Memory Optimization Draft one complete

utils/pathfunctions.py

@@ -17,6 +17,7 @@ import pandas as pd
 import os
 from itertools import chain
 import ast
+import re
 
 
 
@@ -134,3 +135,28 @@ def filter_and_drop(approved, eligiblepaths, min_hashes):
     filtered = filtered[filtered['sha256'].apply(len) >= min_hashes]
     
     return filtered
+
+
+def inspect_parquet(path):
+    try:
+        df = pd.read_parquet(path)
+        print(f"✅ Successfully read: {path}")
+        print(f"📄 Columns: {df.columns.tolist()}")
+        print(f"🔢 Rows: {len(df)}")
+        return df
+    except Exception as e:
+        print(f"❌ Error reading {path}: {e}")
+        return pd.DataFrame()
+
+
+
+def regulator(paths, case_insensitive=True):
+    """
+    Build a Python raw string regex that matches any of the given Windows path fragments.
+    """
+    escaped = [re.escape(p) for p in paths]
+    pattern = "(?:" + "|".join(escaped) + ")"
+    if case_insensitive:
+        pattern = pattern
+        print(f"Regulator is providing {pattern}")
+    return f'r"{pattern}"'