Fixed some logic, added functions to list allowlist, and category. Category list function will need work, the subcategories are not being parsed at this time

utils/pathfunctions.py

@@ -81,24 +81,38 @@ def export_groups_for_review(df, col="filename_x", group_col="longestcfp"):
     return grouped, df
 
 
+
 def mask_from_csv(df, csv_path, filepath_col):
     """
     Reads reviewed CSV of groups, keeps only files in approved groups.
     """
     review_df = pd.read_csv(csv_path)
-    # Convert string representation of lists back to actual lists
-    review_df[filepath_col] = review_df[filepath_col].apply(ast.literal_eval)
-    
+
+    def parse_paths(val):
+        if isinstance(val, str):
+            try:
+                # Try to parse as a list
+                parsed = ast.literal_eval(val)
+                # If it's not a list, wrap it
+                return parsed if isinstance(parsed, list) else [parsed]
+            except (ValueError, SyntaxError):
+                # If parsing fails, treat it as a single path
+                return [val]
+        return [val]
+
+    review_df[filepath_col] = review_df[filepath_col].apply(parse_paths)
+
     # Flatten all approved file paths into a set for masking
     approved_files = set()
     for paths in review_df[filepath_col]:
         approved_files.update(paths)
-    
+
     # Keep only rows in df that are in approved_files
     masked_df = df[df[filepath_col].isin(approved_files)].copy()
     remainder = df[~df[filepath_col].isin(approved_files)].copy()
     return masked_df, remainder
 
+
 def filter_and_drop(approved, eligiblepaths, min_hashes):
     """
     Filters eligiblepaths to rows where all hashes are in approved,