#!/usr/bin/env python3
"""
Compare rolling_stone_top_500_albums_2020.csv and wikipedia_top_500_albums.csv to find dropped albums.
"""

import csv

def normalize_text(text):
    """Normalize text for comparison"""
    return text.lower().strip().replace('&', 'and').replace('  ', ' ')

def main():
    # Read 2020 Rolling Stone albums
    albums_2020 = {}
    with open('rolling_stone_2020_simplified.csv', 'r', encoding='utf-8') as file:
        reader = csv.DictReader(file)
        for row in reader:
            key = (normalize_text(row['Artist']), normalize_text(row['Album']))
            albums_2020[key] = {
                'rank': row['Rank'],
                'artist': row['Artist'],
                'album': row['Album']
            }
    
    print(f"📊 Loaded {len(albums_2020)} albums from 2020 Rolling Stone list")
    
    # Read Wikipedia 2023 albums (note: columns are rank,album,artist)
    albums_2023_wiki = set()
    with open('wikipedia_top_500_albums.csv', 'r', encoding='utf-8') as file:
        reader = csv.DictReader(file)
        for row in reader:
            # Wikipedia format: rank,album,artist
            key = (normalize_text(row['artist']), normalize_text(row['album']))
            albums_2023_wiki.add(key)
    
    print(f"📊 Loaded {len(albums_2023_wiki)} albums from Wikipedia 2023 list")
    
    # Find dropped albums (in 2020 but not in Wikipedia 2023)
    dropped_albums = []
    for key, album_info in albums_2020.items():
        if key not in albums_2023_wiki:
            dropped_albums.append(album_info)
    
    # Sort by original 2020 rank
    dropped_albums.sort(key=lambda x: int(x['rank']))
    
    print(f"\n❌ Found {len(dropped_albums)} albums dropped from 2020 to 2023:")
    print("=" * 80)
    
    for album in dropped_albums:
        print(f"#{album['rank']:3s} - {album['artist']} - {album['album']}")
    
    print("=" * 80)
    print(f"\n📊 Summary:")
    print(f"   - Albums in 2020: {len(albums_2020)}")
    print(f"   - Albums in Wikipedia 2023: {len(albums_2023_wiki)}")
    print(f"   - Albums dropped: {len(dropped_albums)}")
    
    # Save dropped albums list
    with open('dropped_albums_2020_vs_2023.csv', 'w', newline='', encoding='utf-8') as file:
        fieldnames = ['Original_Rank_2020', 'Artist', 'Album']
        writer = csv.DictWriter(file, fieldnames=fieldnames)
        writer.writeheader()
        for album in dropped_albums:
            writer.writerow({
                'Original_Rank_2020': album['rank'],
                'Artist': album['artist'],
                'Album': album['album']
            })
    
    print(f"\n💾 Saved dropped albums list to: dropped_albums_2020_vs_2023.csv")

if __name__ == "__main__":
    main()