Added Preflights

utils/pathfunctions.py

@@ -115,4 +115,19 @@ def filepathInitialGroup(df: pd.DataFrame):
     path_eligible = deduplicate_lists(path_eligible)
     path_ineligible = deduplicate_lists(path_ineligible)
 
-    return path_eligible, path_ineligible
+    return path_eligible, path_ineligible
+
+def filter_and_drop(approved, eligiblepaths, min_hashes):
+    """
+    Filters eligiblepaths to rows where all hashes are in approved,
+    then drops rows with fewer than min_hashes hashes.
+    """
+    approved_hashes = set(approved['sha256'])
+
+    def all_hashes_approved(row):
+        return all(h in approved_hashes for h in row['sha256'])
+
+    filtered = eligiblepaths[eligiblepaths.apply(all_hashes_approved, axis=1)]
+    filtered = filtered[filtered['sha256'].apply(len) >= min_hashes]
+    
+    return filtered