#!/usr/bin/env python3
"""
Re-check dropped albums with the corrected artist/album names.
"""

import csv

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

def main():
    # Read 2020 albums (simplified)
    albums_2020 = {}
    with open('rolling_stone_2020_simple.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 list")
    
    # Read current 2023 albums (only first 500)
    albums_2023 = set()
    albums_2023_details = []
    new_count = 0
    
    with open('top_500_albums_2023.csv', 'r', encoding='utf-8') as file:
        reader = csv.DictReader(file)
        for row in reader:
            rank = int(row['Rank'])
            if rank <= 500:
                key = (normalize_text(row['Artist']), normalize_text(row['Album']))
                albums_2023.add(key)
                albums_2023_details.append({
                    'rank': row['Rank'],
                    'artist': row['Artist'],
                    'album': row['Album'],
                    'status': row['Status']
                })
                if row['Status'] == 'New in 2023':
                    new_count += 1
    
    print(f"📊 Loaded {len(albums_2023)} albums from 2023 list (first 500)")
    print(f"🆕 Found {new_count} albums marked as 'New in 2023'")
    
    # Find albums currently marked as dropped
    current_dropped = []
    with open('top_500_albums_2023.csv', 'r', encoding='utf-8') as file:
        reader = csv.DictReader(file)
        for row in reader:
            if 'Dropped' in row['Status']:
                current_dropped.append({
                    'rank': row['Rank'],
                    'artist': row['Artist'],
                    'album': row['Album'],
                    'status': row['Status']
                })
    
    print(f"📊 Currently have {len(current_dropped)} albums marked as dropped")
    
    # Find truly dropped albums (in 2020 but not in 2023)
    truly_dropped = []
    for key, album_info in albums_2020.items():
        if key not in albums_2023:
            truly_dropped.append(album_info)
    
    # Sort by original 2020 rank
    truly_dropped.sort(key=lambda x: int(x['rank']))
    
    print(f"\n❌ Found {len(truly_dropped)} albums that should be dropped (in 2020 but not in 2023)")
    
    # Show first 20 that should be dropped
    print("\nFirst 20 albums that should be dropped:")
    print("=" * 80)
    for i, album in enumerate(truly_dropped[:20]):
        print(f"#{album['rank']:3s} - {album['artist']} - {album['album']}")
    print("=" * 80)
    
    # Check if any current "dropped" albums are actually in the 2023 list
    incorrect_drops = []
    for dropped in current_dropped:
        key = (normalize_text(dropped['artist']), normalize_text(dropped['album']))
        if key in albums_2023:
            # Find it in the 2023 list
            for album_2023 in albums_2023_details:
                if (normalize_text(album_2023['artist']) == key[0] and 
                    normalize_text(album_2023['album']) == key[1]):
                    incorrect_drops.append({
                        'dropped_rank': dropped['rank'],
                        'actual_rank': album_2023['rank'],
                        'artist': dropped['artist'],
                        'album': dropped['album']
                    })
                    break
    
    if incorrect_drops:
        print(f"\n⚠️  Found {len(incorrect_drops)} albums marked as dropped but are in main list:")
        for inc in incorrect_drops[:10]:
            print(f"   Marked as dropped at #{inc['dropped_rank']} but is at #{inc['actual_rank']} - {inc['artist']} - {inc['album']}")
    
    print(f"\n📊 Summary:")
    print(f"   - Should have dropped: {len(truly_dropped)}")
    print(f"   - Currently marked as dropped: {len(current_dropped)}")
    print(f"   - Difference: {len(truly_dropped) - len(current_dropped)}")
    
    # Save the correct dropped list
    with open('correct_dropped_albums.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 truly_dropped:
            writer.writerow({
                'Original_Rank_2020': album['rank'],
                'Artist': album['artist'],
                'Album': album['album']
            })
    
    print(f"\n💾 Saved correct dropped list to: correct_dropped_albums.csv")

if __name__ == "__main__":
    main()