import pandas as pd

# Baca CSV 2024
df = pd.read_csv('Data_2024_Tracer_study.csv', sep=';', encoding='utf-8-sig')
source_cols = list(df.columns)

print("=== HEADER CSV 2024 ===")
print(f"Total kolom: {len(source_cols)}")
print()

# Cari kolom NIM
nim_candidates = [c for c in source_cols if 'nim' in c.lower() or 'nmmhs' in c.lower()]
print(f"Kolom NIM candidates: {nim_candidates}")

# Normalize function dari import_data.py
def normalize(col_name):
    if pd.isna(col_name):
        return ""
    return str(col_name).strip().lower()

# Check find_column
source_cols_lower = {normalize(c): c for c in source_cols}
print()
print("=== TEST find_column ===")
test_names = [
    'nimhsmsmh', 'NIM/Nomor Mahasiswa', 'NIM',
    '3. NIM / nimhsmsmh', '3. NIM / nimhsmsmh  (Gunakan Huruf Besar)',
]

for name in test_names:
    normalized = normalize(name)
    if normalized in source_cols_lower:
        print(f"FOUND: '{name}' -> '{source_cols_lower[normalized]}'")
    else:
        print(f"NOT FOUND: '{name}' (normalized: '{normalized}')")
        # Suggest similar
        for k in source_cols_lower.keys():
            if 'nim' in k or 'nmmhs' in k:
                print(f"  Similar in CSV: '{k}' -> '{source_cols_lower[k]}'")