Update Doors_Schedule.py

Doors_Schedule.py

@@ -1009,7 +1009,7 @@ def get_similar_colors_all(selected_columns_new):
     def col_template():
         d = {
             'values': [],
-            'color': None
+            'color_annot': None
         }
         for field in clmns_fields:
             d[field] = []
@@ -1024,7 +1024,7 @@ def get_similar_colors_all(selected_columns_new):
         for field in clmns_fields:
             col_dict[key][field].append(row.get(field, None))
 
-        col_dict[key]['color'] = key_colors[key]
+        col_dict[key]['color_annot'] = key_colors[key]
 
     return dict(col_dict)
 
@@ -1040,7 +1040,7 @@ def get_flattened_tuples_list_all(col_dict):
         n_rows = len(values_dict[list_fields[0]]) if list_fields else 0
 
         for i in range(n_rows):
-            tuple_row = tuple(values_dict[field][i] for field in list_fields) + (values_dict['color'],)
+            tuple_row = tuple(values_dict[field][i] for field in list_fields) + (values_dict['color_annot'],)
             flattened_list.append(tuple_row)
 
     return flattened_list
@@ -1549,11 +1549,11 @@ def get_widths_bb_format_st_op(cleaned_width, kelma):
 # New for new dictionary logic
 def create_bb_bax_new(df_points, CountStyles, page_number, height_plan):
   bax_annotations = []
-  exclude = {"location", "color"}
+  exclude = {"location", "color_annot"}
   for _, row in df_points.iterrows():
     rw = row
     customDta = row.drop(labels=exclude, errors="ignore").to_dict()
-    r,g,b = rw['color']
+    r,g,b = rw['color_annot']
     R = str(float(r/255))
     G = str(float(g/255))
     B = str(float(b/255))
@@ -1692,7 +1692,11 @@ def mainRun(schedule, plan, searcharray, sch_csv_pdf):
     if sch_csv_pdf:
       print("shcedule type is PDF")
       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)
+      try:
+         no_tables_model, not_found_any_plan_model = pick_approach(schedule, plan, searcharray, 2)
+      except:
+         print("Model detection has issue of file too large")
+         #no_tables_model = True
       pick_normal = False
       pick_model = False
       if no_tables_model:
@@ -1812,6 +1816,9 @@ def mainRun(schedule, plan, searcharray, sch_csv_pdf):
             else:
                if secondary_presence:
                   main_info = main_info + [""]
+               # new logic can handle it   
+               #col_dict = get_similar_colors_all(selected_columns_combined)
+ 
                flattened_list = get_flattened_tuples_list_no_doortype(selected_columns_combined)
               
             
@@ -1832,15 +1839,22 @@ def mainRun(schedule, plan, searcharray, sch_csv_pdf):
             df_points = grouped_to_dataframe_dynamic(col_dict,
                                          drop_empty_locations=True,
                                          explode_locations=True)
-            df_points.columns = df_points.columns.str.strip().str.replace(r"\s+", "_", regex=True)
+            #df_points.columns = df_points.columns.str.strip().str.replace(r"\s+", "_", regex=True)
+            # Clean column names 
+            df_points.columns = (df_points.columns
+              .str.strip()
+              .str.replace(r"[^\w-]+", "_", regex=True)
+              .str.replace(r"_+", "_", regex=True)
+              .str.strip("_"))
+            
             print(f"col_dict: {col_dict}")
             print(f"selected_columns_combined: {selected_columns_combined}")
             print(f"df: {df_points}")
             if df_points.empty:
-              continue 
+              continue # to the next user input
             # handling no door type in the new dictionary logic
-            if 'color' not in df_points:
-              df_points['color'] = (0, 0, 255)
+            if 'color_annot' not in df_points:
+              df_points['color_annot'] = (0, 0, 255)
             dupes = df_points['door_id'].value_counts()
             repeated_ids = dupes[dupes > 1].index.to_list()
             repeated_labels_list.append(repeated_ids)
@@ -1857,6 +1871,10 @@ def mainRun(schedule, plan, searcharray, sch_csv_pdf):
                 df_points['width'] = widths          # e.g., a list/Series/np.array or a scalar
                 df_points['height'] = heights
               else:
+                # make sure they are strings first to keep the flow of get_width_clean_width_height function
+                df_points['width'] = df_points['width'].astype('string')
+                df_points['height'] = df_points['height'].astype('string')
+
                 lst_width = df_points["width"].tolist()
                 lst_height = df_points["height"].tolist()
                 clean_widths, clean_height = get_width_clean_width_height(lst_width, lst_height)
@@ -1876,7 +1894,7 @@ def mainRun(schedule, plan, searcharray, sch_csv_pdf):
             #widht_count, height_count = generate_separate_dimensions(widths)
             #bax = create_bb_bax_secondary(new_data3, widht_count, height_count, secondary_tobeprinted, CountStyles, user_input, page_number, page)
             #bax_annotations_all_inputs.append(bax)
-            print(f"colors: {df_points['color']}")
+            print(f"color_annot: {df_points['color_annot']}")
             print(f"df: {df_points}")
             bax, customDta = create_bb_bax_new(df_points, CountStyles, page_number, page)
             bax_annotations_all_inputs.append(bax)