Update normalize.py

normalize.py

@@ -1,11 +1,27 @@
 import pandas as pd
-from typing import List
+from typing import List, Optional
 
-def normalize_csv_order(csv_path: str, out_path: str, expected_cols: List[str]) -> str:
-    df = pd.read_csv(csv_path)
-    for c in expected_cols:
-        if c not in df.columns:
-            df[c] = None
-    df = df[expected_cols]
-    df.to_csv(out_path, index=False)
-    return out_path
+def normalize_columns(df: pd.DataFrame) -> pd.DataFrame:
+"""
+Gentle normalization:
+- strip whitespace from column names
+- replace weird invisible chars
+"""
+df = df.copy()
+df.columns = [str(c).strip().replace("\ufeff", "") for c in df.columns]
+return df
+
+def ensure_expected_columns(df: pd.DataFrame, expected: Optional[List[str]] = None) -> pd.DataFrame:
+"""
+If expected columns are provided:
+- add missing cols as empty
+- drop extra cols not in expected
+"""
+if not expected:
+return df
+df = df.copy()
+for col in expected:
+if col not in df.columns:
+df[col] = ""
+df = df[expected]
+return df