import sys
import glob
sys.path.append('Backend')
from app.config.database import SessionLocal
from app.services.import_service import import_data
from app.parsers.mappings import YEAR_CONFIG, IDENTITAS_MAPPING
from app.parsers.column_finder import find_column, get_value
import pandas as pd

files_2025 = glob.glob('Data_Tracerstudy/*2025*.csv') + glob.glob('Data_Tracerstudy/*2025*.xlsx')
print(f"Found {len(files_2025)} files for 2025:")
for f in files_2025:
    print(" -", f)

for fpath in glob.glob('Data_Tracerstudy/*2025*.csv'):
    print("\n" + "="*60)
    print(f"Testing import simulation for: {fpath}")
    print("="*60)
    
    # Check pandas read
    try:
        df = pd.read_csv(fpath, sep=';', encoding='utf-8-sig')
        print(f"DF shape: {df.shape}")
        
        # Check NIM column finding
        source_cols = list(df.columns)
        nim_col = find_column(source_cols, IDENTITAS_MAPPING['nim'])
        print(f"Found NIM column: {repr(nim_col)}")
        
        # Check first 5 NIM values
        if nim_col:
            print("First 5 NIM values:", df[nim_col].dropna().head().tolist())
            print(f"Total rows in df: {len(df)}")
            print(f"Non-null NIMs: {df[nim_col].notna().sum()}")
            empty_nims = df[df[nim_col].isna() | (df[nim_col].astype(str).str.strip() == '')]
            print(f"Empty NIM count: {len(empty_nims)}")
            if len(empty_nims) > 0:
                print("Index of empty NIMs:", empty_nims.index.tolist()[:10])
                print("Sample empty NIM rows preview:")
                print(df.iloc[empty_nims.index[:3]][df.columns[:5]])
        else:
            print("WARNING: NIM column NOT FOUND!")
            print("Columns containing 'nim':", [c for c in source_cols if 'nim' in c.lower()])
            
    except Exception as e:
        print(f"Error reading CSV {fpath}: {e}")