"""
Integration tests for data_loader.py
"""
import pytest
import pandas as pd
import numpy as np
from pathlib import Path
import sys
import tempfile
import os

# Add parent directory to path
sys.path.insert(0, str(Path(__file__).parent.parent))

from data_loader import load_sales_data, validate_data_structure

class TestDataLoader:
    """Test data loading functions"""
    
    def test_load_sales_data_basic(self):
        """Test basic data loading"""
        # Create temporary CSV
        with tempfile.NamedTemporaryFile(mode='w', suffix='.csv', delete=False) as f:
            f.write('InvoiceDate,USD,Customer\n')
            f.write('2023-01-01,100.0,Customer1\n')
            f.write('2023-02-01,200.0,Customer2\n')
            temp_path = f.name
        
        try:
            # Temporarily update config
            import config
            original_data_file = config.DATA_FILE
            config.DATA_FILE = Path(temp_path).name
            
            df = load_sales_data(Path(temp_path))
            
            assert len(df) == 2
            assert 'Year' in df.columns
            assert 'YearMonth' in df.columns
            
            # Restore config
            config.DATA_FILE = original_data_file
        finally:
            os.unlink(temp_path)
    
    def test_validate_data_structure(self):
        """Test data structure validation"""
        # Valid DataFrame
        df_valid = pd.DataFrame({
            'InvoiceDate': pd.to_datetime(['2023-01-01', '2023-02-01']),
            'USD': [100.0, 200.0]
        })
        
        is_valid, msg = validate_data_structure(df_valid)
        assert is_valid
        assert msg == "OK"
        
        # Invalid DataFrame (missing column)
        df_invalid = pd.DataFrame({
            'InvoiceDate': pd.to_datetime(['2023-01-01'])
        })
        
        is_valid, msg = validate_data_structure(df_invalid)
        assert not is_valid
        assert 'Missing required column' in msg

if __name__ == "__main__":
    pytest.main([__file__, '-v'])