Update Doors_Schedule.py

Doors_Schedule.py

@@ -1213,7 +1213,6 @@ def mirrored_points(x, y, height_plan):
   mirrored = []
   mirrored.append([x, height_plan - y])
   return mirrored
-
 def point_mupdf_to_pdf(x, y, page):
     mediabox = page.mediabox
     H = float(mediabox.height)  # Use mediabox height, not rect height
@@ -1222,8 +1221,6 @@ def point_mupdf_to_pdf(x, y, page):
     pdf_y = mediabox.y0 + (H - y)
     
     return [[pdf_x, pdf_y]]
-    
-
 # Modified to adjust mirrored points
 def create_bb_bax_secondary(new_data, widthat, heightat, secondary_tobeprinted, CountStyles, input_user_clmn_names, page_number, height_plan):
   bax_annotations = []
@@ -1346,10 +1343,100 @@ def generate_bluebeam_columns_raw(column_names):
     return tostring(root, encoding="unicode", method="xml")
 
 
+def pick_approach(schedule, plan, searcharray, flag):    
+    not_found_list = []
+    missings = []
+    no_tables = False
+    for p in plan:
+        for k in range(len(schedule)):
+          if flag == 1:
+            dfs = extract_tables(schedule[k])
+          if flag == 2:
+            dfs = extract_tables_model(schedule[k])
+          user_input_this_schedule = searcharray[k]
+          for j in range(len(user_input_this_schedule)):
+            user_input = user_input_this_schedule[j]
+            secondary_presence = False
+            if user_input[4] or user_input[5]:
+              secondary_presence = True
+              main_info_, secondary_info_ = separate_main_secondary(user_input)
+              main_info = [item for item in main_info_ if item]
+              secondary_info = [item for item in secondary_info_ if item]        
+          
+            selected_columns_combined = get_selected_columns_all(dfs, user_input)
+            if selected_columns_combined is None:
+                dfs_normal = extract_tables(schedule[k])
+                column_indices = get_column_indices_from_dfs_normal(dfs_normal, user_input)
+                if column_indices is None:
+                   missing_clmns = check_missing(dfs, user_input)
+                   missing_message = f"{missing_clmns} can't be extracted from table input {j+1} in schedule {k+1}"
+                   missings.append(missing_message)     
+                   no_tables = True 
+                   continue # continue to the next user input
+                if len(dfs) == 1:
+                  selected_columns_combined = get_selected_columns_by_index(dfs[0], column_indices, user_input)
+                if len(dfs) > 1:
+                  index_df = get_df_index(dfs, user_input)
+                  selected_columns_combined = get_selected_columns_by_index(dfs[index_df], column_indices, user_input)
+            selected_columns_combined = selected_columns_combined.applymap(lambda x: 'N/A' if isinstance(x, str) and x.strip() == '' else x)
+            selected_columns_combined = selected_columns_combined.fillna('N/A')
+            selected_columns_combined = selected_columns_combined.replace(r'(?i)\bn/a\b', 'N/A', regex=True)
+            kelma = get_st_op_pattern(selected_columns_combined, user_input)
+            if "door_type" in selected_columns_combined.columns:
+              col_dict = get_similar_colors_all(selected_columns_combined)
+              flattened_list = get_flattened_tuples_list_all(col_dict)
+            else:
+               if secondary_presence:
+                  main_info = main_info + [""]
+               flattened_list = get_flattened_tuples_list_no_doortype(selected_columns_combined)
+            plan_texts = read_text(p)
+
+            if secondary_presence:
+                    locations, not_found = get_word_locations_plan_secondary(flattened_list,plan_texts, main_info, secondary_info)
+                    not_found_list.append(not_found)
+                    
+                                      
+            else:
+                locations, not_found = get_word_locations_plan(flattened_list,plan_texts)
+                not_found_list.append(not_found)
+    
+    ## Getting the not found in all plans
+    flattened_not_found_list = [item for sublist in not_found_list for item in sublist]
+    from collections import Counter
+    counts_not_found = Counter(flattened_not_found_list)
+    not_found_any_plan = []
+    for key, value in counts_not_found.items():
+      if value == len(plan):
+        not_found_any_plan.append(key)
+    return no_tables, not_found_any_plan
 
 def mainRun(schedule, plan, searcharray):
     print("mainRun is RUNNING")
-    
+    no_tables_normal, not_found_any_plan_normal = pick_approach(schedule, plan, searcharray, 1)
+    no_tables_model, not_found_any_plan_model = pick_approach(schedule, plan, searcharray, 2)
+    pick_normal = False
+    pick_model = False
+    if no_tables_model:
+      pick_normal = True
+      #print("choose normal")
+    elif no_tables_normal:
+      pick_model = True
+      #print("choose model")
+    elif no_tables_model and no_tables_normal:
+      print("el etneen bayzeen")
+    else:
+      ## Decide according to the not found labels
+      #print("el etneen shaghaleen")
+      if len(not_found_any_plan_model) > len(not_found_any_plan_normal):
+        #print("choose not_found_any_plan_normal")
+        pick_normal = True
+      elif len(not_found_any_plan_model) < len(not_found_any_plan_normal):
+        pick_model = True
+        #print("choose not_found_any_plan_model")
+      else:
+        pick_normal = True
+        #print("choose any")
+
     #print(type(plan))
     eltype = type(plan)
     print(f"el type beta3 variable plan:: {eltype}")
@@ -1388,7 +1475,10 @@ def mainRun(schedule, plan, searcharray):
         #width_plan = math.ceil(width_plan)
         #height_plan = math.ceil(height_plan)
         for k in range(len(schedule)):
-          dfs = extract_tables_model(schedule[k])
+          if pick_normal:
+             dfs = extract_tables(schedule[k])
+          if pick_model:
+             dfs = extract_tables_model(schedule[k])
           user_input_this_schedule = searcharray[k]
           for j in range(len(user_input_this_schedule)):
             user_input = user_input_this_schedule[j]
@@ -1533,4 +1623,5 @@ def mainRun(schedule, plan, searcharray):
                 v='stroke'
               x,y,z=int(annot_color.get(v)[0]*255),int(annot_color.get(v)[1]*255),int(annot_color.get(v)[2]*255)
               list1.loc[len(list1)] =[annot.info['content'],annot.info['id'],annot.info['subject'],[x,y,z]]
-    return annotatedimgs, doc2 , list1, repeated_labels , not_found, pretty_xml, column_xml
+    return annotatedimgs, doc2 , list1, repeated_labels , not_found, pretty_xml, column_xml
+