Signed-off-by: Matt Bruce <mbrucedogs@gmail.com>

musicbrainz_cleaner.py

@@ -1,10 +0,0 @@
-#!/usr/bin/env python3
-"""
-MusicBrainz Data Cleaner - Entry Point
-Simple entry point that imports from the refactored src structure
-"""
-
-from src.cli.main import main
-
-if __name__ == "__main__":
-    exit(main()) 

quick_test_20.py

@@ -1,108 +0,0 @@
-#!/usr/bin/env python3
-"""
-Quick test script for 20 random songs
-Simple single-threaded approach
-"""
-
-import sys
-import json
-import time
-from pathlib import Path
-
-# Add the src directory to the path
-sys.path.insert(0, '/app')
-from src.cli.main import MusicBrainzCleaner
-
-def main():
-    print('🚀 Starting quick test with 20 random songs...')
-    
-    # Load songs
-    input_file = Path('data/songs.json')
-    if not input_file.exists():
-        print('❌ songs.json not found')
-        return
-    
-    with open(input_file, 'r') as f:
-        all_songs = json.load(f)
-    
-    print(f'📊 Total songs available: {len(all_songs):,}')
-    
-    # Take 20 random songs
-    import random
-    sample_songs = random.sample(all_songs, 20)
-    print(f'🎯 Testing 20 random songs...')
-    
-    # Initialize cleaner
-    cleaner = MusicBrainzCleaner()
-    
-    # Process songs
-    found_artists = 0
-    found_recordings = 0
-    failed_songs = []
-    
-    start_time = time.time()
-    
-    for i, song in enumerate(sample_songs, 1):
-        print(f'  [{i:2d}/20] Processing: "{song.get("artist", "Unknown")}" - "{song.get("title", "Unknown")}"')
-        
-        try:
-            result = cleaner.clean_song(song)
-            
-            artist_found = 'mbid' in result
-            recording_found = 'recording_mbid' in result
-            
-            if artist_found and recording_found:
-                found_artists += 1
-                found_recordings += 1
-                print(f'      ✅ Found both artist and recording')
-            else:
-                failed_songs.append({
-                    'original': song,
-                    'cleaned': result,
-                    'artist_found': artist_found,
-                    'recording_found': recording_found,
-                    'artist_name': song.get('artist', 'Unknown'),
-                    'title': song.get('title', 'Unknown')
-                })
-                print(f'      ❌ Artist: {artist_found}, Recording: {recording_found}')
-                
-        except Exception as e:
-            print(f'      💥 Error: {e}')
-            failed_songs.append({
-                'original': song,
-                'cleaned': {'error': str(e)},
-                'artist_found': False,
-                'recording_found': False,
-                'artist_name': song.get('artist', 'Unknown'),
-                'title': song.get('title', 'Unknown'),
-                'error': str(e)
-            })
-    
-    end_time = time.time()
-    processing_time = end_time - start_time
-    
-    # Calculate success rates
-    artist_success_rate = found_artists / 20 * 100
-    recording_success_rate = found_recordings / 20 * 100
-    failed_rate = len(failed_songs) / 20 * 100
-    
-    print(f'\n📊 Final Results:')
-    print(f'  ⏱️  Processing time: {processing_time:.2f} seconds')
-    print(f'  🚀 Speed: {20/processing_time:.1f} songs/second')
-    print(f'  ✅ Artists found: {found_artists}/20 ({artist_success_rate:.1f}%)')
-    print(f'  ✅ Recordings found: {found_recordings}/20 ({recording_success_rate:.1f}%)')
-    print(f'  ❌ Failed songs: {len(failed_songs)} ({failed_rate:.1f}%)')
-    
-    # Show failed songs
-    if failed_songs:
-        print(f'\n🔍 Failed songs:')
-        for i, failed in enumerate(failed_songs, 1):
-            print(f'  [{i}] "{failed["artist_name"]}" - "{failed["title"]}"')
-            print(f'      Artist found: {failed["artist_found"]}, Recording found: {failed["recording_found"]}')
-            if 'error' in failed:
-                print(f'      Error: {failed["error"]}')
-    else:
-        print('\n🎉 All songs processed successfully!')
-
-if __name__ == '__main__':
-    main()