#!/usr/bin/env python3

from data_comparator import KSTCoordiComparator

def test_sheet_filtering():
    """Test that sheet filtering works correctly and defaults to first sheet"""
    print("Testing sheet filtering functionality...")
    
    # Create comparator and load data
    comparator = KSTCoordiComparator("data/sample-data.xlsx")
    if not comparator.load_data():
        print("Failed to load data!")
        return
    
    print(f"Available sheets: {list(comparator.data.keys())}")
    
    # Test 1: No sheet filter provided (should default to first sheet)
    print("\n=== TEST 1: No sheet filter (should default to first sheet) ===")
    try:
        summary1 = comparator.get_comparison_summary()
        print(f"Default sheet selected: {summary1['current_sheet_filter']}")
        print(f"KST total: {summary1['original_counts']['kst_total']}")
        print(f"Coordi total: {summary1['original_counts']['coordi_total']}")
        print(f"Matched: {summary1['matched_items_count']}")
        print("✓ Test 1 passed")
    except Exception as e:
        print(f"✗ Test 1 failed: {e}")
    
    # Test 2: Specific sheet filter
    sheet_names = list(comparator.data.keys())
    if len(sheet_names) > 1:
        second_sheet = sheet_names[1]
        print(f"\n=== TEST 2: Specific sheet filter ({second_sheet}) ===")
        try:
            summary2 = comparator.get_comparison_summary(second_sheet)
            print(f"Selected sheet: {summary2['current_sheet_filter']}")
            print(f"KST total: {summary2['original_counts']['kst_total']}")
            print(f"Coordi total: {summary2['original_counts']['coordi_total']}")
            print(f"Matched: {summary2['matched_items_count']}")
            print("✓ Test 2 passed")
        except Exception as e:
            print(f"✗ Test 2 failed: {e}")
    else:
        print("\n=== TEST 2: Skipped (only one sheet available) ===")
    
    # Test 3: Verify no duplicates across sheets (this was the original problem)
    print(f"\n=== TEST 3: Verify duplicate detection within single sheets only ===")
    for sheet_name in sheet_names:
        summary = comparator.get_comparison_summary(sheet_name)
        print(f"Sheet '{sheet_name}':")
        print(f"  KST duplicates: {summary['mismatches']['kst_duplicates_count']}")
        print(f"  Coordi duplicates: {summary['mismatches']['coordi_duplicates_count']}")
    
    print("\n✓ All tests completed!")

if __name__ == "__main__":
    test_sheet_filtering()