_path):
         return list(range(0, toc_pages[-1] +1)) if toc_pages else toc_pages
 
     toc_pages = get_toc_page_numbers(doc)
-
+    print('here0')
 
     hierarchy = build_header_hierarchy(doc, toc_pages, most_common_font_size, most_common_color, most_common_font)
     listofHeaderstoMarkup = get_leaf_headers_with_paths(hierarchy)
@@ -1125,7 +1125,7 @@ def extract_section_under_header_withoutNot(pdf_path):
                     if not spans:
                         i += 1
                         continue
-
+                    print('here1')
                     y0 = spans[0]["bbox"][1]
                     y1 = spans[0]["bbox"][3]
                     if y0 < top_margin or y1 > (page_height - bottom_margin):
@@ -1142,7 +1142,7 @@ def extract_section_under_header_withoutNot(pdf_path):
                         combined_line_norm = normalize_text(line_text + " " + next_line_text)
                     else:
                         combined_line_norm = line_text_norm
-
+                    print('hereee2')
                     # Check if we should continue processing
                     if combined_line_norm and combined_line_norm in paths[0]:
                         
@@ -1156,7 +1156,7 @@ def extract_section_under_header_withoutNot(pdf_path):
                       stringtowrite='To be billed'
                     if stringtowrite!='To be billed':
                         alltextWithoutNotbilled+= combined_line_norm #################################################
-                   
+    print('donee')             
     return alltextWithoutNotbilled