_DIRECT_RUN = (__name__ == '__main__') import os import json import asyncio import requests import socket import subprocess import platform import threading import time import uuid import re import sqlite3 import types import collections import functools from contextlib import contextmanager from pathlib import Path from urllib.parse import urljoin, urlparse from concurrent.futures import ThreadPoolExecutor, as_completed from flask import Flask, abort, render_template, request, jsonify, redirect, send_file, send_from_directory, Response, session, g from flask_socketio import SocketIO, emit, join_room, leave_room from utils.logging_config import get_logger, setup_logging from utils.async_helpers import run_async from mutagen.flac import FLAC from mutagen.mp4 import MP4 from mutagen.oggvorbis import OggVorbis # --- Core Application Imports --- # Import the same core clients and config manager used by the GUI app from config.settings import config_manager # Setup logging early to avoid any import-time logs from being swallowed _log_level = config_manager.get('logging.level', 'INFO') _log_path = config_manager.get('logging.path', 'logs/app.log') _log_dir = Path(_log_path).parent logger = setup_logging(_log_level, _log_path) # App version — single source of truth for backup metadata, system-info, update check, etc. # Semver: MAJOR.MINOR.PATCH. Bump at each dev→main release. _SOULSYNC_BASE_VERSION = "2.5.3" def _build_version_string(): """Append short commit hash to version when available (e.g. 2.35+abc1234).""" sha = os.environ.get('SOULSYNC_COMMIT_SHA', '').strip() if not sha: try: import subprocess result = subprocess.run(['git', 'rev-parse', 'HEAD'], capture_output=True, text=True, cwd=os.path.dirname(__file__) or '.') if result.returncode == 0: sha = result.stdout.strip() except Exception as e: logger.debug("git rev-parse failed: %s", e) if sha: return f"{_SOULSYNC_BASE_VERSION}+{sha[:7]}" return _SOULSYNC_BASE_VERSION SOULSYNC_VERSION = _build_version_string() # Dedicated source reuse logger — writes alongside app.log in the configured log directory import logging as _logging import logging.handlers as _logging_handlers source_reuse_logger = _logging.getLogger("source_reuse") source_reuse_logger.setLevel(_logging.DEBUG) if not source_reuse_logger.handlers: _sr_handler = _logging_handlers.RotatingFileHandler( _log_dir / "source_reuse.log", encoding="utf-8", maxBytes=5*1024*1024, backupCount=2 ) _sr_handler.setFormatter(_logging.Formatter("%(asctime)s - %(message)s", datefmt="%Y-%m-%d %H:%M:%S")) source_reuse_logger.addHandler(_sr_handler) source_reuse_logger.propagate = False # Dedicated post-processing logger (failures only) — writes alongside app.log in the configured log directory pp_logger = _logging.getLogger("post_processing") pp_logger.setLevel(_logging.DEBUG) if not pp_logger.handlers: _pp_handler = _logging_handlers.RotatingFileHandler( _log_dir / "post_processing.log", encoding="utf-8", maxBytes=5*1024*1024, backupCount=2 ) _pp_handler.setFormatter(_logging.Formatter("%(asctime)s - %(message)s", datefmt="%Y-%m-%d %H:%M:%S")) pp_logger.addHandler(_pp_handler) pp_logger.propagate = False from core.spotify_client import SpotifyClient, Playlist as SpotifyPlaylist, Track as SpotifyTrack, _is_globally_rate_limited as _spotify_rate_limited from core.plex_client import PlexClient from plexapi.myplex import MyPlexAccount, MyPlexPinLogin from core.jellyfin_client import JellyfinClient from core.navidrome_client import NavidromeClient from core.soulseek_client import SoulseekClient from core.download_orchestrator import DownloadOrchestrator, set_download_orchestrator from core.tidal_client import TidalClient # Added import for Tidal from core.matching_engine import MusicMatchingEngine from core.database_update_worker import DatabaseUpdateWorker from core.web_scan_manager import WebScanManager from core.metadata.cache import get_metadata_cache from core.metadata import registry as metadata_registry from core.metadata import is_internal_image_host from core.metadata import normalize_image_url as fix_artist_image_url from core.webui import build_webui_vite_assets, should_serve_webui_spa from core.metadata.registry import ( clear_cached_metadata_client, get_metadata_source_label, get_spotify_client, get_spotify_disconnect_source, register_runtime_clients, ) from core.metadata.status import ( get_status_snapshot as get_metadata_status_snapshot, get_spotify_status, publish_spotify_status, invalidate_metadata_status_caches, ) from core.imports.context import ( get_import_clean_album, get_import_clean_title, get_import_context_album, get_import_original_search, ) from core.wishlist.payloads import ( build_cancelled_task_wishlist_payload as _build_cancelled_task_wishlist_payload, build_failed_track_wishlist_context as _build_failed_track_wishlist_context, ensure_wishlist_track_format as _ensure_wishlist_track_format, get_track_artist_name as _get_track_artist_name, ) from core.wishlist.routes import ( WishlistRouteRuntime as _WishlistRouteRuntime, add_album_track_to_wishlist as _wishlist_add_album_track_to_wishlist, clear_wishlist as _wishlist_clear_wishlist, get_wishlist_count as _wishlist_get_wishlist_count, get_wishlist_cycle as _wishlist_get_wishlist_cycle, get_wishlist_stats as _wishlist_get_wishlist_stats, get_wishlist_tracks as _wishlist_get_wishlist_tracks, process_wishlist_api as _wishlist_process_api, remove_album_from_wishlist as _wishlist_remove_album_from_wishlist, remove_batch_from_wishlist as _wishlist_remove_batch_from_wishlist, remove_track_from_wishlist as _wishlist_remove_track_from_wishlist, set_wishlist_cycle as _wishlist_set_wishlist_cycle, ) from core.wishlist.processing import ( add_cancelled_tracks_to_failed_tracks as _add_cancelled_tracks_to_failed_tracks, automatic_wishlist_cleanup_after_db_update as _cleanup_wishlist_after_db_update, cleanup_wishlist_against_library as _cleanup_wishlist_against_library, build_wishlist_source_context as _build_wishlist_source_context, finalize_auto_wishlist_completion as _finalize_auto_wishlist_completion, start_manual_wishlist_download_batch as _start_manual_wishlist_download_batch, process_wishlist_automatically as _process_wishlist_automatically_impl, recover_uncaptured_failed_tracks as _recover_uncaptured_failed_tracks, remove_completed_tracks_from_wishlist as _remove_completed_tracks_from_wishlist, WishlistAutoProcessingRuntime as _WishlistAutoProcessingRuntime, WishlistManualDownloadRuntime as _WishlistManualDownloadRuntime, ) from core.wishlist.resolution import ( check_and_remove_from_wishlist as _check_and_remove_from_wishlist, check_and_remove_track_from_wishlist_by_metadata as _check_and_remove_track_from_wishlist_by_metadata, ) from core.wishlist.state import ( is_wishlist_actually_processing as _is_wishlist_actually_processing, reset_flag_if_stuck as _reset_wishlist_flag_if_stuck, ) from core.imports.album_naming import resolve_album_group as _resolve_album_group from core.imports.album import build_album_import_match_payload from core.imports.filename import extract_track_number_from_filename, parse_filename_metadata from core.imports.staging import ( get_staging_path, read_staging_file_metadata, start_import_suggestions_cache, ) from core.imports.routes import ImportRouteRuntime as _ImportRouteRuntime from core.imports.routes import album_match as _import_album_match from core.imports.routes import album_process as _import_album_process from core.imports.routes import process_single_import_file as _import_process_single_import_file from core.imports.routes import search_albums as _import_search_albums from core.imports.routes import search_tracks as _import_search_tracks from core.imports.routes import singles_process as _import_singles_process from core.imports.routes import staging_files as _import_staging_files from core.imports.routes import staging_groups as _import_staging_groups from core.imports.routes import staging_hints as _import_staging_hints from core.imports.routes import staging_suggestions as _import_staging_suggestions from core.imports.paths import build_final_path_for_track as _build_final_path_for_track from core.imports.pipeline import build_import_pipeline_runtime as _build_import_pipeline_runtime from core.metadata.common import get_file_lock from core.metadata.enrichment import build_metadata_enrichment_runtime as _build_metadata_enrichment_runtime from core.metadata.source import ( mb_release_cache, mb_release_cache_lock, mb_release_detail_cache, mb_release_detail_cache_lock, normalize_album_cache_key, ) from core.runtime_state import ( activity_feed, activity_feed_lock, add_activity_item, download_batches, download_tasks, matched_context_lock, matched_downloads_context, mark_task_completed, processed_download_ids, set_activity_toast_emitter, tasks_lock, ) from core.metadata import enrichment as metadata_enrichment from database.music_database import get_database, MusicDatabase from services.sync_service import PlaylistSyncService # --- Docker Volume Mount Guard --- # Pre-v1.3 docker-compose files mounted soulsync_database:/app/database, which overlays # the Python package with stale volume contents. Detect this after import. if not hasattr(MusicDatabase, 'get_system_automation_by_action'): logger.error( "Stale database module detected!\n" "MusicDatabase is missing required methods. This usually means your docker-compose.yml has an outdated volume mount.\n" "Fix:\n" " OLD: soulsync_database:/app/database\n" " NEW: soulsync_database:/app/data\n" "Then run: docker compose down && docker compose up -d" ) from datetime import datetime, timezone import yt_dlp from beatport_unified_scraper import BeatportUnifiedScraper from core.musicbrainz_worker import MusicBrainzWorker from core.audiodb_worker import AudioDBWorker from core.discogs_worker import DiscogsWorker from core.deezer_worker import DeezerWorker from core.spotify_worker import SpotifyWorker from core.itunes_worker import iTunesWorker from core.lastfm_worker import LastFMWorker from core.genius_worker import GeniusWorker from core.tidal_worker import TidalWorker from core.qobuz_worker import QobuzWorker from core.hydrabase_worker import HydrabaseWorker from core.hydrabase_client import HydrabaseClient from core.automation_engine import AutomationEngine # --- Flask App Setup --- base_dir = os.path.abspath(os.path.dirname(__file__)) project_root = os.path.dirname(base_dir) # Go up one level to the project root DEV_STATIC_NO_CACHE = os.environ.get('SOULSYNC_WEB_DEV_NO_CACHE', '0').lower() in ('1', 'true', 'yes', 'on') # Check for environment variable first (Docker support), then fallback to calculated path env_config_path = os.environ.get('SOULSYNC_CONFIG_PATH') if env_config_path: config_path = env_config_path logger.info(f"Using config path from environment: {config_path}") else: config_path = os.path.join(project_root, 'config', 'config.json') if os.path.exists(config_path): # Check if we need to reload or if settings.py already handled it current_loaded_path = getattr(config_manager, 'config_path', None) target_path = Path(config_path).resolve() # Resolve current loaded path if it's a Path object if isinstance(current_loaded_path, Path): current_loaded_path = current_loaded_path.resolve() if current_loaded_path == target_path and config_manager.config_data: logger.info(f"Web server configuration already loaded from: {config_path}") else: logger.info(f"Found config file at: {config_path}") # Load configuration into the existing singleton instance if hasattr(config_manager, 'load_config'): config_manager.load_config(config_path) else: # Fallback for older settings.py in Docker volumes logger.warning("Legacy configuration detected: using fallback loading method") config_manager.config_path = Path(config_path) config_manager._load_config() logger.info("Web server configuration loaded successfully.") else: logger.warning(f"config.json not found at {config_path}. Using default settings.") # Correctly point to the 'webui' directory for templates and static files app = Flask( __name__, template_folder=os.path.join(base_dir, 'webui'), static_folder=os.path.join(base_dir, 'webui', 'static') ) app.config['TEMPLATES_AUTO_RELOAD'] = DEV_STATIC_NO_CACHE app.jinja_env.auto_reload = DEV_STATIC_NO_CACHE # Static assets (library.js / style.css / etc.) get aggressive browser # caching (1 year). Safe because every static URL is bust-tagged with # `?v=static_v` (computed once per process start — see below) so each # server restart effectively invalidates every cached asset for every # user. Within a single deploy, repeat page loads hit zero round-trips # on static files — was a 304 round-trip per asset under the old # max-age=0 setting. # # In dev, DEV_STATIC_NO_CACHE flips this back to 0 so iterating on JS # / CSS doesn't require a server restart between edits. app.config['SEND_FILE_MAX_AGE_DEFAULT'] = 0 if DEV_STATIC_NO_CACHE else 31536000 # Cache-bust query string for static assets. Computed once per process # start so each server restart invalidates the browser's cached copy of # every JS/CSS file. This is the surefire fix for "user has stale JS # even after Ctrl+Shift+R" — the URL itself changes, so the browser # cannot reuse a previously-cached response no matter what its # Cache-Control header said. import time as _cache_bust_time _STATIC_CACHE_BUST = str(int(_cache_bust_time.time())) @app.context_processor def _inject_static_cache_bust(): return {'static_v': _STATIC_CACHE_BUST} @app.context_processor def _inject_soulsync_version(): """Expose the version string to every Jinja template so the sidebar version button + version-modal subtitle don't have to be manually edited at every release. The base version is the source of truth at `_SOULSYNC_BASE_VERSION`; bumping that single constant updates the UI everywhere it's rendered.""" return {'soulsync_version': SOULSYNC_VERSION, 'soulsync_base_version': _SOULSYNC_BASE_VERSION} # --- Flask Session Setup (for multi-profile support) --- import secrets as _secrets def _init_flask_secret_key(): """Load or generate a persistent secret key for Flask sessions""" try: db = get_database() key = db.get_metadata('flask_secret_key') if not key: key = _secrets.token_hex(32) db.set_metadata('flask_secret_key', key) return key except Exception: return _secrets.token_hex(32) app.secret_key = _init_flask_secret_key() # --- WebSocket (Socket.IO) Setup --- from core.socketio_cors import ( resolve_cors_origins as _resolve_socketio_cors_origins, RejectionLogger as _SocketIORejectionLogger, log_startup_status as _log_socketio_startup_status, ) _socketio_cors_origins = _resolve_socketio_cors_origins(config_manager) socketio = SocketIO(app, async_mode='threading', cors_allowed_origins=_socketio_cors_origins) _log_socketio_startup_status(_socketio_cors_origins, logger) _socketio_rejection_logger = _SocketIORejectionLogger(logger) set_activity_toast_emitter(socketio.emit) # Plex PIN auth requests stored in memory for polling _plex_pin_requests = {} _plex_pin_requests_lock = threading.Lock() @app.before_request def _log_rejected_socketio_origin(): """Hook the WS upgrade path so users see a clear log line when their Origin is about to be rejected (engineio otherwise just silently 403s the upgrade). Dedup + threading lives in `core/socketio_cors`. Note: Flask's ``before_request`` runs on every HTTP request to every endpoint — there's no path-scoped equivalent for arbitrary URL prefixes. We early-return on non-/socket.io/ paths to keep the overhead to one string compare per request. """ if not request.path.startswith('/socket.io/'): return _socketio_rejection_logger.maybe_log( _socketio_cors_origins, request.headers.get('Origin'), request.headers.get('Host', ''), request.scheme, request.headers.get('X-Forwarded-Host', ''), request.headers.get('X-Forwarded-Proto', ''), ) @app.context_processor def inject_webui_assets(): return { 'vite_assets': build_webui_vite_assets, } # --- Profile Context (before_request hook) --- @app.before_request def _set_profile_context(): """Set g.profile_id from session for every request""" g.request_start_monotonic = time.perf_counter() # Skip for profile management, static, and root routes path = request.path if (path.startswith('/api/profiles') or path.startswith('/static/') or path == '/' or path.startswith('/api/v1/')): g.profile_id = session.get('profile_id', 1) return pid = session.get('profile_id', 1) # Validate session profile still exists (handles deleted profiles) if pid != 1 and 'profile_id' in session: try: database = get_database() profile = database.get_profile(pid) if not profile: session.pop('profile_id', None) from flask import jsonify as _jsonify return _jsonify({"error": "profile_required", "message": "Profile no longer exists"}), 401 except Exception as e: logger.debug("profile session validate: %s", e) g.profile_id = pid @app.after_request def _log_slow_request(response): """Log slow HTTP requests so we can identify UI stall sources.""" try: path = request.path if path.startswith('/socket.io/'): return response start = getattr(g, 'request_start_monotonic', None) if start is None: return response elapsed_ms = (time.perf_counter() - start) * 1000 slow_threshold_ms = 1000.0 if elapsed_ms >= slow_threshold_ms: logger.warning( "Slow request: %s %s -> %s in %.1fms", request.method, request.full_path.rstrip('?'), response.status_code, elapsed_ms, ) except Exception as e: logger.debug("slow request log failed: %s", e) return response @app.after_request def _add_discover_cache_headers(response): """Browser-cache discover GETs for 5 minutes. The discover surface (hero, similar artists, recent releases, release radar, deep cuts, etc.) returns semi-stable data that's expensive to compute and not user-action-driven within a session. A short browser cache eliminates redundant fetches when the user toggles between Discover sections or navigates back. Scope: only `/api/discover/` and `/api/discovery/` paths, only GET, only successful 2xx responses. Any endpoint that explicitly sets its own Cache-Control wins (we don't override). Uses `private` not `public` because discover data is user-specific (hero artists from your watchlist, similar artists from your taste, etc.). `private` keeps it browser-only — intermediate proxies (corporate caching proxies, Cloudflare with cache rules, Nginx proxy_cache) won't store one user's response and serve it to another. """ try: if request.method != 'GET': return response if not (request.path.startswith('/api/discover/') or request.path.startswith('/api/discovery/')): return response if not (200 <= response.status_code < 300): return response if response.headers.get('Cache-Control'): return response response.headers['Cache-Control'] = 'private, max-age=300' except Exception as exc: # Don't let a header-tagging bug turn a successful response into # a 500 — log and ship the response without the cache header. logger.warning(f"[discover-cache-headers] failed for {request.path}: {exc}") return response def get_current_profile_id() -> int: """Get the current profile ID from Flask g context or default to 1""" try: return g.profile_id except AttributeError: return 1 def admin_only(view_fn): """Restrict a Flask view to the admin profile (profile_id == 1). Settings-class endpoints expose / mutate service tokens, OAuth secrets, and API keys. Non-admin profiles must not see them. NOTE on the underlying auth model: `get_current_profile_id()` defaults to 1 (admin) when no session is present, which means single-admin / no-multi-profile installs have no actual gate here — any request from the local network is treated as admin. This decorator's job is to gate non-admin profiles in MULTI-profile setups, not to authenticate the network. The "trust local network" posture is the project's existing model; tightening it (real auth on every request) is out of scope for this decorator. """ @functools.wraps(view_fn) def wrapper(*args, **kwargs): if get_current_profile_id() != 1: return jsonify({ "success": False, "error": "Admin access required", }), 403 return view_fn(*args, **kwargs) return wrapper def get_spotify_client_for_profile(profile_id=None): """Get the Spotify client for the current profile. If the profile has custom Spotify credentials, returns a dedicated SpotifyClient instance (cached per profile). Otherwise returns the global spotify_client. """ if profile_id is None: profile_id = get_current_profile_id() return metadata_registry.get_spotify_client_for_profile(profile_id) # Valid page IDs for profile permission validation VALID_PAGE_IDS = { 'dashboard', 'sync', 'search', 'discover', 'playlist-explorer', 'watchlist', 'wishlist', 'automations', 'active-downloads', 'library', 'tools', 'artist-detail', 'stats', 'import', 'settings', 'help', 'hydrabase', 'issues', } def check_download_permission(): """Check if current profile has download permission. Returns error response or None if allowed.""" pid = get_current_profile_id() if pid == 1: return None # Root admin always allowed try: profile = get_database().get_profile(pid) if profile and not profile.get('can_download', True): return jsonify({'success': False, 'error': 'Downloads are disabled for this profile.'}), 403 except Exception as e: logger.debug("download permission check: %s", e) return None # --- Docker Helper Functions --- def docker_resolve_path(path_str): """ Resolve absolute paths for Docker container access In Docker, Windows drive paths (E:/) need to be mapped to WSL mount points (/mnt/e/) """ if os.path.exists('/.dockerenv') and len(path_str) >= 3 and path_str[1] == ':' and path_str[0].isalpha(): # Convert Windows path (E:/path) to WSL mount path (/mnt/e/path) drive_letter = path_str[0].lower() rest_of_path = path_str[2:].replace('\\', '/') # Remove E: and convert backslashes return f"/host/mnt/{drive_letter}{rest_of_path}" return path_str def extract_filename(full_path): """ Extract filename by working backwards from the end until we hit a separator. This is cross-platform compatible and handles both Windows and Unix path separators. Special handling for YouTube/Tidal: If the filename contains '||' (encoded format), treat it as a filename, not a path, to avoid splitting on '/' in titles. """ if not full_path: return "" # YouTube filenames are encoded as "video_id||title" and may contain '/' in the title # Don't split these on path separators if '||' in full_path: return full_path last_slash = max(full_path.rfind('/'), full_path.rfind('\\')) if last_slash != -1: return full_path[last_slash + 1:] else: return full_path def _make_context_key(username, filename): """Build a unique context key from username and full Soulseek path. Uses the full remote path (not just filename) to prevent collisions when different tracks from the same user share a filename (e.g., two albums both containing '01 - Intro.flac'). """ normalized = filename.replace('\\', '/').lstrip('/') if filename else '' return f"{username}::{normalized}" IS_SHUTTING_DOWN = False # --- Initialize Core Application Components --- # Each client is initialized independently so one failure doesn't take down everything. # Previously, a single exception set ALL clients to None, breaking the entire app. logger.info("Initializing SoulSync services for Web UI...") spotify_client = download_orchestrator = tidal_client = matching_engine = sync_service = web_scan_manager = media_server_engine = None try: spotify_client = get_spotify_client() logger.info(" Spotify client initialized via metadata registry") except Exception as e: logger.error(f" Spotify client failed to initialize: {e}") def _safe_init_media_client(factory, name): """Build a media-server client, capturing per-server init failures so one broken server doesn't take the engine down with it. Logs the exception class so the boot log distinguishes config errors (ConnectionError, AuthenticationError) from genuine import / dependency failures — the broad ``Exception`` catch is intentional (any failure on this code path means the user can't use that server, and we want the other three to keep working) but the log makes the cause diagnosable.""" try: instance = factory() logger.info(f" {name} client initialized") return instance except Exception as exc: logger.error( f" {name} client failed to initialize: {type(exc).__name__}: {exc}", exc_info=True, ) return None # Build the MediaServerEngine. The engine OWNS the per-server client # instances — no separate web_server.py globals (Cin's standard from # the download refactor: drop redundant access paths). All callers go # through media_server_engine.client(''). try: from core.media_server.engine import MediaServerEngine, set_media_server_engine from core.soulsync_client import SoulSyncClient media_server_engine = MediaServerEngine(clients={ 'plex': _safe_init_media_client(PlexClient, "Plex"), 'jellyfin': _safe_init_media_client(JellyfinClient, "Jellyfin"), 'navidrome': _safe_init_media_client(NavidromeClient, "Navidrome"), 'soulsync': _safe_init_media_client(SoulSyncClient, "SoulSync library"), }) # Install as process-wide singleton so callers reaching via # get_media_server_engine() see the same instance web_server.py # constructs at boot. Matches the metadata + download engine # patterns. set_media_server_engine(media_server_engine) logger.info(" Media server engine initialized") except Exception as e: logger.error(f" Media server engine failed to initialize: {e}", exc_info=True) # Fallback: empty engine so downstream `engine.client('plex')` # returns None instead of AttributeError'ing on a None engine # global. Pre-refactor each per-server client global had its own # try/except so engine failure didn't take down dispatch sites; # this preserves that resilience. If the fallback ALSO fails # (e.g. the import itself broke), media_server_engine stays as # the None initialized at the top of the module. try: from core.media_server.engine import MediaServerEngine, set_media_server_engine media_server_engine = MediaServerEngine(clients={}) set_media_server_engine(media_server_engine) except Exception as fallback_exc: logger.error(f" Empty-engine fallback also failed: {fallback_exc}", exc_info=True) try: download_orchestrator = DownloadOrchestrator() # Install as the process-wide singleton so callers reaching for # get_download_orchestrator() see the same instance web_server.py # constructs at boot. Matches Cin's metadata engine pattern. set_download_orchestrator(download_orchestrator) logger.info(" Download orchestrator initialized") except Exception as e: logger.error(f" Download orchestrator failed to initialize: {e}") try: tidal_client = TidalClient() logger.info(" Tidal client initialized") except Exception as e: logger.error(f" Tidal client failed to initialize: {e}") try: matching_engine = MusicMatchingEngine() logger.info(" Matching engine initialized") except Exception as e: logger.error(f" Matching engine failed to initialize: {e}") try: sync_service = PlaylistSyncService(spotify_client, download_orchestrator, media_server_engine=media_server_engine) logger.info(" Playlist sync service initialized") except Exception as e: logger.error(f" Playlist sync service failed to initialize: {e}") # Inject shutdown check callback into every download source that # accepts one. Generic dispatch via the registry — no per-source # attribute reaches needed. if download_orchestrator and hasattr(download_orchestrator, 'registry'): for _src_name, _src_client in download_orchestrator.registry.all_plugins(): if _src_client is not None and hasattr(_src_client, 'set_shutdown_check'): try: _src_client.set_shutdown_check(lambda: IS_SHUTTING_DOWN) logger.info(" Configured %s client shutdown callback", _src_name) except Exception as _exc: logger.warning(" %s set_shutdown_check failed: %s", _src_name, _exc) # Initialize web scan manager for automatic post-download scanning try: web_scan_manager = WebScanManager(media_server_engine, delay_seconds=60) logger.info(" Web scan manager initialized") except Exception as e: logger.error(f" Web scan manager failed to initialize: {e}") logger.info("Core service initialization complete.") # --- Shared Runtime State --- # These globals are used by routes, background workers, and shutdown helpers. # A prior refactor accidentally dropped this initializer block, so several # modules and handlers were still referencing names that never got created. # Global Streaming State Management stream_state = { "status": "stopped", # States: stopped, loading, queued, ready, error "progress": 0, "track_info": None, "file_path": None, # Path to the audio file in the Stream folder "error_message": None, } stream_lock = threading.Lock() # Prevent race conditions stream_background_task = None stream_executor = ThreadPoolExecutor(max_workers=1) # Only one stream at a time # Global OAuth State Management # Store PKCE values for Tidal OAuth flow tidal_oauth_state = { "code_verifier": None, "code_challenge": None, } tidal_oauth_lock = threading.Lock() # Sync Page Globals sync_executor = ThreadPoolExecutor(max_workers=3, thread_name_prefix="SyncWorker") active_sync_workers = {} # Key: playlist_id, Value: Future object sync_states = {} # Key: playlist_id, Value: dict with progress info sync_lock = threading.Lock() # Database Update / Tool Progress State db_update_executor = ThreadPoolExecutor(max_workers=1, thread_name_prefix="DBUpdate") db_update_worker = None db_update_state = { "status": "idle", # idle, running, finished, error "phase": "Idle", "progress": 0, "current_item": "", "processed": 0, "total": 0, "error_message": "", "removed_artists": 0, "removed_albums": 0, "removed_tracks": 0, } _db_update_automation_id = None # Set when automation triggers DB update, used by callbacks db_update_lock = threading.Lock() # Quality Scanner state quality_scanner_state = { "status": "idle", # idle, running, finished, error "phase": "Ready to scan", "progress": 0, "processed": 0, "total": 0, "quality_met": 0, "low_quality": 0, "matched": 0, "error_message": "", "results": [], # List of low quality tracks with match status } quality_scanner_lock = threading.Lock() quality_scanner_executor = ThreadPoolExecutor(max_workers=1, thread_name_prefix="QualityScanner") # Duplicate Cleaner state duplicate_cleaner_state = { "status": "idle", # idle, running, finished, error "phase": "Ready to scan", "progress": 0, "files_scanned": 0, "total_files": 0, "duplicates_found": 0, "deleted": 0, "space_freed": 0, # in bytes "error_message": "", } duplicate_cleaner_lock = threading.Lock() duplicate_cleaner_executor = ThreadPoolExecutor(max_workers=1, thread_name_prefix="DuplicateCleaner") # Retag Tool Globals retag_state = { "status": "idle", "phase": "Ready", "progress": 0, "current_track": "", "total_tracks": 0, "processed": 0, "error_message": "", } retag_lock = threading.Lock() retag_executor = ThreadPoolExecutor(max_workers=1, thread_name_prefix="RetagWorker") # Download Missing Tracks Modal State Management # Thread-safe state tracking for modal download functionality. # Shared task/batch state now lives in core.runtime_state. missing_download_executor = ThreadPoolExecutor(max_workers=3, thread_name_prefix="MissingTrackWorker") # Parallelizes the per-file metadata-lookup + post-processing in # /api/import/singles/process. Single-file work is dominated by # Spotify/iTunes/Deezer search round-trips so 3 workers give a near- # linear speedup on a typical user's network without saturating any # one provider's rate limit. Each file is independent (unique # context_key, separate disk path), and the downstream pipeline # already serializes DB access through its own SQLite locks. import_singles_executor = ThreadPoolExecutor(max_workers=3, thread_name_prefix="ImportSingleWorker") # Automatic Wishlist / Watchlist Processing Flags # Processing state flags (guards/recovery - timers are now managed by AutomationEngine) wishlist_auto_processing = False wishlist_auto_processing_timestamp = 0 wishlist_timer_lock = threading.Lock() watchlist_auto_scanning = False watchlist_auto_scanning_timestamp = 0 watchlist_timer_lock = threading.Lock() # Beatport Data Cache # Cache Beatport scraping data to reduce load times and avoid hammering Beatport.com beatport_data_cache = { 'homepage': { 'hero_tracks': {'data': None, 'timestamp': 0, 'ttl': 86400}, # 24 hours 'top_10_lists': {'data': None, 'timestamp': 0, 'ttl': 86400}, # 24 hours 'top_10_releases': {'data': None, 'timestamp': 0, 'ttl': 86400}, # 24 hours 'new_releases': {'data': None, 'timestamp': 0, 'ttl': 86400}, # 24 hours 'hype_picks': {'data': None, 'timestamp': 0, 'ttl': 86400}, # 24 hours 'featured_charts': {'data': None, 'timestamp': 0, 'ttl': 86400}, # 24 hours 'dj_charts': {'data': None, 'timestamp': 0, 'ttl': 86400}, # 24 hours }, 'genre': { # Future expansion for genre-specific caching # 'house': {'top_10': {...}, 'releases': {...}}, # 'techno': {'top_10': {...}, 'releases': {...}} }, 'cache_lock': threading.Lock(), } # Shared Soulseek transfer cache # Keeps download status polling from hammering the API when multiple modals are open. transfer_data_cache = { 'data': {}, 'last_update': 0, 'update_lock': threading.Lock(), 'cache_duration': 0.75, } # --- Restored Web UI Helper State --- session_completed_downloads = 0 session_stats_lock = threading.Lock() # `batch_locks` lives in core/runtime_state.py (re-exported here so the existing # call sites resolve without modification). All download globals share that home. from core.runtime_state import batch_locks _orphaned_download_keys = set() _enrichment_activity_log = {} _idle_since = {} _IDLE_GRACE_SECONDS = 5 _status_cache = { 'media_server': {'connected': False, 'response_time': 0, 'type': None}, 'soulseek': {'connected': False, 'response_time': 0}, } _status_cache_timestamps: dict[str, float] = { 'media_server': 0, 'soulseek': 0, } STATUS_CACHE_TTL = 120 dev_mode_enabled = False _hydrabase_ws = None _hydrabase_lock = threading.Lock() # --- Automation Engine --- try: automation_engine = AutomationEngine(get_database()) logger.info("Automation engine initialized.") except Exception as e: logger.error(f"Automation engine failed to initialize: {e}") automation_engine = None # --- Automation Progress Tracking --- _scan_library_automation_id = None def _register_automation_handlers(): """Register real SoulSync action handlers with the automation engine.""" if not automation_engine: return def _auto_process_wishlist(config): try: _process_wishlist_automatically(automation_id=config.get('_automation_id')) return {'status': 'completed'} except Exception as e: return {'status': 'error', 'error': str(e)} # Note: wishlist processing is async (batch submitted to executor), stats come via batch completion def _auto_scan_watchlist(config): try: pre_state_id = id(watchlist_scan_state) _process_watchlist_scan_automatically( automation_id=config.get('_automation_id'), profile_id=config.get('_profile_id') ) # Only report stats if a fresh scan actually ran (state dict was reassigned) if id(watchlist_scan_state) != pre_state_id: summary = watchlist_scan_state.get('summary', {}) return { 'status': 'completed', 'artists_scanned': summary.get('total_artists', 0), 'successful_scans': summary.get('successful_scans', 0), 'new_tracks_found': summary.get('new_tracks_found', 0), 'tracks_added_to_wishlist': summary.get('tracks_added_to_wishlist', 0), } return {'status': 'completed'} except Exception as e: return {'status': 'error', 'error': str(e)} def _auto_scan_library(config): global _scan_library_automation_id automation_id = config.get('_automation_id') if not web_scan_manager: return {'status': 'error', 'reason': 'Scan manager not available'} # If another automation is already tracking the scan, just forward the request if _scan_library_automation_id is not None: web_scan_manager.request_scan('Automation trigger (additional batch)') return {'status': 'skipped', 'reason': 'Scan already being tracked'} _scan_library_automation_id = automation_id try: result = web_scan_manager.request_scan('Automation trigger') scan_status_val = result.get('status', 'unknown') if scan_status_val == 'queued': _update_automation_progress(automation_id, log_line='Scan already in progress — waiting for completion', log_type='info') else: delay = result.get('delay_seconds', 60) _update_automation_progress(automation_id, log_line=f'Scan scheduled (debounce: {delay}s)', log_type='info') # Unified polling loop — handles debounce → scanning → idle transitions poll_start = time.time() scan_started = (scan_status_val == 'queued') # Already scanning if queued while time.time() - poll_start < 1800: # Max 30 min overall status = web_scan_manager.get_scan_status() st = status.get('status') if st == 'idle': break # Scan completed (or finished before we started polling) elif st == 'scheduled': elapsed = int(time.time() - poll_start) _update_automation_progress(automation_id, phase=f'Waiting for scan to start... ({elapsed}s)', progress=min(int(elapsed / 60 * 10), 14)) time.sleep(2) elif st == 'scanning': if not scan_started: scan_started = True _update_automation_progress(automation_id, progress=15, log_line='Scan triggered on media server', log_type='success') elapsed = status.get('elapsed_seconds', 0) max_time = status.get('max_time_seconds', 300) pct = min(15 + int(elapsed / max_time * 80), 95) mins, secs = divmod(elapsed, 60) _update_automation_progress(automation_id, phase=f'Library scan in progress... ({mins}m {secs}s)', progress=pct) time.sleep(5) else: time.sleep(2) # Unknown status, avoid tight loop else: # 30-min timeout reached _update_automation_progress(automation_id, status='error', phase='Timed out', log_line='Library scan timed out after 30 minutes', log_type='error') return {'status': 'error', 'reason': 'Timed out', '_manages_own_progress': True} elapsed = round(time.time() - poll_start, 1) _update_automation_progress(automation_id, status='finished', progress=100, phase='Complete', log_line='Library scan completed', log_type='success') return {'status': 'completed', '_manages_own_progress': True, 'scan_duration_seconds': elapsed} except Exception as e: _update_automation_progress(automation_id, status='error', phase='Error', log_line=str(e), log_type='error') return {'status': 'error', 'error': str(e), '_manages_own_progress': True} finally: _scan_library_automation_id = None # Self-guards only — prevent duplicate runs of the same operation, # but allow wishlist processing and watchlist scanning to run concurrently. # Downloads use bandwidth (Soulseek/Tidal/etc), scans use API calls — different resources. # The per-call rate limiter handles any API contention during post-processing. automation_engine.register_action_handler('process_wishlist', _auto_process_wishlist, guard_fn=lambda: is_wishlist_actually_processing()) automation_engine.register_action_handler('scan_watchlist', _auto_scan_watchlist, guard_fn=lambda: is_watchlist_actually_scanning()) automation_engine.register_action_handler('scan_library', _auto_scan_library, lambda: _scan_library_automation_id is not None) def _auto_refresh_mirrored(config): """Refresh mirrored playlist(s) from source.""" db = get_database() playlist_id = config.get('playlist_id') refresh_all = config.get('all', False) auto_id = config.get('_automation_id') if refresh_all: playlists = db.get_mirrored_playlists() elif playlist_id: p = db.get_mirrored_playlist(int(playlist_id)) playlists = [p] if p else [] else: return {'status': 'error', 'reason': 'No playlist specified'} # Filter out sources that can't be refreshed (no external API) playlists = [pl for pl in playlists if pl.get('source', '') not in ('file', 'beatport')] refreshed = 0 errors = [] for idx, pl in enumerate(playlists): try: source = pl.get('source', '') source_id = pl.get('source_playlist_id', '') _update_automation_progress(auto_id, progress=(idx / max(1, len(playlists))) * 100, phase=f'Refreshing: "{pl.get("name", "")}"', current_item=pl.get('name', '')) tracks = None if source == 'spotify': # Try authenticated API first, fall back to public embed scraper if spotify_client and spotify_client.is_spotify_authenticated(): playlist_obj = spotify_client.get_playlist_by_id(source_id) if playlist_obj and playlist_obj.tracks: tracks = [] for t in playlist_obj.tracks: artist_name = t.artists[0] if t.artists else '' track_dict = { 'track_name': t.name or '', 'artist_name': str(artist_name), 'album_name': t.album or '', 'duration_ms': t.duration_ms or 0, 'source_track_id': t.id or '', } # Spotify data IS official — auto-mark as discovered if t.id: _album_obj = {'name': t.album or ''} if getattr(t, 'image_url', None): _album_obj['images'] = [{'url': t.image_url, 'height': 600, 'width': 600}] track_dict['extra_data'] = json.dumps({ 'discovered': True, 'provider': 'spotify', 'confidence': 1.0, 'matched_data': { 'id': t.id, 'name': t.name or '', 'artists': [{'name': str(a)} for a in (t.artists or [])], 'album': _album_obj, 'duration_ms': t.duration_ms or 0, 'image_url': getattr(t, 'image_url', None), } }) tracks.append(track_dict) # Fallback: public embed scraper (no auth needed) if tracks is None: try: from core.spotify_public_scraper import scrape_spotify_embed embed_data = scrape_spotify_embed('playlist', source_id) if embed_data and not embed_data.get('error') and embed_data.get('tracks'): embed_album = embed_data.get('name', '') if embed_data.get('type') == 'album' else '' tracks = [] for t in embed_data['tracks']: artist_names = [a['name'] for a in t.get('artists', [])] artist_name = artist_names[0] if artist_names else '' track_dict = { 'track_name': t.get('name', ''), 'artist_name': artist_name, 'album_name': embed_album, 'duration_ms': t.get('duration_ms', 0), 'source_track_id': t.get('id', ''), } # Store Spotify track ID hint but don't mark discovered — # Discover step needs to run for proper album art if t.get('id'): track_dict['extra_data'] = json.dumps({ 'discovered': False, 'spotify_hint': { 'id': t['id'], 'name': t.get('name', ''), 'artists': t.get('artists', []), } }) tracks.append(track_dict) except Exception as e: logger.warning(f"Spotify public scraper fallback failed for {source_id}: {e}") elif source == 'spotify_public': # source_playlist_id is an MD5 hash; extract actual Spotify ID from stored description (URL) try: from core.spotify_public_scraper import parse_spotify_url, scrape_spotify_embed spotify_url = pl.get('description', '') parsed = parse_spotify_url(spotify_url) if spotify_url else None # If Spotify is authenticated, use the full API (auto-discovers with album art) if parsed and parsed.get('type') == 'playlist' and spotify_client and spotify_client.is_spotify_authenticated(): playlist_obj = spotify_client.get_playlist_by_id(parsed['id']) if playlist_obj and playlist_obj.tracks: tracks = [] for t in playlist_obj.tracks: artist_name = t.artists[0] if t.artists else '' track_dict = { 'track_name': t.name or '', 'artist_name': str(artist_name), 'album_name': t.album or '', 'duration_ms': t.duration_ms or 0, 'source_track_id': t.id or '', } if t.id: _album_obj = {'name': t.album or ''} if getattr(t, 'image_url', None): _album_obj['images'] = [{'url': t.image_url, 'height': 600, 'width': 600}] track_dict['extra_data'] = json.dumps({ 'discovered': True, 'provider': 'spotify', 'confidence': 1.0, 'matched_data': { 'id': t.id, 'name': t.name or '', 'artists': [{'name': str(a)} for a in (t.artists or [])], 'album': _album_obj, 'duration_ms': t.duration_ms or 0, 'image_url': getattr(t, 'image_url', None), } }) tracks.append(track_dict) # Fallback: public embed scraper (no auth or album-type URL) if tracks is None and parsed: embed_data = scrape_spotify_embed(parsed['type'], parsed['id']) if embed_data and not embed_data.get('error') and embed_data.get('tracks'): embed_album = embed_data.get('name', '') if embed_data.get('type') == 'album' else '' tracks = [] for t in embed_data['tracks']: artist_names = [a['name'] for a in t.get('artists', [])] artist_name = artist_names[0] if artist_names else '' tracks.append({ 'track_name': t.get('name', ''), 'artist_name': artist_name, 'album_name': embed_album, 'duration_ms': t.get('duration_ms', 0), 'source_track_id': t.get('id', ''), }) # No extra_data — let preservation code keep existing discovery data except Exception as e: logger.warning(f"Spotify public playlist refresh failed for {source_id}: {e}") elif source == 'deezer': try: deezer = _get_deezer_client() playlist_data = deezer.get_playlist(source_id) if playlist_data and playlist_data.get('tracks'): tracks = [] for t in playlist_data['tracks']: artist_name = t['artists'][0] if t.get('artists') else '' tracks.append({ 'track_name': t.get('name', ''), 'artist_name': str(artist_name), 'album_name': t.get('album', ''), 'duration_ms': t.get('duration_ms', 0), 'source_track_id': str(t.get('id', '')), }) except Exception as e: logger.warning(f"Deezer playlist refresh failed for {source_id}: {e}") elif source == 'tidal': if not tidal_client or not tidal_client.is_authenticated(): logger.warning(f"Tidal not authenticated — skipping refresh for '{pl.get('name', '')}'") _update_automation_progress(auto_id, log_line=f'Skipped "{pl.get("name", "")}" — Tidal not authenticated', log_type='skip') continue full_playlist = tidal_client.get_playlist(source_id) if full_playlist and full_playlist.tracks: tracks = [] for t in full_playlist.tracks: artist_name = t.artists[0] if t.artists else '' tracks.append({ 'track_name': t.name or '', 'artist_name': str(artist_name), 'album_name': t.album or '', 'duration_ms': t.duration_ms or 0, 'source_track_id': t.id or '', }) elif source == 'youtube': # source_playlist_id is now a deterministic hash; use stored description (original URL) for refresh yt_url = pl.get('description', '') or f"https://www.youtube.com/playlist?list={source_id}" playlist_data = parse_youtube_playlist(yt_url) if playlist_data and playlist_data.get('tracks'): tracks = [] for t in playlist_data['tracks']: artist_name = t['artists'][0] if t.get('artists') else '' tracks.append({ 'track_name': t.get('name', ''), 'artist_name': str(artist_name), 'album_name': '', 'duration_ms': t.get('duration_ms', 0), 'source_track_id': t.get('id', ''), }) if tracks is not None: # Compare old vs new track IDs to detect changes old_tracks = db.get_mirrored_playlist_tracks(pl['id']) if pl.get('id') else [] old_ids = {t.get('source_track_id') for t in old_tracks if t.get('source_track_id')} new_ids = {t.get('source_track_id') for t in tracks if t.get('source_track_id')} # Preserve existing discovery extra_data for tracks that still exist old_extra_map = db.get_mirrored_tracks_extra_data_map(pl['id']) if pl.get('id') else {} for t in tracks: sid = t.get('source_track_id', '') if sid and sid in old_extra_map and 'extra_data' not in t: t['extra_data'] = old_extra_map[sid] db.mirror_playlist( source=source, source_playlist_id=source_id, name=pl['name'], tracks=tracks, profile_id=pl.get('profile_id', 1), owner=pl.get('owner'), image_url=pl.get('image_url'), ) refreshed += 1 # Emit playlist_changed if tracks actually changed if old_ids != new_ids: added_count = len(new_ids - old_ids) removed_count = len(old_ids - new_ids) logger.info(f"[AUTOMATION] Playlist changed: '{pl.get('name', '')}' — {added_count} added, {removed_count} removed (old={len(old_ids)}, new={len(new_ids)})") _update_automation_progress(auto_id, log_line=f'"{pl.get("name", "")}" — {added_count} added, {removed_count} removed', log_type='success') try: if automation_engine: automation_engine.emit('playlist_changed', { 'playlist_name': pl.get('name', ''), 'playlist_id': str(pl.get('id', '')), 'old_count': str(len(old_ids)), 'new_count': str(len(new_ids)), 'added': str(added_count), 'removed': str(removed_count), }) except Exception as e: logger.debug("playlist_synced automation emit failed: %s", e) else: logger.warning(f"[AUTOMATION] No changes: '{pl.get('name', '')}' (tracks={len(old_ids)})") _update_automation_progress(auto_id, log_line=f'No changes: "{pl.get("name", "")}"', log_type='skip') except Exception as e: errors.append(f"{pl.get('name', '?')}: {str(e)}") _update_automation_progress(auto_id, log_line=f'Error: {pl.get("name", "?")} — {str(e)}', log_type='error') return {'status': 'completed', 'refreshed': str(refreshed), 'errors': str(len(errors))} def _auto_sync_playlist(config): """Sync a mirrored playlist to media server. Uses discovered metadata when available, skips undiscovered tracks. When triggered on a schedule, skips if nothing changed since last sync.""" auto_id = config.get('_automation_id') playlist_id = config.get('playlist_id') if not playlist_id: return {'status': 'error', 'reason': 'No playlist specified'} db = get_database() pl = db.get_mirrored_playlist(int(playlist_id)) if not pl: return {'status': 'error', 'reason': 'Playlist not found'} tracks = db.get_mirrored_playlist_tracks(int(playlist_id)) if not tracks: return {'status': 'error', 'reason': 'No tracks in playlist'} # Count currently discovered tracks for smart-skip check current_discovered = 0 for t in tracks: extra = {} if t.get('extra_data'): try: extra = json.loads(t['extra_data']) if isinstance(t['extra_data'], str) else t['extra_data'] except (json.JSONDecodeError, TypeError): pass if extra.get('discovered') and extra.get('matched_data'): current_discovered += 1 # Convert mirrored tracks to format expected by _run_sync_task # Use discovered metadata when available, skip undiscovered tracks tracks_json = [] skipped_count = 0 for t in tracks: # Parse extra_data for discovery info extra = {} if t.get('extra_data'): try: extra = json.loads(t['extra_data']) if isinstance(t['extra_data'], str) else t['extra_data'] except (json.JSONDecodeError, TypeError): pass if extra.get('discovered') and extra.get('matched_data'): # Use official discovered metadata md = extra['matched_data'] album_raw = md.get('album', '') album_obj = album_raw if isinstance(album_raw, dict) else {'name': album_raw or ''} _track_entry = { 'name': md.get('name', ''), 'artists': md.get('artists', [{'name': t.get('artist_name', '')}]), 'album': album_obj, 'duration_ms': md.get('duration_ms', 0), 'id': md.get('id', ''), } if md.get('track_number'): _track_entry['track_number'] = md['track_number'] if md.get('disc_number'): _track_entry['disc_number'] = md['disc_number'] tracks_json.append(_track_entry) else: # NOT discovered — try to include using available metadata so the # track can still be searched on Soulseek and added to wishlist. # Without this, failed discovery blocks the entire download pipeline. # # Priority: spotify_hint (has real Spotify ID from embed scraper) # > raw playlist fields (only if source_track_id is valid) hint = extra.get('spotify_hint', {}) # Build album object with cover art from the mirrored playlist track track_image = (t.get('image_url') or '').strip() album_obj = { 'name': (t.get('album_name') or '').strip(), 'images': [{'url': track_image, 'height': 300, 'width': 300}] if track_image else [], } if hint.get('id') and hint.get('name'): # spotify_hint has proper Spotify track ID + metadata from embed scraper hint_artists = hint.get('artists', []) if hint_artists and isinstance(hint_artists[0], str): hint_artists = [{'name': a} for a in hint_artists] elif hint_artists and isinstance(hint_artists[0], dict): pass # Already in correct format else: hint_artists = [{'name': t.get('artist_name', '')}] tracks_json.append({ 'name': hint['name'], 'artists': hint_artists, 'album': album_obj, 'duration_ms': t.get('duration_ms', 0), 'id': hint['id'], }) elif t.get('source_track_id') and (t.get('track_name') or '').strip(): # Has a valid source ID and track name — usable for wishlist tracks_json.append({ 'name': t['track_name'].strip(), 'artists': [{'name': (t.get('artist_name') or '').strip() or 'Unknown Artist'}], 'album': album_obj, 'duration_ms': t.get('duration_ms', 0), 'id': t['source_track_id'], }) else: skipped_count += 1 # No usable ID or name — truly can't process if not tracks_json: _update_automation_progress(auto_id, log_line=f'No discovered tracks — {skipped_count} need discovery first', log_type='skip') return { 'status': 'skipped', 'reason': f'No discovered tracks to sync ({skipped_count} tracks need discovery first)', 'skipped_tracks': str(skipped_count), } # Preflight: hash the track list and compare against last sync # Skip if the exact same set of tracks was already synced and all matched import hashlib track_ids_str = ','.join(sorted(t.get('id', '') for t in tracks_json)) tracks_hash = hashlib.md5(track_ids_str.encode()).hexdigest() sync_id_key = f"auto_mirror_{playlist_id}" try: sync_statuses = _load_sync_status_file() last_status = sync_statuses.get(sync_id_key, {}) last_hash = last_status.get('tracks_hash', '') last_matched = last_status.get('matched_tracks', -1) if (last_hash == tracks_hash and last_matched >= len(tracks_json)): # Exact same tracks, all matched last time — nothing to do _update_automation_progress(auto_id, log_line=f'All {len(tracks_json)} tracks unchanged since last sync — skipping', log_type='skip') return { 'status': 'skipped', 'reason': f'All {len(tracks_json)} tracks unchanged since last sync', } except Exception as e: logger.debug("mirror sync last-status read: %s", e) _update_automation_progress(auto_id, progress=50, phase=f'Syncing "{pl["name"]}"', log_line=f'{len(tracks_json)} discovered, {skipped_count} skipped', log_type='info') sync_id = f"auto_mirror_{playlist_id}" _update_automation_progress(auto_id, progress=90, log_line=f'Starting sync: {len(tracks_json)} tracks', log_type='success') threading.Thread( target=_run_sync_task, args=(sync_id, pl['name'], tracks_json, auto_id, 1, pl.get('image_url', '')), daemon=True, name=f'auto-sync-{playlist_id}' ).start() return { 'status': 'started', 'playlist_name': pl['name'], 'discovered_tracks': str(len(tracks_json)), 'skipped_tracks': str(skipped_count), '_manages_own_progress': True, } def _auto_discover_playlist(config): """Discover official Spotify/iTunes metadata for mirrored playlist tracks.""" db = get_database() playlist_id = config.get('playlist_id') discover_all = config.get('all', False) if discover_all: playlists = db.get_mirrored_playlists() elif playlist_id: p = db.get_mirrored_playlist(int(playlist_id)) playlists = [p] if p else [] else: return {'status': 'error', 'reason': 'No playlist specified'} if not playlists: return {'status': 'error', 'reason': 'No playlists found'} threading.Thread( target=_run_playlist_discovery_worker, args=(playlists, config.get('_automation_id')), daemon=True, name='auto-discover-playlist' ).start() names = ', '.join(p['name'] for p in playlists[:3]) return {'status': 'started', 'playlist_count': str(len(playlists)), 'playlists': names, '_manages_own_progress': True} # --- Playlist Pipeline: single automation for full lifecycle --- _pipeline_running = False def _pipeline_guard(): return _pipeline_running def _auto_playlist_pipeline(config): """Full playlist lifecycle: refresh → discover → sync → wishlist. Runs all 4 phases sequentially in one automation, reporting progress throughout.""" nonlocal _pipeline_running _pipeline_running = True automation_id = config.get('_automation_id') pipeline_start = time.time() try: db = get_database() playlist_id = config.get('playlist_id') process_all = config.get('all', False) skip_wishlist = config.get('skip_wishlist', False) # Resolve playlists if process_all: playlists = db.get_mirrored_playlists() elif playlist_id: p = db.get_mirrored_playlist(int(playlist_id)) playlists = [p] if p else [] else: _pipeline_running = False return {'status': 'error', 'error': 'No playlist specified'} playlists = [pl for pl in playlists if pl.get('source', '') not in ('file', 'beatport')] if not playlists: _pipeline_running = False return {'status': 'error', 'error': 'No refreshable playlists found'} pl_names = ', '.join(p.get('name', '?') for p in playlists[:3]) if len(playlists) > 3: pl_names += f' (+{len(playlists) - 3} more)' _update_automation_progress(automation_id, progress=2, phase=f'Pipeline: {len(playlists)} playlist(s)', log_line=f'Starting pipeline for: {pl_names}', log_type='info') # ── PHASE 1: REFRESH ────────────────────────────────────────── _update_automation_progress(automation_id, progress=3, phase='Phase 1/4: Refreshing playlists...', log_line='Phase 1: Refresh', log_type='info') refresh_config = dict(config) refresh_config['_automation_id'] = None # Don't let sub-handler hijack pipeline progress refresh_result = _auto_refresh_mirrored(refresh_config) refreshed = int(refresh_result.get('refreshed', 0)) refresh_errors = int(refresh_result.get('errors', 0)) _update_automation_progress(automation_id, progress=25, phase='Phase 1/4: Refresh complete', log_line=f'Phase 1 done: {refreshed} refreshed, {refresh_errors} errors', log_type='success' if refresh_errors == 0 else 'warning') # ── PHASE 2: DISCOVER ───────────────────────────────────────── _update_automation_progress(automation_id, progress=26, phase='Phase 2/4: Discovering metadata...', log_line='Phase 2: Discover', log_type='info') # Reload playlists (refresh may have updated them) if process_all: disc_playlists = db.get_mirrored_playlists() else: disc_playlists = [db.get_mirrored_playlist(int(playlist_id))] disc_playlists = [p for p in disc_playlists if p] # Run discovery in a thread and wait for it disc_done = threading.Event() disc_result = {'discovered': 0, 'failed': 0, 'skipped': 0, 'total': 0} def _disc_wrapper(pls): try: # The worker updates automation_progress internally, # but we pass None so it doesn't conflict with our pipeline progress _run_playlist_discovery_worker(pls, automation_id=None) except Exception as e: logger.error(f"[Pipeline] Discovery error: {e}") finally: disc_done.set() threading.Thread(target=_disc_wrapper, args=(disc_playlists,), daemon=True, name='pipeline-discover').start() # Poll for completion with progress updates poll_start = time.time() while not disc_done.wait(timeout=3): elapsed = int(time.time() - poll_start) _update_automation_progress(automation_id, progress=min(26 + elapsed // 4, 54), phase=f'Phase 2/4: Discovering... ({elapsed}s)') if elapsed > 3600: # 1hr safety timeout _update_automation_progress(automation_id, log_line='Discovery timed out after 1 hour', log_type='warning') break _update_automation_progress(automation_id, progress=55, phase='Phase 2/4: Discovery complete', log_line='Phase 2 done: discovery complete', log_type='success') # ── PHASE 3: SYNC ───────────────────────────────────────────── _update_automation_progress(automation_id, progress=56, phase='Phase 3/4: Syncing to server...', log_line='Phase 3: Sync', log_type='info') total_synced = 0 total_skipped = 0 sync_errors = 0 for pl_idx, pl in enumerate(playlists): pl_id = pl.get('id') if not pl_id: continue # Build sync config for this playlist (reuse existing sync handler) sync_config = { 'playlist_id': str(pl_id), '_automation_id': None, # Don't let sync handler hijack our progress } sync_result = _auto_sync_playlist(sync_config) sync_status = sync_result.get('status', '') if sync_status == 'started': # Sync launched a background thread — wait for it sync_id = f"auto_mirror_{pl_id}" sync_poll_start = time.time() while time.time() - sync_poll_start < 600: # 10 min per playlist max if sync_id in sync_states and sync_states[sync_id].get('status') in ('finished', 'complete', 'error', 'failed'): break time.sleep(2) elapsed = int(time.time() - sync_poll_start) sub_progress = 56 + ((pl_idx + 1) / max(1, len(playlists))) * 29 _update_automation_progress(automation_id, progress=min(int(sub_progress), 84), phase=f'Phase 3/4: Syncing "{pl.get("name", "")}" ({elapsed}s)') # Check result ss = sync_states.get(sync_id, {}) ss_result = ss.get('result', ss.get('progress', {})) matched = ss_result.get('matched_tracks', 0) if isinstance(ss_result, dict) else 0 total_synced += int(matched) if matched else 0 _update_automation_progress(automation_id, log_line=f'Synced "{pl.get("name", "")}": {matched} tracks matched', log_type='success') elif sync_status == 'skipped': total_skipped += 1 reason = sync_result.get('reason', 'unchanged') _update_automation_progress(automation_id, log_line=f'Skipped "{pl.get("name", "")}": {reason}', log_type='skip') elif sync_status == 'error': sync_errors += 1 _update_automation_progress(automation_id, log_line=f'Sync error "{pl.get("name", "")}": {sync_result.get("reason", "unknown")}', log_type='error') _update_automation_progress(automation_id, progress=85, phase='Phase 3/4: Sync complete', log_line=f'Phase 3 done: {total_synced} matched, {total_skipped} skipped, {sync_errors} errors', log_type='success' if sync_errors == 0 else 'warning') # ── PHASE 4: WISHLIST ───────────────────────────────────────── wishlist_queued = 0 if not skip_wishlist: _update_automation_progress(automation_id, progress=86, phase='Phase 4/4: Processing wishlist...', log_line='Phase 4: Wishlist', log_type='info') try: if not is_wishlist_actually_processing(): _process_wishlist_automatically(automation_id=None) _update_automation_progress(automation_id, log_line='Wishlist processing triggered', log_type='success') wishlist_queued = 1 else: _update_automation_progress(automation_id, log_line='Wishlist already running — skipped', log_type='skip') except Exception as e: _update_automation_progress(automation_id, log_line=f'Wishlist error: {e}', log_type='warning') else: _update_automation_progress(automation_id, progress=86, log_line='Phase 4: Wishlist skipped (disabled)', log_type='skip') # ── COMPLETE ────────────────────────────────────────────────── duration = int(time.time() - pipeline_start) _update_automation_progress(automation_id, status='finished', progress=100, phase='Pipeline complete', log_line=f'Pipeline finished in {duration // 60}m {duration % 60}s', log_type='success') _pipeline_running = False return { 'status': 'completed', '_manages_own_progress': True, 'playlists_refreshed': str(refreshed), 'tracks_discovered': 'completed', 'tracks_synced': str(total_synced), 'sync_skipped': str(total_skipped), 'wishlist_queued': str(wishlist_queued), 'duration_seconds': str(duration), } except Exception as e: _pipeline_running = False _update_automation_progress(automation_id, status='error', progress=100, phase='Pipeline error', log_line=f'Pipeline failed: {e}', log_type='error') return {'status': 'error', 'error': str(e), '_manages_own_progress': True} automation_engine.register_action_handler('refresh_mirrored', _auto_refresh_mirrored) automation_engine.register_action_handler('sync_playlist', _auto_sync_playlist) automation_engine.register_action_handler('discover_playlist', _auto_discover_playlist) automation_engine.register_action_handler('playlist_pipeline', _auto_playlist_pipeline, _pipeline_guard) # --- Phase 3 action handlers --- def _auto_start_database_update(config): global _db_update_automation_id automation_id = config.get('_automation_id') if db_update_state.get('status') == 'running': return {'status': 'skipped', 'reason': 'Database update already running'} _db_update_automation_id = automation_id full = config.get('full_refresh', False) active_server = config_manager.get_active_media_server() with db_update_lock: db_update_state.update({ "status": "running", "phase": "Initializing...", "progress": 0, "current_item": "", "processed": 0, "total": 0, "error_message": "" }) db_update_executor.submit(_run_db_update_task, full, active_server) # Monitor DB update progress (callbacks handle card updates, we just block until done) time.sleep(1) poll_start = time.time() last_progress_time = time.time() last_progress_val = 0 while time.time() - poll_start < 7200: # Max 2 hours time.sleep(3) with db_update_lock: status = db_update_state.get('status', 'idle') current_progress = db_update_state.get('progress', 0) if status != 'running': break # Track stall detection — if no progress change in 10 minutes, warn if current_progress != last_progress_val: last_progress_val = current_progress last_progress_time = time.time() elif time.time() - last_progress_time > 600: _update_automation_progress(automation_id, log_line='Database update appears stalled — waiting...', log_type='warning') last_progress_time = time.time() # Reset so warning repeats every 10 min else: # 2-hour timeout reached _update_automation_progress(automation_id, status='error', phase='Timed out', log_line='Database update timed out after 2 hours', log_type='error') return {'status': 'error', 'reason': 'Timed out', '_manages_own_progress': True} # Finished/error callback already updated the card — return matching status with db_update_lock: final_status = db_update_state.get('status', 'unknown') if final_status == 'error': return {'status': 'error', 'reason': db_update_state.get('error_message', 'Unknown error'), '_manages_own_progress': True} with db_update_lock: stats = { 'status': 'completed', 'full_refresh': str(full), '_manages_own_progress': True, 'artists': db_update_state.get('total', 0), 'albums': db_update_state.get('total_albums', 0), 'tracks': db_update_state.get('total_tracks', 0), 'removed_artists': db_update_state.get('removed_artists', 0), 'removed_albums': db_update_state.get('removed_albums', 0), 'removed_tracks': db_update_state.get('removed_tracks', 0), } return stats def _auto_deep_scan_library(config): global _db_update_automation_id automation_id = config.get('_automation_id') if db_update_state.get('status') == 'running': return {'status': 'skipped', 'reason': 'Database update already running'} _db_update_automation_id = automation_id active_server = config_manager.get_active_media_server() with db_update_lock: db_update_state.update({ "status": "running", "phase": "Deep scan: Initializing...", "progress": 0, "current_item": "", "processed": 0, "total": 0, "error_message": "" }) db_update_executor.submit(_run_deep_scan_task, active_server) # Monitor progress (callbacks handle card updates, we just block until done) time.sleep(1) poll_start = time.time() last_progress_time = time.time() last_progress_val = 0 while time.time() - poll_start < 7200: # Max 2 hours time.sleep(3) with db_update_lock: status = db_update_state.get('status', 'idle') current_progress = db_update_state.get('progress', 0) if status != 'running': break if current_progress != last_progress_val: last_progress_val = current_progress last_progress_time = time.time() elif time.time() - last_progress_time > 600: _update_automation_progress(automation_id, log_line='Deep scan appears stalled — waiting...', log_type='warning') last_progress_time = time.time() else: _update_automation_progress(automation_id, status='error', phase='Timed out', log_line='Deep scan timed out after 2 hours', log_type='error') return {'status': 'error', 'reason': 'Timed out', '_manages_own_progress': True} with db_update_lock: final_status = db_update_state.get('status', 'unknown') if final_status == 'error': return {'status': 'error', 'reason': db_update_state.get('error_message', 'Unknown error'), '_manages_own_progress': True} with db_update_lock: stats = { 'status': 'completed', '_manages_own_progress': True, 'artists': db_update_state.get('total', 0), 'albums': db_update_state.get('total_albums', 0), 'tracks': db_update_state.get('total_tracks', 0), 'removed_artists': db_update_state.get('removed_artists', 0), 'removed_albums': db_update_state.get('removed_albums', 0), 'removed_tracks': db_update_state.get('removed_tracks', 0), } return stats def _auto_run_duplicate_cleaner(config): automation_id = config.get('_automation_id') if duplicate_cleaner_state.get('status') == 'running': return {'status': 'skipped', 'reason': 'Duplicate cleaner already running'} # Pre-set status before submit so polling loop doesn't see stale 'finished' from last run with duplicate_cleaner_lock: duplicate_cleaner_state["status"] = "running" duplicate_cleaner_executor.submit(_run_duplicate_cleaner) _update_automation_progress(automation_id, log_line='Duplicate cleaner started', log_type='info') # Monitor duplicate cleaner progress (max 2 hours) time.sleep(1) # Brief pause for executor to start poll_start = time.time() while time.time() - poll_start < 7200: time.sleep(3) status = duplicate_cleaner_state.get('status', 'idle') if status not in ('running',): break phase = duplicate_cleaner_state.get('phase', 'Scanning...') progress = duplicate_cleaner_state.get('progress', 0) scanned = duplicate_cleaner_state.get('files_scanned', 0) total = duplicate_cleaner_state.get('total_files', 0) _update_automation_progress(automation_id, phase=phase, progress=progress, processed=scanned, total=total) else: # 2-hour timeout reached _update_automation_progress(automation_id, status='error', phase='Timed out', log_line='Duplicate cleaner timed out after 2 hours', log_type='error') return {'status': 'error', 'reason': 'Timed out', '_manages_own_progress': True} # Check actual exit status (could be 'finished' or 'error') final_status = duplicate_cleaner_state.get('status', 'idle') if final_status == 'error': err = duplicate_cleaner_state.get('error_message', 'Unknown error') _update_automation_progress(automation_id, status='error', progress=100, phase='Error', log_line=err, log_type='error') return {'status': 'error', 'reason': err, '_manages_own_progress': True} dupes = duplicate_cleaner_state.get('duplicates_found', 0) removed = duplicate_cleaner_state.get('deleted', 0) space_freed = duplicate_cleaner_state.get('space_freed', 0) scanned = duplicate_cleaner_state.get('files_scanned', 0) _update_automation_progress(automation_id, status='finished', progress=100, phase='Complete', log_line=f'Found {dupes} duplicates, removed {removed} files', log_type='success') return { 'status': 'completed', '_manages_own_progress': True, 'files_scanned': scanned, 'duplicates_found': dupes, 'files_deleted': removed, 'space_freed_mb': round(space_freed / (1024 * 1024), 1), } def _auto_clear_quarantine(config): import shutil as _shutil automation_id = config.get('_automation_id') quarantine_path = os.path.join(docker_resolve_path(config_manager.get('soulseek.download_path', './downloads')), 'ss_quarantine') if not os.path.exists(quarantine_path): _update_automation_progress(automation_id, log_line='No quarantine folder found', log_type='info') return {'status': 'completed', 'removed': '0'} removed = 0 for f in os.listdir(quarantine_path): fp = os.path.join(quarantine_path, f) try: if os.path.isfile(fp): os.remove(fp) removed += 1 elif os.path.isdir(fp): _shutil.rmtree(fp) removed += 1 except Exception as e: logger.debug("quarantine entry purge failed: %s", e) _update_automation_progress(automation_id, log_line=f'Removed {removed} quarantined items', log_type='success' if removed > 0 else 'info') return {'status': 'completed', 'removed': str(removed)} def _auto_cleanup_wishlist(config): automation_id = config.get('_automation_id') db = get_database() removed = db.remove_wishlist_duplicates(get_current_profile_id()) _update_automation_progress(automation_id, log_line=f'Removed {removed or 0} duplicate wishlist entries', log_type='success' if removed else 'info') return {'status': 'completed', 'removed': str(removed or 0)} def _auto_update_discovery_pool(config): automation_id = config.get('_automation_id') try: from core.watchlist_scanner import get_watchlist_scanner scanner = get_watchlist_scanner(spotify_client) _update_automation_progress(automation_id, log_line='Updating discovery pool...', log_type='info') scanner.update_discovery_pool_incremental(get_current_profile_id()) _update_automation_progress(automation_id, status='finished', progress=100, phase='Complete', log_line='Discovery pool updated', log_type='success') return {'status': 'completed', '_manages_own_progress': True} except Exception as e: _update_automation_progress(automation_id, status='error', phase='Error', log_line=str(e), log_type='error') return {'status': 'error', 'reason': str(e), '_manages_own_progress': True} def _auto_start_quality_scan(config): automation_id = config.get('_automation_id') if quality_scanner_state.get('status') == 'running': return {'status': 'skipped', 'reason': 'Quality scan already running'} scope = config.get('scope', 'watchlist') # Pre-set status before submit so polling loop doesn't see stale 'finished' from last run with quality_scanner_lock: quality_scanner_state["status"] = "running" quality_scanner_executor.submit(_run_quality_scanner, scope, get_current_profile_id()) _update_automation_progress(automation_id, log_line=f'Quality scan started (scope: {scope})', log_type='info') # Monitor quality scanner progress (max 2 hours) time.sleep(1) # Brief pause for executor to start poll_start = time.time() while time.time() - poll_start < 7200: time.sleep(3) status = quality_scanner_state.get('status', 'idle') if status not in ('running',): break phase = quality_scanner_state.get('phase', 'Scanning...') progress = quality_scanner_state.get('progress', 0) processed = quality_scanner_state.get('processed', 0) total = quality_scanner_state.get('total', 0) _update_automation_progress(automation_id, phase=phase, progress=progress, processed=processed, total=total) else: # 2-hour timeout reached _update_automation_progress(automation_id, status='error', phase='Timed out', log_line='Quality scan timed out after 2 hours', log_type='error') return {'status': 'error', 'reason': 'Timed out', '_manages_own_progress': True} # Check actual exit status (could be 'finished' or 'error') final_status = quality_scanner_state.get('status', 'idle') if final_status == 'error': err = quality_scanner_state.get('error_message', 'Unknown error') _update_automation_progress(automation_id, status='error', progress=100, phase='Error', log_line=err, log_type='error') return {'status': 'error', 'reason': err, '_manages_own_progress': True} issues = quality_scanner_state.get('low_quality', 0) _update_automation_progress(automation_id, status='finished', progress=100, phase='Complete', log_line=f'Quality scan complete — {issues} issues found', log_type='success') return { 'status': 'completed', 'scope': scope, '_manages_own_progress': True, 'tracks_scanned': quality_scanner_state.get('processed', 0), 'quality_met': quality_scanner_state.get('quality_met', 0), 'low_quality': issues, 'matched': quality_scanner_state.get('matched', 0), } def _auto_backup_database(config): import sqlite3, glob as _glob automation_id = config.get('_automation_id') db_path = os.environ.get('DATABASE_PATH', 'database/music_library.db') if not os.path.exists(db_path): return {'status': 'error', 'reason': 'Database file not found'} max_backups = 5 timestamp = datetime.now().strftime('%Y%m%d_%H%M%S') backup_path = f"{db_path}.backup_{timestamp}" # Use SQLite backup API for safe hot-copy of active database src = sqlite3.connect(db_path) dst = sqlite3.connect(backup_path) src.backup(dst) dst.close() src.close() size_mb = round(os.path.getsize(backup_path) / (1024 * 1024), 1) # Rolling cleanup — keep only the newest N backups existing = sorted(_glob.glob(f"{db_path}.backup_*"), key=os.path.getmtime) while len(existing) > max_backups: try: os.remove(existing.pop(0)) except Exception as e: logger.debug("rolling backup cleanup failed: %s", e) _update_automation_progress(automation_id, log_line=f'Backup created: {size_mb}MB ({os.path.basename(backup_path)})', log_type='success') return {'status': 'completed', 'backup_path': backup_path, 'size_mb': str(size_mb)} def _auto_refresh_beatport_cache(config): """Refresh Beatport homepage cache by calling each endpoint internally.""" automation_id = config.get('_automation_id') sections = [ ('hero_tracks', '/api/beatport/hero-tracks', 'Hero Tracks'), ('new_releases', '/api/beatport/new-releases', 'New Releases'), ('featured_charts', '/api/beatport/featured-charts', 'Featured Charts'), ('dj_charts', '/api/beatport/dj-charts', 'DJ Charts'), ('top_10_lists', '/api/beatport/homepage/top-10-lists', 'Top 10 Lists'), ('top_10_releases', '/api/beatport/homepage/top-10-releases-cards', 'Top 10 Releases'), ('hype_picks', '/api/beatport/hype-picks', 'Hype Picks'), ] # Invalidate all homepage cache timestamps so endpoints re-scrape with beatport_data_cache['cache_lock']: for key in beatport_data_cache['homepage']: beatport_data_cache['homepage'][key]['timestamp'] = 0 beatport_data_cache['homepage'][key]['data'] = None refreshed = 0 errors = [] with app.test_client() as client: for idx, (_, endpoint, label) in enumerate(sections): _update_automation_progress(automation_id, progress=(idx / len(sections)) * 100, phase=f'Scraping: {label}', current_item=label) try: resp = client.get(endpoint) if resp.status_code == 200: refreshed += 1 _update_automation_progress(automation_id, log_line=f'{label}: cached', log_type='success') else: errors.append(label) _update_automation_progress(automation_id, log_line=f'{label}: HTTP {resp.status_code}', log_type='error') except Exception as e: errors.append(label) _update_automation_progress(automation_id, log_line=f'{label}: {str(e)}', log_type='error') if idx < len(sections) - 1: time.sleep(2) _update_automation_progress(automation_id, status='finished', progress=100, phase='Complete', log_line=f'Refreshed {refreshed}/{len(sections)} sections', log_type='success') return {'status': 'completed', 'refreshed': str(refreshed), 'errors': str(len(errors)), '_manages_own_progress': True} def _auto_clean_search_history(config): """Remove old searches from Soulseek.""" automation_id = config.get('_automation_id') # Skip if soulseek is not the active download source or in hybrid order dl_mode = config_manager.get('download_source.mode', 'hybrid') hybrid_order = config_manager.get('download_source.hybrid_order', ['hifi', 'youtube', 'soulseek']) soulseek_active = (dl_mode == 'soulseek' or (dl_mode == 'hybrid' and 'soulseek' in hybrid_order)) # Reach the underlying SoulseekClient via the orchestrator's # generic accessor. slskd = download_orchestrator.client('soulseek') if download_orchestrator else None if not soulseek_active or not slskd or not slskd.base_url: _update_automation_progress(automation_id, log_line='Soulseek not active — skipped', log_type='skip') return {'status': 'skipped'} if not config_manager.get('soulseek.auto_clear_searches', True): _update_automation_progress(automation_id, log_line='Auto-clear disabled in settings', log_type='skip') return {'status': 'skipped'} try: success = run_async(download_orchestrator.maintain_search_history_with_buffer( keep_searches=50, trigger_threshold=200 )) if success: _update_automation_progress(automation_id, log_line='Search history maintenance completed', log_type='success') return {'status': 'completed'} else: _update_automation_progress(automation_id, log_line='No cleanup needed', log_type='skip') return {'status': 'completed'} except Exception as e: return {'status': 'error', 'error': str(e)} def _auto_clean_completed_downloads(config): """Clear completed downloads and empty directories.""" automation_id = config.get('_automation_id') try: has_active_batches = False has_post_processing = False with tasks_lock: for batch_data in download_batches.values(): if batch_data.get('phase') not in ['complete', 'error', 'cancelled', None]: has_active_batches = True break if not has_active_batches: for task_data in download_tasks.values(): if task_data.get('status') == 'post_processing': has_post_processing = True break if has_active_batches: _update_automation_progress(automation_id, log_line='Skipped — downloads active', log_type='skip') return {'status': 'completed'} run_async(download_orchestrator.clear_all_completed_downloads()) if not has_post_processing: _sweep_empty_download_directories() _update_automation_progress(automation_id, log_line='Download cleanup completed', log_type='success') return {'status': 'completed'} except Exception as e: return {'status': 'error', 'reason': str(e)} def _auto_full_cleanup(config): """Run all cleanup tasks: quarantine, download queue, empty dirs, staging, search history.""" import shutil as _shutil automation_id = config.get('_automation_id') steps = [] # --- 1. Clear quarantine --- _update_automation_progress(automation_id, phase='Clearing quarantine...', progress=0) quarantine_path = os.path.join(docker_resolve_path(config_manager.get('soulseek.download_path', './downloads')), 'ss_quarantine') q_removed = 0 if os.path.exists(quarantine_path): for f in os.listdir(quarantine_path): fp = os.path.join(quarantine_path, f) try: if os.path.isfile(fp): os.remove(fp) q_removed += 1 elif os.path.isdir(fp): _shutil.rmtree(fp) q_removed += 1 except Exception as e: logger.debug("quarantine entry purge failed: %s", e) steps.append(f'Quarantine: removed {q_removed} items') _update_automation_progress(automation_id, log_line=f'Quarantine: removed {q_removed} items', log_type='success' if q_removed else 'info') # --- 2. Clear completed/errored/cancelled downloads from Soulseek queue --- _update_automation_progress(automation_id, phase='Clearing download queue...', progress=20) has_active_batches = False has_post_processing = False with tasks_lock: for batch_data in download_batches.values(): if batch_data.get('phase') not in ['complete', 'error', 'cancelled', None]: has_active_batches = True break if not has_active_batches: for task_data in download_tasks.values(): if task_data.get('status') == 'post_processing': has_post_processing = True break if has_active_batches: steps.append('Download queue: skipped (active batches)') _update_automation_progress(automation_id, log_line='Download queue: skipped (active batches)', log_type='skip') else: try: run_async(download_orchestrator.clear_all_completed_downloads()) steps.append('Download queue: cleared') _update_automation_progress(automation_id, log_line='Download queue: cleared', log_type='success') except Exception as e: steps.append(f'Download queue: error ({e})') _update_automation_progress(automation_id, log_line=f'Download queue: error ({e})', log_type='error') # --- 3. Sweep empty download directories --- _update_automation_progress(automation_id, phase='Sweeping empty directories...', progress=40) if has_active_batches or has_post_processing: reason = 'active batches' if has_active_batches else 'post-processing active' steps.append(f'Empty directories: skipped ({reason})') _update_automation_progress(automation_id, log_line=f'Empty directories: skipped ({reason})', log_type='skip') else: dirs_removed = _sweep_empty_download_directories() steps.append(f'Empty directories: removed {dirs_removed}') _update_automation_progress(automation_id, log_line=f'Empty directories: removed {dirs_removed}', log_type='success' if dirs_removed else 'info') # --- 4. Sweep empty staging directories --- _update_automation_progress(automation_id, phase='Sweeping import folder...', progress=60) staging_path = get_staging_path() s_removed = 0 if os.path.isdir(staging_path): for dirpath, _dirnames, _filenames in os.walk(staging_path, topdown=False): if os.path.normpath(dirpath) == os.path.normpath(staging_path): continue try: entries = os.listdir(dirpath) except OSError: continue visible = [e for e in entries if not e.startswith('.')] if not visible: for hidden in entries: try: os.remove(os.path.join(dirpath, hidden)) except Exception as e: logger.debug("hidden file cleanup failed: %s", e) try: os.rmdir(dirpath) s_removed += 1 except OSError: pass steps.append(f'Staging: removed {s_removed} empty directories') _update_automation_progress(automation_id, log_line=f'Staging: removed {s_removed} empty directories', log_type='success' if s_removed else 'info') # --- 5. Clean search history (if enabled) --- _update_automation_progress(automation_id, phase='Cleaning search history...', progress=80) try: if not config_manager.get('soulseek.auto_clear_searches', True): steps.append('Search cleanup: disabled in settings') _update_automation_progress(automation_id, log_line='Search cleanup: disabled in settings', log_type='skip') else: run_async(download_orchestrator.maintain_search_history_with_buffer( keep_searches=50, trigger_threshold=200 )) steps.append('Search history: cleaned') _update_automation_progress(automation_id, log_line='Search history: cleaned', log_type='success') except Exception as e: steps.append(f'Search history: error ({e})') _update_automation_progress(automation_id, log_line=f'Search history: error ({e})', log_type='error') total_removed = q_removed + s_removed _update_automation_progress(automation_id, status='finished', progress=100, phase='Complete', log_line=f'Full cleanup complete — {total_removed} items removed', log_type='success') return { 'status': 'completed', 'quarantine_removed': str(q_removed), 'staging_removed': str(s_removed), 'total_removed': str(total_removed), 'steps': steps, '_manages_own_progress': True, } def _auto_run_script(config): """Execute a user script from the scripts directory.""" import subprocess as _sp script_name = config.get('script_name', '') timeout = min(int(config.get('timeout', 60)), 300) automation_id = config.get('_automation_id') if not script_name: return {'status': 'error', 'error': 'No script selected'} scripts_dir = docker_resolve_path(config_manager.get('scripts.path', './scripts')) if not scripts_dir or not os.path.isdir(scripts_dir): os.makedirs(scripts_dir, exist_ok=True) return {'status': 'error', 'error': 'Scripts directory is empty. Add scripts to the scripts/ folder.'} script_path = os.path.join(scripts_dir, script_name) script_path = os.path.realpath(script_path) # Security: block path traversal if not script_path.startswith(os.path.realpath(scripts_dir)): return {'status': 'error', 'error': 'Script path traversal blocked'} if not os.path.isfile(script_path): return {'status': 'error', 'error': f'Script not found: {script_name}'} _update_automation_progress(automation_id, phase=f'Running {script_name}...', progress=10) # Build environment with SoulSync context env = os.environ.copy() event_data = config.get('_event_data') or {} env['SOULSYNC_EVENT'] = str(event_data.get('type', '')) env['SOULSYNC_AUTOMATION'] = config.get('_automation_name', '') env['SOULSYNC_SCRIPTS_DIR'] = scripts_dir try: # Determine how to run the script if script_path.endswith('.py'): cmd = ['python', script_path] elif script_path.endswith('.sh'): cmd = ['bash', script_path] else: cmd = [script_path] result = _sp.run( cmd, capture_output=True, text=True, timeout=timeout, cwd=scripts_dir, env=env ) _update_automation_progress(automation_id, phase='Script completed', progress=100) stdout = result.stdout[:2000] if result.stdout else '' stderr = result.stderr[:1000] if result.stderr else '' if result.returncode == 0: logger.info(f"Script '{script_name}' completed (exit 0)") else: logger.warning(f"Script '{script_name}' exited with code {result.returncode}") return { 'status': 'completed' if result.returncode == 0 else 'error', 'exit_code': str(result.returncode), 'stdout': stdout, 'stderr': stderr, 'script': script_name, } except _sp.TimeoutExpired: _update_automation_progress(automation_id, phase='Script timed out', progress=100) return {'status': 'error', 'error': f'Script timed out after {timeout}s', 'script': script_name} except Exception as e: return {'status': 'error', 'error': str(e), 'script': script_name} automation_engine.register_action_handler('run_script', _auto_run_script) automation_engine.register_action_handler('full_cleanup', _auto_full_cleanup) automation_engine.register_action_handler('start_database_update', _auto_start_database_update, lambda: db_update_state.get('status') == 'running') automation_engine.register_action_handler('deep_scan_library', _auto_deep_scan_library, lambda: db_update_state.get('status') == 'running') automation_engine.register_action_handler('run_duplicate_cleaner', _auto_run_duplicate_cleaner, lambda: duplicate_cleaner_state.get('status') == 'running') automation_engine.register_action_handler('clear_quarantine', _auto_clear_quarantine) automation_engine.register_action_handler('cleanup_wishlist', _auto_cleanup_wishlist) automation_engine.register_action_handler('update_discovery_pool', _auto_update_discovery_pool) automation_engine.register_action_handler('start_quality_scan', _auto_start_quality_scan, lambda: quality_scanner_state.get('status') == 'running') automation_engine.register_action_handler('backup_database', _auto_backup_database) automation_engine.register_action_handler('refresh_beatport_cache', _auto_refresh_beatport_cache) automation_engine.register_action_handler('clean_search_history', _auto_clean_search_history) automation_engine.register_action_handler('clean_completed_downloads', _auto_clean_completed_downloads) def _auto_search_and_download(config): """Search for a track and download the best match.""" automation_id = config.get('_automation_id') query = config.get('query', '').strip() # Event-triggered: pull query from event data (e.g. webhook_received) if not query: event_data = config.get('_event_data', {}) query = (event_data.get('query', '') or '').strip() if not query: if automation_id: _update_automation_progress(automation_id, log_line='No search query provided', log_type='error') return {'status': 'error', 'error': 'No search query provided'} try: if automation_id: _update_automation_progress(automation_id, phase='Searching', log_line=f'Searching: {query}', log_type='info') result = run_async(download_orchestrator.search_and_download_best(query)) if result: if automation_id: _update_automation_progress(automation_id, log_line=f'Download started for: {query}', log_type='success') return {'status': 'completed', 'query': query, 'download_id': result} else: if automation_id: _update_automation_progress(automation_id, log_line=f'No match found for: {query}', log_type='warning') return {'status': 'not_found', 'query': query, 'error': 'No match found'} except Exception as e: if automation_id: _update_automation_progress(automation_id, log_line=f'Error: {e}', log_type='error') return {'status': 'error', 'query': query, 'error': str(e)} automation_engine.register_action_handler('search_and_download', _auto_search_and_download) # Register progress tracking callbacks def _progress_init(aid, name, action_type): _init_automation_progress(aid, name, action_type) def _progress_finish(aid, result): result_status = result.get('status', '') # Skip for handlers that manage their own progress lifecycle # (they call _update_automation_progress(status='finished') themselves) if result.get('_manages_own_progress'): return status = 'error' if result_status == 'error' else 'finished' msg = result.get('error', result.get('reason', result_status or 'done')) _update_automation_progress(aid, status=status, progress=100, phase='Error' if status == 'error' else 'Complete', log_line=msg, log_type='error' if status == 'error' else 'success') def _record_automation_history(aid, result): """Capture progress state into run history before cleanup clears it.""" _auto_progress.record_history(aid, result, get_database()) automation_engine.register_progress_callbacks(_progress_init, _progress_finish, _update_automation_progress, _record_automation_history) # Register permanent callback: when any scan completes, emit library_scan_completed event # This replaces the hardcoded scan_completion_callback → trigger_automatic_database_update chain if web_scan_manager: def _on_library_scan_completed(): if automation_engine: server_type = getattr(web_scan_manager, '_current_server_type', None) or 'unknown' automation_engine.emit('library_scan_completed', { 'server_type': server_type, }) web_scan_manager.add_scan_completion_callback(_on_library_scan_completed) logger.info("Automation action handlers registered") # --- Register Public REST API Blueprint (v1) --- try: from api import create_api_blueprint, limiter limiter.init_app(app) api_bp = create_api_blueprint() app.register_blueprint(api_bp, url_prefix='/api/v1') app.soulsync = { 'spotify_client': spotify_client, 'download_orchestrator': download_orchestrator, 'tidal_client': tidal_client, 'matching_engine': matching_engine, 'config_manager': config_manager, 'automation_engine': automation_engine, 'hydrabase_client': None, # updated after Hydrabase init 'hydrabase_worker': None, # updated after Hydrabase init } logger.info("Public REST API v1 registered at /api/v1") except Exception as e: logger.error(f"Public REST API v1 failed to register: {e}") # --- Automation Progress Tracking --- # State + helpers live in core/automation/progress.py. Re-exported here # so the existing call sites (registered as engine progress callbacks # and used inside _record_automation_history) keep resolving. from core.automation import progress as _auto_progress automation_progress_states = _auto_progress.progress_states automation_progress_lock = _auto_progress.progress_lock def _init_automation_progress(automation_id, automation_name, action_type): """Initialize progress state when an automation starts running.""" _auto_progress.init_progress(automation_id, automation_name, action_type) def _update_automation_progress(automation_id, **kwargs): """Update progress state from handler threads. Thread-safe.""" _auto_progress.update_progress(automation_id, socketio_emit=socketio.emit, **kwargs) # --- Global Matched Downloads Context Management --- # Shared with core.runtime_state so the refactored pipeline and web # server operate on the same context registry. # --- Download Missing Tracks Modal State Management --- # Thread-safe state tracking for modal download functionality with batch management def _get_max_concurrent(): """Get configured max concurrent downloads. Default 3.""" return config_manager.get('download_source.max_concurrent', 3) def _get_batch_max_concurrent(is_album=False, source=None): """Get max concurrent workers for a batch. Soulseek album downloads always use 1 (source reuse per user). Everything else uses the configured setting.""" if is_album and source in ('soulseek', None): # Check if active source is soulseek if source == 'soulseek': return 1 mode = config_manager.get('download_source.mode', 'soulseek') if mode == 'soulseek': return 1 return _get_max_concurrent() # --- Session Download Statistics --- # Track individual download completions (matches dashboard.py behavior) def _mark_task_completed(task_id, track_info=None): """ Mark a download task as completed and increment session counter. Centralizes completion logic to ensure consistent behavior. Assumes task_id exists in download_tasks (should be called within tasks_lock). """ global session_completed_downloads mark_task_completed(task_id, track_info) # Increment session counter (matches dashboard.py behavior) with session_stats_lock: session_completed_downloads += 1 # --- Automatic Wishlist Processing Infrastructure --- # Server-side timer system for automatic wishlist processing (replaces client-side JavaScript timers) # --- Automatic Wishlist/Watchlist Processing Flags --- # Processing state flags (guards/recovery — timers are now managed by AutomationEngine) # --- Shared Transfer Data Cache --- # Cache transfer data to avoid hammering the Soulseek API with multiple concurrent modals def get_cached_transfer_data(): """ Get transfer data with caching to reduce API calls when multiple modals are active. Returns a lookup dictionary for efficient transfer matching. """ current_time = time.time() with transfer_data_cache['update_lock']: # Check if cache is still valid if (current_time - transfer_data_cache['last_update']) < transfer_data_cache['cache_duration']: return transfer_data_cache['data'] # Cache expired or empty, fetch new data live_transfers_lookup = {} try: # Skip Soulseek API call if not active or known disconnected _dl_mode = config_manager.get('download_source.mode', 'hybrid') _hybrid_order = config_manager.get('download_source.hybrid_order', ['hifi', 'youtube', 'soulseek']) _slsk_active = (_dl_mode == 'soulseek' or (_dl_mode == 'hybrid' and 'soulseek' in _hybrid_order)) soulseek_known_down = not _slsk_active or not _status_cache.get('soulseek', {}).get('connected', True) # First, get Soulseek downloads from API transfers_data = None _slsk = download_orchestrator.client("soulseek") if download_orchestrator else None if not soulseek_known_down and _slsk and _slsk.base_url: transfers_data = run_async(download_orchestrator._make_request('GET', 'transfers/downloads')) if transfers_data: all_transfers = [] for user_data in transfers_data: username = user_data.get('username', 'Unknown') if 'directories' in user_data: for directory in user_data['directories']: if 'files' in directory: for file_info in directory['files']: file_info['username'] = username all_transfers.append(file_info) for transfer in all_transfers: key = _make_context_key(transfer.get('username'), transfer.get('filename', '')) live_transfers_lookup[key] = transfer # Also add non-Soulseek downloads. Soulseek is excluded # because slskd's transfers endpoint was already pulled # above — without the exclude both fetch paths run. # Every streaming source must appear here — task progress # for in-flight downloads comes from this lookup. Missing a # source = task.progress stays at 0 even when the # underlying client knows the real percent. try: all_downloads = [] if download_orchestrator and hasattr(download_orchestrator, 'engine'): try: all_downloads = run_async( download_orchestrator.engine.get_all_downloads(exclude=('soulseek',)) ) except Exception as e: logger.debug("get_all_downloads failed: %s", e) for download in all_downloads: key = _make_context_key(download.username, download.filename) # Convert DownloadStatus to transfer dict format live_transfers_lookup[key] = { 'id': download.id, 'filename': download.filename, 'username': download.username, 'state': download.state, 'percentComplete': download.progress, 'size': download.size, 'bytesTransferred': download.transferred, 'averageSpeed': download.speed, } except Exception as e: logger.error(f"Could not fetch streaming source downloads: {e}") # Update cache transfer_data_cache['data'] = live_transfers_lookup transfer_data_cache['last_update'] = current_time except Exception as e: logger.error(f"Could not fetch live transfers (cached): {e}") # Return empty dict on error, but don't update cache timestamp # This way we'll retry on the next request return {} return live_transfers_lookup # --- Beatport Data Cache --- # Cache Beatport scraping data to reduce load times and avoid hammering Beatport.com def get_cached_beatport_data(section_type, data_key, genre_slug=None): """ Get Beatport data from cache if valid, otherwise return None. Args: section_type: 'homepage' or 'genre' data_key: specific data type (e.g., 'hero_tracks', 'top_10_lists') genre_slug: only used for genre section_type Returns: Cached data if valid, None if cache miss or expired """ current_time = time.time() with beatport_data_cache['cache_lock']: try: if section_type == 'homepage': cache_entry = beatport_data_cache['homepage'].get(data_key) elif section_type == 'genre' and genre_slug: cache_entry = beatport_data_cache['genre'].get(genre_slug, {}).get(data_key) else: return None if not cache_entry: return None # Check if cache is still valid age = current_time - cache_entry['timestamp'] if age < cache_entry['ttl'] and cache_entry['data'] is not None: logger.debug(f"Cache HIT for {section_type}/{data_key} (age: {age:.1f}s)") return cache_entry['data'] else: logger.debug(f"⏰ Cache MISS for {section_type}/{data_key} (age: {age:.1f}s, ttl: {cache_entry['ttl']}s)") return None except Exception as e: logger.error(f"Cache lookup error for {section_type}/{data_key}: {e}") return None def set_cached_beatport_data(section_type, data_key, data, genre_slug=None): """ Store Beatport data in cache with current timestamp. Args: section_type: 'homepage' or 'genre' data_key: specific data type (e.g., 'hero_tracks', 'top_10_lists') data: the data to cache genre_slug: only used for genre section_type """ current_time = time.time() with beatport_data_cache['cache_lock']: try: if section_type == 'homepage': if data_key in beatport_data_cache['homepage']: beatport_data_cache['homepage'][data_key]['data'] = data beatport_data_cache['homepage'][data_key]['timestamp'] = current_time logger.info(f"Cached {section_type}/{data_key} (ttl: {beatport_data_cache['homepage'][data_key]['ttl']}s)") elif section_type == 'genre' and genre_slug: # Initialize genre cache if not exists if genre_slug not in beatport_data_cache['genre']: beatport_data_cache['genre'][genre_slug] = {} # For genre caching, we need to define TTL structure (for future use) if data_key not in beatport_data_cache['genre'][genre_slug]: beatport_data_cache['genre'][genre_slug][data_key] = { 'data': None, 'timestamp': 0, 'ttl': 600 # Default 10 minutes } beatport_data_cache['genre'][genre_slug][data_key]['data'] = data beatport_data_cache['genre'][genre_slug][data_key]['timestamp'] = current_time logger.info(f"Cached {section_type}/{genre_slug}/{data_key}") except Exception as e: logger.error(f"Cache storage error for {section_type}/{data_key}: {e}") def add_cache_headers(response, cache_duration=300): """ Add HTTP cache control headers to responses for browser-side caching. Args: response: Flask response object cache_duration: Cache duration in seconds (default: 5 minutes) """ response.headers['Cache-Control'] = f'public, max-age={cache_duration}' response.headers['Pragma'] = 'cache' return response # Enhanced-search cache + helpers live in core/search/cache.py. # Re-exported here so the existing call sites in this module still resolve. from core.search.cache import ( get_cache_key as _get_enhanced_search_cache_key_impl, get_cached_response as _get_cached_enhanced_search_response, set_cached_response as _set_cached_enhanced_search_response, ) from core.search.orchestrator import VALID_SOURCES as ENHANCED_SEARCH_VALID_SOURCES def _get_enhanced_search_cache_key(query, requested_source=None): """Thin wrapper that wires live config providers into the cache-key builder.""" return _get_enhanced_search_cache_key_impl( query, requested_source, active_server_provider=config_manager.get_active_media_server, fallback_source_provider=_get_metadata_fallback_source, hydrabase_active_provider=_is_hydrabase_active, ) # --- Background Download Monitoring (GUI Parity) --- from core.downloads.monitor import ( WebUIDownloadMonitor, init as _init_download_monitor, ) import core.downloads.monitor as _download_monitor_module # Global download monitor instance download_monitor = WebUIDownloadMonitor() def validate_and_heal_batch_states(): """ Periodic validation and healing of batch states to prevent permanent inconsistencies. This is the server-side equivalent of the frontend's worker count validation. """ try: if globals().get('IS_SHUTTING_DOWN', False): return import time current_time = time.time() # Collect work to do outside the lock batches_needing_workers = [] # batch_ids that need _start_next_batch_of_downloads batches_needing_completion_check = [] # batch_ids that need _check_batch_completion_v2 with tasks_lock: healed_batches = [] batches_to_cleanup = [] for batch_id, batch_data in list(download_batches.items()): active_count = batch_data.get('active_count', 0) queue = batch_data.get('queue', []) phase = batch_data.get('phase', 'unknown') # AUTO-CLEANUP: Remove completed batches after 5 minutes to prevent stale state if phase in ['complete', 'error', 'cancelled']: # Check if batch has a completion timestamp completion_time = batch_data.get('completion_time') if not completion_time: # Set completion time if not set batch_data['completion_time'] = current_time else: # Check if batch has been complete for >5 minutes time_since_completion = current_time - completion_time if time_since_completion > 300: # 5 minutes logger.warning(f"[Auto-Cleanup] Removing stale completed batch {batch_id} (completed {time_since_completion:.0f}s ago)") batches_to_cleanup.append(batch_id) continue # Skip other healing logic for this batch # Count actually active tasks actually_active = 0 orphaned_tasks = [] # Respect _on_download_completed dedup set — don't re-inflate active_count completed_task_ids = batch_data.get('_completed_task_ids', set()) for task_id in queue: if task_id in download_tasks: task_status = download_tasks[task_id]['status'] if task_status in ['searching', 'downloading', 'queued', 'post_processing']: if task_id not in completed_task_ids: actually_active += 1 elif task_status in ['failed', 'completed', 'cancelled', 'not_found']: orphaned_tasks.append(task_id) else: # Task in queue but not in download_tasks dict orphaned_tasks.append(task_id) # Check for inconsistencies if active_count != actually_active: logger.info(f"[Batch Healing] {batch_id}: fixing active count {active_count} → {actually_active}") batch_data['active_count'] = actually_active healed_batches.append(batch_id) # If we freed up slots, defer starting workers to outside the lock if actually_active < batch_data.get('max_concurrent', 3): queue_index = batch_data.get('queue_index', 0) if queue_index < len(queue): batches_needing_workers.append(batch_id) # Clean up orphaned tasks that are blocking progress if orphaned_tasks and phase == 'downloading': logger.warning(f"[Batch Healing] Found {len(orphaned_tasks)} orphaned tasks in active batch {batch_id}") batches_needing_completion_check.append(batch_id) # Cleanup stale batches inside the lock (safe - just dict mutations) for batch_id in batches_to_cleanup: task_ids_to_remove = download_batches[batch_id].get('queue', []) del download_batches[batch_id] # Clean up associated tasks for task_id in task_ids_to_remove: if task_id in download_tasks: del download_tasks[task_id] if batches_to_cleanup: logger.warning(f"[Auto-Cleanup] Removed {len(batches_to_cleanup)} stale completed batches") if healed_batches: logger.info(f"[Batch Healing] Healed {len(healed_batches)} batches: {healed_batches}") # ---- All work below runs WITHOUT tasks_lock held ---- # Start replacement workers for healed batches for batch_id in batches_needing_workers: try: logger.info(f"[Batch Healing] Starting replacement workers for {batch_id}") _start_next_batch_of_downloads(batch_id) except Exception as e: logger.error(f"[Batch Healing] Error starting workers for {batch_id}: {e}") # Trigger completion checks for batches with orphaned tasks for batch_id in batches_needing_completion_check: try: logger.warning("[Batch Healing] Triggering completion check for batch with orphaned tasks") _check_batch_completion_v2(batch_id) except Exception as e: logger.error(f"[Batch Healing] Error checking completion for {batch_id}: {e}") except Exception as healing_error: logger.error(f"[Batch Healing] Error during validation: {healing_error}") # Start periodic batch healing (every 30 seconds) import threading _batch_healing_timer = None _batch_healing_timer_lock = threading.Lock() def _schedule_batch_healing_timer(delay_seconds=30.0): """Schedule the next batch healing cycle.""" global _batch_healing_timer if globals().get('IS_SHUTTING_DOWN', False): return timer = threading.Timer(delay_seconds, start_batch_healing_timer) timer.daemon = True with _batch_healing_timer_lock: _batch_healing_timer = timer timer.start() def _cancel_batch_healing_timer(): """Cancel the current batch healing timer if one exists.""" global _batch_healing_timer with _batch_healing_timer_lock: timer = _batch_healing_timer _batch_healing_timer = None if timer: timer.cancel() def start_batch_healing_timer(): """Start periodic batch state validation and healing""" try: if globals().get('IS_SHUTTING_DOWN', False): return validate_and_heal_batch_states() except Exception as e: logger.error(f"[Batch Healing Timer] {e}") finally: # Schedule next healing cycle _schedule_batch_healing_timer(30.0) # Start the healing timer when the server starts start_batch_healing_timer() # Cleanup handler for Flask shutdown/reload import atexit import signal import sys def cleanup_monitor(): """Clean up background monitor on shutdown""" if download_monitor.monitoring: logger.info("Flask shutdown detected, stopping download monitor...") download_monitor.shutdown() # Give the thread a moment to exit cleanly time.sleep(0.5) # Clean up batch locks to prevent memory leaks try: acquired = tasks_lock.acquire(timeout=1.0) if acquired: try: batch_locks.clear() logger.info("Cleaned up batch locks") finally: tasks_lock.release() else: logger.warning("Skipped batch lock cleanup - tasks_lock busy") except Exception as e: logger.error(f"Error cleaning up batch locks: {e}") # Global shutdown flag def _shutdown_executor(executor, name): """Shut down a ThreadPoolExecutor without waiting for long-running tasks.""" if executor is None: return try: logger.info(f"Shutting down {name}...") executor.shutdown(wait=False, cancel_futures=True) except Exception as e: logger.error(f"Error shutting down {name}: {e}") def _stop_component(component, name, method_names=("stop", "shutdown")): """Call a best-effort stop method on a component if it has one.""" if component is None: return for method_name in method_names: method = getattr(component, method_name, None) if callable(method): try: logger.info(f"Stopping {name}...") method() except Exception as e: logger.error(f"Error stopping {name}: {e}") return def _stop_components_parallel(components): """Stop multiple components concurrently and wait for all stop calls to finish.""" stop_threads = [] for component, name in components: if component is None: continue thread = threading.Thread( target=_stop_component, args=(component, name), name=f"shutdown-{name.replace(' ', '-')}", ) thread.start() stop_threads.append((name, thread)) for _name, thread in stop_threads: thread.join() def _shutdown_runtime_components(): """Best-effort shutdown for timers, monitors, workers, and executors.""" global IS_SHUTTING_DOWN if IS_SHUTTING_DOWN: return IS_SHUTTING_DOWN = True _download_monitor_module.IS_SHUTTING_DOWN = True _cancel_batch_healing_timer() cleanup_monitor() _stop_component(web_scan_manager, "web scan manager") _stop_component(automation_engine, "automation engine") # Persist API call history before shutting down worker pools. try: from core.api_call_tracker import api_call_tracker api_call_tracker.save() logger.info("API call history saved") except Exception as e: logger.error(f"Error saving API call history: {e}") # Stop the active DB update worker before tearing down the executor it runs on. # This lets an in-flight update observe should_stop and exit cleanly. _stop_component(db_update_worker, "db update worker") _stop_component(metadata_update_runtime_worker, "metadata update worker") # Stop long-lived worker components in parallel so shutdown waits for the # slowest worker instead of serially burning the timeout for each one. _stop_components_parallel([ (mb_worker, "musicbrainz worker"), (audiodb_worker, "audiodb worker"), (discogs_worker, "discogs worker"), (deezer_worker, "deezer worker"), (spotify_enrichment_worker, "spotify enrichment worker"), (itunes_enrichment_worker, "itunes enrichment worker"), (lastfm_worker, "lastfm worker"), (genius_worker, "genius worker"), (tidal_enrichment_worker, "tidal enrichment worker"), (qobuz_enrichment_worker, "qobuz enrichment worker"), (hydrabase_worker, "hydrabase worker"), (soulid_worker, "soulid worker"), (listening_stats_worker, "listening stats worker"), (repair_worker, "repair worker"), ]) # Shut down executor pools so their worker threads stop keeping the process alive. for executor, name in [ (stream_executor, "stream executor"), (db_update_executor, "db update executor"), (quality_scanner_executor, "quality scanner executor"), (duplicate_cleaner_executor, "duplicate cleaner executor"), (retag_executor, "retag executor"), (sync_executor, "sync executor"), (missing_download_executor, "missing download executor"), (import_singles_executor, "import singles executor"), (tidal_discovery_executor, "tidal discovery executor"), (deezer_discovery_executor, "deezer discovery executor"), (spotify_public_discovery_executor, "spotify public discovery executor"), (youtube_discovery_executor, "youtube discovery executor"), (beatport_discovery_executor, "beatport discovery executor"), (listenbrainz_discovery_executor, "listenbrainz discovery executor"), (similar_artists_executor, "similar artists executor"), (metadata_update_executor, "metadata update executor"), ]: _shutdown_executor(executor, name) # Give daemon cleanup threads a moment to observe the shutdown flag. time.sleep(0.2) def signal_handler(signum, frame): """Handle SIGINT (Ctrl+C) and SIGTERM""" logger.info(f"Signal {signum} received, cleaning up...") _shutdown_runtime_components() sys.exit(0) # Register cleanup handlers def _atexit_save_history(): try: from core.api_call_tracker import api_call_tracker api_call_tracker.save() except Exception: # noqa: S110 — atexit handler, log handles may be closed pass def _atexit_shutdown(): try: _shutdown_runtime_components() except Exception: # noqa: S110 — atexit handler, log handles may be closed pass def _atexit_silence_shutdown_logger_errors(): # Pytest tears down log file handles before atexit fires, so every # "Shutting down ..." line a worker emits while stopping crashes # Python's logger with "I/O operation on closed file" and floods # CI stderr. The messages themselves are best-effort debug # breadcrumbs, not data we need to preserve at process exit. # Registered last so atexit's LIFO order makes this run FIRST, # ahead of cleanup_monitor / _atexit_shutdown / _atexit_save_history. import logging as _logging _logging.raiseExceptions = False atexit.register(_atexit_save_history) atexit.register(_atexit_shutdown) atexit.register(cleanup_monitor) # atexit runs in LIFO order — register the silencer LAST so it runs # FIRST, before any other shutdown handler emits its "Shutting down" # log line into a stream pytest already closed. atexit.register(_atexit_silence_shutdown_logger_errors) signal.signal(signal.SIGINT, signal_handler) signal.signal(signal.SIGTERM, signal_handler) def _update_task_status(task_id, new_status): """Helper to update task status and timestamp for timeout tracking""" with tasks_lock: if task_id in download_tasks: download_tasks[task_id]['status'] = new_status download_tasks[task_id]['status_change_time'] = time.time() # --- Album Grouping State Management (Ported from GUI) --- # Thread-safe album grouping for consistent naming across tracks album_cache_lock = threading.Lock() album_groups = {} # album_key -> final_album_name album_artists = {} # album_key -> artist_name album_editions = {} # album_key -> "standard" or "deluxe" album_name_cache = {} # album_key -> cached_final_name # Regexes to strip edition suffixes for cache key normalization. # Prevents Navidrome splitting albums when tracks get different MusicBrainz release IDs. import re as _re # Strip parenthetical/bracketed editions: "Album (Deluxe Edition)" → "Album" _EDITION_PAREN_RE = _re.compile( r'\s*[\(\[]' r'[^)\]]*' r'(?:deluxe|expanded|remaster(?:ed)?|anniversary|special|collector|' r'limited|bonus|platinum|gold|super\s*deluxe|standard|edition)' r'[^)\]]*' r'[\)\]]', _re.IGNORECASE ) # Strip trailing bare editions (no parens): "Album Deluxe Edition" → "Album" _EDITION_BARE_RE = _re.compile( r'\s+(?:-\s+)?(?:deluxe|expanded|remaster(?:ed)?|anniversary|special|collector|' r'limited|bonus|platinum|gold|super\s*deluxe|standard)' r'(?:\s+(?:edition|version))?\s*$', _re.IGNORECASE ) # Stream-prep worker logic lives in core/streaming/prepare.py. from core.streaming import prepare as _streaming_prepare def _build_prepare_stream_deps(): """Build the PrepareStreamDeps bundle from web_server.py globals on each call.""" def _get_stream_state(): return stream_state def _set_stream_state(value): global stream_state stream_state = value return _streaming_prepare.PrepareStreamDeps( config_manager=config_manager, download_orchestrator=download_orchestrator, stream_lock=stream_lock, project_root=os.path.dirname(os.path.abspath(__file__)), docker_resolve_path=docker_resolve_path, find_streaming_download_in_all_downloads=_find_streaming_download_in_all_downloads, find_downloaded_file=_find_downloaded_file, extract_filename=extract_filename, cleanup_empty_directories=_cleanup_empty_directories, _get_stream_state=_get_stream_state, _set_stream_state=_set_stream_state, ) def _prepare_stream_task(track_data): return _streaming_prepare.prepare_stream_task(track_data, _build_prepare_stream_deps()) def _find_streaming_download_in_all_downloads(all_downloads, track_data): """ Find streaming download in DownloadStatus list (works for Soulseek, YouTube, and Tidal). Replaces the old _find_streaming_download_in_transfers function. """ try: if not all_downloads: return None # Look for our specific file by filename and username target_filename = extract_filename(track_data.get('filename', '')) target_username = track_data.get('username', '') for download in all_downloads: download_filename = extract_filename(download.filename) download_username = download.username if (download_filename == target_filename and download_username == target_username): # Convert DownloadStatus to dict format expected by caller return { 'percentComplete': download.progress, 'state': download.state, 'size': download.size, 'bytesTransferred': download.transferred, 'averageSpeed': download.speed, } return None except Exception as e: logger.error(f"Error finding streaming download: {e}") return None def _find_downloaded_file(download_path, track_data): """Find the downloaded audio file in the downloads directory tree (works for Soulseek, YouTube, and Tidal)""" # Ensure path is accessible in Docker (handles E:/ -> /host/mnt/e/) download_path = docker_resolve_path(download_path) audio_extensions = {'.mp3', '.flac', '.ogg', '.aac', '.wma', '.wav', '.m4a'} target_filename = extract_filename(track_data.get('filename', '')) # YOUTUBE/TIDAL/QOBUZ/HIFI SUPPORT: Handle encoded filename format "id||title" # The file on disk will be "title.ext", not "id||title" is_youtube = track_data.get('username') == 'youtube' is_tidal = track_data.get('username') == 'tidal' is_qobuz = track_data.get('username') == 'qobuz' is_hifi = track_data.get('username') == 'hifi' is_streaming_source = is_youtube or is_tidal or is_qobuz or is_hifi target_filename_youtube = None if is_streaming_source and '||' in target_filename: _, title = target_filename.split('||', 1) if is_tidal or is_qobuz or is_hifi: # Tidal/Qobuz/HiFi files can be flac or m4a — match any audio extension safe_title = re.sub(r'[<>:"/\\|?*]', '_', title) target_filename_youtube = safe_title # Extension-less for flexible matching source_name = 'HiFi' if is_hifi else ('Qobuz' if is_qobuz else 'Tidal') logger.debug(f"[{source_name} Stream] Looking for file starting with: {target_filename_youtube}") else: # yt-dlp will create "Title.mp3" from "Title" target_filename_youtube = f"{title}.mp3" logger.debug(f"[YouTube Stream] Looking for file: {target_filename_youtube}") elif is_streaming_source: # Fallback: if streaming source but no encoded format, use as-is target_filename_youtube = target_filename logger.debug(f"[Stream] Using direct filename: {target_filename_youtube}") try: # Walk through the downloads directory to find the file best_match = None best_similarity = 0.0 for root, _dirs, files in os.walk(download_path): for file in files: # Skip non-audio files if os.path.splitext(file)[1].lower() not in audio_extensions: continue file_path = os.path.join(root, file) # Skip empty files try: if os.path.getsize(file_path) < 1024: # At least 1KB continue except: continue # Check if this is our target file if is_streaming_source and target_filename_youtube: # For YouTube/Tidal, use fuzzy matching (case-insensitive, flexible) from difflib import SequenceMatcher # For Tidal, compare without extension (file could be .flac or .m4a) compare_target = target_filename_youtube.lower() compare_file = file.lower() if is_tidal or is_qobuz or is_hifi: compare_file = os.path.splitext(compare_file)[0] similarity = SequenceMatcher(None, compare_file, compare_target).ratio() source_label = 'HiFi' if is_hifi else ('Qobuz' if is_qobuz else ('Tidal' if is_tidal else 'YouTube')) logger.debug(f"[{source_label} Stream] Comparing: '{file}' vs '{target_filename_youtube}' = {similarity:.2f}") # Keep track of best match if similarity > best_similarity: best_similarity = similarity best_match = file_path # If we have a very good match (95%+), use it immediately if similarity >= 0.95: logger.debug(f"Found excellent match for streaming file: {file_path}") return file_path else: # For Soulseek, exact match if file == target_filename: logger.debug(f"Found streaming file: {file_path}") return file_path # For YouTube/Tidal, if we found a good enough match (80%+), use it if is_streaming_source and best_match and best_similarity >= 0.80: source_label = 'Qobuz' if is_qobuz else ('Tidal' if is_tidal else 'YouTube') logger.debug(f"Found good match ({best_similarity:.2f}) for {source_label} streaming file: {best_match}") return best_match logger.error(f"Could not find downloaded file: {target_filename}") if is_streaming_source: logger.debug(f" Looking for: {target_filename_youtube}") logger.debug(f" Best similarity: {best_similarity:.2f}") return None except Exception as e: logger.error(f"Error searching for downloaded file: {e}") return None # --- Refactored Logic from GUI Threads --- # This logic is extracted from the database update worker to be used directly by Flask. # ── Settings Connection Status Registry ── # Maps each service shown in Settings → Connections to its config requirements. # Used by _is_service_configured() to drive the green/yellow header gradient. # # Registry entry shapes: # {'required': [keys]} — green if all keys populated in config_manager.get(service) # {'always': True} — always green (no credentials required, e.g. default-storefront iTunes) # {'custom': callable} — callable(service_name) -> bool, for services with non-field checks (e.g. token file) # {'any_of': [[keys_a], [keys_b]]} — green if any one group's keys are all populated (e.g. Qobuz: email+password OR token) SERVICE_CONFIG_REGISTRY = { 'spotify': {'required': ['client_id', 'client_secret']}, 'itunes': {'always': True}, # default storefront works anon 'deezer': {'always': True}, # anon search works, premium ARL is optional 'discogs': {'required': ['token']}, 'tidal': {'custom': lambda _svc: _tidal_has_auth_token()}, 'qobuz': {'any_of': [['email', 'password'], ['token'], ['user_auth_token']]}, 'lastfm': {'required': ['api_key']}, 'genius': {'required': ['access_token']}, 'acoustid': {'required': ['api_key']}, 'listenbrainz': {'required': ['token']}, 'hydrabase': {'required': ['url', 'api_key']}, # Soulseek (slskd) needs a base URL. Used by the search source picker # to dim Soulseek and redirect to Settings when the user has no slskd # configured — clicking it would otherwise fire searches that always # fail. URL field lives on Settings → Downloads, gated behind the # download-source-mode dropdown. 'soulseek': {'required': ['slskd_url']}, } def _tidal_has_auth_token() -> bool: """Check if Tidal has a cached OAuth token. Tidal uses a token file, not config fields.""" try: return bool(tidal_client and tidal_client.is_authenticated()) except Exception: return False def _is_service_configured(service: str) -> bool: """Return True if the user has provided the required credentials for this service. Drives the green/yellow header gradient on the Connections tab. """ entry = SERVICE_CONFIG_REGISTRY.get(service) if not entry: return False if entry.get('always'): return True if 'custom' in entry: try: return bool(entry['custom'](service)) except Exception: return False service_config = config_manager.get(service, {}) or {} if 'required' in entry: return all(bool(service_config.get(key)) for key in entry['required']) if 'any_of' in entry: for key_group in entry['any_of']: if all(bool(service_config.get(key)) for key in key_group): return True return False return False from core.connection_test import ( run_service_test, init as _init_connection_test, ) from core.connection_detect import run_detection # --- Web UI Routes --- @app.route('/') def index(): return render_template('index.html') @app.route('/sw.js') def service_worker(): """Serve sw.js from root scope so the service worker can intercept fetches site-wide. A service worker only controls URLs at or below its own served path — `/static/sw.js` would scope to `/static/*` only. Serving from `/sw.js` (with the file living under static/) grants full-site scope without needing the Service-Worker-Allowed header dance. Cache-Control: no-cache so deploys that change the SW propagate on the next page load instead of being pinned by the 1-year static cache the rest of /static/ uses. """ response = send_from_directory(app.static_folder, 'sw.js', mimetype='application/javascript') response.headers['Cache-Control'] = 'no-cache' return response @app.route('/') def spa_catch_all(page): # Serve index.html for client-side routes; let Flask handle real routes first. if not should_serve_webui_spa(f'/{page}'): abort(404) return index() # --- API Endpoints --- # Tracks cumulative item-processed totals over time for windowed counting. # Each entry: (timestamp, cumulative_total). Polled every ~5s, 24h = ~17280 entries. def _get_windowed_calls(key, current_total): """Record current cumulative total and return (calls_1h, calls_24h). Deque stores (timestamp, cumulative_total) in chronological order. To get calls in a window: current_total minus the oldest total within that window.""" now = time.time() history = _enrichment_activity_log.setdefault(key, collections.deque(maxlen=17300)) history.append((now, current_total)) cutoff_1h = now - 3600 cutoff_24h = now - 86400 # Forward scan: first entry with ts >= cutoff is the oldest in that window oldest_1h_total = current_total oldest_24h_total = current_total found_24h = False for ts, total in history: if not found_24h and ts >= cutoff_24h: oldest_24h_total = total found_24h = True if ts >= cutoff_1h: oldest_1h_total = total break return max(0, current_total - oldest_1h_total), max(0, current_total - oldest_24h_total) def _get_enrichment_status(): """Get lightweight status for all enrichment services (no DB queries). Reads worker properties directly to avoid expensive get_stats() calls.""" services = {} # Worker-based enrichment services: (key, display_name, worker_var) workers_info = [ ('musicbrainz', 'MusicBrainz', lambda: mb_worker), ('spotify_enrichment', 'Spotify', lambda: spotify_enrichment_worker), ('itunes_enrichment', 'iTunes', lambda: itunes_enrichment_worker), ('deezer_enrichment', 'Deezer', lambda: deezer_worker), ('tidal_enrichment', 'Tidal', lambda: tidal_enrichment_worker), ('qobuz_enrichment', 'Qobuz', lambda: qobuz_enrichment_worker), ('lastfm', 'Last.fm', lambda: lastfm_worker), ('genius', 'Genius', lambda: genius_worker), ('audiodb', 'AudioDB', lambda: audiodb_worker), ('discogs', 'Discogs', lambda: discogs_worker), ] # Config-based "configured" checks for services that need API keys/credentials configured_checks = { 'spotify_enrichment': lambda: bool(config_manager.get('spotify.client_id') and config_manager.get('spotify.client_secret')), 'tidal_enrichment': lambda: bool(tidal_client and getattr(tidal_client, 'access_token', None)), 'qobuz_enrichment': lambda: bool(qobuz_enrichment_worker and qobuz_enrichment_worker.client and qobuz_enrichment_worker.client.user_auth_token), 'lastfm': lambda: bool(config_manager.get('lastfm.api_key', '')), 'genius': lambda: bool(config_manager.get('genius.access_token', '')), } for key, name, get_worker in workers_info: worker = get_worker() if worker is not None: is_alive = worker.thread is not None and worker.thread.is_alive() try: configured = configured_checks.get(key, lambda: True)() except Exception: configured = False # Compute windowed API call counts from cumulative stats stats = worker.stats total_processed = stats.get('matched', 0) + stats.get('not_found', 0) + stats.get('errors', 0) calls_1h, calls_24h = _get_windowed_calls(key, total_processed) # Debounced idle detection — only report idle after 5s of no current_item has_item = getattr(worker, 'current_item', None) is not None if has_item: _idle_since.pop(key, None) is_idle = False else: if key not in _idle_since: _idle_since[key] = time.time() is_idle = (time.time() - _idle_since[key]) >= _IDLE_GRACE_SECONDS svc_data = { 'name': name, 'configured': configured, 'running': worker.running and is_alive and not worker.paused, 'paused': worker.paused, 'idle': is_alive and not worker.paused and is_idle, 'calls_1h': calls_1h, 'calls_24h': calls_24h, } # Spotify-specific: include daily budget info if key == 'spotify_enrichment': try: svc_data['daily_budget'] = worker._get_daily_budget_info() except Exception as e: logger.debug("spotify daily budget read failed: %s", e) services[key] = svc_data else: services[key] = { 'name': name, 'configured': False, 'running': False, 'paused': False, 'idle': False, 'calls_1h': 0, 'calls_24h': 0, } # Non-worker services (configured status only) services['acoustid'] = { 'name': 'AcoustID', 'configured': bool(config_manager.get('acoustid.api_key', '')), } services['listenbrainz'] = { 'name': 'ListenBrainz', 'configured': bool(config_manager.get('listenbrainz.token', '')), } return services # Status check caching to reduce unnecessary API calls @app.route('/status') def get_status(): if not config_manager: return jsonify({"error": "Server configuration manager is not initialized."}), 500 try: import time current_time = time.time() active_server = config_manager.get_active_media_server() metadata_status = get_metadata_status_snapshot(spotify_client=spotify_client) # Test media server — engine reads active_server config + dispatches # to the right client (with internal connection caching). Engine # returns False safely if the active client is None / not registered. if current_time - _status_cache_timestamps['media_server'] > STATUS_CACHE_TTL: media_server_start = time.time() media_server_status = ( media_server_engine.is_connected() if media_server_engine else False ) media_server_response_time = (time.time() - media_server_start) * 1000 _status_cache['media_server'] = { 'connected': media_server_status, 'response_time': round(media_server_response_time, 1), 'type': active_server } _status_cache_timestamps['media_server'] = current_time # else: use cached value # Test Soulseek - only if it's the active source or in the hybrid order if current_time - _status_cache_timestamps['soulseek'] > STATUS_CACHE_TTL: download_mode = config_manager.get('download_source.mode', 'hybrid') hybrid_order = config_manager.get('download_source.hybrid_order', ['hifi', 'youtube', 'soulseek']) soulseek_relevant = (download_mode == 'soulseek' or (download_mode == 'hybrid' and 'soulseek' in hybrid_order)) # Serverless sources (YouTube, HiFi, Qobuz, Tidal, Deezer, Lidarr, SoundCloud) # don't depend on slskd being reachable — when one of these is the # active source, surface "connected" without probing slskd so the # dashboard / sidebar indicator stays green. serverless_sources = ('youtube', 'hifi', 'qobuz', 'tidal', 'deezer_dl', 'lidarr', 'soundcloud') is_serverless = (download_mode in serverless_sources or (download_mode == 'hybrid' and hybrid_order and any(s in serverless_sources for s in hybrid_order))) # Serverless check first — avoids slow slskd timeout when YouTube/HiFi are in hybrid order if is_serverless: soulseek_status = True soulseek_response_time = 0 elif soulseek_relevant and download_orchestrator: soulseek_start = time.time() try: soulseek_status = run_async(download_orchestrator.check_connection()) except Exception: soulseek_status = False soulseek_response_time = (time.time() - soulseek_start) * 1000 else: soulseek_status = False soulseek_response_time = 0 _status_cache['soulseek'] = { 'connected': soulseek_status, 'response_time': round(soulseek_response_time, 1) } _status_cache_timestamps['soulseek'] = current_time # Include download source mode so frontend can update labels download_mode = config_manager.get('download_source.mode', 'hybrid') _status_cache['soulseek']['source'] = download_mode # Count active downloads for nav badge active_dl_count = 0 with tasks_lock: for t in download_tasks.values(): if t.get('status') in ('downloading', 'searching', 'post_processing', 'queued', 'pending'): active_dl_count += 1 status_data = { 'metadata_source': metadata_status['metadata_source'], 'spotify': metadata_status['spotify'], 'media_server': _status_cache['media_server'], 'soulseek': _status_cache['soulseek'], 'active_media_server': active_server, 'enrichment': _get_enrichment_status(), 'active_downloads': active_dl_count, } return jsonify(status_data) except Exception as e: return jsonify({'error': str(e)}), 500 @app.route('/api/fix-navidrome-urls', methods=['POST']) def fix_navidrome_urls(): """Fix Navidrome artist image URLs to use correct Subsonic format""" try: db = get_database() with db._get_connection() as conn: cursor = conn.cursor() # Get all Navidrome artists with old URL format cursor.execute('SELECT id, name, thumb_url FROM artists WHERE server_source = "navidrome" AND thumb_url LIKE "/api/artist/%"') artists = cursor.fetchall() if not artists: return jsonify({"status": "success", "message": "No URLs needed fixing", "updated": 0}) # Update URLs to new Subsonic format import re updated = 0 examples = [] for artist_id, name, old_url in artists: # Extract artist ID from old URL: /api/artist/ARTIST_ID/image match = re.search(r'/api/artist/([^/]+)/image', old_url) if match: artist_spotify_id = match.group(1) new_url = f'/rest/getCoverArt?id={artist_spotify_id}' cursor.execute('UPDATE artists SET thumb_url = ? WHERE id = ? AND server_source = "navidrome"', (new_url, artist_id)) updated += 1 if len(examples) < 3: # Show first 3 as examples examples.append(f'{name}: {old_url} -> {new_url}') conn.commit() return jsonify({ "status": "success", "message": f"Updated {updated} Navidrome artist URLs to Subsonic format", "updated": updated, "examples": examples }) except Exception as e: return jsonify({"status": "error", "message": str(e)}), 500 def _regenerate_batch_m3u(batch, tracks): """Regenerate M3U file for a completed batch using real library DB paths. Called from batch completion handler after all post-processing is done.""" try: from difflib import SequenceMatcher try: from unidecode import unidecode as _unidecode except ImportError: _unidecode = lambda x: x def _norm(text): return _unidecode(text).lower().strip() if text else '' playlist_name = batch.get('playlist_name', 'Playlist') db = get_database() active_server = config_manager.get_active_media_server() raw_base = config_manager.get('m3u_export.entry_base_path', '') or '' entry_base_path = raw_base.rstrip('/\\') # Resolve file paths from library DB from collections import defaultdict artist_groups = defaultdict(list) for idx, t in enumerate(tracks): artist_groups[t.get('artist', '') or ''].append((idx, t)) file_path_map = {} for artist, group in artist_groups.items(): if not artist: for idx, _ in group: file_path_map[idx] = None continue db_tracks = db.search_tracks(artist=artist, limit=500, server_source=active_server) if not db_tracks: for idx, _ in group: file_path_map[idx] = None continue db_entries = [(_norm(t.title), t) for t in db_tracks] for idx, track in group: name = track.get('name', '') if not name: file_path_map[idx] = None continue s_norm = _norm(name) matched = None for db_n, db_t in db_entries: if s_norm == db_n or SequenceMatcher(None, s_norm, db_n).ratio() >= 0.7: matched = db_t break file_path_map[idx] = matched.file_path if matched else None # Build M3U content import datetime as _dt lines = ['#EXTM3U', f'#PLAYLIST:{playlist_name}', f'#GENERATED:{_dt.datetime.utcnow().isoformat()}Z', ''] found = 0 for idx, track in enumerate(tracks): dur_s = int((track.get('duration_ms', 0) or 0) / 1000) artist = track.get('artist', 'Unknown') name = track.get('name', 'Unknown') lines.append(f'#EXTINF:{dur_s},{artist} - {name}') fp = file_path_map.get(idx) if fp: path = f'{entry_base_path}/{fp}' if entry_base_path else fp lines.append(path) found += 1 else: lines.append(f'# MISSING: {artist} - {name}') lines.append('') if found == 0: return # Don't overwrite with an all-missing M3U m3u_content = '\n'.join(lines) transfer_dir = docker_resolve_path(config_manager.get('soulseek.transfer_path', './Transfer')) m3u_folder = _compute_m3u_folder(transfer_dir, 'playlist', playlist_name, '', '', '') os.makedirs(m3u_folder, exist_ok=True) safe_fn = _sanitize_filename(playlist_name) m3u_path = os.path.join(m3u_folder, f'{safe_fn}.m3u') with open(m3u_path, 'w', encoding='utf-8') as f: f.write(m3u_content) logger.info(f"[M3U] Regenerated M3U on batch complete: {m3u_path} ({found}/{len(tracks)} resolved)") except Exception as e: logger.error(f"[M3U] Error in _regenerate_batch_m3u: {e}") @app.route('/api/save-playlist-m3u', methods=['POST']) def save_playlist_m3u(): """Save M3U playlist file to the relevant download folder""" try: data = request.get_json() if not data: return jsonify({"status": "error", "message": "No data provided"}), 400 playlist_name = data.get('playlist_name', 'Playlist') m3u_content = data.get('m3u_content', '') context_type = data.get('context_type', 'playlist') artist_name = data.get('artist_name', '') album_name = data.get('album_name', '') year = data.get('year', '') force = data.get('force', False) # Check if M3U export is enabled (unless force=True from manual Export button) if not force and not config_manager.get('m3u_export.enabled', False): return jsonify({"status": "success", "message": "M3U export disabled in settings", "skipped": True}) if not m3u_content: return jsonify({"status": "error", "message": "No M3U content provided"}), 400 # Compute target folder using the template system transfer_dir = docker_resolve_path(config_manager.get('soulseek.transfer_path', './Transfer')) m3u_folder = _compute_m3u_folder(transfer_dir, context_type, playlist_name, artist_name, album_name, year) os.makedirs(m3u_folder, exist_ok=True) # Build M3U filename from playlist or album name if context_type == 'album' and artist_name and album_name: safe_filename = _sanitize_filename(f"{artist_name} - {album_name}") else: safe_filename = _sanitize_filename(playlist_name) m3u_filename = f"{safe_filename}.m3u" m3u_path = os.path.join(m3u_folder, m3u_filename) # Write M3U file (overwrite if exists) with open(m3u_path, 'w', encoding='utf-8') as f: f.write(m3u_content) logger.info(f"Saved M3U file: {m3u_path}") return jsonify({ "status": "success", "message": f"M3U file saved: {m3u_filename}", "path": m3u_path }) except Exception as e: logger.error(f"Error saving M3U file: {e}") return jsonify({"status": "error", "message": str(e)}), 500 @app.route('/api/generate-playlist-m3u', methods=['POST']) def generate_playlist_m3u(): """Generate M3U content with real file paths resolved from the library DB. Each track entry uses its actual stored file_path rather than a synthesised Artist - Title.mp3 string, so media servers can locate the files. An optional entry_base_path prefix (from settings) is prepended to every path. """ try: data = request.get_json() if not data: return jsonify({"success": False, "error": "No data"}), 400 playlist_name = data.get('playlist_name', 'Playlist') tracks = data.get('tracks', []) # [{name, artist, duration_ms}, ...] context_type = data.get('context_type', 'playlist') artist_name_ctx = data.get('artist_name', '') album_name = data.get('album_name', '') year = data.get('year', '') save_to_disk = data.get('save_to_disk', False) force = data.get('force', False) raw_base = config_manager.get('m3u_export.entry_base_path', '') or '' entry_base_path = raw_base.rstrip('/\\') db = get_database() active_server = config_manager.get_active_media_server() # --- fuzzy matching helpers (same logic as library_check_tracks) --- import re as _re from difflib import SequenceMatcher try: from unidecode import unidecode as _unidecode except ImportError: _unidecode = lambda x: x def _norm(text): return _unidecode(text).lower().strip() if text else '' def _clean(text): s = _norm(text) s = _re.sub(r'\s*[\[\(].*?[\]\)]', '', s) s = _re.sub(r'\s*-\s*', ' ', s) s = _re.sub(r'\s*feat\..*', '', s) s = _re.sub(r'\s*featuring.*', '', s) s = _re.sub(r'\s*ft\..*', '', s) s = _re.sub(r'\s*\d{4}\s*remaster.*', '', s) s = _re.sub(r'\s*remaster(ed)?.*', '', s) return _re.sub(r'\s+', ' ', s).strip() # Group tracks by primary artist to minimise DB queries from collections import defaultdict artist_groups = defaultdict(list) for idx, t in enumerate(tracks): artist_groups[t.get('artist', '') or ''].append((idx, t)) file_path_map = {} for artist, group in artist_groups.items(): if not artist: for idx, _ in group: file_path_map[idx] = None continue db_tracks = db.search_tracks(artist=artist, limit=500, server_source=active_server) if not db_tracks: for idx, _ in group: file_path_map[idx] = None continue db_entries = [(_norm(t.title), _clean(t.title), t) for t in db_tracks] for idx, track in group: name = track.get('name', '') if not name: file_path_map[idx] = None continue s_norm, s_clean = _norm(name), _clean(name) matched = None for db_n, db_c, db_t in db_entries: if s_norm == db_n or s_clean == db_c: matched = db_t break if max(SequenceMatcher(None, s_norm, db_n).ratio(), SequenceMatcher(None, s_clean, db_c).ratio()) >= 0.7: matched = db_t break file_path_map[idx] = matched.file_path if matched else None # --- build M3U content --- import datetime as _dt found_count = 0 missing_count = 0 lines = [ '#EXTM3U', f'#PLAYLIST:{playlist_name}', f'#GENERATED:{_dt.datetime.utcnow().isoformat()}Z', '', ] for idx, track in enumerate(tracks): name = track.get('name', '') or 'Unknown' artist = track.get('artist', '') or 'Unknown Artist' dur_s = int((track.get('duration_ms') or 0) / 1000) or -1 file_path = file_path_map.get(idx) lines.append(f'#EXTINF:{dur_s},{artist} - {name}') if file_path: found_count += 1 lines.append('#STATUS:FOUND_IN_LIBRARY') entry = f'{entry_base_path}/{file_path}' if entry_base_path else file_path lines.append(entry.replace('\\', '/')) else: missing_count += 1 lines.append('#STATUS:MISSING') safe = _re.sub(r'[/\\?%*:|"<>]', '-', f'{artist} - {name}') lines.append(f'# NOT AVAILABLE: {safe}') lines.append('') lines += [ '#SUMMARY', f'#TOTAL_TRACKS:{len(tracks)}', f'#FOUND_IN_LIBRARY:{found_count}', '#DOWNLOADED:0', f'#MISSING:{missing_count}', ] m3u_content = '\n'.join(lines) # --- optionally save to disk --- saved_path = None if save_to_disk and (force or config_manager.get('m3u_export.enabled', False)): transfer_dir = docker_resolve_path(config_manager.get('soulseek.transfer_path', './Transfer')) m3u_folder = _compute_m3u_folder(transfer_dir, context_type, playlist_name, artist_name_ctx, album_name, year) os.makedirs(m3u_folder, exist_ok=True) if context_type == 'album' and artist_name_ctx and album_name: safe_fn = _sanitize_filename(f'{artist_name_ctx} - {album_name}') else: safe_fn = _sanitize_filename(playlist_name) m3u_path = os.path.join(m3u_folder, f'{safe_fn}.m3u') with open(m3u_path, 'w', encoding='utf-8') as f: f.write(m3u_content) saved_path = m3u_path logger.info(f"Saved M3U file: {m3u_path}") return jsonify({ "success": True, "m3u_content": m3u_content, "stats": {"found": found_count, "downloaded": 0, "missing": missing_count}, "path": saved_path }) except Exception as e: logger.error(f"Error generating M3U: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 def _build_system_stats(): """Build system statistics dict — shared by HTTP handler and WebSocket emitter.""" import psutil import time from datetime import timedelta # Calculate uptime start_time = getattr(app, 'start_time', time.time()) uptime_seconds = time.time() - start_time uptime = str(timedelta(seconds=int(uptime_seconds))) # Get memory usage memory = psutil.virtual_memory() memory_usage = f"{memory.percent}%" # Count active downloads from download_batches (batches that are currently downloading) active_downloads = len([batch_id for batch_id, batch_data in download_batches.items() if batch_data.get('phase') == 'downloading']) # Count finished downloads (completed this session) - use session counter like dashboard.py with session_stats_lock: finished_downloads = session_completed_downloads # Calculate total download speed from active soulseek transfers # Skip the slskd API call entirely when Soulseek is not the active download # source — avoids connection timeout spam every 10 seconds for users who have # a slskd URL configured but are using YouTube/Tidal/etc. total_download_speed = 0.0 soulseek_known_down = not _status_cache.get('soulseek', {}).get('connected', True) download_mode = config_manager.get('download_source.mode', 'hybrid') hybrid_order = config_manager.get('download_source.hybrid_order', ['hifi', 'youtube', 'soulseek']) soulseek_active = (download_mode == 'soulseek' or (download_mode == 'hybrid' and 'soulseek' in hybrid_order)) if soulseek_active and not soulseek_known_down: try: transfers_data = run_async(download_orchestrator._make_request('GET', 'transfers/downloads')) if transfers_data: for user_data in transfers_data: if 'directories' in user_data: for directory in user_data['directories']: if 'files' in directory: for file_info in directory['files']: state = file_info.get('state', '').lower() # Only count actively downloading files if 'inprogress' in state or 'downloading' in state or 'transferring' in state: speed = file_info.get('averageSpeed', 0) if isinstance(speed, (int, float)) and speed > 0: total_download_speed += float(speed) except Exception as e: logger.error(f"Could not fetch download speeds: {e}") # Convert bytes/sec to KB/s and format if total_download_speed > 0: speed_kb_s = total_download_speed / 1024 if speed_kb_s >= 1024: speed_mb_s = speed_kb_s / 1024 download_speed_str = f"{speed_mb_s:.1f} MB/s" else: download_speed_str = f"{speed_kb_s:.1f} KB/s" else: download_speed_str = "0 KB/s" # Count active syncs (playlists currently syncing) active_syncs = 0 # Count Spotify playlist syncs for _playlist_id, sync_state in sync_states.items(): if sync_state.get('status') == 'syncing': active_syncs += 1 # Count YouTube playlist syncs for _url_hash, state in youtube_playlist_states.items(): if state.get('phase') == 'syncing': active_syncs += 1 # Count Tidal playlist syncs for _playlist_id, state in tidal_discovery_states.items(): if state.get('phase') == 'syncing': active_syncs += 1 return { 'active_downloads': active_downloads, 'finished_downloads': finished_downloads, 'download_speed': download_speed_str, 'active_syncs': active_syncs, 'uptime': uptime, 'memory_usage': memory_usage } @app.route('/api/system/stats') def get_system_stats(): """Get system statistics for dashboard""" try: return jsonify(_build_system_stats()) except Exception as e: return jsonify({'error': str(e)}), 500 from core.debug_info import ( _safe_check, get_debug_info as _debug_info_get, init as _init_debug_info, ) @app.route('/api/debug-info') def get_debug_info(): return _debug_info_get() @app.route('/api/activity/feed') def get_activity_feed(): """Get recent activity feed for dashboard""" try: with activity_feed_lock: # Return last 10 activities in reverse chronological order return jsonify({'activities': activity_feed[-10:][::-1]}) except Exception as e: return jsonify({'error': str(e)}), 500 @app.route('/api/activity/toasts') def get_recent_toasts(): """Get recent activities that should show toasts""" try: import time current_time = time.time() with activity_feed_lock: # Return activities from last 10 seconds that should show toasts recent_toasts = [ activity for activity in activity_feed if activity.get('show_toast', True) and (current_time - activity.get('timestamp', 0)) <= 10 ] return jsonify({'toasts': recent_toasts}) except Exception as e: return jsonify({'error': str(e)}), 500 @app.route('/api/logs') def get_activity_logs(): """Get formatted activity feed for display in sync page log area""" try: with activity_feed_lock: # Get the last 50 activities (more than the dashboard shows) recent_activities = activity_feed[-50:] if len(activity_feed) > 50 else activity_feed[:] # Reverse order so newest appears at top recent_activities = recent_activities[::-1] # Format activities as readable log entries formatted_logs = [] if not recent_activities: formatted_logs = [ "No recent activity.", "Sync and download operations will appear here in real-time." ] else: for activity in recent_activities: # Format: [TIME] ICON TITLE - SUBTITLE timestamp = activity.get('time', 'Unknown') icon = activity.get('icon', '•') title = activity.get('title', 'Activity') subtitle = activity.get('subtitle', '') # Create a clean, readable log entry if subtitle: log_entry = f"[{timestamp}] {icon} {title} - {subtitle}" else: log_entry = f"[{timestamp}] {icon} {title}" formatted_logs.append(log_entry) return jsonify({'logs': formatted_logs}) except Exception as e: return jsonify({'logs': [f'Error reading activity feed: {str(e)}']}) # --- Internal API Key Management (browser-only, no auth) --- @app.route('/api/v1/api-keys-internal', methods=['GET']) def list_api_keys_internal(): """List API keys for the settings page (no auth required — same as all UI routes).""" keys = config_manager.get('api_keys', []) safe_keys = [ { "id": k.get("id"), "label": k.get("label", ""), "key_prefix": k.get("key_prefix", ""), "created_at": k.get("created_at"), "last_used_at": k.get("last_used_at"), } for k in keys ] return jsonify({"success": True, "data": {"keys": safe_keys}}) @app.route('/api/v1/api-keys-internal/generate', methods=['POST']) def generate_api_key_internal(): """Generate API key from settings page (no auth required).""" from api.auth import generate_api_key body = request.get_json(silent=True) or {} label = body.get("label", "") raw_key, record = generate_api_key(label) keys = config_manager.get('api_keys', []) keys.append(record) config_manager.set('api_keys', keys) return jsonify({"success": True, "data": { "key": raw_key, "id": record["id"], "label": record["label"], "key_prefix": record["key_prefix"], "created_at": record["created_at"], }}), 201 @app.route('/api/v1/api-keys-internal/revoke/', methods=['DELETE']) def revoke_api_key_internal(key_id): """Revoke API key from settings page (no auth required).""" keys = config_manager.get('api_keys', []) original_len = len(keys) keys = [k for k in keys if k.get("id") != key_id] if len(keys) == original_len: return jsonify({"success": False, "error": {"message": "Key not found"}}), 404 config_manager.set('api_keys', keys) return jsonify({"success": True, "data": {"message": "API key revoked"}}) @app.route('/api/settings', methods=['GET', 'POST']) @admin_only def handle_settings(): global tidal_client # Declare that we might modify the global instance if not config_manager: return jsonify({"error": "Server configuration manager is not initialized."}), 500 if request.method == 'POST': try: new_settings = request.get_json() if not new_settings: return jsonify({"success": False, "error": "No data received."}), 400 if 'active_media_server' in new_settings: config_manager.set_active_media_server(new_settings['active_media_server']) for service in ['spotify', 'plex', 'jellyfin', 'navidrome', 'soulseek', 'download_source', 'settings', 'database', 'metadata_enhancement', 'file_organization', 'playlist_sync', 'tidal', 'tidal_download', 'qobuz', 'hifi_download', 'deezer_download', 'lidarr_download', 'listenbrainz', 'acoustid', 'lastfm', 'genius', 'import', 'lossy_copy', 'listening_stats', 'ui_appearance', 'youtube', 'content_filter', 'itunes', 'm3u_export', 'musicbrainz', 'deezer', 'audiodb', 'metadata', 'hydrabase', 'security', 'discogs', 'library', 'discover', 'wishlist', 'genre_whitelist', 'post_processing']: if service in new_settings: for key, value in new_settings[service].items(): config_manager.set(f'{service}.{key}', value) logger.info("Settings saved successfully via Web UI.") # Add activity for settings save changed_services = list(new_settings.keys()) services_text = ", ".join(changed_services) add_activity_item("", "Settings Updated", f"{services_text} configuration saved", "Now") add_activity_item("", "Settings Updated", f"{services_text} configuration saved", "Now") # Reload service clients with new settings (guard against None from partial init) if spotify_client: spotify_client.reload_config() if media_server_engine.client('plex'): media_server_engine.client('plex').server = None if media_server_engine.client('jellyfin'): media_server_engine.client('jellyfin').reload_config() if media_server_engine.client('navidrome'): media_server_engine.client('navidrome').reload_config() # Reload orchestrator settings (download source mode, hybrid_primary, etc.) if download_orchestrator: download_orchestrator.reload_settings() # Reload YouTube client settings (rate limiting, cookies) _yt = download_orchestrator.client("youtube") if _yt: _yt.reload_settings() # FIX: Re-instantiate the global tidal_client to pick up new settings try: tidal_client = TidalClient() except Exception as e: logger.debug("tidal client re-init: %s", e) # Reload enrichment worker clients for key-based services if lastfm_worker: lastfm_worker._init_client() if genius_worker: genius_worker._init_client() if tidal_enrichment_worker: tidal_enrichment_worker.client = tidal_client if 'spotify' in new_settings: publish_spotify_status( connected=False, authenticated=False, rate_limited=False, rate_limit=None, post_ban_cooldown=None, ) # Invalidate status cache so next poll reflects new settings (e.g. fallback source change) invalidate_metadata_status_caches() logger.info("Service clients re-initialized with new settings.") return jsonify({"success": True, "message": "Settings saved successfully."}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 else: # GET request try: data = dict(config_manager.config_data) # Include which download sources are configured so the UI can auto-disable unconfigured ones try: data['_source_status'] = download_orchestrator.get_source_status() except Exception as e: logger.debug("download source status read failed: %s", e) return jsonify(data) except Exception as e: return jsonify({"error": str(e)}), 500 @app.route('/api/dev-mode', methods=['GET', 'POST']) def handle_dev_mode(): global dev_mode_enabled if request.method == 'POST': data = request.get_json() if data.get('password') == 'hydratest': dev_mode_enabled = True logger.info("Dev mode activated") return jsonify({"success": True, "enabled": True}) return jsonify({"success": False, "error": "Invalid password"}), 401 return jsonify({"enabled": dev_mode_enabled}) # ── Hydrabase WebSocket Connection ── # ── Hydrabase Comparison Store ── import collections as _collections _hydrabase_comparisons = _collections.OrderedDict() _COMPARISON_MAX_ENTRIES = 50 _comparison_lock = threading.Lock() def _is_hydrabase_active(): """Check if Hydrabase is connected and enabled for metadata use.""" try: from core.metadata.registry import is_hydrabase_enabled return is_hydrabase_enabled() except Exception: return False def _run_background_comparison(query, hydrabase_counts=None): """Run Spotify + fallback source searches in background and store for comparison. Args: query: Search query string. hydrabase_counts: Optional pre-computed dict {'tracks': N, 'artists': N, 'albums': N} from the primary search to avoid redundant Hydrabase round-trips. """ def _worker(): try: result = {'timestamp': time.time(), 'query': query} # Use pre-computed counts if available, otherwise fetch from Hydrabase if hydrabase_counts is not None: hydra_data = hydrabase_counts else: hydra_data = {'tracks': 0, 'artists': 0, 'albums': 0} if _is_hydrabase_active(): raw_t = hydrabase_client.search_raw(query, 'track') raw_ar = hydrabase_client.search_raw(query, 'artists') raw_al = hydrabase_client.search_raw(query, 'album') hydra_data = { 'tracks': len(raw_t) if raw_t else 0, 'artists': len(raw_ar) if raw_ar else 0, 'albums': len(raw_al) if raw_al else 0 } result['hydrabase'] = hydra_data # Spotify results spotify_data = {'tracks': 0, 'artists': 0, 'albums': 0} if spotify_client and spotify_client.is_authenticated(): try: s_tracks = spotify_client.search_tracks(query, limit=10) s_artists = spotify_client.search_artists(query, limit=10) s_albums = spotify_client.search_albums(query, limit=10) spotify_data = { 'tracks': len(s_tracks), 'artists': len(s_artists), 'albums': len(s_albums) } except Exception as e: logger.debug(f"Comparison Spotify search failed: {e}") result['spotify'] = spotify_data # Fallback metadata source results (iTunes or Deezer) fallback_source = _get_metadata_fallback_source() fallback_data = {'tracks': 0, 'artists': 0, 'albums': 0} try: fallback_client = _get_metadata_fallback_client() f_tracks = fallback_client.search_tracks(query, limit=10) f_artists = fallback_client.search_artists(query, limit=10) f_albums = fallback_client.search_albums(query, limit=10) fallback_data = { 'tracks': len(f_tracks), 'artists': len(f_artists), 'albums': len(f_albums) } except Exception as e: logger.debug(f"Comparison {fallback_source} search failed: {e}") result['fallback'] = fallback_data result['fallback_source'] = fallback_source with _comparison_lock: _hydrabase_comparisons[query] = result while len(_hydrabase_comparisons) > _COMPARISON_MAX_ENTRIES: _hydrabase_comparisons.popitem(last=False) logger.info(f"Background comparison stored for '{query}': H={hydra_data}, S={spotify_data}, {fallback_source.capitalize()}={fallback_data}") except Exception as e: logger.error(f"Background comparison failed for '{query}': {e}") threading.Thread(target=_worker, daemon=True).start() @app.route('/api/hydrabase/connect', methods=['POST']) def hydrabase_connect(): """Connect to a Hydrabase instance via WebSocket.""" global _hydrabase_ws data = request.get_json() url = data.get('url', '').strip() api_key = data.get('api_key', '').strip() if not url or not api_key: return jsonify({"success": False, "error": "URL and API key required"}), 400 try: import websocket with _hydrabase_lock: # Close existing connection if any if _hydrabase_ws: try: _hydrabase_ws.close() except Exception as _e: logger.debug("hydrabase connect-existing close: %s", _e) ws = websocket.create_connection( url, header={"x-api-key": api_key}, timeout=10 ) _hydrabase_ws = ws # Save credentials for auto-reconnect config_manager.set('hydrabase.url', url) config_manager.set('hydrabase.api_key', api_key) config_manager.set('hydrabase.auto_connect', True) logger.info(f"[Hydrabase] Connected to {url}") return jsonify({"success": True, "message": "Connected"}) except Exception as e: logger.error(f"[Hydrabase] Connection failed: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/hydrabase/disconnect', methods=['POST']) def hydrabase_disconnect(): """Disconnect from Hydrabase and disable dev mode.""" global _hydrabase_ws, dev_mode_enabled with _hydrabase_lock: if _hydrabase_ws: try: _hydrabase_ws.close() except Exception as e: logger.debug("hydrabase disconnect close: %s", e) _hydrabase_ws = None config_manager.set('hydrabase.auto_connect', False) # Only disable dev mode if not using Hydrabase as a regular fallback source if _get_metadata_fallback_source() != 'hydrabase': dev_mode_enabled = False logger.info("[Hydrabase] Disconnected") return jsonify({"success": True}) @app.route('/api/hydrabase/status') def hydrabase_status(): """Check if connected to Hydrabase.""" try: connected = _hydrabase_ws is not None and _hydrabase_ws.connected except Exception: connected = False try: hydra_config = config_manager.get_hydrabase_config() except AttributeError: hydra_config = {} peer_count = None try: if hydrabase_client and hydrabase_client.last_peer_count is not None: peer_count = hydrabase_client.last_peer_count except NameError: pass return jsonify({ "connected": connected, "saved_url": hydra_config.get('url', ''), "saved_api_key": hydra_config.get('api_key', ''), "auto_connect": hydra_config.get('auto_connect', False), "peer_count": peer_count }) @app.route('/api/hydrabase/comparisons') def hydrabase_comparisons(): """Get recent comparison results (Hydrabase vs Spotify vs fallback source).""" if not dev_mode_enabled: return jsonify({"success": False, "error": "Dev mode not active"}), 403 with _comparison_lock: items = list(reversed(_hydrabase_comparisons.values())) return jsonify({"success": True, "comparisons": items}) @app.route('/api/hydrabase/send', methods=['POST']) def hydrabase_send(): """Send a raw JSON payload to Hydrabase and return the response.""" global _hydrabase_ws if not dev_mode_enabled: return jsonify({"success": False, "error": "Dev mode not active"}), 403 if not _hydrabase_ws or not _hydrabase_ws.connected: return jsonify({"success": False, "error": "Not connected to Hydrabase"}), 400 data = request.get_json() payload = data.get('payload') if not payload: return jsonify({"success": False, "error": "No payload provided"}), 400 try: message = json.dumps(payload) if isinstance(payload, dict) else str(payload) with _hydrabase_lock: _hydrabase_ws.send(message) response = _hydrabase_ws.recv() try: result = json.loads(response) except json.JSONDecodeError: result = response logger.info("[Hydrabase] Sent payload — got response") return jsonify({"success": True, "data": result}) except Exception as e: logger.error(f"[Hydrabase] Send failed: {e}") with _hydrabase_lock: try: _hydrabase_ws.close() except Exception as _e: logger.debug("hydrabase send close: %s", _e) _hydrabase_ws = None return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/settings/log-level', methods=['GET', 'POST']) @admin_only def handle_log_level(): """Get or set the application log level""" from utils.logging_config import set_log_level, get_current_log_level from database.music_database import MusicDatabase if request.method == 'POST': try: data = request.get_json() level = data.get('level') if not level or level.upper() not in ['DEBUG', 'INFO', 'WARNING', 'ERROR']: return jsonify({"success": False, "error": "Invalid log level. Must be DEBUG, INFO, WARNING, or ERROR"}), 400 # Change the log level dynamically success = set_log_level(level) if success: # Save to database preferences db = MusicDatabase() db.set_preference('log_level', level.upper()) logger.info(f"Log level changed to {level.upper()} via Web UI") add_activity_item("", "Log Level Changed", f"Set to {level.upper()}", "Now") return jsonify({"success": True, "level": level.upper()}) else: return jsonify({"success": False, "error": "Failed to set log level"}), 500 except Exception as e: logger.error(f"Error setting log level: {e}") return jsonify({"success": False, "error": str(e)}), 500 else: # GET request try: current_level = get_current_log_level() return jsonify({"success": True, "level": current_level}) except Exception as e: logger.error(f"Error getting log level: {e}") return jsonify({"success": False, "error": str(e)}), 500 # =========================== # LIVE LOG VIEWER API # =========================== # In-memory ring buffer for live log streaming via WebSocket _live_log_buffer = [] _live_log_buffer_lock = threading.Lock() _LIVE_LOG_BUFFER_MAX = 500 @app.route('/api/logs/tail', methods=['GET']) def get_log_tail(): """Return the last N lines from a log file, optionally filtered by level.""" log_source = request.args.get('source', 'app') lines = request.args.get('lines', 200, type=int) lines = max(10, min(lines, 1000)) level_filter = request.args.get('level', '').upper() # DEBUG, INFO, WARNING, ERROR or empty log_map = { 'app': Path(_log_path), 'acoustid': _log_dir / 'acoustid.log', 'post_processing': _log_dir / 'post_processing.log', 'source_reuse': _log_dir / 'source_reuse.log', } log_path = log_map.get(log_source, log_map['app']) search = request.args.get('search', '').lower() def _classify_log_level(line): """Classify a log line's level. Returns DEBUG/INFO/WARNING/ERROR or empty for unclassified.""" if ' - DEBUG - ' in line: return 'DEBUG' if ' - INFO - ' in line: return 'INFO' if ' - WARNING - ' in line: return 'WARNING' if ' - ERROR - ' in line or ' - CRITICAL - ' in line: return 'ERROR' # Heuristic for plain-text output and non-logger lines ll = line.lower() if 'error' in ll or 'traceback' in ll or 'exception' in ll or 'failed' in ll: return 'ERROR' if 'warning' in ll or 'warn' in ll: return 'WARNING' if 'debug' in ll: return 'DEBUG' return 'INFO' # Default unclassified lines to INFO result_lines = [] if os.path.exists(log_path): try: with open(log_path, 'r', encoding='utf-8', errors='replace') as f: all_lines = f.readlines() # Read more lines than requested so filtering has enough to work with pool_size = lines * 5 if (level_filter or search) else lines tail = all_lines[-pool_size:] for line in tail: stripped = line.rstrip() if not stripped: continue if level_filter and level_filter in ('DEBUG', 'INFO', 'WARNING', 'ERROR'): if _classify_log_level(stripped) != level_filter: continue if search and search not in stripped.lower(): continue result_lines.append(stripped) # Trim to requested count after filtering result_lines = result_lines[-lines:] except Exception as e: result_lines = [f'Error reading log file: {e}'] # Available log files available = [] logs_dir = 'logs' if os.path.isdir(logs_dir): for fname in sorted(os.listdir(logs_dir)): if fname.endswith('.log'): fpath = os.path.join(logs_dir, fname) size_kb = os.path.getsize(fpath) / 1024 available.append({ 'key': fname.replace('.log', ''), 'file': fname, 'size': f"{size_kb:.0f} KB" if size_kb < 1024 else f"{size_kb/1024:.1f} MB", }) return jsonify({ 'lines': result_lines, 'source': log_source, 'total': len(result_lines), 'available_logs': available, }) # =========================== # AUTOMATIONS API # =========================== @app.route('/api/genre-whitelist/defaults', methods=['GET']) def get_genre_whitelist_defaults(): """Return the default genre whitelist.""" from core.genre_filter import DEFAULT_GENRES return jsonify({'genres': sorted(DEFAULT_GENRES, key=str.lower)}) # Automation route bodies live in core/automation/api.py — these routes are thin handlers. from core.automation import api as _auto_api from core.automation import blocks as _auto_blocks from core.automation import signals as _auto_signals @app.route('/api/automations', methods=['GET']) def list_automations(): """List all automations for the current profile.""" try: profile_id = session.get('profile_id', 1) return jsonify(_auto_api.list_automations(get_database(), profile_id)) except Exception as e: logger.error(f"Error listing automations: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/automations', methods=['POST']) def create_automation(): """Create a new automation.""" try: profile_id = session.get('profile_id', 1) body, status = _auto_api.create_automation(get_database(), automation_engine, profile_id, request.get_json()) return jsonify(body), status except Exception as e: logger.error(f"Error creating automation: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/automations/', methods=['GET']) def get_automation(automation_id): """Get a single automation.""" try: auto = _auto_api.get_automation(get_database(), automation_id) if auto is None: return jsonify({"error": "Automation not found"}), 404 return jsonify(auto) except Exception as e: logger.error(f"Error getting automation: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/automations/', methods=['PUT']) def update_automation_endpoint(automation_id): """Update an automation.""" try: body, status = _auto_api.update_automation(get_database(), automation_engine, automation_id, request.get_json()) return jsonify(body), status except Exception as e: logger.error(f"Error updating automation: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/automations/group', methods=['PUT']) def batch_update_automation_group(): """Batch update group_name for multiple automations.""" try: data = request.get_json() body, status = _auto_api.batch_update_group(get_database(), data.get('automation_ids', []), data.get('group_name')) return jsonify(body), status except Exception as e: logger.error(f"Error batch updating automation group: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/automations/bulk-toggle', methods=['POST']) def bulk_toggle_automations(): """Bulk enable/disable multiple automations.""" try: data = request.get_json() body, status = _auto_api.bulk_toggle(get_database(), automation_engine, data.get('automation_ids', []), data.get('enabled', True)) return jsonify(body), status except Exception as e: logger.error(f"Error bulk toggling automations: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/automations/', methods=['DELETE']) def delete_automation_endpoint(automation_id): """Delete an automation. System automations cannot be deleted.""" try: body, status = _auto_api.delete_automation(get_database(), automation_engine, automation_id) return jsonify(body), status except Exception as e: logger.error(f"Error deleting automation: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/automations//duplicate', methods=['POST']) def duplicate_automation_endpoint(automation_id): """Duplicate an automation. System automations cannot be duplicated.""" try: profile_id = session.get('profile_id', 1) body, status = _auto_api.duplicate_automation(get_database(), automation_engine, profile_id, automation_id) return jsonify(body), status except Exception as e: logger.error(f"Error duplicating automation: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/automations//toggle', methods=['POST']) def toggle_automation_endpoint(automation_id): """Toggle an automation's enabled state.""" try: body, status = _auto_api.toggle_automation(get_database(), automation_engine, automation_id) return jsonify(body), status except Exception as e: logger.error(f"Error toggling automation: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/automations//run', methods=['POST']) def run_automation_endpoint(automation_id): """Manually trigger an automation.""" try: body, status = _auto_api.run_automation(automation_engine, automation_id, get_current_profile_id()) return jsonify(body), status except Exception as e: logger.error(f"Error running automation: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/automations/progress', methods=['GET']) def get_automation_progress(): """Get current progress state for all running/recently finished automations.""" try: return jsonify(_auto_progress.get_running_progress()) except Exception as e: return jsonify({"error": str(e)}), 500 @app.route('/api/automations//history', methods=['GET']) def get_automation_history(automation_id): """Get run history for a specific automation.""" try: limit = request.args.get('limit', 50, type=int) offset = request.args.get('offset', 0, type=int) return jsonify(_auto_api.get_history(get_database(), automation_id, limit=limit, offset=offset)) except Exception as e: logger.error(f"Error getting automation history: {e}") return jsonify({"error": str(e)}), 500 def _collect_known_signals(): """Collect all signal names used across automations (for autocomplete).""" return _auto_signals.collect_known_signals(get_database()) @app.route('/api/scripts', methods=['GET']) def list_available_scripts(): """List executable scripts in the scripts directory.""" try: scripts_dir = docker_resolve_path(config_manager.get('scripts.path', './scripts')) if not scripts_dir or not os.path.isdir(scripts_dir): return jsonify({'scripts': []}) allowed_ext = {'.sh', '.py', '.bat', '.ps1', '.rb', '.pl', '.js'} scripts = [] for fname in sorted(os.listdir(scripts_dir)): ext = os.path.splitext(fname)[1].lower() fpath = os.path.join(scripts_dir, fname) if os.path.isfile(fpath) and (ext in allowed_ext or os.access(fpath, os.X_OK)): scripts.append({ 'name': fname, 'extension': ext, 'size': os.path.getsize(fpath), }) return jsonify({'scripts': scripts}) except Exception as e: return jsonify({'scripts': [], 'error': str(e)}) @app.route('/api/automations/blocks', methods=['GET']) def get_automation_blocks(): """Return available block types for the automation builder sidebar.""" return jsonify({ 'triggers': _auto_blocks.TRIGGERS, 'actions': _auto_blocks.ACTIONS, 'notifications': _auto_blocks.NOTIFICATIONS, 'known_signals': _collect_known_signals(), }) @app.route('/api/mirrored-playlists/list', methods=['GET']) def get_mirrored_playlists_list(): """Return simple list of mirrored playlists for automation config dropdowns.""" try: database = get_database() profile_id = get_current_profile_id() playlists = database.get_mirrored_playlists(profile_id=profile_id) spotify_authed = bool(spotify_client and spotify_client.is_spotify_authenticated()) return jsonify({ "playlists": [{"id": p['id'], "name": p['name'], "source": p.get('source', '')} for p in playlists], "spotify_authenticated": spotify_authed }) except Exception as e: return jsonify({"playlists": [], "spotify_authenticated": False}), 200 @app.route('/api/setup/status', methods=['GET']) def setup_status_endpoint(): """Check if first-run setup has been completed.""" # The setup wizard sets this flag when completed. download_source.mode is only # set by user action (wizard or settings page), never by config.json defaults. setup_done = config_manager.get('setup.completed', False) download_mode = config_manager.get('download_source.mode', '') # Either the explicit flag or a user-configured download source means setup is done has_user_config = bool(setup_done) or bool(download_mode) return jsonify({ "setup_complete": has_user_config, }) @app.route('/api/setup/complete', methods=['POST']) def setup_complete_endpoint(): """Mark first-run setup as completed.""" config_manager.set('setup.completed', True) return jsonify({"success": True}) @app.route('/api/test-connection', methods=['POST']) def test_connection_endpoint(): data = request.get_json() service = data.get('service') if not service: return jsonify({"success": False, "error": "No service specified."}), 400 logger.info(f"Received test connection request for: {service}") # Get the current settings from the main config manager to test with test_config = config_manager.get(service, {}) # For media servers, the service name might be 'server' if service == 'server': active_server = config_manager.get_active_media_server() test_config = config_manager.get(active_server, {}) service = active_server # use the actual server name for the test success, message = run_service_test(service, test_config) # Update status cache immediately when test succeeds to reflect current state import time if success: current_time = time.time() if service == 'spotify': invalidate_metadata_status_caches() logger.info("Updated Spotify status cache after successful test") elif service in ['plex', 'jellyfin', 'navidrome', 'soulsync']: _status_cache['media_server']['connected'] = True _status_cache['media_server']['type'] = service _status_cache_timestamps['media_server'] = current_time logger.info(f"Updated {service} status cache after successful test") elif service == 'soulseek': _status_cache['soulseek']['connected'] = True _status_cache_timestamps['soulseek'] = current_time logger.info("Updated Soulseek status cache after successful test") elif service == 'listenbrainz': logger.info("ListenBrainz test successful") # Add activity for connection test if success: add_activity_item("", "Connection Test", message, "Now") else: add_activity_item("", "Connection Test", f"{service.title()} connection failed", "Now") return jsonify({"success": success, "error": "" if success else message, "message": message if success else ""}) @app.route('/api/settings/config-status', methods=['GET']) @admin_only def settings_config_status_endpoint(): """Return per-service config state for the Settings → Connections page. Drives the green/yellow header gradient. No API calls — just config reads. """ try: return jsonify({ service: {'configured': _is_service_configured(service)} for service in SERVICE_CONFIG_REGISTRY }) except Exception as e: logger.error(f"config-status error: {e}") return jsonify({"error": str(e)}), 500 # ── Per-service verify cache ── # Stores the last verify result per service for 5 minutes to prevent # hammering external APIs when the user rapidly expands/collapses cards. _settings_verify_cache = {} # service -> {'success': bool, 'message': str, 'error': str, 'ts': float} _settings_verify_cache_lock = threading.Lock() _SETTINGS_VERIFY_TTL_SECONDS = 300 def _get_cached_verify_result(service: str): with _settings_verify_cache_lock: entry = _settings_verify_cache.get(service) if entry and (time.time() - entry['ts']) < _SETTINGS_VERIFY_TTL_SECONDS: return entry return None def _store_verify_result(service: str, success: bool, message: str): with _settings_verify_cache_lock: _settings_verify_cache[service] = { 'success': bool(success), 'message': message or '', 'error': '' if success else (message or 'Unknown error'), 'ts': time.time(), } def _run_single_verify(service: str): """Run verify for one service, reading its current saved config. Returns cached result if recent, else executes run_service_test and caches the outcome. """ if service not in SERVICE_CONFIG_REGISTRY: return {'success': False, 'error': f'Unknown service: {service}', 'cached': False} cached = _get_cached_verify_result(service) if cached: return { 'success': cached['success'], 'error': cached.get('error', ''), 'message': cached.get('message', ''), 'cached': True, } try: saved_config = config_manager.get(service, {}) or {} success, message = run_service_test(service, saved_config) _store_verify_result(service, success, message) return { 'success': bool(success), 'error': '' if success else (message or 'Verification failed'), 'message': message or '', 'cached': False, } except Exception as e: logger.error(f"verify error for {service}: {e}") _store_verify_result(service, False, str(e)) return {'success': False, 'error': str(e), 'cached': False} @app.route('/api/settings/verify', methods=['POST']) @admin_only def settings_verify_endpoint(): """Run connection verification for one or more services. Body: {"services": ["spotify", "deezer"]} — which services to check Query: ?force=true — bust cache and re-run Returns {service: {success, error, message, cached}} per requested service. Concurrency capped at 3 to avoid rate-limiting ourselves on Expand All. """ try: data = request.get_json(silent=True) or {} services = data.get('services') or [] if isinstance(services, str): services = [services] if not services: return jsonify({'error': 'No services specified'}), 400 force = (request.args.get('force') or '').strip().lower() in ('1', 'true', 'yes') if force: with _settings_verify_cache_lock: for svc in services: _settings_verify_cache.pop(svc, None) from concurrent.futures import ThreadPoolExecutor, as_completed results = {} with ThreadPoolExecutor(max_workers=3) as pool: futures = {pool.submit(_run_single_verify, svc): svc for svc in services} for fut in as_completed(futures): svc = futures[fut] try: results[svc] = fut.result() except Exception as e: results[svc] = {'success': False, 'error': str(e), 'cached': False} return jsonify(results) except Exception as e: logger.error(f"settings/verify error: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/test-dashboard-connection', methods=['POST']) def test_dashboard_connection_endpoint(): """Test connection from dashboard - creates specific dashboard activity items""" data = request.get_json() service = data.get('service') if not service: return jsonify({"success": False, "error": "No service specified."}), 400 logger.info(f"Received dashboard test connection request for: {service}") # Get the current settings from the main config manager to test with test_config = config_manager.get(service, {}) # For media servers, the service name might be 'server' if service == 'server': active_server = config_manager.get_active_media_server() test_config = config_manager.get(active_server, {}) service = active_server # use the actual server name for the test success, message = run_service_test(service, test_config) # Update status cache immediately when test succeeds to reflect current state import time if success: current_time = time.time() if service == 'spotify': invalidate_metadata_status_caches() logger.info("Updated Spotify status cache after successful dashboard test") elif service in ['plex', 'jellyfin', 'navidrome', 'soulsync']: _status_cache['media_server']['connected'] = True _status_cache['media_server']['type'] = service _status_cache_timestamps['media_server'] = current_time logger.info(f"Updated {service} status cache after successful dashboard test") elif service == 'soulseek': _status_cache['soulseek']['connected'] = True _status_cache_timestamps['soulseek'] = current_time logger.info("Updated Soulseek status cache after successful dashboard test") # Add activity for dashboard connection test (different from settings test) if success: add_activity_item("", "Dashboard Test", message, "Now") else: add_activity_item("", "Dashboard Test", f"{service.title()} service check failed", "Now") return jsonify({"success": success, "error": "" if success else message, "message": message if success else ""}) @app.route('/api/detect-media-server', methods=['POST']) def detect_media_server_endpoint(): data = request.get_json() server_type = data.get('server_type') logger.info(f"Received auto-detect request for: {server_type}") # Add activity for auto-detect start add_activity_item("", "Auto-Detect Started", f"Searching for {server_type} server", "Now") found_url = run_detection(server_type) if found_url: add_activity_item("", "Auto-Detect Complete", f"{server_type} found at {found_url}", "Now") return jsonify({"success": True, "found_url": found_url}) else: add_activity_item("", "Auto-Detect Failed", f"No {server_type} server found", "Now") return jsonify({"success": False, "error": f"No {server_type} server found on common local addresses."}) @app.route('/api/plex/pin/start', methods=['POST']) def start_plex_pin_auth(): try: pinlogin = MyPlexPinLogin(oauth=False) except Exception as e: logger.error(f'Failed to start Plex PIN auth: {e}') return jsonify({"success": False, "error": str(e)}), 500 pin_code = getattr(pinlogin, 'pin', None) if not pin_code: return jsonify({"success": False, "error": 'Failed to generate Plex PIN code.'}), 500 request_id = str(uuid.uuid4()) with _plex_pin_requests_lock: _plex_pin_requests[request_id] = { 'pinlogin': pinlogin, 'created_at': time.time(), 'expires_at': getattr(pinlogin, 'expires_at', None) } expires_in = None expires_at = getattr(pinlogin, 'expires_at', None) if expires_at: try: expires_in = int((expires_at - datetime.now(timezone.utc)).total_seconds()) except Exception: expires_in = None return jsonify({ "success": True, "request_id": request_id, "code": str(pin_code), "auth_url": "https://plex.tv/link", "expires_in": expires_in }) @app.route('/api/plex/pin/status', methods=['GET']) def get_plex_pin_status(): request_id = request.args.get('request_id') if not request_id: return jsonify({"success": False, "error": 'request_id is required'}), 400 with _plex_pin_requests_lock: entry = _plex_pin_requests.get(request_id) if not entry: return jsonify({"success": False, "error": 'Invalid or expired PIN request id.'}), 400 pinlogin = entry.get('pinlogin') if not pinlogin: return jsonify({"success": False, "error": 'Invalid PIN login state.'}), 500 try: if getattr(pinlogin, 'expired', False): with _plex_pin_requests_lock: _plex_pin_requests.pop(request_id, None) return jsonify({"success": False, "expired": True, "error": 'PIN code expired.'}) if pinlogin.checkLogin(): token = getattr(pinlogin, 'token', None) if not token: raise ValueError('Plex token was not returned after authorization.') try: account = MyPlexAccount(token=token) resources = account.resources() except Exception as e: logger.error(f'Failed to fetch Plex account resources: {e}') return jsonify({"success": False, "error": f'Plex authorization succeeded but failed to resolve server resources: {e}'}), 500 server_resources = [r for r in resources if 'server' in (getattr(r, 'provides', '') or '').lower()] if not server_resources: return jsonify({"success": False, "error": 'No Plex server resources found for this account.'}), 500 local_conn = None relay_conn = None for resource in server_resources: for conn in getattr(resource, 'connections', []) or []: if getattr(conn, 'local', False): local_conn = conn break if getattr(conn, 'relay', False) and relay_conn is None: relay_conn = conn if local_conn: break chosen_conn = local_conn or relay_conn if not chosen_conn: chosen_conn = getattr(server_resources[0], 'connections', [None])[0] found_url = getattr(chosen_conn, 'uri', None) if chosen_conn else None with _plex_pin_requests_lock: _plex_pin_requests.pop(request_id, None) if not found_url: return jsonify({"success": False, "error": 'Plex authorized, but no usable server connection URI was found.'}), 500 return jsonify({ "success": True, "found_url": found_url, "token": token, "status": 'Plex authorization complete.' }) return jsonify({"success": False, "status": 'Waiting for Plex authorization. Enter the PIN on plex.tv/link.'}) except Exception as e: logger.error(f'Error checking Plex PIN status: {e}') return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/plex/clear-library', methods=['POST']) def clear_plex_library_preference(): try: from database.music_database import MusicDatabase db = MusicDatabase() db.set_preference('plex_music_library', '') plex = media_server_engine.client('plex') if plex: plex.music_library = None # Also clear all-libraries mode so a fresh "select library" # flow doesn't inherit stale state. plex._all_libraries_mode = False return jsonify({"success": True, "message": "Plex library preference cleared."}) except Exception as e: logger.error(f"Error clearing Plex library preference: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/plex/music-libraries', methods=['GET']) def get_plex_music_libraries(): """Get list of all available music libraries from Plex""" try: libraries = media_server_engine.client('plex').get_available_music_libraries() # Get currently selected library from database.music_database import MusicDatabase db = MusicDatabase() selected_library = db.get_preference('plex_music_library') # Get the currently active library name. In all-libraries mode # ``music_library`` is None — surface a friendly label so the # settings UI displays the active selection correctly. current_library = None plex = media_server_engine.client('plex') if plex.music_library: current_library = plex.music_library.title elif plex.is_all_libraries_mode(): current_library = 'All Libraries (combined)' return jsonify({ "success": True, "libraries": libraries, "selected": selected_library, "current": current_library }) except Exception as e: logger.error(f"Error getting Plex music libraries: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/plex/select-music-library', methods=['POST']) def select_plex_music_library(): """Set the active Plex music library""" try: data = request.get_json() library_name = data.get('library_name') if not library_name: return jsonify({"success": False, "error": "No library name provided"}), 400 success = media_server_engine.client('plex').set_music_library_by_name(library_name) if success: add_activity_item("", "Library Selected", f"Plex music library set to: {library_name}", "Now") return jsonify({"success": True, "message": f"Music library set to: {library_name}"}) else: return jsonify({"success": False, "error": f"Library '{library_name}' not found"}), 404 except Exception as e: logger.error(f"Error setting Plex music library: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/jellyfin/users', methods=['GET']) def get_jellyfin_users(): """Get list of Jellyfin users that have music libraries""" try: users = media_server_engine.client('jellyfin').get_available_users() # Get currently selected user from database.music_database import MusicDatabase db = MusicDatabase() selected_user = db.get_preference('jellyfin_user') # Determine the current user name from user_id current_user = None if media_server_engine.client('jellyfin').user_id: for u in users: if u['id'] == media_server_engine.client('jellyfin').user_id: current_user = u['name'] break return jsonify({ "success": True, "users": users, "selected": selected_user, "current": current_user }) except Exception as e: logger.error(f"Error getting Jellyfin users: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/jellyfin/select-user', methods=['POST']) def select_jellyfin_user(): """Set the active Jellyfin user""" try: data = request.get_json() username = data.get('username') if not username: return jsonify({"success": False, "error": "No username provided"}), 400 success = media_server_engine.client('jellyfin').set_user_by_name(username) if success: add_activity_item("", "User Selected", f"Jellyfin user set to: {username}", "Now") return jsonify({"success": True, "message": f"User set to: {username}"}) else: return jsonify({"success": False, "error": f"User '{username}' not found or has no music library"}), 404 except Exception as e: logger.error(f"Error setting Jellyfin user: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/jellyfin/music-libraries', methods=['GET']) def get_jellyfin_music_libraries(): """Get list of all available music libraries from Jellyfin""" try: libraries = media_server_engine.client('jellyfin').get_available_music_libraries() # Get currently selected library from database.music_database import MusicDatabase db = MusicDatabase() selected_library = db.get_preference('jellyfin_music_library') # Get the currently active library name (match Plex behavior) current_library = None if media_server_engine.client('jellyfin').music_library_id: # Look up library name from ID for lib in libraries: if lib['key'] == media_server_engine.client('jellyfin').music_library_id: current_library = lib['title'] break return jsonify({ "success": True, "libraries": libraries, "selected": selected_library, "current": current_library }) except Exception as e: logger.error(f"Error getting Jellyfin music libraries: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/jellyfin/select-music-library', methods=['POST']) def select_jellyfin_music_library(): """Set the active Jellyfin music library""" try: data = request.get_json() library_name = data.get('library_name') if not library_name: return jsonify({"success": False, "error": "No library name provided"}), 400 success = media_server_engine.client('jellyfin').set_music_library_by_name(library_name) if success: add_activity_item("", "Library Selected", f"Jellyfin music library set to: {library_name}", "Now") return jsonify({"success": True, "message": f"Music library set to: {library_name}"}) else: return jsonify({"success": False, "error": f"Library '{library_name}' not found"}), 404 except Exception as e: logger.error(f"Error setting Jellyfin music library: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/navidrome/music-folders', methods=['GET']) def get_navidrome_music_folders(): """Get list of available music folders from Navidrome""" try: if not media_server_engine.client('navidrome'): return jsonify({"success": False, "error": "Navidrome client not configured"}), 400 folders = media_server_engine.client('navidrome').get_music_folders() from database.music_database import MusicDatabase db = MusicDatabase() selected_folder = db.get_preference('navidrome_music_folder') current_folder = None if media_server_engine.client('navidrome').music_folder_id: for f in folders: if f['key'] == media_server_engine.client('navidrome').music_folder_id: current_folder = f['title'] break return jsonify({ "success": True, "folders": folders, "selected": selected_folder, "current": current_folder }) except Exception as e: logger.error(f"Error getting Navidrome music folders: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/navidrome/select-music-folder', methods=['POST']) def select_navidrome_music_folder(): """Set the active Navidrome music folder""" try: data = request.get_json() folder_name = data.get('folder_name', '') success = media_server_engine.client('navidrome').set_music_folder_by_name(folder_name) if success: if folder_name: add_activity_item("", "Library Selected", f"Navidrome music folder set to: {folder_name}", "Now") return jsonify({"success": True, "message": f"Music folder set to: {folder_name}"}) else: add_activity_item("", "Library Selection Cleared", "Navidrome will use all libraries", "Now") return jsonify({"success": True, "message": "Music folder selection cleared — using all libraries"}) else: return jsonify({"success": False, "error": f"Folder '{folder_name}' not found"}), 404 except Exception as e: logger.error(f"Error setting Navidrome music folder: {e}") return jsonify({"success": False, "error": str(e)}), 500 # =============================== # == QUALITY PROFILE API == # =============================== @app.route('/api/quality-profile', methods=['GET']) def get_quality_profile(): """Get current quality profile configuration""" try: from database.music_database import MusicDatabase db = MusicDatabase() profile = db.get_quality_profile() return jsonify({ "success": True, "profile": profile }) except Exception as e: logger.error(f"Error getting quality profile: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/quality-profile', methods=['POST']) def save_quality_profile(): """Save quality profile configuration""" try: from database.music_database import MusicDatabase db = MusicDatabase() data = request.get_json() if not data: return jsonify({"success": False, "error": "No profile data provided"}), 400 success = db.set_quality_profile(data) if success: add_activity_item("", "Quality Profile Updated", f"Preset: {data.get('preset', 'custom')}", "Now") return jsonify({"success": True, "message": "Quality profile saved successfully"}) else: return jsonify({"success": False, "error": "Failed to save quality profile"}), 500 except Exception as e: logger.error(f"Error saving quality profile: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/quality-profile/presets', methods=['GET']) def get_quality_presets(): """Get all available quality presets""" try: from database.music_database import MusicDatabase db = MusicDatabase() presets = { "audiophile": db.get_quality_preset("audiophile"), "balanced": db.get_quality_preset("balanced"), "space_saver": db.get_quality_preset("space_saver") } return jsonify({ "success": True, "presets": presets }) except Exception as e: logger.error(f"Error getting quality presets: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/quality-profile/preset/', methods=['POST']) def apply_quality_preset(preset_name): """Apply a predefined quality preset""" try: from database.music_database import MusicDatabase db = MusicDatabase() preset = db.get_quality_preset(preset_name) success = db.set_quality_profile(preset) if success: add_activity_item("", "Quality Preset Applied", f"Applied '{preset_name}' preset", "Now") return jsonify({ "success": True, "message": f"Applied '{preset_name}' preset", "profile": preset }) else: return jsonify({"success": False, "error": "Failed to apply preset"}), 500 except Exception as e: logger.error(f"Error applying quality preset: {e}") return jsonify({"success": False, "error": str(e)}), 500 # =============================== # == END QUALITY PROFILE API == # =============================== @app.route('/api/detect-soulseek', methods=['POST']) def detect_soulseek_endpoint(): logger.info("Received auto-detect request for slskd") # Add activity for soulseek auto-detect start add_activity_item("", "Auto-Detect Started", "Searching for slskd server", "Now") found_url = run_detection('slskd') if found_url: add_activity_item("", "Auto-Detect Complete", f"slskd found at {found_url}", "Now") return jsonify({"success": True, "found_url": found_url}) else: add_activity_item("", "Auto-Detect Failed", "No slskd server found", "Now") return jsonify({"success": False, "error": "No slskd server found on common local addresses."}) # --- Authentication Routes --- @app.route('/auth/spotify') def auth_spotify(): """ Initiates Spotify OAuth authentication flow. Supports per-profile auth via ?profile_id= query param. """ try: profile_id = request.args.get('profile_id', '') # Per-profile auth: use profile's own credentials if profile_id and profile_id != '1': try: profile_id_int = int(profile_id) db = get_database() creds = db.get_profile_spotify(profile_id_int) if creds and creds.get('client_id'): from spotipy.oauth2 import SpotifyOAuth redirect_uri = creds.get('redirect_uri') or config_manager.get_spotify_config().get('redirect_uri', 'http://127.0.0.1:8888/callback') auth_manager = SpotifyOAuth( client_id=creds['client_id'], client_secret=creds['client_secret'], redirect_uri=redirect_uri, scope="user-library-read user-read-private playlist-read-private playlist-read-collaborative user-read-email user-follow-read", cache_path=f'config/.spotify_cache_profile_{profile_id_int}', state=f'profile_{profile_id_int}' ) auth_url = auth_manager.get_authorize_url() logger.info(f"Per-profile Spotify auth initiated for profile {profile_id_int}") return redirect(auth_url) except (ValueError, Exception) as e: logger.error(f"Per-profile Spotify auth failed, falling back to global: {e}") # Global auth (admin or fallback) temp_spotify_client = get_spotify_client() if temp_spotify_client.sp and temp_spotify_client.sp.auth_manager: # Get the authorization URL auth_url = temp_spotify_client.sp.auth_manager.get_authorize_url() configured_uri = config_manager.get_spotify_config().get('redirect_uri', 'http://127.0.0.1:8888/callback') logger.info(f"Spotify auth initiated — redirect_uri: {configured_uri}") add_activity_item("", "Spotify Auth Started", "Please complete OAuth in browser", "Now") # Detect if accessing remotely host = request.host.split(':')[0] is_remote = host not in ['127.0.0.1', 'localhost'] is_docker = os.path.exists('/.dockerenv') # If in Docker and accessing via 127.0.0.1, recommend localhost if is_docker and host == '127.0.0.1': host = 'localhost' # Check if the redirect_uri uses port 8008 (main app) vs the standalone callback server. # A localhost URI (127.0.0.1/localhost) on a non-8008 port → standalone callback server. # A custom domain or port 8008 → main Flask app (or reverse proxy to it). uses_main_port = ':8008' in configured_uri or ( '127.0.0.1' not in configured_uri and 'localhost' not in configured_uri ) if not (is_remote or is_docker): return redirect(auth_url) if uses_main_port: # The OAuth callback returns to the app itself, so there is no # need to keep an intermediate page open. return redirect(auth_url) # redirect_uri points to the standalone callback server — show manual steps AND suggest switching import re as _re _port_match = _re.search(r':(\d+)/', configured_uri) callback_server_port = _port_match.group(1) if _port_match else str(os.environ.get('SOULSYNC_SPOTIFY_CALLBACK_PORT', '8888')) return f'''

Spotify Authentication (Remote/Docker)

Using a reverse proxy? Your redirect URI is set to {configured_uri} which uses port {callback_server_port}. If you're behind a reverse proxy (Caddy, Nginx, Traefik), change the redirect URI in SoulSync settings to use your proxy URL on the main port instead, e.g.:
https://{host}/callback
Then update the same URI in your Spotify Dashboard. This avoids the need for manual URL editing below.

Step 1: Click the link below to authenticate with Spotify

{auth_url}


Step 2: After authorizing, you'll see a blank page. The URL will look like:

http://127.0.0.1:{callback_server_port}/callback?code=...

Step 3: Change 127.0.0.1 to {host} and press Enter:

http://{host}:{callback_server_port}/callback?code=...

Authentication will then complete!

''' else: return "

Spotify Authentication Failed

Could not initialize Spotify client. Check your credentials.

", 400 except Exception as e: logger.error(f"Error starting Spotify auth: {e}") return f"

Spotify Authentication Error

{str(e)}

", 500 @app.route('/auth/tidal') def auth_tidal(): """ Initiates Tidal OAuth authentication flow """ logger.info("TIDAL AUTH ROUTE CALLED ") try: # Create a fresh tidal client to get OAuth URL from core.tidal_client import TidalClient temp_tidal_client = TidalClient() if not temp_tidal_client.client_id: return "

Tidal Authentication Failed

Tidal client ID not configured. Check your credentials.

", 400 # Generate PKCE challenge and store globally temp_tidal_client._generate_pkce_challenge() # Store PKCE values globally for callback use global tidal_oauth_state with tidal_oauth_lock: tidal_oauth_state["code_verifier"] = temp_tidal_client.code_verifier tidal_oauth_state["code_challenge"] = temp_tidal_client.code_challenge # Use the user's configured redirect_uri from settings, falling back # to the constructor default (``http://127.0.0.1:/tidal/callback``). # The settings UI displays the default as the placeholder, and SoulSync's # docs tell users to register THAT URI with their Tidal Developer App # — Tidal validates the redirect_uri sent in the authorize request # against the one in the portal, so sending anything else (e.g. a # network-IP variant built from request.host) returns Tidal error 1002 # "Invalid redirect URI" and the user can't authenticate. # # Docker/remote-access workflow is preserved by the post-auth swap step # in the instructions page below: SoulSync sends ``127.0.0.1:``, # Tidal redirects the user's browser to that URI (which fails locally), # the instructions tell the user to swap ``127.0.0.1`` for the host # they're accessing SoulSync from, and the swapped URL hits the # container's exposed callback port. Building the URI from request.host # at authorize time used to skip the swap entirely but broke users # who registered the documented default. configured_redirect = config_manager.get('tidal.redirect_uri', '') if configured_redirect: temp_tidal_client.redirect_uri = configured_redirect logger.info(f"Using configured Tidal redirect_uri: {configured_redirect}") else: logger.info( f"Using default Tidal redirect_uri (no config override): " f"{temp_tidal_client.redirect_uri}" ) # Store PKCE + redirect_uri for callback to use the same values with tidal_oauth_lock: tidal_oauth_state["redirect_uri"] = temp_tidal_client.redirect_uri logger.info(f"Stored PKCE - verifier: {temp_tidal_client.code_verifier[:20]}... challenge: {temp_tidal_client.code_challenge[:20]}...") # Store profile_id for per-profile auth profile_id = request.args.get('profile_id', '') with tidal_oauth_lock: tidal_oauth_state["profile_id"] = profile_id if profile_id and profile_id != '1' else None # Create OAuth URL. # `collection.read` is required for the `userCollectionTracks` # endpoint that powers the virtual "Favorite Tracks" playlist # (issue #502). `prompt=consent` forces Tidal to display the # consent screen even when the app is already authorized — without # it, re-authenticating after a scope expansion can silently # return a token carrying only the ORIGINAL scope set because # Tidal treats the existing authorization as still valid. import urllib.parse params = { 'response_type': 'code', 'client_id': temp_tidal_client.client_id, 'redirect_uri': temp_tidal_client.redirect_uri, 'scope': 'user.read playlists.read collection.read', 'code_challenge': temp_tidal_client.code_challenge, 'code_challenge_method': 'S256', 'prompt': 'consent', } auth_url = f"{temp_tidal_client.auth_url}?" + urllib.parse.urlencode(params) logger.info(f"Generated Tidal OAuth URL: {auth_url}") logger.info(f"Redirect URI in URL: {params['redirect_uri']}") add_activity_item("", "Tidal Auth Started", "Please complete OAuth in browser", "Now") # Detect if accessing remotely (copied from Spotify auth logic) host = request.host.split(':')[0] is_remote = host not in ['127.0.0.1', 'localhost'] is_docker = os.path.exists('/.dockerenv') # If in Docker and accessing via 127.0.0.1, recommend localhost if is_docker and host == '127.0.0.1': host = 'localhost' if is_remote or is_docker: # Show instructions for remote/docker access page_title = "Tidal Authentication (Remote/Docker)" step_1_text = "Click the link below to authenticate with Tidal" # Pull the actual Tidal callback port from the same place the # OAuth URL was built. Using a hardcoded 8888 here used to # mislead users into saving Spotify's port into their Tidal # redirect URI, which then gave Tidal error 1002 (invalid # redirect URI) on every auth attempt. try: from urllib.parse import urlparse as _urlparse _parsed = _urlparse(temp_tidal_client.redirect_uri) tidal_port = _parsed.port or int( os.environ.get('SOULSYNC_TIDAL_CALLBACK_PORT', 8889) ) except Exception: tidal_port = int(os.environ.get('SOULSYNC_TIDAL_CALLBACK_PORT', 8889)) return f'''

{page_title}

Step 1: {step_1_text}

{auth_url}


Step 2: After authorizing, you'll see a blank page or an error. The URL will look like:

http://127.0.0.1:{tidal_port}/tidal/callback?code=...

Step 3: Change 127.0.0.1 to {host} and press Enter:

http://{host}:{tidal_port}/tidal/callback?code=...

Authentication will then complete!

''' else: return f'

Tidal Authentication

Please visit this URL to authenticate:

{auth_url}

After authentication, return to the app.

' except Exception as e: logger.error(f"Error starting Tidal auth: {e}") import traceback logger.error(f"Full traceback: {traceback.format_exc()}") return f"

Tidal Authentication Error

{str(e)}

", 500 def _spotify_auth_result_page(detail_text: str, authenticated: bool = True) -> str: """Return the post-auth page and notify the opener.""" title = "Spotify Authentication Successful" if authenticated else "Spotify Authentication Completed" heading = title close_script = """ setTimeout(() => window.close(), 300); """ if authenticated else """ const closeBtn = document.getElementById('close-window-btn'); if (closeBtn) { closeBtn.addEventListener('click', () => window.close()); } """ return f""" {title}

{heading}

{detail_text}

{'' if not authenticated else ''} """ @app.route('/callback') def spotify_callback(): """ Handles Spotify OAuth callback via the main Flask app (port 8008). This is the recommended callback for reverse proxy / Docker setups. The dedicated HTTPServer on port 8888 continues to work for direct/local access. """ global spotify_client auth_code = request.args.get('code') if not auth_code: error = request.args.get('error') if error: logger.error(f"Spotify OAuth error on port 8008: Spotify returned error: {error}") add_activity_item("", "Spotify Auth Failed", f"Spotify returned error: {error}", "Now") return f"

Spotify Authentication Failed

Spotify returned error: {error}

", 400 # No code AND no error — check if query params were stripped if request.args: logger.info(f"Spotify callback on port 8008 received unexpected params: {dict(request.args)}") else: # Completely empty — likely a healthcheck or spurious request pass return '', 204 logger.info("Spotify callback received on port 8008 with authorization code") # Check for per-profile state parameter state = request.args.get('state', '') profile_id_from_state = None if state and state.startswith('profile_'): try: profile_id_from_state = int(state.replace('profile_', '')) logger.info(f"Per-profile callback detected for profile {profile_id_from_state}") except ValueError: pass try: from core.spotify_client import SpotifyClient from spotipy.oauth2 import SpotifyOAuth from config.settings import config_manager # Per-profile callback: use profile's credentials if profile_id_from_state and profile_id_from_state != 1: db = get_database() creds = db.get_profile_spotify(profile_id_from_state) if creds and creds.get('client_id'): redirect_uri = creds.get('redirect_uri') or config_manager.get_spotify_config().get('redirect_uri', 'http://127.0.0.1:8888/callback') auth_manager = SpotifyOAuth( client_id=creds['client_id'], client_secret=creds['client_secret'], redirect_uri=redirect_uri, scope="user-library-read user-read-private playlist-read-private playlist-read-collaborative user-read-email user-follow-read", cache_path=f'config/.spotify_cache_profile_{profile_id_from_state}', state=f'profile_{profile_id_from_state}' ) token_info = auth_manager.get_access_token(auth_code) if token_info: metadata_registry.clear_cached_profile_spotify_client(profile_id_from_state) profile_client = metadata_registry.get_spotify_client_for_profile(profile_id_from_state) profile_authenticated = bool(profile_client and profile_client.is_spotify_authenticated()) if profile_authenticated: if profile_client: profile_client._invalidate_auth_cache() add_activity_item("", "Spotify Auth Complete", f"Profile {profile_id_from_state} authenticated with Spotify", "Now") return _spotify_auth_result_page("Your personal Spotify account is now connected. You can close this window.", authenticated=True) if profile_client: profile_client._invalidate_auth_cache() invalidate_metadata_status_caches() add_activity_item("", "Spotify Auth Warning", f"Profile {profile_id_from_state} completed OAuth but Spotify did not confirm an authenticated session", "Now") return _spotify_auth_result_page( "Spotify authorization completed, but SoulSync could not confirm an authenticated Spotify session for this profile. You can close this window and try Authenticate again.", authenticated=False, ) else: raise Exception("Failed to exchange authorization code for access token") # Global callback (admin) config = config_manager.get_spotify_config() configured_uri = config.get('redirect_uri', "http://127.0.0.1:8888/callback") logger.info(f"Using redirect_uri for token exchange: {configured_uri}") auth_manager = SpotifyOAuth( client_id=config['client_id'], client_secret=config['client_secret'], redirect_uri=configured_uri, scope="user-library-read user-read-private playlist-read-private playlist-read-collaborative user-read-email user-follow-read", cache_path='config/.spotify_cache' ) token_info = auth_manager.get_access_token(auth_code) if token_info: # CRITICAL: update the GLOBAL spotify_client, not a local variable global spotify_client clear_cached_metadata_client("spotify") spotify_client = get_spotify_client() if spotify_client.is_spotify_authenticated(): # Clear any active rate limit ban and post-ban cooldown # so Spotify is immediately usable after re-auth from core.spotify_client import _clear_rate_limit _clear_rate_limit() spotify_client._invalidate_auth_cache() # Invalidate status cache so next poll picks up the new connection invalidate_metadata_status_caches() # Refresh enrichment worker's client so it picks up new auth if spotify_enrichment_worker and hasattr(spotify_enrichment_worker, 'client'): spotify_enrichment_worker.client.reload_config() spotify_enrichment_worker.client._invalidate_auth_cache() add_activity_item("", "Spotify Auth Complete", "Successfully authenticated with Spotify", "Now") return _spotify_auth_result_page("You can close this window.", authenticated=True) else: logger.warning("Spotify OAuth token exchange succeeded but authentication validation failed") spotify_client._invalidate_auth_cache() invalidate_metadata_status_caches() add_activity_item("", "Spotify Auth Warning", "OAuth completed, but Spotify did not confirm an authenticated session", "Now") return _spotify_auth_result_page( "Spotify authorization completed, but SoulSync could not confirm an authenticated Spotify session. You can close this window and try Authenticate again.", authenticated=False, ) else: raise Exception("Failed to exchange authorization code for access token") except Exception as e: logger.error(f"Spotify OAuth callback error on port 8008: {e}") add_activity_item("", "Spotify Auth Failed", f"Token processing failed: {str(e)}", "Now") return f"

Spotify Authentication Failed

{str(e)}

", 400 @app.route('/api/spotify/disconnect', methods=['POST']) def spotify_disconnect(): """Disconnect Spotify and keep using the active primary metadata source.""" global spotify_client try: configured_source = config_manager.get('metadata.fallback_source', 'deezer') or 'deezer' # Pause enrichment worker before disconnecting to prevent it from hammering API if spotify_enrichment_worker: spotify_enrichment_worker.pause() spotify_client.disconnect() # Immediately update status cache so UI reflects the change active_source = get_spotify_disconnect_source(configured_source) source_label = get_metadata_source_label(active_source) if configured_source == 'spotify': config_manager.set('metadata.fallback_source', active_source) invalidate_metadata_status_caches() add_activity_item("", "Spotify Disconnected", f"Using {source_label} for metadata", "Now") return jsonify({ 'success': True, 'message': f'Spotify disconnected. Using {source_label} for metadata.', 'source': active_source, 'authenticated': False, 'primary_source_changed': configured_source == 'spotify' }) except Exception as e: logger.error(f"Error disconnecting Spotify: {e}") return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/spotify/rate-limit-status', methods=['GET']) def spotify_rate_limit_status(): """Get Spotify rate limit ban details""" try: info = get_spotify_status(spotify_client=spotify_client) rate_limit_info = info.get('rate_limit') if info: payload = { 'rate_limited': bool(info.get('rate_limited')), } if rate_limit_info: payload.update({ 'remaining_seconds': rate_limit_info.get('remaining_seconds', 0), 'retry_after': rate_limit_info.get('retry_after'), 'endpoint': rate_limit_info.get('endpoint'), 'expires_at': rate_limit_info.get('expires_at'), }) return jsonify(payload) return jsonify({'rate_limited': False}) except Exception as e: logger.error(f"Error getting Spotify rate limit status: {e}") return jsonify({'error': str(e)}), 500 @app.route('/tidal/callback') def tidal_callback(): """ Handles the callback from Tidal after the user authorizes the application. It receives an authorization code, exchanges it for an access token, and saves the token. """ global tidal_client # We will re-initialize the global client auth_code = request.args.get('code') if not auth_code: error = request.args.get('error', 'Unknown error') error_description = request.args.get('error_description', 'No description provided.') return f"

Tidal Authentication Failed

Error: {error}

{error_description}

Please close this window and try again.

", 400 try: # Create a temporary client for the token exchange temp_tidal_client = TidalClient() # Restore PKCE values, redirect_uri, and profile_id from the auth request profile_id_for_tidal = None with tidal_oauth_lock: temp_tidal_client.code_verifier = tidal_oauth_state["code_verifier"] temp_tidal_client.code_challenge = tidal_oauth_state["code_challenge"] if "redirect_uri" in tidal_oauth_state: temp_tidal_client.redirect_uri = tidal_oauth_state["redirect_uri"] profile_id_for_tidal = tidal_oauth_state.get("profile_id") success = temp_tidal_client.fetch_token_from_code(auth_code) if success: # Per-profile: store tokens on profile, don't touch global client if profile_id_for_tidal: try: profile_id_int = int(profile_id_for_tidal) db = get_database() # Store Tidal tokens on the profile from config.settings import config_manager as _cm enc_access = _cm._encrypt_value(temp_tidal_client.access_token) if temp_tidal_client.access_token else None enc_refresh = _cm._encrypt_value(temp_tidal_client.refresh_token) if temp_tidal_client.refresh_token else None with db._get_connection() as conn: cursor = conn.cursor() cursor.execute(""" UPDATE profiles SET tidal_access_token = ?, tidal_refresh_token = ?, updated_at = CURRENT_TIMESTAMP WHERE id = ? """, (enc_access, enc_refresh, profile_id_int)) conn.commit() add_activity_item("", "Tidal Auth Complete", f"Profile {profile_id_int} authenticated with Tidal", "Now") return "

Tidal Authentication Successful!

Your personal Tidal account is now connected. You can close this window.

" except Exception as profile_err: logger.error(f"Per-profile Tidal auth failed, falling back to global: {profile_err}") # Global: Re-initialize the main global tidal_client instance with the new token tidal_client = TidalClient() if tidal_enrichment_worker: tidal_enrichment_worker.client = tidal_client return "

Tidal Authentication Successful!

You can now close this window and return to the SoulSync application.

" else: return "

Tidal Authentication Failed

Could not exchange authorization code for a token. Please try again.

", 400 except Exception as e: logger.error(f"Error during Tidal token exchange: {e}") return f"

An Error Occurred

An unexpected error occurred during the authentication process: {e}

", 500 # --- Deezer OAuth --- @app.route('/auth/deezer') def auth_deezer(): """Initialize Deezer OAuth flow. Redirects user to Deezer authorization page.""" try: app_id = config_manager.get('deezer.app_id', '') redirect_uri = config_manager.get('deezer.redirect_uri', 'http://127.0.0.1:8008/deezer/callback') if not app_id: return "

Deezer App ID not configured

Go to Settings → Connections and enter your Deezer App ID first.

", 400 perms = 'basic_access,email,offline_access,manage_library,listening_history' import urllib.parse auth_url = f"https://connect.deezer.com/oauth/auth.php?app_id={app_id}&redirect_uri={urllib.parse.quote(redirect_uri)}&perms={perms}" host = request.host.split(':')[0] return f"""

Deezer Authorization

Click the link below to authorize SoulSync with your Deezer account:

Authorize on Deezer →


If running remotely, replace 127.0.0.1 in the redirect URI with {host}

""" except Exception as e: return f"

Error

{e}

", 500 @app.route('/deezer/callback') def deezer_callback(): """Handle Deezer OAuth callback — exchange code for access token.""" auth_code = request.args.get('code') error_reason = request.args.get('error_reason', '') if not auth_code: return f"

Deezer Authentication Failed

{error_reason or 'No authorization code received.'}

", 400 try: app_id = config_manager.get('deezer.app_id', '') app_secret = config_manager.get('deezer.app_secret', '') if not app_id or not app_secret: return "

Missing Credentials

Deezer App ID or Secret not configured.

", 400 # Exchange code for token — simple GET request (Deezer's unique approach) token_url = f"https://connect.deezer.com/oauth/access_token.php?app_id={app_id}&secret={app_secret}&code={auth_code}" resp = requests.get(token_url, timeout=15) if resp.status_code != 200: return f"

Token Exchange Failed

Deezer returned status {resp.status_code}

", 400 # Deezer returns: access_token=TOKEN&expires=SECONDS (URL-encoded, not JSON) import urllib.parse token_data = dict(urllib.parse.parse_qsl(resp.text)) access_token = token_data.get('access_token') if not access_token: # Try JSON format (some Deezer API versions) try: json_data = resp.json() access_token = json_data.get('access_token') except Exception as e: logger.debug("deezer token json parse failed: %s", e) if not access_token: return f"

No Access Token

Deezer response: {resp.text[:200]}

", 400 # Save token to config (encrypted at rest) config_manager.set('deezer.access_token', access_token) # Reload the global deezer client to pick up the token deezer_client = _get_deezer_client() deezer_client.reload_config() add_activity_item("", "Deezer Auth Complete", "Deezer account connected via OAuth", "Now") logger.info("Deezer OAuth authentication successful") return """

Deezer Authentication Successful!

Your Deezer account is now connected. You can close this window.

""" except Exception as e: logger.error(f"Deezer OAuth callback error: {e}") return f"

Error

{e}

", 500 # --- Beatport Data API --- @app.route('/api/beatport/hero-tracks') def get_beatport_hero_tracks(): """Get fresh tracks from Beatport hero slideshow for the rebuild slider""" try: logger.info("Fetching Beatport hero tracks...") # Check cache first cached_data = get_cached_beatport_data('homepage', 'hero_tracks') if cached_data: logger.info("Returning cached hero tracks data") response = jsonify(cached_data) return add_cache_headers(response, 3600) # 1 hour # Cache miss - scrape fresh data logger.info("Cache miss - scraping fresh hero tracks data...") # Initialize scraper scraper = BeatportUnifiedScraper() # Get tracks from hero slideshow (increased limit to capture all slides) tracks = scraper.scrape_new_on_beatport_hero(limit=15) # SMART FILTERING - Remove duplicates and invalid tracks valid_tracks = [] seen_urls = set() filtered_reasons = collections.Counter() for _i, track in enumerate(tracks): # Extract and clean basic data title = track.get('title', '').strip() artist = track.get('artist', '').strip() url = track.get('url', '').strip() image_url = track.get('image_url', '').strip() # Apply text cleaning for proper spacing if title: title = clean_beatport_text(title) if artist: artist = clean_beatport_text(artist) # Validation filters is_valid = True skip_reasons = [] # Filter 1: Must have title (artist can be fallback) if not title or title in ['No title', 'MISSING', 'Unknown Title']: is_valid = False skip_reasons.append("Missing/invalid title") # If no artist, use fallback based on URL or default if not artist or artist in ['No artist', 'MISSING', 'Unknown Artist', 'NO_ARTIST']: if url and '/release/' in url: artist = 'Various Artists' # Release pages often have multiple artists else: artist = 'Unknown Artist' # Filter 2: Must have valid URL and image if not url or not image_url: is_valid = False skip_reasons.append("Missing URL or image") # Filter 3: URL must be a track/release page (not promotional pages) if url and not any(pattern in url for pattern in ['/release/', '/track/']): is_valid = False skip_reasons.append("URL is not a track/release page") # Filter 4: Deduplication by URL (most reliable method) if url in seen_urls: is_valid = False skip_reasons.append("Duplicate URL") if not is_valid: filtered_reasons.update(skip_reasons) continue # Mark URL as seen for deduplication seen_urls.add(url) # Clean up title title = title.replace(" t ", "'t ").replace("(Extended)DJ", "(Extended)") # Clean up artist names if 'SyrossianHappy' in artist: artist = 'Darius Syrossian' if 'Carroll,' in artist: artist = 'Ron Carroll' if artist.endswith('DJ') and ' ' not in artist[-4:]: artist = artist[:-2].strip() # Create clean track data track_data = { 'title': title, 'artist': artist, 'url': url, 'image_url': image_url, 'genre': 'Electronic', # Default genre 'year': datetime.now().year } # Determine genre based on artist genre_mapping = { 'thakzin': 'Afro House', 'yaya': 'Tech House', 'darius syrossian': 'Techno', 'ron carroll': 'House', 'dj minx': 'House', 'durante': 'Progressive House' } for artist_key, mapped_genre in genre_mapping.items(): if artist_key in artist.lower(): track_data['genre'] = mapped_genre break valid_tracks.append(track_data) sample_titles = [f"{t['title']} - {t['artist']}" for t in valid_tracks[:3]] logger.debug( "Beatport smart filter summary: raw=%s valid=%s filtered=%s reasons=%s sample=%s", len(tracks), len(valid_tracks), len(tracks) - len(valid_tracks), dict(filtered_reasons), sample_titles, ) logger.info(f"Retrieved {len(valid_tracks)} valid unique Beatport tracks (SMART FILTERING)") # Prepare response data response_data = { 'success': True, 'tracks': valid_tracks, 'count': len(valid_tracks), 'timestamp': datetime.now().isoformat() } # Cache the successful response set_cached_beatport_data('homepage', 'hero_tracks', response_data) response = jsonify(response_data) return add_cache_headers(response, 3600) # 1 hour except Exception as e: logger.error(f"Error fetching Beatport tracks: {str(e)}") return jsonify({ 'success': False, 'error': str(e), 'tracks': [] }), 500 @app.route('/api/beatport/new-releases') def get_beatport_new_releases(): """Get new releases from Beatport for the rebuild slider grid""" try: logger.info("🆕 Fetching Beatport new releases...") # Check cache first cached_data = get_cached_beatport_data('homepage', 'new_releases') if cached_data: logger.info("🆕 Returning cached new releases data") response = jsonify(cached_data) return add_cache_headers(response, 3600) # 1 hour # Cache miss - scrape fresh data logger.info("Cache miss - scraping fresh new releases data...") # Initialize scraper scraper = BeatportUnifiedScraper() # Get page and extract releases soup = scraper.get_page(scraper.base_url) if not soup: raise Exception("Could not fetch Beatport homepage") # Find New Releases GridSlider container by section heading # Use partial class match to avoid brittle hashed class names gridsliders = soup.select('[class*="GridSlider-style__Wrapper"]') releases_container = None for container in gridsliders: h2 = container.select_one('h2') if h2: title = h2.get_text(strip=True).lower() if 'new release' in title: releases_container = container logger.info(f"🆕 FOUND NEW RELEASES: '{h2.get_text(strip=True)}'") break # Fallback: try ReleaseCard partial class match on whole page if releases_container: release_cards = releases_container.select('[class*="ReleaseCard-style__Wrapper"]') else: logger.warning("No New Releases GridSlider found, trying page-wide ReleaseCard search") release_cards = soup.select('[class*="ReleaseCard-style__Wrapper"]') releases = [] logger.info(f"Found {len(release_cards)} release cards") for _i, card in enumerate(release_cards[:100]): # Limit to 100 for 10 slides release_data = {} # Extract title from Meta section title_elem = card.select_one('[class*="ReleaseCard-style__Meta"] a[href*="/release/"]') if not title_elem: title_elem = card.select_one('[class*="title"], [class*="Title"], h3, h4, h5, h6') if title_elem: title_text = title_elem.get_text(strip=True) if title_text and len(title_text) > 2 and title_text not in ['New Releases', 'Buy', 'Play']: release_data['title'] = title_text # Extract artist artist_elem = card.select_one('a[href*="/artist/"]') if artist_elem: artist_text = artist_elem.get_text(strip=True) if artist_text and len(artist_text) > 1: release_data['artist'] = artist_text # Extract label label_elem = card.select_one('a[href*="/label/"]') if label_elem: label_text = label_elem.get_text(strip=True) if label_text and len(label_text) > 1: release_data['label'] = label_text # Extract URL url_link = card.select_one('a[href*="/release/"]') if url_link: href = url_link.get('href') if href: release_data['url'] = urljoin(scraper.base_url, href) # Extract image img = card.select_one('img') if img: src = img.get('src') or img.get('data-src') or img.get('data-lazy-src') if src: release_data['image_url'] = src # URL fallback for title if not release_data.get('title') and release_data.get('url'): url_parts = release_data['url'].split('/release/') if len(url_parts) > 1: slug = url_parts[1].split('/')[0] release_data['title'] = slug.replace('-', ' ').title() # Only add if we have essential data if release_data.get('title') and release_data.get('url'): # Add fallbacks for missing data if not release_data.get('artist'): release_data['artist'] = 'Various Artists' if not release_data.get('label'): release_data['label'] = 'Unknown Label' releases.append(release_data) logger.info(f"Successfully extracted {len(releases)} new releases") # Prepare response data response_data = { 'success': True, 'releases': releases, 'count': len(releases), 'slides': (len(releases) + 9) // 10, # Calculate number of slides needed 'timestamp': datetime.now().isoformat() } # Cache the successful response set_cached_beatport_data('homepage', 'new_releases', response_data) response = jsonify(response_data) return add_cache_headers(response, 3600) # 1 hour except Exception as e: logger.error(f"Error fetching new releases: {str(e)}") return jsonify({ 'success': False, 'error': str(e), 'releases': [] }), 500 @app.route('/api/beatport/featured-charts') def get_beatport_featured_charts(): """Get featured charts from Beatport for the charts slider grid using GridSlider approach""" try: logger.info("Fetching Beatport featured charts...") # Check cache first cached_data = get_cached_beatport_data('homepage', 'featured_charts') if cached_data: logger.info("Returning cached featured charts data") response = jsonify(cached_data) return add_cache_headers(response, 3600) # 1 hour # Cache miss - scrape fresh data logger.info("Cache miss - scraping fresh featured charts data...") # Initialize scraper scraper = BeatportUnifiedScraper() # Get page and extract charts soup = scraper.get_page(scraper.base_url) if not soup: raise Exception("Could not fetch Beatport homepage") # Find Featured Charts GridSlider container (like New Releases) gridsliders = soup.select('[class*="GridSlider-style__Wrapper"]') featured_container = None logger.debug(f"Checking {len(gridsliders)} GridSlider containers for featured charts...") for container in gridsliders: h2 = container.select_one('h2') if h2: title = h2.get_text(strip=True).lower() logger.debug(f"Found section: '{h2.get_text(strip=True)}'") if 'featured' in title and 'chart' in title: featured_container = container logger.debug(f"FOUND FEATURED CHARTS: '{h2.get_text(strip=True)}'") break if not featured_container: logger.warning("No Featured Charts GridSlider container found") return jsonify({ 'success': False, 'error': 'Featured Charts section not found', 'charts': [] }) # Extract charts from the container using chart links charts = [] chart_links = featured_container.select('a[href*="/chart/"]') logger.debug(f"Found {len(chart_links)} chart links in Featured Charts section") for _i, link in enumerate(chart_links[:100]): # Limit to 100 for 10 slides chart_data = {} # Extract chart name from link text or nearby elements name_elem = link.select_one('h3, h4, h5, h6, [class*="title"], [class*="Title"], [class*="name"], [class*="Name"]') if name_elem: name_text = name_elem.get_text(strip=True) else: name_text = link.get_text(strip=True) if name_text and len(name_text) > 2 and name_text.lower() not in ['featured charts', 'buy', 'play']: chart_data['name'] = name_text # Extract creator using the specific CSS class pattern from chart cards creator = 'Beatport' # Default # Look for the ChartCard Name class that contains the creator creator_elem = link.select_one('[class*="ChartCard-style__Name"]') if creator_elem: creator_text = creator_elem.get_text(strip=True) if creator_text and len(creator_text) > 1 and creator_text.lower() not in ['by', 'chart', 'featured', 'beatport']: creator = creator_text elif creator_text.lower() == 'beatport': creator = 'Beatport' else: # Fallback: look for other creator indicators parent = link.parent if parent: fallback_selectors = [ '[class*="artist"]', '[class*="Artist"]', '[class*="creator"]', '[class*="Creator"]', '[class*="author"]', '[class*="Author"]' ] for selector in fallback_selectors: fallback_elem = parent.select_one(selector) if fallback_elem: fallback_text = fallback_elem.get_text(strip=True) if fallback_text and len(fallback_text) > 1 and fallback_text.lower() not in ['by', 'chart', 'featured']: creator = fallback_text break chart_data['creator'] = creator # Extract URL href = link.get('href', '') if href: if href.startswith('/'): chart_data['url'] = f"https://www.beatport.com{href}" else: chart_data['url'] = href # Extract image img_elem = link.select_one('img') or (link.parent.select_one('img') if link.parent else None) if img_elem: src = img_elem.get('src', '') or img_elem.get('data-src', '') if src: if src.startswith('//'): src = f"https:{src}" elif src.startswith('/'): src = f"https://www.beatport.com{src}" chart_data['image'] = src # Only add if we have meaningful data if 'name' in chart_data and 'url' in chart_data: charts.append(chart_data) logger.debug(f"Chart {len(charts)}: {chart_data['name']} by {chart_data['creator']}") logger.info(f"Successfully extracted {len(charts)} featured charts") # Prepare response data response_data = { 'success': True, 'charts': charts, 'count': len(charts), 'slides': (len(charts) + 9) // 10, # Calculate number of slides needed 'timestamp': datetime.now().isoformat() } # Cache the successful response set_cached_beatport_data('homepage', 'featured_charts', response_data) response = jsonify(response_data) return add_cache_headers(response, 3600) # 1 hour except Exception as e: logger.error(f"Error fetching featured charts: {str(e)}") return jsonify({ 'success': False, 'error': str(e), 'charts': [] }), 500 @app.route('/api/beatport/dj-charts') def get_beatport_dj_charts(): """Get DJ charts from Beatport for the DJ charts slider using Carousel approach""" try: logger.info("Fetching Beatport DJ charts...") # Check cache first cached_data = get_cached_beatport_data('homepage', 'dj_charts') if cached_data: logger.info("Returning cached DJ charts data") response = jsonify(cached_data) return add_cache_headers(response, 3600) # 1 hour # Cache miss - scrape fresh data logger.info("Cache miss - scraping fresh DJ charts data...") # Initialize scraper scraper = BeatportUnifiedScraper() # Get page and extract charts soup = scraper.get_page(scraper.base_url) if not soup: raise Exception("Could not fetch Beatport homepage") # Find all Carousel containers carousels = soup.select('[class*="Carousel-style__Wrapper"]') dj_container = None logger.debug(f"Checking {len(carousels)} Carousel containers for DJ charts...") # Based on test results, DJ charts are in the second carousel (index 1) with ~9 chart links for i, container in enumerate(carousels): chart_links = container.select('a[href*="/chart/"]') logger.debug(f"Carousel {i+1}: {len(chart_links)} chart links") # DJ charts container typically has 8-12 chart links (not 99+ like featured charts) if 5 <= len(chart_links) <= 15: dj_container = container logger.info(f"FOUND DJ CHARTS: Carousel {i+1} with {len(chart_links)} charts") break if not dj_container: logger.warning("No DJ Charts Carousel container found") return jsonify({ 'success': False, 'error': 'DJ Charts section not found', 'charts': [] }) # Extract charts from the container using chart links charts = [] chart_links = dj_container.select('a[href*="/chart/"]') logger.info(f"Found {len(chart_links)} DJ chart links") for _i, link in enumerate(chart_links): chart_data = {} # Extract chart name from link text or nearby elements name_elem = link.select_one('h3, h4, h5, h6, [class*="title"], [class*="Title"], [class*="name"], [class*="Name"]') if name_elem: name_text = name_elem.get_text(strip=True) else: name_text = link.get_text(strip=True) if name_text and len(name_text) > 2: chart_data['name'] = name_text # Extract creator - for DJ charts, the chart name might be the artist name creator = name_text # Use chart name as creator for DJ charts # Look for additional creator info in parent elements parent = link.parent if parent: creator_selectors = [ '[class*="artist"]', '[class*="Artist"]', '[class*="creator"]', '[class*="Creator"]', '[class*="author"]', '[class*="Author"]' ] for selector in creator_selectors: creator_elem = parent.select_one(selector) if creator_elem: creator_text = creator_elem.get_text(strip=True) if creator_text and len(creator_text) > 1 and creator_text != name_text: creator = creator_text break chart_data['creator'] = creator # Extract URL href = link.get('href', '') if href: if href.startswith('/'): chart_data['url'] = f"https://www.beatport.com{href}" else: chart_data['url'] = href # Extract image img_elem = link.select_one('img') or (link.parent.select_one('img') if link.parent else None) if img_elem: src = img_elem.get('src', '') or img_elem.get('data-src', '') if src: if src.startswith('//'): src = f"https:{src}" elif src.startswith('/'): src = f"https://www.beatport.com{src}" chart_data['image'] = src # Only add if we have meaningful data if 'name' in chart_data and 'url' in chart_data: charts.append(chart_data) logger.info(f"DJ Chart {len(charts)}: {chart_data['name']} by {chart_data['creator']}") logger.info(f"Successfully extracted {len(charts)} DJ charts") # Prepare response data response_data = { 'success': True, 'charts': charts, 'count': len(charts), 'slides': max(1, (len(charts) + 2) // 3), # 3 cards per slide 'timestamp': datetime.now().isoformat() } # Cache the successful response set_cached_beatport_data('homepage', 'dj_charts', response_data) response = jsonify(response_data) return add_cache_headers(response, 3600) # 1 hour except Exception as e: logger.error(f"Error fetching DJ charts: {str(e)}") return jsonify({ 'success': False, 'error': str(e), 'charts': [] }), 500 # --- Placeholder API Endpoints for Other Pages --- @app.route('/api/activity') def get_activity(): # Placeholder: returns mock activity data mock_activity = [ {"time": "1 min ago", "text": "Service status checked."}, {"time": "5 min ago", "text": "Application server started."} ] return jsonify({"activities": mock_activity}) @app.route('/api/playlists') def get_playlists(): # Placeholder: returns mock playlist data if spotify_client and spotify_client.is_authenticated(): # In a real implementation, you would call spotify_client.get_user_playlists() mock_playlists = [ {"id": "1", "name": "Chill Vibes"}, {"id": "2", "name": "Workout Mix"}, {"id": "3", "name": "Liked Songs"} ] return jsonify({"playlists": mock_playlists}) return jsonify({"playlists": [], "error": "Spotify not authenticated."}) @app.route('/api/sync', methods=['POST']) def start_sync(): # Placeholder: simulates starting a sync return jsonify({"success": True, "message": "Sync process started."}) # Search route bodies live in core/search/* — these routes are thin handlers. from core.search import basic as _search_basic from core.search import library_check as _search_library_check from core.search import orchestrator as _search_orchestrator from core.search import stream as _search_stream def _build_search_deps(): """Build the SearchDeps bundle from this module's globals on each request. Constructed per-request so config / client state is always live. """ return _search_orchestrator.SearchDeps( database=get_database(), config_manager=config_manager, spotify_client=spotify_client, hydrabase_client=hydrabase_client, hydrabase_worker=hydrabase_worker, download_orchestrator=download_orchestrator, fix_artist_image_url=fix_artist_image_url, is_hydrabase_active=_is_hydrabase_active, get_metadata_fallback_source=_get_metadata_fallback_source, get_metadata_fallback_client=_get_metadata_fallback_client, get_itunes_client=_get_itunes_client, get_deezer_client=_get_deezer_client, get_discogs_client=_get_discogs_client, run_background_comparison=_run_background_comparison, run_async=run_async, dev_mode_enabled_provider=lambda: dev_mode_enabled, ) @app.route('/api/search', methods=['POST']) def search_music(): """Basic Soulseek file search.""" data = request.get_json() query = data.get('query') if not query: return jsonify({"error": "No search query provided."}), 400 logger.info(f"Web UI Search initiated for: '{query}'") add_activity_item("", "Search Started", f"'{query}'", "Now") try: results = _search_basic.run_basic_soulseek_search(query, download_orchestrator, run_async) add_activity_item("", "Search Complete", f"'{query}' - {len(results)} results", "Now") return jsonify({"results": results}) except Exception as e: logger.error(f"Search error: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/enhanced-search', methods=['POST']) def enhanced_search(): """Unified metadata search across configured sources + local DB artists. Optional `source` body param ("spotify"|"itunes"|"deezer"|"discogs"| "hydrabase"|"musicbrainz"|"auto"|"") forces a single-source search and bypasses the fan-out. Otherwise picks a primary source per the user's configuration and lists alternates for the frontend to fetch async. """ data = request.get_json() query = data.get('query', '').strip() requested_source = (data.get('source') or '').strip().lower() if requested_source == 'auto': requested_source = '' if requested_source and requested_source not in ENHANCED_SEARCH_VALID_SOURCES: return jsonify({"error": f"Unknown source: {requested_source}"}), 400 if not query: return jsonify(_search_orchestrator.empty_response()) cache_key = _get_enhanced_search_cache_key(query, requested_source) cached = _get_cached_enhanced_search_response(cache_key) if cached is not None: logger.info(f"Enhanced search cache hit for: '{query}'") return jsonify(cached) logger.info(f"Enhanced search initiated for: '{query}' (source={requested_source or 'auto'})") try: deps = _build_search_deps() response_data = _search_orchestrator.run_enhanced_search(query, requested_source, deps) _set_cached_enhanced_search_response(cache_key, response_data) return jsonify(response_data) except Exception as e: logger.error(f"Enhanced search error: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/enhanced-search/source/', methods=['POST']) def enhanced_search_source(source_name): """Streaming NDJSON search for one alternate metadata source. One line per search-kind (artists, albums, tracks) as it completes, plus a final `{"type":"done"}` marker. `youtube_videos` yields a single `videos` chunk via yt-dlp instead. When the requested source's client isn't available (Spotify unauthed, Discogs missing token, Hydrabase disconnected, MusicBrainz import failure, download_orchestrator.client("youtube") missing), returns plain JSON `{"artists":[],"albums":[],"tracks":[],"available":false}` to match the original endpoint contract. """ if source_name not in _search_orchestrator.VALID_STREAM_SOURCES: return jsonify({"error": f"Unknown source: {source_name}"}), 400 data = request.get_json() query = (data.get('query', '') if data else '').strip() if not query: return jsonify({"artists": [], "albums": [], "tracks": [], "available": False}) deps = _build_search_deps() if source_name == 'youtube_videos': youtube_client = _search_orchestrator.resolve_youtube_videos_client(deps) if youtube_client is None: return jsonify({"videos": [], "available": False}) try: return app.response_class( _search_orchestrator.stream_youtube_videos(query, youtube_client, run_async), mimetype='application/x-ndjson', ) except Exception as e: return jsonify({"error": str(e)}), 500 try: client, _available = _search_orchestrator.resolve_client(source_name, deps) if client is None: return jsonify({"artists": [], "albums": [], "tracks": [], "available": False}) return app.response_class( _search_orchestrator.stream_metadata_source(source_name, query, client), mimetype='application/x-ndjson', ) except Exception as e: logger.error(f"Enhanced search source ({source_name}) error: {e}") return jsonify({"artists": [], "albums": [], "tracks": [], "available": False}) @app.route('/api/enhanced-search/library-check', methods=['POST']) def enhanced_search_library_check(): """Batch-check which albums/tracks from search results are already in the library. Called async after search renders so badges fade in without blocking results. """ try: data = request.get_json() or {} result = _search_library_check.check_library_presence( database=get_database(), plex_client=media_server_engine.client('plex') if media_server_engine else None, config_manager=config_manager, profile_id=get_current_profile_id(), albums=data.get('albums', []), tracks=data.get('tracks', []), ) return jsonify(result) except Exception as e: logger.debug(f"Library check error: {e}") return jsonify({'albums': [], 'tracks': []}) @app.route('/api/enhanced-search/stream-track', methods=['POST']) def stream_enhanced_search_track(): """Single-track preview search — finds the best Soulseek/stream-source match. Uses a multi-query retry strategy to work around Soulseek keyword filtering. """ data = request.get_json() track_name = data.get('track_name', '').strip() artist_name = data.get('artist_name', '').strip() album_name = data.get('album_name', '').strip() duration_ms = data.get('duration_ms', 0) if not track_name or not artist_name: return jsonify({"error": "Track name and artist name are required"}), 400 logger.info(f"Enhanced search stream request: '{track_name}' by '{artist_name}'") try: result = _search_stream.stream_search_track( track_name=track_name, artist_name=artist_name, album_name=album_name, duration_ms=duration_ms, config_manager=config_manager, download_orchestrator=download_orchestrator, matching_engine=matching_engine, run_async=run_async, ) if result is None: return jsonify({ "success": False, "error": "No suitable track found after trying multiple search strategies", }), 404 return jsonify({"success": True, "result": result}) except Exception as e: logger.error(f"Error streaming enhanced search track: {e}", exc_info=True) return jsonify({"error": str(e)}), 500 # ============================================================================= # MUSIC VIDEO DOWNLOADS # ============================================================================= _music_video_downloads = {} # {video_id: {status, progress, path, error}} @app.route('/api/music-video/download', methods=['POST']) def download_music_video(): """Download a YouTube video as a music video file to the configured music videos folder.""" data = request.get_json() if not data: return jsonify({"error": "No data"}), 400 video_id = data.get('video_id', '') video_url = data.get('url', '') raw_title = data.get('title', '') raw_channel = data.get('channel', '') if not video_id or not video_url: return jsonify({"error": "Missing video_id or url"}), 400 # Check if already downloading if video_id in _music_video_downloads and _music_video_downloads[video_id].get('status') == 'downloading': return jsonify({"error": "Already downloading"}), 409 # Get and validate music videos path music_videos_path = config_manager.get('library.music_videos_path', '') or '' if not music_videos_path.strip(): return jsonify({"error": "Music Videos directory not configured. Set it in Settings > Downloads."}), 400 music_videos_path = docker_resolve_path(music_videos_path) try: os.makedirs(music_videos_path, exist_ok=True) # Quick write test test_file = os.path.join(music_videos_path, '.soulsync_write_test') with open(test_file, 'w') as f: f.write('test') os.remove(test_file) except (OSError, PermissionError) as e: return jsonify({"error": f"Music Videos directory is not writable: {e}"}), 400 # Initialize download state _music_video_downloads[video_id] = {'status': 'searching', 'progress': 0, 'path': None, 'error': None} def _do_download(): try: # Step 1: Try to match against primary metadata source for clean artist/title _music_video_downloads[video_id]['status'] = 'matching' artist_name = raw_channel track_title = raw_title year = '' # Strip common YouTube suffixes for cleaner search import re as _re clean_search = _re.sub(r'\s*[\(\[](official\s*(music\s*)?video|official\s*lyric\s*video|official\s*audio|official\s*hd|hd|4k|remastered|lyric\s*video|visualizer|audio)[\)\]]', '', raw_title, flags=_re.IGNORECASE).strip() clean_search = _re.sub(r'\s*-\s*$', '', clean_search).strip() try: fallback_client = _get_metadata_fallback_client() results = fallback_client.search_tracks(clean_search, limit=5) if results: from difflib import SequenceMatcher best = None best_score = 0 for r in results: name_sim = SequenceMatcher(None, clean_search.lower(), r.name.lower()).ratio() if r.artists: artist_sim = SequenceMatcher(None, raw_channel.lower(), r.artists[0].lower()).ratio() name_sim = (name_sim * 0.6) + (artist_sim * 0.4) if name_sim > best_score: best_score = name_sim best = r if best and best_score >= 0.5: artist_name = best.artists[0] if best.artists else raw_channel track_title = best.name if hasattr(best, 'release_date') and best.release_date: year = str(best.release_date)[:4] logger.info(f"[Music Video] Matched to: {artist_name} - {track_title} (confidence: {best_score:.2f})") else: # Parse artist from video title: "Artist - Title" pattern if ' - ' in raw_title: parts = raw_title.split(' - ', 1) artist_name = parts[0].strip() track_title = _re.sub(r'\s*[\(\[].*?[\)\]]', '', parts[1]).strip() logger.warning(f"[Music Video] No metadata match, using parsed: {artist_name} - {track_title}") except Exception as e: logger.error(f"[Music Video] Metadata lookup failed: {e}") if ' - ' in raw_title: parts = raw_title.split(' - ', 1) artist_name = parts[0].strip() track_title = _re.sub(r'\s*[\(\[].*?[\)\]]', '', parts[1]).strip() # Sanitize for filesystem def _sanitize(s): return _re.sub(r'[<>:"/\\|?*]', '_', s).strip().rstrip('.') # Apply video path template video_template = config_manager.get('file_organization.templates', {}).get('video_path', '$artist/$title-video') if not video_template or not video_template.strip(): video_template = '$artist/$title-video' safe_artist = _sanitize(artist_name) video_path = video_template video_path = video_path.replace('$artistletter', safe_artist[0].upper() if safe_artist else 'A') video_path = video_path.replace('$artist', safe_artist) video_path = video_path.replace('$title', _sanitize(track_title)) video_path = video_path.replace('$year', str(year) if year else '') # Clean up empty segments from missing variables video_path = _re.sub(r'//+', '/', video_path).strip('/') # Split into folder and filename path_parts = video_path.rsplit('/', 1) if len(path_parts) == 2: folder_part, file_part = path_parts else: folder_part, file_part = '', path_parts[0] output_dir = os.path.join(music_videos_path, folder_part) if folder_part else music_videos_path os.makedirs(output_dir, exist_ok=True) output_path = os.path.join(output_dir, file_part) # Step 2: Download _music_video_downloads[video_id]['status'] = 'downloading' _music_video_downloads[video_id]['artist'] = artist_name _music_video_downloads[video_id]['title'] = track_title def _progress(pct): _music_video_downloads[video_id]['progress'] = round(pct, 1) final_path = download_orchestrator.client("youtube").download_music_video(video_url, output_path, progress_callback=_progress) if final_path and os.path.exists(final_path): _music_video_downloads[video_id]['status'] = 'completed' _music_video_downloads[video_id]['progress'] = 100 _music_video_downloads[video_id]['path'] = final_path logger.info(f"[Music Video] Downloaded: {artist_name} - {track_title} → {final_path}") add_activity_item("", "Music Video Downloaded", f"{artist_name} - {track_title}", "Now") else: _music_video_downloads[video_id]['status'] = 'error' _music_video_downloads[video_id]['error'] = 'Download failed — file not found' logger.error(f"[Music Video] Download failed for: {artist_name} - {track_title}") except Exception as e: _music_video_downloads[video_id]['status'] = 'error' _music_video_downloads[video_id]['error'] = str(e) logger.error(f"[Music Video] {e}") # Run in background thread import threading threading.Thread(target=_do_download, daemon=True, name=f'music-video-{video_id}').start() return jsonify({"success": True, "video_id": video_id}) @app.route('/api/music-video/status/', methods=['GET']) def get_music_video_status(video_id): """Get download status for a music video.""" status = _music_video_downloads.get(video_id) if not status: return jsonify({"status": "unknown"}) return jsonify(status) @app.route('/api/download', methods=['POST']) def start_download(): """Simple download route""" dl_err = check_download_permission() if dl_err: return dl_err data = request.get_json() if not data: return jsonify({"error": "No download data provided."}), 400 try: result_type = data.get('result_type', 'track') if result_type == 'album': tracks = data.get('tracks', []) if not tracks: return jsonify({"error": "No tracks found in album."}), 400 started_downloads = 0 for track_data in tracks: try: username = track_data.get('username') filename = track_data.get('filename') file_size = track_data.get('size', 0) download_id = run_async(download_orchestrator.download( username, filename, file_size )) if download_id: # Register download for post-processing (simple transfer to /Transfer) context_key = _make_context_key(username, filename) with matched_context_lock: matched_downloads_context[context_key] = { 'search_result': { 'username': username, 'filename': filename, 'size': file_size, 'title': track_data.get('title', 'Unknown'), 'artist': track_data.get('artist', 'Unknown'), 'quality': track_data.get('quality', 'Unknown'), 'is_simple_download': True # Flag for simple processing }, 'spotify_artist': None, # No Spotify metadata 'spotify_album': None, 'track_info': None } started_downloads += 1 except Exception as e: logger.error(f"Failed to start track download: {e}") continue # Add activity for album download start album_name = data.get('album_name', 'Unknown Album') logger.info(f"Starting simple album download: '{album_name}' with {started_downloads}/{len(tracks)} tracks") add_activity_item("", "Album Download Started", f"'{album_name}' - {started_downloads} tracks", "Now") return jsonify({ "success": True, "message": f"Started {started_downloads} downloads from album" }) else: # Single track download username = data.get('username') filename = data.get('filename') file_size = data.get('size', 0) logger.info(f"Download request - Username: {username}, Filename: {filename[:50]}...") if not username or not filename: return jsonify({"error": "Missing username or filename."}), 400 download_id = run_async(download_orchestrator.download(username, filename, file_size)) logger.info(f"Download ID returned: {download_id}") if download_id: # Register download for post-processing (simple transfer to /Transfer) context_key = _make_context_key(username, filename) is_streaming_source = username in ('youtube', 'tidal', 'qobuz', 'hifi', 'deezer_dl', 'lidarr', 'soundcloud') with matched_context_lock: matched_downloads_context[context_key] = { 'search_result': { 'username': username, 'filename': filename, 'size': file_size, 'title': data.get('title', 'Unknown'), 'artist': data.get('artist', 'Unknown'), 'quality': data.get('quality', 'Unknown'), 'is_simple_download': True # Flag for simple processing }, 'spotify_artist': None, # No Spotify metadata 'spotify_album': None, 'track_info': None } source_label = username.title() if is_streaming_source else 'Soulseek' logger.info(f"[{source_label}] Registered simple download for post-processing: {context_key}") # Extract track name from filename for activity track_name = filename.split('/')[-1] if '/' in filename else filename.split('\\')[-1] if '\\' in filename else filename logger.info(f"Starting simple track download: '{track_name}'") add_activity_item("", "Track Download Started", f"'{track_name}'", "Now") return jsonify({"success": True, "message": "Download started"}) else: logger.error(f"Failed to start download for: {filename}") return jsonify({"error": "Failed to start download"}), 500 except Exception as e: logger.error(f"Download error: {e}") return jsonify({"error": str(e)}), 500 def _find_completed_file_robust(download_dir, api_filename, transfer_dir=None): """ Robustly finds a completed file on disk, accounting for name variations and unexpected subdirectories. This version uses the superior normalization logic from the GUI's matching_engine.py to ensure consistency. First searches in download_dir, then optionally searches in transfer_dir if provided. Returns tuple (file_path, location) where location is 'downloads' or 'transfer'. """ import re import os from difflib import SequenceMatcher from unidecode import unidecode # YOUTUBE/TIDAL SUPPORT: Handle encoded filename format "id||title" # Extract just the title part for file matching if '||' in api_filename: _, title = api_filename.split('||', 1) api_filename = title # Use just the title for file searching def normalize_for_finding(text: str) -> str: """A powerful normalization function adapted from matching_engine.py.""" if not text: return "" text = unidecode(text).lower() # Replace common separators with spaces to preserve word boundaries text = re.sub(r'[._/]', ' ', text) # Keep alphanumeric, spaces, and hyphens. Remove brackets/parentheses content. text = re.sub(r'[\[\(].*?[\]\)]', '', text) text = re.sub(r'[^a-z0-9\s-]', '', text) # Consolidate multiple spaces return ' '.join(text.split()).strip() def _path_matches_api_dirs(file_path): """Check if ALL api directory components appear in the file's path.""" path_parts = set(p.lower() for p in file_path.replace('\\', '/').split('/')) return all(d in path_parts for d in api_dir_parts) def search_in_directory(search_dir, location_name): """Search for the file in a specific directory.""" best_fuzzy_path = None highest_fuzzy_similarity = 0.0 exact_matches = [] # Walk through the entire directory for root, dirs, files in os.walk(search_dir): # Skip quarantine folder — contains known-wrong files from AcoustID verification dirs[:] = [d for d in dirs if d != 'ss_quarantine'] for file in files: # Direct basename match if os.path.basename(file) == target_basename: file_path = os.path.join(root, file) # Fast path: if path aligns with expected directory structure, return now if api_dir_parts and _path_matches_api_dirs(file_path): logger.info(f"Found path-confirmed match in {location_name}: {file_path}") return file_path, 1.0 if not api_dir_parts: # No directory info to disambiguate — return first match (original behavior) logger.info(f"Found exact match in {location_name}: {file_path}") return file_path, 1.0 exact_matches.append(file_path) continue # Check for slskd dedup suffix (e.g. "Song_639067852665564677.flac") # slskd appends _ when a file with the same name already exists file_stem, file_ext_part = os.path.splitext(file) stripped_stem = re.sub(r'_\d{10,}$', '', file_stem) if stripped_stem != file_stem and stripped_stem + file_ext_part == target_basename: file_path = os.path.join(root, file) if api_dir_parts and _path_matches_api_dirs(file_path): logger.info(f"Found path-confirmed dedup match in {location_name}: {file_path}") return file_path, 1.0 if not api_dir_parts: logger.info(f"Found dedup-suffix match in {location_name}: {file_path}") return file_path, 1.0 exact_matches.append(file_path) continue # Fuzzy matching for variations normalized_file = normalize_for_finding(file) similarity = SequenceMatcher(None, normalized_target, normalized_file).ratio() if similarity > highest_fuzzy_similarity: highest_fuzzy_similarity = similarity best_fuzzy_path = os.path.join(root, file) # Return best exact match (disambiguated by path), or fall back to fuzzy if exact_matches: if len(exact_matches) == 1: logger.info(f"Found exact match in {location_name}: {exact_matches[0]}") return exact_matches[0], 1.0 # Multiple files share the basename — pick the one whose path best # matches the expected directory structure from the Soulseek remote path best = exact_matches[0] best_score = -1 for m in exact_matches: m_parts = set(p.lower() for p in m.replace('\\', '/').split('/')) score = sum(1 for d in api_dir_parts if d in m_parts) if score > best_score: best_score = score best = m logger.info(f"Found {len(exact_matches)} files named '{target_basename}' in {location_name}, picked best path match: {best}") return best, 1.0 return best_fuzzy_path, highest_fuzzy_similarity # Extract filename using the helper function target_basename = extract_filename(api_filename) normalized_target = normalize_for_finding(target_basename) # Extract directory components from the API path for disambiguation. # When multiple downloads produce the same basename (e.g., "01 - Silent Night.flac" # from different albums/users), these let us pick the correct file on disk. api_path_normalized = api_filename.replace('\\', '/') if api_filename else '' api_dir_parts = [p.lower() for p in api_path_normalized.split('/')[:-1] if p] # First search in downloads directory best_downloads_path, downloads_similarity = search_in_directory(download_dir, 'downloads') # Use a high confidence threshold for fuzzy matches to prevent false positives if downloads_similarity > 0.85: location = 'downloads' if downloads_similarity < 1.0: logger.info(f"Found fuzzy match in downloads ({downloads_similarity:.2f}): {best_downloads_path}") return (best_downloads_path, location) # If not found in downloads and transfer_dir is provided, search there transfer_similarity = 0.0 # Initialize transfer_similarity if transfer_dir and os.path.exists(transfer_dir): best_transfer_path, transfer_similarity = search_in_directory(transfer_dir, 'transfer') if transfer_similarity > 0.85: location = 'transfer' if transfer_similarity < 1.0: logger.info(f"Found fuzzy match in transfer ({transfer_similarity:.2f}): {best_transfer_path}") return (best_transfer_path, location) # Don't spam logs - file not found is common for completed/processed downloads return (None, None) @app.route('/api/downloads/status') def get_download_status(): """ A robust status checker that correctly finds completed files by searching the entire download directory with fuzzy matching, mirroring the logic from downloads.py. """ if not download_orchestrator: return jsonify({"transfers": []}) try: global processed_download_ids # Skip slskd API call if Soulseek is already known to be disconnected soulseek_known_down = not _status_cache.get('soulseek', {}).get('connected', True) transfers_data = None if not soulseek_known_down: transfers_data = run_async(download_orchestrator._make_request('GET', 'transfers/downloads')) # Don't return early if no Soulseek transfers - YouTube/Tidal downloads need to be checked too! all_transfers = [] completed_matched_downloads = [] # Track files already claimed this poll cycle to prevent two contexts from # grabbing the same physical file when downloads share a basename (e.g., # "07 - Aurora.flac" from two different albums/artists). _files_claimed_this_cycle = set() if not transfers_data: # No Soulseek transfers, but continue to check YouTube/Tidal downloads below pass else: # This logic now correctly processes the nested structure from the slskd API for user_data in transfers_data: username = user_data.get('username', 'Unknown') if 'directories' in user_data: for directory in user_data['directories']: if 'files' in directory: for file_info in directory['files']: file_info['username'] = username all_transfers.append(file_info) state = file_info.get('state', '').lower() # Check for completion state if ('succeeded' in state or 'completed' in state) and 'errored' not in state and 'rejected' not in state: # Verify bytes actually transferred before trusting state _fi_size = file_info.get('size', 0) _fi_transferred = file_info.get('bytesTransferred', 0) if _fi_size > 0 and _fi_transferred < _fi_size: continue # Not truly complete yet filename_from_api = file_info.get('filename') if not filename_from_api: continue # Check if this completed download has a matched context context_key = _make_context_key(username, filename_from_api) # Check if this is an orphaned download that completed after retry if context_key in _orphaned_download_keys: # Safety check: if a new context exists for this key, the retry # re-claimed the same source — treat it as active, not orphaned with matched_context_lock: has_active_context = context_key in matched_downloads_context if has_active_context: logger.warning(f"Orphaned key {context_key} has active context — retry re-used same source, treating as active") _orphaned_download_keys.discard(context_key) # Fall through to normal processing below else: download_dir = docker_resolve_path(config_manager.get('soulseek.download_path', './downloads')) found_result = _find_completed_file_robust(download_dir, filename_from_api) found_path = found_result[0] if found_result and found_result[0] else None orphan_cleaned = False if found_path: try: os.remove(found_path) logger.warning(f"Deleted orphaned download: {os.path.basename(found_path)}") orphan_cleaned = True except Exception as e: logger.error(f"Failed to delete orphaned file (will retry next poll): {e}") else: # File not on disk (already gone or never written) — nothing to clean orphan_cleaned = True if orphan_cleaned: # Remove transfer from slskd transfer_id = file_info.get('id') if transfer_id: try: run_async(download_orchestrator.cancel_download(str(transfer_id), username, remove=True)) except Exception as e: logger.debug("orphan transfer cancel failed: %s", e) _orphaned_download_keys.discard(context_key) continue # Skip normal post-processing either way # Skip downloads we've already processed (prevents log spam) if context_key in processed_download_ids: continue with matched_context_lock: context = matched_downloads_context.get(context_key) available_keys = list(matched_downloads_context.keys())[:5] if not context else None if context: logger.info(f"[Context Lookup] Found context for key: {context_key}") elif context_key not in _stale_transfer_keys: # Only log once per stale key to avoid spamming every poll cycle logger.warning(f"[Context Lookup] No context found for key: {context_key}") logger.info(f" Available keys: {available_keys}...") _stale_transfer_keys.add(context_key) if context: download_dir = docker_resolve_path(config_manager.get('soulseek.download_path', './downloads')) # Use the new robust file finder (only search downloads for post-processing candidates) found_result = _find_completed_file_robust(download_dir, filename_from_api) found_path = found_result[0] if found_result and found_result[0] else None if found_path: # Prevent two contexts from claiming the same physical file _norm_path = os.path.normpath(found_path) if _norm_path in _files_claimed_this_cycle: logger.info(f"File already claimed by another context this cycle: {os.path.basename(found_path)} — deferring to next poll") else: _files_claimed_this_cycle.add(_norm_path) logger.info(f"Found completed matched file on disk: {found_path}") completed_matched_downloads.append((context_key, context, found_path)) # Don't add to processed_download_ids yet - wait until thread starts successfully # Clean up retry tracking if file was found after retries with _download_retry_lock: if context_key in _download_retry_attempts: retry_count = _download_retry_attempts[context_key]['count'] elapsed = time.time() - _download_retry_attempts[context_key]['first_attempt'] logger.warning(f"File found after {retry_count} retry attempt(s) ({elapsed:.1f}s): {os.path.basename(filename_from_api)}") del _download_retry_attempts[context_key] else: # File not found yet - implement retry logic instead of immediate give-up # This fixes race condition where slskd reports completion before file is written to disk with _download_retry_lock: if context_key not in _download_retry_attempts: # First retry attempt _download_retry_attempts[context_key] = { 'count': 1, 'first_attempt': time.time() } logger.warning(f"File not found yet: '{os.path.basename(filename_from_api)}' - Will retry (attempt 1/{_download_retry_max})") else: # Increment retry count _download_retry_attempts[context_key]['count'] += 1 retry_count = _download_retry_attempts[context_key]['count'] elapsed = time.time() - _download_retry_attempts[context_key]['first_attempt'] if retry_count >= _download_retry_max: # Max retries reached, give up logger.error(f"CRITICAL: Could not find '{os.path.basename(filename_from_api)}' after {retry_count} attempts over {elapsed:.1f}s. Giving up.") processed_download_ids.add(context_key) # Clean up retry tracking del _download_retry_attempts[context_key] else: logger.warning(f"File not found yet: '{os.path.basename(filename_from_api)}' - Will retry (attempt {retry_count}/{_download_retry_max}, elapsed: {elapsed:.1f}s)") # If we found completed matched downloads, start processing them in background threads if completed_matched_downloads: def process_completed_downloads(): for context_key, context, found_path in completed_matched_downloads: try: logger.info(f"Starting post-processing thread for: {context_key}") # Use verification wrapper if context has task tracking IDs, # otherwise call directly (race guard flag still gets set on context) _pp_task_id = context.get('task_id') _pp_batch_id = context.get('batch_id') if _pp_task_id and _pp_batch_id: _pp_target = _post_process_matched_download_with_verification _pp_args = (context_key, context, found_path, _pp_task_id, _pp_batch_id) else: _pp_target = _post_process_matched_download _pp_args = (context_key, context, found_path) thread = threading.Thread(target=_pp_target, args=_pp_args) thread.daemon = True thread.start() # Only mark as processed AFTER thread starts successfully processed_download_ids.add(context_key) logger.info(f"Marked as processed: {context_key}") # DON'T remove context immediately - verification worker needs it # Context will be cleaned up by verification worker after both processors complete logger.info(f"Keeping context for verification worker: {context_key}") except Exception as e: logger.error(f"Error starting post-processing thread for {context_key}: {e}") # Don't add to processed set if thread failed to start logger.warning(f"Will retry {context_key} on next check") # Start a single thread to manage the launching of all processing threads processing_thread = threading.Thread(target=process_completed_downloads) processing_thread.daemon = True processing_thread.start() # Also include YouTube/Tidal downloads in the response try: all_streaming_downloads = run_async(download_orchestrator.get_all_downloads()) for download in all_streaming_downloads: if download.username in ('youtube', 'tidal', 'qobuz', 'hifi', 'deezer_dl', 'lidarr', 'soundcloud'): source_label = download.username.title() # Convert DownloadStatus to transfer format that frontend expects streaming_transfer = { 'id': download.id, 'filename': download.filename, 'username': download.username, 'state': download.state, 'percentComplete': download.progress, 'size': download.size, 'bytesTransferred': download.transferred, 'averageSpeed': download.speed, 'direction': 'Download', # Required by frontend } all_transfers.append(streaming_transfer) # Check if download is completed and needs post-processing # Verify bytes match before trusting state string _st_bytes_ok = download.size <= 0 or download.transferred >= download.size if _st_bytes_ok and download.state and ('succeeded' in download.state.lower() or 'completed' in download.state.lower()): context_key = _make_context_key(download.username, download.filename) with matched_context_lock: context = matched_downloads_context.get(context_key) if context and context_key not in processed_download_ids: download_dir = docker_resolve_path(config_manager.get('soulseek.download_path', './downloads')) found_result = _find_completed_file_robust(download_dir, download.filename) found_path = found_result[0] if found_result and found_result[0] else None if found_path: # Prevent two contexts from claiming the same physical file _st_norm = os.path.normpath(found_path) if _st_norm in _files_claimed_this_cycle: logger.info(f"[{source_label}] File already claimed this cycle: {os.path.basename(found_path)} — deferring") continue _files_claimed_this_cycle.add(_st_norm) logger.info(f"[{source_label}] Found completed matched file on disk: {found_path}") # Start post-processing thread def process_streaming_download(_ctx_key=context_key, _ctx=context, _path=found_path, _label=source_label): try: logger.info(f"[{_label}] Starting post-processing thread for: {_ctx_key}") # Use verification wrapper if context has task tracking IDs _st_task_id = _ctx.get('task_id') _st_batch_id = _ctx.get('batch_id') if _st_task_id and _st_batch_id: _st_target = _post_process_matched_download_with_verification _st_args = (_ctx_key, _ctx, _path, _st_task_id, _st_batch_id) else: _st_target = _post_process_matched_download _st_args = (_ctx_key, _ctx, _path) thread = threading.Thread(target=_st_target, args=_st_args) thread.daemon = True thread.start() processed_download_ids.add(_ctx_key) logger.info(f"[{_label}] Marked as processed: {_ctx_key}") except Exception as e: logger.error(f"[{_label}] Error starting post-processing thread for {_ctx_key}: {e}") processing_thread = threading.Thread(target=process_streaming_download) processing_thread.daemon = True processing_thread.start() else: # File not found - likely already processed and moved to library # Mark as processed to prevent infinite checking processed_download_ids.add(context_key) except Exception as streaming_error: import traceback logger.error(f"Could not fetch YouTube/Tidal downloads for status: {streaming_error}") traceback.print_exc() # Enrich transfers with metadata from download context (artist, album, artwork) with matched_context_lock: for transfer in all_transfers: ctx_key = _make_context_key(transfer.get('username', ''), transfer.get('filename', '')) ctx = matched_downloads_context.get(ctx_key) if ctx: _sp_artist = ctx.get('spotify_artist') or {} _sp_album = ctx.get('spotify_album') or {} _sp_track = ctx.get('track_info') or {} # Cover art can live in a few places depending on the # origin path: album.images[0].url (Spotify-shaped), # album.image_url (context-built / wishlist / fixes), or # track_info.image_url (some discovery flows). Try them # all so fixed-discovery tracks render their artwork. _sp_images = _sp_album.get('images') or [] _art_url = '' if _sp_images and isinstance(_sp_images[0], dict): _art_url = _sp_images[0].get('url', '') or '' if not _art_url: _art_url = _sp_album.get('image_url') or '' if not _art_url: _art_url = _sp_track.get('image_url') or '' transfer['_meta'] = { 'artist': _sp_artist.get('name', ''), 'album': _sp_album.get('name', ''), 'artwork_url': _art_url, 'track_number': _sp_track.get('track_number'), 'quality': ctx.get('_audio_quality', ''), } return jsonify({"transfers": all_transfers}) except Exception as e: logger.error(f"Error fetching download status: {e}") return jsonify({"error": str(e)}), 500 # Cancel + clear logic lives in core/downloads/cancel.py — these routes are thin handlers. from core.downloads import cancel as _downloads_cancel @app.route('/api/downloads/cancel', methods=['POST']) def cancel_download(): """Cancel a specific download transfer, matching GUI functionality.""" data = request.get_json() if not data: return jsonify({"success": False, "error": "No data provided."}), 400 download_id = data.get('download_id') username = data.get('username') if not all([download_id, username]): return jsonify({"success": False, "error": "Missing download_id or username."}), 400 try: success = _downloads_cancel.cancel_single_download(download_orchestrator, run_async, download_id, username) if success: return jsonify({"success": True, "message": "Download cancelled."}) return jsonify({"success": False, "error": "Failed to cancel download via slskd."}), 500 except Exception as e: logger.error(f"Error cancelling download: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/downloads/cancel-all', methods=['POST']) def cancel_all_downloads(): """Cancel all active downloads from slskd, then clear completed ones.""" try: success, msg = _downloads_cancel.cancel_all_active( download_orchestrator, run_async, _sweep_empty_download_directories, ) if success: return jsonify({"success": True, "message": msg}) return jsonify({"success": False, "error": msg}), 500 except Exception as e: logger.error(f"Error cancelling all downloads: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/downloads/clear-finished', methods=['POST']) def clear_finished_downloads(): """Clear all terminal (completed, cancelled, failed) downloads from slskd.""" try: success = _downloads_cancel.clear_finished_active( download_orchestrator, run_async, _sweep_empty_download_directories, ) if success: return jsonify({"success": True, "message": "Finished downloads cleared."}) return jsonify({"success": False, "error": "Backend failed to clear downloads."}), 500 except Exception as e: logger.error(f"Error clearing finished downloads: {e}") return jsonify({"success": False, "error": str(e)}), 500 # Streaming sources where the candidate's `username` field IS the source name # (Soulseek uses a real peer username; everything else stamps the source string). _STREAMING_SOURCE_NAMES = frozenset(( 'youtube', 'tidal', 'qobuz', 'hifi', 'deezer_dl', 'lidarr', 'soundcloud' )) def _infer_candidate_source(username: str) -> str: """Infer which download source a candidate came from based on its `username` field. Streaming sources stamp their canonical name there; everything else is Soulseek.""" if not username: return 'soulseek' return username if username in _STREAMING_SOURCE_NAMES else 'soulseek' def _serialize_candidate(c, source_override: str = None) -> dict: """Convert a TrackResult (or dict) into the JSON shape the candidates modal expects. ``source_override`` lets manual-search callers stamp the source explicitly when the dispatcher knows it; otherwise we infer from the username.""" if hasattr(c, '__dict__'): username = getattr(c, 'username', '') return { 'username': username, 'filename': getattr(c, 'filename', ''), 'size': getattr(c, 'size', 0), 'bitrate': getattr(c, 'bitrate', None), 'duration': getattr(c, 'duration', None), 'quality': getattr(c, 'quality', ''), 'free_upload_slots': getattr(c, 'free_upload_slots', 0), 'upload_speed': getattr(c, 'upload_speed', 0), 'queue_length': getattr(c, 'queue_length', 0), 'artist': getattr(c, 'artist', None), 'title': getattr(c, 'title', None), 'album': getattr(c, 'album', None), 'source': source_override or _infer_candidate_source(username), } if isinstance(c, dict): out = dict(c) out.setdefault('source', source_override or _infer_candidate_source(out.get('username', ''))) return out return {} def _list_available_download_sources() -> tuple: """Return ``(download_mode, available_sources)`` for the current download configuration. ``download_mode`` is the value of ``download_source.mode`` (one of 'soulseek'/'youtube'/.../'hybrid'). ``available_sources`` is a list of ``{id, label}`` dicts — the sources the manual-search dropdown should offer. In single-source mode: returns just that one source if it's initialized + configured (the user picked it, so we expose it even if is_configured() doesn't fully approve — they may still want to retry). In hybrid mode: filters ``hybrid_order`` down to sources that are BOTH initialized and ``is_configured()`` — same gate hybrid-mode fallback already uses. """ if not download_orchestrator: return 'soulseek', [] download_mode = config_manager.get('download_source.mode', 'soulseek') sources = [] def _make_entry(name: str) -> dict: spec = download_orchestrator.registry.get_spec(name) if hasattr(download_orchestrator, 'registry') else None return { 'id': name, 'label': spec.display_name if spec else name.title(), } if download_mode == 'hybrid': hybrid_order = config_manager.get('download_source.hybrid_order', ['hifi', 'youtube', 'soulseek']) or [] seen = set() for raw_name in hybrid_order: spec = download_orchestrator.registry.get_spec(raw_name) if hasattr(download_orchestrator, 'registry') else None canonical = spec.name if spec else raw_name if canonical in seen: continue client = download_orchestrator.client(canonical) if not client: continue try: if not client.is_configured(): continue except Exception: continue seen.add(canonical) sources.append(_make_entry(canonical)) else: # Single-source mode — just expose the configured mode (the user # picked it, so they expect manual search to hit that source). client = download_orchestrator.client(download_mode) if client: sources.append(_make_entry(download_mode)) return download_mode, sources @app.route('/api/downloads/task//candidates', methods=['GET']) def get_task_candidates(task_id): """Returns the cached search candidates for a download task so the UI can show what was found.""" try: with tasks_lock: task = download_tasks.get(task_id) if not task: return jsonify({"error": "Task not found"}), 404 candidates = task.get('cached_candidates', []) track_info = task.get('track_info', {}) error_message = task.get('error_message', '') serialized = [_serialize_candidate(c) for c in candidates if c is not None] serialized = [s for s in serialized if s] download_mode, available_sources = _list_available_download_sources() return jsonify({ "task_id": task_id, "track_info": { "name": track_info.get('name', 'Unknown') if isinstance(track_info, dict) else 'Unknown', "artist": _get_track_artist_name(track_info) if isinstance(track_info, dict) else 'Unknown', }, "error_message": error_message, "candidates": serialized, "candidate_count": len(serialized), "download_mode": download_mode, "available_sources": available_sources, }) except Exception as e: logger.error(f"[Candidates] Error fetching candidates for task {task_id}: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/downloads/task//download-candidate', methods=['POST']) def download_selected_candidate(task_id): """Restart a not_found/failed task by downloading a user-selected candidate.""" dl_err = check_download_permission() if dl_err: return dl_err try: data = request.get_json() if not data or not data.get('username') or not data.get('filename'): return jsonify({"error": "Missing username or filename"}), 400 username = data['username'] filename = data['filename'] size = data.get('size', 0) with tasks_lock: task = download_tasks.get(task_id) if not task: return jsonify({"error": "Task not found"}), 404 if task['status'] not in ('not_found', 'failed'): return jsonify({"error": f"Task is {task['status']}, not eligible for retry"}), 400 batch_id = task.get('batch_id') track_info = task.get('track_info', {}) # Reset task state task['status'] = 'downloading' task['error_message'] = None task['status_change_time'] = time.time() task.pop('download_id', None) task.pop('username', None) task.pop('filename', None) # Mark this as a user-initiated manual pick. The auto-retry # monitor (`_should_retry_task`) and the engine-state status # fallback both check this flag and skip the "fall back to # another candidate via fresh search" behavior. When the user # explicitly chose THIS file, the mental model is "try this # one and tell me if it failed", not "try this, then auto- # pick something else if it fails". Stays set until the task # reaches a terminal state. task['_user_manual_pick'] = True # Reset retry counters so previous auto-attempts don't # immediately exhaust the manual pick. task.pop('stuck_retry_count', None) task.pop('error_retry_count', None) task.pop('last_retry_time', None) task.pop('last_error_retry_time', None) # Clear the selected candidate from used_sources so it won't be skipped used_sources = task.get('used_sources', set()) source_key = f"{username}_{filename}" used_sources.discard(source_key) # Reset batch tracking for this task if batch_id and batch_id in download_batches: batch = download_batches[batch_id] # Remove from completed set so _on_download_completed can fire again completed_set = batch.get('_completed_task_ids', set()) completed_set.discard(task_id) # Remove from permanently_failed_tracks track_index = task.get('track_index') batch['permanently_failed_tracks'] = [ t for t in batch.get('permanently_failed_tracks', []) if t.get('table_index') != track_index and t.get('download_index') != track_index ] # Restore worker slot batch['active_count'] = batch.get('active_count', 0) + 1 # Build a TrackResult-like candidate object from core.download_plugins.types import TrackResult candidate = TrackResult( username=username, filename=filename, size=size, bitrate=data.get('bitrate'), duration=data.get('duration'), quality=data.get('quality', 'unknown'), free_upload_slots=data.get('free_upload_slots', 0), upload_speed=data.get('upload_speed', 0), queue_length=data.get('queue_length', 0), artist=data.get('artist'), title=data.get('title'), album=data.get('album'), ) candidate.confidence = 1.0 # Required by _attempt_download_with_candidates sort # Reconstruct Track object from task's track_info from core.itunes_client import Track artists = track_info.get('artists', []) artist_names = [] for a in (artists if isinstance(artists, list) else []): if isinstance(a, dict): artist_names.append(a.get('name', 'Unknown')) elif isinstance(a, str): artist_names.append(a) if not artist_names: artist_names = [track_info.get('artist', 'Unknown')] track = Track( id=track_info.get('id', ''), name=track_info.get('name', 'Unknown'), artists=artist_names, album=track_info.get('album', {}).get('name', '') if isinstance(track_info.get('album'), dict) else track_info.get('album', ''), duration_ms=track_info.get('duration_ms', 0), popularity=0, ) track_name = track_info.get('name', 'Unknown') # Run on a dedicated thread instead of `missing_download_executor` # — that pool is shared with the batch's other in-flight tracks # (3 workers total) and a saturated pool would queue the manual # pick indefinitely, leaving the user stuck at "downloading 0%". # Manual picks are user-initiated and infrequent; a fresh thread # per pick is cheaper than starving them behind background work. def _run_manual_download(): logger.info(f"[Manual Download] worker started for task {task_id} ({username} / {track_name})") try: success = _attempt_download_with_candidates(task_id, [candidate], track, batch_id) logger.info(f"[Manual Download] worker finished for task {task_id} success={success}") if not success: with tasks_lock: if task_id in download_tasks: download_tasks[task_id]['status'] = 'failed' download_tasks[task_id]['error_message'] = 'Manual download failed to start — source may be unavailable' if batch_id: _on_download_completed(batch_id, task_id, success=False) except Exception as exc: logger.exception(f"[Manual Download] worker crashed for task {task_id}: {exc}") with tasks_lock: if task_id in download_tasks: download_tasks[task_id]['status'] = 'failed' download_tasks[task_id]['error_message'] = f'Manual download crashed: {exc}' if batch_id: try: _on_download_completed(batch_id, task_id, success=False) except Exception: logger.exception("[Manual Download] _on_download_completed cleanup also failed") threading.Thread( target=_run_manual_download, name=f"manual-download-{task_id[:8]}", daemon=True, ).start() logger.info(f"[Manual Download] User selected candidate for '{track_name}' from {username}") return jsonify({"success": True, "message": f"Download initiated for '{track_name}'"}) except Exception as e: logger.error(f"[Manual Download] {e}") import traceback traceback.print_exc() return jsonify({"error": str(e)}), 500 @app.route('/api/downloads/task//manual-search', methods=['POST']) def manual_search_for_task(task_id): """Run a user-driven search against one (or all) configured download sources and stream candidate results as NDJSON — one JSON object per line, terminated by ``\\n``. Streaming lets the modal render results as each source completes instead of blocking on the slowest source. The candidates modal lets the user pick a result; that retry still goes through ``/download-candidate``, so all AcoustID + post-download safety nets stay in the loop. Stream shape (one JSON object per line): - ``{"type": "header", ...}`` — emitted first; carries ``track_info``, ``download_mode``, ``available_sources``, ``query``, ``sources_queried``. - ``{"type": "source_results", "source": "", "candidates": [...]}`` — one per source, emitted as that source's search completes. - ``{"type": "source_error", "source": "", "error": ""}`` — when a source's search raised. - ``{"type": "done", "total": }`` — terminator. """ try: data = request.get_json(silent=True) or {} raw_query = data.get('query', '') query = raw_query.strip() if isinstance(raw_query, str) else '' source = data.get('source', 'all') if len(query) < 2: return jsonify({"error": "Query must be at least 2 characters"}), 400 with tasks_lock: task = download_tasks.get(task_id) if not task: return jsonify({"error": "Task not found"}), 404 track_info = dict(task.get('track_info', {})) download_mode, available_sources = _list_available_download_sources() valid_source_ids = {s['id'] for s in available_sources} if source != 'all': if source not in valid_source_ids: return jsonify({ "error": f"Source '{source}' is not configured or available" }), 400 sources_to_query = [source] else: sources_to_query = list(valid_source_ids) track_payload = { "name": track_info.get('name', 'Unknown'), "artist": _get_track_artist_name(track_info) if isinstance(track_info, dict) else 'Unknown', } from concurrent.futures import ThreadPoolExecutor, as_completed def _search_one(src_name: str): client = download_orchestrator.client(src_name) if download_orchestrator else None if not client: return src_name, [], None try: result = run_async(client.search(query)) if isinstance(result, tuple): tracks = result[0] if result else [] else: tracks = result or [] return src_name, tracks, None except Exception as exc: logger.warning(f"[Manual Search] {src_name} search failed for query '{query}': {exc}") return src_name, [], str(exc) def _generate(): yield json.dumps({ "type": "header", "task_id": task_id, "track_info": track_payload, "download_mode": download_mode, "available_sources": available_sources, "query": query, "sources_queried": sources_to_query, }) + "\n" if not sources_to_query: yield json.dumps({"type": "done", "total": 0}) + "\n" return total = 0 max_workers = min(8, max(1, len(sources_to_query))) with ThreadPoolExecutor(max_workers=max_workers, thread_name_prefix='manual-search') as executor: futures = [executor.submit(_search_one, name) for name in sources_to_query] for future in as_completed(futures): src_name, tracks, error = future.result() if error is not None: yield json.dumps({ "type": "source_error", "source": src_name, "error": error, }) + "\n" continue serialized = [] for t in tracks: s = _serialize_candidate(t, source_override=src_name) if s: serialized.append(s) total += len(serialized) yield json.dumps({ "type": "source_results", "source": src_name, "candidates": serialized, }) + "\n" logger.info( f"[Manual Search] task={task_id} query='{query}' source={source} " f"sources_queried={sources_to_query} results={total}" ) yield json.dumps({"type": "done", "total": total}) + "\n" return Response( _generate(), mimetype='application/x-ndjson', headers={'Cache-Control': 'no-cache', 'X-Accel-Buffering': 'no'}, ) except Exception as e: logger.error(f"[Manual Search] {e}") import traceback traceback.print_exc() return jsonify({"error": str(e)}), 500 @app.route('/api/quarantine/clear', methods=['POST']) def clear_quarantine(): """Delete all files and folders inside the ss_quarantine directory.""" import shutil try: download_path = docker_resolve_path(config_manager.get('soulseek.download_path', './downloads')) quarantine_path = os.path.join(download_path, 'ss_quarantine') if not os.path.isdir(quarantine_path): return jsonify({"success": True, "message": "Quarantine folder is already empty."}) removed_files = 0 for entry in os.listdir(quarantine_path): entry_path = os.path.join(quarantine_path, entry) try: if os.path.isfile(entry_path): os.remove(entry_path) removed_files += 1 elif os.path.isdir(entry_path): shutil.rmtree(entry_path) removed_files += 1 except Exception as e: logger.error(f"[Quarantine] Failed to remove {entry}: {e}") logger.info(f"[Quarantine] Cleared {removed_files} item(s) from quarantine folder") return jsonify({"success": True, "message": f"Quarantine cleared ({removed_files} item{'s' if removed_files != 1 else ''} removed)."}) except Exception as e: logger.error(f"[Quarantine] Error clearing quarantine: {e}") return jsonify({"success": False, "error": str(e)}), 500 def _get_quarantine_dir(): return os.path.join( docker_resolve_path(config_manager.get('soulseek.download_path', './downloads')), 'ss_quarantine', ) @app.route('/api/quarantine/list', methods=['GET']) def list_quarantine(): """Return all quarantined files with sidecar metadata.""" try: from core.imports.quarantine import list_quarantine_entries entries = list_quarantine_entries(_get_quarantine_dir()) return jsonify({"success": True, "entries": entries}) except Exception as e: logger.error(f"[Quarantine] Error listing entries: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/quarantine/', methods=['DELETE']) def delete_quarantine_item(entry_id): """Delete a single quarantined file + sidecar.""" try: from core.imports.quarantine import delete_quarantine_entry ok = delete_quarantine_entry(_get_quarantine_dir(), entry_id) if not ok: return jsonify({"success": False, "error": "Entry not found"}), 404 return jsonify({"success": True}) except Exception as e: logger.error(f"[Quarantine] Error deleting {entry_id}: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/quarantine//approve', methods=['POST']) def approve_quarantine_item(entry_id): """One-click approve: restore the file and re-run post-process with the matching per-check bypass flag set so the original quarantine trigger is skipped. Other checks still run.""" try: from core.imports.quarantine import approve_quarantine_entry # Restore inside the soulseek download dir so existing path-resolution # logic finds it. Unique subdir keeps it from re-mingling with active # transfers. restore_dir = os.path.join( docker_resolve_path(config_manager.get('soulseek.download_path', './downloads')), 'Transfer', ) result = approve_quarantine_entry(_get_quarantine_dir(), entry_id, restore_dir) if result is None: return jsonify({ "success": False, "error": "Cannot one-click approve — entry has thin sidecar (no embedded context). Use 'Recover to Staging' instead.", }), 400 restored_path, context, trigger = result # Mark the bypass so the pipeline skips the trigger that fired. context['_skip_quarantine_check'] = trigger # Re-dispatch through the same pipeline. Run async so the HTTP # request returns quickly — UI polls /list to see the entry vanish. context_key = f"approve_{entry_id}_{int(time.time())}" threading.Thread( target=lambda: _post_process_matched_download(context_key, context, restored_path), daemon=True, ).start() logger.info(f"[Quarantine] Approved {entry_id} (bypass={trigger}) → re-running pipeline") return jsonify({"success": True, "trigger_bypassed": trigger}) except Exception as e: logger.error(f"[Quarantine] Error approving {entry_id}: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/quarantine//recover', methods=['POST']) def recover_quarantine_item(entry_id): """Fallback for legacy thin sidecars: move file into Staging so the user can manually finish via the existing Import flow.""" try: from core.imports.quarantine import recover_to_staging from core.imports.staging import get_staging_path target = recover_to_staging(_get_quarantine_dir(), get_staging_path(), entry_id) if not target: return jsonify({"success": False, "error": "Entry not found"}), 404 return jsonify({"success": True, "staged_path": target}) except Exception as e: logger.error(f"[Quarantine] Error recovering {entry_id}: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/scan/request', methods=['POST']) def request_media_scan(): """ Request a media library scan. Database update is handled automatically by the 'Auto-Update Database After Scan' system automation. """ try: if not web_scan_manager: return jsonify({"success": False, "error": "Scan manager not initialized"}), 500 data = request.get_json() or {} reason = data.get('reason', 'Web UI download completed') result = web_scan_manager.request_scan(reason=reason) add_activity_item("", "Media Scan", f"Scan requested: {reason}", "Now") return jsonify({ "success": True, "scan_info": result, }) except Exception as e: logger.error(f"Error requesting media scan: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/scan/status', methods=['GET']) def get_scan_status(): """ Get current media scan status. """ try: if not web_scan_manager: return jsonify({"success": False, "error": "Scan manager not initialized"}), 500 status = web_scan_manager.get_scan_status() return jsonify({"success": True, "status": status}) except Exception as e: logger.error(f"Error getting scan status: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/database/incremental-update', methods=['POST']) def request_incremental_database_update(): """ Request an incremental database update with prerequisites checking. """ try: data = request.get_json() or {} reason = data.get('reason', 'Web UI manual request') # Check prerequisites (similar to GUI logic) db = get_database() # Check if database has enough content for incremental updates track_count = db.execute("SELECT COUNT(*) FROM tracks").fetchone()[0] if track_count < 100: return jsonify({ "success": False, "error": f"Database has only {track_count} tracks - insufficient for incremental updates (minimum 100)", "track_count": track_count }), 400 # Check if there's been a previous full refresh last_refresh = db.execute( "SELECT value FROM system_info WHERE key = 'last_full_refresh'" ).fetchone() if not last_refresh: return jsonify({ "success": False, "error": "No previous full refresh found - incremental updates require established database", "suggestion": "Run a full refresh first" }), 400 # Start incremental update if db_update_state.get('status') == 'running': return jsonify({"success": False, "error": "Database update already running"}), 409 active_server = config_manager.get_active_media_server() with db_update_lock: db_update_state.update({ "status": "running", "phase": "Initializing...", "progress": 0, "current_item": "", "processed": 0, "total": 0, "error_message": "" }) db_update_executor.submit(_run_db_update_task, False, active_server) add_activity_item("", "Database Update", f"Incremental update started: {reason}", "Now") return jsonify({ "success": True, "message": "Incremental database update started", "track_count": track_count, "last_refresh": last_refresh[0] if last_refresh else None, "reason": reason }) except Exception as e: logger.error(f"Error requesting incremental database update: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/test/automation', methods=['POST']) def test_automation_workflow(): """ Test endpoint to verify the automatic workflow functionality. """ try: data = request.get_json() or {} test_type = data.get('test_type', 'full') results = {} # Test 1: Scan manager status if web_scan_manager: scan_status = web_scan_manager.get_scan_status() results['scan_manager'] = {'status': 'available', 'current_status': scan_status} else: results['scan_manager'] = {'status': 'unavailable'} # Test 2: Database prerequisites try: db = get_database() track_count = db.execute("SELECT COUNT(*) FROM tracks").fetchone()[0] last_refresh = db.execute( "SELECT value FROM system_info WHERE key = 'last_full_refresh'" ).fetchone() results['database'] = { 'track_count': track_count, 'meets_minimum': track_count >= 100, 'has_previous_refresh': last_refresh is not None, 'last_refresh': last_refresh[0] if last_refresh else None } except Exception as e: results['database'] = {'error': str(e)} # Test 3: Media client connections active_server = config_manager.get_active_media_server() results['media_clients'] = {'active_server': active_server} for client_name, client in [ ('plex', media_server_engine.client('plex')), ('jellyfin', media_server_engine.client('jellyfin')), ('navidrome', media_server_engine.client('navidrome')) ]: try: is_connected = client.is_connected() if client else False results['media_clients'][client_name] = { 'available': client is not None, 'connected': is_connected } except Exception as e: results['media_clients'][client_name] = { 'available': client is not None, 'connected': False, 'error': str(e) } # Test 4: If requested, actually test the scan request if test_type == 'full' and web_scan_manager: try: scan_result = web_scan_manager.request_scan( reason="Automation test", callback=None ) results['scan_test'] = {'success': True, 'result': scan_result} except Exception as e: results['scan_test'] = {'success': False, 'error': str(e)} return jsonify({ "success": True, "test_results": results, "automation_ready": ( results.get('scan_manager', {}).get('status') == 'available' and results.get('database', {}).get('meets_minimum', False) and results.get('database', {}).get('has_previous_refresh', False) ) }) except Exception as e: logger.error(f"Error in automation test: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/searches/clear-all', methods=['POST']) def clear_all_searches(): """ Clear all searches from slskd search history. """ try: success = run_async(download_orchestrator.clear_all_searches()) if success: add_activity_item("", "Search Cleanup", "All search history cleared manually", "Now") return jsonify({"success": True, "message": "All searches cleared."}) else: return jsonify({"success": False, "error": "Backend failed to clear searches."}), 500 except Exception as e: logger.error(f"Error clearing searches: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/searches/maintain', methods=['POST']) def maintain_search_history(): """ Maintain search history by keeping only recent searches. """ try: data = request.get_json() or {} keep_searches = data.get('keep_searches', 50) trigger_threshold = data.get('trigger_threshold', 200) success = run_async(download_orchestrator.maintain_search_history_with_buffer( keep_searches=keep_searches, trigger_threshold=trigger_threshold )) if success: add_activity_item("", "Search Maintenance", f"Search history maintained (keeping {keep_searches} searches)", "Now") return jsonify({"success": True, "message": f"Search history maintained (keeping {keep_searches} searches)."}) else: return jsonify({"success": False, "error": "Backend failed to maintain search history."}), 500 except Exception as e: logger.error(f"Error maintaining search history: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/history') def get_library_history(): """Get persistent library history (downloads and server imports).""" try: event_type = request.args.get('type', None) if event_type and event_type not in ('download', 'import'): event_type = None page = max(1, int(request.args.get('page', 1))) limit = min(200, max(1, int(request.args.get('limit', 50)))) db = get_database() entries, total = db.get_library_history(event_type=event_type, page=page, limit=limit) stats = db.get_library_history_stats() return jsonify({ 'success': True, 'entries': entries, 'total': total, 'page': page, 'limit': limit, 'stats': stats }) except Exception as e: logger.error(f"Error fetching library history: {e}") return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/library/history//file-tags') def get_library_history_file_tags(history_id: int): """Read embedded tags from the actual audio file for one library history row. Backs the Audit Trail modal's "Embedded Tags" section. The file is the single source of truth — persisted snapshot columns drift the moment a background worker writes more tags. `read_embedded_tags` returns a uniform dict; we pass through. """ try: db = get_database() entries, _total = db.get_library_history(event_type=None, page=1, limit=200) entry = next((e for e in entries if e.get('id') == history_id), None) if entry is None: # Wider lookup — pagination above may not have caught older rows. conn = db._get_connection() cursor = conn.cursor() cursor.execute("SELECT * FROM library_history WHERE id = ?", (history_id,)) row = cursor.fetchone() entry = dict(row) if row else None if entry is None: return jsonify({'success': False, 'error': 'history row not found'}), 404 raw_path = entry.get('file_path') or '' resolved = _resolve_library_file_path(raw_path) if raw_path else None target_path = resolved or raw_path from core.library.file_tags import read_embedded_tags result = read_embedded_tags(target_path) return jsonify({'success': True, **result}) except Exception as e: logger.error(f"Error reading file tags for history {history_id}: {e}") return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/library/artists') def get_library_artists(): """Get artists for the library page with search, filtering, and pagination""" try: # Get query parameters search_query = request.args.get('search', '') letter = request.args.get('letter', 'all') page = int(request.args.get('page', 1)) limit = int(request.args.get('limit', 75)) watchlist_filter = request.args.get('watchlist', 'all') source_filter = request.args.get('source_filter', '') # Get database instance database = get_database() # Get artists from database result = database.get_library_artists( search_query=search_query, letter=letter, page=page, limit=limit, watchlist_filter=watchlist_filter, profile_id=get_current_profile_id(), source_filter=source_filter ) # Fix image URLs for all artists for artist in result['artists']: if artist.get('image_url'): artist['image_url'] = fix_artist_image_url(artist['image_url']) return jsonify({ "success": True, **result }) except Exception as e: logger.error(f"Error fetching library artists: {e}") import traceback traceback.print_exc() return jsonify({ "success": False, "error": str(e), "artists": [], "pagination": { "page": 1, "limit": 75, "total_count": 0, "total_pages": 0, "has_prev": False, "has_next": False } }), 500 @app.route('/api/test-artist/') def test_artist_endpoint(artist_id): """Simple test endpoint""" return jsonify({ "success": True, "message": f"Test endpoint working for artist ID: {artist_id}" }) from core.artist_source_lookup import ( SOURCE_ID_FIELD as _SOURCE_ID_FIELD, SOURCE_ONLY_ARTIST_SOURCES as _SOURCE_ONLY_ARTIST_SOURCES, find_library_artist_for_source as _core_find_library_artist_for_source, ) def _find_library_artist_for_source(database, source, source_artist_id, artist_name=None): """Thin wrapper that injects the active-server context for the core lookup.""" try: active_server = config_manager.get_active_media_server() except Exception: active_server = None return _core_find_library_artist_for_source( database, source, source_artist_id, artist_name, active_server=active_server ) def _build_source_only_artist_detail(artist_id, artist_name, source): """Thin wrapper around ``core.artist_source_detail.build_source_only_artist_detail``. Builds the per-source client bag from web_server's module globals (each source's module-level client + Last.fm api key), forwards to the pure implementation in ``core/``, and wraps the (dict, status) return in ``jsonify``. """ from core.artist_source_detail import build_source_only_artist_detail # Resolve the per-source clients defensively — the original inline code # wrapped the whole source-side lookup in try/except so a failing # client helper (e.g. Spotify auth probe during a rate-limit ban, # Discogs client init error) would degrade gracefully to empty # enrichment instead of 500-ing the request. Preserve that. sp = None dz = None it = None dc = None try: if spotify_client and spotify_client.is_spotify_authenticated(): sp = spotify_client except Exception as e: logger.debug(f"Spotify client resolution failed: {e}") try: dz = _get_deezer_client() except Exception as e: logger.debug(f"Deezer client resolution failed: {e}") try: it = _get_itunes_client() except Exception as e: logger.debug(f"iTunes client resolution failed: {e}") try: discogs_token = config_manager.get('discogs.token', '') or '' if discogs_token: dc = _get_discogs_client(discogs_token) except Exception as e: logger.debug(f"Discogs client resolution failed: {e}") try: lastfm_api_key = config_manager.get('lastfm.api_key', '') or None except Exception: lastfm_api_key = None payload, status = build_source_only_artist_detail( artist_id, artist_name, source, spotify_client=sp, deezer_client=dz, itunes_client=it, discogs_client=dc, lastfm_api_key=lastfm_api_key, ) return jsonify(payload), status @app.route('/api/artist-detail/') def get_artist_detail(artist_id): """Get artist detail data. For library artists, `artist_id` is the local DB primary key and the full library-aware path runs (owned releases + merged source discography + per- service enrichment coverage). For source artists (Spotify/Deezer/iTunes/etc. that aren't in the library yet), pass `?source=&name=` and the endpoint synthesizes a response directly from the metadata source — no owned releases, just name + image + discography so the artist-detail page can still render. """ try: source_param = (request.args.get('source', '') or '').strip().lower() artist_name_arg = (request.args.get('name', '') or '').strip() logger.info( f"Getting artist detail for ID: {artist_id} " f"(source={source_param or 'library'})" ) # Get database instance database = get_database() # Get artist discography from database db_result = database.get_artist_discography(artist_id) # Library upgrade: if direct ID lookup missed AND we have a source hint, # check whether the user already owns this artist in the library under # a different ID (e.g. clicking a Deezer search result for an artist # they have indexed in Plex). Prefer the library record so they get # all their owned releases + enrichment instead of a bare source view. if not db_result.get('success') and source_param in _SOURCE_ONLY_ARTIST_SOURCES: library_pk = _find_library_artist_for_source( database, source_param, artist_id, artist_name_arg ) if library_pk: logger.info( f"Source-id {source_param}:{artist_id} matched library artist " f"PK={library_pk} — upgrading to library response" ) db_result = database.get_artist_discography(library_pk) if not db_result.get('success'): # Library lookup still failed. If a metadata source was specified, # fall back to a source-only response so the page can render a # non-library artist. if source_param in _SOURCE_ONLY_ARTIST_SOURCES: return _build_source_only_artist_detail( artist_id, artist_name_arg, source_param ) logger.error(f"Database returned error: {db_result}") return jsonify({ "success": False, "error": db_result.get('error', 'Artist not found') }), 404 artist_info = db_result['artist'] owned_releases = db_result['owned_releases'] logger.info(f"Found artist: {artist_info['name']} with {len(owned_releases['albums'])} albums") # Fix artist image URL logger.info(f"Artist image before fix: '{artist_info.get('image_url')}'") if artist_info.get('image_url'): artist_info['image_url'] = fix_artist_image_url(artist_info['image_url']) logger.info(f"Artist image after fix: '{artist_info['image_url']}'") else: logger.warning(f"No artist image URL found for {artist_info['name']}") # Debug final artist data being sent logger.info(f"Final artist data being sent: {artist_info}") # Fix image URLs for all albums for album in owned_releases['albums']: if album.get('image_url'): album['image_url'] = fix_artist_image_url(album['image_url']) # Fix image URLs for EPs and singles (currently empty but for future use) for ep in owned_releases['eps']: if ep.get('image_url'): ep['image_url'] = fix_artist_image_url(ep['image_url']) for single in owned_releases['singles']: if single.get('image_url'): single['image_url'] = fix_artist_image_url(single['image_url']) # Get source-priority discography for proper categorization and missing releases artist_detail_discography = None try: from core.metadata.lookup import MetadataLookupOptions from core.metadata_service import get_artist_detail_discography as _get_artist_detail_discography artist_source_ids = { 'spotify': artist_info.get('spotify_artist_id'), 'deezer': artist_info.get('deezer_id'), 'itunes': artist_info.get('itunes_artist_id'), 'discogs': artist_info.get('discogs_id'), 'hydrabase': artist_info.get('soul_id'), } artist_detail_discography = _get_artist_detail_discography( artist_id, artist_name=artist_info['name'], options=MetadataLookupOptions( allow_fallback=True, skip_cache=False, max_pages=0, # Match the Download Discography endpoint cap (200) # so the artist detail view sees the same release # set the modal lists. Spotify already paginates # all; Deezer/iTunes/Discogs/Hydrabase respect the # outer limit. 200 matches iTunes/Discogs internal # caps and covers prolific catalogues. limit=200, artist_source_ids=artist_source_ids, ), ) if artist_detail_discography['success']: logger.debug( "Source-priority discography found - " f"Albums: {len(artist_detail_discography['albums'])}, " f"EPs: {len(artist_detail_discography['eps'])}, " f"Singles: {len(artist_detail_discography['singles'])}" ) merged_discography = artist_detail_discography else: logger.debug(f"Source-priority discography not found: {artist_detail_discography.get('error', 'Unknown error')}") merged_discography = owned_releases except Exception as detail_error: logger.error(f"Error fetching source-priority discography: {detail_error}") merged_discography = owned_releases spotify_artist_data = None if artist_info.get('spotify_artist_id'): spotify_artist_data = { 'spotify_artist_id': artist_info.get('spotify_artist_id'), 'spotify_artist_name': artist_info.get('name'), 'artist_image': artist_info.get('image_url') } # Compute per-artist track enrichment coverage enrichment_coverage = {} try: with database._get_connection() as conn: cursor = conn.cursor() artist_name = artist_info['name'] server_source = artist_info.get('server_source', '') cursor.execute(""" SELECT COUNT(*) FROM tracks t JOIN albums al ON al.id = t.album_id JOIN artists ar ON ar.id = al.artist_id WHERE ar.name = ? AND ar.server_source = ? """, (artist_name, server_source)) total = (cursor.fetchone() or [0])[0] if total > 0: for svc, col in [('spotify', 'spotify_track_id'), ('musicbrainz', 'musicbrainz_recording_id'), ('deezer', 'deezer_id'), ('lastfm', 'lastfm_url'), ('itunes', 'itunes_track_id'), ('audiodb', 'audiodb_id'), ('genius', 'genius_id'), ('tidal', 'tidal_id'), ('qobuz', 'qobuz_id')]: try: cursor.execute(f""" SELECT COUNT(*) FROM tracks t JOIN albums al ON al.id = t.album_id JOIN artists ar ON ar.id = al.artist_id WHERE ar.name = ? AND ar.server_source = ? AND t.{col} IS NOT NULL AND t.{col} != '' """, (artist_name, server_source)) matched = (cursor.fetchone() or [0])[0] enrichment_coverage[svc] = round(matched / total * 100, 1) except Exception: enrichment_coverage[svc] = 0 enrichment_coverage['total_tracks'] = total except Exception as e: logger.debug("enrichment coverage build failed: %s", e) response_data = { "success": True, "artist": artist_info, "discography": merged_discography, "enrichment_coverage": enrichment_coverage } # Add Spotify artist data if available if spotify_artist_data: response_data["spotify_artist"] = spotify_artist_data return jsonify(response_data) except Exception as e: logger.error(f"Error in get_artist_detail: {e}") import traceback traceback.print_exc() return jsonify({ "success": False, "error": str(e) }), 500 @app.route('/api/library/debug-photos') def debug_library_photos(): """Debug endpoint to check artist photo URLs""" try: database = get_database() with database._get_connection() as conn: cursor = conn.cursor() # Get first 10 artists with their photo URLs cursor.execute(""" SELECT name, thumb_url, server_source FROM artists WHERE thumb_url IS NOT NULL AND thumb_url != '' LIMIT 10 """) artists_with_photos = cursor.fetchall() # Get first 10 artists without photos cursor.execute(""" SELECT name, thumb_url, server_source FROM artists WHERE thumb_url IS NULL OR thumb_url = '' LIMIT 10 """) artists_without_photos = cursor.fetchall() return jsonify({ "artists_with_photos": [dict(row) for row in artists_with_photos], "artists_without_photos": [dict(row) for row in artists_without_photos], "total_with_photos": len(artists_with_photos), "total_without_photos": len(artists_without_photos) }) except Exception as e: return jsonify({"error": str(e)}), 500 @app.route('/api/artist/similar//stream') def get_similar_artists_stream(artist_name): """Stream MusicMap similar artists using source-priority metadata matching.""" from core.metadata_service import iter_musicmap_similar_artist_events def generate(): logger.info(f"Streaming similar artists for: {artist_name}") for event in iter_musicmap_similar_artist_events(artist_name, limit=20): yield f"data: {json.dumps(event)}\n\n" if event.get('artist'): time.sleep(0.1) return Response(generate(), mimetype='text/event-stream') @app.route('/api/artist/similar/') def get_similar_artists(artist_name): """Get MusicMap similar artists using source-priority metadata matching.""" from core.metadata_service import get_musicmap_similar_artists try: logger.info(f"Getting similar artists for: {artist_name}") result = get_musicmap_similar_artists(artist_name, limit=20) if not result.get('success'): error = result.get('error', 'Failed to fetch similar artists') status_code = int(result.get('status_code') or 500) return jsonify({ "success": False, "error": error }), status_code return jsonify({ "success": True, "artist": artist_name, "similar_artists": result.get('similar_artists', []), "total_found": result.get('total_found', 0), "total_matched": result.get('total_matched', 0), "source_priority": result.get('source_priority', []), }) except Exception as e: logger.error(f"Error getting similar artists: {e}") import traceback traceback.print_exc() return jsonify({ "success": False, "error": str(e) }), 500 @app.route('/api/artist//write-image-to-disk', methods=['POST']) def write_artist_image_to_disk(artist_id): """Write `artist.jpg` to the artist's folder on disk. Issue #572 (rhwc): Navidrome has no API for setting an artist image — it reads `artist.jpg` from the artist's folder during library scans. SoulSync's `update_artist_poster` for Navidrome is a NO-OP today. This endpoint closes the gap by: 1. Resolving the artist's folder on disk via any of their albums' tracks (`_resolve_library_file_path` handles Docker mount translation + the same library-path probes #558 settled on) 2. Fetching an artist photo URL from the configured metadata source priority chain (Spotify → Deezer → ... already wired through `core.metadata_service.get_artist_image_url`) 3. Downloading the image bytes and writing `/artist.jpg` atomically via the pure helpers in `core/library/artist_image.py` 4. Triggering a Navidrome library scan so the file gets picked up immediately Request body (JSON, all optional): - ``image_url`` — explicit URL to use, bypassing metadata source resolution (useful for "use this exact photo" UX) - ``overwrite`` — when True, replace existing `artist.jpg` (default False respects user-supplied files) - ``source_override`` — pin the metadata source for URL resolution (e.g. ``"deezer"``) """ try: from core.library.artist_image import ( derive_artist_folder, download_image_bytes, write_artist_jpg, ) from core.metadata_service import get_artist_image_url as _get_artist_image_url data = request.get_json(silent=True) or {} explicit_url = (data.get('image_url') or '').strip() or None overwrite = bool(data.get('overwrite', False)) source_override = (data.get('source_override') or '').strip().lower() or None db = get_database() try: artist_id_int = int(artist_id) except (TypeError, ValueError): return jsonify({"success": False, "error": "Invalid artist id"}), 400 artist_row = db.get_artist(artist_id_int) if artist_row is None: return jsonify({"success": False, "error": "Artist not found"}), 404 # Find a track file on disk so we can derive the artist folder. # Walk albums in DB order; first one with a resolvable track wins. albums = db.get_albums_by_artist(artist_id_int) if not albums: return jsonify({"success": False, "error": "No albums for this artist; cannot derive folder."}), 400 resolved_track_path = None for album in albums: tracks = db.get_tracks_by_album(album.id) for tr in tracks: if not getattr(tr, 'file_path', None): continue candidate = _resolve_library_file_path(tr.file_path) or tr.file_path if candidate and os.path.exists(candidate): resolved_track_path = candidate break if resolved_track_path: break if not resolved_track_path: return jsonify({"success": False, "error": "Could not locate any track file on disk to derive the artist folder. " "Configure Settings → Library → Music Paths to point at the library mount."}), 400 album_folder = os.path.dirname(resolved_track_path) artist_folder = derive_artist_folder(album_folder) if not artist_folder or not os.path.isdir(artist_folder): return jsonify({"success": False, "error": f"Resolved artist folder is invalid: {artist_folder!r}"}), 400 # Pick the image URL. Explicit override (from request body) # wins so users can paste a specific photo URL. Otherwise # resolve from the active metadata source. if explicit_url: image_url = explicit_url else: try: image_url = _get_artist_image_url( artist_id_int, source_override=source_override, artist_name=getattr(artist_row, 'name', None), ) except Exception as exc: logger.error(f"artist image lookup failed: {exc}") image_url = None if not image_url: return jsonify({"success": False, "error": "No artist image URL found from metadata sources."}), 404 image_bytes = download_image_bytes(image_url) if not image_bytes: return jsonify({"success": False, "error": f"Failed to download image from {image_url}"}), 502 success, detail = write_artist_jpg(artist_folder, image_bytes, overwrite=overwrite) if not success: return jsonify({"success": False, "error": detail}), 400 # If the active media server is Navidrome, trigger a scan so # the new file gets indexed without waiting for the next # automatic scan cycle. scan_triggered = False try: active_server = config_manager.get_active_media_server() if active_server == 'navidrome': nav = media_server_engine.client('navidrome') if nav is not None: nav.trigger_library_scan() scan_triggered = True except Exception as exc: logger.debug(f"Navidrome scan trigger after artist image write failed: {exc}") return jsonify({ "success": True, "written_to": detail, "image_url": image_url, "scan_triggered": scan_triggered, }) except Exception as e: logger.error(f"Error writing artist image to disk: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/artist//image', methods=['GET']) def get_artist_image(artist_id): """Get an artist image URL using source-aware metadata resolution.""" try: from core.metadata_service import get_artist_image_url as _get_artist_image_url source_override = request.args.get('source', '').strip().lower() or None plugin = request.args.get('plugin', '').strip().lower() or None # `name` is optional but required for sources that don't store # artist images directly (MusicBrainz) — the resolver falls back # to searching iTunes/Deezer by name. artist_name = request.args.get('name', '').strip() or None image_url = _get_artist_image_url( artist_id, source_override=source_override, plugin=plugin, artist_name=artist_name, ) return jsonify({"success": True, "image_url": image_url}) except Exception as e: logger.error(f"Error fetching artist image: {e}") return jsonify({"success": False, "image_url": None, "error": str(e)}) @app.route('/api/artist//top-tracks', methods=['GET']) def get_artist_top_tracks_endpoint(artist_id): """Return an artist's top-N tracks via the primary metadata source. Issue #513: users want a "top X popular songs" path that doesn't pull the entire discography. Spotify's `artist_top_tracks` endpoint and Deezer's `/artist/{id}/top` both expose this; iTunes / Discogs / MusicBrainz don't have popularity ranking, so this endpoint returns `success=False` for those primary sources and the frontend falls back to the existing Last.fm display-only sidebar. Resolves per-source artist IDs from the DB row (matching what /discography already does) so a Spotify ID in the URL still works when Deezer is primary, and vice versa. """ try: primary_source = _get_metadata_fallback_source() if primary_source not in ('spotify', 'deezer'): return jsonify({ 'success': False, 'reason': 'unsupported_source', 'source': primary_source, 'tracks': [], }) try: limit = max(1, min(int(request.args.get('limit', 10)), 50)) except (TypeError, ValueError): limit = 10 # Per-source ID resolution from the DB — same pattern as # /discography. Without this, the frontend's chosen ID type # (Spotify, Deezer, iTunes, library DB id) decides which source # can answer; we want the URL ID to be neutral. resolved_id = artist_id try: _db = get_database() _conn = _db._get_connection() try: _cur = _conn.cursor() _cur.execute(""" SELECT spotify_artist_id, deezer_id FROM artists WHERE id = ? OR spotify_artist_id = ? OR itunes_artist_id = ? OR deezer_id = ? OR musicbrainz_id = ? LIMIT 1 """, (artist_id, artist_id, artist_id, artist_id, artist_id)) _row = _cur.fetchone() if _row: if primary_source == 'spotify' and _row['spotify_artist_id']: resolved_id = str(_row['spotify_artist_id']) elif primary_source == 'deezer' and _row['deezer_id']: resolved_id = str(_row['deezer_id']) finally: _conn.close() except Exception as e: logger.debug("top-tracks per-source ID resolution failed: %s", e) tracks = [] if primary_source == 'spotify': if not spotify_client or not spotify_client.is_spotify_authenticated(): return jsonify({ 'success': False, 'reason': 'spotify_not_authenticated', 'source': 'spotify', 'tracks': [], }) market = config_manager.get('spotify.market', 'US') or 'US' tracks = spotify_client.get_artist_top_tracks(resolved_id, country=market, limit=limit) else: # deezer deezer_client = _get_deezer_client() if not deezer_client: return jsonify({ 'success': False, 'reason': 'deezer_unavailable', 'source': 'deezer', 'tracks': [], }) tracks = deezer_client.get_artist_top_tracks(resolved_id, limit=limit) if not tracks: return jsonify({ 'success': False, 'reason': 'no_tracks_found', 'source': primary_source, 'tracks': [], }) return jsonify({ 'success': True, 'source': primary_source, 'resolved_artist_id': resolved_id, 'tracks': tracks, }) except Exception as e: logger.exception("Error fetching artist top tracks for %s", artist_id) return jsonify({"success": False, "error": str(e), "tracks": []}), 500 @app.route('/api/artist//discography', methods=['GET']) def get_artist_discography(artist_id): """Get an artist's complete discography (albums and singles)""" try: # Get optional artist name for fallback searches artist_name = request.args.get('artist_name', '').strip() # Optional source override from multi-source search tabs source_override = request.args.get('source', '').strip().lower() # Mirror to Hydrabase P2P network if hydrabase_worker and dev_mode_enabled and artist_name: hydrabase_worker.enqueue(artist_name, 'artist.albums') effective_override_source = source_override if source_override == 'hydrabase': plugin = request.args.get('plugin', '').strip().lower() if plugin == 'deezer': effective_override_source = 'deezer' elif plugin == 'itunes' or artist_id.isdigit(): effective_override_source = 'itunes' else: effective_override_source = 'spotify' from core.metadata.lookup import MetadataLookupOptions from core.metadata_service import get_artist_discography as _get_artist_discography # Server-side per-source ID resolution. Look up the library row # by ANY of the IDs the frontend might send: library DB id, # spotify_artist_id, itunes_artist_id, deezer_id, or # musicbrainz_id. Once matched, pull every stored provider ID # and dispatch the right ID to each source via # ``artist_source_ids``. Mirrors what the watchlist scanner # already does. # # Without this, the frontend's ID choice fully decides which # source can answer correctly: # - sends DB id 194687 → Deezer accepts (wrong: it's a real # Deezer ID for a different artist) # - sends Spotify ID `1bDWGdIC...` → Deezer rejects → falls # back to fuzzy name search → may pick wrong artist # With server-side resolution, every source gets its OWN stored # ID regardless of which one the URL carries. artist_source_ids = {} try: _db = get_database() _conn = _db._get_connection() try: _cur = _conn.cursor() _cur.execute(""" SELECT spotify_artist_id, itunes_artist_id, deezer_id, musicbrainz_id FROM artists WHERE id = ? OR spotify_artist_id = ? OR itunes_artist_id = ? OR deezer_id = ? OR musicbrainz_id = ? LIMIT 1 """, (artist_id, artist_id, artist_id, artist_id, artist_id)) _row = _cur.fetchone() if _row: if _row['spotify_artist_id']: artist_source_ids['spotify'] = str(_row['spotify_artist_id']) if _row['itunes_artist_id']: artist_source_ids['itunes'] = str(_row['itunes_artist_id']) if _row['deezer_id']: artist_source_ids['deezer'] = str(_row['deezer_id']) if _row['musicbrainz_id']: artist_source_ids['musicbrainz'] = str(_row['musicbrainz_id']) logger.info( f"Discography: resolved per-source IDs for artist_id={artist_id} → " f"{artist_source_ids}" ) finally: _conn.close() except Exception as _id_exc: logger.debug(f"Could not resolve per-source artist IDs for {artist_id}: {_id_exc}") discography = _get_artist_discography( artist_id, artist_name=artist_name, options=MetadataLookupOptions( source_override=effective_override_source, allow_fallback=True, skip_cache=False, max_pages=0, # Discord report: prolific artists (Bach, Beatles # complete box, deep dance/electronic catalogues) # showed only ~50 entries in the Download Discography # modal. Spotify's `max_pages=0` already paginates # through everything (per-page is clamped to 10 # internally), but Deezer / iTunes / Discogs / # Hydrabase all honor the outer `limit` as a hard # cap. 200 lines up with iTunes's and Discogs's own # internal caps and covers near-everyone's full # catalogue. limit=200, artist_source_ids=artist_source_ids or None, ), ) album_list = discography['albums'] singles_list = discography['singles'] active_source = discography['source'] source_priority = discography['source_priority'] # Gather artist enrichment info from cache + library artist_info = {} try: cache = get_metadata_cache() cache_sources = [] if active_source: cache_sources.append(active_source) for source in source_priority: if source not in cache_sources: cache_sources.append(source) # Try metadata cache for genres, image, followers cached = None for src in cache_sources: cached = cache.get_entity(src, 'artist', artist_id) if cached: break if not cached and artist_name: # Try by name across all sources for src in cache_sources: db_tmp = get_database() conn_tmp = db_tmp._get_connection() try: cur = conn_tmp.cursor() cur.execute(""" SELECT genres, image_url, followers, popularity, external_urls FROM metadata_cache_entities WHERE entity_type = 'artist' AND name COLLATE NOCASE = ? AND source = ? LIMIT 1 """, (artist_name, src)) row = cur.fetchone() if row: cached = dict(row) break finally: conn_tmp.close() if cached: try: artist_info['genres'] = json.loads(cached.get('genres', '[]')) if isinstance(cached.get('genres'), str) else (cached.get('genres') or []) except Exception: artist_info['genres'] = [] artist_info['image_url'] = cached.get('image_url') artist_info['followers'] = cached.get('followers') artist_info['popularity'] = cached.get('popularity') try: artist_info['external_urls'] = json.loads(cached.get('external_urls', '{}')) if isinstance(cached.get('external_urls'), str) else (cached.get('external_urls') or {}) except Exception: artist_info['external_urls'] = {} # Try library for full enrichment (Last.fm bio, stats, service IDs) if artist_name: db_lib = get_database() conn_lib = db_lib._get_connection() try: cur_lib = conn_lib.cursor() cur_lib.execute(""" SELECT id, summary, genres, thumb_url, spotify_artist_id, musicbrainz_id, deezer_id, itunes_artist_id, audiodb_id, discogs_id, tidal_id, qobuz_id, genius_id, soul_id, lastfm_bio, lastfm_listeners, lastfm_playcount, lastfm_tags, lastfm_url, genius_url, style, mood, label FROM artists WHERE name COLLATE NOCASE = ? LIMIT 1 """, (artist_name,)) lib_row = cur_lib.fetchone() if lib_row: lib = dict(lib_row) artist_info['library_id'] = lib['id'] # Image fallback if not artist_info.get('image_url') and lib['thumb_url']: artist_info['image_url'] = fix_artist_image_url(lib['thumb_url']) # Genres fallback if not artist_info.get('genres') and lib['genres']: try: artist_info['genres'] = json.loads(lib['genres']) except Exception as e: logger.debug("genres json parse failed: %s", e) # Last.fm enrichment if lib.get('lastfm_bio'): artist_info['lastfm_bio'] = lib['lastfm_bio'] if lib.get('lastfm_listeners'): artist_info['lastfm_listeners'] = lib['lastfm_listeners'] if lib.get('lastfm_playcount'): artist_info['lastfm_playcount'] = lib['lastfm_playcount'] if lib.get('lastfm_tags'): try: artist_info['lastfm_tags'] = json.loads(lib['lastfm_tags']) if isinstance(lib['lastfm_tags'], str) else lib['lastfm_tags'] except Exception as e: logger.debug("lastfm_tags json parse failed: %s", e) if lib.get('lastfm_url'): artist_info['lastfm_url'] = lib['lastfm_url'] if lib.get('genius_url'): artist_info['genius_url'] = lib['genius_url'] # Service IDs for badges for key in ['spotify_artist_id', 'musicbrainz_id', 'deezer_id', 'itunes_artist_id', 'audiodb_id', 'discogs_id', 'tidal_id', 'qobuz_id', 'genius_id', 'soul_id']: if lib.get(key): artist_info[key] = lib[key] # Bio fallback from summary if not artist_info.get('lastfm_bio') and lib.get('summary'): artist_info['bio'] = lib['summary'] finally: conn_lib.close() except Exception as e: logger.debug(f"Artist info enrichment failed (non-fatal): {e}") return jsonify({ "albums": album_list, "singles": singles_list, "source": active_source or (source_priority[0] if source_priority else "unknown"), "artist_info": artist_info, }) except Exception as e: logger.exception("Error fetching artist discography for %s", artist_id) return jsonify({"error": str(e)}), 500 @app.route('/api/album//tracks', methods=['GET']) def get_album_tracks(album_id): """Get tracks for specific album formatted for download missing tracks modal""" try: album_name = request.args.get('name', '').strip() artist_name = request.args.get('artist', '').strip() source_override = request.args.get('source', '').strip().lower() if source_override == 'hydrabase': plugin = request.args.get('plugin', '').strip().lower() if plugin in ('itunes', 'deezer'): source_override = plugin elif album_id.isdigit(): source_override = 'itunes' else: source_override = 'spotify' from core.metadata_service import get_artist_album_tracks as _get_artist_album_tracks result = _get_artist_album_tracks( album_id, artist_name=artist_name, album_name=album_name, source_override=source_override or None, ) if not result.get('success'): return jsonify({"error": result.get('error', 'Album not found')}), result.get('status_code', 404) logger.info( "Successfully formatted %s tracks for album %s", len(result.get('tracks', [])), result.get('album', {}).get('name', album_name or album_id), ) return jsonify({ 'success': True, 'album': result['album'], 'tracks': result['tracks'], 'source': result.get('source'), 'source_priority': result.get('source_priority', []), 'resolved_album_id': result.get('resolved_album_id'), }) except Exception as e: logger.exception("Error fetching album tracks for album %s", album_id) return jsonify({"error": str(e)}), 500 @app.route('/api/artist//download-discography', methods=['POST']) def download_discography(artist_id): """Add selected albums from an artist's discography to the wishlist. Resolves each album through the same source-aware path that the individual-album flow uses, so albums whose IDs come from a fallback/provider-specific source (e.g. Deezer-formatted IDs surfaced via Hydrabase) don't fail with "Album not found" when the primary source can't look them up directly. """ try: data = request.get_json() if not data: return jsonify({"success": False, "error": "request body required"}), 400 # Preferred payload: per-album metadata so each album can be resolved # through its own source. Falls back to the legacy album_ids list, # in which case every album is looked up under the artist-level source. albums_payload = data.get('albums') legacy_album_ids = data.get('album_ids') if not albums_payload and not legacy_album_ids: return jsonify({"success": False, "error": "albums or album_ids required"}), 400 artist_name = data.get('artist_name', 'Unknown Artist') artist_source = (data.get('source') or '').strip().lower() or None if albums_payload: album_entries = [ { 'id': str(a.get('id', '')), 'name': a.get('name') or a.get('title') or '', 'source': (a.get('source') or '').strip().lower() or artist_source, 'artist_name': a.get('artist_name') or artist_name, } for a in albums_payload if a.get('id') ] else: album_entries = [ { 'id': str(aid), 'name': '', 'source': artist_source, 'artist_name': artist_name, } for aid in legacy_album_ids if aid ] if not album_entries: return jsonify({"success": False, "error": "no valid albums in payload"}), 400 from database.music_database import MusicDatabase from core.metadata.album_tracks import get_artist_album_tracks from core.metadata.discography_filters import ( content_type_skip_reason, load_global_content_filter_settings, track_already_owned, track_artist_matches, ) db = MusicDatabase() profile_id = get_current_profile_id() # Honor the same content-type filters the watchlist scanner uses # (issue #559). One read at the top — settings don't change # mid-stream and the four bool reads aren't worth re-running per # track. content_settings = load_global_content_filter_settings(config_manager) # Library-ownership check uses the active media server so the # match is scoped to the same source whose tracks the user can # actually see in their library. None falls through to a # cross-server search inside check_track_exists. active_server = None try: active_server = config_manager.get_active_media_server() except Exception as e: logger.debug("active media server lookup failed: %s", e) total_added = 0 total_skipped = 0 total_skipped_artist = 0 total_skipped_filter = 0 total_skipped_owned = 0 def generate_ndjson(): nonlocal total_added, total_skipped, total_skipped_artist, total_skipped_filter, total_skipped_owned for entry in album_entries: album_id = entry['id'] hint_album_name = entry['name'] hint_artist = entry['artist_name'] source_override = entry['source'] try: result = get_artist_album_tracks( album_id, artist_name=hint_artist, album_name=hint_album_name, source_override=source_override, ) if not result.get('success'): message = result.get('error') or 'Album not found' yield json.dumps({ "album_id": album_id, "name": hint_album_name or album_id, "status": "error", "message": message, }) + '\n' continue album = result.get('album', {}) or {} tracks = result.get('tracks', []) or [] album_name = album.get('name') or hint_album_name or 'Unknown' album_images = album.get('images') or ( [{'url': album['image_url']}] if album.get('image_url') else [] ) album_type = album.get('album_type', 'album') release_date = album.get('release_date', '') or '' album_artists = album.get('artists') or [{'name': hint_artist}] resolved_album_id = result.get('resolved_album_id') or album.get('id') or album_id resolved_source = result.get('source') or source_override or 'unknown' if not tracks: yield json.dumps({ "album_id": album_id, "name": album_name, "status": "error", "message": "No tracks", }) + '\n' continue added = 0 skipped = 0 skipped_artist = 0 skipped_filter = 0 skipped_owned = 0 for track in tracks: track_name = track.get('name', '') if not track_name: continue track_artists = track.get('artists', []) or album_artists track_id = track.get('id', '') # Issue #559: drop tracks where the requested # artist isn't in the track's artists list # (cross-artist compilation / appears_on # contamination). Keeps features. if not track_artist_matches(track_artists, hint_artist): skipped_artist += 1 continue # Issue #559: honor watchlist global content-type # filters (live / remix / acoustic / instrumental) # for one-off discography downloads too — same # contract as the discography backfill repair job. skip_reason = content_type_skip_reason(track_name, album_name, content_settings) if skip_reason: skipped_filter += 1 continue # Skowl (Discord): clicking Download Discography # twice re-queued every track because add_to_wishlist # only dedups against the wishlist, not the library. # Same library-ownership check the discography # backfill repair job uses. Format-agnostic so # Blasphemy mode (FLAC→MP3) doesn't false-miss. if track_already_owned(db, track_name, hint_artist, album_name, active_server): skipped_owned += 1 continue spotify_track_data = { 'id': track_id, 'name': track_name, 'artists': track_artists if isinstance(track_artists, list) else [{'name': str(track_artists)}], 'album': { 'id': str(resolved_album_id), 'name': album_name, 'artists': album_artists, 'images': album_images, 'album_type': album_type, 'release_date': release_date, 'total_tracks': len(tracks), }, 'duration_ms': track.get('duration_ms', 0), 'explicit': track.get('explicit', False), 'track_number': track.get('track_number', 0), 'disc_number': track.get('disc_number', 1), 'uri': track.get('uri', ''), 'preview_url': track.get('preview_url'), 'external_urls': track.get('external_urls', {}), 'is_local': False, '_source': resolved_source, } try: was_added = db.add_to_wishlist( spotify_track_data=spotify_track_data, failure_reason="Added via Download Discography", source_type="discography", source_info=json.dumps({ 'artist_name': hint_artist, 'album_name': album_name, 'album_type': album_type, 'source': resolved_source, }), profile_id=profile_id, ) if was_added: added += 1 else: skipped += 1 except Exception: skipped += 1 total_added += added total_skipped += skipped total_skipped_artist += skipped_artist total_skipped_filter += skipped_filter total_skipped_owned += skipped_owned logger.warning( f"[Discography] {album_name} ({resolved_source}): {added} added, " f"{skipped} skipped (wishlist), {skipped_artist} skipped (artist mismatch), " f"{skipped_filter} skipped (content filter), " f"{skipped_owned} skipped (already in library)" ) yield json.dumps({ "album_id": album_id, "name": album_name, "status": "done", "tracks_added": added, "tracks_skipped": skipped, "tracks_skipped_artist": skipped_artist, "tracks_skipped_filter": skipped_filter, "tracks_skipped_owned": skipped_owned, "tracks_total": len(tracks), "source": resolved_source, }) + '\n' except Exception as album_err: yield json.dumps({ "album_id": album_id, "name": hint_album_name or album_id, "status": "error", "message": str(album_err), }) + '\n' logger.warning( f"[Discography] Complete for {artist_name}: {total_added} tracks added, " f"{total_skipped} skipped (wishlist), {total_skipped_artist} skipped (artist mismatch), " f"{total_skipped_filter} skipped (content filter), " f"{total_skipped_owned} skipped (already in library) across {len(album_entries)} albums" ) yield json.dumps({ "status": "complete", "total_added": total_added, "total_skipped": total_skipped, "total_skipped_artist": total_skipped_artist, "total_skipped_filter": total_skipped_filter, "total_skipped_owned": total_skipped_owned, "total_albums": len(album_entries), }) + '\n' return app.response_class(generate_ndjson(), mimetype='application/x-ndjson', headers={'X-Accel-Buffering': 'no'}) except Exception as e: logger.error(f"Error in download discography: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/artist//completion', methods=['POST']) def check_artist_discography_completion(artist_id): """Check completion status for artist's albums and singles""" try: data = request.get_json() if not data or 'discography' not in data: return jsonify({"error": "Missing discography data"}), 400 from core.metadata_service import check_artist_discography_completion as _check_artist_discography_completion discography = data['discography'] source_override = (data.get('source') or '').strip().lower() or None result = _check_artist_discography_completion( discography, artist_name=data.get('artist_name', 'Unknown Artist'), source_override=source_override, ) return jsonify(result) except Exception as e: logger.error(f"Error checking discography completion: {e}") import traceback traceback.print_exc() return jsonify({"error": str(e)}), 500 @app.route('/api/artist//completion-stream', methods=['POST']) def check_artist_discography_completion_stream(artist_id): """Stream completion status for artist's albums and singles one by one""" # Capture request data BEFORE the generator function try: data = request.get_json() if not data or 'discography' not in data: return jsonify({"error": "Missing discography data"}), 400 except Exception as e: return jsonify({"error": "Invalid request data"}), 400 # Extract data for the generator discography = data['discography'] artist_name = data.get('artist_name', 'Unknown Artist') source_override = (data.get('source') or '').strip().lower() or None from core.metadata_service import iter_artist_discography_completion_events def generate_completion_stream(): try: logger.info(f"Starting streaming completion check for artist: {artist_name}") for event in iter_artist_discography_completion_events( discography, artist_name=artist_name, source_override=source_override, ): yield f"data: {json.dumps(event)}\n\n" if event.get('type') in ('album_completion', 'single_completion'): # Small delay to make the streaming effect visible time.sleep(0.1) # 100ms delay between items except Exception as e: logger.error(f"Error in streaming completion check: {e}") import traceback traceback.print_exc() yield f"data: {json.dumps({'type': 'error', 'error': str(e)})}\n\n" return Response( generate_completion_stream(), content_type='text/event-stream', headers={ 'Cache-Control': 'no-cache', 'Connection': 'keep-alive', 'Access-Control-Allow-Origin': '*', 'Access-Control-Allow-Headers': 'Cache-Control' } ) @app.route('/api/library/completion-stream', methods=['POST']) def library_completion_stream(): """Stream completion status for library artist detail view - checks ownership per release via SSE""" try: data = request.get_json() if not data or 'artist_name' not in data: return jsonify({"error": "Missing artist_name"}), 400 except Exception as e: return jsonify({"error": "Invalid request data"}), 400 artist_name = data['artist_name'] def generate(): try: from core.metadata_service import check_album_completion, check_single_completion db = get_database() source_override = (data.get('source') or '').strip().lower() or None categories = ['albums', 'eps', 'singles'] all_items = [] for cat in categories: for item in data.get(cat, []): all_items.append((cat, item)) # Pre-fetch the artist's library albums AND tracks ONCE so per-item # matching runs in-memory instead of firing per-item SQL searches. # Turns N*K queries into 2 broad fetches + N track-count lookups. from config.settings import config_manager as _cm_cs _active_server = _cm_cs.get_active_media_server() candidate_albums = None candidate_tracks = None _t0 = time.perf_counter() try: candidate_albums = db.get_candidate_albums_for_artist(artist_name, server_source=_active_server) except Exception as _cand_err: print(f"[completion-stream] Failed to pre-fetch album candidates for '{artist_name}': {_cand_err}") candidate_albums = None _t1 = time.perf_counter() print(f"[completion-stream] Pre-fetched {len(candidate_albums) if candidate_albums is not None else 0} library albums for '{artist_name}' in {(_t1 - _t0) * 1000:.0f}ms") if candidate_albums: _t2 = time.perf_counter() try: candidate_tracks = db.get_candidate_tracks_for_albums([a.id for a in candidate_albums]) except Exception as _tr_err: print(f"[completion-stream] Failed to pre-fetch track candidates for '{artist_name}': {_tr_err}") candidate_tracks = None _t3 = time.perf_counter() print(f"[completion-stream] Pre-fetched {len(candidate_tracks) if candidate_tracks is not None else 0} library tracks in {(_t3 - _t2) * 1000:.0f}ms") yield f"data: {json.dumps({'type': 'start', 'total_items': len(all_items)})}\n\n" _loop_start = time.perf_counter() for _i, (category, item) in enumerate(all_items): try: # Map Library field names to helper field names mapped = { 'id': item['id'], 'name': item['title'], 'total_tracks': item.get('track_count', 0), 'album_type': item.get('album_type', 'album') } if category == 'singles': result = check_single_completion(db, mapped, artist_name, source_override=source_override, candidate_albums=candidate_albums, candidate_tracks=candidate_tracks) else: result = check_album_completion(db, mapped, artist_name, source_override=source_override, candidate_albums=candidate_albums) result['id'] = item['id'] result['category'] = category result['type'] = 'completion' yield f"data: {json.dumps(result)}\n\n" except Exception as e: yield f"data: {json.dumps({'type': 'completion', 'category': category, 'id': item['id'], 'status': 'error', 'owned_tracks': 0, 'expected_tracks': item.get('track_count', 0), 'completion_percentage': 0, 'confidence': 0.0, 'error': str(e)})}\n\n" time.sleep(0.05) # 50ms between items for visible streaming _loop_elapsed = time.perf_counter() - _loop_start _sleep_floor = 0.05 * len(all_items) print(f"[completion-stream] Processed {len(all_items)} items for '{artist_name}' in {_loop_elapsed * 1000:.0f}ms (sleep floor: {_sleep_floor * 1000:.0f}ms)") yield f"data: {json.dumps({'type': 'complete', 'processed_count': len(all_items)})}\n\n" except Exception as e: logger.error(f"Error in library completion stream: {e}") import traceback traceback.print_exc() yield f"data: {json.dumps({'type': 'error', 'error': str(e)})}\n\n" return Response( generate(), content_type='text/event-stream', headers={ 'Cache-Control': 'no-cache', 'Connection': 'keep-alive', 'Access-Control-Allow-Origin': '*', 'Access-Control-Allow-Headers': 'Cache-Control' } ) @app.route('/api/library/check-tracks', methods=['POST']) def library_check_tracks(): """Check which tracks from a list are already owned in the library. Uses a single batch DB query + in-memory fuzzy matching for speed.""" try: data = request.get_json() if not data or 'artist_name' not in data or 'tracks' not in data: return jsonify({"success": False, "error": "Missing artist_name or tracks"}), 400 artist_name = data['artist_name'] tracks = data['tracks'] from database.music_database import MusicDatabase db = MusicDatabase() active_server = config_manager.get_active_media_server() # Single query: get ALL tracks by this artist from the DB db_tracks = db.search_tracks(artist=artist_name, limit=500, server_source=active_server) if not db_tracks: # No tracks by this artist in DB — none owned owned_map = {t.get('name', ''): {"owned": False} for t in tracks if t.get('name')} return jsonify({"success": True, "owned_tracks": owned_map}) # Pre-normalize all DB track titles for fast in-memory comparison from difflib import SequenceMatcher try: from unidecode import unidecode except ImportError: unidecode = lambda x: x def _normalize(text): if not text: return "" return unidecode(text).lower().strip() def _clean_title(text): import re cleaned = _normalize(text) # Remove parenthetical/bracket content, dashes, feat/ft, remaster tags cleaned = re.sub(r'\s*[\[\(].*?[\]\)]', '', cleaned) cleaned = re.sub(r'\s*-\s*', ' ', cleaned) cleaned = re.sub(r'\s*feat\..*', '', cleaned) cleaned = re.sub(r'\s*featuring.*', '', cleaned) cleaned = re.sub(r'\s*ft\..*', '', cleaned) cleaned = re.sub(r'\s*\d{4}\s*remaster.*', '', cleaned) cleaned = re.sub(r'\s*remaster(ed)?.*', '', cleaned) cleaned = re.sub(r'\s+', ' ', cleaned).strip() return cleaned # Pre-compute normalized DB titles once (keep reference to db_track for metadata) db_title_entries = [(_normalize(t.title), _clean_title(t.title), t) for t in db_tracks] # Album-aware matching: if album_name provided, prefer tracks from that album target_album = data.get('album_name', '') target_album_norm = _normalize(target_album) if target_album else '' def _match_title(search_norm, search_clean, candidates): """Find best matching track from a list of (norm, clean, db_track) candidates.""" for db_norm, db_clean, db_track in candidates: if search_norm == db_norm or search_clean == db_clean: return db_track sim = max( SequenceMatcher(None, search_norm, db_norm).ratio(), SequenceMatcher(None, search_clean, db_clean).ratio() ) if sim >= 0.7: return db_track return None # Split DB tracks by album if album-aware matching is active album_entries = [] other_entries = [] if target_album_norm: for entry in db_title_entries: db_album = _normalize(getattr(entry[2], 'album_title', '') or '') if db_album and SequenceMatcher(None, target_album_norm, db_album).ratio() >= 0.7: album_entries.append(entry) else: other_entries.append(entry) else: other_entries = db_title_entries owned_map = {} for track in tracks: track_name = track.get('name', '') if not track_name: continue search_norm = _normalize(track_name) search_clean = _clean_title(track_name) # When album context provided, only match within that album — # prevents false positives where "Thriller" on Album A shows as owned # because it exists on Album B. Without album context, search all tracks. if target_album_norm: matched_db_track = _match_title(search_norm, search_clean, album_entries) else: matched_db_track = _match_title(search_norm, search_clean, other_entries) if matched_db_track: import os file_ext = os.path.splitext(matched_db_track.file_path or '')[1].lstrip('.').upper() or None owned_map[track_name] = { "owned": True, "format": file_ext, "bitrate": matched_db_track.bitrate, "album": getattr(matched_db_track, 'album_title', None) } else: owned_map[track_name] = {"owned": False} return jsonify({"success": True, "owned_tracks": owned_map}) except Exception as e: logger.error(f"Error checking track ownership: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 # ==================== Enhanced Library Management Endpoints ==================== @app.route('/api/library/artist//enhanced') def get_artist_enhanced_detail(artist_id): """Get full artist detail with all albums and tracks for enhanced library view.""" try: database = get_database() result = database.get_artist_full_detail(artist_id) if not result.get('success'): return jsonify(result), 404 # Fix image URLs for artist and all albums (resolve Plex/Jellyfin relative paths) if result.get('artist', {}).get('thumb_url'): result['artist']['thumb_url'] = fix_artist_image_url(result['artist']['thumb_url']) for album in result.get('albums', []): if album.get('thumb_url'): album['thumb_url'] = fix_artist_image_url(album['thumb_url']) # Include server type for sync option — engine routes to active client. active_server = config_manager.get_active_media_server() server_connected = media_server_engine.is_connected() if media_server_engine else False result['server_type'] = active_server if server_connected else None return jsonify(result) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/artist//quality-analysis') def get_artist_quality_analysis(artist_id): """Analyze track quality for an artist — returns tier classification for each track.""" try: database = get_database() result = database.get_artist_full_detail(artist_id) if not result.get('success'): return jsonify(result), 404 artist = result.get('artist', {}) albums = result.get('albums', []) # Get user's quality profile to determine min acceptable tier quality_profile = database.get_quality_profile() preferred_qualities = quality_profile.get('qualities', {}) min_acceptable_tier = 999 tier_map = {'flac': 'lossless', 'mp3_320': 'low_lossy', 'mp3_256': 'low_lossy', 'mp3_192': 'low_lossy'} for qname, qconfig in preferred_qualities.items(): if qconfig.get('enabled', False): tname = tier_map.get(qname) if tname and tname in QUALITY_TIERS: min_acceptable_tier = min(min_acceptable_tier, QUALITY_TIERS[tname]['tier']) tracks = [] summary = {'total': 0, 'lossless': 0, 'high_lossy': 0, 'standard_lossy': 0, 'low_lossy': 0, 'unknown': 0} for album in albums: album_title = album.get('title', 'Unknown Album') album_id = album.get('id') for track in album.get('tracks', []): file_path = track.get('file_path') if not file_path: continue tier_name, tier_num = _get_quality_tier_from_extension(file_path) ext = os.path.splitext(file_path)[1].lstrip('.').upper() # Use filename as fallback when title is empty title = track.get('title', '') or '' if not title.strip(): title = os.path.splitext(os.path.basename(file_path))[0] tracks.append({ 'track_id': track.get('id'), 'title': title, 'album_title': album_title, 'album_id': album_id, 'file_path': file_path, 'format': ext or 'Unknown', 'tier_name': tier_name, 'tier_num': tier_num, 'bitrate': track.get('bitrate'), 'spotify_track_id': track.get('spotify_track_id'), 'track_number': track.get('track_number'), 'disc_number': track.get('disc_number'), }) summary['total'] += 1 if tier_name in summary: summary[tier_name] += 1 else: summary['unknown'] += 1 return jsonify({ 'success': True, 'artist_name': artist.get('name', 'Unknown Artist'), 'artist_id': artist_id, 'tracks': tracks, 'quality_summary': summary, 'min_acceptable_tier': min_acceptable_tier }) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 # Artist quality enhancement logic lives in core/artists/quality.py. from core.artists import quality as _artists_quality def _build_artist_quality_deps(): """Build the ArtistQualityDeps bundle from web_server.py globals on each call.""" from core.wishlist_service import get_wishlist_service as _get_ws def _resolve_search_sources(): """Mirror the Track Redownload modal's source list. Every configured metadata source contributes to the parallel multi-source search — Spotify (only when authenticated), iTunes, Deezer, plus Discogs / Hydrabase when configured.""" sources = [] if spotify_client and spotify_client.is_authenticated(): sources.append(('spotify', spotify_client)) try: sources.append(('itunes', _get_itunes_client())) except Exception as e: logger.debug("itunes client init failed: %s", e) try: sources.append(('deezer', _get_deezer_client())) except Exception as e: logger.debug("deezer client init failed: %s", e) # Discogs needs an explicit token; only include when configured. try: _discogs_token = config_manager.get('discogs.token', '') if _discogs_token: sources.append(('discogs', _get_discogs_client(_discogs_token))) except Exception as e: logger.debug("discogs client init failed: %s", e) # Hydrabase only when connected (dev-mode + active client). try: if hydrabase_client and hydrabase_client.is_connected(): sources.append(('hydrabase', hydrabase_client)) except Exception as e: logger.debug("hydrabase client check failed: %s", e) return sources return _artists_quality.ArtistQualityDeps( matching_engine=matching_engine, get_database=get_database, get_wishlist_service=_get_ws, get_current_profile_id=get_current_profile_id, get_quality_tier_from_extension=_get_quality_tier_from_extension, get_metadata_search_sources=_resolve_search_sources, ) @app.route('/api/library/artist//enhance', methods=['POST']) def enhance_artist_quality(artist_id): """Add selected tracks to wishlist for quality enhancement re-download.""" try: data = request.get_json() or {} track_ids = data.get('track_ids', []) payload, status = _artists_quality.enhance_artist_quality( artist_id, track_ids, _build_artist_quality_deps() ) return jsonify(payload), status except Exception as e: logger.error(f"[Enhance] {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/artist/', methods=['PUT']) def update_library_artist(artist_id): """Update artist metadata fields.""" try: database = get_database() data = request.get_json() if not data: return jsonify({"success": False, "error": "No data provided"}), 400 result = database.update_artist_fields(artist_id, data) if not result.get('success'): return jsonify(result), 400 return jsonify(result) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/album/', methods=['PUT']) def update_library_album(album_id): """Update album metadata fields.""" try: database = get_database() data = request.get_json() if not data: return jsonify({"success": False, "error": "No data provided"}), 400 result = database.update_album_fields(album_id, data) if not result.get('success'): return jsonify(result), 400 return jsonify(result) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/track/', methods=['PUT']) def update_library_track(track_id): """Update track metadata fields.""" try: database = get_database() data = request.get_json() if not data: return jsonify({"success": False, "error": "No data provided"}), 400 result = database.update_track_fields(track_id, data) if not result.get('success'): return jsonify(result), 400 return jsonify(result) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/tracks/batch', methods=['PUT']) def batch_update_library_tracks(): """Batch update multiple tracks with the same field values.""" try: database = get_database() data = request.get_json() if not data: return jsonify({"success": False, "error": "No data provided"}), 400 track_ids = data.get('track_ids', []) updates = data.get('updates', {}) if not track_ids or not updates: return jsonify({"success": False, "error": "track_ids and updates are required"}), 400 result = database.batch_update_tracks(track_ids, updates) if not result.get('success'): return jsonify(result), 400 return jsonify(result) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 # ── Write Tags to File endpoints ── @app.route('/api/library/track//tag-preview', methods=['GET']) def get_track_tag_preview(track_id): """Read current file tags and compare against DB metadata for a single track.""" try: from core.tag_writer import read_file_tags, build_tag_diff database = get_database() # Get track + album + artist data from DB conn = database._get_connection() cursor = conn.cursor() cursor.execute(""" SELECT t.*, a.name as artist_name, al.title as album_title, al.year, al.genres as album_genres, al.track_count, al.thumb_url as album_thumb_url, a.thumb_url as artist_thumb_url FROM tracks t JOIN artists a ON t.artist_id = a.id JOIN albums al ON t.album_id = al.id WHERE t.id = ? """, (str(track_id),)) row = cursor.fetchone() if not row: return jsonify({"success": False, "error": "Track not found"}), 404 track_data = dict(row) file_path = track_data.get('file_path') # Resolve path if needed resolved_path = _resolve_library_file_path(file_path) if not resolved_path: return jsonify({"success": False, "error": _get_file_not_found_error(file_path), "file_path": file_path}), 404 # Read current file tags file_tags = read_file_tags(resolved_path) if file_tags.get('error'): return jsonify({"success": False, "error": file_tags['error']}), 400 # Parse album genres for diff album_genres = [] if track_data.get('album_genres'): try: import json as _json parsed = _json.loads(track_data['album_genres']) album_genres = parsed if isinstance(parsed, list) else [str(parsed)] except (ValueError, TypeError): album_genres = [g.strip() for g in track_data['album_genres'].split(',') if g.strip()] # Build DB metadata dict for comparison db_data = { 'title': track_data.get('title'), 'artist_name': track_data.get('artist_name'), 'track_artist': track_data.get('track_artist'), 'album_title': track_data.get('album_title'), 'year': track_data.get('year'), 'genres': album_genres, 'track_number': track_data.get('track_number'), 'disc_number': track_data.get('disc_number'), 'bpm': track_data.get('bpm'), 'track_count': track_data.get('track_count'), 'thumb_url': track_data.get('album_thumb_url') or track_data.get('artist_thumb_url'), } diff = build_tag_diff(file_tags, db_data) has_changes = any(d['changed'] for d in diff) # Include server type so frontend can offer server sync option active_server = config_manager.get_active_media_server() server_connected = media_server_engine.is_connected() if media_server_engine else False return jsonify({ "success": True, "file_path": resolved_path, "file_tags": file_tags, "db_data": db_data, "diff": diff, "has_changes": has_changes, "server_type": active_server if server_connected else None, }) except Exception as e: logger.error(f"Tag preview error for track {track_id}: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/tracks/tag-preview-batch', methods=['POST']) def get_batch_tag_preview(): """Read current file tags and compare against DB metadata for multiple tracks.""" try: from core.tag_writer import read_file_tags, build_tag_diff data = request.get_json() track_ids = data.get('track_ids', []) if not track_ids: return jsonify({"success": False, "error": "No track IDs provided"}), 400 database = get_database() conn = database._get_connection() cursor = conn.cursor() placeholders = ','.join('?' for _ in track_ids) cursor.execute(f""" SELECT t.*, a.name as artist_name, al.title as album_title, al.year, al.genres as album_genres, al.track_count, al.thumb_url as album_thumb_url, a.thumb_url as artist_thumb_url FROM tracks t JOIN artists a ON t.artist_id = a.id JOIN albums al ON t.album_id = al.id WHERE t.id IN ({placeholders}) """, [str(tid) for tid in track_ids]) rows = [dict(r) for r in cursor.fetchall()] results = [] for track_data in rows: track_id = track_data['id'] file_path = track_data.get('file_path') resolved_path = _resolve_library_file_path(file_path) entry = { 'track_id': track_id, 'title': track_data.get('title', 'Unknown'), 'track_number': track_data.get('track_number'), } if not resolved_path: entry['error'] = _get_file_not_found_error(file_path) results.append(entry) continue try: file_tags = read_file_tags(resolved_path) if file_tags.get('error'): entry['error'] = file_tags['error'] results.append(entry) continue album_genres = [] if track_data.get('album_genres'): try: parsed = json.loads(track_data['album_genres']) album_genres = parsed if isinstance(parsed, list) else [str(parsed)] except (ValueError, TypeError): album_genres = [g.strip() for g in track_data['album_genres'].split(',') if g.strip()] db_data = { 'title': track_data.get('title'), 'artist_name': track_data.get('artist_name'), 'album_title': track_data.get('album_title'), 'year': track_data.get('year'), 'genres': album_genres, 'track_number': track_data.get('track_number'), 'disc_number': track_data.get('disc_number'), 'bpm': track_data.get('bpm'), 'track_count': track_data.get('track_count'), 'thumb_url': track_data.get('album_thumb_url') or track_data.get('artist_thumb_url'), } diff = build_tag_diff(file_tags, db_data) has_changes = any(d['changed'] for d in diff) changed_fields = [d for d in diff if d['changed']] entry['diff'] = diff entry['has_changes'] = has_changes entry['changed_count'] = len(changed_fields) except Exception as e: entry['error'] = str(e) results.append(entry) # Server type info — engine routes to active client. active_server = config_manager.get_active_media_server() server_connected = media_server_engine.is_connected() if media_server_engine else False return jsonify({ "success": True, "tracks": results, "server_type": active_server if server_connected else None, }) except Exception as e: logger.error(f"Batch tag preview error: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/track//write-tags', methods=['POST']) def write_track_tags(track_id): """Write DB metadata into the audio file tags for a single track.""" try: from core.tag_writer import write_tags_to_file database = get_database() data = request.get_json() or {} embed_cover = data.get('embed_cover', True) # Get full track data conn = database._get_connection() cursor = conn.cursor() cursor.execute(""" SELECT t.*, a.name as artist_name, al.title as album_title, al.year, al.genres as album_genres, al.track_count, al.thumb_url as album_thumb_url, a.thumb_url as artist_thumb_url FROM tracks t JOIN artists a ON t.artist_id = a.id JOIN albums al ON t.album_id = al.id WHERE t.id = ? """, (str(track_id),)) row = cursor.fetchone() if not row: return jsonify({"success": False, "error": "Track not found"}), 404 track_data = dict(row) file_path = track_data.get('file_path') resolved_path = _resolve_library_file_path(file_path) if not resolved_path: return jsonify({"success": False, "error": _get_file_not_found_error(file_path)}), 404 # Parse genres album_genres = [] if track_data.get('album_genres'): try: import json as _json parsed = _json.loads(track_data['album_genres']) album_genres = parsed if isinstance(parsed, list) else [str(parsed)] except (ValueError, TypeError): album_genres = [g.strip() for g in track_data['album_genres'].split(',') if g.strip()] # Build data for writer db_data = { 'title': track_data.get('title'), 'artist_name': track_data.get('artist_name'), 'album_title': track_data.get('album_title'), 'year': track_data.get('year'), 'genres': album_genres, 'track_number': track_data.get('track_number'), 'disc_number': track_data.get('disc_number'), 'bpm': track_data.get('bpm'), 'track_count': track_data.get('track_count'), } # Resolve cover URL cover_url = None if embed_cover: thumb = track_data.get('album_thumb_url') or track_data.get('artist_thumb_url') if thumb and thumb.startswith('http'): cover_url = thumb # Use file lock for thread safety file_lock = get_file_lock(resolved_path) with file_lock: result = write_tags_to_file(resolved_path, db_data, embed_cover=embed_cover, cover_url=cover_url) # Sync to media server if requested and write succeeded sync_result = None if result.get('success') and data.get('sync_to_server'): server_type = config_manager.get_active_media_server() sync_result = _sync_tracks_to_server([track_data], server_type) result['server_sync'] = sync_result return jsonify(result) except Exception as e: logger.error(f"Write tags error for track {track_id}: {e}") return jsonify({"success": False, "error": str(e)}), 500 _write_tags_batch_state = { 'status': 'idle', # idle | running | done 'total': 0, 'processed': 0, 'written': 0, 'failed': 0, 'current_track': '', 'errors': [], 'sync_phase': None, # None | 'syncing' | 'done' 'sync_server': None, 'sync_synced': 0, 'sync_failed': 0, } _write_tags_batch_lock = threading.Lock() @app.route('/api/library/tracks/write-tags-batch', methods=['POST']) def write_tracks_tags_batch(): """Write DB metadata into audio file tags for multiple tracks (runs in background).""" try: with _write_tags_batch_lock: if _write_tags_batch_state['status'] == 'running': return jsonify({"success": False, "error": "A batch tag write is already in progress"}), 409 database = get_database() data = request.get_json() if not data or not data.get('track_ids'): return jsonify({"success": False, "error": "track_ids required"}), 400 track_ids = data['track_ids'] embed_cover = data.get('embed_cover', True) # Fetch all track data upfront (in the request thread, fast DB query) conn = database._get_connection() cursor = conn.cursor() placeholders = ','.join('?' * len(track_ids)) cursor.execute(f""" SELECT t.*, a.name as artist_name, al.title as album_title, al.year, al.genres as album_genres, al.track_count, al.thumb_url as album_thumb_url, a.thumb_url as artist_thumb_url FROM tracks t JOIN artists a ON t.artist_id = a.id JOIN albums al ON t.album_id = al.id WHERE t.id IN ({placeholders}) """, [str(tid) for tid in track_ids]) rows = [dict(r) for r in cursor.fetchall()] sync_to_server = data.get('sync_to_server', False) # Initialize state with _write_tags_batch_lock: _write_tags_batch_state.update({ 'status': 'running', 'total': len(track_ids), 'processed': 0, 'written': 0, 'failed': 0, 'current_track': '', 'errors': [], 'sync_phase': None, 'sync_server': None, 'sync_synced': 0, 'sync_failed': 0, }) # Count missing DB rows found_ids = {str(r['id']) for r in rows} missing = [tid for tid in track_ids if str(tid) not in found_ids] if missing: with _write_tags_batch_lock: _write_tags_batch_state['failed'] += len(missing) _write_tags_batch_state['processed'] += len(missing) for tid in missing: _write_tags_batch_state['errors'].append({'track_id': tid, 'error': 'Track not found in database'}) # Run the actual writes in a background thread def _run_batch(): try: from core.tag_writer import write_tags_to_file, download_cover_art written_tracks = [] # Track dicts that were successfully written (for server sync) # Pre-download cover art once per unique album URL cover_cache = {} # url → (bytes, mime) or None if embed_cover: unique_urls = set() for td in rows: thumb = td.get('album_thumb_url') or td.get('artist_thumb_url') if thumb and thumb.startswith('http'): unique_urls.add(thumb) if unique_urls: with _write_tags_batch_lock: _write_tags_batch_state['current_track'] = f'Downloading cover art ({len(unique_urls)} album{"s" if len(unique_urls) != 1 else ""})...' for url in unique_urls: cover_cache[url] = download_cover_art(url) for track_data in rows: file_path = track_data.get('file_path') resolved_path = _resolve_library_file_path(file_path) track_title = track_data.get('title', 'Unknown') with _write_tags_batch_lock: _write_tags_batch_state['current_track'] = track_title if not resolved_path: with _write_tags_batch_lock: _write_tags_batch_state['failed'] += 1 _write_tags_batch_state['processed'] += 1 _write_tags_batch_state['errors'].append({'track_id': track_data['id'], 'error': _get_file_not_found_error(file_path)}) continue # Parse genres album_genres = [] if track_data.get('album_genres'): try: parsed = json.loads(track_data['album_genres']) album_genres = parsed if isinstance(parsed, list) else [str(parsed)] except (ValueError, TypeError): album_genres = [g.strip() for g in track_data['album_genres'].split(',') if g.strip()] db_data = { 'title': track_data.get('title'), 'artist_name': track_data.get('artist_name'), 'album_title': track_data.get('album_title'), 'year': track_data.get('year'), 'genres': album_genres, 'track_number': track_data.get('track_number'), 'disc_number': track_data.get('disc_number'), 'bpm': track_data.get('bpm'), 'track_count': track_data.get('track_count'), } # Get pre-downloaded cover art for this track's album art_data = None if embed_cover: thumb = track_data.get('album_thumb_url') or track_data.get('artist_thumb_url') if thumb and thumb.startswith('http'): art_data = cover_cache.get(thumb) file_lock = get_file_lock(resolved_path) with file_lock: write_result = write_tags_to_file( resolved_path, db_data, embed_cover=embed_cover, cover_data=art_data ) with _write_tags_batch_lock: _write_tags_batch_state['processed'] += 1 if write_result.get('success'): _write_tags_batch_state['written'] += 1 written_tracks.append(track_data) else: _write_tags_batch_state['failed'] += 1 _write_tags_batch_state['errors'].append({ 'track_id': track_data['id'], 'error': write_result.get('error', 'Unknown') }) # Server sync phase if sync_to_server and written_tracks: server_type = config_manager.get_active_media_server() with _write_tags_batch_lock: _write_tags_batch_state['sync_phase'] = 'syncing' _write_tags_batch_state['sync_server'] = server_type _write_tags_batch_state['current_track'] = f'Syncing to {server_type.title()}...' sync_result = _sync_tracks_to_server(written_tracks, server_type) with _write_tags_batch_lock: _write_tags_batch_state['sync_phase'] = 'done' _write_tags_batch_state['sync_synced'] = sync_result['synced'] _write_tags_batch_state['sync_failed'] = sync_result['failed'] except Exception as e: logger.error(f"Batch write tags background error: {e}") finally: with _write_tags_batch_lock: _write_tags_batch_state['status'] = 'done' _write_tags_batch_state['current_track'] = '' thread = threading.Thread(target=_run_batch, daemon=True, name="WriteTagsBatch") thread.start() return jsonify({"success": True, "message": "Batch tag write started", "total": len(track_ids)}) except Exception as e: logger.error(f"Batch write tags error: {e}") with _write_tags_batch_lock: _write_tags_batch_state['status'] = 'idle' return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/tracks/write-tags-batch/status', methods=['GET']) def get_write_tags_batch_status(): """Poll the status of a running batch tag write.""" with _write_tags_batch_lock: state = dict(_write_tags_batch_state) state['errors'] = list(_write_tags_batch_state['errors']) # snapshot to avoid mutation during serialize return jsonify(state) # ── ReplayGain Analysis endpoints ── from core.replaygain import ( analyze_track as _rg_analyze_track, write_replaygain_tags as _rg_write_tags, is_ffmpeg_available as _rg_ffmpeg_available, RG_REFERENCE_LUFS as _RG_REFERENCE_LUFS, ) # State machine for album-level ReplayGain jobs _rg_album_state = { 'status': 'idle', # idle | running | done 'album_id': None, 'total': 0, 'processed': 0, 'analyzed': 0, 'failed': 0, 'current_track': '', 'errors': [], } _rg_album_lock = threading.Lock() # State machine for selected-tracks batch ReplayGain jobs _rg_batch_state = { 'status': 'idle', 'total': 0, 'processed': 0, 'analyzed': 0, 'failed': 0, 'current_track': '', 'errors': [], } _rg_batch_lock = threading.Lock() @app.route('/api/library/track//analyze-replaygain', methods=['POST']) def analyze_track_replaygain(track_id): """ Analyze a single track and write ReplayGain track-level tags immediately. Synchronous — runs FFmpeg inline (typically 1–3 s per track). """ if not _rg_ffmpeg_available(): return jsonify({'success': False, 'error': 'ffmpeg not found on PATH'}), 500 database = get_database() conn = database._get_connection() cursor = conn.cursor() cursor.execute("SELECT * FROM tracks WHERE id = ?", (str(track_id),)) row = cursor.fetchone() if not row: return jsonify({'success': False, 'error': 'Track not found'}), 404 file_path = _resolve_library_file_path(dict(row).get('file_path')) if not file_path: return jsonify({'success': False, 'error': 'File not found on disk'}), 404 try: lufs, peak_dbfs = _rg_analyze_track(file_path) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 track_gain_db = _RG_REFERENCE_LUFS - lufs file_lock = get_file_lock(file_path) with file_lock: ok = _rg_write_tags(file_path, track_gain_db, peak_dbfs) if not ok: return jsonify({'success': False, 'error': 'Failed to write tags to file'}), 500 return jsonify({ 'success': True, 'track_gain': f"{track_gain_db:+.2f} dB", 'track_peak': f"{10 ** (peak_dbfs / 20.0):.6f}", 'lufs': round(lufs, 2), }) @app.route('/api/library/album//analyze-replaygain', methods=['POST']) def analyze_album_replaygain(album_id): """ Analyze all tracks in an album and write both track-level and album-level ReplayGain tags. Runs in a background thread — poll /status for progress. """ with _rg_album_lock: if _rg_album_state['status'] == 'running': return jsonify({'success': False, 'error': 'An album ReplayGain job is already running'}), 409 if not _rg_ffmpeg_available(): return jsonify({'success': False, 'error': 'ffmpeg not found on PATH'}), 500 database = get_database() conn = database._get_connection() cursor = conn.cursor() cursor.execute( "SELECT * FROM tracks WHERE album_id = ? ORDER BY track_number, title", (album_id,) ) tracks = [dict(r) for r in cursor.fetchall()] if not tracks: return jsonify({'success': False, 'error': 'No tracks found for this album'}), 404 with _rg_album_lock: _rg_album_state.update({ 'status': 'running', 'album_id': album_id, 'total': len(tracks), 'processed': 0, 'analyzed': 0, 'failed': 0, 'current_track': '', 'errors': [], }) def _run_album(): lufs_values = [] peak_values = [] track_results = [] # (file_path, track_gain_db, peak_dbfs) # Pass 1: analyze every track for track in tracks: file_path = _resolve_library_file_path(track.get('file_path')) title = track.get('title') or track.get('file_path') or '' with _rg_album_lock: _rg_album_state['current_track'] = title if not file_path: with _rg_album_lock: _rg_album_state['failed'] += 1 _rg_album_state['errors'].append({'track': title, 'error': 'File not found'}) _rg_album_state['processed'] += 1 track_results.append(None) continue try: lufs, peak_dbfs = _rg_analyze_track(file_path) lufs_values.append(lufs) peak_values.append(peak_dbfs) track_gain_db = _RG_REFERENCE_LUFS - lufs track_results.append((file_path, track_gain_db, peak_dbfs)) with _rg_album_lock: _rg_album_state['analyzed'] += 1 _rg_album_state['processed'] += 1 except Exception as e: with _rg_album_lock: _rg_album_state['failed'] += 1 _rg_album_state['errors'].append({'track': title, 'error': str(e)}) _rg_album_state['processed'] += 1 track_results.append(None) # Compute album gain from tracks that analyzed successfully album_gain_db = None album_peak_dbfs = None if lufs_values: mean_lufs = sum(lufs_values) / len(lufs_values) album_gain_db = _RG_REFERENCE_LUFS - mean_lufs album_peak_dbfs = max(peak_values) # Pass 2: write tags to every successfully analyzed track for i, track in enumerate(tracks): entry = track_results[i] if entry is None: continue file_path, track_gain_db, peak_dbfs = entry try: file_lock = get_file_lock(file_path) with file_lock: _rg_write_tags(file_path, track_gain_db, peak_dbfs, album_gain_db, album_peak_dbfs) except Exception as e: with _rg_album_lock: _rg_album_state['failed'] += 1 _rg_album_state['errors'].append({'track': track.get('title', ''), 'error': str(e)}) with _rg_album_lock: _rg_album_state['status'] = 'done' _rg_album_state['current_track'] = '' threading.Thread(target=_run_album, daemon=True, name='RgAlbum').start() return jsonify({'success': True}) @app.route('/api/library/album//analyze-replaygain/status', methods=['GET']) def get_album_replaygain_status(album_id): """Poll the status of a running album ReplayGain job.""" with _rg_album_lock: state = dict(_rg_album_state) state['errors'] = list(_rg_album_state['errors']) return jsonify(state) @app.route('/api/library/tracks/analyze-replaygain-batch', methods=['POST']) def analyze_tracks_replaygain_batch(): """ Analyze a set of selected tracks and write track-level ReplayGain tags. No album gain is computed (tracks may span multiple albums). Runs in a background thread — poll /status for progress. """ with _rg_batch_lock: if _rg_batch_state['status'] == 'running': return jsonify({'success': False, 'error': 'A batch ReplayGain job is already running'}), 409 if not _rg_ffmpeg_available(): return jsonify({'success': False, 'error': 'ffmpeg not found on PATH'}), 500 data = request.get_json() or {} track_ids = data.get('track_ids', []) if not track_ids: return jsonify({'success': False, 'error': 'No track IDs provided'}), 400 database = get_database() conn = database._get_connection() cursor = conn.cursor() placeholders = ','.join('?' for _ in track_ids) cursor.execute( f"SELECT * FROM tracks WHERE id IN ({placeholders})", [str(tid) for tid in track_ids] ) tracks = [dict(r) for r in cursor.fetchall()] if not tracks: return jsonify({'success': False, 'error': 'No valid tracks found'}), 404 with _rg_batch_lock: _rg_batch_state.update({ 'status': 'running', 'total': len(tracks), 'processed': 0, 'analyzed': 0, 'failed': 0, 'current_track': '', 'errors': [], }) def _run_batch(): for track in tracks: file_path = _resolve_library_file_path(track.get('file_path')) title = track.get('title') or track.get('file_path') or '' with _rg_batch_lock: _rg_batch_state['current_track'] = title if not file_path: with _rg_batch_lock: _rg_batch_state['failed'] += 1 _rg_batch_state['errors'].append({'track': title, 'error': 'File not found'}) _rg_batch_state['processed'] += 1 continue try: lufs, peak_dbfs = _rg_analyze_track(file_path) track_gain_db = _RG_REFERENCE_LUFS - lufs file_lock = get_file_lock(file_path) with file_lock: _rg_write_tags(file_path, track_gain_db, peak_dbfs) with _rg_batch_lock: _rg_batch_state['analyzed'] += 1 _rg_batch_state['processed'] += 1 except Exception as e: with _rg_batch_lock: _rg_batch_state['failed'] += 1 _rg_batch_state['errors'].append({'track': title, 'error': str(e)}) _rg_batch_state['processed'] += 1 with _rg_batch_lock: _rg_batch_state['status'] = 'done' _rg_batch_state['current_track'] = '' threading.Thread(target=_run_batch, daemon=True, name='RgBatch').start() return jsonify({'success': True}) @app.route('/api/library/tracks/analyze-replaygain-batch/status', methods=['GET']) def get_tracks_replaygain_batch_status(): """Poll the status of a running batch ReplayGain job.""" with _rg_batch_lock: state = dict(_rg_batch_state) state['errors'] = list(_rg_batch_state['errors']) return jsonify(state) # ── Reorganize Album Files endpoints ── # # Reorganize requests flow through ``core.reorganize_queue`` — a FIFO # queue with a single background worker. The endpoints here are thin # enqueue / snapshot / cancel wrappers; the heavy lifting is in # :mod:`core.library_reorganize`. @app.route('/api/library/reorganize/sources', methods=['GET']) def reorganize_sources_global(): """List metadata sources the user has authed on this instance. Used by the bulk "Reorganize All" modal where per-album ID coverage varies. No network calls.""" try: from core.library_reorganize import authed_sources return jsonify({"success": True, "sources": authed_sources()}) except Exception as e: logger.error(f"Reorganize sources (global) error: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/album//reorganize/sources', methods=['GET']) def reorganize_album_sources(album_id): """List metadata sources the user can pick for this album's reorganize — every entry has both a stored album ID on the local row AND an authenticated client. No network calls.""" try: from core.library_reorganize import available_sources_for_album, load_album_and_tracks album_data, _tracks = load_album_and_tracks(get_database(), album_id) if album_data is None: return jsonify({"success": False, "error": "Album not found"}), 404 return jsonify({"success": True, "sources": available_sources_for_album(album_data)}) except Exception as e: logger.error(f"Reorganize sources error: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/album//reorganize/preview', methods=['POST']) def reorganize_album_preview(album_id): """Preview file reorganization for an album — returns current vs proposed paths without moving anything. Implementation lives in :mod:`core.library_reorganize` and shares the planning logic with the apply endpoint, so the preview is guaranteed to match what apply would actually produce. Optional body param ``source``: when provided, only that metadata source is queried (no fallback chain).""" try: from core.library_reorganize import preview_album_reorganize data = request.get_json() or {} chosen_source = data.get('source') or None transfer_dir = docker_resolve_path(config_manager.get('soulseek.transfer_path', './Transfer')) result = preview_album_reorganize( album_id=album_id, db=get_database(), transfer_dir=transfer_dir, resolve_file_path_fn=_resolve_library_file_path, build_final_path_fn=_build_final_path_for_track, primary_source=chosen_source, strict_source=bool(chosen_source), ) if result.get('status') == 'no_album': return jsonify({"success": False, "error": "Album not found"}), 404 if result.get('status') == 'no_tracks': return jsonify({"success": False, "error": "No tracks found for this album"}), 404 return jsonify(result) except Exception as e: logger.error(f"Reorganize preview error: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/album//reorganize', methods=['POST']) def reorganize_album_files(album_id): """Enqueue an album for reorganize. Returns immediately — the queue worker processes items FIFO. Repeat clicks for an album that's already queued or running are deduped (returns ``{queued: false, reason: 'already_queued'}``). Body params: source (optional): per-album source pick (Spotify / iTunes / Deezer / Discogs / Hydrabase). When omitted, the orchestrator uses the configured primary with fallback. """ try: from core.reorganize_queue import get_queue data = request.get_json() or {} chosen_source = data.get('source') or None # Capture display fields at enqueue time so the status panel # can render them without a DB lookup later. meta = get_database().get_album_display_meta(album_id) if meta is None: return jsonify({"success": False, "error": "Album not found"}), 404 result = get_queue().enqueue( album_id=str(album_id), album_title=meta['album_title'], artist_id=meta['artist_id'], artist_name=meta['artist_name'], source=chosen_source, ) return jsonify({"success": True, **result}) except Exception as e: logger.error(f"Reorganize enqueue error: {e}", exc_info=True) return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/artist//reorganize-all', methods=['POST']) def reorganize_all_artist_albums(artist_id): """Enqueue every album for an artist. Replaces the old frontend bulk-loop. Each album becomes its own queue item, processed FIFO. Albums already queued or running are deduped silently. Body params: source (optional): same pick applied to every album. Per-album overrides aren't supported here — use the per-album modal for that. """ try: from core.reorganize_queue import get_queue data = request.get_json() or {} chosen_source = data.get('source') or None albums = get_database().get_artist_albums_for_reorganize(artist_id) if not albums: return jsonify({"success": False, "error": "No albums found for this artist"}), 404 # Apply the user's chosen source to every album, then hand off # to the queue's bulk-enqueue helper which owns the loop+tally. for album in albums: album['source'] = chosen_source result = get_queue().enqueue_many(albums) return jsonify({ "success": True, "enqueued": result['enqueued'], "already_queued": result['already_queued'], "total_albums": result['total'], }) except Exception as e: logger.error(f"Reorganize-all enqueue error: {e}", exc_info=True) return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/reorganize/queue', methods=['GET']) def reorganize_queue_snapshot(): """Snapshot of the reorganize queue — what's running, what's queued, recent completions. Polled by the status panel.""" try: from core.reorganize_queue import get_queue return jsonify({"success": True, **get_queue().snapshot()}) except Exception as e: logger.error(f"Reorganize queue snapshot error: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/reorganize/queue//cancel', methods=['POST']) def reorganize_queue_cancel(queue_id): """Cancel a queued item (running items can't be cleanly cancelled — see the queue module's design rules).""" try: from core.reorganize_queue import get_queue result = get_queue().cancel(queue_id) status_code = 200 if result.get('cancelled') else 409 return jsonify({"success": result.get('cancelled', False), **result}), status_code except Exception as e: logger.error(f"Reorganize cancel error: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/reorganize/queue/clear', methods=['POST']) def reorganize_queue_clear(): """Cancel all queued items at once (the running item continues).""" try: from core.reorganize_queue import get_queue cancelled = get_queue().clear_queued() return jsonify({"success": True, "cancelled": cancelled}) except Exception as e: logger.error(f"Reorganize clear error: {e}") return jsonify({"success": False, "error": str(e)}), 500 # Wire the reorganize queue worker to its runner at module load. The # runner factory lives in :mod:`core.reorganize_runner` so this monolith # stays small. Config (paths) is read **per run** inside the closure, # so changing your download path in Settings takes effect on the next # reorganize without a server restart. # # The injected callables are wrapped in lambdas because the underlying # helpers (``_resolve_library_file_path`` etc.) are defined LATER in # this file. Lambdas defer name resolution to call time so module-load # import order works regardless of definition order. try: from core.reorganize_queue import get_queue as _get_reorganize_queue from core.reorganize_runner import build_runner as _build_reorganize_runner _get_reorganize_queue().set_runner(_build_reorganize_runner( get_database=get_database, resolve_file_path_fn=lambda p: _resolve_library_file_path(p), post_process_fn=lambda *a, **kw: _post_process_matched_download(*a, **kw), cleanup_empty_directories_fn=lambda *a, **kw: _cleanup_empty_directories(*a, **kw), is_shutting_down_fn=lambda: bool(IS_SHUTTING_DOWN), get_download_path=lambda: docker_resolve_path( config_manager.get('soulseek.download_path', './downloads') ), get_transfer_path=lambda: docker_resolve_path( config_manager.get('soulseek.transfer_path', './Transfer') ), )) except Exception as _runner_init_err: logger.error(f"Failed to register reorganize queue runner: {_runner_init_err}") # ── Library Issues endpoints ── @app.route('/api/issues', methods=['GET']) def list_issues(): """List issues. Admin sees all; non-admin sees own only.""" try: database = get_database() profile_id = request.headers.get('X-Profile-Id', '1') try: profile_id = int(profile_id) except (ValueError, TypeError): profile_id = 1 # Determine admin status profile = database.get_profile(profile_id) is_admin = profile.get('is_admin', False) if profile else False status = request.args.get('status') category = request.args.get('category') entity_type = request.args.get('entity_type') try: limit = min(200, max(1, int(request.args.get('limit', 100)))) except (ValueError, TypeError): limit = 100 try: offset = max(0, int(request.args.get('offset', 0))) except (ValueError, TypeError): offset = 0 result = database.get_issues( profile_id=profile_id, status=status, category=category, entity_type=entity_type, limit=limit, offset=offset, is_admin=is_admin, ) # Fix Plex/Jellyfin relative thumb URLs in stored snapshots for issue in result.get('issues', []): snap = issue.get('snapshot_data') if isinstance(snap, dict): for key in ('thumb_url', 'artist_thumb', 'album_thumb'): if snap.get(key): snap[key] = fix_artist_image_url(snap[key]) or snap[key] return jsonify(result) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/issues', methods=['POST']) def create_issue(): """Create a new library issue.""" try: database = get_database() data = request.get_json() if not data: return jsonify({"success": False, "error": "No data provided"}), 400 # Use header for profile_id (not body) to prevent spoofing profile_id = request.headers.get('X-Profile-Id', '1') try: profile_id = int(profile_id) except (ValueError, TypeError): profile_id = 1 entity_type = data.get('entity_type') entity_id = data.get('entity_id') category = data.get('category') title = data.get('title', '').strip() description = data.get('description', '').strip() priority = data.get('priority', 'normal') if not entity_type or not entity_id or not category or not title: return jsonify({"success": False, "error": "entity_type, entity_id, category, and title are required"}), 400 valid_types = ('artist', 'album', 'track') if entity_type not in valid_types: return jsonify({"success": False, "error": f"entity_type must be one of: {', '.join(valid_types)}"}), 400 valid_categories = ('wrong_track', 'wrong_metadata', 'wrong_cover', 'duplicate_tracks', 'missing_tracks', 'audio_quality', 'wrong_artist', 'wrong_album', 'incomplete_album', 'other') if category not in valid_categories: return jsonify({"success": False, "error": f"Invalid category: {category}"}), 400 # Build snapshot of the entity's current state snapshot = _build_issue_snapshot(database, entity_type, str(entity_id)) result = database.create_issue( profile_id=profile_id, entity_type=entity_type, entity_id=str(entity_id), category=category, title=title, description=description, snapshot_data=snapshot, priority=priority, ) return jsonify(result), 201 if result.get('success') else 400 except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/issues/', methods=['GET']) def get_issue(issue_id): """Get a single issue.""" try: database = get_database() issue = database.get_issue(issue_id) if not issue: return jsonify({"success": False, "error": "Issue not found"}), 404 # Fix Plex/Jellyfin relative thumb URLs in stored snapshot snap = issue.get('snapshot_data') if isinstance(snap, dict): for key in ('thumb_url', 'artist_thumb', 'album_thumb'): if snap.get(key): snap[key] = fix_artist_image_url(snap[key]) or snap[key] return jsonify({"success": True, "issue": issue}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/issues/', methods=['PUT']) def update_issue(issue_id): """Update an issue (admin: respond/resolve; user: edit own description).""" try: database = get_database() data = request.get_json() if not data: return jsonify({"success": False, "error": "No data provided"}), 400 profile_id = request.headers.get('X-Profile-Id', '1') try: profile_id = int(profile_id) except (ValueError, TypeError): profile_id = 1 profile = database.get_profile(profile_id) is_admin = profile.get('is_admin', False) if profile else False # Non-admin can only edit their own issue's title/description if not is_admin: issue = database.get_issue(issue_id) if not issue: return jsonify({"success": False, "error": "Issue not found"}), 404 if issue['profile_id'] != profile_id: return jsonify({"success": False, "error": "Not authorized"}), 403 data = {k: v for k, v in data.items() if k in ('title', 'description')} # If resolving, stamp resolved_by and resolved_at if data.get('status') in ('resolved', 'dismissed') and is_admin: data['resolved_by'] = profile_id from datetime import datetime data['resolved_at'] = datetime.utcnow().strftime('%Y-%m-%d %H:%M:%S') # If reopening, clear resolution metadata elif data.get('status') in ('open', 'in_progress') and is_admin: data['resolved_by'] = None data['resolved_at'] = None result = database.update_issue(issue_id, data) return jsonify(result) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/issues/', methods=['DELETE']) def delete_issue(issue_id): """Delete an issue (admin or issue owner).""" try: database = get_database() profile_id = request.headers.get('X-Profile-Id', '1') try: profile_id = int(profile_id) except (ValueError, TypeError): profile_id = 1 profile = database.get_profile(profile_id) is_admin = profile.get('is_admin', False) if profile else False if not is_admin: issue = database.get_issue(issue_id) if not issue: return jsonify({"success": False, "error": "Issue not found"}), 404 if issue['profile_id'] != profile_id: return jsonify({"success": False, "error": "Not authorized"}), 403 result = database.delete_issue(issue_id) return jsonify(result) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/issues/counts', methods=['GET']) def get_issue_counts(): """Get issue counts by status for badge display.""" try: database = get_database() profile_id = request.headers.get('X-Profile-Id', '1') try: profile_id = int(profile_id) except (ValueError, TypeError): profile_id = 1 profile = database.get_profile(profile_id) is_admin = profile.get('is_admin', False) if profile else False counts = database.get_issue_counts(is_admin=is_admin, profile_id=profile_id) return jsonify({"success": True, "counts": counts}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 def _build_issue_snapshot(database, entity_type, entity_id): """Capture current state of the entity for the issue report.""" snapshot = {} try: conn = database._get_connection() cursor = conn.cursor() if entity_type == 'track': cursor.execute(""" SELECT t.id, t.title, t.track_number, t.duration, t.file_path, t.bitrate, t.bpm, t.spotify_track_id, t.musicbrainz_recording_id, t.deezer_id as track_deezer_id, a.name as artist_name, a.id as artist_id, a.spotify_artist_id, a.musicbrainz_id as artist_musicbrainz_id, a.deezer_id as artist_deezer_id, a.tidal_id as artist_tidal_id, a.qobuz_id as artist_qobuz_id, a.thumb_url as artist_thumb, al.title as album_title, al.year, al.thumb_url as album_thumb, al.id as album_id, al.spotify_album_id, al.musicbrainz_release_id, al.deezer_id as album_deezer_id, al.tidal_id as album_tidal_id, al.qobuz_id as album_qobuz_id, al.label, al.record_type, al.track_count as album_track_count FROM tracks t JOIN artists a ON t.artist_id = a.id JOIN albums al ON t.album_id = al.id WHERE t.id = ? """, (entity_id,)) row = cursor.fetchone() if row: d = dict(row) # Add format info if file exists resolved = _resolve_library_file_path(d.get('file_path')) if resolved: ext = os.path.splitext(resolved)[1].lower().lstrip('.') d['format'] = ext.upper() d['quality'] = _get_audio_quality_string(resolved) # Fix Plex/Jellyfin relative thumb URLs if d.get('artist_thumb'): d['artist_thumb'] = fix_artist_image_url(d['artist_thumb']) or d['artist_thumb'] if d.get('album_thumb'): d['album_thumb'] = fix_artist_image_url(d['album_thumb']) or d['album_thumb'] snapshot = d elif entity_type == 'album': cursor.execute(""" SELECT al.id, al.title, al.year, al.track_count, al.thumb_url, al.genres, al.label, al.record_type, al.duration, al.spotify_album_id, al.musicbrainz_release_id, al.deezer_id as album_deezer_id, al.tidal_id as album_tidal_id, al.qobuz_id as album_qobuz_id, al.upc, a.name as artist_name, a.id as artist_id, a.spotify_artist_id, a.musicbrainz_id as artist_musicbrainz_id, a.deezer_id as artist_deezer_id, a.tidal_id as artist_tidal_id, a.qobuz_id as artist_qobuz_id, a.thumb_url as artist_thumb FROM albums al JOIN artists a ON al.artist_id = a.id WHERE al.id = ? """, (entity_id,)) row = cursor.fetchone() if row: d = dict(row) # Fix Plex/Jellyfin relative thumb URLs if d.get('thumb_url'): d['thumb_url'] = fix_artist_image_url(d['thumb_url']) or d['thumb_url'] if d.get('artist_thumb'): d['artist_thumb'] = fix_artist_image_url(d['artist_thumb']) or d['artist_thumb'] # Parse genres if d.get('genres'): try: d['genres'] = json.loads(d['genres']) except (json.JSONDecodeError, TypeError): pass # Get track listing with enriched data cursor.execute(""" SELECT id, title, track_number, duration, file_path, bitrate, spotify_track_id, bpm FROM tracks WHERE album_id = ? ORDER BY track_number """, (entity_id,)) tracks_list = [] for r in cursor.fetchall(): td = dict(r) # Add format from file extension if td.get('file_path'): resolved = _resolve_library_file_path(td['file_path']) if resolved: ext = os.path.splitext(resolved)[1].lower().lstrip('.') td['format'] = ext.upper() tracks_list.append(td) d['tracks'] = tracks_list snapshot = d elif entity_type == 'artist': cursor.execute(""" SELECT id, name, thumb_url, genres, summary, spotify_artist_id, musicbrainz_id as artist_musicbrainz_id, deezer_id as artist_deezer_id, tidal_id as artist_tidal_id, qobuz_id as artist_qobuz_id FROM artists WHERE id = ? """, (entity_id,)) row = cursor.fetchone() if row: d = dict(row) # Fix Plex/Jellyfin relative thumb URL if d.get('thumb_url'): d['thumb_url'] = fix_artist_image_url(d['thumb_url']) or d['thumb_url'] if d.get('genres'): try: d['genres'] = json.loads(d['genres']) except (json.JSONDecodeError, TypeError): pass snapshot = d except Exception as e: logger.error(f"Error building issue snapshot: {e}") snapshot['_snapshot_error'] = str(e) return snapshot def _sync_tracks_to_server(track_rows, server_type): """Sync metadata for tracks to the active media server after writing file tags. Args: track_rows: list of track dicts (must include 'id', 'title', 'artist_name', 'album_title', 'year', 'server_source') server_type: 'plex', 'jellyfin', or 'navidrome' Returns: dict with 'synced', 'failed', 'skipped' counts and 'errors' list """ result = {'synced': 0, 'failed': 0, 'skipped': 0, 'errors': []} if server_type == 'navidrome': # Navidrome auto-detects file tag changes, no action needed result['synced'] = len(track_rows) return result if server_type == 'plex': for track_data in track_rows: # Only sync tracks that came from this server if track_data.get('server_source') and track_data['server_source'] != 'plex': result['skipped'] += 1 continue try: metadata = {} if track_data.get('title'): metadata['title'] = track_data['title'] if track_data.get('artist_name'): metadata['artist'] = track_data['artist_name'] if track_data.get('album_title'): metadata['album'] = track_data['album_title'] if track_data.get('year'): metadata['year'] = track_data['year'] if metadata: success = media_server_engine.client('plex').update_track_metadata(str(track_data['id']), metadata) if success: result['synced'] += 1 else: result['failed'] += 1 result['errors'].append({'track_id': track_data['id'], 'error': 'Plex update returned false'}) else: result['skipped'] += 1 except Exception as e: result['failed'] += 1 result['errors'].append({'track_id': track_data['id'], 'error': str(e)}) elif server_type == 'jellyfin': # Jellyfin: just trigger a library scan once after all file writes try: success = media_server_engine.client('jellyfin').trigger_library_scan() if success: result['synced'] = len(track_rows) else: result['failed'] = len(track_rows) result['errors'].append({'error': 'Jellyfin library scan failed'}) except Exception as e: result['failed'] = len(track_rows) result['errors'].append({'error': f'Jellyfin scan error: {e}'}) return result def _resolve_library_file_path(file_path): """Resolve a library file path to an actual file on disk.""" if not file_path: return None if os.path.exists(file_path): return file_path # Try resolving server-side paths to local directories # Check transfer path, download path, and media server library paths transfer_dir = docker_resolve_path(config_manager.get('soulseek.transfer_path', './Transfer')) download_dir = docker_resolve_path(config_manager.get('soulseek.download_path', './downloads')) # Also check the media server's music library path (handles Docker↔host path mismatch). # ``get_music_library_locations`` handles both single-library mode and # all-libraries mode (unions location paths across every music section). library_dirs = set() try: plex = media_server_engine.client('plex') if plex and plex.server: for loc in plex.get_music_library_locations(): library_dirs.add(loc) except Exception as e: logger.debug("plex library locations lookup failed: %s", e) # Check user-configured music library paths (Settings > Library) try: music_paths = config_manager.get('library.music_paths', []) if isinstance(music_paths, list): for p in music_paths: if p and isinstance(p, str): resolved_p = docker_resolve_path(p.strip()) if resolved_p: library_dirs.add(resolved_p) except Exception as e: logger.debug("library music paths read failed: %s", e) path_parts = file_path.replace('\\', '/').split('/') # Try progressively shorter path suffixes against each candidate directory # (skip index 0 to avoid drive letter issues) for base_dir in [transfer_dir, download_dir] + list(library_dirs): if not base_dir or not os.path.isdir(base_dir): continue for i in range(1, len(path_parts)): candidate = os.path.join(base_dir, *path_parts[i:]) if os.path.exists(candidate): return candidate return None def _get_file_not_found_error(file_path): """Return a helpful error message when a library file can't be found.""" active_server = config_manager.get_active_media_server() if active_server == 'navidrome': # Check if path looks like a Navidrome fake path (no real filesystem root) # Fake paths look like: "Artist/Album/01 - Track.flac" or just "Track.flac" if file_path and ('/' not in file_path or not file_path.startswith('/')): return ('File not found — Navidrome may be sending virtual paths. ' 'Go to Navidrome → Profile → Players → select SoulSync → enable "Report Real Path", ' 'then run a full database refresh in SoulSync.') return ('File not found on disk — check that your Navidrome music folder ' 'is mounted in the SoulSync container and that "Report Real Path" is enabled ' 'in Navidrome\'s player settings.') return 'File not found on disk' @app.route('/api/library/play', methods=['POST']) def library_play_track(): """Start playing a track directly from the user's library (no download needed).""" try: data = request.get_json() if not data or not data.get('file_path'): return jsonify({"success": False, "error": "file_path is required"}), 400 file_path = data['file_path'] # Resolve server-side paths (e.g. /mnt/musicBackup/...) to local transfer path resolved = _resolve_library_file_path(file_path) if resolved: file_path = resolved else: return jsonify({"success": False, "error": _get_file_not_found_error(file_path)}), 404 logger.info(f"Library play request: {os.path.basename(file_path)}") # Set stream state to ready with the library file path directly with stream_lock: stream_state.update({ "status": "ready", "progress": 100, "track_info": { "title": data.get('title', os.path.basename(file_path)), "artist": data.get('artist', 'Unknown Artist'), "album": data.get('album', 'Unknown Album'), }, "file_path": file_path, "error_message": None, "is_library": True }) return jsonify({"success": True, "message": "Library track ready for playback"}) except Exception as e: logger.error(f"Error playing library track: {e}") return jsonify({"success": False, "error": str(e)}), 500 _enrichment_locks = {svc: threading.Lock() for svc in ('audiodb', 'deezer', 'musicbrainz', 'spotify', 'itunes', 'lastfm', 'genius', 'tidal', 'qobuz', 'discogs')} @app.route('/api/library/enrich', methods=['POST']) def library_enrich_entity(): """Trigger enrichment of a specific entity from a single service. Body: { entity_type: 'artist'|'album'|'track', entity_id: str, service: str, name: str, artist_name: str? } service: 'audiodb', 'deezer', 'musicbrainz', 'spotify', 'itunes', 'lastfm', 'genius', 'tidal', 'qobuz' """ try: data = request.get_json() if not data: return jsonify({"success": False, "error": "No data provided"}), 400 entity_type = data.get('entity_type') # artist, album, track entity_id = data.get('entity_id') service = data.get('service') name = data.get('name', '') artist_name = data.get('artist_name', '') if not entity_type or not entity_id or not service: return jsonify({"success": False, "error": "entity_type, entity_id, and service are required"}), 400 if entity_type not in ('artist', 'album', 'track'): return jsonify({"success": False, "error": "entity_type must be artist, album, or track"}), 400 valid_services = ('audiodb', 'deezer', 'musicbrainz', 'spotify', 'itunes', 'lastfm', 'genius', 'tidal', 'qobuz', 'discogs') if service not in valid_services: return jsonify({"success": False, "error": f"service must be one of: {', '.join(valid_services)}"}), 400 # Per-service lock to avoid thread-safety issues with shared worker clients lock = _enrichment_locks.get(service) if not lock: return jsonify({"success": False, "error": f"Unknown service: {service}"}), 400 acquired = lock.acquire(blocking=False) if not acquired: return jsonify({"success": False, "error": f"{service} enrichment already in progress. Please wait."}), 429 try: results = {} try: result = _run_single_enrichment(service, entity_type, entity_id, name, artist_name) results[service] = result except Exception as e: results[service] = {"success": False, "error": str(e)} finally: lock.release() # Re-fetch updated data to return fresh state database = get_database() updated = database.get_artist_full_detail( data.get('artist_id', entity_id) if entity_type == 'artist' else _get_artist_id_for_entity(database, entity_type, entity_id) ) # Fix image URLs in updated data if updated.get('success'): if updated.get('artist', {}).get('thumb_url'): updated['artist']['thumb_url'] = fix_artist_image_url(updated['artist']['thumb_url']) for album in updated.get('albums', []): if album.get('thumb_url'): album['thumb_url'] = fix_artist_image_url(album['thumb_url']) return jsonify({ "success": True, "results": results, "updated_data": updated if updated.get('success') else None }) except Exception as e: logger.error(f"Error enriching entity: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 def _get_artist_id_for_entity(database, entity_type, entity_id): """Look up the artist_id for an album or track.""" try: with database._get_connection() as conn: cursor = conn.cursor() if entity_type == 'album': cursor.execute("SELECT artist_id FROM albums WHERE id = ?", (entity_id,)) elif entity_type == 'track': cursor.execute("SELECT artist_id FROM tracks WHERE id = ?", (entity_id,)) else: return entity_id row = cursor.fetchone() return row['artist_id'] if row else entity_id except Exception: return entity_id def _run_single_enrichment(service, entity_type, entity_id, name, artist_name): """Run a single enrichment service on a single entity.""" if service == 'audiodb': if not audiodb_worker: return {"success": False, "error": "AudioDB worker not initialized"} item = {'type': entity_type, 'id': entity_id, 'name': name} if entity_type in ('album', 'track'): item['artist'] = artist_name audiodb_worker._process_item(item) return {"success": True, "message": f"AudioDB lookup complete for {entity_type}"} elif service == 'deezer': if not deezer_worker: return {"success": False, "error": "Deezer worker not initialized"} item = {'type': entity_type, 'id': entity_id, 'name': name, 'artist': artist_name} if entity_type == 'artist': deezer_worker._process_artist(entity_id, name) elif entity_type == 'album': deezer_worker._process_album(entity_id, name, artist_name, item) elif entity_type == 'track': deezer_worker._process_track(entity_id, name, artist_name, item) return {"success": True, "message": f"Deezer lookup complete for {entity_type}"} elif service == 'musicbrainz': if not mb_worker: return {"success": False, "error": "MusicBrainz worker not initialized"} item = {'type': entity_type, 'id': entity_id, 'name': name} if entity_type in ('album', 'track'): item['artist'] = artist_name mb_worker._process_item(item) return {"success": True, "message": f"MusicBrainz lookup complete for {entity_type}"} elif service == 'spotify': if not spotify_enrichment_worker: return {"success": False, "error": "Spotify worker not initialized"} if entity_type == 'artist': spotify_enrichment_worker._process_artist({'type': 'artist', 'id': entity_id, 'name': name}) elif entity_type == 'album': spotify_enrichment_worker._process_album_individual({'type': 'album_individual', 'id': entity_id, 'name': name, 'artist': artist_name}) elif entity_type == 'track': spotify_enrichment_worker._process_track_individual({'type': 'track_individual', 'id': entity_id, 'name': name, 'artist': artist_name}) return {"success": True, "message": f"Spotify lookup complete for {entity_type}"} elif service == 'itunes': if not itunes_enrichment_worker: return {"success": False, "error": "iTunes worker not initialized"} if entity_type == 'artist': itunes_enrichment_worker._process_artist({'type': 'artist', 'id': entity_id, 'name': name}) elif entity_type == 'album': itunes_enrichment_worker._process_album_individual({'type': 'album_individual', 'id': entity_id, 'name': name, 'artist': artist_name}) elif entity_type == 'track': itunes_enrichment_worker._process_track_individual({'type': 'track_individual', 'id': entity_id, 'name': name, 'artist': artist_name}) return {"success": True, "message": f"iTunes lookup complete for {entity_type}"} elif service == 'lastfm': if not lastfm_worker: return {"success": False, "error": "Last.fm worker not initialized"} item = {'type': entity_type, 'id': entity_id, 'name': name} if entity_type in ('album', 'track'): item['artist'] = artist_name lastfm_worker._process_item(item) return {"success": True, "message": f"Last.fm lookup complete for {entity_type}"} elif service == 'genius': if not genius_worker: return {"success": False, "error": "Genius worker not initialized"} item = {'type': entity_type, 'id': entity_id, 'name': name} if entity_type == 'track': item['artist'] = artist_name elif entity_type == 'album': return {"success": False, "error": "Genius does not support album enrichment"} genius_worker._process_item(item) return {"success": True, "message": f"Genius lookup complete for {entity_type}"} elif service == 'tidal': if not tidal_enrichment_worker: return {"success": False, "error": "Tidal worker not initialized"} item = {'type': entity_type, 'id': entity_id, 'name': name, 'artist': artist_name} if entity_type == 'artist': tidal_enrichment_worker._process_artist(entity_id, name) elif entity_type == 'album': tidal_enrichment_worker._process_album(entity_id, name, artist_name, item) elif entity_type == 'track': tidal_enrichment_worker._process_track(entity_id, name, artist_name, item) return {"success": True, "message": f"Tidal lookup complete for {entity_type}"} elif service == 'qobuz': if not qobuz_enrichment_worker: return {"success": False, "error": "Qobuz worker not initialized"} item = {'type': entity_type, 'id': entity_id, 'name': name, 'artist': artist_name} if entity_type == 'artist': qobuz_enrichment_worker._process_artist(entity_id, name) elif entity_type == 'album': qobuz_enrichment_worker._process_album(entity_id, name, artist_name, item) elif entity_type == 'track': qobuz_enrichment_worker._process_track(entity_id, name, artist_name, item) return {"success": True, "message": f"Qobuz lookup complete for {entity_type}"} elif service == 'discogs': if not discogs_worker: return {"success": False, "error": "Discogs worker not initialized"} item = {'type': entity_type, 'id': entity_id, 'name': name} if entity_type in ('album', 'track'): item['artist'] = artist_name if entity_type == 'track': return {"success": False, "error": "Discogs does not support track-level enrichment"} discogs_worker._process_item(item) return {"success": True, "message": f"Discogs lookup complete for {entity_type}"} else: return {"success": False, "error": f"Unknown service: {service}"} @app.route('/api/library/search-service', methods=['POST']) def library_search_service(): """Search a specific service for matching entities (for manual matching). Body: { service: str, entity_type: str, query: str } Returns normalized list of results. """ try: data = request.get_json() if not data: return jsonify({"success": False, "error": "Invalid or missing JSON body"}), 400 service = data.get('service', '') entity_type = data.get('entity_type', '') query = data.get('query', '').strip() if not service or not entity_type or not query: return jsonify({"success": False, "error": "service, entity_type, and query are required"}), 400 results = _search_service(service, entity_type, query) return jsonify({"success": True, "results": results}) except Exception as e: logger.error(f"Error searching service: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 from core.library.service_search import ( _detect_provider, _search_service, init as _init_service_search, ) # Column name mappings for manual matching _SERVICE_ID_COLUMNS = { 'spotify': {'artist': 'spotify_artist_id', 'album': 'spotify_album_id', 'track': 'spotify_track_id'}, 'musicbrainz': {'artist': 'musicbrainz_id', 'album': 'musicbrainz_release_id', 'track': 'musicbrainz_recording_id'}, 'deezer': {'artist': 'deezer_id', 'album': 'deezer_id', 'track': 'deezer_id'}, 'audiodb': {'artist': 'audiodb_id', 'album': 'audiodb_id', 'track': 'audiodb_id'}, 'discogs': {'artist': 'discogs_id', 'album': 'discogs_id'}, 'itunes': {'artist': 'itunes_artist_id', 'album': 'itunes_album_id', 'track': 'itunes_track_id'}, 'lastfm': {'artist': 'lastfm_url', 'album': 'lastfm_url', 'track': 'lastfm_url'}, 'genius': {'artist': 'genius_id', 'track': 'genius_id'}, 'tidal': {'artist': 'tidal_id', 'album': 'tidal_id', 'track': 'tidal_id'}, 'qobuz': {'artist': 'qobuz_id', 'album': 'qobuz_id', 'track': 'qobuz_id'}, } @app.route('/api/library/manual-match', methods=['PUT']) def library_manual_match(): """Manually set a service ID for an entity. Body: { entity_type: str, entity_id: str, service: str, service_id: str, artist_id: str } """ try: data = request.get_json() entity_type = data.get('entity_type') entity_id = data.get('entity_id') service = data.get('service') service_id = data.get('service_id') if not all([entity_type, entity_id, service, service_id]): return jsonify({"success": False, "error": "entity_type, entity_id, service, and service_id are required"}), 400 id_col = _SERVICE_ID_COLUMNS.get(service, {}).get(entity_type) if not id_col: return jsonify({"success": False, "error": "Invalid service/entity_type combination"}), 400 status_col = f"{service}_match_status" attempted_col = f"{service}_last_attempted" table = {'artist': 'artists', 'album': 'albums', 'track': 'tracks'}[entity_type] database = get_database() with database._get_connection() as conn: cursor = conn.cursor() cursor.execute(f""" UPDATE {table} SET {id_col} = ?, {status_col} = 'matched', {attempted_col} = CURRENT_TIMESTAMP WHERE id = ? """, (service_id, entity_id)) conn.commit() if cursor.rowcount == 0: return jsonify({"success": False, "error": "Entity not found"}), 404 # Re-fetch fresh data artist_id = data.get('artist_id', entity_id) if entity_type != 'artist': artist_id = _get_artist_id_for_entity(database, entity_type, entity_id) updated = database.get_artist_full_detail(artist_id) if updated.get('success'): if updated.get('artist', {}).get('thumb_url'): updated['artist']['thumb_url'] = fix_artist_image_url(updated['artist']['thumb_url']) for album in updated.get('albums', []): if album.get('thumb_url'): album['thumb_url'] = fix_artist_image_url(album['thumb_url']) return jsonify({ "success": True, "message": f"Manually matched {entity_type} to {service} ID: {service_id}", "updated_data": updated if updated.get('success') else None }) except Exception as e: logger.error(f"Error manual matching: {e}") @app.route('/api/library/clear-match', methods=['PUT']) def library_clear_match(): """Clear a service ID match for an entity, reverting it to not_found. Body: { entity_type: str, entity_id: str, service: str } """ try: data = request.get_json() entity_type = data.get('entity_type') entity_id = data.get('entity_id') service = data.get('service') if not all([entity_type, entity_id, service]): return jsonify({"success": False, "error": "entity_type, entity_id, and service are required"}), 400 id_col = _SERVICE_ID_COLUMNS.get(service, {}).get(entity_type) if not id_col: return jsonify({"success": False, "error": "Invalid service/entity_type combination"}), 400 status_col = f"{service}_match_status" attempted_col = f"{service}_last_attempted" table = {'artist': 'artists', 'album': 'albums', 'track': 'tracks'}.get(entity_type) if not table: return jsonify({"success": False, "error": "Invalid entity_type"}), 400 database = get_database() with database._get_connection() as conn: cursor = conn.cursor() cursor.execute(f""" UPDATE {table} SET {id_col} = NULL, {status_col} = 'not_found', {attempted_col} = NULL WHERE id = ? """, (entity_id,)) conn.commit() if cursor.rowcount == 0: return jsonify({"success": False, "error": "Entity not found"}), 404 # Re-fetch fresh data artist_id = data.get('artist_id', entity_id) if entity_type != 'artist': artist_id = _get_artist_id_for_entity(database, entity_type, entity_id) updated = database.get_artist_full_detail(artist_id) if updated.get('success'): if updated.get('artist', {}).get('thumb_url'): updated['artist']['thumb_url'] = fix_artist_image_url(updated['artist']['thumb_url']) for album in updated.get('albums', []): if album.get('thumb_url'): album['thumb_url'] = fix_artist_image_url(album['thumb_url']) return jsonify({ "success": True, "message": f"Cleared {service} match for {entity_type}", "updated_data": updated if updated.get('success') else None }) except Exception as e: logger.error(f"Error clearing match: {e}") return jsonify({"success": False, "error": str(e)}), 500 import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/track/', methods=['DELETE']) def library_delete_track(track_id): """Delete a track from the database, optionally deleting the file and blacklisting the source.""" try: delete_file = request.args.get('delete_file', 'false').lower() == 'true' add_blacklist = request.args.get('blacklist', 'false').lower() == 'true' database = get_database() file_deleted = False blacklisted = False with database._get_connection() as conn: cursor = conn.cursor() # Get track info before deleting (for file removal + blacklist) track_info = None if delete_file or add_blacklist: cursor.execute(""" SELECT t.file_path, t.title, ar.name AS artist_name FROM tracks t JOIN artists ar ON t.artist_id = ar.id WHERE t.id = ? """, (track_id,)) track_info = cursor.fetchone() # Delete file from disk if requested file_error = None if delete_file and track_info and track_info['file_path']: resolved = _resolve_library_file_path(track_info['file_path']) if resolved and os.path.exists(resolved): try: os.remove(resolved) file_deleted = True logger.info(f"Deleted file from disk: {resolved}") # Clean up sidecar files (.lrc, .txt lyrics, cover.jpg) base_no_ext = os.path.splitext(resolved)[0] for sidecar_ext in ('.lrc', '.txt'): sidecar = base_no_ext + sidecar_ext if os.path.exists(sidecar): try: os.remove(sidecar) logger.info(f"Deleted sidecar file: {sidecar}") except Exception as e: logger.debug("sidecar removal failed: %s", e) except Exception as e: logger.warning(f"Failed to delete file: {e}") file_error = str(e) else: logger.warning(f"Could not resolve file path for deletion: {track_info['file_path']} (resolved={resolved})") file_error = _get_file_not_found_error(track_info['file_path']) # Add to blacklist if requested if add_blacklist and track_info and track_info['file_path']: # Extract username and filename from the file path for blacklisting # Soulseek paths are stored as: username/path/to/file.ext or just the local path fp = track_info['file_path'].replace('\\', '/') database.add_to_blacklist( track_title=track_info['title'], track_artist=track_info['artist_name'], blocked_filename=os.path.basename(fp), blocked_username='', # Local files don't have a username reason='user_rejected' ) blacklisted = True # Delete DB record cursor.execute("DELETE FROM tracks WHERE id = ?", (track_id,)) conn.commit() if cursor.rowcount == 0: return jsonify({"success": False, "error": "Track not found"}), 404 result = {"success": True, "deleted_count": cursor.rowcount, "file_deleted": file_deleted, "blacklisted": blacklisted} if delete_file and not file_deleted and file_error: result["file_error"] = file_error return jsonify(result) except Exception as e: logger.error(f"Error deleting track {track_id}: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 # ================================================================================== # DOWNLOAD BLACKLIST API # ================================================================================== @app.route('/api/library/blacklist', methods=['GET']) def get_blacklist(): """Get all blacklisted download sources.""" try: database = get_database() entries = database.get_blacklist(limit=200) return jsonify({"success": True, "entries": entries}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/blacklist', methods=['POST']) def add_to_blacklist(): """Add a download source to the blacklist.""" try: data = request.get_json() database = get_database() result = database.add_to_blacklist( track_title=data.get('track_title', ''), track_artist=data.get('track_artist', ''), blocked_filename=data.get('blocked_filename', ''), blocked_username=data.get('blocked_username', ''), reason=data.get('reason', 'user_rejected'), ) return jsonify({"success": result}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/blacklist/', methods=['DELETE']) def remove_from_blacklist(blacklist_id): """Remove an entry from the blacklist.""" try: database = get_database() result = database.remove_from_blacklist(blacklist_id) return jsonify({"success": result}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 # ================================================================================== # TRACK SOURCE INFO & PROVENANCE # ================================================================================== @app.route('/api/library/track//source-info', methods=['GET']) def get_track_source_info(track_id): """Get download provenance info for a library track.""" try: database = get_database() downloads = database.get_track_downloads(str(track_id)) if not downloads: # Try matching by file path as fallback (exact, then filename suffix) conn = database._get_connection() cursor = conn.cursor() cursor.execute("SELECT file_path FROM tracks WHERE id = ?", (track_id,)) row = cursor.fetchone() conn.close() if row and row['file_path']: dl = database.get_download_by_file_path(row['file_path']) if dl: downloads = [dl] else: # Path format mismatch (e.g. Plex path vs local Windows path) — # fall back to filename-only match and back-link the track_id import os as _os fname = _os.path.basename(row['file_path'].replace('\\', '/')) if fname: dl = database.get_download_by_filename(fname, link_track_id=track_id) if dl: downloads = [dl] return jsonify({"success": True, "downloads": downloads}) except Exception as e: logger.error(f"Error getting track source info: {e}") return jsonify({"success": False, "error": str(e)}), 500 # ================================================================================== # TRACK REDOWNLOAD — Search metadata, search download sources, start redownload # ================================================================================== @app.route('/api/library/track//redownload/search-metadata', methods=['POST']) def redownload_search_metadata(track_id): """Search all available metadata sources for a track to find the correct version.""" try: database = get_database() conn = database._get_connection() cursor = conn.cursor() cursor.execute(""" SELECT t.id, t.title, t.file_path, t.bitrate, t.duration, ar.name AS artist_name, al.title AS album_title, al.thumb_url AS album_thumb_url, t.spotify_track_id, t.deezer_id FROM tracks t JOIN artists ar ON t.artist_id = ar.id JOIN albums al ON t.album_id = al.id WHERE t.id = ? """, (track_id,)) row = cursor.fetchone() conn.close() if not row: return jsonify({"success": False, "error": "Track not found"}), 404 track_title = row['title'] artist_name = row['artist_name'] # Clean the title for better search results — strip version/edition suffixes import re as _re clean_title = _re.sub(r'\s*[\(\[](single version|album version|remaster|deluxe|bonus|explicit|clean|radio edit)[\)\]]', '', track_title, flags=_re.IGNORECASE).strip() query = f"{artist_name} {clean_title}" # Resolve file info file_path = row['file_path'] or '' ext = os.path.splitext(file_path)[1].lstrip('.').upper() if file_path else '' fmt = ext if ext in ('FLAC', 'MP3', 'OPUS', 'OGG', 'M4A', 'WAV') else '' # Resolve album thumb URL (may be relative Plex path) thumb_url = row['album_thumb_url'] or '' if thumb_url and not thumb_url.startswith('http'): _ab = '' _at = '' if media_server_engine.client('plex') and media_server_engine.client('plex').server: _ab = getattr(media_server_engine.client('plex').server, '_baseurl', '') or '' _at = getattr(media_server_engine.client('plex').server, '_token', '') or '' if not _ab: _pc = config_manager.get_plex_config() _ab = (_pc.get('base_url', '') or '').rstrip('/') _at = _at or _pc.get('token', '') if _ab and thumb_url.startswith('/'): thumb_url = f"{_ab}{thumb_url}?X-Plex-Token={_at}" if _at else f"{_ab}{thumb_url}" current_track = { 'id': row['id'], 'title': track_title, 'artist': artist_name, 'album': row['album_title'], 'duration_ms': row['duration'] or 0, 'file_path': file_path, 'format': fmt, 'bitrate': row['bitrate'] or 0, 'spotify_track_id': row['spotify_track_id'], 'deezer_id': row['deezer_id'], 'thumb_url': thumb_url, } # Search all available metadata sources in parallel via the # shared module — same code path the Enhance Quality flow uses # so both endpoints have identical scoring + per-source query # optimization + current-match flagging. from core.metadata.multi_source_search import ( TrackQuery, search_all_sources, ) sources_to_search = [] if spotify_client and spotify_client.is_authenticated(): sources_to_search.append(('spotify', spotify_client)) try: sources_to_search.append(('itunes', _get_itunes_client())) except Exception as e: logger.debug(f"iTunes client not available for redownload search: {e}") try: sources_to_search.append(('deezer', _get_deezer_client())) except Exception as e: logger.debug(f"Deezer client not available for redownload search: {e}") track_query = TrackQuery( title=track_title, artist=artist_name, album=row['album_title'] or '', duration_ms=row['duration'] or 0, spotify_track_id=row['spotify_track_id'], deezer_id=row['deezer_id'], ) result = search_all_sources( track_query, sources_to_search, clean_title=clean_title, ) return jsonify({ "success": True, "current_track": current_track, "metadata_results": result.metadata_results, "best_match": result.best_match, }) except Exception as e: logger.error(f"Error in redownload metadata search: {e}", exc_info=True) return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/track//redownload/search-sources', methods=['POST']) def redownload_search_sources(track_id): """Search all active download sources for a track using the selected metadata.""" try: data = request.get_json() metadata = data.get('metadata', {}) if not metadata.get('name'): return jsonify({"success": False, "error": "metadata with name required"}), 400 # Build a track-like object for query generation from core.itunes_client import Track as MetaTrack track_obj = MetaTrack( id=metadata.get('id', ''), name=metadata['name'], artists=[metadata.get('artist', '')], album=metadata.get('album', ''), duration_ms=metadata.get('duration_ms', 0), popularity=0, ) # Generate search queries search_queries = matching_engine.generate_download_queries(track_obj) if not search_queries: search_queries = [f"{metadata.get('artist', '')} {metadata['name']}".strip()] # Use first 2 queries for speed search_queries = search_queries[:2] # Search ALL configured download sources individually (not through hybrid which stops at first hit) candidates = [] database = get_database() # Get all available download source clients via the orchestrator's # generic accessor — replaces the old per-source if/hasattr chain # that Cin called out as defeating the purpose of the registry refactor. download_clients = {} try: if download_orchestrator and hasattr(download_orchestrator, 'configured_clients'): download_clients = dict(download_orchestrator.configured_clients()) except Exception as e: logger.warning(f"[Redownload] Error getting download clients: {e}") if not download_clients: # Fallback: use orchestrator directly download_clients = {'default': download_orchestrator} logger.info(f"[Redownload] Streaming search across {len(download_clients)} sources: {list(download_clients.keys())}") def _search_one_source(source_name, client): """Search a single download source and return formatted candidates.""" source_candidates = [] for _qi, q in enumerate(search_queries): try: tracks_result, _ = run_async(client.search(q, timeout=20)) if not tracks_result: continue valid = get_valid_candidates(tracks_result, track_obj, q) for candidate in valid: is_bl = database.is_blacklisted(candidate.username, candidate.filename) display_name = os.path.basename(candidate.filename.replace('\\', '/')) ext = os.path.splitext(display_name)[1].lstrip('.').upper() quality = ext if ext in ('FLAC', 'MP3', 'OPUS', 'OGG', 'M4A', 'WAV') else candidate.quality or '' svc = source_name if source_name != 'default' else 'hybrid' uname = candidate.username if uname in ('youtube', 'tidal', 'qobuz', 'hifi', 'deezer_dl', 'lidarr', 'soundcloud'): svc = uname source_candidates.append({ 'username': uname, 'filename': candidate.filename, 'display_name': display_name, 'size': candidate.size or 0, 'size_display': f"{(candidate.size or 0) / 1048576:.1f} MB", 'bitrate': candidate.bitrate or 0, 'quality': quality, 'duration': candidate.duration or 0, 'confidence': round(getattr(candidate, 'confidence', 0), 3), 'source_service': svc, 'source_query': q, 'blacklisted': is_bl, 'free_upload_slots': getattr(candidate, 'free_upload_slots', 0), 'upload_speed': getattr(candidate, 'upload_speed', 0), 'queue_length': getattr(candidate, 'queue_length', 0), }) except Exception as e: logger.debug(f"[Redownload] {source_name} search failed for query '{q}': {e}") # Deduplicate within source seen = set() unique = [] for c in source_candidates: key = f"{c['username']}|{c['filename']}" if key not in seen: seen.add(key) unique.append(c) unique.sort(key=lambda c: (-int(not c['blacklisted']), -c['confidence'])) return unique # Stream NDJSON — one line per source as it completes from concurrent.futures import ThreadPoolExecutor, as_completed def generate_stream(): with ThreadPoolExecutor(max_workers=4) as pool: futures = {pool.submit(_search_one_source, name, client): name for name, client in download_clients.items()} for future in as_completed(futures): source_name = futures[future] try: results = future.result() yield json.dumps({'source': source_name, 'candidates': results}) + '\n' except Exception as e: yield json.dumps({'source': source_name, 'candidates': [], 'error': str(e)}) + '\n' yield json.dumps({'done': True}) + '\n' return app.response_class(generate_stream(), mimetype='application/x-ndjson', headers={'X-Accel-Buffering': 'no'}) except Exception as e: logger.error(f"Error in redownload source search: {e}", exc_info=True) return jsonify({"success": False, "error": str(e)}), 500 from core.library.redownload import ( redownload_start as _redownload_start_impl, init as _init_redownload, ) @app.route('/api/library/track//redownload/start', methods=['POST']) def redownload_start(track_id): return _redownload_start_impl(track_id) @app.route('/api/library/artist//sync', methods=['POST']) def sync_artist_library(artist_id): """Bidirectional sync: pull new content from media server AND remove stale entries.""" try: database = get_database() with database._get_connection() as conn: cursor = conn.cursor() # Resolve artist_id: could be a DB integer ID or a source artist ID (Spotify/iTunes/Deezer) db_artist_id = None # Try direct ID match first (works for both integer and text IDs) cursor.execute("SELECT id FROM artists WHERE id = ?", (artist_id,)) row = cursor.fetchone() if row: db_artist_id = row['id'] # Also try as integer (legacy integer PKs) if not db_artist_id: try: candidate = int(artist_id) cursor.execute("SELECT id FROM artists WHERE id = ?", (candidate,)) row = cursor.fetchone() if row: db_artist_id = row['id'] except (ValueError, TypeError): pass # Try source-specific ID columns if not db_artist_id: for col in ('spotify_artist_id', 'itunes_artist_id', 'deezer_id', 'discogs_id'): cursor.execute(f"SELECT id FROM artists WHERE {col} = ?", (artist_id,)) row = cursor.fetchone() if row: db_artist_id = row['id'] break if not db_artist_id: return jsonify({"success": False, "error": "Artist not found"}), 404 cursor.execute("SELECT name, server_source FROM artists WHERE id = ?", (db_artist_id,)) artist_row = cursor.fetchone() artist_name = artist_row['name'] if artist_row else f'ID {db_artist_id}' server_source = artist_row['server_source'] if artist_row else None # ── Phase 1: Pull new content from media server ── new_albums = 0 new_tracks = 0 name_updated = False if server_source: media_client = None if server_source == 'plex' and media_server_engine.client('plex') and media_server_engine.client('plex').server: media_client = media_server_engine.client('plex') elif server_source == 'jellyfin' and media_server_engine.client('jellyfin'): media_client = media_server_engine.client('jellyfin') elif server_source == 'navidrome' and media_server_engine.client('navidrome'): media_client = media_server_engine.client('navidrome') if media_client: try: from core.database_update_worker import DatabaseUpdateWorker worker = DatabaseUpdateWorker( media_client=media_client, full_refresh=False, server_type=server_source, force_sequential=True, ) worker.database = database # Use existing DB instance instead of creating new one # Fetch the artist object from the server server_artist = None logger.info(f"[Artist Sync] Fetching artist {db_artist_id} from {server_source}...") if server_source == 'plex' and hasattr(media_client, 'server'): try: server_artist = media_client.server.fetchItem(int(db_artist_id)) logger.info(f"[Artist Sync] Plex returned: {getattr(server_artist, 'title', 'None')}") except Exception as e: logger.error(f"[Artist Sync] Plex fetchItem failed: {e}") elif hasattr(media_client, 'get_artist_by_id'): try: server_artist = media_client.get_artist_by_id(str(db_artist_id)) logger.info(f"[Artist Sync] Server returned: {getattr(server_artist, 'title', None) or server_artist}") except Exception as e: logger.error(f"[Artist Sync] get_artist_by_id failed: {e}") else: logger.warning(f"[Artist Sync] No get_artist_by_id method on {type(media_client).__name__}") if not server_artist: logger.error("[Artist Sync] Could not fetch artist from server — skipping pull phase") if server_artist: # Check for name change new_name = getattr(server_artist, 'title', None) if new_name and new_name != artist_name: database.execute_query( "UPDATE artists SET name = ?, updated_at = CURRENT_TIMESTAMP WHERE id = ?", (new_name, db_artist_id) ) logger.info(f"[Artist Sync] Name updated: '{artist_name}' → '{new_name}'") artist_name = new_name name_updated = True # Process artist content (deep scan mode — skip existing, preserve enrichment) success, details, new_albums, new_tracks = worker._process_artist_with_content( server_artist, skip_existing_tracks=True ) logger.info(f"[Artist Sync] Server pull for {artist_name}: {details}") except Exception as e: logger.error(f"[Artist Sync] Server pull failed for {artist_name}: {e}") # ── Phase 2: Remove stale entries (files no longer on disk) ── stale_removed = 0 empty_albums_removed = 0 with database._get_connection() as conn: cursor = conn.cursor() cursor.execute("SELECT id, file_path FROM tracks WHERE artist_id = ?", (db_artist_id,)) tracks = cursor.fetchall() stale_ids = [] for track in tracks: fp = track['file_path'] if not fp: stale_ids.append(track['id']) continue resolved = _resolve_library_file_path(fp) if not resolved or not os.path.exists(resolved): stale_ids.append(track['id']) if stale_ids: placeholders = ','.join('?' for _ in stale_ids) cursor.execute(f"DELETE FROM tracks WHERE id IN ({placeholders})", stale_ids) stale_removed = len(stale_ids) cursor.execute(""" DELETE FROM albums WHERE artist_id = ? AND id NOT IN (SELECT DISTINCT album_id FROM tracks) """, (db_artist_id,)) empty_albums_removed = cursor.rowcount cursor.execute(""" UPDATE albums SET track_count = ( SELECT COUNT(*) FROM tracks WHERE tracks.album_id = albums.id ) WHERE artist_id = ? """, (db_artist_id,)) conn.commit() logger.warning(f"[Artist Sync] {artist_name}: +{new_albums} albums, +{new_tracks} tracks, " f"-{stale_removed} stale, -{empty_albums_removed} empty albums") return jsonify({ "success": True, "artist_name": artist_name, "name_updated": name_updated, "new_albums": new_albums, "new_tracks": new_tracks, "stale_removed": stale_removed, "empty_albums_removed": empty_albums_removed, }) except Exception as e: logger.error(f"Error syncing artist {artist_id}: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/album/', methods=['DELETE']) def library_delete_album(album_id): """Delete an album and all its tracks from the database, optionally deleting files on disk.""" try: delete_files = request.args.get('delete_files', 'false').lower() == 'true' database = get_database() files_deleted = 0 files_failed = 0 with database._get_connection() as conn: cursor = conn.cursor() # If deleting files, resolve and remove each track's file first if delete_files: cursor.execute("SELECT id, file_path FROM tracks WHERE album_id = ?", (album_id,)) track_rows = cursor.fetchall() for row in track_rows: fp = row['file_path'] if not fp: continue resolved = _resolve_library_file_path(fp) if resolved and os.path.exists(resolved): try: os.remove(resolved) files_deleted += 1 # Clean up sidecar files (.lrc, .txt lyrics) base_no_ext = os.path.splitext(resolved)[0] for sidecar_ext in ('.lrc', '.txt'): sidecar = base_no_ext + sidecar_ext if os.path.exists(sidecar): try: os.remove(sidecar) except Exception as e: logger.debug("sidecar removal failed: %s", e) except Exception as e: logger.warning(f"Failed to delete track file: {e}") files_failed += 1 else: files_failed += 1 # Try to remove the album folder if it's now empty if track_rows: first_fp = track_rows[0]['file_path'] if first_fp: resolved_first = _resolve_library_file_path(first_fp) if resolved_first: album_dir = os.path.dirname(resolved_first) try: if os.path.isdir(album_dir) and not os.listdir(album_dir): os.rmdir(album_dir) logger.info(f"Removed empty album directory: {album_dir}") except Exception as e: logger.debug("empty album dir cleanup failed: %s", e) # Delete all tracks belonging to this album cursor.execute("DELETE FROM tracks WHERE album_id = ?", (album_id,)) tracks_deleted = cursor.rowcount # Delete the album itself cursor.execute("DELETE FROM albums WHERE id = ?", (album_id,)) if cursor.rowcount == 0: conn.rollback() return jsonify({"success": False, "error": "Album not found"}), 404 conn.commit() return jsonify({ "success": True, "deleted_count": 1, "tracks_deleted": tracks_deleted, "files_deleted": files_deleted, "files_failed": files_failed }) except Exception as e: logger.error(f"Error deleting album {album_id}: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/tracks/delete-batch', methods=['POST']) def library_delete_tracks_batch(): """Delete multiple track records from the database (does NOT delete files on disk). Body: { track_ids: [int] } """ try: data = request.get_json() track_ids = data.get('track_ids', []) if not track_ids or not isinstance(track_ids, list): return jsonify({"success": False, "error": "track_ids array is required"}), 400 database = get_database() with database._get_connection() as conn: cursor = conn.cursor() placeholders = ','.join('?' for _ in track_ids) cursor.execute(f"DELETE FROM tracks WHERE id IN ({placeholders})", track_ids) conn.commit() return jsonify({"success": True, "deleted_count": cursor.rowcount}) except Exception as e: logger.error(f"Error batch deleting tracks: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/radio') def library_radio(): """Get a smart queue of similar tracks for radio mode auto-play.""" try: track_id = request.args.get('track_id') if not track_id: return jsonify({"success": False, "error": "track_id is required"}), 400 limit = request.args.get('limit', 20, type=int) exclude_raw = request.args.get('exclude', '') exclude_ids = [eid.strip() for eid in exclude_raw.split(',') if eid.strip()] if exclude_raw else None database = get_database() result = database.get_radio_tracks(track_id, limit=limit, exclude_ids=exclude_ids) if not result.get('success'): return jsonify(result), 404 # Fix image URLs (DB stores server-relative paths that need base URL + auth) for track in result.get('tracks', []): if track.get('image_url'): track['image_url'] = fix_artist_image_url(track['image_url']) return jsonify(result) except Exception as e: logger.error(f"Error getting radio tracks: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 # ==================== End Enhanced Library Management ==================== @app.route('/api/stream/start', methods=['POST']) def stream_start(): """Start streaming a track in the background""" global stream_background_task data = request.get_json() if not data: return jsonify({"success": False, "error": "No track data provided"}), 400 logger.info(f"Web UI Stream request for: {data.get('filename')}") try: # Stop any existing streaming task if stream_background_task and not stream_background_task.done(): stream_background_task.cancel() # Reset stream state with stream_lock: stream_state.update({ "status": "stopped", "progress": 0, "track_info": None, "file_path": None, "error_message": None, "is_library": False }) # Start new background streaming task stream_background_task = stream_executor.submit(_prepare_stream_task, data) return jsonify({"success": True, "message": "Streaming started"}) except Exception as e: logger.error(f"Error starting stream: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/stream/status') def stream_status(): """Get current streaming status and progress""" try: with stream_lock: # Return copy of current stream state return jsonify({ "status": stream_state["status"], "progress": stream_state["progress"], "track_info": stream_state["track_info"], "error_message": stream_state["error_message"] }) except Exception as e: logger.error(f"Error getting stream status: {e}") return jsonify({ "status": "error", "progress": 0, "track_info": None, "error_message": str(e) }), 500 @app.route('/stream/audio') def stream_audio(): """Serve the audio file from the Stream folder with range request support""" try: with stream_lock: if stream_state["status"] != "ready" or not stream_state["file_path"]: return jsonify({"error": "No audio file ready for streaming"}), 404 file_path = stream_state["file_path"] if not os.path.exists(file_path): return jsonify({"error": "Audio file not found"}), 404 logger.info(f"Serving audio file: {os.path.basename(file_path)}") # Determine MIME type based on file extension file_ext = os.path.splitext(file_path)[1].lower() mime_types = { '.mp3': 'audio/mpeg', '.flac': 'audio/flac', '.ogg': 'audio/ogg', '.aac': 'audio/aac', '.m4a': 'audio/mp4', '.wav': 'audio/wav', '.opus': 'audio/ogg', '.webm': 'audio/webm', '.wma': 'audio/x-ms-wma' } mimetype = mime_types.get(file_ext, 'audio/mpeg') # Get file size file_size = os.path.getsize(file_path) # Handle range requests (important for HTML5 audio seeking) range_header = request.headers.get('Range', None) if range_header: byte_start = 0 byte_end = file_size - 1 # Parse range header (format: "bytes=start-end") try: range_match = re.match(r'bytes=(\d*)-(\d*)', range_header) if range_match: start_str, end_str = range_match.groups() if start_str: byte_start = int(start_str) if end_str: byte_end = int(end_str) else: # If no end specified, serve from start to end of file byte_end = file_size - 1 except (ValueError, AttributeError): # Invalid range header, serve full file pass # Ensure valid range byte_start = max(0, byte_start) byte_end = min(file_size - 1, byte_end) content_length = byte_end - byte_start + 1 # Create response with partial content def generate(): with open(file_path, 'rb') as f: f.seek(byte_start) remaining = content_length while remaining: chunk_size = min(8192, remaining) # 8KB chunks chunk = f.read(chunk_size) if not chunk: break remaining -= len(chunk) yield chunk response = Response(generate(), status=206, # Partial Content mimetype=mimetype, direct_passthrough=True) # Set range headers response.headers.add('Content-Range', f'bytes {byte_start}-{byte_end}/{file_size}') response.headers.add('Accept-Ranges', 'bytes') response.headers.add('Content-Length', str(content_length)) response.headers.add('Cache-Control', 'no-cache') return response else: # No range request, serve entire file response = send_file(file_path, as_attachment=False, mimetype=mimetype) response.headers.add('Accept-Ranges', 'bytes') response.headers.add('Content-Length', str(file_size)) # Override the default static-cache max-age — streaming media # bypasses caching (range requests, mid-track seeks). response.headers['Cache-Control'] = 'no-cache' return response except Exception as e: logger.error(f"Error serving audio file: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/stream/stop', methods=['POST']) def stream_stop(): """Stop streaming and clean up""" global stream_background_task try: # Cancel background task if stream_background_task and not stream_background_task.done(): stream_background_task.cancel() # Only clear Stream folder if NOT playing a library file with stream_lock: is_library = stream_state.get("is_library", False) if not is_library: project_root = os.path.dirname(os.path.abspath(__file__)) stream_folder = os.path.join(project_root, 'Stream') if os.path.exists(stream_folder): for filename in os.listdir(stream_folder): file_path = os.path.join(stream_folder, filename) if os.path.isfile(file_path): os.remove(file_path) logger.info(f"Removed stream file: {filename}") else: logger.info("Library playback stopped - skipping file deletion") # Reset stream state with stream_lock: stream_state.update({ "status": "stopped", "progress": 0, "track_info": None, "file_path": None, "error_message": None, "is_library": False }) return jsonify({"success": True, "message": "Stream stopped"}) except Exception as e: logger.error(f"Error stopping stream: {e}") return jsonify({"success": False, "error": str(e)}), 500 # --- Matched Downloads API Endpoints --- def _generate_artist_suggestions(search_result, is_album=False, album_result=None): """ Port of ArtistSuggestionThread.generate_artist_suggestions() from GUI Generate artist suggestions using multiple strategies """ if not spotify_client or not matching_engine: return [] try: logger.info(f"Generating artist suggestions for: {search_result.get('artist', '')} - {search_result.get('title', '')}") suggestions = [] # Special handling for albums - use album title to find artist if is_album and album_result and album_result.get('album_title'): logger.info("Album mode detected - using album title for artist search") album_title = album_result.get('album_title', '') # Clean album title (remove year prefixes like "(2005)") import re clean_album_title = re.sub(r'^\(\d{4}\)\s*', '', album_title).strip() logger.info(f" clean_album_title: '{clean_album_title}'") # Search tracks using album title to find the artist tracks = spotify_client.search_tracks(clean_album_title, limit=10) logger.info(f"Found {len(tracks)} tracks from album search") # Collect unique artists and their associated tracks/albums unique_artists = {} # artist_name -> list of (track, album) tuples for track in tracks: for artist_name in track.artists: if artist_name not in unique_artists: unique_artists[artist_name] = [] unique_artists[artist_name].append((track, track.album)) # Batch fetch artist objects for speed from concurrent.futures import ThreadPoolExecutor, as_completed artist_objects = {} # artist_name -> Artist object def fetch_artist(artist_name): try: matches = spotify_client.search_artists(artist_name, limit=1) if matches: return artist_name, matches[0] except Exception as e: logger.error(f"Error fetching artist '{artist_name}': {e}") return artist_name, None # Use limited concurrency to respect rate limits with ThreadPoolExecutor(max_workers=3) as executor: future_to_artist = {executor.submit(fetch_artist, name): name for name in unique_artists.keys()} for future in as_completed(future_to_artist): artist_name, artist_obj = future.result() if artist_obj: artist_objects[artist_name] = artist_obj # Calculate confidence scores for each artist artist_scores = {} for artist_name, track_album_pairs in unique_artists.items(): if artist_name not in artist_objects: continue artist = artist_objects[artist_name] best_confidence = 0 # Find the best confidence score across all albums for this artist for _track, album in track_album_pairs: confidence = matching_engine.similarity_score( matching_engine.normalize_string(clean_album_title), matching_engine.normalize_string(album) ) if confidence > best_confidence: best_confidence = confidence artist_scores[artist_name] = (artist, best_confidence) # Create suggestions from top matches for _artist_name, (artist, confidence) in sorted(artist_scores.items(), key=lambda x: x[1][1], reverse=True)[:8]: suggestions.append({ "artist": { "id": artist.id, "name": artist.name, "image_url": getattr(artist, 'image_url', None), "genres": getattr(artist, 'genres', []), "popularity": getattr(artist, 'popularity', 0) }, "confidence": confidence }) else: # Single track mode - search by artist name search_artist = search_result.get('artist', '') if not search_artist: return [] logger.info(f"Single track mode - searching for artist: '{search_artist}'") # Search for artists directly artist_matches = spotify_client.search_artists(search_artist, limit=10) for artist in artist_matches: # Calculate confidence based on artist name similarity confidence = matching_engine.similarity_score( matching_engine.normalize_string(search_artist), matching_engine.normalize_string(artist.name) ) suggestions.append({ "artist": { "id": artist.id, "name": artist.name, "image_url": getattr(artist, 'image_url', None), "genres": getattr(artist, 'genres', []), "popularity": getattr(artist, 'popularity', 0) }, "confidence": confidence }) # Sort by confidence and return top results suggestions.sort(key=lambda x: x['confidence'], reverse=True) return suggestions[:4] except Exception as e: logger.error(f"Error generating artist suggestions: {e}") return [] def _generate_album_suggestions(selected_artist, search_result): """ Port of AlbumSuggestionThread logic from GUI Generate album suggestions for a selected artist """ if not spotify_client or not matching_engine: return [] try: logger.info(f"Generating album suggestions for artist: {selected_artist['name']}") # Determine target album name from search result target_album_name = search_result.get('album', '') or search_result.get('album_title', '') if not target_album_name: logger.warning("No album name found in search result") return [] # Clean target album name import re clean_target = re.sub(r'^\(\d{4}\)\s*', '', target_album_name).strip() logger.info(f" target_album: '{clean_target}'") # Get artist's albums from Spotify artist_albums = spotify_client.get_artist_albums(selected_artist['id']) logger.info(f"Found {len(artist_albums)} albums for artist") album_matches = [] for album in artist_albums: # Calculate confidence based on album name similarity confidence = matching_engine.similarity_score( matching_engine.normalize_string(clean_target), matching_engine.normalize_string(album.name) ) album_matches.append({ "album": { "id": album.id, "name": album.name, "release_date": getattr(album, 'release_date', ''), "album_type": getattr(album, 'album_type', 'album'), "image_url": getattr(album, 'image_url', None), "total_tracks": getattr(album, 'total_tracks', 0) }, "confidence": confidence }) # Sort by confidence and return top results album_matches.sort(key=lambda x: x['confidence'], reverse=True) return album_matches[:4] except Exception as e: logger.error(f"Error generating album suggestions: {e}") return [] @app.route('/api/match/suggestions', methods=['POST']) def get_match_suggestions(): """Get AI-powered suggestions for artist or album matching""" try: data = request.get_json() search_result = data.get('search_result', {}) context = data.get('context', 'artist') # 'artist' or 'album' if context == 'artist': is_album = data.get('is_album', False) album_result = data.get('album_result', None) if is_album else None suggestions = _generate_artist_suggestions(search_result, is_album, album_result) elif context == 'album': selected_artist = data.get('selected_artist', {}) suggestions = _generate_album_suggestions(selected_artist, search_result) else: return jsonify({"error": "Invalid context. Must be 'artist' or 'album'"}), 400 return jsonify({"suggestions": suggestions}) except Exception as e: logger.error(f"Error in match suggestions: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/match/search', methods=['POST']) def search_match(): """Manual search for artists or albums""" try: data = request.get_json() query = data.get('query', '').strip() context = data.get('context', 'artist') # 'artist' or 'album' if not query: return jsonify({"results": []}) use_hydrabase = _is_hydrabase_active() # Mirror to Hydrabase P2P network (fire-and-forget when not primary) if not use_hydrabase and hydrabase_worker and dev_mode_enabled: hydrabase_worker.enqueue(query, context) if context == 'artist': # Search for artists — title-case the query for better API results # (some metadata APIs return fewer results for all-lowercase queries) search_query = query.title() if query == query.lower() else query if use_hydrabase: artist_matches = hydrabase_client.search_artists(search_query, limit=8) provider = 'hydrabase' else: artist_matches = _get_metadata_fallback_client().search_artists(search_query, limit=8) provider = _get_metadata_fallback_source() results = [] for artist in artist_matches: # Calculate confidence based on search similarity confidence = matching_engine.similarity_score( matching_engine.normalize_string(query), matching_engine.normalize_string(artist.name) ) results.append({ "artist": { "id": artist.id, "name": artist.name, "image_url": getattr(artist, 'image_url', None), "genres": getattr(artist, 'genres', []), "popularity": getattr(artist, 'popularity', 0), "followers": getattr(artist, 'followers', 0) }, "confidence": confidence }) return jsonify({"results": results, "provider": provider}) elif context == 'album': # Search for albums by specific artist artist_id = data.get('artist_id') if use_hydrabase: # Hydrabase: search albums by query directly album_matches = hydrabase_client.search_albums(query, limit=20) provider = 'hydrabase' else: if not artist_id: return jsonify({"error": "Artist ID required for album search"}), 400 # Get artist's albums and filter by query album_matches = _get_metadata_fallback_client().get_artist_albums(artist_id) provider = _get_metadata_fallback_source() results = [] for album in album_matches: # Calculate confidence based on query similarity confidence = matching_engine.similarity_score( matching_engine.normalize_string(query), matching_engine.normalize_string(album.name) ) # Only include results with reasonable similarity if confidence > 0.3: results.append({ "album": { "id": album.id, "name": album.name, "release_date": getattr(album, 'release_date', ''), "album_type": getattr(album, 'album_type', 'album'), "image_url": getattr(album, 'image_url', None), "total_tracks": getattr(album, 'total_tracks', 0) }, "confidence": confidence }) # Sort by confidence results.sort(key=lambda x: x['confidence'], reverse=True) return jsonify({"results": results[:8], "provider": provider}) else: return jsonify({"error": "Invalid context. Must be 'artist' or 'album'"}), 400 except Exception as e: logger.error(f"Error in match search: {e}") return jsonify({"error": str(e)}), 500 def _is_explicit_blocked(track_data): """Check if a track should be blocked by the explicit content filter. Returns True if the track is explicit and explicit content is disabled.""" if config_manager.get('content_filter.allow_explicit', True): return False # Check direct explicit field if track_data.get('explicit', False): return True # Check nested spotify_data (wishlist tracks) sp_data = track_data.get('spotify_data', {}) if isinstance(sp_data, str): try: sp_data = json.loads(sp_data) except Exception: sp_data = {} return sp_data.get('explicit', False) def _start_enhanced_album_download(enhanced_tracks, unmatched_tracks, spotify_artist, spotify_album): """ Download album tracks that have been matched to Spotify with full track metadata. This provides the best possible metadata enhancement and organization. """ logger.info(f"Processing enhanced album download for '{spotify_album['name']}' with {len(enhanced_tracks)} matched tracks") # Compute total_discs for multi-disc album subfolder support total_discs = max((t['spotify_track'].get('disc_number', 1) for t in enhanced_tracks), default=1) spotify_album['total_discs'] = total_discs started_count = 0 # PREFLIGHT: Pre-populate MusicBrainz release cache so all tracks get the same release try: mb_svc = mb_worker.mb_service if mb_worker else None if mb_svc and spotify_album.get('name') and spotify_artist.get('name'): from core.album_consistency import _find_best_release _pf_count = len(enhanced_tracks) + len(unmatched_tracks) _pf_release = _find_best_release(spotify_album['name'], spotify_artist['name'], _pf_count, mb_svc) if _pf_release and _pf_release.get('id'): _pf_mbid = _pf_release['id'] _pf_artist_key = spotify_artist['name'].lower().strip() with mb_release_cache_lock: mb_release_cache[(normalize_album_cache_key(spotify_album['name']), _pf_artist_key)] = _pf_mbid mb_release_cache[(spotify_album['name'].lower().strip(), _pf_artist_key)] = _pf_mbid with mb_release_detail_cache_lock: mb_release_detail_cache[_pf_mbid] = _pf_release logger.info(f"[Preflight] Pre-cached MB release for '{spotify_album['name']}': " f"'{_pf_release.get('title', '')}' ({_pf_mbid[:8]}...)") except Exception as pf_err: logger.error(f"[Preflight] MB release preflight failed: {pf_err}") # Process matched tracks with full Spotify metadata for matched_item in enhanced_tracks: try: slskd_track = matched_item['slskd_track'] spotify_track = matched_item['spotify_track'] if _is_explicit_blocked(spotify_track): logger.info(f"[Content Filter] Skipping explicit track: '{spotify_track.get('name')}'") continue username = slskd_track.get('username') filename = slskd_track.get('filename') size = slskd_track.get('size', 0) if not username or not filename: logger.warning(f"Skipping track with missing username or filename: {slskd_track}") continue # Start download download_id = run_async(download_orchestrator.download(username, filename, size)) if download_id: context_key = _make_context_key(username, filename) with matched_context_lock: # Create context with FULL Spotify track metadata (like Download Missing Tracks modal) matched_downloads_context[context_key] = { "spotify_artist": spotify_artist, "spotify_album": spotify_album, "track_info": spotify_track, # Full Spotify track object! "original_search_result": { 'username': username, 'filename': filename, 'size': size, 'title': spotify_track['name'], # Use Spotify title 'artist': spotify_artist['name'], 'album': spotify_album['name'], 'track_number': spotify_track['track_number'], # Use Spotify track number 'disc_number': spotify_track.get('disc_number', 1), 'spotify_clean_title': spotify_track['name'] # For filename generation }, "is_album_download": True, "has_full_spotify_metadata": True # Flag for robust processing } logger.info( "Queued matched track: title=%r track_number=%s", spotify_track['name'], spotify_track['track_number'], ) started_count += 1 else: logger.error("Failed to queue track: filename=%s", filename) except Exception as e: logger.error(f"Error processing matched track: {e}") continue # Process unmatched tracks with basic cleanup for slskd_track in unmatched_tracks: try: username = slskd_track.get('username') filename = slskd_track.get('filename') size = slskd_track.get('size', 0) if not username or not filename: continue download_id = run_async(download_orchestrator.download(username, filename, size)) if download_id: context_key = _make_context_key(username, filename) with matched_context_lock: # Basic context for unmatched tracks (simple cleanup) matched_downloads_context[context_key] = { 'search_result': { 'username': username, 'filename': filename, 'size': size, 'is_simple_download': True # Falls back to simple transfer }, 'spotify_artist': None, 'spotify_album': None, 'track_info': None } logger.info(f"Queued unmatched track (basic cleanup): {filename}") started_count += 1 except Exception as e: logger.error(f"Error processing unmatched track: {e}") continue return started_count def _start_album_download_tasks(album_result, spotify_artist, spotify_album): """ This final version now fetches the official Spotify tracklist and uses it to match and correct the metadata for each individual track before downloading, ensuring perfect tagging and naming. """ logger.info(f"Processing matched album download for '{spotify_album['name']}' with {len(album_result.get('tracks', []))} tracks.") tracks_to_download = album_result.get('tracks', []) if not tracks_to_download: logger.warning("Album result contained no tracks. Aborting.") return 0 # --- THIS IS THE NEW LOGIC --- # Fetch the official tracklist from Spotify ONCE for the entire album. official_spotify_tracks = _get_spotify_album_tracks(spotify_album) if not official_spotify_tracks: logger.error("Could not fetch official tracklist from Spotify. Metadata may be inaccurate.") # --- END OF NEW LOGIC --- # Compute total_discs for multi-disc album subfolder support if official_spotify_tracks: total_discs = max((t.get('disc_number', 1) for t in official_spotify_tracks), default=1) else: total_discs = 1 spotify_album['total_discs'] = total_discs # PREFLIGHT: Pre-populate MusicBrainz release cache so all tracks get the same release try: mb_svc = mb_worker.mb_service if mb_worker else None if mb_svc and spotify_album.get('name') and spotify_artist.get('name'): from core.album_consistency import _find_best_release _pf_release = _find_best_release(spotify_album['name'], spotify_artist['name'], len(tracks_to_download), mb_svc) if _pf_release and _pf_release.get('id'): _pf_mbid = _pf_release['id'] _pf_artist_key = spotify_artist['name'].lower().strip() with mb_release_cache_lock: mb_release_cache[(normalize_album_cache_key(spotify_album['name']), _pf_artist_key)] = _pf_mbid mb_release_cache[(spotify_album['name'].lower().strip(), _pf_artist_key)] = _pf_mbid with mb_release_detail_cache_lock: mb_release_detail_cache[_pf_mbid] = _pf_release logger.info(f"[Preflight] Pre-cached MB release for '{spotify_album['name']}': " f"'{_pf_release.get('title', '')}' ({_pf_mbid[:8]}...)") except Exception as pf_err: logger.error(f"[Preflight] MB release preflight failed: {pf_err}") started_count = 0 for track_data in tracks_to_download: try: username = track_data.get('username') or album_result.get('username') filename = track_data.get('filename') size = track_data.get('size', 0) if not username or not filename: continue # Pre-parse the filename to get a baseline for metadata parsed_meta = _parse_filename_metadata(filename) # --- THIS IS THE CRITICAL MATCHING STEP --- # Match the parsed metadata against the official Spotify tracklist corrected_meta = _match_track_to_spotify_title(parsed_meta, official_spotify_tracks) # --- END OF CRITICAL STEP --- if _is_explicit_blocked(corrected_meta): logger.info(f"[Content Filter] Skipping explicit track: '{corrected_meta.get('title')}'") continue # Create a clean context object using the CORRECTED metadata individual_track_context = { 'username': username, 'filename': filename, 'size': size, 'title': corrected_meta.get('title'), 'artist': corrected_meta.get('artist') or spotify_artist['name'], 'album': spotify_album['name'], 'track_number': corrected_meta.get('track_number'), 'disc_number': corrected_meta.get('disc_number', 1) } download_id = run_async(download_orchestrator.download(username, filename, size)) if download_id: context_key = _make_context_key(username, filename) with matched_context_lock: # Enhanced context storage with Spotify clean titles (GUI parity) enhanced_context = individual_track_context.copy() enhanced_context['spotify_clean_title'] = individual_track_context.get('title', '') matched_downloads_context[context_key] = { "spotify_artist": spotify_artist, "spotify_album": spotify_album, "original_search_result": enhanced_context, # Contains corrected data + clean title "is_album_download": True } logger.info( "Queued track: filename=%s matched_title=%r", filename, corrected_meta.get('title'), ) started_count += 1 else: logger.error("Failed to queue track: filename=%s", filename) except Exception as e: logger.error(f"Error processing track in album batch: {track_data.get('filename')}: {e}") continue return started_count @app.route('/api/download/matched', methods=['POST']) def start_matched_download(): """ Starts a matched download. Supports: 1. Enhanced album downloads with full Spotify track metadata 2. Regular album downloads (fallback) 3. Single track downloads """ dl_err = check_download_permission() if dl_err: return dl_err try: data = request.get_json() download_payload = data.get('search_result', {}) spotify_artist = data.get('spotify_artist', {}) spotify_album = data.get('spotify_album', None) enhanced_tracks = data.get('enhanced_tracks', []) # Album: Matched tracks with Spotify data unmatched_tracks = data.get('unmatched_tracks', []) # Album: Tracks that didn't match spotify_track = data.get('spotify_track', None) # Single: Full Spotify track object is_single_track = data.get('is_single_track', False) # Single: Flag for single track if not download_payload or not spotify_artist: return jsonify({"success": False, "error": "Missing download payload or artist data"}), 400 # NEW: Enhanced single track with full Spotify metadata if is_single_track and spotify_track: if _is_explicit_blocked(spotify_track): return jsonify({"success": False, "error": "Explicit content is disabled in settings", "explicit_blocked": True}), 403 logger.info(f"Starting enhanced single track download: '{spotify_track['name']}' by {spotify_artist['name']}") username = download_payload.get('username') filename = download_payload.get('filename') size = download_payload.get('size', 0) if not username or not filename: return jsonify({"success": False, "error": "Missing username or filename"}), 400 download_id = run_async(download_orchestrator.download(username, filename, size)) if download_id: context_key = _make_context_key(username, filename) with matched_context_lock: # Create context with FULL Spotify track metadata (like Download Missing Tracks modal) matched_downloads_context[context_key] = { "spotify_artist": spotify_artist, "spotify_album": spotify_track.get('album'), # Single's album from Spotify "track_info": spotify_track, # Full Spotify track object! "original_search_result": { 'username': username, 'filename': filename, 'size': size, 'title': spotify_track['name'], 'artist': spotify_artist['name'], 'album': spotify_track.get('album', {}).get('name', 'Unknown Album'), 'track_number': spotify_track.get('track_number', 1), 'spotify_clean_title': spotify_track['name'] }, "is_album_download": False, # It's a single "has_full_spotify_metadata": True # Flag for robust processing } logger.info(f"Queued enhanced single track: '{spotify_track['name']}'") return jsonify({"success": True, "message": "Enhanced single track download started"}) else: return jsonify({"success": False, "error": "Failed to start download via slskd"}), 500 # NEW: Enhanced album download with track-to-track matching if enhanced_tracks: logger.info(f"Starting enhanced album download: {len(enhanced_tracks)} matched tracks, {len(unmatched_tracks)} unmatched") started_count = _start_enhanced_album_download(enhanced_tracks, unmatched_tracks, spotify_artist, spotify_album) if started_count > 0: return jsonify({"success": True, "message": f"Queued {started_count} tracks with full Spotify metadata."}) else: return jsonify({"success": False, "error": "Failed to queue any tracks from the album."}), 500 # Regular album download (fallback if matching fails) is_full_album_download = bool(spotify_album and download_payload.get('result_type') == 'album') if is_full_album_download: started_count = _start_album_download_tasks(download_payload, spotify_artist, spotify_album) if started_count > 0: return jsonify({"success": True, "message": f"Queued {started_count} tracks for matched album download."}) else: return jsonify({"success": False, "error": "Failed to queue any tracks from the album."}), 500 else: # This block handles BOTH regular singles AND individual tracks from an album card. username = download_payload.get('username') filename = download_payload.get('filename') size = download_payload.get('size', 0) if not username or not filename: return jsonify({"success": False, "error": "Missing username or filename"}), 400 parsed_meta = _parse_filename_metadata(filename) download_payload['title'] = parsed_meta.get('title') or download_payload.get('title') download_payload['artist'] = parsed_meta.get('artist') or download_payload.get('artist') download_id = run_async(download_orchestrator.download(username, filename, size)) if download_id: context_key = _make_context_key(username, filename) with matched_context_lock: # THE FIX: We preserve the spotify_album context if it was provided. # For a regular single, spotify_album will be None. # For an album track, it will contain the album's data. # Enhanced context storage with Spotify clean titles (GUI parity) enhanced_payload = download_payload.copy() enhanced_payload['spotify_clean_title'] = download_payload.get('title', '') matched_downloads_context[context_key] = { "spotify_artist": spotify_artist, "spotify_album": spotify_album, # PRESERVE album context "original_search_result": enhanced_payload, "is_album_download": False # It's a single track download, not a full album job. } return jsonify({"success": True, "message": "Matched download started"}) else: return jsonify({"success": False, "error": "Failed to start download via slskd"}), 500 except Exception as e: import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 def _parse_filename_metadata(filename: str) -> dict: """ A direct port of the metadata parsing logic from the GUI's download_orchestrator.py. This is the crucial missing step that cleans filenames BEFORE Spotify matching. """ return parse_filename_metadata(filename) def _read_staging_file_metadata(full_path: str, filename: str) -> dict: """Read metadata from a staging file — tags first, filename parsing as fallback. Returns dict with: title, artist, albumartist, album, track_number, disc_number. Only falls back to filename parsing when BOTH title AND artist tags are empty. """ return read_staging_file_metadata(full_path, filename) # =================================================================== # NEW POST-PROCESSING HELPERS (Ported from downloads.py) # =================================================================== def _sanitize_filename(filename: str) -> str: """Sanitize filename for file system compatibility.""" import re sanitized = re.sub(r'[<>:"/\\|?*]', '_', filename) sanitized = re.sub(r'\s+', ' ', sanitized).strip() # Windows forbids trailing dots/spaces on files and folders. # Artists like "Fred again.." would create mangled 8.3 short names. sanitized = sanitized.rstrip('. ') or '_' # Windows reserved device names (CON, PRN, AUX, NUL, COM1-9, LPT1-9) # can't be used as file or folder names even with extensions. if re.match(r'^(CON|PRN|AUX|NUL|COM[1-9]|LPT[1-9])(\.|$)', sanitized, re.IGNORECASE): sanitized = '_' + sanitized return sanitized[:200] def _sanitize_context_values(context: dict) -> dict: """ Sanitize all string values in context dict for path safety. Prevents characters like '/' in artist names (e.g., 'AC/DC') from being interpreted as path separators during template substitution. Args: context: Dictionary with metadata values Returns: New dictionary with sanitized string values """ sanitized = {} for key, value in context.items(): if isinstance(value, str) and value: sanitized[key] = _sanitize_filename(value) else: sanitized[key] = value return sanitized def _clean_track_title(track_title: str, artist_name: str) -> str: """Clean up track title by removing artist prefix and other noise.""" import re original = track_title.strip() cleaned = original cleaned = re.sub(r'^\d{1,2}[\.\s\-]+', '', cleaned) artist_pattern = re.escape(artist_name) + r'\s*-\s*' cleaned = re.sub(f'^{artist_pattern}', '', cleaned, flags=re.IGNORECASE) cleaned = re.sub(r'^[A-Za-z0-9\.]+\s*-\s*\d{1,2}\s*-\s*', '', cleaned) quality_patterns = [r'\s*[\[\(][0-9]+\s*kbps[\]\)]\s*', r'\s*[\[\(]flac[\]\)]\s*', r'\s*[\[\(]mp3[\]\)]\s*'] for pattern in quality_patterns: cleaned = re.sub(pattern, '', cleaned, flags=re.IGNORECASE) cleaned = re.sub(r'^[-\s\.]+', '', cleaned) cleaned = re.sub(r'[-\s\.]+$', '', cleaned) cleaned = re.sub(r'\s+', ' ', cleaned).strip() return cleaned if cleaned else original def _extract_track_number_from_filename(filename: str, title: str = None) -> int: """Extract track number from filename, returns 1 if not found. Requires a separator after digits to avoid matching artist names like '50 Cent'.""" import re import os basename = os.path.splitext(os.path.basename(filename))[0].strip() # Match: "01 - Song", "01. Song", "01-Song", "1.Song", "(01) Song", "[01] Song" match = re.match(r'^\(?(\d{1,3})\)?\s*[\-\.)\]]\s*', basename) if match: num = int(match.group(1)) if 1 <= num <= 999: return num # Match: "1-03 Song" (disc-track format) match = re.match(r'^\d[\-\.](\d{1,2})\s*[\-\.]\s*', basename) if match: num = int(match.group(1)) if 1 <= num <= 99: return num return 1 def _search_track_in_album_context(original_search: dict, artist: dict) -> dict: """ Searches for a track within its album context to avoid matching promotional singles. This is a direct port from downloads.py for web server use. """ try: album_name = original_search.get('album') track_title = original_search.get('title') if not all([album_name, track_title, artist]): return None clean_album = _clean_track_title(album_name, artist['name']) # Use track cleaner for album too clean_track = _clean_track_title(track_title, artist['name']) album_query = f"album:\"{clean_album}\" artist:\"{artist['name']}\"" albums = spotify_client.search_albums(album_query, limit=1) if not albums: return None spotify_album = albums[0] album_tracks_data = spotify_client.get_album_tracks(spotify_album.id) if not album_tracks_data or 'items' not in album_tracks_data: return None for track_data in album_tracks_data['items']: similarity = matching_engine.similarity_score( matching_engine.normalize_string(clean_track), matching_engine.normalize_string(track_data['name']) ) if similarity > 0.7: logger.info(f"Found track in album context: '{track_data['name']}'") return { 'is_album': True, 'album_name': spotify_album.name, 'track_number': track_data['track_number'], 'clean_track_name': track_data['name'], 'album_image_url': spotify_album.image_url } return None except Exception as e: logger.error(f"Error in _search_track_in_album_context: {e}") return None def _cleanup_empty_directories(download_path, moved_file_path): """Cleans up empty directories after a file move, ignoring hidden files.""" import os try: current_dir = os.path.dirname(moved_file_path) while current_dir != download_path and current_dir.startswith(download_path): is_empty = not any(not f.startswith('.') for f in os.listdir(current_dir)) if is_empty: logger.warning(f"Removing empty directory: {current_dir}") os.rmdir(current_dir) current_dir = os.path.dirname(current_dir) else: break except Exception as e: logger.error(f"An error occurred during directory cleanup: {e}") def _sweep_empty_download_directories(): """ Walk the download directory bottom-up and remove ALL empty directories. Called periodically when no downloads or post-processing are active. Handles the edge case where per-file cleanup misses folders that become empty only after all sibling downloads in a batch have been processed. """ import os try: download_path = docker_resolve_path(config_manager.get('soulseek.download_path', './downloads')) if not os.path.isdir(download_path): return 0 removed = 0 # os.walk bottom-up: deepest directories first so parents become empty after children removed for dirpath, _dirnames, _filenames in os.walk(download_path, topdown=False): # Never remove the root download directory itself if os.path.normpath(dirpath) == os.path.normpath(download_path): continue # Re-read actual contents — os.walk's lists are stale after child removal try: entries = os.listdir(dirpath) except OSError: continue visible = [e for e in entries if not e.startswith('.')] if not visible: try: # Remove any leftover hidden files (e.g. .DS_Store) before rmdir for hidden in entries: try: os.remove(os.path.join(dirpath, hidden)) except Exception as e: logger.debug("hidden file cleanup failed: %s", e) os.rmdir(dirpath) removed += 1 except OSError: pass # Directory not actually empty or locked — skip silently if removed > 0: logger.warning(f"[Folder Cleanup] Removed {removed} empty director{'y' if removed == 1 else 'ies'} from downloads folder") return removed except Exception as e: logger.error(f"[Folder Cleanup] Error sweeping empty directories: {e}") return 0 # =================================================================== # ALBUM GROUPING SYSTEM (Ported from GUI downloads.py) # =================================================================== def _get_base_album_name(album_name: str) -> str: """ Extract the base album name without edition indicators. E.g., 'good kid, m.A.A.d city (Deluxe Edition)' -> 'good kid, m.A.A.d city' 'Battle Hymns (MMXI Special Edition)' -> 'Battle Hymns' """ import re # Remove common edition suffixes base_name = album_name # Remove edition indicators in parentheses or brackets # Allow any prefix before the keyword (e.g. "MMXI Special Edition", "20th Anniversary Edition") base_name = re.sub(r'\s*[\[\(][^)\]]*\b(deluxe|special|expanded|extended|bonus|remaster(?:ed)?|anniversary|collectors?|limited|silver|gold|platinum)\b[^)\]]*[\]\)]\s*$', '', base_name, flags=re.IGNORECASE) # Generic: any parenthesized/bracketed text ending with "edition" base_name = re.sub(r'\s*[\[\(][^)\]]*\bedition\b[^)\]]*[\]\)]\s*$', '', base_name, flags=re.IGNORECASE) # Remove standalone edition words at the end base_name = re.sub(r'\s+(deluxe|special|expanded|extended|bonus|remastered|anniversary|collectors?|limited|silver|gold|platinum)\s*(edition)?\s*$', '', base_name, flags=re.IGNORECASE) return base_name.strip() def _detect_deluxe_edition(album_name: str) -> bool: """ Detect if an album name indicates a deluxe/special edition. Returns True if it's a deluxe variant, False for standard. """ if not album_name: return False album_lower = album_name.lower() # Check for deluxe indicators deluxe_indicators = [ 'deluxe', 'deluxe edition', 'special edition', 'expanded edition', 'extended edition', 'bonus', 'remastered', 'anniversary', 'collectors edition', 'limited edition', 'silver edition', 'gold edition', 'platinum edition', ] for indicator in deluxe_indicators: if indicator in album_lower: logger.info(f"Detected deluxe edition: '{album_name}' contains '{indicator}'") return True return False def _normalize_base_album_name(base_album: str, artist_name: str) -> str: """ Normalize the base album name to handle case variations and known corrections. """ import re # Apply known album corrections for consistent naming normalized_lower = base_album.lower().strip() # Handle common album title variations known_corrections = { # Add specific album name corrections here as needed # Example: "good kid maad city": "good kid, m.A.A.d city" } # Check for exact matches in our corrections for variant, correction in known_corrections.items(): if normalized_lower == variant.lower(): logger.info(f"Album correction applied: '{base_album}' -> '{correction}'") return correction # Handle punctuation variations normalized = base_album # Normalize common punctuation patterns normalized = re.sub(r'\s*&\s*', ' & ', normalized) # Standardize & spacing normalized = re.sub(r'\s+', ' ', normalized) # Clean multiple spaces normalized = normalized.strip() logger.info(f"Album variant normalization: '{base_album}' -> '{normalized}'") return normalized def _clean_album_title_web(album_title: str, artist_name: str) -> str: """Clean up album title by removing common prefixes, suffixes, and artist redundancy""" import re # Start with the original title original = album_title.strip() cleaned = original logger.info(f"Album Title Cleaning: '{original}' (artist: '{artist_name}')") # Remove "Album - " prefix cleaned = re.sub(r'^Album\s*-\s*', '', cleaned, flags=re.IGNORECASE) # Remove artist name prefix if it appears at the beginning # This handles cases like "Kendrick Lamar - good kid, m.A.A.d city" artist_pattern = re.escape(artist_name) + r'\s*-\s*' cleaned = re.sub(f'^{artist_pattern}', '', cleaned, flags=re.IGNORECASE) # Remove common Soulseek suffixes in square brackets and parentheses # Examples: [Deluxe Edition] [2012] [320 Kbps] [Album+iTunes+Bonus Tracks] [F10] # (Deluxe Edition) (2012) (320 Kbps) etc. # Remove year patterns like [2012], (2020), etc. cleaned = re.sub(r'\s*[\[\(]\d{4}[\]\)]\s*', ' ', cleaned) # Remove quality/format indicators quality_patterns = [ r'\s*[\[\(].*?320.*?kbps.*?[\]\)]\s*', r'\s*[\[\(].*?256.*?kbps.*?[\]\)]\s*', r'\s*[\[\(].*?flac.*?[\]\)]\s*', r'\s*[\[\(].*?mp3.*?[\]\)]\s*', r'\s*[\[\(].*?itunes.*?[\]\)]\s*', r'\s*[\[\(].*?web.*?[\]\)]\s*', r'\s*[\[\(].*?cd.*?[\]\)]\s*' ] for pattern in quality_patterns: cleaned = re.sub(pattern, ' ', cleaned, flags=re.IGNORECASE) # Remove common edition indicators (but preserve them for deluxe detection above) # This happens AFTER deluxe detection to avoid interfering with that logic # Clean up spacing cleaned = re.sub(r'\s+', ' ', cleaned).strip() # Remove leading/trailing punctuation cleaned = re.sub(r'^[-\s]+|[-\s]+$', '', cleaned) logger.info(f"Album Title Result: '{original}' -> '{cleaned}'") return cleaned if cleaned else original def _search_track_in_album_context_web(context: dict, spotify_artist: dict) -> dict: """ Search for a track within its album context to avoid promotional single confusion. (Ported from GUI downloads.py) """ try: from core.matching_engine import MusicMatchingEngine matching_engine = MusicMatchingEngine() # Get album and track info from context original_search = context.get("original_search_result", {}) album_name = original_search.get("album") track_title = original_search.get("title") artist_name = spotify_artist["name"] if not album_name or not track_title: logger.error(f"Album-aware search failed: Missing album ({album_name}) or track ({track_title})") return None logger.info(f"Album-aware search: '{track_title}' in album '{album_name}' by '{artist_name}'") # Clean the album name for better search results clean_album = _clean_album_title_web(album_name, artist_name) clean_track = _clean_track_title_web(track_title, artist_name) # Search for the specific album first album_query = f"album:{clean_album} artist:{artist_name}" logger.info(f"Searching albums: {album_query}") albums = spotify_client.search_albums(album_query, limit=5) if not albums: logger.warning(f"No albums found for query: {album_query}") return None # Check each album to see if our track is in it for album in albums: logger.info(f"Checking album: '{album.name}' ({album.total_tracks} tracks)") # Get tracks from this album album_tracks_data = spotify_client.get_album_tracks(album.id) if not album_tracks_data or 'items' not in album_tracks_data: logger.error(f"Could not get tracks for album: {album.name}") continue # Check if our track is in this album for track_data in album_tracks_data['items']: track_name = track_data['name'] track_number = track_data['track_number'] # Calculate similarity between our track and this album track similarity = matching_engine.similarity_score( matching_engine.normalize_string(clean_track), matching_engine.normalize_string(track_name) ) # Use higher threshold for remix matching to ensure precision (GUI PARITY) is_remix = any(word in clean_track.lower() for word in ['remix', 'mix', 'edit', 'version']) threshold = 0.9 if is_remix else 0.65 # Lower threshold to favor album matches over singles if similarity > threshold: logger.info(f"FOUND: '{track_name}' (track #{track_number}) matches '{clean_track}' (similarity: {similarity:.2f})") # Classify as album vs single using the shared detect_album_info_web helper ctx_album_type = getattr(album, 'album_type', 'album') or 'album' ctx_total_tracks = getattr(album, 'total_tracks', 1) or 1 ctx_is_album = ( ctx_album_type == 'album' and ctx_total_tracks > 1 and matching_engine.normalize_string(album.name) != matching_engine.normalize_string(clean_track) and matching_engine.normalize_string(album.name) != matching_engine.normalize_string(artist_name) ) logger.info(f"Album context classification: is_album={ctx_is_album} (type={ctx_album_type}, tracks={ctx_total_tracks})") return { 'is_album': ctx_is_album, 'album_name': album.name, 'track_number': track_number, 'clean_track_name': clean_track, # Use the ORIGINAL download title, not the database match 'album_image_url': album.image_url, 'confidence': similarity, 'source': 'album_context_search' } logger.warning(f"Track '{clean_track}' not found in album '{album.name}'") logger.warning(f"Track '{clean_track}' not found in any matching albums") return None except Exception as e: logger.error(f"Error in album-aware search: {e}") return None def _clean_track_title_web(track_title: str, artist_name: str) -> str: """Clean up track title by removing artist prefix and common patterns""" import re # Start with the original title original = track_title.strip() cleaned = original logger.info(f"Track Title Cleaning: '{original}' (artist: '{artist_name}')") # Remove artist name prefix if it appears at the beginning # This handles cases like "Kendrick Lamar - HUMBLE." artist_pattern = re.escape(artist_name) + r'\s*-\s*' cleaned = re.sub(f'^{artist_pattern}', '', cleaned, flags=re.IGNORECASE) # Remove common prefixes cleaned = re.sub(r'^Track\s*\d*\s*-\s*', '', cleaned, flags=re.IGNORECASE) cleaned = re.sub(r'^\d+\.\s*', '', cleaned) # Remove track numbers like "01. " # Remove quality/format indicators quality_patterns = [ r'\s*[\[\(].*?320.*?kbps.*?[\]\)]\s*', r'\s*[\[\(].*?256.*?kbps.*?[\]\)]\s*', r'\s*[\[\(].*?flac.*?[\]\)]\s*', r'\s*[\[\(].*?mp3.*?[\]\)]\s*', r'\s*[\[\(].*?explicit.*?[\]\)]\s*' ] for pattern in quality_patterns: cleaned = re.sub(pattern, ' ', cleaned, flags=re.IGNORECASE) # Clean up spacing cleaned = re.sub(r'\s+', ' ', cleaned).strip() # Remove leading/trailing punctuation cleaned = re.sub(r'^[-\s]+|[-\s]+$', '', cleaned) logger.info(f"Track Title Result: '{original}' -> '{cleaned}'") return cleaned if cleaned else original # =================================================================== # YOUTUBE TRACK CLEANING FUNCTIONS (Ported from GUI sync.py) # =================================================================== def clean_youtube_track_title(title, artist_name=None): """ Aggressively clean YouTube track titles by removing video noise and extracting clean track names Examples: 'No Way Jose (Official Music Video)' → 'No Way Jose' 'bbno$ - mary poppins (official music video)' → 'mary poppins' 'Beyond (From "Moana 2") (Official Video) ft. Rachel House' → 'Beyond' 'Temporary (feat. Skylar Grey) [Official Music Video]' → 'Temporary' 'ALL MY LOVE (Directors\' Cut)' → 'ALL MY LOVE' 'Espresso Macchiato | Estonia 🇪🇪 | Official Music Video | #Eurovision2025' → 'Espresso Macchiato' """ import re if not title: return title original_title = title # FIRST: Try to extract track name from "Artist - Track" or "Track - Artist" format artist_removed = False if artist_name and '-' in title: # Check if artist is at the start: "Artist - Track" or "Artist & Others - Track" # Handle collaborations: "Artist1 & Artist2 - Track" or "Artist, Artist2 - Track" artist_pattern = r'^' + re.escape(artist_name.strip()) + r'(?:\s*[&,x]\s*[^-]+)?\s*[-–—]\s*' cleaned_title = re.sub(artist_pattern, '', title, flags=re.IGNORECASE).strip() if cleaned_title != title: logger.info(f"Removed artist from start: '{title}' -> '{cleaned_title}' (artist: '{artist_name}')") title = cleaned_title artist_removed = True else: # Artist not at start, check if format is "Track - Artist" by looking for artist at end # Only remove trailing artist if it comes after a dash artist_end_pattern = r'\s*[-–—]\s*' + re.escape(artist_name.strip()) + r'(?:\s*[&,x]\s*[^-]+)?\s*$' cleaned_title = re.sub(artist_end_pattern, '', title, flags=re.IGNORECASE).strip() if cleaned_title != title: logger.info(f"Removed artist from end: '{title}' -> '{cleaned_title}' (artist: '{artist_name}')") title = cleaned_title artist_removed = True # Remove content in brackets/braces BEFORE removing dashes title = re.sub(r'【[^】]*】', '', title) # Japanese brackets title = re.sub(r'\s*\([^)]*\)', '', title) # Parentheses - removes everything after first ( title = re.sub(r'\s*\(.*$', '', title) # Remove everything after lone ( (unmatched parentheses) title = re.sub(r'\[[^\]]*\]', '', title) # Square brackets title = re.sub(r'\{[^}]*\}', '', title) # Curly braces title = re.sub(r'<[^>]*>', '', title) # Angle brackets # ONLY remove trailing dashes with garbage if artist was already removed # This prevents "Artist1, Artist2 - Song" from becoming "Artist1, Artist2" if artist_removed: # Safe to remove any remaining trailing dash content (likely album/extra info) title = re.sub(r'\s*-\s*.*$', '', title) # Remove everything after pipes (|) - often used for additional context title = re.split(r'\s*\|\s*', title)[0].strip() # Remove common video/platform noise noise_patterns = [ r'\bapple\s+music\b', r'\bfull\s+video\b', r'\bmusic\s+video\b', r'\bofficial\s+video\b', r'\bofficial\s+music\s+video\b', r'\bofficial\b', r'\bcensored\s+version\b', r'\buncensored\s+version\b', r'\bexplicit\s+version\b', r'\blive\s+version\b', r'\bversion\b', r'\btopic\b', r'\baudio\b', r'\blyrics?\b', r'\blyric\s+video\b', r'\bwith\s+lyrics?\b', r'\bvisuali[sz]er\b', r'\bmv\b', r'\bdirectors?\s+cut\b', r'\bremaster(ed)?\b', r'\bremix\b' ] for pattern in noise_patterns: title = re.sub(pattern, '', title, flags=re.IGNORECASE) # Only remove artist name if it's standalone (not part of "Artist1 & Artist2") # Skip this if the title contains collaboration indicators near the artist name if artist_name: # Check if artist appears with collaboration indicators (& or ,) collab_pattern = rf'\b{re.escape(artist_name)}\s*[&,]\s*\w+|[\w\s]+[&,]\s*{re.escape(artist_name)}\b' has_collab = re.search(collab_pattern, title, flags=re.IGNORECASE) if not has_collab: # Safe to remove artist - it's standalone title = re.sub(rf'\b{re.escape(artist_name)}\b', '', title, flags=re.IGNORECASE) title = re.sub(rf'\b{re.escape(artist_name)}\s*[-–—:]\s*', '', title, flags=re.IGNORECASE) title = re.sub(rf'^{re.escape(artist_name)}\s*[-–—:]\s*', '', title, flags=re.IGNORECASE) else: logger.info(f"Skipping artist removal - collaboration detected: '{title}'") # Remove "prod. Producer" patterns title = re.sub(r'\s+prod\.?\s+\S+', '', title, flags=re.IGNORECASE) # Remove all quotes and other punctuation title = re.sub(r'["\'''""„‚‛‹›«»]', '', title) # Remove featured artist patterns (after removing parentheses) feat_patterns = [ r'\s+feat\.?\s+.+$', # " feat Artist" at end r'\s+ft\.?\s+.+$', # " ft Artist" at end r'\s+featuring\s+.+$', # " featuring Artist" at end r'\s+with\s+.+$', # " with Artist" at end ] for pattern in feat_patterns: title = re.sub(pattern, '', title, flags=re.IGNORECASE).strip() # Clean up whitespace and punctuation title = re.sub(r'\s+', ' ', title).strip() title = re.sub(r'^[-–—:,.\s]+|[-–—:,.\s]+$', '', title).strip() # If we cleaned too much, return original if not title.strip() or len(title.strip()) < 2: title = original_title if title != original_title: logger.info(f"YouTube title cleaned: '{original_title}' → '{title}'") return title def clean_youtube_artist(artist_string): """ Clean YouTube artist strings to get primary artist name Examples: 'Yung Gravy, bbno$ (BABY GRAVY)' → 'Yung Gravy' 'Y2K, bbno$' → 'Y2K' 'LITTLE BIG' → 'LITTLE BIG' 'Artist "Nickname" Name' → 'Artist Nickname Name' 'ArtistVEVO' → 'Artist' """ import re if not artist_string: return artist_string original_artist = artist_string # Remove all quotes - they're usually not part of artist names artist_string = artist_string.replace('"', '').replace("'", '').replace(''', '').replace(''', '').replace('"', '').replace('"', '') # Remove anything in parentheses (often group/label names) artist_string = re.sub(r'\s*\([^)]*\)', '', artist_string).strip() # Remove anything in brackets (often additional info) artist_string = re.sub(r'\s*\[[^\]]*\]', '', artist_string).strip() # Remove common YouTube channel suffixes channel_suffixes = [ r'\s*-\s*Topic\s*$', # YouTube auto-generated "Topic" channels (e.g. "Koven - Topic") r'\s*VEVO\s*$', r'\s*Music\s*$', r'\s*Official\s*$', r'\s*Records\s*$', r'\s*Entertainment\s*$', r'\s*TV\s*$', r'\s*Channel\s*$' ] for suffix in channel_suffixes: artist_string = re.sub(suffix, '', artist_string, flags=re.IGNORECASE).strip() # Split on common separators and take the first artist separators = [',', '&', ' and ', ' x ', ' X ', ' feat.', ' ft.', ' featuring', ' with', ' vs ', ' vs.'] for sep in separators: if sep in artist_string: parts = artist_string.split(sep) artist_string = parts[0].strip() break # Clean up extra whitespace and punctuation artist_string = re.sub(r'\s+', ' ', artist_string).strip() artist_string = re.sub(r'^\-\s*|\s*\-$', '', artist_string).strip() # Remove leading/trailing dashes artist_string = re.sub(r'^,\s*|\s*,$', '', artist_string).strip() # Remove leading/trailing commas # If we cleaned too much, return original if not artist_string.strip(): artist_string = original_artist if artist_string != original_artist: logger.info(f"YouTube artist cleaned: '{original_artist}' → '{artist_string}'") return artist_string def parse_youtube_playlist(url): """ Parse a YouTube Music playlist URL and extract track information using yt-dlp Uses flat playlist extraction to avoid rate limits and get all tracks Returns a list of track dictionaries compatible with our Track structure """ try: # Configure yt-dlp options for flat playlist extraction (avoids rate limits) ydl_opts = { 'quiet': True, 'no_warnings': True, 'extract_flat': 'in_playlist', # Only extract basic info, no individual video metadata 'skip_download': True, # Don't download, just extract IDs and basic info 'lazy_playlist': False, # Force full playlist resolution (prevents ~100 entry cap) } tracks = [] with yt_dlp.YoutubeDL(ydl_opts) as ydl: # Extract playlist info playlist_info = ydl.extract_info(url, download=False) if not playlist_info: logger.error("Could not extract playlist information") return None playlist_name = playlist_info.get('title', 'Unknown Playlist') playlist_id = playlist_info.get('id', 'unknown_id') entries = list(playlist_info.get('entries', []) or []) logger.info(f"Found YouTube playlist: '{playlist_name}' with {len(entries)} entries") for entry in entries: if not entry: continue # Extract basic information from flat extraction raw_title = entry.get('title', 'Unknown Track') raw_uploader = entry.get('uploader', 'Unknown Artist') duration = entry.get('duration', 0) video_id = entry.get('id', '') # Clean the track title and artist using our cleaning functions cleaned_artist = clean_youtube_artist(raw_uploader) cleaned_title = clean_youtube_track_title(raw_title, cleaned_artist) # Create track object matching GUI structure track_data = { 'id': video_id, 'name': cleaned_title, 'artists': [cleaned_artist], 'duration_ms': duration * 1000 if duration else 0, 'raw_title': raw_title, # Keep original for reference 'raw_artist': raw_uploader, # Keep original for reference 'url': f"https://www.youtube.com/watch?v={video_id}" } tracks.append(track_data) # Create playlist object matching GUI structure playlist_data = { 'id': playlist_id, 'name': playlist_name, 'tracks': tracks, 'track_count': len(tracks), 'url': url, 'source': 'youtube', 'image_url': playlist_info.get('thumbnail', '') or '', } logger.info(f"Successfully parsed YouTube playlist: {len(tracks)} tracks extracted") return playlist_data except Exception as e: logger.error(f"Error parsing YouTube playlist: {e}") return None # =================================================================== # FILE ORGANIZATION TEMPLATE ENGINE # =================================================================== def _compute_m3u_folder(transfer_dir, context_type, playlist_name, artist_name='', album_name='', year=''): """ Compute the target folder for an M3U file using the template system. For playlists: uses playlist_path template, extracts folder portion. For albums: uses album_path template, extracts folder portion. Returns: absolute folder path """ if context_type == 'album' and artist_name and album_name: template_context = { 'artist': artist_name, 'albumartist': artist_name, 'album': album_name, 'title': 'placeholder', 'track_number': 1, 'disc_number': 1, 'year': year, 'quality': '' } folder_path, _ = _get_file_path_from_template(template_context, 'album_path') if folder_path: return os.path.join(transfer_dir, folder_path) # Fallback artist_sanitized = _sanitize_filename(artist_name) album_sanitized = _sanitize_filename(album_name) return os.path.join(transfer_dir, artist_sanitized, f"{artist_sanitized} - {album_sanitized}") else: template_context = { 'artist': 'placeholder', 'albumartist': 'placeholder', 'album': 'placeholder', 'title': 'placeholder', 'playlist_name': playlist_name, 'track_number': 1, 'disc_number': 1, 'year': '', 'quality': '' } folder_path, _ = _get_file_path_from_template(template_context, 'playlist_path') if folder_path: return os.path.join(transfer_dir, folder_path) # Fallback playlist_sanitized = _sanitize_filename(playlist_name) return os.path.join(transfer_dir, playlist_sanitized) def _get_file_path_from_template_raw(template: str, context: dict) -> tuple: """ Build file path using a user-provided template string directly. Unlike _get_file_path_from_template, this bypasses config lookup and the file_organization.enabled check — used by the reorganize feature where the user supplies the template explicitly. Args: template: Template string like "$artist/$album/$track - $title" context: Dict with all track/album metadata Returns: (folder_path, filename_base) tuple — no file extension included """ import re full_path = _apply_path_template(template, context) quality_value = context.get('quality', '') disc_value = f"{context.get('disc_number', 1):02d}" disc_value_raw = str(context.get('disc_number', 1)) path_parts = full_path.split('/') if len(path_parts) > 1: folder_parts = path_parts[:-1] filename_base = path_parts[-1] # $discnum before $disc — longer match first cleaned_folders = [] for part in folder_parts: part = part.replace('$quality', '') part = part.replace('$discnum', '') part = part.replace('$disc', '') part = re.sub(r'\s*\[\s*\]', '', part) part = re.sub(r'\s*\(\s*\)', '', part) part = re.sub(r'\s*\{\s*\}', '', part) part = re.sub(r'\s*-\s*$', '', part) part = re.sub(r'^\s*-\s*', '', part) part = re.sub(r'\s+', ' ', part).strip() if part: cleaned_folders.append(part) filename_base = filename_base.replace('$quality', quality_value) filename_base = filename_base.replace('$discnum', disc_value_raw) filename_base = filename_base.replace('$disc', disc_value) filename_base = re.sub(r'\s*\[\s*\]', '', filename_base) filename_base = re.sub(r'\s*\(\s*\)', '', filename_base) filename_base = re.sub(r'\s*\{\s*\}', '', filename_base) filename_base = re.sub(r'\s*-\s*$', '', filename_base) filename_base = re.sub(r'\s+', ' ', filename_base).strip() sanitized_folders = [_sanitize_filename(part) for part in cleaned_folders] folder_path = os.path.join(*sanitized_folders) if sanitized_folders else '' return folder_path, _sanitize_filename(filename_base) else: full_path = full_path.replace('$quality', quality_value) full_path = full_path.replace('$discnum', disc_value_raw) full_path = full_path.replace('$disc', disc_value) full_path = re.sub(r'\s*\[\s*\]', '', full_path) full_path = re.sub(r'\s*\(\s*\)', '', full_path) full_path = re.sub(r'\s*\{\s*\}', '', full_path) full_path = re.sub(r'\s*-\s*$', '', full_path) full_path = re.sub(r'\s+', ' ', full_path).strip() return '', _sanitize_filename(full_path) def _get_audio_quality_string(file_path): """ Read audio file and return a quality descriptor string. Returns strings like 'FLAC 16bit', 'MP3-320', 'M4A-256', 'OGG-192'. Returns empty string on any error. """ try: ext = os.path.splitext(file_path)[1].lower() if ext == '.flac': audio = FLAC(file_path) bits = audio.info.bits_per_sample return f"FLAC {bits}bit" elif ext == '.mp3': from mutagen.mp3 import MP3, BitrateMode audio = MP3(file_path) bitrate_kbps = audio.info.bitrate // 1000 if audio.info.bitrate_mode == BitrateMode.VBR: return "MP3-VBR" return f"MP3-{bitrate_kbps}" elif ext in ('.m4a', '.aac', '.mp4'): audio = MP4(file_path) bitrate_kbps = audio.info.bitrate // 1000 return f"M4A-{bitrate_kbps}" elif ext == '.ogg': audio = OggVorbis(file_path) bitrate_kbps = audio.info.bitrate // 1000 return f"OGG-{bitrate_kbps}" elif ext == '.opus': from mutagen.oggopus import OggOpus audio = OggOpus(file_path) bitrate_kbps = audio.info.bitrate // 1000 return f"OPUS-{bitrate_kbps}" return '' except Exception as e: logger.debug(f"Could not determine audio quality for {file_path}: {e}") return '' def _get_album_type_display(raw_type, track_count) -> str: """ Return the display form of an album's type for the $albumtype template variable. Mirrors the inference used in the download pipeline so reorganize output matches initial placement. Values: 'Album', 'Single', 'EP', 'Compilation'. """ raw = (raw_type or '').strip().lower() try: tc = int(track_count or 0) except (TypeError, ValueError): tc = 0 # Deezer's raw API returns 'compile' (only mapped to 'compilation' in the # Album dataclass path); the Deezer enrichment worker writes the raw value, # so both need to match here. if raw in ('compilation', 'compile'): return 'Compilation' if raw == 'album': return 'Album' if raw in ('single', 'ep'): # Match download-pipeline logic: Spotify labels both singles and EPs # as 'single', so final classification is by track count. Applying the # same rule to explicit 'ep' keeps reorganize consistent with where # the files were first placed. if tc <= 3: return 'Single' if tc <= 6: return 'EP' return 'Album' # Unknown/missing — infer from track count if tc <= 0: return 'Album' if tc <= 3: return 'Single' if tc <= 6: return 'EP' return 'Album' def _apply_path_template(template: str, context: dict) -> str: """ Apply template to build file path. Args: template: Template string like "$artist/$album/$track - $title" context: Dict with values like {'artist': 'Drake', 'album': 'Scorpion', ...} Returns: Processed path string """ # Sanitize context values BEFORE template substitution # This prevents '/' in metadata from creating unintended path components clean_context = _sanitize_context_values(context) result = template # Replace variables in order from longest to shortest to avoid partial replacements # (e.g., $albumartist must be replaced before $album to prevent "Scorpionartist" from typo "$albumartis") # Longest variables first album_artist_value = clean_context.get('albumartist', clean_context.get('artist', 'Unknown Artist')) # Collaborative album artist handling: "first" uses only the primary artist for folder names collab_mode = config_manager.get('file_organization.collab_artist_mode', 'first') if collab_mode == 'first' and album_artist_value: # Use structured artists list to safely extract first artist # Only splits when we have multiple distinct artist objects (Spotify provides these) # Avoids string splitting which breaks names like "Tyler, the Creator" or "Simon & Garfunkel" artists_list = context.get('_artists_list') if artists_list and len(artists_list) > 1: # Multiple artist objects (Spotify) — use first first = artists_list[0] album_artist_value = first.get('name', first) if isinstance(first, dict) else str(first) elif artists_list and len(artists_list) == 1: # Single artist string — could be a combined name from iTunes # Resolve via artistId if available (safe: "Simon & Garfunkel" ID → "Simon & Garfunkel") itunes_artist_id = context.get('_itunes_artist_id') if itunes_artist_id and (',' in album_artist_value or ' & ' in album_artist_value): try: resolved = _get_itunes_client().resolve_primary_artist(itunes_artist_id) if resolved and resolved != album_artist_value: album_artist_value = resolved except Exception as e: logger.debug("itunes primary artist resolve failed: %s", e) # $cdnum — smart CD label for multi-disc filenames. Produces "CD01" / # "CD02" etc. when the album has 2+ discs, empty string otherwise. # Empty output collapses gracefully via the trailing double-dash cleanup # regex, so single-disc albums don't end up with "CD01" in every name. _total_discs = int(clean_context.get('total_discs', 1) or 1) _disc_number = int(clean_context.get('disc_number', 1) or 1) cdnum_value = f"CD{_disc_number:02d}" if _total_discs > 1 else '' # Support ${var} delimited syntax (e.g. ${albumtype}s → Albums) # Must run before $var replacements to prevent partial matching _bracket_map = { 'albumartist': album_artist_value, 'albumtype': clean_context.get('albumtype', 'Album'), 'playlist': clean_context.get('playlist_name', ''), 'artistletter': (clean_context.get('artist', 'U') or 'U')[0].upper(), 'artist': clean_context.get('artist', 'Unknown Artist'), 'album': clean_context.get('album', 'Unknown Album'), 'title': clean_context.get('title', 'Unknown Track'), 'track': f"{clean_context.get('track_number', 1):02d}", 'cdnum': cdnum_value, 'disc': str(clean_context.get('disc_number', 1)), 'discnum': str(clean_context.get('disc_number', 1)), 'year': str(clean_context.get('year', '')), 'quality': clean_context.get('quality', ''), } for var_name, val in _bracket_map.items(): result = result.replace('${' + var_name + '}', val) result = result.replace('$albumartist', album_artist_value) result = result.replace('$albumtype', clean_context.get('albumtype', 'Album')) result = result.replace('$playlist', clean_context.get('playlist_name', '')) # Medium length variables result = result.replace('$artistletter', (clean_context.get('artist', 'U') or 'U')[0].upper()) result = result.replace('$artist', clean_context.get('artist', 'Unknown Artist')) result = result.replace('$album', clean_context.get('album', 'Unknown Album')) result = result.replace('$title', clean_context.get('title', 'Unknown Track')) # $cdnum must replace before $track to avoid conflict with variables that # start with "$c" — no such variable exists today but this ordering # mirrors the "longest first" rule used throughout this function. result = result.replace('$cdnum', cdnum_value) result = result.replace('$track', f"{clean_context.get('track_number', 1):02d}") result = result.replace('$year', str(clean_context.get('year', ''))) # Empty string instead of 'Unknown' # Clean up extra spaces that might result from empty variables import re result = re.sub(r'\s+', ' ', result) # Multiple spaces to single space result = re.sub(r'\s*-\s*-\s*', ' - ', result) # Clean up double dashes result = result.strip() # Remove leading/trailing spaces return result def _get_file_path_from_template(context: dict, template_type: str = 'album_path') -> tuple: """ Build complete file path using configured templates. Args: context: Dict with all track/album metadata template_type: 'album_path', 'single_path', 'compilation_path', 'playlist_path' Returns: (folder_path, filename) tuple """ # Check if template system is enabled if not config_manager.get('file_organization.enabled', True): # Fallback to hardcoded structure return None, None # Get template from config templates = config_manager.get('file_organization.templates', {}) template = templates.get(template_type) if not template: # Fallback templates if config missing default_templates = { 'album_path': '$albumartist/$albumartist - $album/$track - $title', 'single_path': '$artist/$artist - $title/$title', 'compilation_path': 'Compilations/$album/$track - $artist - $title', 'playlist_path': '$playlist/$artist - $title' } template = default_templates.get(template_type, '$artist/$album/$track - $title') # Apply template full_path = _apply_path_template(template, context) # Split into folder and filename path_parts = full_path.split('/') # Handle $quality and $disc: only substituted in the filename (last component). # In folder components they become empty string to prevent album splits # when tracks arrive in mixed qualities or disc numbers in folder names. import re quality_value = context.get('quality', '') disc_value = f"{context.get('disc_number', 1):02d}" disc_value_raw = str(context.get('disc_number', 1)) if len(path_parts) > 1: folder_parts = path_parts[:-1] filename_base = path_parts[-1] # Strip $quality, $discnum, $disc from folder parts and clean up artifacts # $discnum before $disc — longer match first to prevent partial replacement cleaned_folders = [] for part in folder_parts: part = part.replace('$quality', '') part = part.replace('$discnum', '') part = part.replace('$disc', '') part = re.sub(r'\s*\[\s*\]', '', part) # empty [] part = re.sub(r'\s*\(\s*\)', '', part) # empty () part = re.sub(r'\s*\{\s*\}', '', part) # empty {} part = re.sub(r'\s*-\s*$', '', part) # trailing dash part = re.sub(r'^\s*-\s*', '', part) # leading dash part = re.sub(r'\s+', ' ', part).strip() if part: cleaned_folders.append(part) # Substitute $quality, $discnum, $disc in filename only # $discnum before $disc — longer match first filename_base = filename_base.replace('$quality', quality_value) filename_base = filename_base.replace('$discnum', disc_value_raw) filename_base = filename_base.replace('$disc', disc_value) # Clean up empty brackets/parens from any variable that resolved to empty filename_base = re.sub(r'\s*\[\s*\]', '', filename_base) filename_base = re.sub(r'\s*\(\s*\)', '', filename_base) filename_base = re.sub(r'\s*\{\s*\}', '', filename_base) filename_base = re.sub(r'\s*-\s*$', '', filename_base) # Leading dash cleanup — lets $cdnum (and other optional vars) sit at # the start of the filename without leaving a stray "- " when empty. filename_base = re.sub(r'^\s*-\s*', '', filename_base) filename_base = re.sub(r'\s+', ' ', filename_base).strip() # Sanitize each folder component sanitized_folders = [_sanitize_filename(part) for part in cleaned_folders] folder_path = os.path.join(*sanitized_folders) if sanitized_folders else '' # Sanitize filename filename = _sanitize_filename(filename_base) return folder_path, filename else: # Single component, treat as filename — substitute $quality, $discnum, $disc full_path = full_path.replace('$quality', quality_value) full_path = full_path.replace('$discnum', disc_value_raw) full_path = full_path.replace('$disc', disc_value) full_path = re.sub(r'\s*\[\s*\]', '', full_path) full_path = re.sub(r'\s*\(\s*\)', '', full_path) full_path = re.sub(r'\s*\{\s*\}', '', full_path) full_path = re.sub(r'\s*-\s*$', '', full_path) full_path = re.sub(r'^\s*-\s*', '', full_path) full_path = re.sub(r'\s+', ' ', full_path).strip() return '', _sanitize_filename(full_path) # METADATA & COVER ART HELPERS (Ported from downloads.py) # =================================================================== from mutagen import File as MutagenFile from mutagen.id3 import ID3, TIT2, TPE1, TALB, TDRC, TRCK, TCON, TPE2, TPOS, TXXX, APIC, UFID, TSRC, TBPM, TCOP, TPUB, TMED, TDOR from mutagen.apev2 import APEv2, APENoHeaderError import urllib.request def _wipe_source_tags(file_path: str) -> bool: return metadata_enrichment.wipe_source_tags(file_path) def _enhance_file_metadata(file_path: str, context: dict, artist: dict, album_info: dict, metadata_runtime=None) -> bool: return metadata_enrichment.enhance_file_metadata( file_path, context, artist, album_info, runtime=metadata_runtime or _build_metadata_enrichment_runtime( mb_worker=mb_worker, deezer_worker=deezer_worker, audiodb_worker=audiodb_worker, tidal_client=tidal_client, qobuz_enrichment_worker=qobuz_enrichment_worker, lastfm_worker=lastfm_worker, genius_worker=genius_worker, spotify_enrichment_worker=spotify_enrichment_worker, itunes_enrichment_worker=itunes_enrichment_worker, hifi_client=download_orchestrator.client("hifi") if download_orchestrator else None, ), ) def _download_cover_art(album_info: dict, target_dir: str, context: dict = None): return metadata_enrichment.download_cover_art( album_info, target_dir, context, ) def _get_spotify_album_tracks(spotify_album: dict) -> list: """Fetches all tracks for a given Spotify album ID.""" if not spotify_album or not spotify_album.get('id'): return [] try: tracks_data = spotify_client.get_album_tracks(spotify_album['id']) if tracks_data and 'items' in tracks_data: return [{ 'name': item.get('name'), 'track_number': item.get('track_number'), 'disc_number': item.get('disc_number', 1), 'id': item.get('id'), 'explicit': item.get('explicit', False) } for item in tracks_data['items']] return [] except Exception as e: logger.error(f"Error fetching Spotify album tracks: {e}") return [] def _match_track_to_spotify_title(slsk_track_meta: dict, spotify_tracks: list) -> dict: """ Intelligently matches a Soulseek track to a track from the official Spotify tracklist using track numbers and title similarity. Returns the matched Spotify track data. """ if not spotify_tracks: return slsk_track_meta # Return original if no list to match against # Priority 1: Match by track number if slsk_track_meta.get('track_number'): track_num = slsk_track_meta['track_number'] for sp_track in spotify_tracks: if sp_track.get('track_number') == track_num: logger.info(f"Matched track by number ({track_num}): '{slsk_track_meta['title']}' -> '{sp_track['name']}'") # Return a new dict with the corrected title and number return { 'title': sp_track['name'], 'artist': slsk_track_meta.get('artist'), 'album': slsk_track_meta.get('album'), 'track_number': sp_track['track_number'], 'disc_number': sp_track.get('disc_number', 1), 'explicit': sp_track.get('explicit', False) } # Priority 2: Match by title similarity (if track number fails) best_match = None best_score = 0.6 # Require a decent similarity for sp_track in spotify_tracks: score = matching_engine.similarity_score( matching_engine.normalize_string(slsk_track_meta.get('title', '')), matching_engine.normalize_string(sp_track.get('name', '')) ) if score > best_score: best_score = score best_match = sp_track if best_match: logger.info(f"Matched track by title similarity ({best_score:.2f}): '{slsk_track_meta['title']}' -> '{best_match['name']}'") return { 'title': best_match['name'], 'artist': slsk_track_meta.get('artist'), 'album': slsk_track_meta.get('album'), 'track_number': best_match['track_number'], 'disc_number': best_match.get('disc_number', 1), 'explicit': best_match.get('explicit', False) } logger.error(f"Could not confidently match track '{slsk_track_meta['title']}'. Using original metadata.") return slsk_track_meta # Fallback to original def _post_process_matched_download_with_verification(context_key, context, file_path, task_id, batch_id): """ NEW VERIFICATION WORKFLOW: Enhanced post-processing with file verification. Only sets task status to 'completed' after successful file verification and move operation. """ from core.imports.pipeline import post_process_matched_download_with_verification return post_process_matched_download_with_verification( context_key, context, file_path, task_id, batch_id, _build_import_pipeline_runtime(), _build_metadata_enrichment_runtime( mb_worker=mb_worker, deezer_worker=deezer_worker, audiodb_worker=audiodb_worker, tidal_client=tidal_client, qobuz_enrichment_worker=qobuz_enrichment_worker, lastfm_worker=lastfm_worker, genius_worker=genius_worker, spotify_enrichment_worker=spotify_enrichment_worker, itunes_enrichment_worker=itunes_enrichment_worker, hifi_client=download_orchestrator.client("hifi") if download_orchestrator else None, ), ) def _safe_move_file(src, dst): """ Safely move a file across different filesystems/volumes. Handles Docker volume mount issues where shutil.move() fails on metadata preservation. Args: src: Source file path (str or Path) dst: Destination file path (str or Path) """ import shutil from pathlib import Path src = Path(src) dst = Path(dst) # Ensure parent directory exists dst.parent.mkdir(parents=True, exist_ok=True) # If source doesn't exist, check if it was already moved to destination # This happens when a retry or parallel thread already transferred the file if not src.exists(): if dst.exists(): logger.info(f"Source gone but destination exists, file already transferred: {dst.name}") return else: raise FileNotFoundError(f"Source file not found and destination does not exist: {src}") # On Windows, shutil.move fails with FileExistsError if destination exists. # Remove it first, retrying briefly for Windows file locks (e.g. Plex scanning). if dst.exists(): for _attempt in range(3): try: dst.unlink() break except PermissionError: if _attempt < 2: time.sleep(1) else: logger.warning(f"Could not remove locked destination after 3 attempts: {dst.name}") except Exception: break try: # Try standard move first (works if same filesystem) shutil.move(str(src), str(dst)) return except FileNotFoundError: # Source vanished between our exists() check and the move - another thread got it first # If destination now exists, the other thread completed the transfer successfully if dst.exists(): logger.info(f"Source moved by another thread, destination exists: {dst.name}") return raise except (OSError, PermissionError) as e: error_msg = str(e).lower() # shutil.move may have already copied the file successfully but failed # to delete the source (e.g. permission denied on slskd-owned downloads). # If destination exists with content, treat as success. if dst.exists() and dst.stat().st_size > 0: logger.warning(f"Move raised {type(e).__name__} but destination exists, treating as success: {e}") # Try to clean up source, but don't fail if we can't try: src.unlink() except Exception: logger.info(f"Could not delete source file (may be owned by another process): {src}") return # Cross-device link error — do manual binary copy if "cross-device" in error_msg or "operation not permitted" in error_msg or "permission denied" in error_msg: logger.warning(f"Cross-device move detected, using fallback copy method: {e}") try: # Simple copy without metadata preservation (avoids permission errors) with open(src, 'rb') as f_src: with open(dst, 'wb') as f_dst: shutil.copyfileobj(f_src, f_dst) f_dst.flush() os.fsync(f_dst.fileno()) # Delete source after successful copy try: src.unlink() except PermissionError: logger.info(f"Could not delete source file (may be owned by another process): {src}") logger.info(f"Successfully moved file using fallback method: {src} -> {dst}") return except Exception as fallback_error: logger.error(f"Fallback copy also failed: {fallback_error}") raise else: # Re-raise if it's a different error raise def _post_process_matched_download(context_key, context, file_path): """ This is the final, corrected post-processing function. It now mirrors the GUI's logic by trusting the pre-matched context for album downloads, which solves the track numbering issue. Also handles simple downloads (from search page "Download" button) which just move files to /Transfer without metadata enhancement. """ from core.imports.pipeline import post_process_matched_download return post_process_matched_download( context_key, context, file_path, _build_import_pipeline_runtime(), metadata_runtime=_build_metadata_enrichment_runtime( mb_worker=mb_worker, deezer_worker=deezer_worker, audiodb_worker=audiodb_worker, tidal_client=tidal_client, qobuz_enrichment_worker=qobuz_enrichment_worker, lastfm_worker=lastfm_worker, genius_worker=genius_worker, spotify_enrichment_worker=spotify_enrichment_worker, itunes_enrichment_worker=itunes_enrichment_worker, hifi_client=download_orchestrator.client("hifi") if download_orchestrator else None, ), ) # Track stale transfer keys (completed in slskd but no context — e.g., from before app restart) # so we only log the warning once per key instead of spamming every poll cycle _stale_transfer_keys = set() # --- File Discovery Retry System --- # Prevents race condition where slskd reports completion before file is written to disk # Tracks retry attempts per download to give files time to finish writing _download_retry_attempts = {} # {context_key: {'count': N, 'first_attempt': timestamp}} _download_retry_max = 10 # Max retries before giving up (10 seconds with 1s poll interval) _download_retry_lock = threading.Lock() # Retag worker logic lives in core/library/retag.py. from core.library import retag as _library_retag def _build_retag_deps(): """Build the RetagDeps bundle from web_server.py globals on each call.""" from database.music_database import get_database as _get_db def _get_state(): return retag_state def _set_state(value): global retag_state retag_state = value from core.metadata.lyrics import generate_lrc_file as _generate_lrc_file return _library_retag.RetagDeps( config_manager=config_manager, retag_lock=retag_lock, spotify_client=spotify_client, get_audio_quality_string=_get_audio_quality_string, enhance_file_metadata=_enhance_file_metadata, build_final_path_for_track=_build_final_path_for_track, safe_move_file=_safe_move_file, cleanup_empty_directories=_cleanup_empty_directories, download_cover_art=_download_cover_art, docker_resolve_path=docker_resolve_path, _get_retag_state=_get_state, _set_retag_state=_set_state, get_database=_get_db, generate_lrc_file=_generate_lrc_file, ) def _execute_retag(group_id, album_id): return _library_retag.execute_retag(group_id, album_id, _build_retag_deps()) def _automatic_wishlist_cleanup_after_db_update(): """Automatic wishlist cleanup that runs after database updates.""" return _cleanup_wishlist_after_db_update(logger=logger) # ── Update detection ───────────────────────────────────────────── _GITHUB_REPO = "Nezreka/SoulSync" _update_cache = {'latest_sha': None, 'last_check': 0, 'error': None} _UPDATE_CHECK_INTERVAL = 3600 # 1 hour def _get_current_commit_sha(): """Get the commit SHA of the running instance (env var for Docker, git for local).""" # Docker: baked in at build time via COMMIT_SHA build arg sha = os.environ.get('SOULSYNC_COMMIT_SHA', '').strip() if sha: return sha # Local dev: read from git try: import subprocess result = subprocess.run(['git', 'rev-parse', 'HEAD'], capture_output=True, text=True, cwd=os.path.dirname(__file__) or '.') if result.returncode == 0: return result.stdout.strip() except Exception as e: logger.debug("git rev-parse failed: %s", e) return None _current_commit_sha = _get_current_commit_sha() def _check_for_updates(): """Check GitHub for the latest commit SHA on main branch.""" import time as _time now = _time.time() if now - _update_cache['last_check'] < _UPDATE_CHECK_INTERVAL: return # Still fresh _update_cache['last_check'] = now try: import urllib.request import json as _json req = urllib.request.Request( f"https://api.github.com/repos/{_GITHUB_REPO}/commits/main", headers={'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'SoulSync-UpdateCheck'} ) with urllib.request.urlopen(req, timeout=10) as resp: data = _json.loads(resp.read().decode()) _update_cache['latest_sha'] = data.get('sha') _update_cache['error'] = None except Exception as e: _update_cache['error'] = str(e) logger.debug(f"Update check failed: {e}") @app.route('/api/update-check', methods=['GET']) def check_for_update(): """Check if a newer version is available on GitHub.""" _check_for_updates() current = _current_commit_sha latest = _update_cache.get('latest_sha') update_available = bool(current and latest and current != latest) return jsonify({ 'update_available': update_available, 'current_sha': current[:8] if current else None, 'latest_sha': latest[:8] if latest else None, 'is_docker': os.path.exists('/.dockerenv'), }) def _simple_monitor_task(): """The actual monitoring task that runs in the background thread. Search cleanup and download cleanup are now handled by system automations.""" logger.info("Simple background monitor started") while not globals().get('IS_SHUTTING_DOWN', False): try: with matched_context_lock: pending_count = len(matched_downloads_context) if pending_count > 0: # Use app_context to safely call endpoint logic from a thread with app.app_context(): get_download_status() # Cleanup stale retry attempts (older than 60 seconds) # This prevents memory leaks from stuck/failed downloads with _download_retry_lock: current_time = time.time() stale_keys = [ key for key, data in _download_retry_attempts.items() if current_time - data['first_attempt'] > 60 ] for key in stale_keys: logger.warning(f"Cleaning up stale retry attempt: {key}") del _download_retry_attempts[key] time.sleep(1) except Exception as e: logger.error(f"Simple monitor error: {e}") time.sleep(10) logger.info("Simple background monitor stopped") def start_simple_background_monitor(): """Starts the simple background monitor thread.""" monitor_thread = threading.Thread(target=_simple_monitor_task) monitor_thread.daemon = True monitor_thread.start() def check_and_recover_stuck_flags(): """ Check if wishlist_auto_processing or watchlist_auto_scanning flags are stuck. If a flag has been True for more than 2 hours (7200 seconds), reset it. This prevents indefinite blocking when processes crash without cleanup. """ global wishlist_auto_processing, wishlist_auto_processing_timestamp global watchlist_auto_scanning, watchlist_auto_scanning_timestamp import time current_time = time.time() stuck_timeout = 900 # 15 minutes in seconds (reduced from 2 hours for faster recovery) def _reset_wishlist_processing_state(): global wishlist_auto_processing, wishlist_auto_processing_timestamp with wishlist_timer_lock: wishlist_auto_processing = False wishlist_auto_processing_timestamp = 0 # Check wishlist flag if _reset_wishlist_flag_if_stuck( wishlist_auto_processing, wishlist_auto_processing_timestamp, timeout_seconds=stuck_timeout, now=current_time, label="Wishlist auto-processing", reset_callback=_reset_wishlist_processing_state, ): return True # Check watchlist flag if watchlist_auto_scanning: time_stuck = current_time - watchlist_auto_scanning_timestamp if time_stuck > stuck_timeout: stuck_minutes = time_stuck / 60 logger.info(f"[Stuck Detection] Watchlist auto-scanning flag has been stuck for {stuck_minutes:.1f} minutes - RESETTING") with watchlist_timer_lock: watchlist_auto_scanning = False watchlist_auto_scanning_timestamp = 0 return True return False def is_wishlist_actually_processing(): """ Check if wishlist is truly processing (not just flag stuck). Returns True only if flag is set AND timestamp is recent (< 15 minutes). """ global wishlist_auto_processing, wishlist_auto_processing_timestamp import time current_time = time.time() return _is_wishlist_actually_processing( wishlist_auto_processing, wishlist_auto_processing_timestamp, timeout_seconds=900, now=current_time, on_stuck=check_and_recover_stuck_flags, ) def is_watchlist_actually_scanning(): """ Check if watchlist is truly scanning (not just flag stuck). Returns True only if flag is set AND timestamp is recent (< 15 minutes). """ global watchlist_auto_scanning, watchlist_auto_scanning_timestamp if not watchlist_auto_scanning: return False import time current_time = time.time() time_since_start = current_time - watchlist_auto_scanning_timestamp # If more than 15 minutes, flag is stuck - auto-recover and return False if time_since_start > 900: # 15 minutes stuck_minutes = time_since_start / 60 logger.warning(f"[Stuck Detection] Watchlist flag stuck for {stuck_minutes:.1f} minutes - auto-recovering") check_and_recover_stuck_flags() return False return True def _process_wishlist_automatically(automation_id=None): """Main automatic processing logic that runs in background thread.""" global wishlist_auto_processing, wishlist_auto_processing_timestamp from core.wishlist_service import get_wishlist_service @contextmanager def _processing_guard(): global wishlist_auto_processing, wishlist_auto_processing_timestamp with wishlist_timer_lock: if wishlist_auto_processing: yield False return wishlist_auto_processing = True wishlist_auto_processing_timestamp = time.time() logger.info(f"[Auto-Wishlist] Flag set at timestamp {wishlist_auto_processing_timestamp}") try: yield True finally: with wishlist_timer_lock: wishlist_auto_processing = False wishlist_auto_processing_timestamp = 0 runtime = _WishlistAutoProcessingRuntime( processing_guard=_processing_guard, is_actually_processing=is_wishlist_actually_processing, app_context_factory=lambda: app.app_context(), get_profiles_database=get_database, get_music_database=MusicDatabase, download_batches=download_batches, tasks_lock=tasks_lock, update_automation_progress=_update_automation_progress, automation_engine=automation_engine, missing_download_executor=missing_download_executor, run_full_missing_tracks_process=_run_full_missing_tracks_process, get_batch_max_concurrent=_get_batch_max_concurrent, get_active_server=config_manager.get_active_media_server, current_time_fn=time.time, profile_id=1, ) _process_wishlist_automatically_impl(runtime, automation_id=automation_id) # =============================== # == DATABASE UPDATER API == # =============================== def _db_update_progress_callback(current_item, processed, total, percentage): logger.info(f"[DB Progress] {current_item} - {processed}/{total} ({percentage:.1f}%)") with db_update_lock: db_update_state.update({ "current_item": current_item, "processed": processed, "total": total, "progress": percentage }) _update_automation_progress(_db_update_automation_id, progress=percentage, processed=processed, total=total, current_item=current_item) def _db_update_phase_callback(phase): logger.info(f"[DB Phase] {phase}") with db_update_lock: db_update_state["phase"] = phase _update_automation_progress(_db_update_automation_id, phase=phase) def _db_update_artist_callback(artist_name, success, details, album_count, track_count): if success: # Use the details string from the worker — it includes context like "0 new tracks (150 existing updated)" log_msg = f'{artist_name} — {details}' if details else f'{artist_name} — {album_count} albums, {track_count} tracks' _update_automation_progress(_db_update_automation_id, log_line=log_msg, log_type='success') else: _update_automation_progress(_db_update_automation_id, log_line=f'{artist_name} — {details}', log_type='error') def _db_update_finished_callback(total_artists, total_albums, total_tracks, successful, failed): global _db_update_automation_id # Check for removal results from the worker removed_artists = 0 removed_albums = 0 removed_tracks = 0 if db_update_worker: removed_artists = getattr(db_update_worker, 'removed_artists', 0) removed_albums = getattr(db_update_worker, 'removed_albums', 0) removed_tracks = getattr(db_update_worker, 'removed_tracks', 0) removal_msg = "" if removed_artists > 0 or removed_albums > 0: removal_msg = f" | Removed: {removed_artists} artists, {removed_albums} albums" if removed_tracks > 0: removal_msg += f", {removed_tracks} tracks" # Build a clear summary message # For deep scans: total_tracks = new tracks only, successful = artists processed # Include skipped/existing count when available for clarity skipped_tracks = 0 if db_update_worker: skipped_tracks = getattr(db_update_worker, '_total_skipped', 0) # Calculate from processed counts if not tracked directly if not skipped_tracks: total_processed = getattr(db_update_worker, 'processed_tracks', 0) if total_processed == 0 and total_tracks == 0 and successful > 0: # Deep scan with nothing new — show artists scanned skipped_tracks = getattr(db_update_worker, 'processed_albums', 0) if total_tracks > 0: phase_msg = f"Completed: {total_artists} artists, {total_albums} albums, {total_tracks} new tracks{removal_msg}." elif successful > 0: phase_msg = f"Completed: {successful} artists scanned, library up to date{removal_msg}." else: phase_msg = f"Completed: {successful} successful, {failed} failed{removal_msg}." with db_update_lock: db_update_state["status"] = "finished" db_update_state["phase"] = phase_msg db_update_state["total_albums"] = total_albums db_update_state["total_tracks"] = total_tracks db_update_state["removed_artists"] = removed_artists db_update_state["removed_albums"] = removed_albums db_update_state["removed_tracks"] = removed_tracks # Finalize automation progress auto_summary = f"{total_tracks} tracks, {total_albums} albums from {total_artists} artists" if removed_artists > 0 or removed_albums > 0: auto_summary += f" | Removed {removed_artists} artists, {removed_albums} albums" _update_automation_progress(_db_update_automation_id, status='finished', progress=100, phase='Complete', log_line=auto_summary, log_type='success') _db_update_automation_id = None # Resume enrichment workers now that scan is done _resume_workers_after_scan() # Add activity for database update completion summary = f"{total_tracks} tracks, {total_albums} albums, {total_artists} artists processed" if removed_artists > 0 or removed_albums > 0: summary += f" | {removed_artists} artists, {removed_albums} albums removed" add_activity_item("", "Database Update Complete", summary, "Now") try: if automation_engine: automation_engine.emit('database_update_completed', { 'total_artists': str(total_artists), 'total_albums': str(total_albums), 'total_tracks': str(total_tracks), }) except Exception as e: logger.debug("library_updated automation emit failed: %s", e) # Invalidate sync match cache (track IDs may have changed) try: inv_db = get_database() cleared = inv_db.invalidate_sync_match_cache() if cleared: logger.info(f"Cleared {cleared} sync match cache entries after database update") except Exception as e: logger.debug("sync match cache invalidation failed: %s", e) # WISHLIST CLEANUP: Automatically clean up wishlist after database update try: logger.info("[DB Update] Database update completed, starting automatic wishlist cleanup...") # Run cleanup in background to avoid blocking the UI missing_download_executor.submit(_automatic_wishlist_cleanup_after_db_update) except Exception as cleanup_error: logger.error(f"[DB Update] Error starting automatic wishlist cleanup: {cleanup_error}") def _db_update_error_callback(error_message): global _db_update_automation_id with db_update_lock: db_update_state["status"] = "error" db_update_state["error_message"] = error_message # Resume enrichment workers even on error _resume_workers_after_scan() _update_automation_progress(_db_update_automation_id, status='error', phase='Error', log_line=error_message, log_type='error') _db_update_automation_id = None # Add activity for database update error add_activity_item("", "Database Update Failed", error_message, "Now") _workers_paused_by_scan = set() # Track which workers WE paused (don't resume manually-paused ones) def _pause_workers_for_scan(): """Pause all enrichment and maintenance workers during database scans to reduce lock contention.""" global _workers_paused_by_scan _workers_paused_by_scan = set() workers = { 'mb': mb_worker, 'spotify': spotify_enrichment_worker, 'itunes': itunes_enrichment_worker, 'deezer': deezer_worker, 'audiodb': audiodb_worker, 'discogs': discogs_worker, 'lastfm': lastfm_worker, 'genius': genius_worker, 'tidal': tidal_enrichment_worker, 'qobuz': qobuz_enrichment_worker, 'repair': repair_worker, 'soulid': soulid_worker, } for name, w in workers.items(): if w and hasattr(w, 'pause') and not getattr(w, 'paused', True): w.pause() _workers_paused_by_scan.add(name) if _workers_paused_by_scan: logger.warning(f"Paused {len(_workers_paused_by_scan)} workers during database scan: {', '.join(_workers_paused_by_scan)}") def _resume_workers_after_scan(): """Resume only the workers that WE paused (don't resume manually-paused ones).""" global _workers_paused_by_scan workers = { 'mb': mb_worker, 'spotify': spotify_enrichment_worker, 'itunes': itunes_enrichment_worker, 'deezer': deezer_worker, 'audiodb': audiodb_worker, 'discogs': discogs_worker, 'lastfm': lastfm_worker, 'genius': genius_worker, 'tidal': tidal_enrichment_worker, 'qobuz': qobuz_enrichment_worker, 'repair': repair_worker, 'soulid': soulid_worker, } resumed = 0 for name, w in workers.items(): if name in _workers_paused_by_scan and w and hasattr(w, 'resume'): w.resume() resumed += 1 if resumed: logger.info(f"Resumed {resumed} workers after database scan") _workers_paused_by_scan = set() def _run_soulsync_full_refresh(): """Full refresh for SoulSync standalone — wipe all soulsync records, re-scan output folder, rebuild library from file tags.""" try: from core.soulsync_client import _read_tags, _stable_id transfer_path = docker_resolve_path(config_manager.get('soulseek.transfer_path', './Transfer')) if not os.path.isdir(transfer_path): _db_update_error_callback(f"Output folder not found: {transfer_path}") return logger.info(f"[SoulSync Full Refresh] Starting — clearing soulsync data, re-scanning: {transfer_path}") _db_update_phase_callback('Clearing library...') db = get_database() db.clear_server_data('soulsync') # Collect all audio files _db_update_phase_callback('Scanning output folder...') audio_exts = {'.mp3', '.flac', '.ogg', '.opus', '.m4a', '.aac', '.wav', '.wma', '.aiff', '.aif', '.ape'} audio_files = [] for root, _dirs, files in os.walk(transfer_path): for fname in files: if os.path.splitext(fname)[1].lower() in audio_exts: audio_files.append(os.path.join(root, fname)) total = len(audio_files) logger.info(f"[SoulSync Full Refresh] Found {total} audio files, rebuilding library...") if total == 0: _db_update_finished_callback(0, 0, 0, 0, 0) return # Group files by artist → album using tags _db_update_phase_callback(f'Reading tags from {total} files...') artists_map = {} # artist_name → { albums_map: { album_name → [tracks] } } processed = 0 for file_path in audio_files: tags = _read_tags(file_path) artist_name = tags.get('album_artist') or tags.get('artist') or 'Unknown Artist' album_name = tags.get('album') or 'Unknown Album' if artist_name not in artists_map: artists_map[artist_name] = {} if album_name not in artists_map[artist_name]: artists_map[artist_name][album_name] = [] artists_map[artist_name][album_name].append((file_path, tags)) processed += 1 if processed % 50 == 0: _db_update_phase_callback(f'Reading tags... {processed}/{total}') # Write to DB _db_update_phase_callback('Writing to database...') successful = 0 failed = 0 try: with db._get_connection() as conn: cursor = conn.cursor() for artist_name, albums in artists_map.items(): artist_id = _stable_id(artist_name.lower()) + '::soulsync' # Insert artist try: cursor.execute(""" INSERT OR IGNORE INTO artists (id, name, server_source, created_at, updated_at) VALUES (?, ?, 'soulsync', CURRENT_TIMESTAMP, CURRENT_TIMESTAMP) """, (artist_id, artist_name)) except Exception as e: logger.debug("soulsync artist insert failed: %s", e) for album_name, tracks in albums.items(): album_key = f"{artist_name.lower()}::{album_name.lower()}" album_id = _stable_id(album_key) + '::soulsync' # Get year from first track with a year year = '' for _, t in tracks: if t.get('year'): year = t['year'] break # Insert album try: cursor.execute(""" INSERT OR IGNORE INTO albums (id, artist_id, title, year, track_count, server_source, created_at, updated_at) VALUES (?, ?, ?, ?, ?, 'soulsync', CURRENT_TIMESTAMP, CURRENT_TIMESTAMP) """, (album_id, artist_id, album_name, year, len(tracks))) except Exception as e: logger.debug("soulsync album insert failed: %s", e) # Insert tracks for file_path, tags in tracks: track_id = _stable_id(file_path) + '::soulsync' try: cursor.execute(""" INSERT OR IGNORE INTO tracks (id, album_id, artist_id, title, track_number, disc_number, duration, file_path, bitrate, year, server_source, created_at, updated_at) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, 'soulsync', CURRENT_TIMESTAMP, CURRENT_TIMESTAMP) """, (track_id, album_id, artist_id, tags['title'], tags['track_number'], tags['disc_number'], tags['duration_ms'], file_path, tags['bitrate'], tags.get('year', ''))) successful += 1 except Exception as e: failed += 1 logger.error(f"[SoulSync Full Refresh] Track insert error: {e}") conn.commit() except Exception as e: logger.error(f"[SoulSync Full Refresh] DB error: {e}") _db_update_error_callback(f"Database error: {e}") return artist_count = len(artists_map) album_count = sum(len(albums) for albums in artists_map.values()) summary = f"Full refresh complete: {successful} tracks from {album_count} albums by {artist_count} artists" if failed > 0: summary += f" ({failed} failed)" logger.info(f"[SoulSync Full Refresh] {summary}") add_activity_item("", "SoulSync Full Refresh", summary, "Now") _db_update_finished_callback(artist_count, album_count, total, successful, failed) except Exception as e: logger.error(f"[SoulSync Full Refresh] {e}") import traceback traceback.print_exc() _db_update_error_callback(f"Full refresh failed: {e}") def _run_soulsync_deep_scan(): """Deep scan for SoulSync standalone mode. 1. Scans the output folder for all audio files 2. Compares against soulsync DB records (by file_path) 3. Untracked files → moved to import folder for auto-import processing 4. Stale DB records (file gone) → removed from DB """ try: import shutil transfer_path = docker_resolve_path(config_manager.get('soulseek.transfer_path', './Transfer')) staging_path = docker_resolve_path(config_manager.get('import.staging_path', './Staging')) if not os.path.isdir(transfer_path): _db_update_error_callback(f"Output folder not found: {transfer_path}") return logger.info(f"[SoulSync Deep Scan] Starting — Transfer: {transfer_path}") _db_update_phase_callback('scanning') # Phase 1: Collect all audio files in Transfer audio_extensions = {'.mp3', '.flac', '.ogg', '.opus', '.m4a', '.aac', '.wav', '.wma', '.aiff', '.aif', '.ape'} transfer_files = set() for root, _dirs, files in os.walk(transfer_path): for filename in files: if os.path.splitext(filename)[1].lower() in audio_extensions: transfer_files.add(os.path.join(root, filename)) logger.info(f"[SoulSync Deep Scan] Found {len(transfer_files)} audio files in Transfer") # Phase 2: Get all soulsync file paths from DB db = get_database() db_paths = set() try: with db._get_connection() as conn: cursor = conn.cursor() cursor.execute("SELECT file_path FROM tracks WHERE server_source = 'soulsync' AND file_path IS NOT NULL") for row in cursor.fetchall(): if row['file_path']: db_paths.add(row['file_path']) except Exception as e: logger.error(f"[SoulSync Deep Scan] Error reading DB paths: {e}") logger.info(f"[SoulSync Deep Scan] {len(db_paths)} tracks in soulsync DB") # Phase 3: Find untracked files (in Transfer but not in DB) untracked = transfer_files - db_paths # Also check with normalized paths (Windows vs Unix separators) if untracked: db_paths_normalized = {p.replace('\\', '/') for p in db_paths} untracked = {f for f in untracked if f.replace('\\', '/') not in db_paths_normalized} # Phase 4: Move untracked files to Staging for auto-import moved_count = 0 if untracked and os.path.isdir(staging_path): _db_update_phase_callback('moving_untracked') for file_path in untracked: try: # Preserve relative folder structure from Transfer rel_path = os.path.relpath(file_path, transfer_path) dest_path = os.path.join(staging_path, rel_path) os.makedirs(os.path.dirname(dest_path), exist_ok=True) shutil.move(file_path, dest_path) moved_count += 1 except Exception as e: logger.error(f"[SoulSync Deep Scan] Could not move {os.path.basename(file_path)}: {e}") # Clean up empty directories in Transfer after moving files for root, dirs, _files in os.walk(transfer_path, topdown=False): for d in dirs: dir_path = os.path.join(root, d) try: if not os.listdir(dir_path): os.rmdir(dir_path) except OSError: pass # Phase 5: Find stale DB records (in DB but file gone from disk) _db_update_phase_callback('cleanup') stale_count = 0 stale_track_ids = [] for db_path in db_paths: if not os.path.exists(db_path): stale_track_ids.append(db_path) stale_count += 1 # Remove stale records if stale_track_ids: try: with db._get_connection() as conn: cursor = conn.cursor() for fp in stale_track_ids: cursor.execute("DELETE FROM tracks WHERE file_path = ? AND server_source = 'soulsync'", (fp,)) conn.commit() # Clean up orphaned albums (no tracks left) cursor.execute(""" DELETE FROM albums WHERE server_source = 'soulsync' AND id NOT IN (SELECT DISTINCT album_id FROM tracks WHERE server_source = 'soulsync') """) orphan_albums = cursor.rowcount # Clean up orphaned artists (no albums left) cursor.execute(""" DELETE FROM artists WHERE server_source = 'soulsync' AND id NOT IN (SELECT DISTINCT artist_id FROM albums WHERE server_source = 'soulsync') """) orphan_artists = cursor.rowcount conn.commit() if orphan_albums > 0 or orphan_artists > 0: logger.warning(f"[SoulSync Deep Scan] Cleaned up {orphan_albums} orphaned albums, {orphan_artists} orphaned artists") except Exception as e: logger.error(f"[SoulSync Deep Scan] Error cleaning stale records: {e}") summary = f"Deep scan complete: {len(transfer_files)} files scanned" if moved_count > 0: summary += f", {moved_count} untracked files moved to Staging" if stale_count > 0: summary += f", {stale_count} stale records removed" if moved_count == 0 and stale_count == 0: summary += " — library is clean" logger.info(f"[SoulSync Deep Scan] {summary}") add_activity_item("", "SoulSync Deep Scan", summary, "Now") _db_update_finished_callback(0, 0, len(transfer_files), moved_count + stale_count, 0) except Exception as e: logger.error(f"[SoulSync Deep Scan] {e}") import traceback traceback.print_exc() _db_update_error_callback(f"Deep scan failed: {e}") def _run_db_update_task(full_refresh, server_type): """The actual function that runs in the background thread.""" global db_update_worker # SoulSync standalone if server_type == "soulsync": if full_refresh: _run_soulsync_full_refresh() else: # Incremental: library updates at download/import time, nothing to do logger.warning("[SoulSync Standalone] Incremental scan skipped — library updates at download time. Use Deep Scan or Full Refresh.") _db_update_finished_callback(0, 0, 0, 0, 0) return media_client = None if server_type == "plex": media_client = media_server_engine.client('plex') elif server_type == "jellyfin": media_client = media_server_engine.client('jellyfin') elif server_type == "navidrome": media_client = media_server_engine.client('navidrome') if not media_client: _db_update_error_callback(f"Media client for '{server_type}' not available.") return # Pause enrichment workers to reduce DB lock contention during scan _pause_workers_for_scan() with db_update_lock: db_update_worker = DatabaseUpdateWorker( media_client=media_client, full_refresh=full_refresh, server_type=server_type, force_sequential=True # Force sequential processing in web server mode ) # Connect signals to callbacks (handle both Qt and headless modes) try: # Try Qt signal connection first db_update_worker.progress_updated.connect(_db_update_progress_callback) db_update_worker.phase_changed.connect(_db_update_phase_callback) db_update_worker.artist_processed.connect(_db_update_artist_callback) db_update_worker.finished.connect(_db_update_finished_callback) db_update_worker.error.connect(_db_update_error_callback) except AttributeError: # Headless mode - use callback system db_update_worker.connect_callback('progress_updated', _db_update_progress_callback) db_update_worker.connect_callback('phase_changed', _db_update_phase_callback) db_update_worker.connect_callback('artist_processed', _db_update_artist_callback) db_update_worker.connect_callback('finished', _db_update_finished_callback) db_update_worker.connect_callback('error', _db_update_error_callback) # This is a blocking call that runs the worker logic db_update_worker.run() def _run_deep_scan_task(server_type): """Run a deep library scan in the background thread.""" global db_update_worker media_client = None if server_type == "plex": media_client = media_server_engine.client('plex') elif server_type == "jellyfin": media_client = media_server_engine.client('jellyfin') elif server_type == "navidrome": media_client = media_server_engine.client('navidrome') elif server_type == "soulsync": # SoulSync standalone deep scan: find untracked files → move to Staging, # remove stale DB records where files no longer exist on disk _run_soulsync_deep_scan() return if not media_client: _db_update_error_callback(f"Media client for '{server_type}' not available.") return # Pause enrichment workers to reduce DB lock contention during deep scan _pause_workers_for_scan() with db_update_lock: db_update_worker = DatabaseUpdateWorker( media_client=media_client, full_refresh=False, server_type=server_type, force_sequential=True ) try: db_update_worker.progress_updated.connect(_db_update_progress_callback) db_update_worker.phase_changed.connect(_db_update_phase_callback) db_update_worker.artist_processed.connect(_db_update_artist_callback) db_update_worker.finished.connect(_db_update_finished_callback) db_update_worker.error.connect(_db_update_error_callback) except AttributeError: db_update_worker.connect_callback('progress_updated', _db_update_progress_callback) db_update_worker.connect_callback('phase_changed', _db_update_phase_callback) db_update_worker.connect_callback('artist_processed', _db_update_artist_callback) db_update_worker.connect_callback('finished', _db_update_finished_callback) db_update_worker.connect_callback('error', _db_update_error_callback) # Run deep scan instead of normal run() db_update_worker.run_deep_scan() @app.route('/api/database/stats', methods=['GET']) def get_database_stats(): """Endpoint to get current database statistics.""" try: # This endpoint returns the same stats shape the UI expects. db = get_database() stats = db.get_database_info_for_server() return jsonify(stats) except Exception as e: logger.error(f"Error getting database stats: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/wishlist/process', methods=['POST']) def process_wishlist_api(): """Trigger wishlist processing via API. Processes pending wishlist tracks in the background.""" try: runtime = _build_wishlist_route_runtime( is_auto_processing_flag=lambda: wishlist_auto_processing, ) payload, status_code = _wishlist_process_api( runtime, start_processing=lambda: _process_wishlist_automatically(), ) return jsonify(payload), status_code except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/wishlist/count', methods=['GET']) def get_wishlist_count(): """Endpoint to get current wishlist count.""" try: runtime = _build_wishlist_route_runtime() payload, status_code = _wishlist_get_wishlist_count(runtime) return jsonify(payload), status_code except Exception as e: logger.error(f"Error getting wishlist count: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/wishlist/stats', methods=['GET']) def get_wishlist_stats(): """ Get wishlist statistics broken down by category. Returns: { "singles": int, # Count of singles + EPs "albums": int, # Count of album tracks "total": int # Total count } """ try: runtime = _build_wishlist_route_runtime( get_next_run_seconds=( automation_engine.get_system_automation_next_run_seconds if automation_engine else None ), ) payload, status_code = _wishlist_get_wishlist_stats(runtime) return jsonify(payload), status_code except Exception as e: logger.error(f"Error getting wishlist stats: {e}") import traceback traceback.print_exc() return jsonify({"error": str(e)}), 500 @app.route('/api/wishlist/cycle', methods=['GET']) def get_wishlist_cycle(): """ Get the current wishlist processing cycle. Returns: {"cycle": "albums" | "singles"} """ try: runtime = _build_wishlist_route_runtime() payload, status_code = _wishlist_get_wishlist_cycle(runtime) return jsonify(payload), status_code except Exception as e: logger.error(f"Error getting wishlist cycle: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/wishlist/cycle', methods=['POST']) def set_wishlist_cycle(): """ Set the current wishlist processing cycle. Body: {"cycle": "albums" | "singles"} """ try: data = request.get_json() cycle = data.get('cycle') runtime = _build_wishlist_route_runtime() payload, status_code = _wishlist_set_wishlist_cycle(runtime, cycle) return jsonify(payload), status_code except Exception as e: logger.error(f"Error setting wishlist cycle: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/discovery/lookback-period', methods=['GET']) def get_discovery_lookback_period(): """ Get the discovery pool lookback period setting. Returns: {"period": "7" | "30" | "90" | "180" | "all"} """ try: from database.music_database import MusicDatabase db = MusicDatabase() # Get lookback period from metadata table with db._get_connection() as conn: cursor = conn.cursor() cursor.execute("SELECT value FROM metadata WHERE key = 'discovery_lookback_period'") row = cursor.fetchone() if row: period = row['value'] else: # Default to 30 days on first access period = '30' cursor.execute(""" INSERT OR REPLACE INTO metadata (key, value, updated_at) VALUES ('discovery_lookback_period', '30', CURRENT_TIMESTAMP) """) conn.commit() return jsonify({"period": period}) except Exception as e: logger.error(f"Error getting discovery lookback period: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/discovery/lookback-period', methods=['POST']) def set_discovery_lookback_period(): """ Set the discovery pool lookback period setting. Body: {"period": "7" | "30" | "90" | "180" | "all"} """ try: data = request.get_json() period = data.get('period') valid_periods = ['7', '30', '90', '180', 'all'] if period not in valid_periods: return jsonify({"error": f"Invalid period. Must be one of: {', '.join(valid_periods)}"}), 400 from database.music_database import MusicDatabase db = MusicDatabase() # Store lookback period in metadata table with db._get_connection() as conn: cursor = conn.cursor() cursor.execute(""" INSERT OR REPLACE INTO metadata (key, value, updated_at) VALUES ('discovery_lookback_period', ?, CURRENT_TIMESTAMP) """, (period,)) # Set a one-time rescan cutoff so the next scan cycle uses the new # lookback window for artists that were already scanned under the old setting. # This avoids wiping last_scan_timestamp (which is needed for UI display). if period == 'all': # 'all' means no cutoff — store empty to signal "scan everything" rescan_value = '' else: from datetime import datetime, timedelta, timezone cutoff = datetime.now(timezone.utc) - timedelta(days=int(period)) rescan_value = cutoff.isoformat() cursor.execute(""" INSERT OR REPLACE INTO metadata (key, value, updated_at) VALUES ('watchlist_rescan_cutoff', ?, CURRENT_TIMESTAMP) """, (rescan_value,)) conn.commit() logger.info(f"Discovery lookback period set to: {period}") return jsonify({"success": True, "period": period}) except Exception as e: logger.error(f"Error setting discovery lookback period: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/discovery/hemisphere', methods=['GET']) def get_hemisphere(): """Get the hemisphere setting for seasonal content.""" try: db = get_database() with db._get_connection() as conn: cursor = conn.cursor() cursor.execute("SELECT value FROM metadata WHERE key = 'hemisphere'") row = cursor.fetchone() value = 'northern' if row: val = row[0] if isinstance(row, tuple) else row['value'] if val in ('northern', 'southern'): value = val return jsonify({"hemisphere": value}) except Exception as e: return jsonify({"error": str(e)}), 500 @app.route('/api/discovery/hemisphere', methods=['POST']) def set_hemisphere(): """Set the hemisphere for seasonal content (northern or southern).""" try: data = request.get_json() hemisphere = data.get('hemisphere', '').lower() if hemisphere not in ('northern', 'southern'): return jsonify({"error": "Must be 'northern' or 'southern'"}), 400 db = get_database() with db._get_connection() as conn: cursor = conn.cursor() cursor.execute(""" INSERT OR REPLACE INTO metadata (key, value, updated_at) VALUES ('hemisphere', ?, CURRENT_TIMESTAMP) """, (hemisphere,)) conn.commit() logger.info("Hemisphere set to: %s", hemisphere) return jsonify({"success": True, "hemisphere": hemisphere}) except Exception as e: return jsonify({"error": str(e)}), 500 @app.route('/api/wishlist/tracks', methods=['GET']) def get_wishlist_tracks(): """ Endpoint to get wishlist tracks for display in modal. Supports category filtering via query parameter. Query Parameters: category (optional): 'singles' or 'albums' - filters tracks by album type limit (optional): Maximum number of tracks to return (for performance) """ try: category = request.args.get('category', None) # None = all tracks limit = request.args.get('limit', type=int, default=None) # None = no limit runtime = _build_wishlist_route_runtime() payload, status_code = _wishlist_get_wishlist_tracks(runtime, category=category, limit=limit) return jsonify(payload), status_code except Exception as e: logger.error(f"Error getting wishlist tracks: {e}") return jsonify({"error": str(e)}), 500 def _build_wishlist_route_runtime( *, is_actually_processing_fn=None, reset_wishlist_processing_state=None, get_next_run_seconds=None, ): from database.music_database import MusicDatabase return _WishlistRouteRuntime( get_music_database=MusicDatabase, profile_id=get_current_profile_id(), download_batches=download_batches, download_tasks=download_tasks, tasks_lock=tasks_lock, is_wishlist_actually_processing=is_actually_processing_fn or is_wishlist_actually_processing, reset_wishlist_processing_state=reset_wishlist_processing_state or (lambda: None), add_activity_item=add_activity_item, active_server=config_manager.get_active_media_server(), get_next_run_seconds=get_next_run_seconds, ) @app.route('/api/wishlist/download_missing', methods=['POST']) def start_wishlist_missing_downloads(): """ This endpoint fetches wishlist tracks and manages them with batch processing identical to playlist processing, maintaining exactly 3 concurrent downloads. """ dl_err = check_download_permission() if dl_err: return dl_err try: # Check if auto-processing is currently running (prevent concurrent wishlist access) if is_wishlist_actually_processing(): return jsonify({ "error": "Wishlist auto-processing is currently running. Please wait for it to complete.", "retry_after": 30 }), 409 data = request.get_json() or {} from database.music_database import MusicDatabase db = MusicDatabase() manual_profile_id = get_current_profile_id() manual_runtime = _WishlistManualDownloadRuntime( get_music_database=lambda: db, download_batches=download_batches, tasks_lock=tasks_lock, missing_download_executor=missing_download_executor, run_full_missing_tracks_process=_run_full_missing_tracks_process, get_batch_max_concurrent=_get_batch_max_concurrent, add_activity_item=add_activity_item, active_server=config_manager.get_active_media_server(), profile_id=manual_profile_id, ) payload, status_code = _start_manual_wishlist_download_batch( manual_runtime, track_ids=data.get('track_ids'), category=data.get('category'), force_download_all=data.get('force_download_all', False), ) return jsonify(payload), status_code except Exception as e: logger.error(f"Error starting wishlist download process: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/wishlist/clear', methods=['POST']) def clear_wishlist(): """Endpoint to clear all tracks from the wishlist. Also cancels any active wishlist download batch so cleared tracks don't keep downloading.""" try: def _reset_wishlist_processing_state(): global wishlist_auto_processing, wishlist_auto_processing_timestamp with wishlist_timer_lock: wishlist_auto_processing = False wishlist_auto_processing_timestamp = 0 runtime = _build_wishlist_route_runtime( reset_wishlist_processing_state=_reset_wishlist_processing_state, ) payload, status_code = _wishlist_clear_wishlist(runtime) return jsonify(payload), status_code except Exception as e: logger.error(f"Error clearing wishlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/wishlist/cleanup', methods=['POST']) def cleanup_wishlist(): """Endpoint to remove tracks from wishlist that already exist in the database.""" try: from core.wishlist_service import get_wishlist_service from database.music_database import MusicDatabase wishlist_service = get_wishlist_service() db = MusicDatabase() active_server = config_manager.get_active_media_server() payload, status_code = _cleanup_wishlist_against_library( wishlist_service, db, get_current_profile_id(), active_server, ) return jsonify(payload), status_code except Exception as e: logger.error(f"Error in wishlist cleanup: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/wishlist/remove-track', methods=['POST']) def remove_track_from_wishlist(): """Endpoint to remove a single track from the wishlist.""" try: data = request.get_json() spotify_track_id = data.get('spotify_track_id') runtime = _build_wishlist_route_runtime() payload, status_code = _wishlist_remove_track_from_wishlist(runtime, spotify_track_id) return jsonify(payload), status_code except Exception as e: logger.error(f"Error removing track from wishlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/wishlist/remove-album', methods=['POST']) def remove_album_from_wishlist(): """Endpoint to remove all tracks from an album from the wishlist.""" try: data = request.get_json() album_id = data.get('album_id') album_name_filter = data.get('album_name') runtime = _build_wishlist_route_runtime() payload, status_code = _wishlist_remove_album_from_wishlist( runtime, album_id=album_id, album_name_filter=album_name_filter, ) return jsonify(payload), status_code except Exception as e: logger.error(f"Error removing album from wishlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/wishlist/remove-batch', methods=['POST']) def remove_batch_from_wishlist(): """Endpoint to remove multiple tracks from the wishlist.""" try: data = request.get_json() spotify_track_ids = data.get('spotify_track_ids', []) runtime = _build_wishlist_route_runtime() payload, status_code = _wishlist_remove_batch_from_wishlist(runtime, spotify_track_ids) return jsonify(payload), status_code except Exception as e: logger.error(f"Error batch removing from wishlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/add-album-to-wishlist', methods=['POST']) def add_album_track_to_wishlist(): """Endpoint to add a single track from an album to the wishlist.""" try: data = request.get_json() if not data: return jsonify({"success": False, "error": "No data provided"}), 400 track = data.get('track') artist = data.get('artist') album = data.get('album') source_type = data.get('source_type', 'album') source_context = data.get('source_context', {}) runtime = _build_wishlist_route_runtime() payload, status_code = _wishlist_add_album_track_to_wishlist( runtime, track=track, artist=artist, album=album, source_type=source_type, source_context=source_context, ) return jsonify(payload), status_code except Exception as e: logger.error(f"Error adding track to wishlist: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/database/update', methods=['POST']) def start_database_update(): """Endpoint to start the database update process.""" global db_update_worker with db_update_lock: if db_update_state["status"] == "running": return jsonify({"success": False, "error": "An update is already in progress."}), 409 data = request.get_json() full_refresh = data.get('full_refresh', False) deep_scan = data.get('deep_scan', False) active_server = config_manager.get_active_media_server() scan_type = "Deep scan" if deep_scan else ("Full" if full_refresh else "Incremental") db_update_state.update({ "status": "running", "phase": f"{scan_type}: Initializing...", "progress": 0, "current_item": "", "processed": 0, "total": 0, "error_message": "" }) # Add activity for database update start server_name = active_server.capitalize() add_activity_item("", "Database Update", f"Starting {scan_type.lower()} update from {server_name}...", "Now") # Submit the appropriate worker if deep_scan: db_update_executor.submit(_run_deep_scan_task, active_server) else: db_update_executor.submit(_run_db_update_task, full_refresh, active_server) return jsonify({"success": True, "message": "Database update started."}) @app.route('/api/database/update/status', methods=['GET']) def get_database_update_status(): """Endpoint to poll for the current update status.""" with db_update_lock: # Debug: Log current state occasionally if db_update_state["status"] == "running": logger.info(f"[Status Check] {db_update_state['processed']}/{db_update_state['total']} ({db_update_state['progress']:.1f}%) - {db_update_state['phase']}") return jsonify(db_update_state) @app.route('/api/database/update/stop', methods=['POST']) def stop_database_update(): """Endpoint to stop the current database update.""" global db_update_worker with db_update_lock: if db_update_worker and db_update_state["status"] == "running": db_update_worker.stop() db_update_state["status"] = "finished" db_update_state["phase"] = "Update stopped by user." return jsonify({"success": True, "message": "Stop request sent."}) else: return jsonify({"success": False, "error": "No update is currently running."}), 404 _BACKUP_FILENAME_RE = re.compile(r'^music_library\.db\.backup_\d{8}_\d{6}$') @app.route('/api/database/backup', methods=['POST']) def backup_database_endpoint(): """Create a rolling backup of the database (max 5).""" try: import sqlite3, glob as _glob db_path = os.environ.get('DATABASE_PATH', 'database/music_library.db') if not os.path.exists(db_path): return jsonify({"success": False, "error": "Database file not found"}), 404 max_backups = 5 timestamp = datetime.now().strftime('%Y%m%d_%H%M%S') backup_path = f"{db_path}.backup_{timestamp}" src = sqlite3.connect(db_path) dst = sqlite3.connect(backup_path) src.backup(dst) dst.close() src.close() size_mb = round(os.path.getsize(backup_path) / (1024 * 1024), 1) # Write version metadata sidecar meta_path = backup_path + '.meta.json' try: with open(meta_path, 'w') as mf: json.dump({"version": SOULSYNC_VERSION, "created": timestamp}, mf) except Exception as e: logger.debug("backup meta sidecar write: %s", e) # Rolling cleanup existing = sorted(_glob.glob(f"{db_path}.backup_*"), key=os.path.getmtime) # Filter out .meta.json files from the backup list existing = [f for f in existing if not f.endswith('.meta.json')] while len(existing) > max_backups: try: removed = existing.pop(0) os.remove(removed) # Also remove sidecar if present if os.path.exists(removed + '.meta.json'): os.remove(removed + '.meta.json') except Exception as e: logger.debug("rolling backup cleanup failed: %s", e) return jsonify({"success": True, "backup_path": backup_path, "size_mb": size_mb, "version": SOULSYNC_VERSION}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/database/backups', methods=['GET']) def list_backups_endpoint(): """List all database backups with metadata.""" try: import glob as _glob db_path = os.environ.get('DATABASE_PATH', 'database/music_library.db') backup_files = sorted( _glob.glob(f"{db_path}.backup_*"), key=os.path.getmtime, reverse=True ) backups = [] for fp in backup_files: fname = os.path.basename(fp) if not _BACKUP_FILENAME_RE.match(fname): continue stat = os.stat(fp) entry = { 'filename': fname, 'size_mb': round(stat.st_size / (1024 * 1024), 2), 'created': datetime.utcfromtimestamp(stat.st_mtime).isoformat() } # Read version from sidecar metadata if available meta_path = fp + '.meta.json' if os.path.exists(meta_path): try: with open(meta_path, 'r') as mf: meta = json.load(mf) entry['version'] = meta.get('version') except Exception as e: logger.debug("backup metadata read failed: %s", e) backups.append(entry) db_size_mb = round(os.path.getsize(db_path) / (1024 * 1024), 2) if os.path.exists(db_path) else 0 return jsonify({ 'success': True, 'backups': backups, 'count': len(backups), 'db_size_mb': db_size_mb }) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/database/backups/', methods=['DELETE']) def delete_backup_endpoint(filename): """Delete a specific database backup.""" try: if not _BACKUP_FILENAME_RE.match(filename) or '/' in filename or '\\' in filename or '..' in filename: return jsonify({"success": False, "error": "Invalid backup filename"}), 400 db_path = os.environ.get('DATABASE_PATH', 'database/music_library.db') backup_path = os.path.join(os.path.dirname(db_path), filename) if not os.path.exists(backup_path): return jsonify({"success": False, "error": "Backup not found"}), 404 os.remove(backup_path) # Also remove sidecar metadata if present meta_path = backup_path + '.meta.json' if os.path.exists(meta_path): try: os.remove(meta_path) except Exception as e: logger.debug("backup sidecar removal failed: %s", e) return jsonify({"success": True, "deleted": filename}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/database/backups//restore', methods=['POST']) def restore_backup_endpoint(filename): """Restore the database from a specific backup.""" try: import sqlite3 if not _BACKUP_FILENAME_RE.match(filename) or '/' in filename or '\\' in filename or '..' in filename: return jsonify({"success": False, "error": "Invalid backup filename"}), 400 db_path = os.environ.get('DATABASE_PATH', 'database/music_library.db') db_dir = os.path.dirname(db_path) backup_path = os.path.join(db_dir, filename) if not os.path.exists(backup_path): return jsonify({"success": False, "error": "Backup not found"}), 404 # Check version compatibility backup_version = None meta_path = backup_path + '.meta.json' if os.path.exists(meta_path): try: with open(meta_path, 'r') as mf: meta = json.load(mf) backup_version = meta.get('version') except Exception as e: logger.debug("backup version metadata read failed: %s", e) version_warning = None # Compare base versions only (strip +commit suffix) to avoid false mismatches _backup_base = backup_version.split('+')[0] if backup_version else None _current_base = SOULSYNC_VERSION.split('+')[0] if _backup_base and _backup_base != _current_base: # Allow restore but warn — the caller must pass force=true to confirm force = request.json.get('force', False) if request.is_json else False if not force: return jsonify({ "success": False, "version_mismatch": True, "backup_version": backup_version, "current_version": SOULSYNC_VERSION, "error": f"This backup was created on SoulSync v{backup_version}, but you're running v{SOULSYNC_VERSION}. Restoring may cause issues. Send force=true to proceed." }), 409 version_warning = f"Restored from v{backup_version} backup (current: v{SOULSYNC_VERSION})" # Create safety backup of current DB before restoring safety_ts = datetime.now().strftime('%Y%m%d_%H%M%S') safety_filename = f"music_library.db.backup_{safety_ts}" safety_path = os.path.join(db_dir, safety_filename) src_conn = sqlite3.connect(db_path) dst_conn = sqlite3.connect(safety_path) src_conn.backup(dst_conn) dst_conn.close() src_conn.close() # Write version metadata for the safety backup too try: with open(safety_path + '.meta.json', 'w') as mf: json.dump({"version": SOULSYNC_VERSION, "created": safety_ts}, mf) except Exception as e: logger.debug("safety backup metadata write failed: %s", e) # Restore using SQLite backup API (handles concurrent access safely) from database.music_database import close_database, get_database close_database() src_restore = sqlite3.connect(backup_path) dst_restore = sqlite3.connect(db_path) src_restore.backup(dst_restore) dst_restore.close() src_restore.close() # Reinitialize database and verify db = get_database() with db._get_connection() as conn: cursor = conn.cursor() cursor.execute("SELECT COUNT(*) FROM artists") artist_count = cursor.fetchone()[0] result = { "success": True, "restored_from": filename, "safety_backup": safety_filename, "artist_count": artist_count } if backup_version: result["backup_version"] = backup_version if version_warning: result["version_warning"] = version_warning return jsonify(result) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/database/backups//download', methods=['GET']) def download_backup_endpoint(filename): """Download a specific database backup file.""" try: if not _BACKUP_FILENAME_RE.match(filename) or '/' in filename or '\\' in filename or '..' in filename: return jsonify({"success": False, "error": "Invalid backup filename"}), 400 db_path = os.environ.get('DATABASE_PATH', 'database/music_library.db') backup_path = os.path.join(os.path.dirname(db_path), filename) if not os.path.exists(backup_path): return jsonify({"success": False, "error": "Backup not found"}), 404 # Override the default static-cache max-age — this is a sensitive # DB backup, browsers should never cache it. response = send_file(backup_path, as_attachment=True, download_name=filename) response.headers['Cache-Control'] = 'no-store' return response except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 # =============================== # == DATABASE MAINTENANCE == # =============================== @app.route('/api/database/maintenance/info', methods=['GET']) def database_maintenance_info(): """Get database size, free pages, and auto_vacuum mode.""" try: import sqlite3 db_path = os.environ.get('DATABASE_PATH', 'database/music_library.db') conn = sqlite3.connect(db_path) c = conn.cursor() c.execute('PRAGMA page_count'); total_pages = c.fetchone()[0] c.execute('PRAGMA freelist_count'); free_pages = c.fetchone()[0] c.execute('PRAGMA page_size'); page_size = c.fetchone()[0] c.execute('PRAGMA auto_vacuum'); auto_vacuum = c.fetchone()[0] conn.close() total_bytes = total_pages * page_size free_bytes = free_pages * page_size auto_vacuum_labels = {0: 'None', 1: 'Full', 2: 'Incremental'} return jsonify({ 'success': True, 'total_size': total_bytes, 'total_size_display': f'{total_bytes / 1024 / 1024:.1f} MB', 'free_pages': free_pages, 'free_size': free_bytes, 'free_size_display': f'{free_bytes / 1024 / 1024:.1f} MB', 'bloat_percent': round(free_pages / total_pages * 100, 1) if total_pages > 0 else 0, 'auto_vacuum': auto_vacuum, 'auto_vacuum_label': auto_vacuum_labels.get(auto_vacuum, 'Unknown'), }) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/database/maintenance/vacuum', methods=['POST']) def database_vacuum(): """Run VACUUM to compact the database. Locks DB during operation.""" try: import sqlite3, time db_path = os.environ.get('DATABASE_PATH', 'database/music_library.db') # Get size before size_before = os.path.getsize(db_path) conn = sqlite3.connect(db_path) start = time.time() conn.execute('VACUUM') elapsed = time.time() - start conn.close() size_after = os.path.getsize(db_path) saved = size_before - size_after logger.info(f"Database VACUUM completed in {elapsed:.1f}s — saved {saved / 1024 / 1024:.1f} MB") return jsonify({ 'success': True, 'elapsed_seconds': round(elapsed, 1), 'size_before': size_before, 'size_after': size_after, 'saved_bytes': saved, 'saved_display': f'{saved / 1024 / 1024:.1f} MB', }) except Exception as e: logger.error(f"Database VACUUM failed: {e}") return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/database/maintenance/enable-incremental-vacuum', methods=['POST']) def enable_incremental_vacuum(): """Enable incremental auto_vacuum. Requires a full VACUUM to activate.""" try: import sqlite3, time db_path = os.environ.get('DATABASE_PATH', 'database/music_library.db') conn = sqlite3.connect(db_path) c = conn.cursor() c.execute('PRAGMA auto_vacuum') current = c.fetchone()[0] if current == 2: conn.close() return jsonify({'success': True, 'message': 'Incremental vacuum is already enabled', 'already_enabled': True}) size_before = os.path.getsize(db_path) # Set incremental mode and VACUUM to activate it c.execute('PRAGMA auto_vacuum = INCREMENTAL') start = time.time() conn.execute('VACUUM') elapsed = time.time() - start conn.close() size_after = os.path.getsize(db_path) saved = size_before - size_after logger.info(f"Incremental auto_vacuum enabled in {elapsed:.1f}s — saved {saved / 1024 / 1024:.1f} MB") return jsonify({ 'success': True, 'message': 'Incremental vacuum enabled', 'elapsed_seconds': round(elapsed, 1), 'saved_display': f'{saved / 1024 / 1024:.1f} MB', }) except Exception as e: logger.error(f"Failed to enable incremental vacuum: {e}") return jsonify({'success': False, 'error': str(e)}), 500 # =============================== # == METADATA CACHE API == # =============================== @app.route('/api/metadata-cache/stats', methods=['GET']) def metadata_cache_stats(): """Get metadata cache statistics.""" try: cache = get_metadata_cache() stats = cache.get_stats() return jsonify(stats) except Exception as e: logger.error(f"Error getting metadata cache stats: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/metadata-cache/browse', methods=['GET']) def metadata_cache_browse(): """Browse cached metadata entities with filtering, search, sorting, and pagination.""" try: cache = get_metadata_cache() entity_type = request.args.get('type', 'artist') source = request.args.get('source') search = request.args.get('search') sort = request.args.get('sort', 'last_accessed_at') sort_dir = request.args.get('sort_dir', 'desc') offset = int(request.args.get('offset', 0)) limit = int(request.args.get('limit', 48)) result = cache.browse( entity_type=entity_type, source=source if source else None, search=search if search else None, sort=sort, sort_dir=sort_dir, offset=offset, limit=limit ) return jsonify(result) except Exception as e: logger.error(f"Error browsing metadata cache: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/metadata-cache/entity///', methods=['GET']) def metadata_cache_entity_detail(source, entity_type, entity_id): """Get detailed view of a single cached entity.""" try: cache = get_metadata_cache() detail = cache.get_entity_detail(source, entity_type, entity_id) if detail is None: return jsonify({"error": "Entity not found"}), 404 return jsonify(detail) except Exception as e: logger.error(f"Error getting metadata cache entity: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/metadata-cache/browse-musicbrainz', methods=['GET']) def metadata_cache_browse_musicbrainz(): """Browse MusicBrainz cache entries in the same format as metadata cache browse.""" try: entity_type = request.args.get('entity_type', 'artist') search = request.args.get('search', '').strip() page = int(request.args.get('page', 1)) limit = int(request.args.get('limit', 48)) offset = (page - 1) * limit database = get_database() conn = database._get_connection() try: cursor = conn.cursor() where_parts = [] params = [] if entity_type: where_parts.append("entity_type = ?") params.append(entity_type) if search: where_parts.append("LOWER(entity_name) LIKE LOWER(?)") params.append(f"%{search}%") where_clause = f"WHERE {' AND '.join(where_parts)}" if where_parts else "" cursor.execute(f"SELECT COUNT(*) FROM musicbrainz_cache {where_clause}", params) total = cursor.fetchone()[0] cursor.execute(f""" SELECT * FROM musicbrainz_cache {where_clause} ORDER BY last_updated DESC LIMIT ? OFFSET ? """, params + [limit, offset]) items = [] for row in cursor.fetchall(): r = dict(row) matched = r.get('musicbrainz_id') is not None items.append({ 'entity_id': r.get('musicbrainz_id') or f"mb-{r.get('entity_type','')}-{r.get('entity_name','')}", 'source': 'musicbrainz', 'name': r.get('entity_name', ''), 'artist_name': r.get('artist_name', ''), 'image_url': None, 'popularity': int((r.get('match_confidence') or 0) * 100), 'access_count': 1, 'last_accessed_at': r.get('last_updated', ''), 'created_at': r.get('last_updated', ''), '_mb_matched': matched, '_mb_id': r.get('musicbrainz_id', ''), }) return jsonify({'items': items, 'total': total, 'offset': offset}) finally: conn.close() except Exception as e: logger.error(f"Error browsing MusicBrainz cache: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/metadata-cache/clear', methods=['DELETE']) def metadata_cache_clear(): """Clear cached metadata. Optional query params: source, type.""" try: cache = get_metadata_cache() source = request.args.get('source') entity_type = request.args.get('type') cleared = cache.clear( source=source if source else None, entity_type=entity_type if entity_type else None ) return jsonify({"success": True, "cleared": cleared}) except Exception as e: logger.error(f"Error clearing metadata cache: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/metadata-cache/evict', methods=['POST']) def metadata_cache_evict(): """Evict expired entries from the metadata cache.""" try: cache = get_metadata_cache() evicted = cache.evict_expired() return jsonify({"success": True, "evicted": evicted}) except Exception as e: logger.error(f"Error evicting metadata cache: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/metadata-cache/clear-musicbrainz', methods=['DELETE']) def metadata_cache_clear_musicbrainz(): """Clear MusicBrainz cache entries. Optional query param: failed_only=true.""" try: cache = get_metadata_cache() failed_only = request.args.get('failed_only', '').lower() == 'true' cleared = cache.clear_musicbrainz(failed_only=failed_only) return jsonify({"success": True, "cleared": cleared}) except Exception as e: logger.error(f"Error clearing MusicBrainz cache: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/metadata-cache/failed-mb-lookups', methods=['GET']) def metadata_cache_failed_mb_lookups(): """Get all failed MusicBrainz lookups with pagination and filtering.""" try: entity_type = request.args.get('entity_type', '') search = request.args.get('search', '').strip() page = int(request.args.get('page', 1)) limit = int(request.args.get('limit', 50)) offset = (page - 1) * limit # Only fetch type_counts on first load (page 1, no filters) — frontend caches them include_counts = request.args.get('counts', '').lower() == 'true' database = get_database() conn = database._get_connection() try: cursor = conn.cursor() where_parts = ["musicbrainz_id IS NULL"] params = [] if entity_type: where_parts.append("entity_type = ?") params.append(entity_type) if search: where_parts.append("(entity_name LIKE ? COLLATE NOCASE OR artist_name LIKE ? COLLATE NOCASE)") params.extend([f"%{search}%", f"%{search}%"]) where_clause = f"WHERE {' AND '.join(where_parts)}" # Single query: fetch items + use SQL window for total count cursor.execute(f""" SELECT id, entity_type, entity_name, artist_name, match_confidence, last_updated, COUNT(*) OVER() as _total FROM musicbrainz_cache {where_clause} ORDER BY last_updated DESC LIMIT ? OFFSET ? """, params + [limit, offset]) rows = cursor.fetchall() total = rows[0]['_total'] if rows else 0 items = [{ 'id': r['id'], 'entity_type': r['entity_type'], 'entity_name': r['entity_name'], 'artist_name': r['artist_name'] or '', 'confidence': r['match_confidence'] or 0, 'last_updated': r['last_updated'] or '', } for r in rows] result = {'items': items, 'total': total, 'page': page} # Type counts only when requested (avoids full table scan on every tab switch) if include_counts: cursor.execute(""" SELECT entity_type, COUNT(*) as cnt FROM musicbrainz_cache WHERE musicbrainz_id IS NULL GROUP BY entity_type """) result['type_counts'] = {row['entity_type']: row['cnt'] for row in cursor.fetchall()} return jsonify(result) finally: conn.close() except Exception as e: logger.error(f"Error getting failed MB lookups: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/metadata-cache/mb-entry/', methods=['DELETE']) def metadata_cache_delete_mb_entry(entry_id): """Delete a single MusicBrainz cache entry by ID.""" try: database = get_database() conn = database._get_connection() try: cursor = conn.cursor() cursor.execute("DELETE FROM musicbrainz_cache WHERE id = ?", (entry_id,)) conn.commit() return jsonify({"success": True, "deleted": cursor.rowcount}) finally: conn.close() except Exception as e: logger.error(f"Error deleting MB cache entry: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/musicbrainz/search', methods=['GET']) def musicbrainz_search_api(): """Search MusicBrainz for manual matching. Returns raw results.""" try: entity_type = request.args.get('type', 'artist') # artist, release, recording query = request.args.get('q', '').strip() artist = request.args.get('artist', '').strip() limit = min(int(request.args.get('limit', 10)), 20) if not query: return jsonify({"error": "Missing query parameter 'q'"}), 400 mb_svc = mb_worker.mb_service if mb_worker else None if not mb_svc: return jsonify({"error": "MusicBrainz service not available"}), 503 mb_client = mb_svc.mb_client results = [] if entity_type == 'artist': raw = mb_client.search_artist(query, limit=limit) for r in raw: results.append({ 'mbid': r.get('id', ''), 'name': r.get('name', ''), 'disambiguation': r.get('disambiguation', ''), 'score': r.get('score', 0), 'type': r.get('type', ''), 'country': r.get('country', ''), }) elif entity_type == 'release': raw = mb_client.search_release(query, artist_name=artist or None, limit=limit) for r in raw: artist_credit = ', '.join(a.get('name', '') for a in r.get('artist-credit', []) if isinstance(a, dict)) results.append({ 'mbid': r.get('id', ''), 'name': r.get('title', ''), 'artist': artist_credit, 'disambiguation': r.get('disambiguation', ''), 'score': r.get('score', 0), 'date': r.get('date', ''), 'country': r.get('country', ''), 'track_count': r.get('track-count', 0), }) elif entity_type == 'recording': raw = mb_client.search_recording(query, artist_name=artist or None, limit=limit) for r in raw: artist_credit = ', '.join(a.get('name', '') for a in r.get('artist-credit', []) if isinstance(a, dict)) releases = r.get('releases', []) first_release = releases[0].get('title', '') if releases else '' results.append({ 'mbid': r.get('id', ''), 'name': r.get('title', ''), 'artist': artist_credit, 'disambiguation': r.get('disambiguation', ''), 'score': r.get('score', 0), 'album': first_release, 'length': r.get('length', 0), }) else: return jsonify({"error": f"Unknown entity type: {entity_type}"}), 400 return jsonify({"results": results, "total": len(results)}) except Exception as e: logger.error(f"Error searching MusicBrainz: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/metadata-cache/mb-match', methods=['POST']) def metadata_cache_save_mb_match(): """Save a manual MusicBrainz match for a failed lookup.""" try: data = request.get_json() entry_id = data.get('entry_id') mbid = data.get('mbid', '').strip() mb_name = data.get('mb_name', '').strip() if not entry_id or not mbid: return jsonify({"success": False, "error": "Missing entry_id or mbid"}), 400 database = get_database() conn = database._get_connection() try: cursor = conn.cursor() # Update the failed entry with the user-selected MBID cursor.execute(""" UPDATE musicbrainz_cache SET musicbrainz_id = ?, match_confidence = 100, metadata_json = ?, last_updated = CURRENT_TIMESTAMP WHERE id = ? """, (mbid, json.dumps({'name': mb_name, 'manual_match': True}), entry_id)) conn.commit() if cursor.rowcount == 0: return jsonify({"success": False, "error": "Entry not found"}), 404 logger.info(f"Manual MB match: entry {entry_id} → {mbid} ({mb_name})") return jsonify({"success": True}) finally: conn.close() except Exception as e: logger.error(f"Error saving MB match: {e}") return jsonify({"success": False, "error": str(e)}), 500 # =============================== # == QUALITY SCANNER == # =============================== # Quality tier mappings QUALITY_TIERS = { 'lossless': { 'extensions': ['.flac', '.ape', '.wav', '.alac', '.dsf', '.dff', '.aiff', '.aif'], 'tier': 1 }, 'high_lossy': { 'extensions': ['.opus', '.ogg'], 'tier': 2 }, 'standard_lossy': { 'extensions': ['.m4a', '.aac'], 'tier': 3 }, 'low_lossy': { 'extensions': ['.mp3', '.wma'], 'tier': 4 } } def _get_quality_tier_from_extension(file_path): """Determine quality tier from file extension""" if not file_path: return ('unknown', 999) ext = os.path.splitext(file_path)[1].lower() for tier_name, tier_data in QUALITY_TIERS.items(): if ext in tier_data['extensions']: return (tier_name, tier_data['tier']) return ('unknown', 999) # Quality scanner worker logic lives in core/discovery/quality_scanner.py. from core.discovery import quality_scanner as _discovery_quality_scanner def _build_quality_scanner_deps(): """Build the QualityScannerDeps bundle from web_server.py globals on each call.""" return _discovery_quality_scanner.QualityScannerDeps( quality_scanner_state=quality_scanner_state, quality_scanner_lock=quality_scanner_lock, QUALITY_TIERS=QUALITY_TIERS, matching_engine=matching_engine, automation_engine=automation_engine, get_quality_tier_from_extension=_get_quality_tier_from_extension, add_activity_item=add_activity_item, ) def _run_quality_scanner(scope='watchlist', profile_id=1): return _discovery_quality_scanner.run_quality_scanner( scope, profile_id, _build_quality_scanner_deps() ) from core.library.duplicate_cleaner import ( _run_duplicate_cleaner, init as _init_duplicate_cleaner, ) _init_duplicate_cleaner( state=duplicate_cleaner_state, lock=duplicate_cleaner_lock, resolve_path_fn=docker_resolve_path, engine=automation_engine, ) @app.route('/api/quality-scanner/start', methods=['POST']) def start_quality_scan(): """Start the quality scanner""" with quality_scanner_lock: if quality_scanner_state["status"] == "running": return jsonify({"success": False, "error": "A scan is already in progress"}), 409 data = request.get_json() or {} scope = data.get('scope', 'watchlist') # 'watchlist' or 'all' logger.info(f"[Quality Scanner API] Starting scan with scope: {scope}") # Reset state quality_scanner_state["status"] = "running" quality_scanner_state["phase"] = "Initializing..." quality_scanner_state["progress"] = 0 quality_scanner_state["processed"] = 0 quality_scanner_state["total"] = 0 quality_scanner_state["quality_met"] = 0 quality_scanner_state["low_quality"] = 0 quality_scanner_state["matched"] = 0 quality_scanner_state["results"] = [] quality_scanner_state["error_message"] = "" # Submit worker (capture profile_id before thread) scan_profile_id = get_current_profile_id() quality_scanner_executor.submit(_run_quality_scanner, scope, scan_profile_id) add_activity_item("", "Quality Scan Started", f"Scanning {scope} tracks", "Now") return jsonify({"success": True, "message": "Quality scan started"}) @app.route('/api/quality-scanner/status', methods=['GET']) def get_quality_scanner_status(): """Get current quality scanner status""" with quality_scanner_lock: return jsonify(quality_scanner_state) @app.route('/api/quality-scanner/stop', methods=['POST']) def stop_quality_scan(): """Stop the quality scanner (sets a stop flag)""" with quality_scanner_lock: if quality_scanner_state["status"] == "running": quality_scanner_state["status"] = "finished" quality_scanner_state["phase"] = "Scan stopped by user" return jsonify({"success": True, "message": "Stop request sent"}) else: return jsonify({"success": False, "error": "No scan is currently running"}), 404 @app.route('/api/duplicate-cleaner/start', methods=['POST']) def start_duplicate_cleaner(): """Start the duplicate cleaner""" with duplicate_cleaner_lock: if duplicate_cleaner_state["status"] == "running": return jsonify({"success": False, "error": "A scan is already in progress"}), 409 logger.warning("[Duplicate Cleaner API] Starting duplicate cleaner...") # Reset state duplicate_cleaner_state["status"] = "running" duplicate_cleaner_state["phase"] = "Initializing..." duplicate_cleaner_state["progress"] = 0 duplicate_cleaner_state["files_scanned"] = 0 duplicate_cleaner_state["total_files"] = 0 duplicate_cleaner_state["duplicates_found"] = 0 duplicate_cleaner_state["deleted"] = 0 duplicate_cleaner_state["space_freed"] = 0 duplicate_cleaner_state["error_message"] = "" # Submit worker duplicate_cleaner_executor.submit(_run_duplicate_cleaner) add_activity_item("", "Duplicate Cleaner Started", "Scanning Transfer folder", "Now") return jsonify({"success": True, "message": "Duplicate cleaner started"}) @app.route('/api/duplicate-cleaner/status', methods=['GET']) def get_duplicate_cleaner_status(): """Get current duplicate cleaner status""" with duplicate_cleaner_lock: # Convert space_freed from bytes to MB for display state_copy = duplicate_cleaner_state.copy() state_copy["space_freed_mb"] = duplicate_cleaner_state["space_freed"] / (1024 * 1024) return jsonify(state_copy) @app.route('/api/duplicate-cleaner/stop', methods=['POST']) def stop_duplicate_cleaner(): """Stop the duplicate cleaner (sets a stop flag)""" with duplicate_cleaner_lock: if duplicate_cleaner_state["status"] == "running": duplicate_cleaner_state["status"] = "finished" duplicate_cleaner_state["phase"] = "Scan stopped by user" return jsonify({"success": True, "message": "Stop request sent"}) else: return jsonify({"success": False, "error": "No scan is currently running"}), 404 # =============================== # == RETAG TOOL ENDPOINTS == # =============================== @app.route('/api/retag/stats', methods=['GET']) def get_retag_stats(): """Get retag tool statistics for the dashboard card.""" from database.music_database import get_database db = get_database() stats = db.get_retag_stats() return jsonify({"success": True, **stats}) @app.route('/api/retag/groups', methods=['GET']) def get_retag_groups(): """Get all retag groups sorted by artist name.""" from database.music_database import get_database db = get_database() groups = db.get_retag_groups() return jsonify({"success": True, "groups": groups}) @app.route('/api/retag/groups//tracks', methods=['GET']) def get_retag_group_tracks(group_id): """Get tracks for a specific retag group.""" from database.music_database import get_database db = get_database() tracks = db.get_retag_tracks(group_id) return jsonify({"success": True, "tracks": tracks}) @app.route('/api/retag/search', methods=['GET']) def search_retag_albums(): """Search for albums to use for retagging (uses Spotify/iTunes fallback).""" query = request.args.get('q', '').strip() if not query: return jsonify({"success": False, "error": "Query parameter 'q' is required"}), 400 limit = min(int(request.args.get('limit', 12)), 50) try: results = spotify_client.search_albums(query, limit=limit) albums = [] for a in results: albums.append({ 'id': str(a.id), 'name': a.name, 'artist': ', '.join(a.artists) if a.artists else 'Unknown Artist', 'release_date': a.release_date or '', 'total_tracks': a.total_tracks, 'image_url': a.image_url, 'album_type': a.album_type or 'album' }) return jsonify({"success": True, "albums": albums}) except Exception as e: logger.error(f"[Retag] Album search error: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/retag/execute', methods=['POST']) def execute_retag(): """Start a retag operation for a group with a new album match.""" data = request.get_json() if not data: return jsonify({"success": False, "error": "JSON body required"}), 400 group_id = data.get('group_id') album_id = data.get('album_id') if not group_id or not album_id: return jsonify({"success": False, "error": "group_id and album_id are required"}), 400 with retag_lock: if retag_state["status"] == "running": return jsonify({"success": False, "error": "A retag operation is already running"}), 409 retag_executor.submit(_execute_retag, group_id, str(album_id)) return jsonify({"success": True, "message": "Retag operation started"}) @app.route('/api/retag/status', methods=['GET']) def get_retag_status(): """Get the current retag operation status.""" with retag_lock: return jsonify(dict(retag_state)) @app.route('/api/retag/groups/', methods=['DELETE']) def delete_retag_group(group_id): """Delete a retag group (files are NOT deleted).""" from database.music_database import get_database db = get_database() success = db.delete_retag_group(group_id) if success: return jsonify({"success": True}) else: return jsonify({"success": False, "error": "Group not found"}), 404 @app.route('/api/retag/groups/delete-batch', methods=['POST']) def delete_retag_groups_batch(): """Delete multiple retag groups at once.""" from database.music_database import get_database data = request.get_json() or {} group_ids = data.get('group_ids', []) if not group_ids: return jsonify({"success": False, "error": "No group IDs provided"}), 400 db = get_database() removed = 0 for gid in group_ids: if db.delete_retag_group(int(gid)): removed += 1 return jsonify({"success": True, "removed": removed}) @app.route('/api/retag/groups/clear-all', methods=['POST']) def clear_all_retag_groups(): """Delete all retag groups.""" from database.music_database import get_database db = get_database() count = db.delete_all_retag_groups() return jsonify({"success": True, "removed": count}) # =============================== # == DOWNLOAD MISSING TRACKS == # =============================== from core.downloads.validation import ( get_valid_candidates, init as _init_download_validation, ) def _recover_worker_slot(batch_id, task_id): """ Emergency worker slot recovery function for when normal completion callback fails. This prevents permanent worker slot leaks that cause modal to show wrong worker counts. """ try: logger.warning(f"[Worker Recovery] Attempting to recover worker slot for batch {batch_id}, task {task_id}") # Acquire lock with timeout to prevent deadlock lock_acquired = tasks_lock.acquire(timeout=3.0) if not lock_acquired: logger.error("[Worker Recovery] FATAL: Could not acquire lock for recovery - worker slot LEAKED") return False try: # Verify batch still exists if batch_id not in download_batches: logger.warning(f"[Worker Recovery] Batch {batch_id} not found - nothing to recover") return True batch = download_batches[batch_id] old_active = batch['active_count'] # Only decrement if there are active workers to prevent negative counts if old_active > 0: batch['active_count'] -= 1 new_active = batch['active_count'] logger.warning(f"[Worker Recovery] Recovered worker slot - Active count: {old_active} → {new_active}") # Try to start next worker if queue isn't empty if batch['queue_index'] < len(batch['queue']) and new_active < batch['max_concurrent']: logger.warning("[Worker Recovery] Attempting to start replacement worker") # Release lock temporarily to avoid deadlock in _start_next_batch_of_downloads tasks_lock.release() try: _start_next_batch_of_downloads(batch_id) finally: # Re-acquire lock for final cleanup tasks_lock.acquire(timeout=2.0) return True else: logger.warning("[Worker Recovery] Active count already 0 - no recovery needed") return True finally: tasks_lock.release() except Exception as recovery_error: logger.error(f"[Worker Recovery] FATAL ERROR in recovery: {recovery_error}") return False def _get_batch_lock(batch_id): """Get or create a lock for a specific batch to prevent race conditions""" with tasks_lock: if batch_id not in batch_locks: batch_locks[batch_id] = threading.Lock() return batch_locks[batch_id] # Batch lifecycle logic lives in core/downloads/lifecycle.py. from core.downloads import lifecycle as _downloads_lifecycle def _build_lifecycle_deps(): """Build LifecycleDeps bundle from web_server.py globals on each call.""" return _downloads_lifecycle.LifecycleDeps( config_manager=config_manager, automation_engine=automation_engine, download_monitor=download_monitor, repair_worker=repair_worker, mb_worker=mb_worker, is_shutting_down=lambda: IS_SHUTTING_DOWN, get_batch_lock=_get_batch_lock, submit_download_track_worker=lambda task_id, batch_id: missing_download_executor.submit( _download_track_worker, task_id, batch_id, ), submit_failed_to_wishlist=lambda batch_id: missing_download_executor.submit( _process_failed_tracks_to_wishlist_exact, batch_id, ), submit_failed_to_wishlist_with_auto_completion=lambda batch_id: missing_download_executor.submit( _process_failed_tracks_to_wishlist_exact_with_auto_completion, batch_id, ), process_failed_to_wishlist=_process_failed_tracks_to_wishlist_exact, process_failed_to_wishlist_with_auto_completion=_process_failed_tracks_to_wishlist_exact_with_auto_completion, ensure_wishlist_track_format=_ensure_wishlist_track_format, get_track_artist_name=_get_track_artist_name, check_and_remove_from_wishlist=_check_and_remove_from_wishlist, regenerate_batch_m3u=_regenerate_batch_m3u, youtube_playlist_states=youtube_playlist_states, tidal_discovery_states=tidal_discovery_states, deezer_discovery_states=deezer_discovery_states, spotify_public_discovery_states=spotify_public_discovery_states, ) def _start_next_batch_of_downloads(batch_id): """Start the next batch of downloads up to the concurrent limit.""" _downloads_lifecycle.start_next_batch_of_downloads(batch_id, _build_lifecycle_deps()) from core.downloads.wishlist_failed import ( _process_failed_tracks_to_wishlist_exact, init as _init_wishlist_failed, ) def _process_failed_tracks_to_wishlist_exact_with_auto_completion(batch_id): """ Process failed tracks to wishlist for auto-initiated batches and handle auto-processing completion. This extends the standard processing with automatic scheduling of the next cycle. """ global wishlist_auto_processing global wishlist_auto_processing_timestamp try: logger.info(f"[Auto-Wishlist] Processing completion for auto-initiated batch {batch_id}") completion_summary = _process_failed_tracks_to_wishlist_exact(batch_id) def _reset_auto_processing_state(): global wishlist_auto_processing, wishlist_auto_processing_timestamp with wishlist_timer_lock: wishlist_auto_processing = False wishlist_auto_processing_timestamp = 0 from database.music_database import MusicDatabase return _finalize_auto_wishlist_completion( batch_id, completion_summary, download_batches=download_batches, tasks_lock=tasks_lock, reset_processing_state=_reset_auto_processing_state, add_activity_item=add_activity_item, automation_engine=automation_engine, db_factory=MusicDatabase, ) except Exception as e: logger.error(f"[Auto-Wishlist] Error in auto-completion processing: {e}") import traceback traceback.print_exc() # Ensure auto-processing flag is reset even on error and reset timestamp with wishlist_timer_lock: wishlist_auto_processing = False wishlist_auto_processing_timestamp = 0 return {'tracks_added': 0, 'errors': 1, 'total_failed': 0} def _on_download_completed(batch_id, task_id, success=True): """Called when a download completes to start the next one in queue.""" _downloads_lifecycle.on_download_completed(batch_id, task_id, success, _build_lifecycle_deps()) # Master worker for the missing tracks pipeline lives in core/downloads/master.py. from core.downloads import master as _downloads_master def _build_master_deps(): """Build the MasterDeps bundle from web_server.py globals on each call.""" def _reset_wishlist_auto_processing(): global wishlist_auto_processing, wishlist_auto_processing_timestamp with wishlist_timer_lock: wishlist_auto_processing = False wishlist_auto_processing_timestamp = 0 return _downloads_master.MasterDeps( config_manager=config_manager, download_orchestrator=download_orchestrator, run_async=run_async, mb_worker=mb_worker, mb_release_cache=mb_release_cache, mb_release_cache_lock=mb_release_cache_lock, mb_release_detail_cache=mb_release_detail_cache, mb_release_detail_cache_lock=mb_release_detail_cache_lock, normalize_album_cache_key=normalize_album_cache_key, check_and_remove_track_from_wishlist_by_metadata=_check_and_remove_track_from_wishlist_by_metadata, is_explicit_blocked=_is_explicit_blocked, youtube_playlist_states=youtube_playlist_states, tidal_discovery_states=tidal_discovery_states, deezer_discovery_states=deezer_discovery_states, spotify_public_discovery_states=spotify_public_discovery_states, missing_download_executor=missing_download_executor, process_failed_tracks_to_wishlist_exact_with_auto_completion=_process_failed_tracks_to_wishlist_exact_with_auto_completion, source_reuse_logger=source_reuse_logger, download_monitor=download_monitor, start_next_batch_of_downloads=_start_next_batch_of_downloads, reset_wishlist_auto_processing=_reset_wishlist_auto_processing, ) def _run_full_missing_tracks_process(batch_id, playlist_id, tracks_json): return _downloads_master.run_full_missing_tracks_process( batch_id, playlist_id, tracks_json, _build_master_deps() ) # Post-processing verification worker logic lives in core/downloads/post_processing.py. from core.downloads import post_processing as _downloads_post_processing def _build_post_processing_deps(): """Build the PostProcessDeps bundle from web_server.py globals on each call.""" return _downloads_post_processing.PostProcessDeps( config_manager=config_manager, download_orchestrator=download_orchestrator, run_async=run_async, docker_resolve_path=docker_resolve_path, extract_filename=extract_filename, make_context_key=_make_context_key, find_completed_file=_find_completed_file_robust, enhance_file_metadata=_enhance_file_metadata, wipe_source_tags=_wipe_source_tags, post_process_with_verification=_post_process_matched_download_with_verification, mark_task_completed=_mark_task_completed, on_download_completed=_on_download_completed, ) def _run_post_processing_worker(task_id, batch_id): """Post-processing verification worker — see core/downloads/post_processing.py.""" _downloads_post_processing.run_post_processing_worker(task_id, batch_id, _build_post_processing_deps()) # Per-task download worker logic lives in core/downloads/task_worker.py. from core.downloads import task_worker as _downloads_task_worker def _build_task_worker_deps(): """Build TaskWorkerDeps bundle from web_server.py globals on each call.""" return _downloads_task_worker.TaskWorkerDeps( download_orchestrator=download_orchestrator, matching_engine=matching_engine, run_async=run_async, try_source_reuse=_try_source_reuse, store_batch_source=_store_batch_source, try_staging_match=_try_staging_match, get_valid_candidates=get_valid_candidates, attempt_download_with_candidates=_attempt_download_with_candidates, on_download_completed=lambda b, t, success: _on_download_completed(b, t, success=success), recover_worker_slot=_recover_worker_slot, ) def _download_track_worker(task_id, batch_id=None): """Per-task download worker — see core/downloads/task_worker.py.""" _downloads_task_worker.download_track_worker(task_id, batch_id, _build_task_worker_deps()) # Candidate fallback download logic lives in core/downloads/candidates.py. from core.downloads import candidates as _downloads_candidates def _build_candidates_deps(): """Build the CandidatesDeps bundle from web_server.py globals on each call.""" return _downloads_candidates.CandidatesDeps( download_orchestrator=download_orchestrator, spotify_client=spotify_client, run_async=run_async, get_database=get_database, update_task_status=_update_task_status, make_context_key=_make_context_key, on_download_completed=_on_download_completed, ) def _attempt_download_with_candidates(task_id, candidates, track, batch_id=None): return _downloads_candidates.attempt_download_with_candidates( task_id, candidates, track, batch_id, _build_candidates_deps() ) # ── Staging folder match cache (per-batch, avoids re-scanning for every track) ── _staging_cache = {} # batch_id -> list of {full_path, title, artist, album, extension} _staging_cache_lock = threading.Lock() STAGING_AUDIO_EXTENSIONS = {'.mp3', '.flac', '.ogg', '.opus', '.m4a', '.aac', '.wav', '.wma', '.aiff', '.aif'} def _get_staging_file_cache(batch_id): """Scan staging folder once per batch and cache the results.""" with _staging_cache_lock: if batch_id in _staging_cache: return _staging_cache[batch_id] staging_path = get_staging_path() if not os.path.isdir(staging_path): with _staging_cache_lock: _staging_cache[batch_id] = [] return [] files = [] for root, _dirs, filenames in os.walk(staging_path): for fname in filenames: ext = os.path.splitext(fname)[1].lower() if ext not in STAGING_AUDIO_EXTENSIONS: continue full_path = os.path.join(root, fname) rel_path = os.path.relpath(full_path, staging_path) meta = _read_staging_file_metadata(full_path, rel_path) files.append({ 'full_path': full_path, 'title': meta['title'] or '', 'artist': meta['albumartist'] or meta['artist'] or '', 'album': meta['album'] or '', 'extension': ext, }) logger.info(f"[Staging] Scanned {len(files)} audio files in staging folder") with _staging_cache_lock: _staging_cache[batch_id] = files return files # Staging-folder match shortcut lives in core/downloads/staging.py. from core.downloads import staging as _downloads_staging def _build_staging_deps(): """Build the StagingDeps bundle from web_server.py globals on each call.""" return _downloads_staging.StagingDeps( config_manager=config_manager, matching_engine=matching_engine, get_staging_file_cache=_get_staging_file_cache, docker_resolve_path=docker_resolve_path, post_process_matched_download_with_verification=_post_process_matched_download_with_verification, ) def _try_staging_match(task_id, batch_id, track): return _downloads_staging.try_staging_match(task_id, batch_id, track, _build_staging_deps()) def _try_source_reuse(task_id, batch_id, track): """ Check batch's last_good_source for the current track before searching. Returns True if source reuse succeeded, False to fall through to normal search. """ _sr = source_reuse_logger _sr.info(f"_try_source_reuse called: task={task_id}, batch={batch_id}, track={track.name}") if not batch_id: _sr.info("Skipped — no batch_id") return False with tasks_lock: batch = download_batches.get(batch_id) if not batch: _sr.info(f"Skipped — batch {batch_id} not found") return False # Gate: album/EP downloads only is_album = batch.get('is_album_download', False) is_wishlist = batch.get('playlist_id', '') == 'wishlist' if not is_album and not is_wishlist: _sr.info(f"Skipped — not album ({is_album}) and not wishlist ({is_wishlist})") return False source_tracks = batch.get('source_folder_tracks') last_source = batch.get('last_good_source') _sr.info(f"Batch state: last_good_source={last_source}, source_folder_tracks={'None' if source_tracks is None else f'{len(source_tracks)} tracks'}") if not source_tracks or not last_source: _sr.info("Skipped — no source_tracks or no last_source") return False if last_source.get('username') in ('youtube', 'tidal', 'qobuz', 'hifi', 'deezer_dl', 'lidarr', 'soundcloud'): _sr.info(f"Skipped — {last_source.get('username')} source (no folder-based reuse)") return False source_username = last_source.get('username') source_folder = last_source.get('folder_path', '') source_key = f"{source_username}:{source_folder}" # Check if this source+folder has already failed for this batch with tasks_lock: batch = download_batches.get(batch_id, {}) failed_sources = batch.get('failed_sources', set()) if source_key in failed_sources: _sr.info(f"Source {source_key} already in failed_sources — skipping") with tasks_lock: if batch_id in download_batches: download_batches[batch_id]['last_good_source'] = None download_batches[batch_id]['source_folder_tracks'] = None return False # Detect retry: if this task already tried the stored source and failed (monitor resubmitted), # the task will still have the previous username/download_id from the failed attempt with tasks_lock: task = download_tasks.get(task_id, {}) prev_username = task.get('username') prev_download_id = task.get('download_id') if prev_username and prev_download_id and prev_username == source_username: _sr.info(f"Task {task_id} already failed from source {source_key} — marking as failed") with tasks_lock: if batch_id in download_batches: if 'failed_sources' not in download_batches[batch_id]: download_batches[batch_id]['failed_sources'] = set() download_batches[batch_id]['failed_sources'].add(source_key) download_batches[batch_id]['last_good_source'] = None download_batches[batch_id]['source_folder_tracks'] = None return False _sr.info(f"Checking reused source for task {task_id}: {source_key}") # Score each folder track against current track candidates = [] for folder_track in source_tracks: confidence = matching_engine.calculate_slskd_match_confidence(track, folder_track) _sr.info(f" Match '{track.name}' vs '{folder_track.filename}' → confidence={confidence:.3f}") if confidence >= 0.70: folder_track.confidence = confidence candidates.append(folder_track) if not candidates: _sr.info(f"No folder tracks matched above 0.70 for task {task_id}") return False # Sort by confidence, filter by quality preference candidates.sort(key=lambda c: c.confidence, reverse=True) _sr.info(f"Found {len(candidates)} candidates above 0.70, best={candidates[0].confidence:.3f} ({candidates[0].filename})") slsk = download_orchestrator.client("soulseek") if hasattr(download_orchestrator, 'client') else download_orchestrator filtered = slsk.filter_results_by_quality_preference(candidates) if not filtered: _sr.info(f"Quality filter rejected all candidates for task {task_id}") return False _sr.info(f"After quality filter: {len(filtered)} candidates remain") # Artist verification artist_name = track.artists[0].lower() if track.artists else '' verified = [c for c in filtered if artist_name and artist_name in c.filename.lower().replace('\\', '/')] final_candidates = verified if verified else filtered[:1] _sr.info(f"Artist verification: artist='{artist_name}', verified={len(verified)}, using={len(final_candidates)} candidates") # Initialize task state for download attempt # IMPORTANT: Preserve used_sources from previous attempts (e.g. monitor error retries) # so that _attempt_download_with_candidates skips sources that already failed. with tasks_lock: if task_id in download_tasks: download_tasks[task_id]['status'] = 'searching' download_tasks[task_id]['current_query_index'] = 0 download_tasks[task_id]['current_candidate_index'] = 0 download_tasks[task_id]['retry_count'] = 0 download_tasks[task_id]['candidates'] = [] # Don't reset used_sources — the download monitor marks failed sources here # Attempt download success = _attempt_download_with_candidates(task_id, final_candidates, track, batch_id) if success: _sr.info(f"SUCCESS — Downloaded from reused source for task {task_id}") return True # Source failed — mark as failed so it's never tried again for this batch with tasks_lock: if batch_id in download_batches: if 'failed_sources' not in download_batches[batch_id]: download_batches[batch_id]['failed_sources'] = set() download_batches[batch_id]['failed_sources'].add(source_key) download_batches[batch_id]['last_good_source'] = None download_batches[batch_id]['source_folder_tracks'] = None _sr.info(f"FAILED — Source {source_key} failed for task {task_id}, added to failed_sources") return False def _store_batch_source(batch_id, username, filename): """Browse the successful download's folder and store results on the batch for reuse.""" _sr = source_reuse_logger _sr.info(f"_store_batch_source called: batch={batch_id}, user={username}, file={filename}") if not batch_id or username in ('youtube', 'tidal', 'qobuz', 'hifi', 'deezer_dl', 'lidarr', 'soundcloud'): _sr.info(f"Skipped — no batch_id or streaming source ({username})") return with tasks_lock: batch = download_batches.get(batch_id) if not batch: _sr.info("Skipped — batch not found") return is_album = batch.get('is_album_download', False) is_wishlist = batch.get('playlist_id', '') == 'wishlist' if not is_album and not is_wishlist: _sr.info(f"Skipped — not album ({is_album}) and not wishlist ({is_wishlist})") return # Don't store a source+folder that already failed for this batch failed_sources = batch.get('failed_sources', set()) # Extract folder path from filename — preserve original separators for slskd API if '\\' in filename: folder_path = filename.rsplit('\\', 1)[0] elif '/' in filename: folder_path = filename.rsplit('/', 1)[0] else: _sr.info(f"Skipped — no folder separator in filename: {filename}") return # Check failed_sources with username:folder key source_key = f"{username}:{folder_path}" if source_key in failed_sources: _sr.info(f"Not storing source {source_key} — already in failed_sources") return try: # Access SoulseekClient directly (download_orchestrator is DownloadOrchestrator) slsk = download_orchestrator.client("soulseek") if hasattr(download_orchestrator, 'client') else download_orchestrator _sr.info(f"Browsing {username}:{folder_path}...") files = run_async(slsk.browse_user_directory(username, folder_path)) if not files: _sr.info(f"Browse returned no files for {username}:{folder_path}") return _sr.info(f"Browse returned {len(files)} raw files") tracks = slsk.parse_browse_results_to_tracks(username, files, directory=folder_path) if not tracks: _sr.info(f"No audio tracks after parsing for {username}:{folder_path}") return _sr.info(f"Parsed {len(tracks)} audio tracks from {username}:{folder_path}") with tasks_lock: if batch_id in download_batches: download_batches[batch_id]['last_good_source'] = { 'username': username, 'folder_path': folder_path } download_batches[batch_id]['source_folder_tracks'] = tracks _sr.info(f"STORED {len(tracks)} tracks from {username}:{folder_path} as last_good_source") except Exception as e: _sr.info(f"EXCEPTION browsing source folder: {e}") import traceback _sr.info(traceback.format_exc()) @app.route('/api/playlists//download_missing', methods=['POST']) def start_playlist_missing_downloads(playlist_id): """ This endpoint receives the list of missing tracks and manages them with batch processing like the GUI, maintaining exactly 3 concurrent downloads. """ dl_err = check_download_permission() if dl_err: return dl_err data = request.get_json() missing_tracks = data.get('missing_tracks', []) if not missing_tracks: return jsonify({"success": False, "error": "No missing tracks provided"}), 400 # Filter explicit tracks if content filter is enabled if not config_manager.get('content_filter.allow_explicit', True): before_count = len(missing_tracks) missing_tracks = [t for t in missing_tracks if not _is_explicit_blocked(t.get('track', t))] skipped = before_count - len(missing_tracks) if skipped > 0: logger.warning(f"[Content Filter] Filtered out {skipped} explicit track(s) from playlist download") if not missing_tracks: return jsonify({"success": False, "error": "All tracks were filtered by explicit content setting"}), 400 # Add activity for playlist download missing start playlist_name = data.get('playlist_name', f'Playlist {playlist_id}') add_activity_item("", "Missing Tracks Download Started", f"'{playlist_name}' - {len(missing_tracks)} tracks", "Now") try: batch_id = str(uuid.uuid4()) # Create task queue for this batch task_queue = [] with tasks_lock: # Initialize batch management download_batches[batch_id] = { 'queue': [], 'active_count': 0, 'max_concurrent': _get_max_concurrent(), 'queue_index': 0, # Track state management (replicating sync.py) 'permanently_failed_tracks': [], 'cancelled_tracks': set(), # Profile context for failed track wishlist re-adds 'profile_id': get_current_profile_id() } for i, track_entry in enumerate(missing_tracks): task_id = str(uuid.uuid4()) # Extract track data and original track index from frontend track_data = track_entry.get('track', track_entry) # Support both old and new format original_track_index = track_entry.get('track_index', i) # Use original index or fallback to enumeration download_tasks[task_id] = { 'status': 'pending', 'track_info': track_data, 'playlist_id': playlist_id, 'batch_id': batch_id, 'track_index': original_track_index, # Use original playlist track index 'download_id': None, 'username': None, 'filename': None, # Retry-related fields (GUI parity) 'retry_count': 0, 'cached_candidates': [], 'used_sources': set(), 'status_change_time': time.time() } # Add to batch queue instead of submitting immediately download_batches[batch_id]['queue'].append(task_id) # Start background monitoring for timeouts and retries (GUI parity) download_monitor.start_monitoring(batch_id) # Start the first batch of downloads (up to 3) _start_next_batch_of_downloads(batch_id) return jsonify({"success": True, "batch_id": batch_id, "message": f"Queued {len(missing_tracks)} downloads for processing."}) except Exception as e: logger.error(f"Error starting missing downloads: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/active-processes', methods=['GET']) def get_active_processes(): """ Returns all active processes for frontend rehydration: - Download batch processes (Spotify playlists) - YouTube discovery/sync processes (non-fresh phases) """ active_processes = [] # Add active download batch processes with tasks_lock: for batch_id, batch_data in download_batches.items(): if batch_data.get('phase') not in ['complete', 'error', 'cancelled']: process_info = { "type": "batch", "playlist_id": batch_data.get('playlist_id'), "playlist_name": batch_data.get('playlist_name'), "batch_id": batch_id, "phase": batch_data.get('phase') } # Enhanced wishlist information for better frontend state management if batch_data.get('playlist_id') == 'wishlist': process_info.update({ "auto_initiated": batch_data.get('auto_initiated', False), "auto_processing_timestamp": batch_data.get('auto_processing_timestamp'), "should_show_modal": True, # Wishlist processes should always be visible "is_background_process": batch_data.get('auto_initiated', False), "current_cycle": batch_data.get('current_cycle') # Pass category filter to frontend }) # Add current auto-processing state for frontend awareness with wishlist_timer_lock: process_info["auto_processing_active"] = wishlist_auto_processing active_processes.append(process_info) # Add YouTube playlists in non-fresh phases for rehydration for url_hash, state in youtube_playlist_states.items(): # Include playlists that have progressed beyond fresh phase if state['phase'] != 'fresh': active_processes.append({ "type": "youtube_playlist", "url_hash": url_hash, "url": state['url'], "playlist_name": state['playlist']['name'], "phase": state['phase'], "status": state['status'], "discovery_progress": state['discovery_progress'], "spotify_matches": state['spotify_matches'], "spotify_total": state['spotify_total'], "converted_spotify_playlist_id": state.get('converted_spotify_playlist_id'), "download_process_id": state.get('download_process_id') # batch_id for download modal rehydration }) logger.info(f"Active processes check: {len([p for p in active_processes if p['type'] == 'batch'])} download batches, {len([p for p in active_processes if p['type'] == 'youtube_playlist'])} YouTube playlists") return jsonify({"active_processes": active_processes}) # Status payload helpers live in core/downloads/status.py. from core.downloads import status as _downloads_status def _build_status_deps(): """Build StatusDeps bundle from web_server.py globals on each call.""" return _downloads_status.StatusDeps( config_manager=config_manager, docker_resolve_path=docker_resolve_path, find_completed_file=_find_completed_file_robust, make_context_key=_make_context_key, submit_post_processing=lambda task_id, batch_id: missing_download_executor.submit( _run_post_processing_worker, task_id, batch_id ), get_cached_transfer_data=get_cached_transfer_data, download_orchestrator=download_orchestrator, run_async=run_async, on_download_completed=_on_download_completed, ) def _build_batch_status_data(batch_id, batch, live_transfers_lookup): """Helper function to build status data for a single batch. Extracted from get_batch_download_status for reuse in batched endpoint. """ return _downloads_status.build_batch_status_data(batch_id, batch, live_transfers_lookup, _build_status_deps()) @app.route('/api/playlists//download_status', methods=['GET']) def get_batch_download_status(batch_id): """Returns real-time status for a single batch.""" try: body, status = _downloads_status.build_single_batch_status(batch_id, _build_status_deps()) return jsonify(body), status except Exception as e: import traceback traceback.print_exc() return jsonify({"error": str(e)}), 500 @app.route('/api/download_status/batch', methods=['GET']) def get_batched_download_statuses(): """Returns status for multiple download batches in one request.""" try: requested_batch_ids = request.args.getlist('batch_ids') return jsonify(_downloads_status.build_batched_status(requested_batch_ids, _build_status_deps())) except Exception as e: import traceback traceback.print_exc() return jsonify({"error": str(e)}), 500 @app.route('/api/downloads/all', methods=['GET']) def get_all_downloads_unified(): """Unified downloads list for the centralized Downloads page.""" try: limit = int(request.args.get('limit', 200)) return jsonify(_downloads_status.build_unified_downloads_response(limit, _build_status_deps())) except Exception as e: logger.error(f"Error getting unified downloads: {e}") return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/downloads/batch-history', methods=['GET']) def get_batch_history(): """Return completed batch summaries from the last N days for the batch panel history section.""" try: days = int(request.args.get('days', 7)) limit = int(request.args.get('limit', 50)) database = get_database() history = database.get_recent_batch_history(days=days, limit=limit) return jsonify({'success': True, 'history': history}) except Exception as e: logger.error(f"Error getting batch history: {e}") return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/downloads/clear-completed', methods=['POST']) def clear_completed_downloads(): """Remove completed/failed/cancelled tasks from the download tracker.""" try: cleared = _downloads_cancel.clear_completed_local() return jsonify({'success': True, 'cleared': cleared}) except Exception as e: logger.error(f"Error clearing completed downloads: {e}") return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/downloads/cancel_task', methods=['POST']) def cancel_download_task(): """ Cancels a single, specific download task. This version is now identical to the GUI, adding the cancelled track to the wishlist for future automatic retries. """ data = request.get_json() task_id = data.get('task_id') if not task_id: return jsonify({"success": False, "error": "Missing task_id"}), 400 try: with tasks_lock: if task_id not in download_tasks: return jsonify({"success": False, "error": "Task not found"}), 404 task = download_tasks[task_id] # Log current task state for debugging current_status = task.get('status', 'unknown') download_id = task.get('download_id') username = task.get('username') logger.info(f"[Cancel Debug] Task {task_id} - Current status: '{current_status}', download_id: {download_id}, username: {username}") # Immediately mark as cancelled to prevent race conditions task['status'] = 'cancelled' # IMPROVED WORKER SLOT MANAGEMENT: Use batch state validation instead of task status batch_id = task.get('batch_id') worker_slot_freed = False if batch_id: try: # Check if we need to free a worker slot by examining batch state with tasks_lock: if batch_id in download_batches: batch = download_batches[batch_id] active_count = batch['active_count'] # Free worker slot if there are active workers and task was actively running # This is more reliable than checking task status which can be inconsistent if active_count > 0 and current_status in ['pending', 'searching', 'downloading', 'queued']: logger.info(f"[Cancel] Task {task_id} (status: {current_status}) - freeing worker slot for batch {batch_id}") logger.info(f"[Cancel] Active count before: {active_count}") # Use the completion callback with error handling _on_download_completed(batch_id, task_id, success=False) worker_slot_freed = True # Verify slot was actually freed new_active = download_batches[batch_id]['active_count'] logger.info(f"[Cancel] Active count after: {new_active}") elif active_count == 0: logger.warning(f"[Cancel] Task {task_id} - no active workers to free") else: logger.warning(f"[Cancel] Task {task_id} (status: {current_status}) - not actively running, no slot to free") else: logger.warning(f"[Cancel] Task {task_id} - batch {batch_id} not found") except Exception as slot_error: logger.error(f"[Cancel] Error managing worker slot for {task_id}: {slot_error}") # Attempt emergency recovery if normal completion failed if not worker_slot_freed: try: logger.warning("[Cancel] Attempting emergency worker slot recovery") _recover_worker_slot(batch_id, task_id) except Exception as recovery_error: logger.error(f"[Cancel] FATAL: Emergency recovery failed: {recovery_error}") else: logger.warning(f"[Cancel] Task {task_id} cancelled (no batch_id - likely already completed)") # Optionally try to cancel the Soulseek download (don't block worker progression) if download_id and username: try: # This is an async call, so we run it and wait run_async(download_orchestrator.cancel_download(download_id, username, remove=True)) logger.warning(f"Successfully cancelled Soulseek download {download_id} for task {task_id}") except Exception as e: logger.error(f"Failed to cancel download on slskd, but worker already moved on: {e}") ### NEW LOGIC START: Add cancelled track to wishlist ### try: from core.wishlist_service import get_wishlist_service wishlist_service = get_wishlist_service() # The task dictionary contains all the necessary info track_info = task.get('track_info', {}) # The wishlist service expects a dictionary with specific keys # We need to properly format the artists to avoid nested structures artists_data = track_info.get('artists', []) formatted_artists = [] for artist in artists_data: if isinstance(artist, str): # Already a string, use as-is formatted_artists.append({'name': artist}) elif isinstance(artist, dict): # Check if it's already in the correct format if 'name' in artist and isinstance(artist['name'], str): # Already properly formatted formatted_artists.append(artist) elif 'name' in artist and isinstance(artist['name'], dict) and 'name' in artist['name']: # Nested structure, extract the inner name formatted_artists.append({'name': artist['name']['name']}) else: # Fallback: convert to string formatted_artists.append({'name': str(artist)}) else: # Fallback for any other type formatted_artists.append({'name': str(artist)}) # Build album data - preserve all fields (including artists) for correct folder placement album_raw = track_info.get('album', {}) if isinstance(album_raw, dict): album_data = dict(album_raw) # Copy all fields including artists album_data.setdefault('name', 'Unknown Album') album_data.setdefault('album_type', track_info.get('album_type', 'album')) else: album_data = { 'name': str(album_raw) if album_raw else 'Unknown Album', 'album_type': track_info.get('album_type', 'album') } spotify_track_data = { 'id': track_info.get('id'), 'name': track_info.get('name'), 'artists': formatted_artists, 'album': album_data, 'duration_ms': track_info.get('duration_ms') } source_context = { 'playlist_name': task.get('playlist_name', 'Unknown Playlist'), 'playlist_id': task.get('playlist_id'), 'added_from': 'modal_cancellation' } # Add to wishlist, treating cancellation as a failure # Pass the spotify data directly instead of creating a fake Track object success = wishlist_service.add_spotify_track_to_wishlist( spotify_track_data=spotify_track_data, failure_reason="Download cancelled by user", source_type="playlist", source_context=source_context, profile_id=get_current_profile_id() ) if success: logger.warning(f"Added cancelled track '{track_info.get('name')}' to wishlist.") else: logger.error(f"Failed to add cancelled track '{track_info.get('name')}' to wishlist.") except Exception as e: logger.error(f"CRITICAL ERROR adding cancelled track to wishlist: {e}") ### NEW LOGIC END ### return jsonify({"success": True, "message": "Task cancelled and added to wishlist for retry."}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 # =============================== # NEW ATOMIC CANCEL SYSTEM V2 # =============================== def _find_task_by_playlist_track(playlist_id, track_index): """ Find task_id by playlist_id and track_index. This enables the new v2 API to work without requiring task_id from frontend. """ for task_id, task in download_tasks.items(): if (task.get('playlist_id') == playlist_id and task.get('track_index') == track_index): return task_id, task return None, None def _atomic_cancel_task(playlist_id, track_index): """ Atomically cancel a single task with proper worker slot management. This is the core of the new cancel system - everything in one transaction. Returns: (success: bool, message: str, task_info: dict) """ try: # Find the task to cancel task_id, task = _find_task_by_playlist_track(playlist_id, track_index) if not task_id: return False, f"Task not found for playlist {playlist_id}, track {track_index}", None # Check if already cancelled if task.get('status') == 'cancelled': return False, "Task already cancelled", {'task_id': task_id, 'status': 'cancelled'} current_status = task.get('status', 'unknown') original_status = current_status # Store original status before changing it batch_id = task.get('batch_id') logger.info(f"[Atomic Cancel] Starting atomic cancel: playlist={playlist_id}, track={track_index}, task={task_id}, status={current_status}") # Mark task as cancelled immediately (within same lock context) task['status'] = 'cancelled' task['cancel_requested'] = True task['cancel_timestamp'] = __import__('time').time() task['ui_state'] = 'cancelled' # Ensure task has persistent identifiers for V2 system if 'playlist_id' not in task: task['playlist_id'] = playlist_id # Handle worker slot management worker_slot_freed = False if batch_id and batch_id in download_batches: batch = download_batches[batch_id] active_count = batch['active_count'] # Free worker slot if task was consuming one # More precise check: only free if task was actually running if active_count > 0 and current_status in ['pending', 'searching', 'downloading', 'queued']: logger.info(f"[Atomic Cancel] Freeing worker slot for {task_id} (was {current_status})") # CRITICAL: Direct worker slot management to prevent _on_download_completed race old_active = batch['active_count'] batch['active_count'] = max(0, old_active - 1) # Prevent negative counts worker_slot_freed = True logger.info(f"[Atomic Cancel] Worker count: {old_active} → {batch['active_count']}") # Try to start next task if available (still within lock) if (batch['queue_index'] < len(batch['queue']) and batch['active_count'] < batch['max_concurrent']): logger.info("[Atomic Cancel] Starting next task in queue") # Call the existing function to start next downloads # Note: This will be called outside the lock to prevent deadlock else: logger.warning(f"[Atomic Cancel] No next task to start (queue_index: {batch['queue_index']}/{len(batch['queue'])}, active: {batch['active_count']}/{batch['max_concurrent']})") # Build result info task_info = { 'task_id': task_id, 'status': 'cancelled', 'original_status': original_status, # Pass original status for slskd cancellation 'track_name': task.get('track_info', {}).get('name', 'Unknown'), 'playlist_id': playlist_id, 'track_index': track_index, 'worker_slot_freed': worker_slot_freed } logger.warning(f"[Atomic Cancel] Successfully cancelled task {task_id}") return True, "Task cancelled successfully", task_info except Exception as e: logger.error(f"[Atomic Cancel] Error in atomic cancel: {e}") import traceback traceback.print_exc() return False, f"Internal error: {str(e)}", None @app.route('/api/downloads/cancel_task_v2', methods=['POST']) def cancel_task_v2(): """ NEW ATOMIC CANCEL SYSTEM V2 Accepts playlist_id and track_index instead of task_id. Performs atomic cancellation with proper worker slot management. No race conditions, no dual state management. """ data = request.get_json() playlist_id = data.get('playlist_id') track_index = data.get('track_index') if not playlist_id or track_index is None: return jsonify({ "success": False, "error": "Missing playlist_id or track_index" }), 400 try: # Everything in one atomic operation within the lock with tasks_lock: success, message, task_info = _atomic_cancel_task(playlist_id, track_index) if not success: return jsonify({"success": False, "error": message}), 400 # Handle post-cancel operations (outside the lock to prevent deadlock) task_id = task_info['task_id'] task = download_tasks.get(task_id) # Try to start next batch of downloads (this may start new workers) if task and task.get('batch_id'): batch_id = task['batch_id'] # Call existing function to manage batch progression try: _start_next_batch_of_downloads(batch_id) except Exception as e: logger.error(f"[Atomic Cancel] Could not start next downloads: {e}") # CRITICAL: Check for batch completion after V2 cancel # V2 system bypasses _on_download_completed, so we need to check completion manually try: _check_batch_completion_v2(batch_id) except Exception as e: logger.error(f"[Atomic Cancel] Could not check batch completion: {e}") # Cancel Soulseek download if active (non-blocking) if task: download_id = task.get('download_id') username = task.get('username') current_status = task.get('status') original_status = task_info.get('original_status', current_status) # Get original status from task_info logger.info(f"[Atomic Cancel] Task {task_id} state: status='{current_status}', original_status='{original_status}', download_id='{download_id}', username='{username}'") logger.info(f"[Atomic Cancel] Download ID type: {type(download_id)}, length: {len(str(download_id)) if download_id else 0}") backslash = '\\' logger.info(f"[Atomic Cancel] Download ID looks like filename: {download_id and ('/' in str(download_id) or backslash in str(download_id))}") if download_id and username: # Route through the DownloadOrchestrator's dispatch (same code # path /api/downloads/cancel uses). It picks the right client by # username: youtube/tidal/qobuz/hifi/deezer_dl/lidarr go to # their streaming clients, anything else goes to Soulseek. # # Replaces an older block that assumed download_orchestrator was a # raw SoulseekClient and accessed .base_url / ._make_request # directly — crashed with AttributeError on the orchestrator # and silently left streaming downloads running in background. try: logger.info(f"[Atomic Cancel] Dispatching cancel to orchestrator: username={username} download_id={download_id}") cancel_success = run_async( download_orchestrator.cancel_download(download_id, username, remove=True) ) if cancel_success: logger.info(f"[Atomic Cancel] Orchestrator cancelled download: {download_id}") else: # Non-fatal: task is already marked cancelled in the DB. # Streaming workers also poll status='cancelled' and bail. logger.warning(f"[Atomic Cancel] Orchestrator could not cancel {download_id} (likely already finished or not yet started)") except Exception as e: logger.error(f"[Atomic Cancel] Exception cancelling download {download_id}: {e}") import traceback logger.error(f"[Atomic Cancel] Cancel error traceback: {traceback.format_exc()}") else: logger.warning("ℹ️ [Atomic Cancel] No download_id or username available - skipping cancel dispatch") # Add to wishlist (non-blocking, best effort) try: _add_cancelled_task_to_wishlist(task) except Exception as e: logger.error(f"[Atomic Cancel] Could not add to wishlist: {e}") return jsonify({ "success": True, "message": message, "task_info": { 'task_id': task_info['task_id'], 'track_name': task_info['track_name'], 'status': 'cancelled' } }) except Exception as e: logger.error(f"[Cancel V2] Unexpected error: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 def _check_batch_completion_v2(batch_id): """V2 SYSTEM: Check if batch is complete after worker slot changes.""" return _downloads_lifecycle.check_batch_completion_v2(batch_id, _build_lifecycle_deps()) def _add_cancelled_task_to_wishlist(task): """ Helper function to add cancelled task to wishlist. Separated for clarity and error isolation. """ if not task: return try: from core.wishlist_service import get_wishlist_service wishlist_service = get_wishlist_service() payload = _build_cancelled_task_wishlist_payload(task, profile_id=get_current_profile_id()) success = wishlist_service.add_spotify_track_to_wishlist(**payload) if success: logger.info(f"[Atomic Cancel] Added '{task.get('track_info', {}).get('name')}' to wishlist") else: logger.error(f"[Atomic Cancel] Failed to add '{task.get('track_info', {}).get('name')}' to wishlist") except Exception as e: logger.error(f"[Atomic Cancel] Critical error adding to wishlist: {e}") @app.route('/api/playlists//cancel_batch', methods=['POST']) def cancel_batch(batch_id): """ Cancels an entire batch - useful for cancelling during analysis phase or cancelling all downloads at once. """ try: with tasks_lock: if batch_id not in download_batches: return jsonify({"success": False, "error": "Batch not found"}), 404 # Mark batch as cancelled download_batches[batch_id]['phase'] = 'cancelled' # Get playlist_id before doing resets playlist_id = download_batches[batch_id].get('playlist_id') # Reset wishlist auto-processing flag if this is a wishlist batch (auto-initiated only) # Manual wishlist downloads don't set the flag, so only reset if auto-initiated if playlist_id == 'wishlist': auto_initiated = download_batches[batch_id].get('auto_initiated', False) if auto_initiated: global wishlist_auto_processing, wishlist_auto_processing_timestamp with wishlist_timer_lock: wishlist_auto_processing = False wishlist_auto_processing_timestamp = 0 logger.warning("[Wishlist Cancel] Reset wishlist auto-processing flag for cancelled auto-batch") else: logger.warning("ℹ️ [Wishlist Cancel] Manual wishlist batch cancelled (no flag reset needed)") # Reset YouTube playlist phase to 'discovered' if this is a YouTube playlist if playlist_id and playlist_id.startswith('youtube_'): url_hash = playlist_id.replace('youtube_', '') if url_hash in youtube_playlist_states: youtube_playlist_states[url_hash]['phase'] = 'discovered' logger.warning(f"Reset YouTube playlist {url_hash} to discovered phase (batch cancelled)") # Cancel all individual tasks in the batch cancelled_count = 0 for task_id in download_batches[batch_id].get('queue', []): if task_id in download_tasks: task = download_tasks[task_id] if task['status'] not in ['completed', 'failed', 'not_found', 'cancelled']: task['status'] = 'cancelled' cancelled_count += 1 # Add activity for batch cancellation playlist_name = download_batches[batch_id].get('playlist_name', 'Unknown Playlist') add_activity_item("", "Batch Cancelled", f"'{playlist_name}' - {cancelled_count} downloads cancelled", "Now") logger.warning(f"Cancelled batch {batch_id} with {cancelled_count} tasks") return jsonify({"success": True, "cancelled_tasks": cancelled_count}) except Exception as e: logger.error(f"Error cancelling batch {batch_id}: {e}") return jsonify({"success": False, "error": str(e)}), 500 # NEW ENDPOINT: Add this function to web_server.py @app.route('/api/playlists/cleanup_batch', methods=['POST']) def cleanup_batch(): """ Cleans up a completed or cancelled batch from the server's in-memory state. This is called by the client after the user closes a finished modal. """ data = request.get_json() batch_id = data.get('batch_id') if not batch_id: return jsonify({"success": False, "error": "Missing batch_id"}), 400 try: with tasks_lock: # Check if the batch exists before trying to delete if batch_id in download_batches: batch = download_batches[batch_id] # CRITICAL: Don't allow cleanup if wishlist processing is in progress # This prevents a race condition where cleanup deletes the batch before # the wishlist processing thread can access it if batch.get('wishlist_processing_started') and not batch.get('wishlist_processing_complete'): logger.info(f"[Cleanup] Batch {batch_id} cleanup deferred - wishlist processing in progress") return jsonify({ "success": False, "error": "Batch cleanup deferred - wishlist processing in progress", "deferred": True }), 202 # 202 = Accepted but not yet processed # Get the list of task IDs before deleting the batch task_ids_to_remove = batch.get('queue', []) # Delete the batch record del download_batches[batch_id] # Clean up the associated tasks from the tasks dictionary for task_id in task_ids_to_remove: if task_id in download_tasks: del download_tasks[task_id] logger.info(f"Cleaned up batch '{batch_id}' and its associated tasks from server state.") return jsonify({"success": True, "message": f"Batch {batch_id} cleaned up."}) else: # It's not an error if the batch is already gone logger.info(f"Cleanup requested for non-existent batch '{batch_id}'. Already cleaned up?") return jsonify({"success": True, "message": "Batch already cleaned up."}) except Exception as e: logger.error(f"Error during batch cleanup for '{batch_id}': {e}") return jsonify({"success": False, "error": str(e)}), 500 # =============================== # == SYNC HISTORY API == # =============================== @app.route('/api/sync/history', methods=['GET']) def get_sync_history(): """Get paginated sync history.""" try: page = int(request.args.get('page', 1)) limit = int(request.args.get('limit', 20)) source = request.args.get('source') or None db = MusicDatabase() entries, total = db.get_sync_history(source=source, page=page, limit=limit) stats = db.get_sync_history_stats() # Parse artist/album names from JSON context for display for entry in entries: if entry.get('artist_context'): try: ac = json.loads(entry['artist_context']) entry['artist_name'] = ac.get('name', '') except: entry['artist_name'] = '' else: entry['artist_name'] = '' if entry.get('album_context'): try: alc = json.loads(entry['album_context']) entry['album_name'] = alc.get('name', '') except: entry['album_name'] = '' else: entry['album_name'] = '' # Remove raw JSON from list response entry.pop('artist_context', None) entry.pop('album_context', None) return jsonify({"success": True, "entries": entries, "total": total, "page": page, "limit": limit, "stats": stats}) except Exception as e: logger.error(f"Error getting sync history: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/sync/history/', methods=['GET']) def get_sync_history_entry(entry_id): """Get a single sync history entry with full cached data for re-trigger.""" try: db = MusicDatabase() entry = db.get_sync_history_entry(entry_id) if not entry: return jsonify({"success": False, "error": "Entry not found"}), 404 # Parse JSON fields entry['tracks'] = json.loads(entry['tracks_json']) if entry.get('tracks_json') else [] entry['artist_context'] = json.loads(entry['artist_context']) if entry.get('artist_context') else None entry['album_context'] = json.loads(entry['album_context']) if entry.get('album_context') else None entry['track_results'] = json.loads(entry['track_results']) if entry.get('track_results') else None entry.pop('tracks_json', None) return jsonify({"success": True, "entry": entry}) except Exception as e: logger.error(f"Error getting sync history entry: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/sync/history/', methods=['DELETE']) def delete_sync_history_entry_api(entry_id): """Delete a sync history entry.""" try: db = MusicDatabase() deleted = db.delete_sync_history_entry(entry_id) return jsonify({"success": deleted}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/sync/history/names', methods=['GET']) def get_sync_history_playlist_names(): """Return distinct playlist names ever synced, for server playlist cross-reference.""" try: db = MusicDatabase() names = db.get_sync_history_playlist_names() return jsonify(names) except Exception as e: return jsonify([]) # =============================== # == UNIFIED MISSING TRACKS API == # =============================== # Sync history recording lives in core/downloads/history.py. # Re-exported here as thin wrappers so existing call sites still resolve. from core.downloads import history as _downloads_history def _detect_sync_source(playlist_id): """Derive the sync source from the playlist_id prefix.""" return _downloads_history.detect_sync_source(playlist_id) def _record_sync_history_start(batch_id, playlist_id, playlist_name, tracks, is_album_download, album_context, artist_context, playlist_folder_mode, source_page=None): """Record a sync start to the database.""" _downloads_history.record_sync_history_start( MusicDatabase(), batch_id, playlist_id, playlist_name, tracks, is_album_download, album_context, artist_context, playlist_folder_mode, source_page=source_page, ) def _record_sync_history_completion(batch_id, batch): """Update sync history with completion stats and per-track results. NOTE: Called from within tasks_lock context — do NOT acquire tasks_lock here.""" _downloads_history.record_sync_history_completion(MusicDatabase(), batch_id, batch) # =============================== # == SERVER PLAYLIST MANAGER == # =============================== @app.route('/api/server/playlists', methods=['GET']) def get_server_playlists(): """Get all playlists from the active media server.""" try: active_server = config_manager.get_active_media_server() logger.info(f"[ServerPlaylists] Active server: {active_server}") if not active_server: return jsonify({"success": False, "error": "No media server configured"}), 400 playlists_data = [] if active_server == 'plex' and media_server_engine.client('plex') and media_server_engine.client('plex').is_connected(): # Use raw Plex API to get playlist metadata without fetching all tracks try: raw_playlists = media_server_engine.client('plex').server.playlists() logger.info(f"[ServerPlaylists] Plex returned {len(raw_playlists)} total playlists") for playlist in raw_playlists: if getattr(playlist, 'playlistType', None) == 'audio': playlists_data.append({ 'id': str(playlist.ratingKey), 'name': playlist.title, 'track_count': playlist.leafCount, }) logger.info(f"[ServerPlaylists] Found {len(playlists_data)} audio playlists") except Exception as e: logger.error(f"[ServerPlaylists] Error fetching Plex playlists: {e}", exc_info=True) return jsonify({"success": False, "error": f"Plex error: {str(e)}"}), 500 elif active_server == 'jellyfin' and media_server_engine.client('jellyfin') and media_server_engine.client('jellyfin').is_connected(): for pl in media_server_engine.client('jellyfin').get_all_playlists(): playlists_data.append({ 'id': pl.id, 'name': pl.title, 'track_count': pl.leaf_count, }) elif active_server == 'navidrome' and media_server_engine.client('navidrome') and media_server_engine.client('navidrome').is_connected(): for pl in media_server_engine.client('navidrome').get_all_playlists(): playlists_data.append({ 'id': pl.id, 'name': pl.title, 'track_count': pl.leaf_count, }) else: logger.warning(f"[ServerPlaylists] Server '{active_server}' not connected. plex_client={media_server_engine.client('plex') is not None}, jellyfin_client={media_server_engine.client('jellyfin') is not None}, navidrome_client={media_server_engine.client('navidrome') is not None}") return jsonify({"success": False, "error": f"{active_server} not connected"}), 400 return jsonify({"success": True, "server_type": active_server, "playlists": playlists_data}) except Exception as e: logger.error(f"Error getting server playlists: {e}", exc_info=True) return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/server/playlist//tracks', methods=['GET']) def get_server_playlist_tracks(playlist_id): """Get tracks from a server playlist with source match info from sync history.""" try: active_server = config_manager.get_active_media_server() playlist_name = request.args.get('name', '') # Get tracks from server server_tracks = [] if active_server == 'plex' and media_server_engine.client('plex'): try: # Try by ID first, fall back to name lookup (ID changes when playlist is recreated) raw_playlist = None try: raw_playlist = media_server_engine.client('plex').server.fetchItem(int(playlist_id)) except Exception as e: logger.debug("plex playlist fetchItem failed: %s", e) if not raw_playlist and playlist_name: try: raw_playlist = media_server_engine.client('plex').server.playlist(playlist_name) except Exception as e: logger.debug("plex playlist by-name lookup failed: %s", e) if not raw_playlist: logger.warning( f"[ServerPlaylistTracks] Plex playlist not found by " f"id={playlist_id} or name='{playlist_name}' — " f"compare view will show every source track as Find & Add" ) if raw_playlist: if not playlist_name: playlist_name = raw_playlist.title plex_base = getattr(media_server_engine.client('plex').server, '_baseurl', '') or '' plex_token = getattr(media_server_engine.client('plex').server, '_token', '') or '' if not plex_base: # Fallback: get from config _pc = config_manager.get_plex_config() plex_base = (_pc.get('base_url', '') or '').rstrip('/') plex_token = plex_token or _pc.get('token', '') logger.debug(f"[ServerPlaylistTracks] Plex base URL: {plex_base}") for item in raw_playlist.items(): grandparent = getattr(item, 'grandparentTitle', '') or '' parent = getattr(item, 'parentTitle', '') or '' # Build full thumb URL from Plex relative path thumb = '' raw_thumb = getattr(item, 'thumb', '') or getattr(item, 'parentThumb', '') or '' if raw_thumb and plex_base and plex_token: thumb = f"{plex_base}{raw_thumb}?X-Plex-Token={plex_token}" server_tracks.append({ 'id': str(item.ratingKey), 'title': item.title, 'artist': grandparent, 'album': parent, 'duration': item.duration or 0, 'thumb': thumb, }) except Exception as e: logger.error(f"[ServerPlaylistTracks] Plex error: {e}", exc_info=True) elif active_server == 'jellyfin' and media_server_engine.client('jellyfin'): tracks = media_server_engine.client('jellyfin').get_playlist_tracks(playlist_id) jf_base = media_server_engine.client('jellyfin').base_url or '' for t in (tracks or []): raw = t._data if hasattr(t, '_data') else {} artists = raw.get('Artists', []) # Jellyfin image: /Items/{Id}/Images/Primary album_id = raw.get('AlbumId', '') thumb = f"{jf_base}/Items/{album_id}/Images/Primary?maxHeight=100" if album_id and jf_base else '' server_tracks.append({ 'id': str(t.ratingKey), 'title': t.title, 'artist': artists[0] if artists else raw.get('AlbumArtist', ''), 'album': raw.get('Album', ''), 'duration': t.duration, 'thumb': thumb, }) elif active_server == 'navidrome' and media_server_engine.client('navidrome'): tracks = media_server_engine.client('navidrome').get_playlist_tracks(playlist_id) for t in (tracks or []): raw = t._data if hasattr(t, '_data') else {} # Navidrome cover art via Subsonic API cover_id = raw.get('coverArt', '') or raw.get('albumId', '') thumb = f"/api/navidrome/cover/{cover_id}" if cover_id else '' server_tracks.append({ 'id': str(t.ratingKey), 'title': t.title, 'artist': raw.get('artist', ''), 'album': raw.get('album', ''), 'duration': t.duration, 'thumb': thumb, }) # Get source tracks — prefer mirrored playlist, fall back to sync history source_tracks = [] mirrored_id = request.args.get('mirrored_playlist_id') if mirrored_id: db = get_database() raw_tracks = db.get_mirrored_playlist_tracks(int(mirrored_id)) # Build server art URL prefix for resolving relative thumb paths _art_prefix = '' _art_suffix = '' if active_server == 'plex' and media_server_engine.client('plex') and media_server_engine.client('plex').server: _ab = getattr(media_server_engine.client('plex').server, '_baseurl', '') or '' _at = getattr(media_server_engine.client('plex').server, '_token', '') or '' if not _ab: _pc = config_manager.get_plex_config() _ab = (_pc.get('base_url', '') or '').rstrip('/') _at = _at or _pc.get('token', '') _art_prefix = _ab _art_suffix = f"?X-Plex-Token={_at}" if _at else '' def _resolve_thumb(url): """Make relative server thumb URLs absolute.""" if not url: return '' if url.startswith('http'): return url if url.startswith('/') and _art_prefix: return f"{_art_prefix}{url}{_art_suffix}" return url # Build art lookup from server tracks we already fetched (no extra DB queries) _server_art_map = {} for svr in server_tracks: if svr.get('thumb'): key = f"{(svr.get('artist') or '').lower().strip()}|{svr['title'].lower().strip()}" _server_art_map[key] = svr['thumb'] # Also store by title-only as fallback _server_art_map[svr['title'].lower().strip()] = svr['thumb'] for t in raw_tracks: img = t.get('image_url') or '' if not img: # Try artist+title first, fall back to title-only key = f"{(t.get('artist_name') or '').lower().strip()}|{(t.get('track_name') or '').lower().strip()}" img = _server_art_map.get(key, '') or _server_art_map.get((t.get('track_name') or '').lower().strip(), '') source_tracks.append({ 'name': t.get('track_name', ''), 'artist': t.get('artist_name', ''), 'album': t.get('album_name', ''), 'image_url': img, 'duration_ms': t.get('duration_ms', 0), 'position': t.get('position', 0), # Spotify track id — required for the user-confirmed # match override lookup (sync_match_cache). Null for # iTunes-only sources. 'source_track_id': t.get('source_track_id') or '', }) elif playlist_name: # Legacy fallback: cross-reference with sync history db = get_database() entries, _ = db.get_sync_history(page=1, limit=50) for entry in entries: if entry.get('playlist_name', '').lower() == playlist_name.lower(): full_entry = db.get_sync_history_entry(entry['id']) if full_entry: try: tr = json.loads(full_entry.get('track_results') or '[]') source_tracks = tr if isinstance(tr, list) else [] except (json.JSONDecodeError, TypeError): pass if not source_tracks: try: source_tracks = json.loads(full_entry.get('tracks_json') or '[]') except (json.JSONDecodeError, TypeError): pass break # Build combined view with two-pass matching (exact then fuzzy) import re as _re from difflib import SequenceMatcher def _norm_title(t): """Strip feat./ft., remaster, and edition qualifiers for comparison only.""" # feat./ft. — e.g. (feat. Artist), [ft. Artist] t = _re.sub(r'\s*[\(\[](?:feat|ft)\.?[^\)\]]*[\)\]]', '', t, flags=_re.IGNORECASE) # Remaster/Remastered — e.g. (2019 Remaster), (Remastered), (2019 Remastered Version) t = _re.sub(r'\s*[\(\[](?:\d{4}\s+)?remaster(?:ed)?(?:\s+version)?\s*[\)\]]', '', t, flags=_re.IGNORECASE) # Edition qualifiers — e.g. (Deluxe Edition), (Special Edition), [Anniversary Edition] t = _re.sub(r'\s*[\(\[](?:deluxe|special|anniversary|legacy|expanded|limited)(?:\s+edition)?\s*[\)\]]', '', t, flags=_re.IGNORECASE) return t.lower().strip() combined = [] used_server_indices = set() unmatched_source = [] # (index_in_combined, src_dict) for fuzzy second pass # Pass 0: User-confirmed match overrides from sync_match_cache. # When a user previously picked a local file via "Find & Add", # the (source_track_id → server_track_id) mapping was persisted # at confidence=1.0. Apply those FIRST so they bypass the # exact/fuzzy passes entirely. Stale-cache safe — if the cached # server track no longer exists, the override is silently # skipped and normal matching runs. from core.sync.match_overrides import resolve_match_overrides _db_for_overrides = get_database() _override_pairs = resolve_match_overrides( source_tracks, server_tracks, lambda src_id: ((_db_for_overrides.read_sync_match_cache(src_id, active_server) or {}).get('server_track_id')), ) # Pass 1: Exact title match (normalized — strips feat./ft. qualifiers) for i, src in enumerate(source_tracks): src_name = src.get('name', '') src_artist = src.get('artist', '') if not src_artist and src.get('artists'): a = src['artists'][0] if src['artists'] else '' src_artist = a.get('name', a) if isinstance(a, dict) else str(a) src_entry = { 'name': src_name, 'artist': src_artist, 'album': src.get('album', ''), 'image_url': src.get('image_url', ''), 'duration_ms': src.get('duration_ms', 0), 'position': src.get('position', i), } # Override hit — paired by user, skip exact/fuzzy matching. if i in _override_pairs: j_override = _override_pairs[i] used_server_indices.add(j_override) combined.append({ 'source_track': src_entry, 'server_track': server_tracks[j_override], 'match_status': 'matched', 'confidence': 1.0, 'override': True, }) continue src_norm = _norm_title(src_name) best_idx = -1 for j, svr in enumerate(server_tracks): if j in used_server_indices: continue if _norm_title(svr['title']) == src_norm: best_idx = j break if best_idx >= 0: used_server_indices.add(best_idx) combined.append({ 'source_track': src_entry, 'server_track': server_tracks[best_idx], 'match_status': 'matched', 'confidence': 1.0, }) else: idx = len(combined) combined.append({ 'source_track': src_entry, 'server_track': None, 'match_status': 'missing', 'confidence': 0.0, }) unmatched_source.append((idx, src_entry)) # Pass 2: Fuzzy match on remaining unmatched source tracks (normalized keys) for combo_idx, src_entry in unmatched_source: src_key = f"{src_entry['artist']} {_norm_title(src_entry['name'])}".strip() best_score = 0.0 best_j = -1 for j, svr in enumerate(server_tracks): if j in used_server_indices: continue svr_key = f"{svr['artist']} {_norm_title(svr['title'])}".strip().lower() score = SequenceMatcher(None, src_key.lower(), svr_key).ratio() if score > best_score and score >= 0.75: best_score = score best_j = j if best_j >= 0: used_server_indices.add(best_j) combined[combo_idx] = { 'source_track': src_entry, 'server_track': server_tracks[best_j], 'match_status': 'matched', 'confidence': round(best_score, 3), } # Add server tracks that aren't in the source (extra tracks on server) for j, svr in enumerate(server_tracks): if j not in used_server_indices: combined.append({ 'source_track': None, 'server_track': svr, 'match_status': 'extra', 'confidence': 0.0, }) return jsonify({ "success": True, "server_type": active_server, "playlist_name": playlist_name, "tracks": combined, "server_track_count": len(server_tracks), "source_track_count": len(source_tracks), }) except Exception as e: logger.error(f"Error getting server playlist tracks: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/server/playlist//replace-track', methods=['POST']) def server_playlist_replace_track(playlist_id): """Replace a track in a server playlist. Rebuilds the playlist with the swap.""" try: data = request.get_json() old_track_id = data.get('old_track_id') new_track_id = data.get('new_track_id') playlist_name = data.get('playlist_name', '') if not old_track_id or not new_track_id: return jsonify({"success": False, "error": "old_track_id and new_track_id required"}), 400 if not playlist_name: return jsonify({"success": False, "error": "playlist_name required"}), 400 active_server = config_manager.get_active_media_server() if active_server == 'plex' and media_server_engine.client('plex'): # ID-first, name-fallback (Plex deletes + recreates on edit # so the cached rating key can be stale). plex_server = media_server_engine.client('plex').server raw_playlist = None try: raw_playlist = plex_server.fetchItem(int(playlist_id)) except Exception as e: logger.debug("plex playlist fetchItem failed: %s", e) if not raw_playlist and playlist_name: try: raw_playlist = plex_server.playlist(playlist_name) except Exception as e: logger.debug("plex playlist by-name lookup failed: %s", e) if not raw_playlist: logger.warning(f"[ServerPlaylist] replace-track: playlist not found by id={playlist_id} or name='{playlist_name}'") return jsonify({"success": False, "error": "Playlist not found on server"}), 404 # Build new track list with replacement new_tracks = [] replaced = False for item in raw_playlist.items(): if str(item.ratingKey) == str(old_track_id) and not replaced: new_item = media_server_engine.client('plex').server.fetchItem(int(new_track_id)) if new_item: new_tracks.append(new_item) replaced = True else: new_tracks.append(item) else: new_tracks.append(item) if replaced: # Delete old and recreate directly (avoid update_playlist's backup logic) raw_playlist.delete() from plexapi.playlist import Playlist new_pl = Playlist.create(media_server_engine.client('plex').server, playlist_name, items=new_tracks) return jsonify({"success": True, "message": "Track replaced", "new_playlist_id": str(new_pl.ratingKey)}) else: return jsonify({"success": False, "error": "Old track not found in playlist"}), 404 elif active_server == 'jellyfin' and media_server_engine.client('jellyfin'): current_tracks = media_server_engine.client('jellyfin').get_playlist_tracks(playlist_id) new_track_ids = [] replaced = False for t in (current_tracks or []): tid = str(t.ratingKey) if tid == str(old_track_id) and not replaced: new_track_ids.append(new_track_id) replaced = True else: new_track_ids.append(tid) if replaced: new_track_objs = [type('T', (), {'ratingKey': tid, 'title': ''})() for tid in new_track_ids] media_server_engine.client('jellyfin').update_playlist(playlist_name, new_track_objs) return jsonify({"success": True, "message": "Track replaced"}) return jsonify({"success": False, "error": "Old track not found"}), 404 elif active_server == 'navidrome' and media_server_engine.client('navidrome'): current_tracks = media_server_engine.client('navidrome').get_playlist_tracks(playlist_id) new_track_ids = [] replaced = False for t in (current_tracks or []): tid = str(t.ratingKey) if tid == str(old_track_id) and not replaced: new_track_ids.append(new_track_id) replaced = True else: new_track_ids.append(tid) if replaced: new_track_objs = [type('T', (), {'ratingKey': tid, 'title': ''})() for tid in new_track_ids] media_server_engine.client('navidrome').create_playlist(playlist_name, new_track_objs, playlist_id=playlist_id) return jsonify({"success": True, "message": "Track replaced"}) return jsonify({"success": False, "error": "Old track not found"}), 404 return jsonify({"success": False, "error": f"Unsupported server: {active_server}"}), 400 except Exception as e: logger.error(f"Error replacing track in server playlist: {e}", exc_info=True) return jsonify({"success": False, "error": str(e)}), 500 def _persist_find_and_add_match(source_track_id, server_source, server_track_id, server_track_title, source_title, source_artist): """Wrap match-override persistence with the active DB. No-op when source_track_id is missing (e.g. add to a non-mirrored playlist).""" if not source_track_id: return try: from core.sync.match_overrides import record_manual_match ok = record_manual_match( get_database(), source_track_id=source_track_id, server_source=server_source, server_track_id=server_track_id, server_track_title=server_track_title, source_title=source_title, source_artist=source_artist, ) if ok: logger.info(f"[ServerPlaylist] Persisted Find & Add override: {source_track_id} → {server_track_id} ({server_source})") except Exception as e: logger.warning(f"[ServerPlaylist] Failed to persist Find & Add override: {e}") @app.route('/api/server/playlist//add-track', methods=['POST']) def server_playlist_add_track(playlist_id): """Add a track to a server playlist at a specific position. When the optional `source_track_id` is provided (the Spotify track id from a mirrored playlist), the user's selection is also persisted to sync_match_cache so future syncs auto-match this source→server pair without requiring the user to re-trigger Find & Add. """ try: data = request.get_json() track_id = data.get('track_id') playlist_name = data.get('playlist_name', '') position = data.get('position') # 0-based index; None = append # Optional Spotify source track id — when present, the (source → # server) mapping is persisted as a hard match override. source_track_id = data.get('source_track_id') or '' source_title = data.get('source_title') or '' source_artist = data.get('source_artist') or '' server_track_title = data.get('server_track_title') or '' if not track_id: return jsonify({"success": False, "error": "track_id required"}), 400 if not playlist_name: return jsonify({"success": False, "error": "playlist_name required"}), 400 active_server = config_manager.get_active_media_server() if active_server == 'plex' and media_server_engine.client('plex'): # ID-first, name-fallback — Plex deletes + recreates playlists # on edit so the rating key the frontend cached can be stale. # The GET tracks endpoint uses the same lookup chain. plex_server = media_server_engine.client('plex').server raw_playlist = None try: raw_playlist = plex_server.fetchItem(int(playlist_id)) except Exception as e: logger.debug("plex playlist fetchItem failed: %s", e) if not raw_playlist and playlist_name: try: raw_playlist = plex_server.playlist(playlist_name) except Exception as e: logger.debug("plex playlist by-name lookup failed: %s", e) if not raw_playlist: logger.warning(f"[ServerPlaylist] add-track: playlist not found by id={playlist_id} or name='{playlist_name}'") return jsonify({"success": False, "error": "Playlist not found"}), 404 new_item = plex_server.fetchItem(int(track_id)) if not new_item: return jsonify({"success": False, "error": "Track not found on server"}), 404 logger.info(f"[ServerPlaylist] Adding track: '{new_item.title}' (ratingKey={new_item.ratingKey}) to playlist '{playlist_name}'") raw_playlist.addItems([new_item]) # Move to correct position if specified (addItems always appends to end) if position is not None: try: raw_playlist.reload() items = list(raw_playlist.items()) pos = max(0, min(int(position), len(items) - 1)) if pos == 0: raw_playlist.moveItem(items[-1]) # Move to first position elif pos < len(items) - 1: raw_playlist.moveItem(items[-1], after=items[pos - 1]) # else: already at end, no move needed logger.info(f"[ServerPlaylist] Moved track to position {pos}") except Exception as move_err: logger.warning(f"[ServerPlaylist] Could not reposition track: {move_err}") new_id = str(raw_playlist.ratingKey) logger.info(f"[ServerPlaylist] Added track to playlist, playlist ID: {new_id}") _persist_find_and_add_match(source_track_id, active_server, track_id, server_track_title or new_item.title, source_title, source_artist) return jsonify({"success": True, "message": "Track added", "new_playlist_id": new_id}) elif active_server == 'jellyfin' and media_server_engine.client('jellyfin'): current_tracks = media_server_engine.client('jellyfin').get_playlist_tracks(playlist_id) or [] track_ids = [str(t.ratingKey) for t in current_tracks] pos = max(0, min(int(position), len(track_ids))) if position is not None else len(track_ids) track_ids.insert(pos, track_id) new_track_objs = [type('T', (), {'ratingKey': tid, 'title': ''})() for tid in track_ids] media_server_engine.client('jellyfin').update_playlist(playlist_name, new_track_objs) _persist_find_and_add_match(source_track_id, active_server, track_id, server_track_title, source_title, source_artist) return jsonify({"success": True, "message": "Track added"}) elif active_server == 'navidrome' and media_server_engine.client('navidrome'): current_tracks = media_server_engine.client('navidrome').get_playlist_tracks(playlist_id) or [] track_ids = [str(t.ratingKey) for t in current_tracks] pos = max(0, min(int(position), len(track_ids))) if position is not None else len(track_ids) track_ids.insert(pos, track_id) new_track_objs = [type('T', (), {'ratingKey': tid, 'title': ''})() for tid in track_ids] media_server_engine.client('navidrome').create_playlist(playlist_name, new_track_objs, playlist_id=playlist_id) _persist_find_and_add_match(source_track_id, active_server, track_id, server_track_title, source_title, source_artist) return jsonify({"success": True, "message": "Track added"}) return jsonify({"success": False, "error": f"Unsupported server: {active_server}"}), 400 except Exception as e: logger.error(f"Error adding track to server playlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/server/playlist//remove-track', methods=['POST']) def server_playlist_remove_track(playlist_id): """Remove a track from a server playlist by its server track ID.""" try: data = request.get_json() remove_track_id = data.get('track_id') playlist_name = data.get('playlist_name', '') if not remove_track_id: return jsonify({"success": False, "error": "track_id required"}), 400 if not playlist_name: return jsonify({"success": False, "error": "playlist_name required"}), 400 active_server = config_manager.get_active_media_server() if active_server == 'plex' and media_server_engine.client('plex'): # ID-first, name-fallback (Plex deletes + recreates on edit # so the cached rating key can be stale). plex_server = media_server_engine.client('plex').server raw_playlist = None try: raw_playlist = plex_server.fetchItem(int(playlist_id)) except Exception as e: logger.debug("plex playlist fetchItem failed: %s", e) if not raw_playlist and playlist_name: try: raw_playlist = plex_server.playlist(playlist_name) except Exception as e: logger.debug("plex playlist by-name lookup failed: %s", e) if not raw_playlist: logger.warning(f"[ServerPlaylist] remove-track: playlist not found by id={playlist_id} or name='{playlist_name}'") return jsonify({"success": False, "error": "Playlist not found"}), 404 # Rebuild without the target track current_items = list(raw_playlist.items()) new_items = [item for item in current_items if str(item.ratingKey) != str(remove_track_id)] if len(new_items) == len(current_items): return jsonify({"success": False, "error": "Track not found in playlist"}), 404 raw_playlist.delete() if new_items: from plexapi.playlist import Playlist new_pl = Playlist.create(media_server_engine.client('plex').server, playlist_name, items=new_items) return jsonify({"success": True, "message": "Track removed", "new_playlist_id": str(new_pl.ratingKey)}) return jsonify({"success": True, "message": "Track removed (playlist now empty)"}) elif active_server == 'jellyfin' and media_server_engine.client('jellyfin'): current_tracks = media_server_engine.client('jellyfin').get_playlist_tracks(playlist_id) or [] new_ids = [str(t.ratingKey) for t in current_tracks if str(t.ratingKey) != str(remove_track_id)] if len(new_ids) == len(current_tracks): return jsonify({"success": False, "error": "Track not found in playlist"}), 404 new_track_objs = [type('T', (), {'ratingKey': tid, 'title': ''})() for tid in new_ids] media_server_engine.client('jellyfin').update_playlist(playlist_name, new_track_objs) return jsonify({"success": True, "message": "Track removed"}) elif active_server == 'navidrome' and media_server_engine.client('navidrome'): current_tracks = media_server_engine.client('navidrome').get_playlist_tracks(playlist_id) or [] new_ids = [str(t.ratingKey) for t in current_tracks if str(t.ratingKey) != str(remove_track_id)] if len(new_ids) == len(current_tracks): return jsonify({"success": False, "error": "Track not found in playlist"}), 404 new_track_objs = [type('T', (), {'ratingKey': tid, 'title': ''})() for tid in new_ids] media_server_engine.client('navidrome').create_playlist(playlist_name, new_track_objs, playlist_id=playlist_id) return jsonify({"success": True, "message": "Track removed"}) return jsonify({"success": False, "error": f"Unsupported server: {active_server}"}), 400 except Exception as e: logger.error(f"Error removing track from server playlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/search-tracks', methods=['GET']) def library_search_tracks(): """Search SoulSync's local database for tracks (for manual match correction).""" try: query = request.args.get('q', '').strip() limit = int(request.args.get('limit', 10)) if not query: return jsonify({"success": True, "tracks": []}) active_server = config_manager.get_active_media_server() database = get_database() # Build thumb URL resolver for this server _art_prefix = '' _art_suffix = '' if active_server == 'plex' and media_server_engine.client('plex') and media_server_engine.client('plex').server: _ab = getattr(media_server_engine.client('plex').server, '_baseurl', '') or '' _at = getattr(media_server_engine.client('plex').server, '_token', '') or '' if not _ab: _pc = config_manager.get_plex_config() _ab = (_pc.get('base_url', '') or '').rstrip('/') _at = _at or _pc.get('token', '') _art_prefix = _ab _art_suffix = f"?X-Plex-Token={_at}" if _at else '' def _resolve_search_thumb(url): if not url: return '' if url.startswith('http'): return url if url.startswith('/') and _art_prefix: return f"{_art_prefix}{url}{_art_suffix}" return url results = database.search_tracks(title=query, artist='', limit=limit, server_source=active_server) tracks = [] for t in results: tracks.append({ 'id': t.id, 'title': t.title, 'artist_name': t.artist_name, 'album_title': getattr(t, 'album_title', ''), 'album_thumb_url': _resolve_search_thumb(getattr(t, 'album_thumb_url', '')), 'file_path': getattr(t, 'file_path', ''), 'bitrate': getattr(t, 'bitrate', 0), 'duration': getattr(t, 'duration', 0), 'server_source': getattr(t, 'server_source', ''), }) return jsonify({"success": True, "tracks": tracks}) except Exception as e: logger.error(f"Error searching library tracks: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/playlists//start-missing-process', methods=['POST']) def start_missing_tracks_process(playlist_id): """ A single, robust endpoint to kick off the entire missing tracks workflow. It creates a batch and starts the master worker in the background. """ data = request.get_json() tracks = data.get('tracks', []) playlist_name = data.get('playlist_name', 'Unknown Playlist') force_download_all = data.get('force_download_all', False) playlist_folder_mode = data.get('playlist_folder_mode', False) wing_it = data.get('wing_it', False) # Get album/artist context for artist album downloads is_album_download = data.get('is_album_download', False) album_context = data.get('album_context', None) artist_context = data.get('artist_context', None) if not tracks: return jsonify({"success": False, "error": "No tracks provided"}), 400 # Log album context if provided if is_album_download and album_context and artist_context: logger.info(f"[Artist Album] Received album context: '{album_context.get('name')}' by '{artist_context.get('name')}' ({album_context.get('album_type', 'album')})") logger.info(f" Release: {album_context.get('release_date', 'Unknown')}, Tracks: {album_context.get('total_tracks', len(tracks))}") # Log playlist folder mode if enabled if playlist_folder_mode: logger.info(f"[Playlist Folder] Enabled for playlist: '{playlist_name}'") # Limit concurrent analysis processes to prevent resource exhaustion with tasks_lock: active_analysis_count = sum(1 for batch in download_batches.values() if batch.get('phase') == 'analysis') if active_analysis_count >= 3: # Allow max 3 concurrent analysis processes return jsonify({ "success": False, "error": "Too many analysis processes running. Please wait for one to complete." }), 429 batch_id = str(uuid.uuid4()) with tasks_lock: download_batches[batch_id] = { 'phase': 'analysis', 'playlist_id': playlist_id, 'playlist_name': playlist_name, 'queue': [], 'active_count': 0, 'max_concurrent': _get_batch_max_concurrent(is_album=is_album_download), # Track state management (replicating sync.py) 'permanently_failed_tracks': [], 'cancelled_tracks': set(), 'queue_index': 0, 'analysis_total': len(tracks), # Profile context for failed track wishlist re-adds 'profile_id': get_current_profile_id(), 'analysis_processed': 0, 'analysis_results': [], 'force_download_all': force_download_all, # Pass the force flag to the batch 'playlist_folder_mode': playlist_folder_mode, # Organize downloads by playlist folder # Album context for artist album downloads (explicit folder structure) 'is_album_download': is_album_download, 'album_context': album_context, 'artist_context': artist_context, 'wing_it': wing_it, } # Record sync history — derive source_page from context if playlist_id == 'wishlist': _source_page = 'wishlist' elif is_album_download: _source_page = 'album' elif playlist_id.startswith('youtube_'): _source_page = 'sync' else: _source_page = 'sync' _record_sync_history_start(batch_id, playlist_id, playlist_name, tracks, is_album_download, album_context, artist_context, playlist_folder_mode, source_page=_source_page) # Link YouTube playlist to download process if this is a YouTube playlist if playlist_id.startswith('youtube_'): url_hash = playlist_id.replace('youtube_', '') if url_hash in youtube_playlist_states: youtube_playlist_states[url_hash]['download_process_id'] = batch_id youtube_playlist_states[url_hash]['phase'] = 'downloading' youtube_playlist_states[url_hash]['converted_spotify_playlist_id'] = playlist_id logger.info(f"Linked YouTube playlist {url_hash} to download process {batch_id} (converted ID: {playlist_id})") # Link Tidal playlist to download process if this is a Tidal playlist if playlist_id.startswith('tidal_'): tidal_playlist_id = playlist_id.replace('tidal_', '') if tidal_playlist_id in tidal_discovery_states: tidal_discovery_states[tidal_playlist_id]['download_process_id'] = batch_id tidal_discovery_states[tidal_playlist_id]['phase'] = 'downloading' tidal_discovery_states[tidal_playlist_id]['converted_spotify_playlist_id'] = playlist_id logger.info(f"Linked Tidal playlist {tidal_playlist_id} to download process {batch_id} (converted ID: {playlist_id})") # Link Spotify Public playlist to download process if this is a Spotify Public playlist if playlist_id.startswith('spotify_public_'): sp_url_hash = playlist_id.replace('spotify_public_', '') if sp_url_hash in spotify_public_discovery_states: spotify_public_discovery_states[sp_url_hash]['download_process_id'] = batch_id spotify_public_discovery_states[sp_url_hash]['phase'] = 'downloading' spotify_public_discovery_states[sp_url_hash]['converted_spotify_playlist_id'] = playlist_id logger.info(f"Linked Spotify Public playlist {sp_url_hash} to download process {batch_id} (converted ID: {playlist_id})") # Link Deezer playlist to download process if this is a Deezer playlist if playlist_id.startswith('deezer_'): deezer_playlist_id = playlist_id.replace('deezer_', '') if deezer_playlist_id in deezer_discovery_states: deezer_discovery_states[deezer_playlist_id]['download_process_id'] = batch_id deezer_discovery_states[deezer_playlist_id]['phase'] = 'downloading' deezer_discovery_states[deezer_playlist_id]['converted_spotify_playlist_id'] = playlist_id logger.info(f"Linked Deezer playlist {deezer_playlist_id} to download process {batch_id} (converted ID: {playlist_id})") # Stamp original index to keep task indices aligned with frontend row order for i, track in enumerate(tracks): if '_original_index' not in track: track['_original_index'] = i missing_download_executor.submit(_run_full_missing_tracks_process, batch_id, playlist_id, tracks) return jsonify({ "success": True, "batch_id": batch_id }) @app.route('/api/tracks/download_missing', methods=['POST']) def start_missing_downloads(): """Legacy endpoint - redirect to new playlist-based endpoint""" dl_err = check_download_permission() if dl_err: return dl_err data = request.get_json() missing_tracks = data.get('missing_tracks', []) if not missing_tracks: return jsonify({"success": False, "error": "No missing tracks provided"}), 400 # Use a default playlist_id for legacy compatibility playlist_id = "legacy_modal" # Call the new endpoint logic directly try: batch_id = str(uuid.uuid4()) # Create task queue for this batch task_queue = [] with tasks_lock: # Initialize batch management download_batches[batch_id] = { 'queue': [], 'active_count': 0, 'max_concurrent': _get_max_concurrent(), 'queue_index': 0, # Track state management (replicating sync.py) 'permanently_failed_tracks': [], 'cancelled_tracks': set(), # Profile context for failed track wishlist re-adds 'profile_id': get_current_profile_id() } for track_index, track_data in enumerate(missing_tracks): task_id = str(uuid.uuid4()) download_tasks[task_id] = { 'status': 'pending', 'track_info': track_data, 'playlist_id': playlist_id, 'batch_id': batch_id, 'track_index': track_index, 'download_id': None, 'username': None } # Add to batch queue instead of submitting immediately download_batches[batch_id]['queue'].append(task_id) # Start the first batch of downloads (up to 3) _start_next_batch_of_downloads(batch_id) return jsonify({"success": True, "batch_id": batch_id, "message": f"Queued {len(missing_tracks)} downloads for processing."}) except Exception as e: logger.error(f"Error starting missing downloads: {e}") return jsonify({"success": False, "error": str(e)}), 500 # =============================== # == SYNC PAGE API == # =============================== def _load_sync_status_file(): """Load sync statuses from database.""" try: database = get_database() raw = database.get_preference('sync_statuses') if raw: data = json.loads(raw) return data return {} except Exception as e: logger.error(f"Error loading sync status: {e}") return {} def _save_sync_status_file(sync_statuses): """Save sync statuses to database.""" try: database = get_database() database.set_preference('sync_statuses', json.dumps(sync_statuses)) except Exception as e: logger.error(f"Error saving sync status: {e}") def _update_and_save_sync_status(playlist_id, playlist_name, playlist_owner, snapshot_id, **kwargs): """Updates the sync status for a given playlist and saves to file (same logic as GUI).""" try: # Load existing sync statuses sync_statuses = _load_sync_status_file() # Update this playlist's sync status from datetime import datetime now = datetime.now() status = { 'name': playlist_name, 'owner': playlist_owner, 'snapshot_id': snapshot_id, 'last_synced': now.isoformat() } # Store match counts and track hash for smart-skip on scheduled syncs for key in ('matched_tracks', 'total_tracks', 'discovered_tracks', 'tracks_hash'): if key in kwargs: status[key] = kwargs[key] sync_statuses[playlist_id] = status # Save to file _save_sync_status_file(sync_statuses) logger.info(f"Updated sync status for playlist '{playlist_name}' (ID: {playlist_id})") except Exception as e: logger.error(f"Error updating sync status for {playlist_id}: {e}") @app.route('/api/spotify/playlists', methods=['GET']) def get_spotify_playlists(): """Fetches all user playlists from Spotify and enriches them with local sync status.""" client = get_spotify_client_for_profile() if not client or not client.is_authenticated(): return jsonify({"error": "Spotify not authenticated."}), 401 try: playlists = client.get_user_playlists_metadata_only() sync_statuses = _load_sync_status_file() playlist_data = [] # Add regular playlists first for p in playlists: status_info = sync_statuses.get(p.id, {}) sync_status = "Never Synced" # Handle snapshot_id safely - may not exist in core Playlist class playlist_snapshot = getattr(p, 'snapshot_id', '') if 'last_synced' in status_info: stored_snapshot = status_info.get('snapshot_id') last_sync_time = datetime.fromisoformat(status_info['last_synced']).strftime('%b %d, %H:%M') if playlist_snapshot != stored_snapshot: sync_status = f"Last Sync: {last_sync_time}" logger.info( "Playlist sync status: name=%s id=%s snapshot=%r stored_snapshot=%r result=Needs Sync display=%s", p.name, p.id, playlist_snapshot, stored_snapshot, sync_status, ) else: sync_status = f"Synced: {last_sync_time}" logger.info( "Playlist sync status: name=%s id=%s snapshot=%r stored_snapshot=%r result=Synced display=%s", p.name, p.id, playlist_snapshot, stored_snapshot, sync_status, ) else: logger.warning( "Playlist sync status: name=%s id=%s snapshot=%r result=Never Synced display=%s", p.name, p.id, playlist_snapshot, sync_status, ) playlist_data.append({ "id": p.id, "name": p.name, "owner": p.owner, "track_count": p.total_tracks, "image_url": getattr(p, 'image_url', None), "sync_status": sync_status, "snapshot_id": playlist_snapshot }) # Add virtual "Liked Songs" playlist at the END (just count, no full fetch) try: liked_songs_count = spotify_client.get_saved_tracks_count() if liked_songs_count > 0: liked_songs_id = "spotify:liked-songs" status_info = sync_statuses.get(liked_songs_id, {}) sync_status = "Never Synced" if 'last_synced' in status_info: last_sync_time = datetime.fromisoformat(status_info['last_synced']).strftime('%b %d, %H:%M') sync_status = f"Synced: {last_sync_time}" # Get user info for owner name user_info = spotify_client.get_user_info() owner_name = user_info.get('display_name', 'You') if user_info else 'You' # Add Liked Songs as LAST playlist playlist_data.append({ "id": liked_songs_id, "name": "Liked Songs", "owner": owner_name, "track_count": liked_songs_count, "image_url": None, # Spotify doesn't provide image for Liked Songs "sync_status": sync_status, "snapshot_id": "" # Liked Songs doesn't have a snapshot_id }) logger.info(f"Added virtual 'Liked Songs' playlist with {liked_songs_count} tracks (count only)") except Exception as liked_error: logger.error(f"Failed to add Liked Songs playlist: {liked_error}") # Don't fail the entire request if Liked Songs fails return jsonify(playlist_data) except Exception as e: return jsonify({"error": str(e)}), 500 @app.route('/api/spotify/playlist/', methods=['GET']) def get_playlist_tracks(playlist_id): """Fetches full track details for a specific playlist.""" if not spotify_client or not spotify_client.is_authenticated(): return jsonify({"error": "Spotify not authenticated."}), 401 try: # Handle special "Liked Songs" virtual playlist if playlist_id == "spotify:liked-songs": user_info = spotify_client.get_user_info() owner_name = user_info.get('display_name', 'You') if user_info else 'You' # Fetch raw saved tracks with full album data tracks = [] limit = 50 offset = 0 while True: if _spotify_rate_limited(): return jsonify({"error": "Spotify is currently rate limited. Please try again later."}), 429 from core.api_call_tracker import api_call_tracker api_call_tracker.record_call('spotify', endpoint='current_user_saved_tracks') results = spotify_client.sp.current_user_saved_tracks(limit=limit, offset=offset) if not results or 'items' not in results: break for item in results['items']: if item['track'] and item['track']['id']: track_data = item['track'] tracks.append({ 'id': track_data['id'], 'name': track_data['name'], 'artists': track_data['artists'], # Full artist objects (matches Download Missing Tracks behavior) 'album': track_data['album'], # Full album object 'duration_ms': track_data['duration_ms'], 'popularity': track_data.get('popularity', 0), 'spotify_track_id': track_data['id'] }) if len(results['items']) < limit or not results.get('next'): break offset += limit # Create virtual playlist dict for Liked Songs playlist_dict = { 'id': 'spotify:liked-songs', 'name': 'Liked Songs', 'description': 'Your saved tracks on Spotify', 'owner': owner_name, 'public': False, 'collaborative': False, 'track_count': len(tracks), 'image_url': None, 'snapshot_id': '', 'tracks': tracks } return jsonify(playlist_dict) # Handle regular playlists if _spotify_rate_limited(): return jsonify({"error": "Spotify is currently rate limited. Please try again later."}), 429 # Fetch raw playlist data to preserve full album objects from core.api_call_tracker import api_call_tracker api_call_tracker.record_call('spotify', endpoint='playlist') playlist_data = spotify_client.sp.playlist(playlist_id) # Fetch all tracks with full album data tracks = [] try: results = spotify_client._get_playlist_items_page(playlist_id, limit=100) except Exception as items_err: # 403 on followed playlists — try the public embed scraper as fallback logger.warning(f"Playlist items fetch failed ({items_err}), trying public embed scraper") try: from core.spotify_public_scraper import scrape_spotify_embed embed_data = scrape_spotify_embed('playlist', playlist_id) if embed_data and not embed_data.get('error') and embed_data.get('tracks'): for t in embed_data['tracks']: artists = t.get('artists', []) tracks.append({ 'id': t.get('id', ''), 'name': t.get('name', ''), 'artists': artists if artists else [{'name': 'Unknown'}], 'album': {'name': '', 'images': []}, 'duration_ms': t.get('duration_ms', 0), 'popularity': 0, 'spotify_track_id': t.get('id', '') }) playlist_dict = { 'id': playlist_data['id'], 'name': playlist_data['name'], 'description': playlist_data.get('description', ''), 'owner': playlist_data['owner']['display_name'], 'public': playlist_data.get('public', False), 'collaborative': playlist_data.get('collaborative', False), 'track_count': len(tracks), 'image_url': playlist_data['images'][0]['url'] if playlist_data.get('images') else None, 'snapshot_id': playlist_data.get('snapshot_id', ''), 'tracks': tracks } return jsonify(playlist_dict) except Exception as scrape_err: logger.warning(f"Public embed scraper also failed: {scrape_err}") raise items_err # Re-raise original error if both failed while results: for item in results['items']: # Handle both old API ('track') and new Feb 2026 API ('item') field names track_data = item.get('track') or item.get('item') if track_data and track_data.get('id'): tracks.append({ 'id': track_data['id'], 'name': track_data['name'], 'artists': track_data['artists'], # Full artist objects (matches Download Missing Tracks behavior) 'album': track_data['album'], # Full album object with album_type, total_tracks, etc. 'duration_ms': track_data['duration_ms'], 'popularity': track_data.get('popularity', 0), 'spotify_track_id': track_data['id'] # Also include as spotify_track_id for consistency }) if results.get('next'): api_call_tracker.record_call('spotify', endpoint='playlist_tracks_page') results = spotify_client.sp.next(results) else: results = None # Convert playlist to dict playlist_dict = { 'id': playlist_data['id'], 'name': playlist_data['name'], 'description': playlist_data.get('description', ''), 'owner': playlist_data['owner']['display_name'], 'public': playlist_data.get('public', False), 'collaborative': playlist_data.get('collaborative', False), 'track_count': len(tracks), 'image_url': playlist_data['images'][0]['url'] if playlist_data.get('images') else None, 'snapshot_id': playlist_data.get('snapshot_id', ''), 'tracks': tracks } return jsonify(playlist_dict) except Exception as e: return jsonify({"error": str(e)}), 500 @app.route('/api/spotify/album/', methods=['GET']) def get_spotify_album_tracks(album_id): """Fetches full track details for a specific album.""" use_hydrabase = _is_hydrabase_active() # Try Hydrabase first when active — look up by album soul_id if use_hydrabase: album_name = request.args.get('name', '') album_artist = request.args.get('artist', '') try: hydra_tracks = hydrabase_client.get_album_tracks(album_id, limit=50) if hydra_tracks: track_items = [] for t in hydra_tracks: artist_list = t.artists if isinstance(t.artists, list) else [t.artists] if t.artists else [] track_items.append({ 'name': t.name, 'track_number': t.track_number or 0, 'disc_number': t.disc_number or 1, 'duration_ms': t.duration_ms, 'id': t.id, 'artists': [{'name': a} if isinstance(a, str) else a for a in artist_list], 'uri': '' }) return jsonify({ 'id': album_id, 'name': album_name or hydra_tracks[0].album or '', 'artists': [{'name': album_artist}] if album_artist else [], 'release_date': '', 'total_tracks': len(track_items), 'album_type': 'album', 'images': [], 'tracks': track_items }) except Exception as e: logger.warning(f"Hydrabase album_tracks failed for '{album_id}', falling back to Spotify: {e}") # Source override: when user clicked from a specific search tab source_override = request.args.get('source', '') if not spotify_client or not spotify_client.is_authenticated(): return jsonify({"error": "Spotify not authenticated."}), 401 try: # Use explicit source client when overridden (prevents numeric ID misrouting) client = spotify_client if source_override == 'itunes': client = _get_itunes_client() elif source_override == 'hydrabase': # Hydrabase IDs originate from whichever plugin the peer runs. # 'plugin' param is authoritative; fall back to ID format detection. plugin = request.args.get('plugin', '').lower() if plugin == 'itunes' or (not plugin and album_id.isdigit()): client = _get_itunes_client() elif plugin == 'deezer': client = _get_deezer_client() # else: spotify (default) elif source_override == 'deezer': client = _get_deezer_client() elif source_override == 'discogs': client = _get_discogs_client() elif source_override == 'musicbrainz': try: from core.musicbrainz_search import MusicBrainzSearchClient mb_search = MusicBrainzSearchClient() album_data = mb_search.get_album(album_id) if not album_data: return jsonify({"error": "Album not found on MusicBrainz"}), 404 return jsonify(album_data) except Exception as e: logger.error(f"MusicBrainz album detail failed: {e}") return jsonify({"error": str(e)}), 500 album_data = client.get_album(album_id) if not album_data: return jsonify({"error": "Album not found"}), 404 # Extract tracks from album data (Spotify format) tracks = album_data.get('tracks', {}).get('items', []) # If no tracks in album data (iTunes format), fetch them separately if not tracks: tracks_data = client.get_album_tracks(album_id) if tracks_data and 'items' in tracks_data: tracks = tracks_data['items'] # Format response album_dict = { 'id': album_data['id'], 'name': album_data['name'], 'artists': album_data.get('artists', []), 'release_date': album_data.get('release_date', ''), 'total_tracks': album_data.get('total_tracks', 0), 'album_type': album_data.get('album_type', 'album'), 'images': album_data.get('images', []), 'tracks': tracks } return jsonify(album_dict) except Exception as e: logger.error(f"Error fetching album tracks: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify/track/', methods=['GET']) def get_spotify_track(track_id): """Fetches full track details including album data for a specific track.""" # Try Hydrabase first when active and track name provided if _is_hydrabase_active(): track_name = request.args.get('name', '') track_artist = request.args.get('artist', '') if track_name: try: query = f"{track_artist} {track_name}".strip() if track_artist else track_name hydra_tracks = hydrabase_client.search_tracks(query, limit=1) if hydra_tracks: t = hydra_tracks[0] artist_list = t.artists if isinstance(t.artists, list) else [t.artists] if t.artists else [] return jsonify({ 'id': t.id, 'name': t.name, 'artists': [{'name': a} if isinstance(a, str) else a for a in artist_list], 'album': {'name': t.album, 'images': [{'url': t.image_url}] if t.image_url else []}, 'duration_ms': t.duration_ms, 'preview_url': t.preview_url, 'external_urls': t.external_urls or {}, 'popularity': t.popularity, }) except Exception as e: logger.warning(f"Hydrabase track lookup failed for '{track_name}', falling back to Spotify: {e}") if not spotify_client or not spotify_client.is_authenticated(): return jsonify({"error": "Spotify not authenticated."}), 401 try: track_data = spotify_client.get_track_details(track_id) if not track_data: return jsonify({"error": "Track not found"}), 404 return jsonify(track_data) except Exception as e: return jsonify({"error": str(e)}), 500 @app.route('/api/spotify/search', methods=['GET']) def search_spotify(): """Generic Spotify search endpoint - supports tracks, albums, artists""" use_hydrabase = _is_hydrabase_active() if not use_hydrabase: if not spotify_client or not spotify_client.is_authenticated(): return jsonify({"error": "Spotify not authenticated."}), 401 try: query = request.args.get('q', '').strip() search_type = request.args.get('type', 'track').strip() limit = int(request.args.get('limit', 20)) if not query: return jsonify({"error": "Query parameter 'q' is required"}), 400 if use_hydrabase: tracks = hydrabase_client.search_tracks(query, limit=limit) else: # Mirror to Hydrabase P2P network if hydrabase_worker and dev_mode_enabled: hydrabase_worker.enqueue(query, search_type) tracks = spotify_client.search_tracks(query, limit=limit) tracks_items = [{ 'id': t.id, 'name': t.name, 'artists': t.artists if isinstance(t.artists, list) else [t.artists], 'album': t.album, 'duration_ms': t.duration_ms, 'uri': f"spotify:track:{t.id}" } for t in tracks] return jsonify({'tracks': {'items': tracks_items}}) except Exception as e: logger.error(f"Error searching Spotify: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify/search_tracks', methods=['GET']) def search_spotify_tracks(): """Search for tracks on Spotify - used by discovery fix modal""" use_hydrabase = _is_hydrabase_active() if not use_hydrabase: if not spotify_client or not spotify_client.is_authenticated(): return jsonify({"error": "Spotify not authenticated."}), 401 try: # Support field-specific search params (track, artist) or legacy combined query track_q = request.args.get('track', '').strip() artist_q = request.args.get('artist', '').strip() legacy_query = request.args.get('query', '').strip() limit = int(request.args.get('limit', 20)) # Build Spotify field-filtered query if track_q or artist_q: parts = [] if track_q: parts.append(f'track:{track_q}') if artist_q: parts.append(f'artist:{artist_q}') query = ' '.join(parts) elif legacy_query: query = legacy_query else: return jsonify({"error": "Query parameter is required"}), 400 if use_hydrabase: tracks = hydrabase_client.search_tracks(query, limit=limit) else: if hydrabase_worker and dev_mode_enabled: hydrabase_worker.enqueue(query, 'tracks') tracks = spotify_client.search_tracks(query, limit=limit) # Local rerank — same helper Deezer + iTunes use. Spotify's # ranking is usually clean but karaoke / cover variants do # leak through; this is the safety net so all three sources # behave consistently from the user's perspective. if track_q or artist_q: from core.metadata.relevance import rerank_tracks tracks = rerank_tracks( tracks, expected_title=track_q, expected_artist=artist_q, ) tracks_dict = [{ 'id': t.id, 'name': t.name, 'artists': t.artists, 'album': t.album, 'duration_ms': t.duration_ms, 'image_url': getattr(t, 'image_url', None), } for t in tracks] return jsonify({'tracks': tracks_dict}) except Exception as e: logger.error(f"Error searching Spotify tracks: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/itunes/search_tracks', methods=['GET']) def search_itunes_tracks(): """Search for tracks on iTunes — used by the import-modal "Search for Match" dialog and by discovery-fix flows. iTunes API doesn't expose a field-scoped search syntax, so the query stays as a free-text join of track + artist. But the response often still contains karaoke / cover / tribute variants (just usually fewer than Deezer), so the same ``core.metadata.relevance.rerank_tracks`` pass applies. Boosts exact-artist-match + penalises known cover/karaoke patterns. """ try: # Support field-specific search params or legacy combined query track_q = request.args.get('track', '').strip() artist_q = request.args.get('artist', '').strip() legacy_query = request.args.get('query', '').strip() limit = int(request.args.get('limit', 20)) if track_q or artist_q: parts = [] if track_q: parts.append(track_q) if artist_q: parts.append(artist_q) query = ' '.join(parts) elif legacy_query: query = legacy_query else: return jsonify({"error": "Query parameter is required"}), 400 use_hydrabase = _is_hydrabase_active() if use_hydrabase: tracks = hydrabase_client.search_tracks(query, limit=limit) source = 'hydrabase' else: if hydrabase_worker and dev_mode_enabled: hydrabase_worker.enqueue(query, 'tracks') fallback_client = _get_metadata_fallback_client() tracks = fallback_client.search_tracks(query, limit=limit) source = _get_metadata_fallback_source() # Local rerank — same helper Deezer uses, applied wherever we # have an expected title/artist signal. Catches karaoke / cover # / tribute results that slip through iTunes's own ranking. if track_q or artist_q: from core.metadata.relevance import rerank_tracks tracks = rerank_tracks( tracks, expected_title=track_q, expected_artist=artist_q, ) tracks_dict = [{ 'id': t.id, 'name': t.name, 'artists': t.artists, 'album': t.album, 'duration_ms': t.duration_ms, 'image_url': t.image_url, 'source': source } for t in tracks] return jsonify({'tracks': tracks_dict}) except Exception as e: logger.error(f"Error searching iTunes tracks: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/search_tracks', methods=['GET']) def search_deezer_tracks(): """Search for tracks on Deezer — used by the import-modal "Search for Match" dialog and by discovery-fix flows. Issue #534: Deezer's free-text ranking buries canonical recordings under karaoke / cover / "originally performed by" variants in some regions. The fix here is the local relevance rerank (``core.metadata.relevance.rerank_tracks``) which penalises cover / karaoke / tribute / remaster patterns + boosts exact-artist-match. Catches the user-reported case (karaoke at top) and the inverse (live-version compilation noise) regardless of which Deezer region's ranking the user hits. Field-scoped advanced-syntax queries (`track:"X" artist:"Y"`) were initially considered as a second tightening layer, but live-API testing showed Deezer's advanced-query ranking has its own bias — e.g. it surfaced a 2008 Remaster on `track:"Dirty White Boy" artist:"Foreigner"` and didn't return the canonical Head Games cut at all. The free-text path actually returns the canonical recording first more reliably, so this endpoint stays free-text + local rerank. Client-level kwarg support remains in ``DeezerClient.search_tracks`` for future callers (e.g. exact-match flows where filtering is more important than ranking). """ try: track_q = request.args.get('track', '').strip() artist_q = request.args.get('artist', '').strip() legacy_query = request.args.get('query', '').strip() limit = int(request.args.get('limit', 20)) if track_q or artist_q: query = ' '.join(p for p in (track_q, artist_q) if p) elif legacy_query: query = legacy_query else: return jsonify({"error": "Query parameter is required"}), 400 client = _get_deezer_client() tracks = client.search_tracks(query, limit=limit) # Local rerank — only when we have an expected title/artist # signal. Free-text-only searches have nothing to rank against. if track_q or artist_q: from core.metadata.relevance import rerank_tracks tracks = rerank_tracks( tracks, expected_title=track_q, expected_artist=artist_q, ) tracks_dict = [{ 'id': t.id, 'name': t.name, 'artists': t.artists, 'album': t.album, 'duration_ms': t.duration_ms, 'image_url': getattr(t, 'image_url', None), 'source': 'deezer' } for t in tracks] return jsonify({'tracks': tracks_dict}) except Exception as e: logger.error(f"Error searching Deezer tracks: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/itunes/album/', methods=['GET']) def get_itunes_album_tracks(album_id): """Fetches full track details for a specific iTunes album.""" try: # Try Hydrabase first when active — look up by album soul_id if _is_hydrabase_active(): album_name = request.args.get('name', '') album_artist = request.args.get('artist', '') try: hydra_tracks = hydrabase_client.get_album_tracks(album_id, limit=50) if hydra_tracks: track_items = [] for t in hydra_tracks: artist_list = t.artists if isinstance(t.artists, list) else [t.artists] if t.artists else [] track_items.append({ 'name': t.name, 'track_number': t.track_number or 0, 'disc_number': t.disc_number or 1, 'duration_ms': t.duration_ms, 'id': t.id, 'artists': [{'name': a} if isinstance(a, str) else a for a in artist_list], 'uri': '' }) return jsonify({ 'id': album_id, 'name': album_name or hydra_tracks[0].album or '', 'artists': [{'name': album_artist}] if album_artist else [], 'release_date': '', 'total_tracks': len(track_items), 'album_type': 'album', 'images': [], 'tracks': track_items, 'source': 'hydrabase' }) except Exception as e: logger.warning(f"Hydrabase album_tracks failed for '{album_id}', falling back to iTunes: {e}") fallback_client = _get_metadata_fallback_client() album_data = fallback_client.get_album(album_id) if not album_data: return jsonify({"error": "Album not found"}), 404 # Get tracks for this album tracks_data = fallback_client.get_album_tracks(album_id) tracks = tracks_data.get('items', []) if tracks_data else [] # Format response to match Spotify structure for frontend compatibility album_dict = { 'id': album_data.get('id', album_id), 'name': album_data.get('name', 'Unknown Album'), 'artists': album_data.get('artists', []), 'release_date': album_data.get('release_date', ''), 'total_tracks': album_data.get('total_tracks', len(tracks)), 'album_type': album_data.get('album_type', 'album'), 'images': album_data.get('images', []), 'tracks': tracks, 'source': _get_metadata_fallback_source() } return jsonify(album_dict) except Exception as e: logger.error(f"Error fetching album tracks: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/discover/album//', methods=['GET']) def get_discover_album(source, album_id): """ Source-agnostic album endpoint for discover page. Fetches album from the appropriate source (spotify, itunes, or hydrabase when active). """ try: # Try Hydrabase first when active — look up by album soul_id if _is_hydrabase_active(): album_name = request.args.get('name', '') album_artist = request.args.get('artist', '') try: hydra_tracks = hydrabase_client.get_album_tracks(album_id, limit=50) if hydra_tracks: track_items = [] for t in hydra_tracks: artist_list = t.artists if isinstance(t.artists, list) else [t.artists] if t.artists else [] track_items.append({ 'name': t.name, 'track_number': t.track_number or 0, 'disc_number': t.disc_number or 1, 'duration_ms': t.duration_ms, 'id': t.id, 'artists': [{'name': a} if isinstance(a, str) else a for a in artist_list], 'uri': '' }) return jsonify({ 'id': album_id, 'name': album_name or hydra_tracks[0].album or '', 'artists': [{'name': album_artist}] if album_artist else [], 'release_date': '', 'total_tracks': len(track_items), 'album_type': 'album', 'images': [], 'tracks': track_items, 'source': 'hydrabase' }) except Exception as e: logger.warning(f"Hydrabase album_tracks failed for '{album_id}', falling back to {source}: {e}") if source == 'spotify': album_data = spotify_client.get_album(album_id) if spotify_client and spotify_client.is_authenticated() else None if album_data: tracks = album_data.get('tracks', {}).get('items', []) if not tracks: tracks_data = spotify_client.get_album_tracks(album_id) if tracks_data and 'items' in tracks_data: tracks = tracks_data['items'] return jsonify({ 'id': album_data['id'], 'name': album_data['name'], 'artists': album_data.get('artists', []), 'release_date': album_data.get('release_date', ''), 'total_tracks': album_data.get('total_tracks', 0), 'album_type': album_data.get('album_type', 'album'), 'images': album_data.get('images', []), 'tracks': tracks, 'source': 'spotify' }) # Spotify failed (not authenticated, album removed, rate limited) — try fallback album_name = request.args.get('name', '') album_artist = request.args.get('artist', '') fallback = _get_metadata_fallback_client() if fallback and (album_name or album_artist): clean_name = album_name.replace(' - Single', '').replace(' - EP', '').replace(' (Single)', '').strip() search_query = f"{album_artist} {clean_name}" if album_artist else clean_name try: results = fallback.search_albums(search_query, limit=3) for r in (results or []): tracks_data = fallback.get_album_tracks(str(r.id)) tracks = tracks_data.get('items', []) if tracks_data else [] if tracks: return jsonify({ 'id': str(r.id), 'name': r.name, 'artists': [{'name': getattr(r, 'artist', album_artist) or album_artist}], 'release_date': getattr(r, 'release_date', '') or '', 'total_tracks': getattr(r, 'total_tracks', len(tracks)), 'album_type': getattr(r, 'album_type', 'album') or 'album', 'images': [{'url': r.image_url}] if getattr(r, 'image_url', None) else [], 'tracks': tracks, 'source': _get_metadata_fallback_source(), }) except Exception as e: logger.debug(f"Fallback album resolve failed: {e}") return jsonify({"error": "Album not found"}), 404 elif source in ('itunes', 'deezer'): # Use the source-specific client, not just the active fallback if source == 'deezer': fallback_client = _get_deezer_client() fallback_source = 'deezer' else: fallback_client = _get_itunes_client() fallback_source = 'itunes' album_data = fallback_client.get_album(album_id) # If ID doesn't resolve (cross-source ID), search by name+artist if not album_data: album_name = request.args.get('name', '') album_artist = request.args.get('artist', '') if album_name or album_artist: clean_name = album_name.replace(' - Single', '').replace(' - EP', '').replace(' (Single)', '').strip() search_query = f"{album_artist} {clean_name}" if album_artist else clean_name try: results = fallback_client.search_albums(search_query, limit=3) for r in (results or []): tracks_data = fallback_client.get_album_tracks(str(r.id)) tracks = tracks_data.get('items', []) if tracks_data else [] if tracks: return jsonify({ 'id': str(r.id), 'name': r.name, 'artists': [{'name': getattr(r, 'artist', album_artist) or album_artist}], 'release_date': getattr(r, 'release_date', '') or '', 'total_tracks': getattr(r, 'total_tracks', len(tracks)), 'album_type': getattr(r, 'album_type', 'album') or 'album', 'images': [{'url': r.image_url}] if getattr(r, 'image_url', None) else [], 'tracks': tracks, 'source': fallback_source, }) except Exception as e: logger.debug(f"Fallback album name search failed: {e}") if not album_data: return jsonify({"error": "Album not found"}), 404 tracks_data = fallback_client.get_album_tracks(album_id) tracks = tracks_data.get('items', []) if tracks_data else [] return jsonify({ 'id': album_data.get('id', album_id), 'name': album_data.get('name', 'Unknown Album'), 'artists': album_data.get('artists', []), 'release_date': album_data.get('release_date', ''), 'total_tracks': album_data.get('total_tracks', len(tracks)), 'album_type': album_data.get('album_type', 'album'), 'images': album_data.get('images', []), 'tracks': tracks, 'source': fallback_source, }) elif source == 'tidal': # Tidal albums from Your Albums (sourced via the V2 user- # collection endpoint). Two-call resolution: get_album for # metadata, get_album_tracks for the cursor-paginated # tracklist. `get_album_tracks` returns `Track` objects # with `track_number` / `disc_number` annotated so the # download modal renders in album order across multi-disc # releases. Serialise to the same shape Spotify/Deezer # return so the frontend track-mapping stays uniform. if not tidal_client or not tidal_client.is_authenticated(): return jsonify({"error": "Tidal not authenticated"}), 401 album_meta = tidal_client.get_album(album_id) tidal_tracks = tidal_client.get_album_tracks(album_id) if not album_meta and not tidal_tracks: return jsonify({"error": "Tidal album not found"}), 404 album_name = (album_meta or {}).get('title') or request.args.get('name', '') release_date = (album_meta or {}).get('releaseDate', '') total_tracks = (album_meta or {}).get('numberOfItems') or len(tidal_tracks) album_artist_name = request.args.get('artist', '') # Build cover image URL from the album metadata. Tidal # exposes cover art via the `coverArt` relationship which # `get_album` doesn't fetch (it's a one-shot attributes # call). Best-effort: request it inline. cover_url = '' try: cover_resp = tidal_client.session.get( f"{tidal_client.base_url}/albums/{album_id}", params={'countryCode': 'US', 'include': 'coverArt'}, headers={'accept': 'application/vnd.api+json'}, timeout=10, ) if cover_resp.status_code == 200: payload = cover_resp.json() _, artworks = tidal_client._build_included_maps(payload.get('included', [])) cover_rel = (payload.get('data') or {}).get('relationships', {}).get('coverArt', {}) cover_url = tidal_client._first_artwork_url(cover_rel, artworks) or '' except Exception as e: logger.debug(f"Tidal cover-art resolve failed for album {album_id}: {e}") tracks_out = [] for t in tidal_tracks: tracks_out.append({ 'id': t.id, 'name': t.name, 'artists': [{'name': a} for a in (t.artists or [])], 'duration_ms': t.duration_ms, 'track_number': getattr(t, 'track_number', 0), 'disc_number': getattr(t, 'disc_number', 1), }) # Album-level artist name preference: explicit ?artist= # query (passed by frontend with the saved-album row) wins # over guessing from the first track. The saved-album row # already resolved the canonical artist via the V2 # collection endpoint. if not album_artist_name and tidal_tracks: first_artists = tidal_tracks[0].artists or [] album_artist_name = first_artists[0] if first_artists else '' return jsonify({ 'id': album_id, 'name': album_name or 'Unknown Album', 'artists': [{'name': album_artist_name}] if album_artist_name else [], 'release_date': release_date, 'total_tracks': total_tracks, 'album_type': 'album', 'images': [{'url': cover_url}] if cover_url else [], 'tracks': tracks_out, 'source': 'tidal', }) elif source == 'discogs': # Discogs release detail. release_id comes from the Your # Albums Discogs source. Tracklist needs normalizing — # Discogs uses {position, title, duration} (duration as # string like "3:45") so map to the standard # {name, track_number, duration_ms, artists} shape the # download modal expects. from core.discogs_client import DiscogsClient try: rel_id = int(album_id) except (TypeError, ValueError): return jsonify({"error": "Invalid Discogs release id"}), 400 release = DiscogsClient().get_release(rel_id) if not release: return jsonify({"error": "Discogs release not found"}), 404 import re as _re _disambig_re = _re.compile(r'\s*\(\d+\)$') artists_raw = release.get('artists') or [] artist_names = [] for a in artists_raw: name = (a.get('name') or '').strip() if isinstance(a, dict) else str(a) # Strip Discogs disambiguation suffix "(N)" name = _disambig_re.sub('', name) if name: artist_names.append({'name': name}) tracks_out = [] for idx, t in enumerate(release.get('tracklist', []) or [], start=1): if not isinstance(t, dict): continue title = (t.get('title') or '').strip() if not title: continue # Discogs duration: "3:45" or "1:23:45". Convert to ms. dur_ms = 0 dur_str = (t.get('duration') or '').strip() if dur_str: try: parts = [int(p) for p in dur_str.split(':')] if len(parts) == 2: dur_ms = (parts[0] * 60 + parts[1]) * 1000 elif len(parts) == 3: dur_ms = (parts[0] * 3600 + parts[1] * 60 + parts[2]) * 1000 except (ValueError, TypeError): dur_ms = 0 tracks_out.append({ 'id': f"discogs_{rel_id}_{idx}", 'name': title, 'track_number': idx, 'duration_ms': dur_ms, 'artists': artist_names, }) images = release.get('images') or [] cover_url = '' if images and isinstance(images[0], dict): cover_url = images[0].get('uri') or images[0].get('uri150') or '' year = release.get('year') release_date = str(year) if year and int(year) > 0 else '' return jsonify({ 'id': str(rel_id), 'name': release.get('title', ''), 'artists': artist_names, 'release_date': release_date, 'total_tracks': len(tracks_out), 'album_type': 'album', 'images': [{'url': cover_url}] if cover_url else [], 'tracks': tracks_out, 'source': 'discogs', }) else: return jsonify({"error": f"Unknown source: {source}"}), 400 except Exception as e: logger.error(f"Error fetching discover album: {e}") return jsonify({"error": str(e)}), 500 # =================================================================== # HIFI DOWNLOAD ENDPOINTS # =================================================================== @app.route('/api/hifi/status', methods=['GET']) def hifi_status(): """Check if HiFi API instances are reachable.""" try: hifi = download_orchestrator.client("hifi") available = hifi.is_available() version = hifi.get_version() if available else None return jsonify({ "available": available, "version": version, "instance": hifi._get_instance(), }) except Exception as e: return jsonify({"available": False, "error": str(e)}) @app.route('/api/soundcloud/status', methods=['GET']) def soundcloud_status(): """Report SoundCloud client availability + a quick reachability probe. SoundCloud anonymous mode needs no credentials, so "configured" is really "yt-dlp is installed and SoundCloud responds to a search." The check fans out a real (cheap) yt-dlp call so the settings page's Test Connection button gives a meaningful pass/fail signal instead of just verifying the import succeeded. """ try: sc = download_orchestrator.client("soundcloud") if download_orchestrator and hasattr(download_orchestrator, 'client') else None if not sc: return jsonify({ "available": False, "configured": False, "error": "SoundCloud client not initialized — check yt-dlp install", }) if not sc.is_available(): return jsonify({ "available": False, "configured": False, "error": "yt-dlp not installed", }) reachable = run_async(sc.check_connection()) return jsonify({ "available": True, "configured": True, "reachable": bool(reachable), }) except Exception as exc: return jsonify({"available": False, "configured": False, "error": str(exc)}) @app.route('/api/hifi/instances', methods=['GET']) def hifi_instances(): """Check availability of all HiFi API instances.""" import requests as req try: hifi = download_orchestrator.client("hifi") instances = list(hifi._instances) results = [] for url in instances: entry = {'url': url, 'status': 'unknown', 'version': None, 'can_search': False, 'can_download': False} try: # Check root for version r = req.get(f'{url}/', timeout=5, headers={'Accept': 'application/json'}) if r.ok: data = r.json() entry['version'] = data.get('version') entry['status'] = 'online' # Check search sr = req.get(f'{url}/search', params={'s': 'test', 'limit': 1}, timeout=5) entry['can_search'] = sr.ok # Check track (download capability) tr = req.get(f'{url}/track', params={'id': '1550546', 'quality': 'LOSSLESS'}, timeout=5) entry['can_download'] = tr.ok if not tr.ok: entry['download_error'] = f'HTTP {tr.status_code}' else: entry['status'] = f'error (HTTP {r.status_code})' except req.exceptions.SSLError: entry['status'] = 'ssl_error' except req.exceptions.ConnectTimeout: entry['status'] = 'timeout' except req.exceptions.ConnectionError: entry['status'] = 'offline' except Exception as e: entry['status'] = f'error ({type(e).__name__})' results.append(entry) return jsonify({'instances': results, 'active': hifi._get_instance()}) except Exception as e: return jsonify({'error': str(e)}), 500 @app.route('/api/hifi/instances', methods=['POST']) @admin_only def hifi_add_instance(): """Add a new HiFi API instance.""" try: data = request.get_json() or {} url = data.get('url', '').strip().rstrip('/') if not url: return jsonify({'success': False, 'error': 'URL is required'}), 400 if not url.startswith(('http://', 'https://')): return jsonify({'success': False, 'error': 'URL must start with http:// or https://'}), 400 from database.music_database import get_database db = get_database() # Get current count to assign next priority existing = db.get_all_hifi_instances() priority = len(existing) added = db.add_hifi_instance(url, priority) if not added: return jsonify({'success': False, 'error': 'Instance already exists'}), 400 # Reload the HiFi client if download_orchestrator: download_orchestrator.reload_instances('hifi') return jsonify({'success': True, 'url': url}) except Exception as e: logger.error(f"Error adding HiFi instance: {e}") return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/hifi/instances', methods=['DELETE']) @admin_only def hifi_remove_instance(): """Remove a HiFi API instance.""" try: url = (request.args.get('url') or '').strip().rstrip('/') if not url: return jsonify({'success': False, 'error': 'URL is required'}), 400 from database.music_database import get_database db = get_database() removed = db.remove_hifi_instance(url) if not removed: return jsonify({'success': False, 'error': 'Instance not found'}), 404 # Reload the HiFi client if download_orchestrator: download_orchestrator.reload_instances('hifi') return jsonify({'success': True, 'url': url}) except Exception as e: logger.error(f"Error removing HiFi instance: {e}") return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/hifi/instances/toggle', methods=['POST']) @admin_only def hifi_toggle_instance(): """Toggle enabled state of a HiFi API instance.""" try: data = request.get_json() or {} url = data.get('url', '').strip().rstrip('/') enabled = data.get('enabled', True) if not url: return jsonify({'success': False, 'error': 'URL is required'}), 400 from database.music_database import get_database db = get_database() db.toggle_hifi_instance(url, enabled) if download_orchestrator: download_orchestrator.reload_instances('hifi') return jsonify({'success': True}) except Exception as e: logger.error(f"Error toggling HiFi instance: {e}") return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/hifi/instances/reorder', methods=['POST']) @admin_only def hifi_reorder_instances(): """Reorder HiFi API instances.""" try: data = request.get_json() or {} urls = data.get('urls', []) if not urls: return jsonify({'success': False, 'error': 'URL list is required'}), 400 from database.music_database import get_database db = get_database() if not db.reorder_hifi_instances(urls): return jsonify({'success': False, 'error': 'One or more URLs not found'}), 400 # Reload the HiFi client if download_orchestrator: download_orchestrator.reload_instances('hifi') return jsonify({'success': True}) except Exception as e: logger.error(f"Error reordering HiFi instances: {e}") return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/hifi/instances/list', methods=['GET']) @admin_only def hifi_list_instances(): """Get editable list of HiFi API instances.""" try: from database.music_database import get_database from core.hifi_client import DEFAULT_INSTANCES db = get_database() db.seed_hifi_instances(DEFAULT_INSTANCES) instances = db.get_all_hifi_instances() return jsonify({'instances': instances}) except Exception as e: logger.error(f"Error listing HiFi instances: {e}") return jsonify({'error': str(e)}), 500 # =================================================================== # DEEZER DOWNLOAD ENDPOINTS # =================================================================== @app.route('/api/deezer-download/test', methods=['POST']) def deezer_download_test(): """Test Deezer ARL token authentication.""" try: data = request.get_json() or {} arl = data.get('arl', '') if not arl: return jsonify({'success': False, 'error': 'No ARL token provided'}) import requests as req import threading session = req.Session() session.headers.update({ 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 ' '(KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36', 'Accept-Language': 'en-US,en;q=0.9', }) session.cookies.set('arl', arl) resp = session.post( 'https://www.deezer.com/ajax/gw-light.php', params={'method': 'deezer.getUserData', 'api_version': '1.0', 'api_token': 'null'}, json={}, timeout=15 ) logger.debug(f"Deezer test raw response status={resp.status_code}, body_preview={resp.text[:500]}") resp.raise_for_status() result = resp.json().get('results', {}) user = result.get('USER', {}) user_id = user.get('USER_ID', 0) logger.info(f"Deezer test: USER_ID={user_id}, keys={list(result.keys())}, user_keys={list(user.keys()) if user else 'none'}") if not user_id or user_id == 0: # Log more detail for debugging error_info = result.get('error', result.get('ERROR', '')) logger.warning(f"Deezer ARL test failed — USER_ID={user_id}, error={error_info}, response_keys={list(result.keys())}") return jsonify({'success': False, 'error': f'Invalid ARL token — Deezer returned no user (USER_ID={user_id})'}) user_name = user.get('BLOG_NAME', 'Unknown') options = user.get('OPTIONS', {}) can_lossless = options.get('web_lossless', False) can_hq = options.get('web_hq', False) tier = 'HiFi' if can_lossless else ('Premium' if can_hq else 'Free') return jsonify({'success': True, 'user': user_name, 'tier': tier}) except Exception as e: logger.error(f"Deezer download test failed: {e}") return jsonify({'success': False, 'error': str(e)}) @app.route('/api/deezer-download/test-search', methods=['GET']) def deezer_download_test_search(): """Test Deezer download search (temporary testing endpoint).""" try: query = request.args.get('q', '') if not query: return jsonify({'success': False, 'error': 'No query provided'}) arl = config_manager.get('deezer_download.arl', '') if not arl: return jsonify({'success': False, 'error': 'No ARL configured'}) from core.deezer_download_client import DeezerDownloadClient client = DeezerDownloadClient() if not client.is_authenticated(): client.reconnect(arl) if not client.is_authenticated(): return jsonify({'success': False, 'error': 'Authentication failed'}) tracks, albums = client._search_sync(query) results = [] for t in tracks[:10]: results.append({ 'title': t.title, 'artist': t.artist, 'album': t.album, 'quality': t.quality, 'bitrate': t.bitrate, 'duration_ms': t.duration, 'size': t.size, 'filename': t.filename, }) return jsonify({'success': True, 'count': len(tracks), 'results': results}) except Exception as e: logger.error(f"Deezer search test failed: {e}") return jsonify({'success': False, 'error': str(e)}) @app.route('/api/deezer-download/test-download', methods=['POST']) def deezer_download_test_download(): """Test Deezer download of a single track (temporary testing endpoint).""" try: data = request.get_json() or {} filename = data.get('filename', '') if not filename: return jsonify({'success': False, 'error': 'No filename provided (use track_id||display_name format)'}) arl = config_manager.get('deezer_download.arl', '') if not arl: return jsonify({'success': False, 'error': 'No ARL configured'}) from core.deezer_download_client import DeezerDownloadClient client = DeezerDownloadClient() if not client.is_authenticated(): client.reconnect(arl) if not client.is_authenticated(): return jsonify({'success': False, 'error': 'Authentication failed'}) download_id = run_async(client.download('deezer_dl', filename)) if not download_id: return jsonify({'success': False, 'error': 'Download failed to start'}) return jsonify({'success': True, 'download_id': download_id, 'message': 'Download started — check logs'}) except Exception as e: logger.error(f"Deezer download test failed: {e}") return jsonify({'success': False, 'error': str(e)}) # =================================================================== # TIDAL DOWNLOAD AUTH ENDPOINTS # =================================================================== def _get_tidal_download_client(): """Get Tidal download client from the orchestrator, with helpful error if unavailable.""" if not download_orchestrator: raise RuntimeError("Download orchestrator not initialized — check startup logs for errors") tidal = download_orchestrator.client("tidal") if hasattr(download_orchestrator, 'client') else None if not tidal: raise RuntimeError("Tidal download client not available — ensure tidalapi is installed") return tidal @app.route('/api/tidal/download/auth/start', methods=['POST']) def tidal_download_auth_start(): """Start Tidal device-code OAuth flow for download client.""" try: tidal_dl = _get_tidal_download_client() result = tidal_dl.start_device_auth() if result: return jsonify({"success": True, **result}) else: return jsonify({"error": "Failed to start Tidal auth. Is tidalapi installed?"}), 500 except Exception as e: return jsonify({"error": f"Failed to start Tidal auth: {e}"}), 500 @app.route('/api/tidal/download/auth/check', methods=['GET']) def tidal_download_auth_check(): """Check status of Tidal device-code OAuth flow.""" try: tidal_dl = _get_tidal_download_client() result = tidal_dl.check_device_auth() return jsonify(result) except Exception as e: return jsonify({"status": "error", "message": str(e)}), 500 @app.route('/api/tidal/download/auth/status', methods=['GET']) def tidal_download_auth_status(): """Check if Tidal download client is authenticated.""" try: tidal_dl = _get_tidal_download_client() authenticated = tidal_dl.is_authenticated() return jsonify({"authenticated": authenticated}) except Exception as e: return jsonify({"authenticated": False, "error": str(e)}) # =================================================================== # QOBUZ AUTH ENDPOINTS # =================================================================== def _sync_qobuz_credentials_to_worker(): """Push the just-saved Qobuz session into the enrichment worker's QobuzClient. Two separate client instances run side by side (one for the auth endpoints, one for the worker thread); without this sync the worker's instance never sees the new token until the next process restart, which is what made the dashboard indicator stay yellow and the connection test return ``Qobuz not authenticated`` after a successful Connect.""" try: worker = qobuz_enrichment_worker if 'qobuz_enrichment_worker' in globals() else None if worker and getattr(worker, 'client', None): worker.client.reload_credentials() except Exception as e: logger.debug(f"Could not sync Qobuz credentials to enrichment worker: {e}") @app.route('/api/qobuz/auth/login', methods=['POST']) def qobuz_auth_login(): """Login to Qobuz with email/password.""" try: data = request.get_json() email = data.get('email', '').strip() password = data.get('password', '').strip() if not email or not password: return jsonify({"success": False, "error": "Email and password required"}), 400 qobuz = download_orchestrator.client("qobuz") result = qobuz.login(email, password) if result['status'] == 'success': _sync_qobuz_credentials_to_worker() return jsonify({"success": True, **result}) else: return jsonify({"success": False, "error": result.get('message', 'Login failed')}), 400 except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/qobuz/auth/token', methods=['POST']) def qobuz_auth_token(): """Login to Qobuz with a pasted user_auth_token (bypasses CAPTCHA).""" try: data = request.get_json() token = data.get('token', '').strip() if not token: return jsonify({"success": False, "error": "Auth token required"}), 400 qobuz = download_orchestrator.client("qobuz") result = qobuz.login_with_token(token) if result['status'] == 'success': _sync_qobuz_credentials_to_worker() return jsonify({"success": True, **result}) else: return jsonify({"success": False, "error": result.get('message', 'Token login failed')}), 400 except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/qobuz/auth/status', methods=['GET']) def qobuz_auth_status(): """Check if Qobuz client is authenticated.""" try: qobuz = download_orchestrator.client("qobuz") authenticated = qobuz.is_authenticated() user_info = {} if authenticated and qobuz.user_info: user_info = { 'display_name': qobuz.user_info.get('display_name', ''), 'subscription': qobuz.user_info.get('credential', {}).get('label', 'Unknown'), } return jsonify({"authenticated": authenticated, "user": user_info}) except Exception as e: return jsonify({"authenticated": False, "error": str(e)}) @app.route('/api/qobuz/auth/logout', methods=['POST']) def qobuz_auth_logout(): """Logout from Qobuz.""" try: download_orchestrator.client("qobuz").logout() _sync_qobuz_credentials_to_worker() return jsonify({"success": True}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 # =================================================================== # TIDAL PLAYLIST API ENDPOINTS # =================================================================== @app.route('/api/tidal/disconnect', methods=['POST']) def tidal_disconnect(): """Clear saved Tidal auth state. Use when re-authentication doesn't pick up newly-added scopes (e.g. existing token predates a scope expansion and `prompt=consent` alone isn't enough to force fresh consent on this user's auth flow).""" if not tidal_client: return jsonify({"error": "Tidal client not available."}), 500 try: tidal_client.disconnect() return jsonify({ 'success': True, 'message': 'Tidal disconnected. Re-authenticate from Settings → Connections.', 'authenticated': False, }) except Exception as e: logger.error(f"Tidal disconnect error: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/tidal/playlists', methods=['GET']) def get_tidal_playlists(): """Fetches all user playlists from Tidal with full track data (like sync.py).""" if not tidal_client or not tidal_client.is_authenticated(): return jsonify({"error": "Tidal not authenticated."}), 401 try: # Use same method as sync.py - this already includes all track data playlists = tidal_client.get_user_playlists_metadata_only() playlist_data = [] for p in playlists: # Get track count from metadata (set during listing) or actual tracks track_count = getattr(p, 'track_count', 0) or (len(p.tracks) if hasattr(p, 'tracks') and p.tracks else 0) playlist_dict = { "id": p.id, "name": p.name, "owner": getattr(p, 'owner', 'Unknown'), "track_count": track_count, "image_url": getattr(p, 'image_url', None), "description": getattr(p, 'description', ''), "tracks": [] # Add tracks data like sync.py } # Include full track data if available (like sync.py has) if hasattr(p, 'tracks') and p.tracks: playlist_dict['tracks'] = [{ 'id': t.id, 'name': t.name, 'artists': t.artists or [], 'album': getattr(t, 'album', 'Unknown Album'), 'duration_ms': getattr(t, 'duration_ms', 0), 'track_number': getattr(t, 'track_number', 0) } for t in p.tracks] playlist_data.append(playlist_dict) # Append virtual "Favorite Tracks" playlist at the END (mirrors # Spotify's "Liked Songs" treatment — count-only here, full # track fetch deferred to the per-playlist detail endpoint). # When the saved Tidal token doesn't have `collection.read` # scope (existing tokens predate the scope expansion), the # endpoint returns 401 — we still surface the entry but with # a `needs_reconnect` flag + a reconnect-hint name so the user # has something visible to act on instead of a silently missing # row. try: from core.tidal_client import ( COLLECTION_PLAYLIST_ID, COLLECTION_PLAYLIST_NAME, COLLECTION_PLAYLIST_DESCRIPTION, ) collection_count = tidal_client.get_collection_tracks_count() needs_reconnect = tidal_client.collection_needs_reconnect() if needs_reconnect: playlist_data.append({ "id": COLLECTION_PLAYLIST_ID, "name": f"{COLLECTION_PLAYLIST_NAME} (reconnect Tidal to enable)", "owner": "You", "track_count": 0, "image_url": None, "description": "Reconnect Tidal in Settings → Connections to grant the new collection.read scope.", "needs_reconnect": True, "tracks": [], }) logger.info( "Tidal Favorite Tracks: token missing `collection.read` scope — surfacing reconnect hint." ) elif collection_count > 0: playlist_data.append({ "id": COLLECTION_PLAYLIST_ID, "name": COLLECTION_PLAYLIST_NAME, "owner": "You", "track_count": collection_count, "image_url": None, "description": COLLECTION_PLAYLIST_DESCRIPTION, "tracks": [], }) logger.info( f"Added virtual '{COLLECTION_PLAYLIST_NAME}' playlist with {collection_count} tracks (count only)" ) except Exception as collection_error: logger.error(f"Failed to add Tidal Favorite Tracks playlist: {collection_error}") # Don't fail the entire request if Favorite Tracks fails logger.info(f"Loaded {len(playlist_data)} Tidal playlists with track data") return jsonify(playlist_data) except Exception as e: return jsonify({"error": str(e)}), 500 @app.route('/api/tidal/playlist/', methods=['GET']) def get_tidal_playlist_tracks(playlist_id): """Fetches full track details for a specific Tidal playlist (matches sync.py pattern).""" if not tidal_client or not tidal_client.is_authenticated(): return jsonify({"error": "Tidal not authenticated."}), 401 try: logger.info(f"Getting full Tidal playlist with tracks for: {playlist_id}") # Fetch this single playlist directly — no need to re-fetch all playlists. # `get_playlist` recognizes the virtual `tidal-favorites` ID and # dispatches to the userCollectionTracks endpoint internally, so # the rest of this handler treats it identically to a real playlist. full_playlist = tidal_client.get_playlist(playlist_id) if not full_playlist: return jsonify({"error": "Playlist not found or unable to access. This may be due to privacy settings or Tidal API restrictions."}), 404 if not full_playlist.tracks: return jsonify({"error": "This playlist appears to have no tracks or they cannot be accessed"}), 403 logger.info(f"Loaded {len(full_playlist.tracks)} tracks from Tidal playlist: {full_playlist.name}") # Convert playlist to dict (matches sync.py structure) playlist_dict = { 'id': full_playlist.id, 'name': full_playlist.name, 'description': getattr(full_playlist, 'description', ''), 'owner': getattr(full_playlist, 'owner', 'Unknown'), 'track_count': len(full_playlist.tracks), 'image_url': getattr(full_playlist, 'image_url', None), 'tracks': [] } # Convert tracks to dict format (for discovery modal) playlist_dict['tracks'] = [{ 'id': t.id, 'name': t.name, 'artists': t.artists or [], 'album': getattr(t, 'album', 'Unknown Album'), 'duration_ms': getattr(t, 'duration_ms', 0), 'track_number': getattr(t, 'track_number', 0) } for t in full_playlist.tracks] return jsonify(playlist_dict) except Exception as e: logger.error(f"Error getting Tidal playlist tracks: {e}") return jsonify({"error": str(e)}), 500 # =================================================================== # TIDAL DISCOVERY API ENDPOINTS # =================================================================== # Global state for Tidal playlist discovery management tidal_discovery_states = {} # Key: playlist_id, Value: discovery state tidal_discovery_executor = ThreadPoolExecutor(max_workers=3, thread_name_prefix="tidal_discovery") @app.route('/api/tidal/discovery/start/', methods=['POST']) def start_tidal_discovery(playlist_id): """Start Spotify discovery process for a Tidal playlist""" try: # Get playlist data from Tidal if not tidal_client or not tidal_client.is_authenticated(): return jsonify({"error": "Tidal not authenticated."}), 401 # Fetch this single playlist directly — no need to re-fetch all playlists target_playlist = tidal_client.get_playlist(playlist_id) if not target_playlist: return jsonify({"error": "Tidal playlist not found"}), 404 if not target_playlist.tracks: return jsonify({"error": "Playlist has no tracks"}), 400 # Initialize discovery state if it doesn't exist, or update existing state if playlist_id in tidal_discovery_states: existing_state = tidal_discovery_states[playlist_id] if existing_state['phase'] == 'discovering': return jsonify({"error": "Discovery already in progress"}), 400 # Update existing state for discovery existing_state['phase'] = 'discovering' existing_state['status'] = 'discovering' existing_state['last_accessed'] = time.time() state = existing_state else: # Create new state for first-time discovery state = { 'playlist': target_playlist, 'phase': 'discovering', # fresh -> discovering -> discovered -> syncing -> sync_complete -> downloading -> download_complete 'status': 'discovering', 'discovery_progress': 0, 'spotify_matches': 0, 'spotify_total': len(target_playlist.tracks), 'discovery_results': [], 'sync_playlist_id': None, 'converted_spotify_playlist_id': None, 'download_process_id': None, # Track associated download missing tracks process 'created_at': time.time(), 'last_accessed': time.time(), 'discovery_future': None, 'sync_progress': {} } tidal_discovery_states[playlist_id] = state # Add activity for discovery start add_activity_item("", "Tidal Discovery Started", f"'{target_playlist.name}' - {len(target_playlist.tracks)} tracks", "Now") # Start discovery worker (capture profile ID while we have Flask context) state['_profile_id'] = get_current_profile_id() future = tidal_discovery_executor.submit(_run_tidal_discovery_worker, playlist_id) state['discovery_future'] = future logger.info(f"Started Spotify discovery for Tidal playlist: {target_playlist.name}") return jsonify({"success": True, "message": "Discovery started"}) except Exception as e: logger.error(f"Error starting Tidal discovery: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/tidal/discovery/status/', methods=['GET']) def get_tidal_discovery_status(playlist_id): """Get real-time discovery status for a Tidal playlist""" try: if playlist_id not in tidal_discovery_states: return jsonify({"error": "Tidal discovery not found"}), 404 state = tidal_discovery_states[playlist_id] state['last_accessed'] = time.time() # Update access time response = { 'phase': state['phase'], 'status': state['status'], 'progress': state['discovery_progress'], 'spotify_matches': state['spotify_matches'], 'spotify_total': state['spotify_total'], 'results': state['discovery_results'], 'complete': state['phase'] == 'discovered' } return jsonify(response) except Exception as e: logger.error(f"Error getting Tidal discovery status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/tidal/discovery/update_match', methods=['POST']) def update_tidal_discovery_match(): """Update a Tidal discovery result with manually selected Spotify track""" try: data = request.get_json() identifier = data.get('identifier') # playlist_id track_index = data.get('track_index') spotify_track = data.get('spotify_track') if not identifier or track_index is None or not spotify_track: return jsonify({'error': 'Missing required fields'}), 400 # Get the state state = tidal_discovery_states.get(identifier) if not state: return jsonify({'error': 'Discovery state not found'}), 404 if track_index >= len(state['discovery_results']): return jsonify({'error': 'Invalid track index'}), 400 # Update the result result = state['discovery_results'][track_index] old_status = result.get('status') # Update with user-selected track result['status'] = 'Found' result['status_class'] = 'found' result['spotify_track'] = spotify_track['name'] result['spotify_artist'] = _join_artist_names(spotify_track['artists']) if isinstance(spotify_track['artists'], list) else _extract_artist_name(spotify_track['artists']) result['spotify_album'] = spotify_track['album'] result['spotify_id'] = spotify_track['id'] # Format duration (Tidal doesn't show duration in table, but store it anyway) duration_ms = spotify_track.get('duration_ms', 0) if duration_ms: minutes = duration_ms // 60000 seconds = (duration_ms % 60000) // 1000 result['duration'] = f"{minutes}:{seconds:02d}" else: result['duration'] = '0:00' # IMPORTANT: Also set spotify_data for sync/download compatibility. # Manual match from the fix modal — build a rich spotify_data (album # as dict with image info) matching the normal discovery shape, and # explicitly clear any prior wing-it flag since the user picked a # real metadata match. result['spotify_data'] = _build_fix_modal_spotify_data(spotify_track) result['wing_it_fallback'] = False result['manual_match'] = True # Flag for tracking # Update match count if status changed from not found/error if old_status != 'found' and old_status != 'Found': state['spotify_matches'] = state.get('spotify_matches', 0) + 1 logger.info(f"Manual match updated: tidal - {identifier} - track {track_index}") logger.info(f" → {result['spotify_artist']} - {result['spotify_track']}") # Save manual fix to discovery cache so it appears in discovery pool try: original_track = result.get('tidal_track', {}) original_name = original_track.get('name', spotify_track['name']) original_artist = '' original_artists = original_track.get('artists', []) if original_artists: original_artist = original_artists[0] if isinstance(original_artists[0], str) else original_artists[0].get('name', '') cache_key = _get_discovery_cache_key(original_name, original_artist) # Normalize artists to plain strings for cache consistency artists_list = spotify_track['artists'] if isinstance(artists_list, list): artists_list = [a if isinstance(a, str) else a.get('name', '') for a in artists_list] # Preserve cover image info so the download pipeline can find # artwork when this cached match is used later. The fix modal # sends image_url at the top level; search results often return # album as a bare string, which previously dropped the artwork. image_url = spotify_track.get('image_url') or '' album_raw = spotify_track.get('album', '') if isinstance(album_raw, dict): album_obj = dict(album_raw) if image_url and not album_obj.get('image_url'): album_obj['image_url'] = image_url if image_url and not album_obj.get('images'): album_obj['images'] = [{'url': image_url}] else: album_obj = {'name': album_raw or ''} if image_url: album_obj['image_url'] = image_url album_obj['images'] = [{'url': image_url}] matched_data = { 'id': spotify_track['id'], 'name': spotify_track['name'], 'artists': artists_list, 'album': album_obj, 'duration_ms': spotify_track.get('duration_ms', 0), 'image_url': image_url, 'source': 'spotify', } cache_db = get_database() cache_db.save_discovery_cache_match( cache_key[0], cache_key[1], _get_active_discovery_source(), 1.0, matched_data, original_name, original_artist ) logger.info(f"Manual fix saved to discovery cache: {original_name} by {original_artist}") except Exception as cache_err: logger.error(f"Error saving manual fix to discovery cache: {cache_err}") return jsonify({'success': True, 'result': result}) except Exception as e: logger.error(f"Error updating Tidal discovery match: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/tidal/playlists/states', methods=['GET']) def get_tidal_playlist_states(): """Get all stored Tidal playlist discovery states for frontend hydration (similar to YouTube playlists)""" try: states = [] current_time = time.time() for playlist_id, state in tidal_discovery_states.items(): # Update access time when requested state['last_accessed'] = current_time # Return essential data for card state recreation state_info = { 'playlist_id': playlist_id, 'phase': state['phase'], 'status': state['status'], 'discovery_progress': state['discovery_progress'], 'spotify_matches': state['spotify_matches'], 'spotify_total': state['spotify_total'], 'discovery_results': state['discovery_results'], 'converted_spotify_playlist_id': state.get('converted_spotify_playlist_id'), 'download_process_id': state.get('download_process_id'), 'last_accessed': state['last_accessed'] } states.append(state_info) logger.info(f"Returning {len(states)} stored Tidal playlist states for hydration") return jsonify({"states": states}) except Exception as e: logger.error(f"Error getting Tidal playlist states: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/tidal/state/', methods=['GET']) def get_tidal_playlist_state(playlist_id): """Get specific Tidal playlist state (detailed version matching YouTube's state endpoint)""" try: if playlist_id not in tidal_discovery_states: return jsonify({"error": "Tidal playlist not found"}), 404 state = tidal_discovery_states[playlist_id] state['last_accessed'] = time.time() # Return full state information (including results for modal hydration) response = { 'playlist_id': playlist_id, 'playlist': state['playlist'].__dict__ if hasattr(state['playlist'], '__dict__') else state['playlist'], 'phase': state['phase'], 'status': state['status'], 'discovery_progress': state['discovery_progress'], 'spotify_matches': state['spotify_matches'], 'spotify_total': state['spotify_total'], 'discovery_results': state['discovery_results'], 'sync_playlist_id': state.get('sync_playlist_id'), 'converted_spotify_playlist_id': state.get('converted_spotify_playlist_id'), 'download_process_id': state.get('download_process_id'), 'sync_progress': state.get('sync_progress', {}), 'last_accessed': state['last_accessed'] } return jsonify(response) except Exception as e: logger.error(f"Error getting Tidal playlist state: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/tidal/reset/', methods=['POST']) def reset_tidal_playlist(playlist_id): """Reset Tidal playlist to fresh phase (clear discovery/sync data)""" try: if playlist_id not in tidal_discovery_states: return jsonify({"error": "Tidal playlist not found"}), 404 state = tidal_discovery_states[playlist_id] # Stop any active discovery if 'discovery_future' in state and state['discovery_future']: state['discovery_future'].cancel() # Reset state to fresh (preserve original playlist data) state['phase'] = 'fresh' state['status'] = 'fresh' state['discovery_results'] = [] state['discovery_progress'] = 0 state['spotify_matches'] = 0 state['sync_playlist_id'] = None state['converted_spotify_playlist_id'] = None state['download_process_id'] = None state['sync_progress'] = {} state['discovery_future'] = None state['last_accessed'] = time.time() logger.info(f"Reset Tidal playlist to fresh: {playlist_id}") return jsonify({"success": True, "message": "Playlist reset to fresh phase"}) except Exception as e: logger.error(f"Error resetting Tidal playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/tidal/delete/', methods=['POST']) def delete_tidal_playlist(playlist_id): """Delete Tidal playlist state completely""" try: if playlist_id not in tidal_discovery_states: return jsonify({"error": "Tidal playlist not found"}), 404 state = tidal_discovery_states[playlist_id] # Stop any active discovery if 'discovery_future' in state and state['discovery_future']: state['discovery_future'].cancel() # Remove from state dictionary del tidal_discovery_states[playlist_id] logger.info(f"Deleted Tidal playlist state: {playlist_id}") return jsonify({"success": True, "message": "Playlist deleted"}) except Exception as e: logger.error(f"Error deleting Tidal playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/tidal/update_phase/', methods=['POST']) def update_tidal_playlist_phase(playlist_id): """Update Tidal playlist phase (used when modal closes to reset from download_complete to discovered)""" try: if playlist_id not in tidal_discovery_states: return jsonify({"error": "Tidal playlist not found"}), 404 data = request.get_json() if not data or 'phase' not in data: return jsonify({"error": "Phase not provided"}), 400 new_phase = data['phase'] valid_phases = ['fresh', 'discovering', 'discovered', 'syncing', 'sync_complete', 'downloading', 'download_complete'] if new_phase not in valid_phases: return jsonify({"error": f"Invalid phase. Must be one of: {', '.join(valid_phases)}"}), 400 state = tidal_discovery_states[playlist_id] old_phase = state.get('phase', 'unknown') state['phase'] = new_phase state['last_accessed'] = time.time() logger.info(f"Updated Tidal playlist {playlist_id} phase: {old_phase} → {new_phase}") return jsonify({"success": True, "message": f"Phase updated to {new_phase}", "old_phase": old_phase, "new_phase": new_phase}) except Exception as e: logger.error(f"Error updating Tidal playlist phase: {e}") return jsonify({"error": str(e)}), 500 _playlist_discovery_cancelled = set() # Set of automation_ids that have been cancelled def _pause_enrichment_workers(label='discovery'): """Pause enrichment workers during discovery to reduce API contention. Returns dict of {name: was_running} for resume.""" was_running = {} workers = { 'Spotify': spotify_enrichment_worker, 'iTunes': itunes_enrichment_worker, 'Tidal': tidal_enrichment_worker if 'tidal_enrichment_worker' in globals() else None, 'Qobuz': qobuz_enrichment_worker if 'qobuz_enrichment_worker' in globals() else None, } for name, worker in workers.items(): try: if worker and not worker.paused: worker.pause() was_running[name] = True logger.warning(f"Paused {name} enrichment worker during {label}") except Exception as e: logger.debug("enrichment worker pause failed: %s", e) return was_running def _resume_enrichment_workers(was_running, label='discovery'): """Resume enrichment workers that were paused by _pause_enrichment_workers.""" workers = { 'Spotify': spotify_enrichment_worker, 'iTunes': itunes_enrichment_worker, 'Tidal': tidal_enrichment_worker if 'tidal_enrichment_worker' in globals() else None, 'Qobuz': qobuz_enrichment_worker if 'qobuz_enrichment_worker' in globals() else None, } for name, worker in workers.items(): try: if was_running.get(name) and worker: worker.resume() logger.info(f"Resumed {name} enrichment worker after {label}") except Exception as e: logger.debug("enrichment worker resume failed: %s", e) def _sync_discovery_results_to_mirrored(source_type, source_playlist_id, discovery_results, discovery_source, profile_id=1): """Write discovery results back to the mirrored playlist's extra_data. Called after Tidal/Deezer/Beatport discovery completes. Matches by source_track_id first, then by track position (index).""" try: db = get_database() playlists = db.get_mirrored_playlists(profile_id=profile_id) mirrored_pl = None for pl in playlists: if pl.get('source') == source_type and str(pl.get('source_playlist_id')) == str(source_playlist_id): mirrored_pl = pl break if not mirrored_pl: logger.warning(f"[Discovery Sync] No mirrored playlist found for {source_type}:{source_playlist_id} (profile {profile_id})") return logger.info(f"[Discovery Sync] Found mirrored playlist '{mirrored_pl.get('name')}' (DB id={mirrored_pl['id']}) for {source_type}:{source_playlist_id}") mirrored_tracks = db.get_mirrored_playlist_tracks(mirrored_pl['id']) if not mirrored_tracks: return # Build lookup maps: source_track_id → db_id AND position → db_id source_id_to_db_id = {} position_to_db_id = {} for mt in mirrored_tracks: sid = mt.get('source_track_id', '') if sid: source_id_to_db_id[str(sid)] = mt['id'] pos = mt.get('position') if pos is not None: position_to_db_id[pos] = mt['id'] updated = 0 for result in discovery_results: if result.get('status') not in ('found', 'Found', 'Wing It'): continue match_data = result.get('match_data') or result.get('spotify_data') if not match_data: continue confidence = result.get('confidence', 0.85) # Try to find the mirrored track DB ID db_track_id = None # Method 1: match by source track ID source_track = result.get('tidal_track') or result.get('source_track') or {} source_tid = str(source_track.get('id', '')) if source_track else '' if source_tid and source_tid in source_id_to_db_id: db_track_id = source_id_to_db_id[source_tid] # Method 2: match by position/index if not db_track_id: idx = result.get('index') if idx is not None and idx in position_to_db_id: db_track_id = position_to_db_id[idx] if not db_track_id: continue extra_data = { 'discovered': True, 'provider': discovery_source, 'confidence': confidence, 'matched_data': match_data, } if result.get('wing_it_fallback'): extra_data['wing_it_fallback'] = True extra_data['provider'] = 'wing_it_fallback' db.update_mirrored_track_extra_data(db_track_id, extra_data) updated += 1 if updated > 0: logger.info(f"Synced {updated} discovery results back to mirrored playlist '{mirrored_pl.get('name', '')}'") except Exception as e: import traceback logger.error(f"Failed to sync discovery results to mirrored playlist: {e}") traceback.print_exc() # Mirrored-playlist discovery worker logic lives in core/discovery/playlist.py. from core.discovery import playlist as _discovery_playlist def _build_playlist_discovery_deps(): """Build the PlaylistDiscoveryDeps bundle from web_server.py globals on each call.""" return _discovery_playlist.PlaylistDiscoveryDeps( spotify_client=spotify_client, matching_engine=matching_engine, automation_engine=automation_engine, playlist_discovery_cancelled=_playlist_discovery_cancelled, pause_enrichment_workers=_pause_enrichment_workers, resume_enrichment_workers=_resume_enrichment_workers, get_active_discovery_source=_get_active_discovery_source, get_metadata_fallback_client=_get_metadata_fallback_client, get_metadata_fallback_source=_get_metadata_fallback_source, update_automation_progress=_update_automation_progress, get_database=get_database, get_discovery_cache_key=_get_discovery_cache_key, validate_discovery_cache_artist=_validate_discovery_cache_artist, discovery_score_candidates=_discovery_score_candidates, get_metadata_cache=get_metadata_cache, build_discovery_wing_it_stub=_build_discovery_wing_it_stub, ) def _run_playlist_discovery_worker(playlists, automation_id=None): return _discovery_playlist.run_playlist_discovery_worker( playlists, automation_id, _build_playlist_discovery_deps() ) def _extract_artist_name(artist): """Extract artist name string from either a string or dict ({"name": "..."}) format.""" if isinstance(artist, dict): return artist.get('name', '') return artist or '' def _extract_artist_names(artists): """Extract a list of artist name strings from a list that may contain dicts or strings.""" return [_extract_artist_name(a) for a in (artists or [])] def _join_artist_names(artists): """Join artist names from a list that may contain dicts or strings.""" return ', '.join(_extract_artist_names(artists)) def _get_discovery_cache_key(title, artist): """Normalize title/artist for discovery cache lookup using matching_engine.""" norm_title = matching_engine.clean_title(title) norm_artist = matching_engine.clean_artist(_extract_artist_name(artist)) return (norm_title, norm_artist) def _validate_discovery_cache_artist(source_artist, cached_match): """Check if a cached discovery match has a valid artist. Returns False if the cached result's artist doesn't match the source artist (stale/wrong cache entry).""" min_artist_similarity = 0.5 source_artist_cleaned = matching_engine.clean_artist(source_artist) if not source_artist_cleaned: return True # No source artist to validate against cached_artists = cached_match.get('artists', []) if not cached_artists: return True # No cached artist to check best_sim = 0.0 for cand_artist in cached_artists: if not cand_artist: continue # Handle both string artists and dict artists ({"name": "..."}) if isinstance(cand_artist, dict): cand_artist = cand_artist.get('name', '') if not cand_artist: continue cand_normalized = matching_engine.normalize_string(cand_artist) if source_artist_cleaned in cand_normalized: return True cand_cleaned = matching_engine.clean_artist(cand_artist) sim = matching_engine.similarity_score(source_artist_cleaned, cand_cleaned) if sim > best_sim: best_sim = sim if best_sim < min_artist_similarity: logger.info(f"Cache artist mismatch: source='{source_artist}' vs cached='{cached_artists[0]}' (sim={best_sim:.2f}), re-searching") return False return True from core.discovery.scoring import ( _discovery_score_candidates, _search_spotify_for_tidal_track, init as _init_discovery_scoring, ) # Tidal discovery worker logic lives in core/discovery/tidal.py. from core.discovery import tidal as _discovery_tidal def _build_tidal_discovery_deps(): """Build the TidalDiscoveryDeps bundle from web_server.py globals on each call.""" return _discovery_tidal.TidalDiscoveryDeps( tidal_discovery_states=tidal_discovery_states, spotify_client=spotify_client, pause_enrichment_workers=_pause_enrichment_workers, resume_enrichment_workers=_resume_enrichment_workers, get_active_discovery_source=_get_active_discovery_source, get_metadata_fallback_client=_get_metadata_fallback_client, get_discovery_cache_key=_get_discovery_cache_key, get_database=get_database, validate_discovery_cache_artist=_validate_discovery_cache_artist, search_spotify_for_tidal_track=_search_spotify_for_tidal_track, build_discovery_wing_it_stub=_build_discovery_wing_it_stub, add_activity_item=add_activity_item, sync_discovery_results_to_mirrored=_sync_discovery_results_to_mirrored, ) def _run_tidal_discovery_worker(playlist_id): return _discovery_tidal.run_tidal_discovery_worker(playlist_id, _build_tidal_discovery_deps()) def convert_tidal_results_to_spotify_tracks(discovery_results): """Convert Tidal discovery results to Spotify tracks format for sync""" spotify_tracks = [] for result in discovery_results: # Support both data formats: spotify_data (manual fixes) and individual fields (automatic discovery) if result.get('spotify_data'): spotify_data = result['spotify_data'] # Create track object matching the expected format track = { 'id': spotify_data['id'], 'name': spotify_data['name'], 'artists': spotify_data['artists'], 'album': spotify_data['album'], 'duration_ms': spotify_data.get('duration_ms', 0) } if spotify_data.get('track_number'): track['track_number'] = spotify_data['track_number'] if spotify_data.get('disc_number'): track['disc_number'] = spotify_data['disc_number'] spotify_tracks.append(track) elif result.get('spotify_track') and result.get('status_class') == 'found': # Build from individual fields (automatic discovery format) track = { 'id': result.get('spotify_id', 'unknown'), 'name': result.get('spotify_track', 'Unknown Track'), 'artists': [result.get('spotify_artist', 'Unknown Artist')] if result.get('spotify_artist') else ['Unknown Artist'], 'album': result.get('spotify_album', 'Unknown Album'), 'duration_ms': 0 } spotify_tracks.append(track) logger.info(f"Converted {len(spotify_tracks)} Tidal matches to Spotify tracks for sync") return spotify_tracks # =================================================================== # TIDAL SYNC API ENDPOINTS # =================================================================== @app.route('/api/tidal/sync/start/', methods=['POST']) def start_tidal_sync(playlist_id): """Start sync process for a Tidal playlist using discovered Spotify tracks""" try: if playlist_id not in tidal_discovery_states: return jsonify({"error": "Tidal playlist not found"}), 404 state = tidal_discovery_states[playlist_id] state['last_accessed'] = time.time() # Update access time if state['phase'] not in ['discovered', 'sync_complete', 'download_complete']: return jsonify({"error": "Tidal playlist not ready for sync"}), 400 # Convert discovery results to Spotify tracks format spotify_tracks = convert_tidal_results_to_spotify_tracks(state['discovery_results']) if not spotify_tracks: return jsonify({"error": "No Spotify matches found for sync"}), 400 # Create a temporary playlist ID for sync tracking sync_playlist_id = f"tidal_{playlist_id}" playlist_name = state['playlist'].name # Tidal playlist object has .name attribute # Add activity for sync start add_activity_item("", "Tidal Sync Started", f"'{playlist_name}' - {len(spotify_tracks)} tracks", "Now") # Update Tidal state state['phase'] = 'syncing' state['sync_playlist_id'] = sync_playlist_id state['sync_progress'] = {} # Start the sync using existing sync infrastructure sync_data = { 'playlist_id': sync_playlist_id, 'playlist_name': playlist_name, 'tracks': spotify_tracks } with sync_lock: sync_states[sync_playlist_id] = {"status": "starting", "progress": {}} # Submit sync task playlist_image_url = getattr(state['playlist'], 'image_url', '') future = sync_executor.submit(_run_sync_task, sync_playlist_id, sync_data['playlist_name'], spotify_tracks, None, get_current_profile_id(), playlist_image_url) active_sync_workers[sync_playlist_id] = future logger.info(f"Started Tidal sync for: {playlist_name} ({len(spotify_tracks)} tracks)") return jsonify({"success": True, "sync_playlist_id": sync_playlist_id}) except Exception as e: logger.error(f"Error starting Tidal sync: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/tidal/sync/status/', methods=['GET']) def get_tidal_sync_status(playlist_id): """Get sync status for a Tidal playlist""" try: if playlist_id not in tidal_discovery_states: return jsonify({"error": "Tidal playlist not found"}), 404 state = tidal_discovery_states[playlist_id] state['last_accessed'] = time.time() # Update access time sync_playlist_id = state.get('sync_playlist_id') if not sync_playlist_id: return jsonify({"error": "No sync in progress"}), 404 # Get sync status from existing sync infrastructure with sync_lock: sync_state = sync_states.get(sync_playlist_id, {}) response = { 'phase': state['phase'], 'sync_status': sync_state.get('status', 'unknown'), 'progress': sync_state.get('progress', {}), 'complete': sync_state.get('status') == 'finished', 'error': sync_state.get('error') } # Update Tidal state if sync completed if sync_state.get('status') == 'finished': state['phase'] = 'sync_complete' state['sync_progress'] = sync_state.get('progress', {}) # Add activity for sync completion playlist = state.get('playlist') playlist_name = playlist.name if playlist and hasattr(playlist, 'name') else 'Unknown Playlist' add_activity_item("", "Sync Complete", f"Tidal playlist '{playlist_name}' synced successfully", "Now") elif sync_state.get('status') == 'error': state['phase'] = 'discovered' # Revert on error playlist = state.get('playlist') playlist_name = playlist.name if playlist and hasattr(playlist, 'name') else 'Unknown Playlist' add_activity_item("", "Sync Failed", f"Tidal playlist '{playlist_name}' sync failed", "Now") return jsonify(response) except Exception as e: logger.error(f"Error getting Tidal sync status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/tidal/sync/cancel/', methods=['POST']) def cancel_tidal_sync(playlist_id): """Cancel sync for a Tidal playlist""" try: if playlist_id not in tidal_discovery_states: return jsonify({"error": "Tidal playlist not found"}), 404 state = tidal_discovery_states[playlist_id] state['last_accessed'] = time.time() # Update access time sync_playlist_id = state.get('sync_playlist_id') if sync_playlist_id: # Cancel the sync using existing sync infrastructure with sync_lock: sync_states[sync_playlist_id] = {"status": "cancelled"} # Clean up sync worker if sync_playlist_id in active_sync_workers: del active_sync_workers[sync_playlist_id] # Revert Tidal state state['phase'] = 'discovered' state['sync_playlist_id'] = None state['sync_progress'] = {} return jsonify({"success": True, "message": "Tidal sync cancelled"}) except Exception as e: logger.error(f"Error cancelling Tidal sync: {e}") return jsonify({"error": str(e)}), 500 # =================================================================== # DEEZER PLAYLIST DISCOVERY API ENDPOINTS # =================================================================== # Global state for Deezer playlist discovery management deezer_discovery_states = {} # Key: playlist_id, Value: discovery state deezer_discovery_executor = ThreadPoolExecutor(max_workers=3, thread_name_prefix="deezer_discovery") def _get_deezer_client(): """Get cached Deezer client.""" from core.metadata.registry import get_deezer_client return get_deezer_client() def _get_itunes_client(): """Get cached iTunes client.""" from core.metadata.registry import get_itunes_client return get_itunes_client() def _get_discogs_client(token=None): """Get cached Discogs client.""" from core.metadata.registry import get_discogs_client return get_discogs_client(token) def _get_metadata_fallback_source(): """Get the configured primary metadata source. Returns 'spotify', 'itunes', 'deezer', 'discogs', or 'hydrabase'. NOTE: This is a thin wrapper — canonical logic lives in core.metadata.registry.get_primary_source(). Kept as a local function because 70+ callers reference it by name.""" from core.metadata.registry import get_primary_source return get_primary_source() def _get_metadata_fallback_client(): """Get the active metadata client based on settings. Returns a SpotifyClient, iTunesClient, DeezerClient, DiscogsClient, or HydrabaseClient instance.""" source = _get_metadata_fallback_source() from core.metadata.registry import get_client_for_source client = get_client_for_source(source) if client is not None: return client if source == 'spotify': return _get_deezer_client() if source == 'discogs': token = config_manager.get('discogs.token', '') if token: return _get_discogs_client(token) return _get_itunes_client() if source == 'hydrabase': if hydrabase_client and hydrabase_client.is_connected(): return hydrabase_client return _get_itunes_client() return _get_itunes_client() @app.route('/api/deezer/arl-status', methods=['GET']) def get_deezer_arl_status(): """Check if Deezer ARL is configured and authenticated.""" try: deezer_dl = download_orchestrator.client("deezer_dl") if download_orchestrator and hasattr(download_orchestrator, 'client') else None if deezer_dl and deezer_dl.is_authenticated(): user_data = deezer_dl._user_data or {} return jsonify({ 'authenticated': True, 'user_name': user_data.get('BLOG_NAME', 'Unknown'), 'user_id': user_data.get('USER_ID'), }) return jsonify({'authenticated': False}) except Exception as e: return jsonify({'authenticated': False, 'error': str(e)}) @app.route('/api/deezer/arl-playlists', methods=['GET']) def get_deezer_arl_playlists(): """Fetch user playlists via Deezer ARL authentication (like /api/spotify/playlists).""" try: deezer_dl = download_orchestrator.client("deezer_dl") if download_orchestrator and hasattr(download_orchestrator, 'client') else None if not deezer_dl or not deezer_dl.is_authenticated(): return jsonify({'error': 'Deezer ARL not authenticated. Configure your ARL token in Settings > Downloads.'}), 401 playlists = deezer_dl.get_user_playlists() # Add sync_status field to match Spotify format playlist_data = [] for p in playlists: playlist_data.append({ 'id': p['id'], 'name': p['name'], 'owner': p.get('owner', ''), 'track_count': p.get('track_count', 0), 'image_url': p.get('image_url', ''), 'sync_status': 'Never Synced', }) logger.info(f"Loaded {len(playlist_data)} Deezer user playlists via ARL") return jsonify(playlist_data) except Exception as e: return jsonify({'error': str(e)}), 500 @app.route('/api/deezer/arl-playlist/', methods=['GET']) def get_deezer_arl_playlist_tracks(playlist_id): """Fetch full playlist with tracks via ARL (like /api/spotify/playlist/).""" try: deezer_dl = download_orchestrator.client("deezer_dl") if download_orchestrator and hasattr(download_orchestrator, 'client') else None if not deezer_dl or not deezer_dl.is_authenticated(): return jsonify({'error': 'Deezer ARL not authenticated.'}), 401 playlist = deezer_dl.get_playlist_tracks(playlist_id) if not playlist: return jsonify({'error': 'Playlist not found or unable to access.'}), 404 logger.info(f"Loaded {len(playlist.get('tracks', []))} tracks from Deezer playlist: {playlist.get('name')}") return jsonify(playlist) except Exception as e: return jsonify({'error': str(e)}), 500 @app.route('/api/deezer/playlist/', methods=['GET']) def get_deezer_playlist(playlist_id): """Fetch a Deezer playlist by ID or URL""" try: from core.deezer_client import DeezerClient # Parse URL if needed parsed_id = DeezerClient.parse_playlist_url(playlist_id) if not parsed_id: return jsonify({"error": "Invalid Deezer playlist ID or URL"}), 400 client = _get_deezer_client() playlist = client.get_playlist(parsed_id) if not playlist: return jsonify({"error": "Deezer playlist not found"}), 404 return jsonify(playlist) except Exception as e: logger.error(f"Error fetching Deezer playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/discovery/start/', methods=['POST']) def start_deezer_discovery(playlist_id): """Start Spotify discovery process for a Deezer playlist""" try: from core.deezer_client import DeezerClient # Parse URL if needed parsed_id = DeezerClient.parse_playlist_url(playlist_id) if parsed_id: playlist_id = parsed_id # Initialize discovery state if it doesn't exist, or update existing state if playlist_id in deezer_discovery_states: existing_state = deezer_discovery_states[playlist_id] if existing_state['phase'] == 'discovering': return jsonify({"error": "Discovery already in progress"}), 400 # Fetch fresh playlist data if not already stored if not existing_state.get('playlist'): client = _get_deezer_client() playlist_data = client.get_playlist(playlist_id) if not playlist_data: return jsonify({"error": "Deezer playlist not found"}), 404 existing_state['playlist'] = playlist_data # Update existing state for discovery existing_state['phase'] = 'discovering' existing_state['status'] = 'discovering' existing_state['last_accessed'] = time.time() state = existing_state else: # Fetch playlist data from Deezer client = _get_deezer_client() playlist_data = client.get_playlist(playlist_id) if not playlist_data: return jsonify({"error": "Deezer playlist not found"}), 404 if not playlist_data.get('tracks'): return jsonify({"error": "Playlist has no tracks"}), 400 # Create new state for first-time discovery state = { 'playlist': playlist_data, 'phase': 'discovering', # fresh -> discovering -> discovered -> syncing -> sync_complete -> downloading -> download_complete 'status': 'discovering', 'discovery_progress': 0, 'spotify_matches': 0, 'spotify_total': len(playlist_data['tracks']), 'discovery_results': [], 'sync_playlist_id': None, 'converted_spotify_playlist_id': None, 'download_process_id': None, 'created_at': time.time(), 'last_accessed': time.time(), 'discovery_future': None, 'sync_progress': {} } deezer_discovery_states[playlist_id] = state # Add activity for discovery start playlist_name = state['playlist']['name'] track_count = len(state['playlist']['tracks']) add_activity_item("", "Deezer Discovery Started", f"'{playlist_name}' - {track_count} tracks", "Now") # Start discovery worker (capture profile ID while we have Flask context) deezer_discovery_states[playlist_id]['_profile_id'] = get_current_profile_id() future = deezer_discovery_executor.submit(_run_deezer_discovery_worker, playlist_id) state['discovery_future'] = future logger.info(f"Started Spotify discovery for Deezer playlist: {playlist_name}") return jsonify({"success": True, "message": "Discovery started"}) except Exception as e: logger.error(f"Error starting Deezer discovery: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/discovery/status/', methods=['GET']) def get_deezer_discovery_status(playlist_id): """Get real-time discovery status for a Deezer playlist""" try: if playlist_id not in deezer_discovery_states: return jsonify({"error": "Deezer discovery not found"}), 404 state = deezer_discovery_states[playlist_id] state['last_accessed'] = time.time() response = { 'phase': state['phase'], 'status': state['status'], 'progress': state['discovery_progress'], 'spotify_matches': state['spotify_matches'], 'spotify_total': state['spotify_total'], 'results': state['discovery_results'], 'complete': state['phase'] == 'discovered' } return jsonify(response) except Exception as e: logger.error(f"Error getting Deezer discovery status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/discovery/update_match', methods=['POST']) def update_deezer_discovery_match(): """Update a Deezer discovery result with manually selected Spotify track""" try: data = request.get_json() identifier = data.get('identifier') # playlist_id track_index = data.get('track_index') spotify_track = data.get('spotify_track') if not identifier or track_index is None or not spotify_track: return jsonify({'error': 'Missing required fields'}), 400 # Get the state state = deezer_discovery_states.get(identifier) if not state: return jsonify({'error': 'Discovery state not found'}), 404 if track_index >= len(state['discovery_results']): return jsonify({'error': 'Invalid track index'}), 400 # Update the result result = state['discovery_results'][track_index] old_status = result.get('status') # Update with user-selected track result['status'] = 'Found' result['status_class'] = 'found' result['spotify_track'] = spotify_track['name'] result['spotify_artist'] = _join_artist_names(spotify_track['artists']) if isinstance(spotify_track['artists'], list) else _extract_artist_name(spotify_track['artists']) result['spotify_album'] = spotify_track['album'] result['spotify_id'] = spotify_track['id'] # Format duration duration_ms = spotify_track.get('duration_ms', 0) if duration_ms: minutes = duration_ms // 60000 seconds = (duration_ms % 60000) // 1000 result['duration'] = f"{minutes}:{seconds:02d}" else: result['duration'] = '0:00' # IMPORTANT: Also set spotify_data for sync/download compatibility. # Manual match from the fix modal — build a rich spotify_data (album # as dict with image info) matching the normal discovery shape, and # explicitly clear any prior wing-it flag since the user picked a # real metadata match. result['spotify_data'] = _build_fix_modal_spotify_data(spotify_track) result['wing_it_fallback'] = False result['manual_match'] = True # Update match count if status changed from not found/error if old_status != 'found' and old_status != 'Found': state['spotify_matches'] = state.get('spotify_matches', 0) + 1 logger.info(f"Manual match updated: deezer - {identifier} - track {track_index}") logger.info(f" → {result['spotify_artist']} - {result['spotify_track']}") # Save manual fix to discovery cache so it appears in discovery pool try: original_track = result.get('deezer_track', {}) original_name = original_track.get('name', spotify_track['name']) original_artists = original_track.get('artists', []) original_artist = original_artists[0] if original_artists else '' cache_key = _get_discovery_cache_key(original_name, original_artist) # Normalize artists to plain strings for cache consistency artists_list = spotify_track['artists'] if isinstance(artists_list, list): artists_list = [a if isinstance(a, str) else a.get('name', '') for a in artists_list] # Preserve cover image info so the download pipeline can find # artwork when this cached match is used later. The fix modal # sends image_url at the top level; search results often return # album as a bare string, which previously dropped the artwork. image_url = spotify_track.get('image_url') or '' album_raw = spotify_track.get('album', '') if isinstance(album_raw, dict): album_obj = dict(album_raw) if image_url and not album_obj.get('image_url'): album_obj['image_url'] = image_url if image_url and not album_obj.get('images'): album_obj['images'] = [{'url': image_url}] else: album_obj = {'name': album_raw or ''} if image_url: album_obj['image_url'] = image_url album_obj['images'] = [{'url': image_url}] matched_data = { 'id': spotify_track['id'], 'name': spotify_track['name'], 'artists': artists_list, 'album': album_obj, 'duration_ms': spotify_track.get('duration_ms', 0), 'image_url': image_url, 'source': 'spotify', } cache_db = get_database() cache_db.save_discovery_cache_match( cache_key[0], cache_key[1], _get_active_discovery_source(), 1.0, matched_data, original_name, original_artist ) logger.info(f"Manual fix saved to discovery cache: {original_name} by {original_artist}") except Exception as cache_err: logger.error(f"Error saving manual fix to discovery cache: {cache_err}") return jsonify({'success': True, 'result': result}) except Exception as e: logger.error(f"Error updating Deezer discovery match: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/deezer/playlists/states', methods=['GET']) def get_deezer_playlist_states(): """Get all stored Deezer playlist discovery states for frontend hydration""" try: states = [] current_time = time.time() for playlist_id, state in deezer_discovery_states.items(): state['last_accessed'] = current_time state_info = { 'playlist_id': playlist_id, 'phase': state['phase'], 'status': state['status'], 'discovery_progress': state['discovery_progress'], 'spotify_matches': state['spotify_matches'], 'spotify_total': state['spotify_total'], 'discovery_results': state['discovery_results'], 'converted_spotify_playlist_id': state.get('converted_spotify_playlist_id'), 'download_process_id': state.get('download_process_id'), 'last_accessed': state['last_accessed'] } states.append(state_info) logger.info(f"Returning {len(states)} stored Deezer playlist states for hydration") return jsonify({"states": states}) except Exception as e: logger.error(f"Error getting Deezer playlist states: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/state/', methods=['GET']) def get_deezer_playlist_state(playlist_id): """Get specific Deezer playlist state (detailed version)""" try: if playlist_id not in deezer_discovery_states: return jsonify({"error": "Deezer playlist not found"}), 404 state = deezer_discovery_states[playlist_id] state['last_accessed'] = time.time() # Deezer playlist is a dict, no __dict__ needed response = { 'playlist_id': playlist_id, 'playlist': state['playlist'], 'phase': state['phase'], 'status': state['status'], 'discovery_progress': state['discovery_progress'], 'spotify_matches': state['spotify_matches'], 'spotify_total': state['spotify_total'], 'discovery_results': state['discovery_results'], 'sync_playlist_id': state.get('sync_playlist_id'), 'converted_spotify_playlist_id': state.get('converted_spotify_playlist_id'), 'download_process_id': state.get('download_process_id'), 'sync_progress': state.get('sync_progress', {}), 'last_accessed': state['last_accessed'] } return jsonify(response) except Exception as e: logger.error(f"Error getting Deezer playlist state: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/reset/', methods=['POST']) def reset_deezer_playlist(playlist_id): """Reset Deezer playlist to fresh phase (clear discovery/sync data)""" try: if playlist_id not in deezer_discovery_states: return jsonify({"error": "Deezer playlist not found"}), 404 state = deezer_discovery_states[playlist_id] # Stop any active discovery if 'discovery_future' in state and state['discovery_future']: state['discovery_future'].cancel() # Reset state to fresh (preserve original playlist data) state['phase'] = 'fresh' state['status'] = 'fresh' state['discovery_results'] = [] state['discovery_progress'] = 0 state['spotify_matches'] = 0 state['sync_playlist_id'] = None state['converted_spotify_playlist_id'] = None state['download_process_id'] = None state['sync_progress'] = {} state['discovery_future'] = None state['last_accessed'] = time.time() logger.info(f"Reset Deezer playlist to fresh: {playlist_id}") return jsonify({"success": True, "message": "Playlist reset to fresh phase"}) except Exception as e: logger.error(f"Error resetting Deezer playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/delete/', methods=['POST']) def delete_deezer_playlist(playlist_id): """Delete Deezer playlist state completely""" try: if playlist_id not in deezer_discovery_states: return jsonify({"error": "Deezer playlist not found"}), 404 state = deezer_discovery_states[playlist_id] # Stop any active discovery if 'discovery_future' in state and state['discovery_future']: state['discovery_future'].cancel() # Remove from state dictionary del deezer_discovery_states[playlist_id] logger.info(f"Deleted Deezer playlist state: {playlist_id}") return jsonify({"success": True, "message": "Playlist deleted"}) except Exception as e: logger.error(f"Error deleting Deezer playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/update_phase/', methods=['POST']) def update_deezer_playlist_phase(playlist_id): """Update Deezer playlist phase (used when modal closes to reset from download_complete to discovered)""" try: if playlist_id not in deezer_discovery_states: return jsonify({"error": "Deezer playlist not found"}), 404 data = request.get_json() if not data or 'phase' not in data: return jsonify({"error": "Phase not provided"}), 400 new_phase = data['phase'] valid_phases = ['fresh', 'discovering', 'discovered', 'syncing', 'sync_complete', 'downloading', 'download_complete'] if new_phase not in valid_phases: return jsonify({"error": f"Invalid phase. Must be one of: {', '.join(valid_phases)}"}), 400 state = deezer_discovery_states[playlist_id] old_phase = state.get('phase', 'unknown') state['phase'] = new_phase state['last_accessed'] = time.time() # Update download process ID if provided (for download persistence) if 'download_process_id' in data: state['download_process_id'] = data['download_process_id'] # Update converted Spotify playlist ID if provided (for download persistence) if 'converted_spotify_playlist_id' in data: state['converted_spotify_playlist_id'] = data['converted_spotify_playlist_id'] logger.info(f"Updated Deezer playlist {playlist_id} phase: {old_phase} → {new_phase}") return jsonify({"success": True, "message": f"Phase updated to {new_phase}", "old_phase": old_phase, "new_phase": new_phase}) except Exception as e: logger.error(f"Error updating Deezer playlist phase: {e}") return jsonify({"error": str(e)}), 500 # Deezer discovery worker logic lives in core/discovery/deezer.py. from core.discovery import deezer as _discovery_deezer def _build_deezer_discovery_deps(): """Build the DeezerDiscoveryDeps bundle from web_server.py globals on each call.""" return _discovery_deezer.DeezerDiscoveryDeps( deezer_discovery_states=deezer_discovery_states, spotify_client=spotify_client, pause_enrichment_workers=_pause_enrichment_workers, resume_enrichment_workers=_resume_enrichment_workers, get_active_discovery_source=_get_active_discovery_source, get_metadata_fallback_client=_get_metadata_fallback_client, get_discovery_cache_key=_get_discovery_cache_key, get_database=get_database, validate_discovery_cache_artist=_validate_discovery_cache_artist, search_spotify_for_tidal_track=_search_spotify_for_tidal_track, build_discovery_wing_it_stub=_build_discovery_wing_it_stub, add_activity_item=add_activity_item, sync_discovery_results_to_mirrored=_sync_discovery_results_to_mirrored, ) def _run_deezer_discovery_worker(playlist_id): return _discovery_deezer.run_deezer_discovery_worker(playlist_id, _build_deezer_discovery_deps()) def convert_deezer_results_to_spotify_tracks(discovery_results): """Convert Deezer discovery results to Spotify tracks format for sync""" spotify_tracks = [] for result in discovery_results: # Support both data formats: spotify_data (manual fixes) and individual fields (automatic discovery) if result.get('spotify_data'): spotify_data = result['spotify_data'] track = { 'id': spotify_data['id'], 'name': spotify_data['name'], 'artists': spotify_data['artists'], 'album': spotify_data['album'], 'duration_ms': spotify_data.get('duration_ms', 0) } if spotify_data.get('track_number'): track['track_number'] = spotify_data['track_number'] if spotify_data.get('disc_number'): track['disc_number'] = spotify_data['disc_number'] spotify_tracks.append(track) elif result.get('spotify_track') and result.get('status_class') == 'found': track = { 'id': result.get('spotify_id', 'unknown'), 'name': result.get('spotify_track', 'Unknown Track'), 'artists': [result.get('spotify_artist', 'Unknown Artist')] if result.get('spotify_artist') else ['Unknown Artist'], 'album': result.get('spotify_album', 'Unknown Album'), 'duration_ms': 0 } spotify_tracks.append(track) logger.info(f"Converted {len(spotify_tracks)} Deezer matches to Spotify tracks for sync") return spotify_tracks # =================================================================== # DEEZER SYNC API ENDPOINTS # =================================================================== @app.route('/api/deezer/sync/start/', methods=['POST']) def start_deezer_sync(playlist_id): """Start sync process for a Deezer playlist using discovered Spotify tracks""" try: if playlist_id not in deezer_discovery_states: return jsonify({"error": "Deezer playlist not found"}), 404 state = deezer_discovery_states[playlist_id] state['last_accessed'] = time.time() if state['phase'] not in ['discovered', 'sync_complete', 'download_complete']: return jsonify({"error": "Deezer playlist not ready for sync"}), 400 # Convert discovery results to Spotify tracks format spotify_tracks = convert_deezer_results_to_spotify_tracks(state['discovery_results']) if not spotify_tracks: return jsonify({"error": "No Spotify matches found for sync"}), 400 # Create a temporary playlist ID for sync tracking sync_playlist_id = f"deezer_{playlist_id}" playlist_name = state['playlist']['name'] # Add activity for sync start add_activity_item("", "Deezer Sync Started", f"'{playlist_name}' - {len(spotify_tracks)} tracks", "Now") # Update Deezer state state['phase'] = 'syncing' state['sync_playlist_id'] = sync_playlist_id state['sync_progress'] = {} # Start the sync using existing sync infrastructure sync_data = { 'playlist_id': sync_playlist_id, 'playlist_name': playlist_name, 'tracks': spotify_tracks } with sync_lock: sync_states[sync_playlist_id] = {"status": "starting", "progress": {}} # Submit sync task playlist_image_url = state['playlist'].get('image_url', '') future = sync_executor.submit(_run_sync_task, sync_playlist_id, sync_data['playlist_name'], spotify_tracks, None, get_current_profile_id(), playlist_image_url) active_sync_workers[sync_playlist_id] = future logger.info(f"Started Deezer sync for: {playlist_name} ({len(spotify_tracks)} tracks)") return jsonify({"success": True, "sync_playlist_id": sync_playlist_id}) except Exception as e: logger.error(f"Error starting Deezer sync: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/sync/status/', methods=['GET']) def get_deezer_sync_status(playlist_id): """Get sync status for a Deezer playlist""" try: if playlist_id not in deezer_discovery_states: return jsonify({"error": "Deezer playlist not found"}), 404 state = deezer_discovery_states[playlist_id] state['last_accessed'] = time.time() sync_playlist_id = state.get('sync_playlist_id') if not sync_playlist_id: return jsonify({"error": "No sync in progress"}), 404 # Get sync status from existing sync infrastructure with sync_lock: sync_state = sync_states.get(sync_playlist_id, {}) response = { 'phase': state['phase'], 'sync_status': sync_state.get('status', 'unknown'), 'progress': sync_state.get('progress', {}), 'complete': sync_state.get('status') == 'finished', 'error': sync_state.get('error') } # Update Deezer state if sync completed if sync_state.get('status') == 'finished': state['phase'] = 'sync_complete' state['sync_progress'] = sync_state.get('progress', {}) playlist_name = state['playlist']['name'] add_activity_item("", "Sync Complete", f"Deezer playlist '{playlist_name}' synced successfully", "Now") elif sync_state.get('status') == 'error': state['phase'] = 'discovered' # Revert on error playlist_name = state['playlist']['name'] add_activity_item("", "Sync Failed", f"Deezer playlist '{playlist_name}' sync failed", "Now") return jsonify(response) except Exception as e: logger.error(f"Error getting Deezer sync status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/deezer/sync/cancel/', methods=['POST']) def cancel_deezer_sync(playlist_id): """Cancel sync for a Deezer playlist""" try: if playlist_id not in deezer_discovery_states: return jsonify({"error": "Deezer playlist not found"}), 404 state = deezer_discovery_states[playlist_id] state['last_accessed'] = time.time() sync_playlist_id = state.get('sync_playlist_id') if sync_playlist_id: # Cancel the sync using existing sync infrastructure with sync_lock: sync_states[sync_playlist_id] = {"status": "cancelled"} # Clean up sync worker if sync_playlist_id in active_sync_workers: del active_sync_workers[sync_playlist_id] # Revert Deezer state state['phase'] = 'discovered' state['sync_playlist_id'] = None state['sync_progress'] = {} return jsonify({"success": True, "message": "Deezer sync cancelled"}) except Exception as e: logger.error(f"Error cancelling Deezer sync: {e}") return jsonify({"error": str(e)}), 500 # =================================================================== # SPOTIFY PUBLIC PLAYLIST DISCOVERY API ENDPOINTS # =================================================================== # Global state for Spotify Public playlist management spotify_public_discovery_states = {} # Key: url_hash, Value: discovery state spotify_public_discovery_executor = ThreadPoolExecutor(max_workers=3, thread_name_prefix="spotify_public_discovery") @app.route('/api/spotify/parse-public', methods=['POST']) def parse_spotify_public_endpoint(): """Parse a public Spotify playlist or album URL without API auth""" try: data = request.get_json() url = data.get('url', '').strip() if not url: return jsonify({"error": "Spotify URL is required"}), 400 from core.spotify_public_scraper import parse_spotify_url, scrape_spotify_embed parsed = parse_spotify_url(url) if not parsed: return jsonify({"error": "Invalid Spotify URL. Please use a playlist or album link from open.spotify.com"}), 400 logger.info(f"Scraping public Spotify {parsed['type']}: {parsed['id']}") result = scrape_spotify_embed(parsed['type'], parsed['id']) if 'error' in result: return jsonify(result), 400 # Convert scraped tracks to Spotify-compatible format spotify_tracks = [] for track in result['tracks']: spotify_tracks.append({ 'id': track['id'], 'name': track['name'], 'artists': track['artists'], 'album': { 'name': result['name'] if result['type'] == 'album' else '', 'images': [] }, 'duration_ms': track['duration_ms'], 'explicit': track.get('is_explicit', False), 'track_number': track.get('track_number', 0) }) url_hash = result['url_hash'] response_data = { 'id': result['id'], 'type': result['type'], 'name': result['name'], 'subtitle': result['subtitle'], 'url': result['url'], 'url_hash': url_hash, 'track_count': len(spotify_tracks), 'tracks': spotify_tracks } # Store playlist data in state for discovery (if not already there) if url_hash not in spotify_public_discovery_states: spotify_public_discovery_states[url_hash] = { 'playlist': response_data, 'phase': 'fresh', 'status': 'fresh', 'discovery_progress': 0, 'spotify_matches': 0, 'spotify_total': len(spotify_tracks), 'discovery_results': [], 'sync_playlist_id': None, 'converted_spotify_playlist_id': None, 'download_process_id': None, 'created_at': time.time(), 'last_accessed': time.time(), 'discovery_future': None, 'sync_progress': {} } else: # Update playlist data in existing state spotify_public_discovery_states[url_hash]['playlist'] = response_data spotify_public_discovery_states[url_hash]['last_accessed'] = time.time() logger.info(f"Spotify {parsed['type']} scraped: {result['name']} ({len(spotify_tracks)} tracks)") return jsonify(response_data) except Exception as e: logger.error(f"Error parsing Spotify URL: {e}") import traceback traceback.print_exc() return jsonify({"error": str(e)}), 500 @app.route('/api/spotify-public/discovery/start/', methods=['POST']) def start_spotify_public_discovery(url_hash): """Start Spotify discovery process for a Spotify Public playlist""" try: # Initialize discovery state if it doesn't exist, or update existing state if url_hash in spotify_public_discovery_states: existing_state = spotify_public_discovery_states[url_hash] if existing_state['phase'] == 'discovering': return jsonify({"error": "Discovery already in progress"}), 400 if not existing_state.get('playlist'): return jsonify({"error": "Spotify Public playlist not found. Please parse the URL first."}), 404 # Update existing state for discovery existing_state['phase'] = 'discovering' existing_state['status'] = 'discovering' existing_state['last_accessed'] = time.time() state = existing_state else: return jsonify({"error": "Spotify Public playlist not found. Please parse the URL first."}), 404 # Add activity for discovery start playlist_name = state['playlist']['name'] track_count = len(state['playlist']['tracks']) add_activity_item("", "Spotify Link Discovery Started", f"'{playlist_name}' - {track_count} tracks", "Now") # Start discovery worker future = spotify_public_discovery_executor.submit(_run_spotify_public_discovery_worker, url_hash) state['discovery_future'] = future logger.info(f"Started Spotify discovery for Spotify Public playlist: {playlist_name}") return jsonify({"success": True, "message": "Discovery started"}) except Exception as e: logger.error(f"Error starting Spotify Public discovery: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify-public/discovery/status/', methods=['GET']) def get_spotify_public_discovery_status(url_hash): """Get real-time discovery status for a Spotify Public playlist""" try: if url_hash not in spotify_public_discovery_states: return jsonify({"error": "Spotify Public discovery not found"}), 404 state = spotify_public_discovery_states[url_hash] state['last_accessed'] = time.time() response = { 'phase': state['phase'], 'status': state['status'], 'progress': state['discovery_progress'], 'spotify_matches': state['spotify_matches'], 'spotify_total': state['spotify_total'], 'results': state['discovery_results'], 'complete': state['phase'] == 'discovered' } return jsonify(response) except Exception as e: logger.error(f"Error getting Spotify Public discovery status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify-public/discovery/update_match', methods=['POST']) def update_spotify_public_discovery_match(): """Update a Spotify Public discovery result with manually selected Spotify track""" try: data = request.get_json() identifier = data.get('identifier') # url_hash track_index = data.get('track_index') spotify_track = data.get('spotify_track') if not identifier or track_index is None or not spotify_track: return jsonify({'error': 'Missing required fields'}), 400 # Get the state state = spotify_public_discovery_states.get(identifier) if not state: return jsonify({'error': 'Discovery state not found'}), 404 if track_index >= len(state['discovery_results']): return jsonify({'error': 'Invalid track index'}), 400 # Update the result result = state['discovery_results'][track_index] old_status = result.get('status') # Update with user-selected track result['status'] = 'Found' result['status_class'] = 'found' result['spotify_track'] = spotify_track['name'] result['spotify_artist'] = _join_artist_names(spotify_track['artists']) if isinstance(spotify_track['artists'], list) else _extract_artist_name(spotify_track['artists']) result['spotify_album'] = spotify_track['album'] result['spotify_id'] = spotify_track['id'] # Format duration duration_ms = spotify_track.get('duration_ms', 0) if duration_ms: minutes = duration_ms // 60000 seconds = (duration_ms % 60000) // 1000 result['duration'] = f"{minutes}:{seconds:02d}" else: result['duration'] = '0:00' # IMPORTANT: Also set spotify_data for sync/download compatibility. # Manual match from the fix modal — build a rich spotify_data (album # as dict with image info) matching the normal discovery shape, and # explicitly clear any prior wing-it flag since the user picked a # real metadata match. result['spotify_data'] = _build_fix_modal_spotify_data(spotify_track) result['wing_it_fallback'] = False result['manual_match'] = True # Update match count if status changed from not found/error if old_status != 'found' and old_status != 'Found': state['spotify_matches'] = state.get('spotify_matches', 0) + 1 logger.info(f"Manual match updated: spotify_public - {identifier} - track {track_index}") logger.info(f" → {result['spotify_artist']} - {result['spotify_track']}") # Save manual fix to discovery cache so it appears in discovery pool try: original_track = result.get('spotify_public_track', {}) original_name = original_track.get('name', spotify_track['name']) original_artists = original_track.get('artists', []) original_artist = original_artists[0] if original_artists else '' cache_key = _get_discovery_cache_key(original_name, original_artist) # Normalize artists to plain strings for cache consistency artists_list = spotify_track['artists'] if isinstance(artists_list, list): artists_list = [a if isinstance(a, str) else a.get('name', '') for a in artists_list] # Preserve cover image info so the download pipeline can find # artwork when this cached match is used later. The fix modal # sends image_url at the top level; search results often return # album as a bare string, which previously dropped the artwork. image_url = spotify_track.get('image_url') or '' album_raw = spotify_track.get('album', '') if isinstance(album_raw, dict): album_obj = dict(album_raw) if image_url and not album_obj.get('image_url'): album_obj['image_url'] = image_url if image_url and not album_obj.get('images'): album_obj['images'] = [{'url': image_url}] else: album_obj = {'name': album_raw or ''} if image_url: album_obj['image_url'] = image_url album_obj['images'] = [{'url': image_url}] matched_data = { 'id': spotify_track['id'], 'name': spotify_track['name'], 'artists': artists_list, 'album': album_obj, 'duration_ms': spotify_track.get('duration_ms', 0), 'image_url': image_url, 'source': 'spotify', } cache_db = get_database() cache_db.save_discovery_cache_match( cache_key[0], cache_key[1], _get_active_discovery_source(), 1.0, matched_data, original_name, original_artist ) logger.info(f"Manual fix saved to discovery cache: {original_name} by {original_artist}") except Exception as cache_err: logger.error(f"Error saving manual fix to discovery cache: {cache_err}") return jsonify({'success': True, 'result': result}) except Exception as e: logger.error(f"Error updating Spotify Public discovery match: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/spotify-public/playlists/states', methods=['GET']) def get_spotify_public_playlist_states(): """Get all stored Spotify Public playlist discovery states for frontend hydration""" try: states = [] current_time = time.time() for url_hash, state in spotify_public_discovery_states.items(): state['last_accessed'] = current_time state_info = { 'playlist_id': url_hash, 'phase': state['phase'], 'status': state['status'], 'discovery_progress': state['discovery_progress'], 'spotify_matches': state['spotify_matches'], 'spotify_total': state['spotify_total'], 'discovery_results': state['discovery_results'], 'converted_spotify_playlist_id': state.get('converted_spotify_playlist_id'), 'download_process_id': state.get('download_process_id'), 'last_accessed': state['last_accessed'] } states.append(state_info) logger.info(f"Returning {len(states)} stored Spotify Public playlist states for hydration") return jsonify({"states": states}) except Exception as e: logger.error(f"Error getting Spotify Public playlist states: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify-public/state/', methods=['GET']) def get_spotify_public_playlist_state(url_hash): """Get specific Spotify Public playlist state (detailed version)""" try: if url_hash not in spotify_public_discovery_states: return jsonify({"error": "Spotify Public playlist not found"}), 404 state = spotify_public_discovery_states[url_hash] state['last_accessed'] = time.time() response = { 'playlist_id': url_hash, 'playlist': state['playlist'], 'phase': state['phase'], 'status': state['status'], 'discovery_progress': state['discovery_progress'], 'spotify_matches': state['spotify_matches'], 'spotify_total': state['spotify_total'], 'discovery_results': state['discovery_results'], 'sync_playlist_id': state.get('sync_playlist_id'), 'converted_spotify_playlist_id': state.get('converted_spotify_playlist_id'), 'download_process_id': state.get('download_process_id'), 'sync_progress': state.get('sync_progress', {}), 'last_accessed': state['last_accessed'] } return jsonify(response) except Exception as e: logger.error(f"Error getting Spotify Public playlist state: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify-public/reset/', methods=['POST']) def reset_spotify_public_playlist(url_hash): """Reset Spotify Public playlist to fresh phase (clear discovery/sync data)""" try: if url_hash not in spotify_public_discovery_states: return jsonify({"error": "Spotify Public playlist not found"}), 404 state = spotify_public_discovery_states[url_hash] # Stop any active discovery if 'discovery_future' in state and state['discovery_future']: state['discovery_future'].cancel() # Reset state to fresh (preserve original playlist data) state['phase'] = 'fresh' state['status'] = 'fresh' state['discovery_results'] = [] state['discovery_progress'] = 0 state['spotify_matches'] = 0 state['sync_playlist_id'] = None state['converted_spotify_playlist_id'] = None state['download_process_id'] = None state['sync_progress'] = {} state['discovery_future'] = None state['last_accessed'] = time.time() logger.info(f"Reset Spotify Public playlist to fresh: {url_hash}") return jsonify({"success": True, "message": "Playlist reset to fresh phase"}) except Exception as e: logger.error(f"Error resetting Spotify Public playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify-public/delete/', methods=['POST']) def delete_spotify_public_playlist(url_hash): """Delete Spotify Public playlist state completely""" try: if url_hash not in spotify_public_discovery_states: return jsonify({"error": "Spotify Public playlist not found"}), 404 state = spotify_public_discovery_states[url_hash] # Stop any active discovery if 'discovery_future' in state and state['discovery_future']: state['discovery_future'].cancel() # Remove from state dictionary del spotify_public_discovery_states[url_hash] logger.info(f"Deleted Spotify Public playlist state: {url_hash}") return jsonify({"success": True, "message": "Playlist deleted"}) except Exception as e: logger.error(f"Error deleting Spotify Public playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify-public/update_phase/', methods=['POST']) def update_spotify_public_playlist_phase(url_hash): """Update Spotify Public playlist phase (used when modal closes to reset from download_complete to discovered)""" try: if url_hash not in spotify_public_discovery_states: return jsonify({"error": "Spotify Public playlist not found"}), 404 data = request.get_json() if not data or 'phase' not in data: return jsonify({"error": "Phase not provided"}), 400 new_phase = data['phase'] valid_phases = ['fresh', 'discovering', 'discovered', 'syncing', 'sync_complete', 'downloading', 'download_complete'] if new_phase not in valid_phases: return jsonify({"error": f"Invalid phase. Must be one of: {', '.join(valid_phases)}"}), 400 state = spotify_public_discovery_states[url_hash] old_phase = state.get('phase', 'unknown') state['phase'] = new_phase state['last_accessed'] = time.time() # Update download process ID if provided (for download persistence) if 'download_process_id' in data: state['download_process_id'] = data['download_process_id'] # Update converted Spotify playlist ID if provided (for download persistence) if 'converted_spotify_playlist_id' in data: state['converted_spotify_playlist_id'] = data['converted_spotify_playlist_id'] logger.info(f"Updated Spotify Public playlist {url_hash} phase: {old_phase} → {new_phase}") return jsonify({"success": True, "message": f"Phase updated to {new_phase}", "old_phase": old_phase, "new_phase": new_phase}) except Exception as e: logger.error(f"Error updating Spotify Public playlist phase: {e}") return jsonify({"error": str(e)}), 500 # Spotify Public discovery worker logic lives in core/discovery/spotify_public.py. from core.discovery import spotify_public as _discovery_spotify_public def _build_spotify_public_discovery_deps(): """Build the SpotifyPublicDiscoveryDeps bundle from web_server.py globals on each call.""" return _discovery_spotify_public.SpotifyPublicDiscoveryDeps( spotify_public_discovery_states=spotify_public_discovery_states, spotify_client=spotify_client, pause_enrichment_workers=_pause_enrichment_workers, resume_enrichment_workers=_resume_enrichment_workers, get_active_discovery_source=_get_active_discovery_source, get_metadata_fallback_client=_get_metadata_fallback_client, get_discovery_cache_key=_get_discovery_cache_key, get_database=get_database, validate_discovery_cache_artist=_validate_discovery_cache_artist, search_spotify_for_tidal_track=_search_spotify_for_tidal_track, build_discovery_wing_it_stub=_build_discovery_wing_it_stub, add_activity_item=add_activity_item, ) def _run_spotify_public_discovery_worker(url_hash): return _discovery_spotify_public.run_spotify_public_discovery_worker( url_hash, _build_spotify_public_discovery_deps() ) def convert_spotify_public_results_to_spotify_tracks(discovery_results): """Convert Spotify Public discovery results to Spotify tracks format for sync""" spotify_tracks = [] for result in discovery_results: # Support both data formats: spotify_data (manual fixes) and individual fields (automatic discovery) if result.get('spotify_data'): spotify_data = result['spotify_data'] track = { 'id': spotify_data['id'], 'name': spotify_data['name'], 'artists': spotify_data['artists'], 'album': spotify_data['album'], 'duration_ms': spotify_data.get('duration_ms', 0) } # Preserve track_number/disc_number from discovery enrichment if spotify_data.get('track_number'): track['track_number'] = spotify_data['track_number'] if spotify_data.get('disc_number'): track['disc_number'] = spotify_data['disc_number'] spotify_tracks.append(track) elif result.get('spotify_track') and result.get('status_class') == 'found': track = { 'id': result.get('spotify_id', 'unknown'), 'name': result.get('spotify_track', 'Unknown Track'), 'artists': [result.get('spotify_artist', 'Unknown Artist')] if result.get('spotify_artist') else ['Unknown Artist'], 'album': result.get('spotify_album', 'Unknown Album'), 'duration_ms': 0 } spotify_tracks.append(track) logger.info(f"Converted {len(spotify_tracks)} Spotify Public matches to Spotify tracks for sync") return spotify_tracks # =================================================================== # SPOTIFY PUBLIC SYNC API ENDPOINTS # =================================================================== @app.route('/api/spotify-public/sync/start/', methods=['POST']) def start_spotify_public_sync(url_hash): """Start sync process for a Spotify Public playlist using discovered Spotify tracks""" try: if url_hash not in spotify_public_discovery_states: return jsonify({"error": "Spotify Public playlist not found"}), 404 state = spotify_public_discovery_states[url_hash] state['last_accessed'] = time.time() if state['phase'] not in ['discovered', 'sync_complete', 'download_complete']: return jsonify({"error": "Spotify Public playlist not ready for sync"}), 400 # Convert discovery results to Spotify tracks format spotify_tracks = convert_spotify_public_results_to_spotify_tracks(state['discovery_results']) if not spotify_tracks: return jsonify({"error": "No Spotify matches found for sync"}), 400 # Create a temporary playlist ID for sync tracking sync_playlist_id = f"spotify_public_{url_hash}" playlist_name = state['playlist']['name'] # Add activity for sync start add_activity_item("", "Spotify Link Sync Started", f"'{playlist_name}' - {len(spotify_tracks)} tracks", "Now") # Update Spotify Public state state['phase'] = 'syncing' state['sync_playlist_id'] = sync_playlist_id state['sync_progress'] = {} # Start the sync using existing sync infrastructure sync_data = { 'playlist_id': sync_playlist_id, 'playlist_name': playlist_name, 'tracks': spotify_tracks } with sync_lock: sync_states[sync_playlist_id] = {"status": "starting", "progress": {}} # Submit sync task playlist_image_url = state['playlist'].get('image_url', '') future = sync_executor.submit(_run_sync_task, sync_playlist_id, sync_data['playlist_name'], spotify_tracks, None, get_current_profile_id(), playlist_image_url) active_sync_workers[sync_playlist_id] = future logger.info(f"Started Spotify Public sync for: {playlist_name} ({len(spotify_tracks)} tracks)") return jsonify({"success": True, "sync_playlist_id": sync_playlist_id}) except Exception as e: logger.error(f"Error starting Spotify Public sync: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify-public/sync/status/', methods=['GET']) def get_spotify_public_sync_status(url_hash): """Get sync status for a Spotify Public playlist""" try: if url_hash not in spotify_public_discovery_states: return jsonify({"error": "Spotify Public playlist not found"}), 404 state = spotify_public_discovery_states[url_hash] state['last_accessed'] = time.time() sync_playlist_id = state.get('sync_playlist_id') if not sync_playlist_id: return jsonify({"error": "No sync in progress"}), 404 # Get sync status from existing sync infrastructure with sync_lock: sync_state = sync_states.get(sync_playlist_id, {}) response = { 'phase': state['phase'], 'sync_status': sync_state.get('status', 'unknown'), 'progress': sync_state.get('progress', {}), 'complete': sync_state.get('status') == 'finished', 'error': sync_state.get('error') } # Update Spotify Public state if sync completed if sync_state.get('status') == 'finished': state['phase'] = 'sync_complete' state['sync_progress'] = sync_state.get('progress', {}) playlist_name = state['playlist']['name'] add_activity_item("", "Sync Complete", f"Spotify Link playlist '{playlist_name}' synced successfully", "Now") elif sync_state.get('status') == 'error': state['phase'] = 'discovered' # Revert on error playlist_name = state['playlist']['name'] add_activity_item("", "Sync Failed", f"Spotify Link playlist '{playlist_name}' sync failed", "Now") return jsonify(response) except Exception as e: logger.error(f"Error getting Spotify Public sync status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/spotify-public/sync/cancel/', methods=['POST']) def cancel_spotify_public_sync(url_hash): """Cancel sync for a Spotify Public playlist""" try: if url_hash not in spotify_public_discovery_states: return jsonify({"error": "Spotify Public playlist not found"}), 404 state = spotify_public_discovery_states[url_hash] state['last_accessed'] = time.time() sync_playlist_id = state.get('sync_playlist_id') if sync_playlist_id: # Cancel the sync using existing sync infrastructure with sync_lock: sync_states[sync_playlist_id] = {"status": "cancelled"} # Clean up sync worker if sync_playlist_id in active_sync_workers: del active_sync_workers[sync_playlist_id] # Revert Spotify Public state state['phase'] = 'discovered' state['sync_playlist_id'] = None state['sync_progress'] = {} return jsonify({"success": True, "message": "Spotify Public sync cancelled"}) except Exception as e: logger.error(f"Error cancelling Spotify Public sync: {e}") return jsonify({"error": str(e)}), 500 # =================================================================== # YOUTUBE PLAYLIST API ENDPOINTS # =================================================================== # Global state for YouTube playlist management (persistent across page reloads) youtube_playlist_states = {} # Key: url_hash, Value: persistent playlist state youtube_discovery_executor = ThreadPoolExecutor(max_workers=3, thread_name_prefix="youtube_discovery") # Global state for Beatport chart management (persistent across page reloads) beatport_chart_states = {} # Key: url_hash, Value: persistent chart state beatport_discovery_executor = ThreadPoolExecutor(max_workers=3, thread_name_prefix="beatport_discovery") # Global state for ListenBrainz playlist management (persistent across page reloads) listenbrainz_playlist_states = {} # Key: playlist_mbid, Value: persistent playlist state listenbrainz_discovery_executor = ThreadPoolExecutor(max_workers=3, thread_name_prefix="listenbrainz_discovery") @app.route('/api/youtube/parse', methods=['POST']) def parse_youtube_playlist_endpoint(): """Parse a YouTube playlist URL and return structured track data""" try: data = request.get_json() url = data.get('url', '').strip() if not url: return jsonify({"error": "YouTube URL is required"}), 400 # Validate URL if not ('youtube.com/playlist' in url or 'music.youtube.com/playlist' in url): return jsonify({"error": "Invalid YouTube playlist URL"}), 400 logger.info(f"Parsing YouTube playlist: {url}") # Parse the playlist using our function playlist_data = parse_youtube_playlist(url) if not playlist_data: return jsonify({"error": "Failed to parse YouTube playlist"}), 500 # Use deterministic hash for state tracking (built-in hash() is randomized per process restart) import hashlib yt_playlist_id = playlist_data.get('id', '') if yt_playlist_id and yt_playlist_id != 'unknown_id': # Use canonical URL with the stable YouTube playlist ID canonical_url = f"https://youtube.com/playlist?list={yt_playlist_id}" else: canonical_url = url url_hash = hashlib.md5(canonical_url.encode()).hexdigest()[:12] # Migrate existing mirrored playlists that used the old non-deterministic hash() # and deduplicate any copies created by the bug try: database = get_database() profile_id = get_current_profile_id() existing = database.get_mirrored_playlists(profile_id=profile_id) yt_dupes = [mp for mp in existing if mp['source'] == 'youtube' and mp['name'] == playlist_data['name']] if yt_dupes: # Keep the newest one, delete the rest keep = yt_dupes[0] # Already sorted by updated_at DESC from get_mirrored_playlists for dupe in yt_dupes[1:]: database.delete_mirrored_playlist(dupe['id']) logger.info(f"Removed duplicate YouTube mirrored playlist '{dupe['name']}' (id={dupe['id']})") # Update the kept entry's source_playlist_id to the new deterministic hash if keep['source_playlist_id'] != url_hash: with database._get_connection() as conn: cursor = conn.cursor() cursor.execute( "UPDATE mirrored_playlists SET source_playlist_id = ? WHERE id = ?", (url_hash, keep['id']) ) conn.commit() logger.info(f"Migrated YouTube mirrored playlist '{keep['name']}' source_playlist_id to deterministic hash {url_hash}") except Exception as e: logger.debug(f"YouTube mirror migration check: {e}") # Initialize persistent playlist state (similar to Spotify download_batches structure) youtube_playlist_states[url_hash] = { 'playlist': playlist_data, 'phase': 'fresh', # fresh -> discovering -> discovered -> syncing -> sync_complete -> downloading -> download_complete 'discovery_results': [], 'discovery_progress': 0, 'spotify_matches': 0, 'spotify_total': len(playlist_data['tracks']), 'status': 'parsed', 'url': url, 'sync_playlist_id': None, 'converted_spotify_playlist_id': None, 'download_process_id': None, # Track associated download missing tracks process 'created_at': time.time(), 'last_accessed': time.time(), 'discovery_future': None, 'sync_progress': {} } playlist_data['url_hash'] = url_hash logger.info(f"YouTube playlist parsed successfully: {playlist_data['name']} ({len(playlist_data['tracks'])} tracks)") return jsonify(playlist_data) except Exception as e: logger.error(f"Error parsing YouTube playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/youtube/discovery/start/', methods=['POST']) def start_youtube_discovery(url_hash): """Start Spotify discovery process for a YouTube playlist""" try: if url_hash not in youtube_playlist_states: return jsonify({"error": "YouTube playlist not found"}), 404 state = youtube_playlist_states[url_hash] state['last_accessed'] = time.time() # Update access time if state['phase'] == 'discovering': return jsonify({"error": "Discovery already in progress"}), 400 # Update phase to discovering state['phase'] = 'discovering' state['status'] = 'discovering' state['discovery_progress'] = 0 state['spotify_matches'] = 0 state['discovery_results'] = [] # Clear skip_discovery flags on all tracks (in case of prior retry) for track in state['playlist']['tracks']: track.pop('skip_discovery', None) # Add activity for discovery start playlist_name = state['playlist']['name'] track_count = len(state['playlist']['tracks']) add_activity_item("", "YouTube Discovery Started", f"'{playlist_name}' - {track_count} tracks", "Now") # Start discovery worker future = youtube_discovery_executor.submit(_run_youtube_discovery_worker, url_hash) state['discovery_future'] = future logger.info(f"Started Spotify discovery for YouTube playlist: {state['playlist']['name']}") return jsonify({"success": True, "message": "Discovery started"}) except Exception as e: logger.error(f"Error starting YouTube discovery: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/youtube/discovery/status/', methods=['GET']) def get_youtube_discovery_status(url_hash): """Get real-time discovery status for a YouTube playlist""" try: if url_hash not in youtube_playlist_states: return jsonify({"error": "YouTube playlist not found"}), 404 state = youtube_playlist_states[url_hash] state['last_accessed'] = time.time() # Update access time response = { 'phase': state['phase'], 'status': state['status'], 'progress': state['discovery_progress'], 'spotify_matches': state['spotify_matches'], 'spotify_total': state['spotify_total'], 'results': state['discovery_results'], 'complete': state['phase'] == 'discovered' } return jsonify(response) except Exception as e: logger.error(f"Error getting YouTube discovery status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/youtube/discovery/unmatch', methods=['POST']) @app.route('/api/tidal/discovery/unmatch', methods=['POST']) @app.route('/api/deezer/discovery/unmatch', methods=['POST']) @app.route('/api/spotify-public/discovery/unmatch', methods=['POST']) @app.route('/api/beatport/discovery/unmatch', methods=['POST']) @app.route('/api/listenbrainz/discovery/unmatch', methods=['POST']) def unmatch_discovery_track(): """Remove a discovery match — sets track back to Not Found""" try: data = request.get_json() identifier = data.get('identifier') track_index = data.get('track_index') if not identifier or track_index is None: return jsonify({'success': False, 'error': 'Missing required fields'}), 400 # Find the state dict for this discovery state = (youtube_playlist_states.get(identifier) or tidal_discovery_states.get(identifier) or deezer_discovery_states.get(identifier) or spotify_public_discovery_states.get(identifier) or beatport_chart_states.get(identifier) or listenbrainz_playlist_states.get(identifier)) if not state: return jsonify({'success': False, 'error': 'Discovery state not found'}), 404 results = state.get('discovery_results', []) if track_index >= len(results): return jsonify({'success': False, 'error': 'Invalid track index'}), 400 result = results[track_index] old_status = result.get('status_class') # Clear the match result['status'] = 'Not Found' result['status_class'] = 'not-found' result['spotify_track'] = '' result['spotify_artist'] = '' result['spotify_album'] = '' result['spotify_data'] = None result['matched_data'] = None result['match_data'] = None result['confidence'] = 0 result['wing_it_fallback'] = False result['manual_match'] = False # Update match count if old_status in ('found', 'wing-it'): state['spotify_matches'] = max(0, state.get('spotify_matches', 0) - 1) if old_status == 'wing-it': state['wing_it_count'] = max(0, state.get('wing_it_count', 0) - 1) # If mirrored playlist, also clear in DB if identifier.startswith('mirrored_'): try: db = get_database() tracks = state.get('tracks', []) if track_index < len(tracks): db_track_id = tracks[track_index].get('db_track_id') if db_track_id: db.update_mirrored_track_extra_data(db_track_id, { 'discovered': False, 'discovery_attempted': True, 'provider': '', 'unmatched_by_user': True, }) except Exception as e: logger.error(f"Error clearing mirrored track match: {e}") logger.info(f"Unmatched discovery track {track_index}: {result.get('yt_track', result.get('lb_track', ''))}") return jsonify({'success': True}) except Exception as e: logger.error(f"Error unmatching discovery track: {e}") return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/youtube/discovery/update_match', methods=['POST']) def update_youtube_discovery_match(): """Update a YouTube discovery result with manually selected Spotify track""" try: data = request.get_json() identifier = data.get('identifier') # url_hash track_index = data.get('track_index') spotify_track = data.get('spotify_track') if not identifier or track_index is None or not spotify_track: return jsonify({'error': 'Missing required fields'}), 400 # Get the state state = youtube_playlist_states.get(identifier) if not state: return jsonify({'error': 'Discovery state not found'}), 404 if track_index >= len(state['discovery_results']): return jsonify({'error': 'Invalid track index'}), 400 # Update the result result = state['discovery_results'][track_index] old_status = result.get('status') # Update with user-selected track result['status'] = 'Found' result['status_class'] = 'found' result['spotify_track'] = spotify_track['name'] result['spotify_artist'] = _join_artist_names(spotify_track['artists']) if isinstance(spotify_track['artists'], list) else _extract_artist_name(spotify_track['artists']) result['spotify_album'] = spotify_track['album'] result['spotify_id'] = spotify_track['id'] # Format duration duration_ms = spotify_track.get('duration_ms', 0) if duration_ms: minutes = duration_ms // 60000 seconds = (duration_ms % 60000) // 1000 result['duration'] = f"{minutes}:{seconds:02d}" else: result['duration'] = '0:00' # IMPORTANT: Also set spotify_data for sync/download compatibility. # Manual match from the fix modal — build a rich spotify_data (album # as dict with image info) matching the normal discovery shape, and # explicitly clear any prior wing-it flag since the user picked a # real metadata match. result['spotify_data'] = _build_fix_modal_spotify_data(spotify_track) result['wing_it_fallback'] = False result['manual_match'] = True # Flag for tracking # Update match count if status changed from not found/error if old_status != 'found' and old_status != 'Found': state['spotify_matches'] = state.get('spotify_matches', 0) + 1 logger.info(f"Manual match updated: youtube - {identifier} - track {track_index}") logger.info(f" → {result['spotify_artist']} - {result['spotify_track']}") # Save manual fix to discovery cache so it appears in discovery pool try: # Get original track name from the YouTube/source track data original_track = result.get('youtube_track', result.get('tidal_track', result.get('deezer_track', {}))) original_name = original_track.get('name', spotify_track['name']) original_artists = original_track.get('artists', []) if original_artists: original_artist = original_artists[0] if isinstance(original_artists[0], str) else original_artists[0].get('name', '') else: original_artist = '' cache_key = _get_discovery_cache_key(original_name, original_artist) # Normalize artists to plain strings for cache consistency artists_list = spotify_track['artists'] if isinstance(artists_list, list): artists_list = [a if isinstance(a, str) else a.get('name', '') for a in artists_list] # Preserve cover image info so the download pipeline can find # artwork when this cached match is used later. The fix modal # sends image_url at the top level; search results often return # album as a bare string, which previously dropped the artwork. image_url = spotify_track.get('image_url') or '' album_raw = spotify_track.get('album', '') if isinstance(album_raw, dict): album_obj = dict(album_raw) if image_url and not album_obj.get('image_url'): album_obj['image_url'] = image_url if image_url and not album_obj.get('images'): album_obj['images'] = [{'url': image_url}] else: album_obj = {'name': album_raw or ''} if image_url: album_obj['image_url'] = image_url album_obj['images'] = [{'url': image_url}] matched_data = { 'id': spotify_track['id'], 'name': spotify_track['name'], 'artists': artists_list, 'album': album_obj, 'duration_ms': spotify_track.get('duration_ms', 0), 'image_url': image_url, 'source': 'spotify', } cache_db = get_database() cache_db.save_discovery_cache_match( cache_key[0], cache_key[1], _get_active_discovery_source(), 1.0, matched_data, original_name, original_artist ) logger.info(f"Manual fix saved to discovery cache: {original_name} by {original_artist}") except Exception as cache_err: logger.error(f"Error saving manual fix to discovery cache: {cache_err}") # Persist manual fix to DB for mirrored playlists if identifier.startswith('mirrored_'): try: tracks = state['playlist']['tracks'] if track_index < len(tracks): db_track_id = tracks[track_index].get('db_track_id') if db_track_id: db = get_database() extra_data = { 'discovered': True, 'provider': 'spotify', 'confidence': 1.0, 'matched_data': matched_data, 'manual_match': True, } db.update_mirrored_track_extra_data(db_track_id, extra_data) result['matched_data'] = matched_data logger.info(f"Persisted manual fix to DB for track {db_track_id}") except Exception as wb_err: logger.error(f"Error persisting manual fix to DB: {wb_err}") return jsonify({'success': True, 'result': result}) except Exception as e: logger.error(f"Error updating YouTube discovery match: {e}") return jsonify({'error': str(e)}), 500 def _build_discovery_wing_it_stub(track_name, artist_name, duration_ms=0, image_url=''): """Build stub matched_data for tracks that failed metadata discovery. Used as automatic Wing It fallback so tracks still flow through the download pipeline.""" return { 'id': f"wing_it_{hash(f'{artist_name}_{track_name}') % 100000}", 'name': track_name, 'artists': [{'name': artist_name}] if isinstance(artist_name, str) else artist_name, 'album': {'name': '', 'album_type': 'single', 'images': [], 'release_date': ''}, 'duration_ms': duration_ms, 'image_url': image_url, 'source': 'wing_it_fallback', } def _build_fix_modal_spotify_data(spotify_track): """Build a rich spotify_data dict from the fix-modal POST payload so manual matches carry the same shape as normal discovery results. Key points: - album is always a dict (normal discovery has it this way; legacy fix-modal produced a bare string which broke cover art lookup downstream) - image_url is carried both at top level and inside album.images for parity with Spotify API responses - handles both legacy string albums (most search endpoints return this) and newer object albums """ if not isinstance(spotify_track, dict): spotify_track = {} image_url = spotify_track.get('image_url') or '' album_raw = spotify_track.get('album', '') if isinstance(album_raw, dict): album_obj = dict(album_raw) if image_url and not album_obj.get('image_url'): album_obj['image_url'] = image_url if image_url and not album_obj.get('images'): album_obj['images'] = [{'url': image_url}] else: album_obj = {'name': album_raw or ''} if image_url: album_obj['image_url'] = image_url album_obj['images'] = [{'url': image_url}] return { 'id': spotify_track.get('id', ''), 'name': spotify_track.get('name', ''), 'artists': spotify_track.get('artists', []), 'album': album_obj, 'duration_ms': spotify_track.get('duration_ms', 0), 'image_url': image_url, } # YouTube discovery worker logic lives in core/discovery/youtube.py. from core.discovery import youtube as _discovery_youtube def _build_youtube_discovery_deps(): """Build the YoutubeDiscoveryDeps bundle from web_server.py globals on each call.""" return _discovery_youtube.YoutubeDiscoveryDeps( youtube_playlist_states=youtube_playlist_states, spotify_client=spotify_client, matching_engine=matching_engine, pause_enrichment_workers=_pause_enrichment_workers, resume_enrichment_workers=_resume_enrichment_workers, get_active_discovery_source=_get_active_discovery_source, get_metadata_fallback_client=_get_metadata_fallback_client, get_discovery_cache_key=_get_discovery_cache_key, validate_discovery_cache_artist=_validate_discovery_cache_artist, extract_artist_name=_extract_artist_name, spotify_rate_limited=_spotify_rate_limited, discovery_score_candidates=_discovery_score_candidates, get_metadata_cache=get_metadata_cache, build_discovery_wing_it_stub=_build_discovery_wing_it_stub, get_database=get_database, add_activity_item=add_activity_item, ) def _run_youtube_discovery_worker(url_hash): return _discovery_youtube.run_youtube_discovery_worker(url_hash, _build_youtube_discovery_deps()) # ListenBrainz discovery worker logic lives in core/discovery/listenbrainz.py. from core.discovery import listenbrainz as _discovery_listenbrainz def _build_listenbrainz_discovery_deps(): """Build the ListenbrainzDiscoveryDeps bundle from web_server.py globals on each call.""" return _discovery_listenbrainz.ListenbrainzDiscoveryDeps( listenbrainz_playlist_states=listenbrainz_playlist_states, spotify_client=spotify_client, matching_engine=matching_engine, pause_enrichment_workers=_pause_enrichment_workers, resume_enrichment_workers=_resume_enrichment_workers, get_active_discovery_source=_get_active_discovery_source, get_metadata_fallback_client=_get_metadata_fallback_client, get_discovery_cache_key=_get_discovery_cache_key, get_database=get_database, validate_discovery_cache_artist=_validate_discovery_cache_artist, extract_artist_name=_extract_artist_name, spotify_rate_limited=_spotify_rate_limited, discovery_score_candidates=_discovery_score_candidates, get_metadata_cache=get_metadata_cache, build_discovery_wing_it_stub=_build_discovery_wing_it_stub, add_activity_item=add_activity_item, ) def _run_listenbrainz_discovery_worker(state_key): return _discovery_listenbrainz.run_listenbrainz_discovery_worker( state_key, _build_listenbrainz_discovery_deps() ) def _calculate_similarity(str1, str2): """Calculate string similarity using simple character overlap""" if not str1 or not str2: return 0 # Convert to lowercase and remove extra spaces str1 = str1.lower().strip() str2 = str2.lower().strip() if str1 == str2: return 1.0 # Calculate character overlap set1 = set(str1.replace(' ', '')) set2 = set(str2.replace(' ', '')) if not set1 or not set2: return 0 intersection = len(set1.intersection(set2)) union = len(set1.union(set2)) return intersection / union if union > 0 else 0 @app.route('/api/youtube/sync/start/', methods=['POST']) def start_youtube_sync(url_hash): """Start sync process for a YouTube playlist using discovered Spotify tracks""" try: if url_hash not in youtube_playlist_states: return jsonify({"error": "YouTube playlist not found"}), 404 state = youtube_playlist_states[url_hash] state['last_accessed'] = time.time() # Update access time if state['phase'] not in ['discovered', 'sync_complete', 'download_complete']: return jsonify({"error": "YouTube playlist not ready for sync"}), 400 # Convert discovery results to Spotify tracks format spotify_tracks = convert_youtube_results_to_spotify_tracks(state['discovery_results']) if not spotify_tracks: return jsonify({"error": "No Spotify matches found for sync"}), 400 # Create a temporary playlist ID for sync tracking sync_playlist_id = f"youtube_{url_hash}" playlist_name = state['playlist']['name'] # Add activity for sync start add_activity_item("", "YouTube Sync Started", f"'{playlist_name}' - {len(spotify_tracks)} tracks", "Now") # Update YouTube state state['phase'] = 'syncing' state['sync_playlist_id'] = sync_playlist_id state['sync_progress'] = {} # Start the sync using existing sync infrastructure sync_data = { 'playlist_id': sync_playlist_id, 'playlist_name': playlist_name, 'tracks': spotify_tracks } with sync_lock: sync_states[sync_playlist_id] = {"status": "starting", "progress": {}} # Submit sync task playlist_image_url = state['playlist'].get('image_url', '') future = sync_executor.submit(_run_sync_task, sync_playlist_id, sync_data['playlist_name'], spotify_tracks, None, get_current_profile_id(), playlist_image_url) active_sync_workers[sync_playlist_id] = future logger.info(f"Started YouTube sync for: {playlist_name} ({len(spotify_tracks)} tracks)") return jsonify({"success": True, "sync_playlist_id": sync_playlist_id}) except Exception as e: logger.error(f"Error starting YouTube sync: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/youtube/sync/status/', methods=['GET']) def get_youtube_sync_status(url_hash): """Get sync status for a YouTube playlist""" try: if url_hash not in youtube_playlist_states: return jsonify({"error": "YouTube playlist not found"}), 404 state = youtube_playlist_states[url_hash] state['last_accessed'] = time.time() # Update access time sync_playlist_id = state.get('sync_playlist_id') if not sync_playlist_id: return jsonify({"error": "No sync in progress"}), 404 # Get sync status from existing sync infrastructure with sync_lock: sync_state = sync_states.get(sync_playlist_id, {}) response = { 'phase': state['phase'], 'sync_status': sync_state.get('status', 'unknown'), 'progress': sync_state.get('progress', {}), 'complete': sync_state.get('status') == 'finished', 'error': sync_state.get('error') } # Update YouTube state if sync completed if sync_state.get('status') == 'finished': state['phase'] = 'sync_complete' state['sync_progress'] = sync_state.get('progress', {}) # Add activity for sync completion playlist_name = state.get('playlist', {}).get('name', 'Unknown Playlist') add_activity_item("", "Sync Complete", f"YouTube playlist '{playlist_name}' synced successfully", "Now") elif sync_state.get('status') == 'error': state['phase'] = 'discovered' # Revert on error playlist_name = state.get('playlist', {}).get('name', 'Unknown Playlist') add_activity_item("", "Sync Failed", f"YouTube playlist '{playlist_name}' sync failed", "Now") return jsonify(response) except Exception as e: logger.error(f"Error getting YouTube sync status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/youtube/sync/cancel/', methods=['POST']) def cancel_youtube_sync(url_hash): """Cancel sync for a YouTube playlist""" try: if url_hash not in youtube_playlist_states: return jsonify({"error": "YouTube playlist not found"}), 404 state = youtube_playlist_states[url_hash] state['last_accessed'] = time.time() # Update access time sync_playlist_id = state.get('sync_playlist_id') if sync_playlist_id: # Cancel the sync using existing sync infrastructure with sync_lock: sync_states[sync_playlist_id] = {"status": "cancelled"} # Clean up sync worker if sync_playlist_id in active_sync_workers: del active_sync_workers[sync_playlist_id] # Revert YouTube state state['phase'] = 'discovered' state['sync_playlist_id'] = None state['sync_progress'] = {} return jsonify({"success": True, "message": "YouTube sync cancelled"}) except Exception as e: logger.error(f"Error cancelling YouTube sync: {e}") return jsonify({"error": str(e)}), 500 # New YouTube Playlist Management Endpoints (for persistent state) @app.route('/api/youtube/playlists', methods=['GET']) def get_all_youtube_playlists(): """Get all stored YouTube playlists for frontend hydration (similar to Spotify playlists)""" try: playlists = [] current_time = time.time() for url_hash, state in youtube_playlist_states.items(): # Skip mirrored playlist entries — they have their own hydration if url_hash.startswith('mirrored_'): continue # Update access time when requested state['last_accessed'] = current_time # Return essential data for card recreation playlist_info = { 'url_hash': url_hash, 'url': state['url'], 'playlist': state['playlist'], 'phase': state['phase'], 'status': state['status'], 'discovery_progress': state['discovery_progress'], 'spotify_matches': state['spotify_matches'], 'spotify_total': state['spotify_total'], 'converted_spotify_playlist_id': state.get('converted_spotify_playlist_id'), 'download_process_id': state.get('download_process_id'), 'created_at': state['created_at'], 'last_accessed': state['last_accessed'] } playlists.append(playlist_info) logger.info(f"Returning {len(playlists)} stored YouTube playlists for hydration") return jsonify({"playlists": playlists}) except Exception as e: logger.error(f"Error getting YouTube playlists: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/youtube/state/', methods=['GET']) def get_youtube_playlist_state(url_hash): """Get specific YouTube playlist state (detailed version of status endpoint)""" try: if url_hash not in youtube_playlist_states: return jsonify({"error": "YouTube playlist not found"}), 404 state = youtube_playlist_states[url_hash] state['last_accessed'] = time.time() # Return full state information (including results for modal hydration) response = { 'url_hash': url_hash, 'url': state['url'], 'playlist': state['playlist'], 'phase': state['phase'], 'status': state['status'], 'discovery_progress': state['discovery_progress'], 'spotify_matches': state['spotify_matches'], 'spotify_total': state['spotify_total'], 'discovery_results': state['discovery_results'], 'sync_playlist_id': state['sync_playlist_id'], 'converted_spotify_playlist_id': state['converted_spotify_playlist_id'], 'sync_progress': state['sync_progress'], 'created_at': state['created_at'], 'last_accessed': state['last_accessed'] } return jsonify(response) except Exception as e: logger.error(f"Error getting YouTube playlist state: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/youtube/reset/', methods=['POST']) def reset_youtube_playlist(url_hash): """Reset YouTube playlist to fresh phase (clear discovery/sync data)""" try: if url_hash not in youtube_playlist_states: return jsonify({"error": "YouTube playlist not found"}), 404 state = youtube_playlist_states[url_hash] # Stop any active discovery if 'discovery_future' in state and state['discovery_future']: state['discovery_future'].cancel() # Reset state to fresh (preserve original playlist data) state['phase'] = 'fresh' state['status'] = 'parsed' state['discovery_results'] = [] state['discovery_progress'] = 0 state['spotify_matches'] = 0 state['sync_playlist_id'] = None state['converted_spotify_playlist_id'] = None state['sync_progress'] = {} state['discovery_future'] = None state['last_accessed'] = time.time() logger.info(f"Reset YouTube playlist to fresh phase: {state['playlist']['name']}") return jsonify({"success": True, "message": "Playlist reset to fresh state"}) except Exception as e: logger.error(f"Error resetting YouTube playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/youtube/delete/', methods=['DELETE']) def delete_youtube_playlist(url_hash): """Remove YouTube playlist from backend storage entirely""" try: if url_hash not in youtube_playlist_states: return jsonify({"error": "YouTube playlist not found"}), 404 state = youtube_playlist_states[url_hash] # Stop any active discovery if 'discovery_future' in state and state['discovery_future']: state['discovery_future'].cancel() # Remove from storage playlist_name = state['playlist']['name'] del youtube_playlist_states[url_hash] logger.info(f"Deleted YouTube playlist from backend: {playlist_name}") return jsonify({"success": True, "message": f"Playlist '{playlist_name}' deleted"}) except Exception as e: logger.error(f"Error deleting YouTube playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/youtube/update_phase/', methods=['POST']) def update_youtube_playlist_phase(url_hash): """Update YouTube playlist phase (used when modal closes to reset from download_complete to discovered)""" try: if url_hash not in youtube_playlist_states: return jsonify({"error": "YouTube playlist not found"}), 404 data = request.get_json() if not data or 'phase' not in data: return jsonify({"error": "Phase not provided"}), 400 new_phase = data['phase'] valid_phases = ['fresh', 'parsed', 'discovering', 'discovered', 'syncing', 'sync_complete', 'downloading', 'download_complete'] if new_phase not in valid_phases: return jsonify({"error": f"Invalid phase. Must be one of: {', '.join(valid_phases)}"}), 400 state = youtube_playlist_states[url_hash] old_phase = state.get('phase', 'unknown') state['phase'] = new_phase state['last_accessed'] = time.time() logger.info(f"Updated YouTube playlist {url_hash} phase: {old_phase} → {new_phase}") return jsonify({"success": True, "message": f"Phase updated to {new_phase}", "old_phase": old_phase, "new_phase": new_phase}) except Exception as e: logger.error(f"Error updating YouTube playlist phase: {e}") return jsonify({"error": str(e)}), 500 def convert_youtube_results_to_spotify_tracks(discovery_results): """Convert YouTube discovery results to Spotify tracks format for sync""" spotify_tracks = [] for result in discovery_results: # Support both data formats: spotify_data (manual fixes) and individual fields (automatic discovery) if result.get('spotify_data'): spotify_data = result['spotify_data'] # Create track object matching the expected format track = { 'id': spotify_data['id'], 'name': spotify_data['name'], 'artists': spotify_data['artists'], 'album': spotify_data['album'], 'duration_ms': spotify_data.get('duration_ms', 0) } if spotify_data.get('track_number'): track['track_number'] = spotify_data['track_number'] if spotify_data.get('disc_number'): track['disc_number'] = spotify_data['disc_number'] spotify_tracks.append(track) elif result.get('spotify_track') and result.get('status_class') == 'found': # Build from individual fields (automatic discovery format) track = { 'id': result.get('spotify_id', 'unknown'), 'name': result.get('spotify_track', 'Unknown Track'), 'artists': [result.get('spotify_artist', 'Unknown Artist')] if result.get('spotify_artist') else ['Unknown Artist'], 'album': result.get('spotify_album', 'Unknown Album'), 'duration_ms': 0 } spotify_tracks.append(track) logger.info(f"Converted {len(spotify_tracks)} YouTube matches to Spotify tracks for sync") return spotify_tracks # Add these new endpoints to the end of web_server.py # Sync background worker logic lives in core/discovery/sync.py. from core.discovery import sync as _discovery_sync def _build_sync_deps(): """Build the SyncDeps bundle from web_server.py globals on each call.""" return _discovery_sync.SyncDeps( config_manager=config_manager, sync_service=sync_service, media_server_engine=media_server_engine, automation_engine=automation_engine, run_async=run_async, record_sync_history_start=_record_sync_history_start, update_automation_progress=_update_automation_progress, update_and_save_sync_status=_update_and_save_sync_status, sync_states=sync_states, sync_lock=sync_lock, ) def _run_sync_task(playlist_id, playlist_name, tracks_json, automation_id=None, profile_id=1, playlist_image_url='', sync_mode='replace'): return _discovery_sync.run_sync_task( playlist_id, playlist_name, tracks_json, automation_id, profile_id, playlist_image_url, _build_sync_deps(), sync_mode=sync_mode, ) @app.route('/api/sync/start', methods=['POST']) def start_playlist_sync(): """Starts a new sync process for a given playlist.""" request_start_time = time.time() logger.info(f"⏱️ [TIMING] Sync request received at {time.strftime('%H:%M:%S')}") data = request.get_json() playlist_id = data.get('playlist_id') playlist_name = data.get('playlist_name') tracks_json = data.get('tracks') # Pass the full track list playlist_image_url = data.get('image_url', '') # 'replace' (default) deletes the server playlist and recreates it from # the source. 'append' preserves user-added tracks already on the server # playlist — only adds tracks that aren't there yet. Per-server clients # implement append via native add APIs (Plex addItems, Jellyfin POST # /Playlists//Items, Navidrome updatePlaylist?songIdToAdd=...). sync_mode = data.get('sync_mode', 'replace') if sync_mode not in ('replace', 'append'): sync_mode = 'replace' if not all([playlist_id, playlist_name, tracks_json]): return jsonify({"success": False, "error": "Missing playlist_id, name, or tracks."}), 400 # Add activity for sync start add_activity_item("", "Spotify Sync Started", f"'{playlist_name}' - {len(tracks_json)} tracks ({sync_mode})", "Now") logger.info(f"Starting playlist sync for '{playlist_name}' with {len(tracks_json)} tracks (mode: {sync_mode})") logger.debug(f"Request parsed at {time.strftime('%H:%M:%S')} (took {(time.time()-request_start_time)*1000:.1f}ms)") with sync_lock: if playlist_id in active_sync_workers and not active_sync_workers[playlist_id].done(): return jsonify({"success": False, "error": "Sync is already in progress for this playlist."}), 409 # Initial state sync_states[playlist_id] = {"status": "starting", "progress": {}} # Submit the task to the thread pool (capture profile_id while still in request context) _sync_profile_id = get_current_profile_id() thread_submit_time = time.time() future = sync_executor.submit(_run_sync_task, playlist_id, playlist_name, tracks_json, None, _sync_profile_id, playlist_image_url, sync_mode) active_sync_workers[playlist_id] = future thread_submit_duration = (time.time() - thread_submit_time) * 1000 logger.info(f"⏱️ [TIMING] Thread submitted at {time.strftime('%H:%M:%S')} (took {thread_submit_duration:.1f}ms)") total_request_time = (time.time() - request_start_time) * 1000 logger.info(f"⏱️ [TIMING] Request completed at {time.strftime('%H:%M:%S')} (total: {total_request_time:.1f}ms)") return jsonify({"success": True, "message": "Sync started."}) @app.route('/api/sync/status/', methods=['GET']) def get_sync_status(playlist_id): """Polls for the status of an ongoing sync.""" with sync_lock: state = sync_states.get(playlist_id) if not state: return jsonify({"status": "not_found"}), 404 # If the task is finished but the state hasn't been updated, check the future if state['status'] not in ['finished', 'error'] and playlist_id in active_sync_workers: if active_sync_workers[playlist_id].done(): # The task might have finished between polls, trigger final state update # This is handled by the _run_sync_task itself pass return jsonify(state) @app.route('/api/sync/cancel', methods=['POST']) def cancel_playlist_sync(): """Cancels an ongoing sync process.""" data = request.get_json() playlist_id = data.get('playlist_id') if not playlist_id: return jsonify({"success": False, "error": "Missing playlist_id."}), 400 with sync_lock: future = active_sync_workers.get(playlist_id) if not future or future.done(): return jsonify({"success": False, "error": "Sync not running or already complete."}), 404 # The GUI's sync_service has a cancel_sync method. We'll replicate that idea. # Since we can't easily stop the thread, we'll set a flag. # The elegant solution is to have the sync_service check for a cancellation flag. # Your `sync_service.py` already has this logic with `self._cancelled`. sync_service.cancel_sync() # We can't guarantee immediate stop, but we can update the state sync_states[playlist_id] = {"status": "cancelled"} # It's best practice to let the task finish and clean itself up. # We don't use future.cancel() as it may not work if the task is already running. return jsonify({"success": True, "message": "Sync cancellation requested."}) @app.route('/api/sync/test-database', methods=['GET']) def test_database_access(): """Test endpoint to verify database connectivity for sync operations""" try: logger.debug("Testing database access for sync operations...") # Test database initialization from database.music_database import MusicDatabase db = MusicDatabase() logger.debug(f" Database initialized: {db is not None}") # Test basic database query stats = db.get_database_info_for_server() logger.debug(f" Database stats retrieved: {stats}") # Test track existence check (like sync service does) db_track, confidence = db.check_track_exists("test track", "test artist", confidence_threshold=0.7) logger.info(f" Track existence check works: found={db_track is not None}, confidence={confidence}") # Test config manager from config.settings import config_manager active_server = config_manager.get_active_media_server() logger.info(f" Active media server: {active_server}") # Test media clients logger.info(" Media clients status:") logger.info(f" media_server_engine.client('plex'): {media_server_engine.client('plex') is not None}") if media_server_engine.client('plex'): logger.info(f" media_server_engine.client('plex').is_connected(): {media_server_engine.client('plex').is_connected()}") logger.info(f" media_server_engine.client('jellyfin'): {media_server_engine.client('jellyfin') is not None}") if media_server_engine.client('jellyfin'): logger.info(f" media_server_engine.client('jellyfin').is_connected(): {media_server_engine.client('jellyfin').is_connected()}") return jsonify({ "success": True, "message": "Database access test successful", "details": { "database_initialized": db is not None, "database_stats": stats, "active_server": active_server, "plex_connected": media_server_engine.client('plex').is_connected() if media_server_engine.client('plex') else False, "jellyfin_connected": media_server_engine.client('jellyfin').is_connected() if media_server_engine.client('jellyfin') else False, } }) except Exception as e: logger.error(f" Database test failed: {e}") import traceback traceback.print_exc() return jsonify({ "success": False, "error": str(e), "message": "Database access test failed" }), 500 # --- Discover Download Snapshot System --- @app.route('/api/discover_downloads/snapshot', methods=['POST']) def save_discover_download_snapshot(): """ Saves a snapshot of current discover download state for persistence across page refreshes. """ try: from datetime import datetime data = request.json if not data or 'downloads' not in data: return jsonify({'success': False, 'error': 'No download data provided'}), 400 downloads = data['downloads'] db = get_database() db.save_bubble_snapshot('discover_downloads', downloads, profile_id=get_current_profile_id()) download_count = len(downloads) logger.info(f"Saved discover download snapshot: {download_count} downloads") return jsonify({ 'success': True, 'message': f'Snapshot saved with {download_count} downloads', 'timestamp': datetime.now().isoformat() }) except Exception as e: logger.error(f"Error saving discover download snapshot: {e}") import traceback traceback.print_exc() return jsonify({ 'success': False, 'error': str(e) }), 500 @app.route('/api/discover_downloads/hydrate', methods=['GET']) def hydrate_discover_downloads(): """ Loads discover downloads with live status by cross-referencing snapshots with active processes. """ try: from datetime import datetime, timedelta db = get_database() snapshot = db.get_bubble_snapshot('discover_downloads', profile_id=get_current_profile_id()) # Load snapshot if it exists if not snapshot: return jsonify({ 'success': True, 'downloads': {}, 'message': 'No snapshots found' }) saved_downloads = snapshot['data'] snapshot_time = snapshot['timestamp'] # Clean up old snapshots (older than 48 hours) try: if snapshot_time: snapshot_dt = datetime.fromisoformat(snapshot_time.replace('Z', '+00:00')) cutoff = datetime.now() - timedelta(hours=48) if snapshot_dt < cutoff: logger.info(f"Cleaning up old discover download snapshot from {snapshot_time}") db.delete_bubble_snapshot('discover_downloads', profile_id=get_current_profile_id()) return jsonify({ 'success': True, 'downloads': {}, 'message': 'Old snapshot cleaned up' }) except ValueError as e: logger.error(f"Error checking discover snapshot age: {e}") # Get current active download processes for live status current_processes = {} try: with tasks_lock: for batch_id, batch_data in download_batches.items(): if batch_data.get('phase') not in ['complete', 'error', 'cancelled']: playlist_id = batch_data.get('playlist_id') if playlist_id: current_processes[playlist_id] = { 'status': 'in_progress' if batch_data.get('phase') == 'downloading' else 'analyzing', 'batch_id': batch_id, 'phase': batch_data.get('phase') } except Exception as e: logger.error(f"Error fetching active processes for discover download hydration: {e}") # If no active processes exist, the app likely restarted - clean up snapshots if not current_processes: logger.warning("No active processes found - app likely restarted, cleaning up discover download snapshot") db.delete_bubble_snapshot('discover_downloads', profile_id=get_current_profile_id()) return jsonify({ 'success': True, 'downloads': {}, 'message': 'No active processes - returning empty downloads' }) # Update download statuses with live data hydrated_downloads = {} for playlist_id, download_data in saved_downloads.items(): # Determine current live status if playlist_id in current_processes: process_info = current_processes[playlist_id] live_status = 'in_progress' logger.info(f"Found active process for discover download {playlist_id}: {process_info['phase']}") else: # No active process - likely completed live_status = 'completed' logger.warning(f"No active process for discover download {playlist_id} - marking as completed") # Create updated download entry hydrated_downloads[playlist_id] = { 'name': download_data.get('name'), 'type': download_data.get('type'), 'status': live_status, 'virtualPlaylistId': playlist_id, 'imageUrl': download_data.get('imageUrl'), 'startTime': download_data.get('startTime', datetime.now().isoformat()) } download_count = len(hydrated_downloads) active_count = sum(1 for d in hydrated_downloads.values() if d['status'] == 'in_progress') completed_count = sum(1 for d in hydrated_downloads.values() if d['status'] == 'completed') logger.info(f"Hydrated {download_count} discover downloads: {active_count} active, {completed_count} completed") return jsonify({ 'success': True, 'downloads': hydrated_downloads, 'stats': { 'total_downloads': download_count, 'active_downloads': active_count, 'completed_downloads': completed_count } }) except Exception as e: logger.error(f"Error hydrating discover downloads: {e}") import traceback traceback.print_exc() return jsonify({ 'success': False, 'error': str(e) }), 500 # --- Artist Bubble Snapshot System --- @app.route('/api/artist_bubbles/snapshot', methods=['POST']) def save_artist_bubble_snapshot(): """ Saves a snapshot of current artist bubble state for persistence across page refreshes. """ try: from datetime import datetime data = request.json if not data or 'bubbles' not in data: return jsonify({'success': False, 'error': 'No bubble data provided'}), 400 bubbles = data['bubbles'] db = get_database() db.save_bubble_snapshot('artist_bubbles', bubbles, profile_id=get_current_profile_id()) bubble_count = len(bubbles) logger.info(f"Saved artist bubble snapshot: {bubble_count} artists") return jsonify({ 'success': True, 'message': f'Snapshot saved with {bubble_count} artist bubbles', 'timestamp': datetime.now().isoformat() }) except Exception as e: logger.error(f"Error saving artist bubble snapshot: {e}") import traceback traceback.print_exc() return jsonify({ 'success': False, 'error': str(e) }), 500 @app.route('/api/artist_bubbles/hydrate', methods=['GET']) def hydrate_artist_bubbles(): """ Loads artist bubbles with live status by cross-referencing snapshots with active processes. """ try: from datetime import datetime, timedelta db = get_database() snapshot = db.get_bubble_snapshot('artist_bubbles', profile_id=get_current_profile_id()) # Load snapshot if it exists if not snapshot: return jsonify({ 'success': True, 'bubbles': {}, 'message': 'No snapshots found' }) saved_bubbles = snapshot['data'] snapshot_time = snapshot['timestamp'] # Clean up old snapshots (older than 48 hours) try: if snapshot_time: snapshot_dt = datetime.fromisoformat(snapshot_time.replace('Z', '+00:00')) cutoff = datetime.now() - timedelta(hours=48) if snapshot_dt < cutoff: logger.info(f"Cleaning up old snapshot from {snapshot_time}") db.delete_bubble_snapshot('artist_bubbles', profile_id=get_current_profile_id()) return jsonify({ 'success': True, 'bubbles': {}, 'message': 'Old snapshot cleaned up' }) except ValueError as e: logger.error(f"Error checking snapshot age: {e}") # Get current active download processes for live status current_processes = {} try: with tasks_lock: for batch_id, batch_data in download_batches.items(): if batch_data.get('phase') not in ['complete', 'error', 'cancelled']: playlist_id = batch_data.get('playlist_id') if playlist_id: current_processes[playlist_id] = { 'status': 'in_progress' if batch_data.get('phase') == 'downloading' else 'analyzing', 'batch_id': batch_id, 'phase': batch_data.get('phase') } except Exception as e: logger.error(f"Error fetching active processes for hydration: {e}") # If no active processes exist, the app likely restarted - clean up snapshots if not current_processes: logger.warning("No active processes found - app likely restarted, cleaning up snapshot") db.delete_bubble_snapshot('artist_bubbles', profile_id=get_current_profile_id()) return jsonify({ 'success': True, 'bubbles': {}, 'message': 'No active processes - returning empty bubbles' }) # Update bubble statuses with live data hydrated_bubbles = {} for artist_id, bubble_data in saved_bubbles.items(): hydrated_bubble = { 'artist': bubble_data['artist'], 'downloads': [], 'hasCompletedDownloads': False } for download in bubble_data.get('downloads', []): virtual_playlist_id = download['virtualPlaylistId'] # Determine current live status if virtual_playlist_id in current_processes: process_info = current_processes[virtual_playlist_id] live_status = 'in_progress' logger.info(f"Found active process for {download['album']['name']}: {process_info['phase']}") else: # No active process - likely completed live_status = 'view_results' logger.warning(f"No active process for {download['album']['name']} - marking as completed") # Create updated download entry updated_download = { 'virtualPlaylistId': virtual_playlist_id, 'album': download['album'], 'albumType': download.get('albumType', 'album'), 'status': live_status, 'startTime': download.get('startTime', datetime.now().isoformat()) } hydrated_bubble['downloads'].append(updated_download) # Update hasCompletedDownloads flag if live_status == 'view_results': hydrated_bubble['hasCompletedDownloads'] = True # Only include artists that still have downloads if hydrated_bubble['downloads']: hydrated_bubbles[artist_id] = hydrated_bubble bubble_count = len(hydrated_bubbles) active_count = sum(1 for bubble in hydrated_bubbles.values() for download in bubble['downloads'] if download['status'] == 'in_progress') completed_count = sum(1 for bubble in hydrated_bubbles.values() for download in bubble['downloads'] if download['status'] == 'view_results') logger.info(f"Hydrated {bubble_count} artist bubbles: {active_count} active, {completed_count} completed") return jsonify({ 'success': True, 'bubbles': hydrated_bubbles, 'stats': { 'total_artists': bubble_count, 'active_downloads': active_count, 'completed_downloads': completed_count, 'snapshot_time': snapshot_time } }) except Exception as e: logger.error(f"Error hydrating artist bubbles: {e}") import traceback traceback.print_exc() return jsonify({ 'success': False, 'error': str(e) }), 500 # --- Search Bubble Snapshot System --- @app.route('/api/search_bubbles/snapshot', methods=['POST']) def save_search_bubble_snapshot(): """ Saves a snapshot of current search bubble state for persistence across page refreshes. """ try: from datetime import datetime data = request.json if not data or 'bubbles' not in data: return jsonify({'success': False, 'error': 'No bubble data provided'}), 400 bubbles = data['bubbles'] db = get_database() db.save_bubble_snapshot('search_bubbles', bubbles, profile_id=get_current_profile_id()) bubble_count = len(bubbles) logger.info(f"Saved search bubble snapshot: {bubble_count} albums/tracks") return jsonify({ 'success': True, 'message': f'Snapshot saved with {bubble_count} search bubbles', 'timestamp': datetime.now().isoformat() }) except Exception as e: logger.error(f"Error saving search bubble snapshot: {e}") import traceback traceback.print_exc() return jsonify({ 'success': False, 'error': str(e) }), 500 @app.route('/api/search_bubbles/hydrate', methods=['GET']) def hydrate_search_bubbles(): """ Loads search bubbles with live status by cross-referencing snapshots with active processes. """ try: from datetime import datetime, timedelta db = get_database() snapshot = db.get_bubble_snapshot('search_bubbles', profile_id=get_current_profile_id()) # Load snapshot if it exists if not snapshot: return jsonify({ 'success': True, 'bubbles': {}, 'message': 'No snapshots found' }) saved_bubbles = snapshot['data'] snapshot_time = snapshot['timestamp'] # Clean up old snapshots (older than 48 hours) try: if snapshot_time: snapshot_dt = datetime.fromisoformat(snapshot_time.replace('Z', '+00:00')) cutoff = datetime.now() - timedelta(hours=48) if snapshot_dt < cutoff: logger.info(f"Cleaning up old search snapshot from {snapshot_time}") db.delete_bubble_snapshot('search_bubbles', profile_id=get_current_profile_id()) return jsonify({ 'success': True, 'bubbles': {}, 'message': 'Old snapshot cleaned up' }) except ValueError as e: logger.error(f"Error checking snapshot age: {e}") # Get current active download processes for live status current_processes = {} try: with tasks_lock: for batch_id, batch_data in download_batches.items(): if batch_data.get('phase') not in ['complete', 'error', 'cancelled']: playlist_id = batch_data.get('playlist_id') if playlist_id: current_processes[playlist_id] = { 'status': 'in_progress' if batch_data.get('phase') == 'downloading' else 'analyzing', 'batch_id': batch_id, 'phase': batch_data.get('phase') } except Exception as e: logger.error(f"Error fetching active processes for hydration: {e}") # If no active processes exist, the app likely restarted - clean up snapshots if not current_processes: logger.warning("No active processes found - app likely restarted, cleaning up search snapshot") db.delete_bubble_snapshot('search_bubbles', profile_id=get_current_profile_id()) return jsonify({ 'success': True, 'bubbles': {}, 'message': 'No active processes - returning empty bubbles' }) # Update bubble statuses with live data (artist-grouped structure) hydrated_bubbles = {} for artist_name, bubble_data in saved_bubbles.items(): hydrated_bubble = { 'artist': bubble_data['artist'], 'downloads': [] } for download in bubble_data.get('downloads', []): virtual_playlist_id = download['virtualPlaylistId'] # Determine current live status if virtual_playlist_id in current_processes: process_info = current_processes[virtual_playlist_id] live_status = 'in_progress' logger.info(f"Found active process for {download['item']['name']}: {process_info['phase']}") else: # No active process - likely completed live_status = 'view_results' logger.warning(f"No active process for {download['item']['name']} - marking as completed") # Create updated download entry updated_download = { 'virtualPlaylistId': virtual_playlist_id, 'item': download['item'], 'type': download.get('type', 'album'), 'status': live_status, 'startTime': download.get('startTime', datetime.now().isoformat()) } hydrated_bubble['downloads'].append(updated_download) # Only include artists that still have downloads if hydrated_bubble['downloads']: hydrated_bubbles[artist_name] = hydrated_bubble bubble_count = len(hydrated_bubbles) active_count = sum(1 for bubble in hydrated_bubbles.values() for download in bubble['downloads'] if download['status'] == 'in_progress') completed_count = sum(1 for bubble in hydrated_bubbles.values() for download in bubble['downloads'] if download['status'] == 'view_results') logger.info(f"Hydrated {bubble_count} search bubbles (artists): {active_count} active, {completed_count} completed") return jsonify({ 'success': True, 'bubbles': hydrated_bubbles, 'stats': { 'total_items': bubble_count, 'active_downloads': active_count, 'completed_downloads': completed_count, 'snapshot_time': snapshot_time } }) except Exception as e: logger.error(f"Error hydrating search bubbles: {e}") import traceback traceback.print_exc() return jsonify({ 'success': False, 'error': str(e) }), 500 @app.route('/api/beatport_bubbles/snapshot', methods=['POST']) def save_beatport_bubble_snapshot(): """Saves a snapshot of current Beatport download bubble state for persistence.""" try: from datetime import datetime data = request.json if not data or 'bubbles' not in data: return jsonify({'success': False, 'error': 'No bubble data provided'}), 400 bubbles = data['bubbles'] db = get_database() db.save_bubble_snapshot('beatport_bubbles', bubbles, profile_id=get_current_profile_id()) bubble_count = len(bubbles) logger.info(f"Saved Beatport bubble snapshot: {bubble_count} charts") return jsonify({ 'success': True, 'message': f'Snapshot saved with {bubble_count} Beatport bubbles', 'timestamp': datetime.now().isoformat() }) except Exception as e: logger.error(f"Error saving Beatport bubble snapshot: {e}") import traceback traceback.print_exc() return jsonify({ 'success': False, 'error': str(e) }), 500 @app.route('/api/beatport_bubbles/hydrate', methods=['GET']) def hydrate_beatport_bubbles(): """Loads Beatport download bubbles with live status from snapshot.""" try: from datetime import datetime, timedelta db = get_database() snapshot = db.get_bubble_snapshot('beatport_bubbles', profile_id=get_current_profile_id()) if not snapshot: return jsonify({ 'success': True, 'bubbles': {}, 'message': 'No snapshots found' }) saved_bubbles = snapshot['data'] snapshot_time = snapshot['timestamp'] # Clean up old snapshots (older than 48 hours) try: if snapshot_time: snapshot_dt = datetime.fromisoformat(snapshot_time.replace('Z', '+00:00')) cutoff = datetime.now() - timedelta(hours=48) if snapshot_dt < cutoff: logger.info(f"Cleaning up old Beatport snapshot from {snapshot_time}") db.delete_bubble_snapshot('beatport_bubbles', profile_id=get_current_profile_id()) return jsonify({ 'success': True, 'bubbles': {}, 'message': 'Old snapshot cleaned up' }) except ValueError as e: logger.error(f"Error checking Beatport snapshot age: {e}") # Get current active download processes for live status current_processes = {} try: with tasks_lock: for batch_id, batch_data in download_batches.items(): if batch_data.get('phase') not in ['complete', 'error', 'cancelled']: playlist_id = batch_data.get('playlist_id') if playlist_id: current_processes[playlist_id] = { 'status': 'in_progress', 'batch_id': batch_id, 'phase': batch_data.get('phase') } except Exception as e: logger.error(f"Error fetching active processes for Beatport hydration: {e}") # If no active processes exist, app likely restarted — clean up if not current_processes: logger.warning("No active processes found - cleaning up Beatport snapshot") db.delete_bubble_snapshot('beatport_bubbles', profile_id=get_current_profile_id()) return jsonify({ 'success': True, 'bubbles': {}, 'message': 'No active processes - returning empty bubbles' }) # Update bubble statuses with live data hydrated_bubbles = {} for chart_key, bubble_data in saved_bubbles.items(): hydrated_bubble = { 'chart': bubble_data['chart'], 'downloads': [] } for download in bubble_data.get('downloads', []): virtual_playlist_id = download['virtualPlaylistId'] if virtual_playlist_id in current_processes: live_status = 'in_progress' else: live_status = 'view_results' hydrated_bubble['downloads'].append({ 'virtualPlaylistId': virtual_playlist_id, 'status': live_status, 'startTime': download.get('startTime', datetime.now().isoformat()) }) if hydrated_bubble['downloads']: hydrated_bubbles[chart_key] = hydrated_bubble bubble_count = len(hydrated_bubbles) active_count = sum(1 for b in hydrated_bubbles.values() for d in b['downloads'] if d['status'] == 'in_progress') completed_count = sum(1 for b in hydrated_bubbles.values() for d in b['downloads'] if d['status'] == 'view_results') logger.info(f"Hydrated {bubble_count} Beatport bubbles: {active_count} active, {completed_count} completed") return jsonify({ 'success': True, 'bubbles': hydrated_bubbles, 'stats': { 'total_charts': bubble_count, 'active_downloads': active_count, 'completed_downloads': completed_count } }) except Exception as e: logger.error(f"Error hydrating Beatport bubbles: {e}") import traceback traceback.print_exc() return jsonify({ 'success': False, 'error': str(e) }), 500 # --- Profile API Endpoints --- @app.route('/api/profiles', methods=['GET']) def list_profiles(): """List all profiles""" try: database = get_database() profiles = database.get_all_profiles() return jsonify({'success': True, 'profiles': profiles}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/profiles', methods=['POST']) def create_profile(): """Create a new profile (admin only)""" try: # Check that requester is admin database = get_database() current = database.get_profile(get_current_profile_id()) if current and not current['is_admin']: return jsonify({'success': False, 'error': 'Admin only'}), 403 data = request.json or {} name = data.get('name', '').strip() if not name: return jsonify({'success': False, 'error': 'Name is required'}), 400 avatar_color = data.get('avatar_color', '#6366f1') avatar_url = data.get('avatar_url') or None pin = data.get('pin') pin_hash = None if pin: from werkzeug.security import generate_password_hash pin_hash = generate_password_hash(pin, method='pbkdf2:sha256') # Profile settings: home_page, allowed_pages, can_download home_page = data.get('home_page') or None allowed_pages = data.get('allowed_pages') # list or None can_download = data.get('can_download', True) # Validate page IDs if home_page and home_page not in VALID_PAGE_IDS: home_page = None if allowed_pages is not None: allowed_pages = [p for p in allowed_pages if p in VALID_PAGE_IDS] # Non-admin should never have 'settings' in allowed_pages if 'settings' in allowed_pages: allowed_pages.remove('settings') # If home_page not in allowed list, reset to first allowed or 'discover' if home_page and home_page not in allowed_pages: home_page = allowed_pages[0] if allowed_pages else None profile_id = database.create_profile( name, avatar_color, pin_hash, is_admin=False, avatar_url=avatar_url, home_page=home_page, allowed_pages=allowed_pages, can_download=bool(can_download) ) if profile_id is None: return jsonify({'success': False, 'error': 'Profile name already exists'}), 409 return jsonify({'success': True, 'profile_id': profile_id}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/profiles/', methods=['PUT']) def update_profile(profile_id): """Update a profile (admin or self)""" try: database = get_database() current_pid = get_current_profile_id() current = database.get_profile(current_pid) if not current: return jsonify({'success': False, 'error': 'Current profile not found'}), 404 # Only admin or self can update if not current['is_admin'] and current_pid != profile_id: return jsonify({'success': False, 'error': 'Unauthorized'}), 403 data = request.json or {} kwargs = {} if 'name' in data: name = data['name'].strip() if not name: return jsonify({'success': False, 'error': 'Name cannot be empty'}), 400 kwargs['name'] = name if 'avatar_color' in data: kwargs['avatar_color'] = data['avatar_color'] if 'avatar_url' in data: kwargs['avatar_url'] = data['avatar_url'] or None if 'is_admin' in data and current['is_admin']: # Prevent demoting the last admin if not data['is_admin']: all_profiles = database.get_all_profiles() admin_count = sum(1 for p in all_profiles if p['is_admin']) target = database.get_profile(profile_id) if target and target['is_admin'] and admin_count <= 1: return jsonify({'success': False, 'error': 'Cannot remove the last admin'}), 400 kwargs['is_admin'] = int(data['is_admin']) # Home page — any user can change their own, admin can change anyone's if 'home_page' in data: hp = data['home_page'] or None if hp and hp not in VALID_PAGE_IDS: hp = None # Non-admin self-edit: validate home_page is in their allowed pages if not current['is_admin'] and current_pid == profile_id: target = database.get_profile(profile_id) ap = target.get('allowed_pages') if target else None if ap is not None and hp and hp not in ap: return jsonify({'success': False, 'error': 'Page not permitted'}), 400 kwargs['home_page'] = hp # Allowed pages & can_download — admin only if current['is_admin']: if 'allowed_pages' in data: ap = data['allowed_pages'] if ap is not None: ap = [p for p in ap if p in VALID_PAGE_IDS] # Non-admin target should never have 'settings' target = database.get_profile(profile_id) if target and not target.get('is_admin'): ap = [p for p in ap if p != 'settings'] # If current home_page not in new allowed list, reset it current_hp = kwargs.get('home_page') or (target.get('home_page') if target else None) if current_hp and current_hp not in ap: kwargs['home_page'] = ap[0] if ap else None kwargs['allowed_pages'] = ap if 'can_download' in data: kwargs['can_download'] = int(bool(data['can_download'])) success = database.update_profile(profile_id, **kwargs) return jsonify({'success': success}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/profiles/', methods=['DELETE']) def delete_profile(profile_id): """Delete a profile (admin only, can't delete self)""" try: database = get_database() current_pid = get_current_profile_id() current = database.get_profile(current_pid) if not current or not current['is_admin']: return jsonify({'success': False, 'error': 'Admin only'}), 403 if current_pid == profile_id: return jsonify({'success': False, 'error': 'Cannot delete your own profile'}), 400 target = database.get_profile(profile_id) if not target: return jsonify({'success': False, 'error': 'Profile not found'}), 404 success = database.delete_profile(profile_id) return jsonify({'success': success}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/profiles/select', methods=['POST']) def select_profile(): """Select a profile (validates PIN if set)""" try: data = request.json or {} try: profile_id = int(data.get('profile_id', 0)) except (TypeError, ValueError): return jsonify({'success': False, 'error': 'Invalid profile_id'}), 400 pin = data.get('pin', '') if not profile_id: return jsonify({'success': False, 'error': 'profile_id required'}), 400 database = get_database() profile = database.get_profile(profile_id) if not profile: return jsonify({'success': False, 'error': 'Profile not found'}), 404 # Only enforce PIN when multiple profiles exist (PIN protects against profile switching) all_profiles = database.get_all_profiles() if len(all_profiles) > 1 and profile['has_pin']: if not pin: return jsonify({'success': False, 'error': 'PIN required', 'pin_required': True}), 401 if not database.verify_profile_pin(profile_id, pin): return jsonify({'success': False, 'error': 'Invalid PIN'}), 401 session['profile_id'] = profile_id # If PIN was just validated, also mark launch PIN as verified # so the subsequent page reload doesn't ask again if pin: session['launch_pin_verified'] = True return jsonify({'success': True, 'profile': profile}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/profiles/current', methods=['GET']) def get_current_profile(): """Get the currently selected profile from session""" try: pid = session.get('profile_id') if not pid: return jsonify({'success': False, 'error': 'No profile selected'}), 200 database = get_database() profile = database.get_profile(pid) if not profile: session.pop('profile_id', None) return jsonify({'success': False, 'error': 'Profile not found'}), 200 # Check if launch PIN is required require_pin = config_manager.get('security.require_pin_on_launch', False) if config_manager else False # Check if PIN was verified this page load, then consume the flag pin_verified = session.pop('launch_pin_verified', False) return jsonify({ 'success': True, 'profile': profile, 'launch_pin_required': bool(require_pin) and not pin_verified, }) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/profiles/verify-launch-pin', methods=['POST']) def verify_launch_pin(): """Verify PIN for launch lock screen""" try: data = request.json or {} pin = data.get('pin', '') if not pin: return jsonify({'success': False, 'error': 'PIN required'}), 401 database = get_database() # Validate against admin profile (ID 1) if not database.verify_profile_pin(1, pin): return jsonify({'success': False, 'error': 'Invalid PIN'}), 401 session['launch_pin_verified'] = True return jsonify({'success': True}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/profiles/reset-pin-via-credential', methods=['POST']) def reset_pin_via_credential(): """Reset admin PIN by verifying a known API credential""" try: data = request.json or {} credential = (data.get('credential') or '').strip() if not credential or len(credential) < 4: return jsonify({'success': False, 'error': 'Enter a valid credential'}), 400 # Check credential against all stored API secrets/tokens checks = [ ('Spotify Client Secret', config_manager.get('spotify.client_secret', '')), ('Tidal Client Secret', config_manager.get('tidal.client_secret', '')), ('Plex Token', config_manager.get('plex.token', '')), ('Jellyfin API Key', config_manager.get('jellyfin.api_key', '')), ('Navidrome Password', config_manager.get('navidrome.password', '')), ('ListenBrainz Token', config_manager.get('listenbrainz.token', '')), ('AcoustID API Key', config_manager.get('acoustid.api_key', '')), ('Last.fm API Secret', config_manager.get('lastfm.api_secret', '')), ('Genius Access Token', config_manager.get('genius.access_token', '')), ] matched = False for _name, stored in checks: if stored and credential == stored: matched = True break if not matched: return jsonify({'success': False, 'error': 'Credential does not match any configured service'}), 401 # Credential verified — clear PIN for the requested profile (default: admin) database = get_database() target_profile = data.get('profile_id', 1) database.update_profile(target_profile, pin_hash=None) # If clearing admin PIN, also disable launch lock if target_profile == 1: config_manager.set('security.require_pin_on_launch', False) session['launch_pin_verified'] = True return jsonify({'success': True, 'message': 'PIN cleared. You can set a new PIN in Settings.'}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/profiles/logout', methods=['POST']) def logout_profile(): """Clear session — back to profile picker""" session.pop('profile_id', None) return jsonify({'success': True}) @app.route('/api/profiles//set-pin', methods=['POST']) def set_profile_pin(profile_id): """Set or change PIN for a profile (admin or self)""" try: database = get_database() current_pid = get_current_profile_id() current = database.get_profile(current_pid) if not current or (not current['is_admin'] and current_pid != profile_id): return jsonify({'success': False, 'error': 'Unauthorized'}), 403 data = request.json or {} pin = data.get('pin', '') if pin: from werkzeug.security import generate_password_hash pin_hash = generate_password_hash(pin, method='pbkdf2:sha256') else: pin_hash = None # Remove PIN success = database.update_profile(profile_id, pin_hash=pin_hash) return jsonify({'success': success}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 # --- Per-Profile ListenBrainz Settings --- def _get_lb_credentials_for_profile(profile_id=None): """Get LB token + base_url for profile, falling back to global config.""" if profile_id is None: profile_id = get_current_profile_id() db = get_database() settings = db.get_profile_listenbrainz(profile_id) if settings and settings.get('token'): return settings['token'], settings.get('base_url', ''), settings.get('username', ''), 'profile' # Fallback to global config return (config_manager.get('listenbrainz.token', ''), config_manager.get('listenbrainz.base_url', ''), None, 'global') def _validate_lb_token(token, base_url=''): """Validate a ListenBrainz token and return (success, username_or_error)""" try: custom_base = (base_url or '').rstrip('/') if custom_base: if not custom_base.endswith('/1'): custom_base += '/1' lb_api_base = custom_base else: lb_api_base = "https://api.listenbrainz.org/1" url = f"{lb_api_base}/validate-token" headers = {'Authorization': f'Token {token}'} response = requests.get(url, headers=headers, timeout=5) if response.status_code == 200: data = response.json() if data.get('valid'): return True, data.get('user_name', 'Unknown') return False, "Invalid ListenBrainz token." elif response.status_code == 401: return False, "Invalid ListenBrainz token (unauthorized)." else: return False, f"Could not connect to ListenBrainz (HTTP {response.status_code})" except Exception as e: return False, f"ListenBrainz connection error: {str(e)}" @app.route('/api/profiles/me/listenbrainz', methods=['GET']) def get_profile_listenbrainz(): """Get current profile's ListenBrainz connection status""" try: profile_id = get_current_profile_id() token, base_url, username, source = _get_lb_credentials_for_profile(profile_id) connected = bool(token) return jsonify({ 'success': True, 'connected': connected, 'username': username if connected else None, 'base_url': base_url or '', 'source': source }) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/profiles/me/listenbrainz', methods=['POST']) def save_profile_listenbrainz(): """Save ListenBrainz credentials for current profile""" try: data = request.json or {} token = data.get('token', '').strip() base_url = data.get('base_url', '').strip() if not token: return jsonify({'success': False, 'error': 'Token is required'}), 400 # Validate token first valid, result = _validate_lb_token(token, base_url) if not valid: return jsonify({'success': False, 'error': result}), 400 username = result profile_id = get_current_profile_id() db = get_database() success = db.set_profile_listenbrainz(profile_id, token, base_url, username) if success: return jsonify({'success': True, 'username': username}) return jsonify({'success': False, 'error': 'Failed to save credentials'}), 500 except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/profiles/me/listenbrainz', methods=['DELETE']) def delete_profile_listenbrainz(): """Clear ListenBrainz credentials for current profile""" try: profile_id = get_current_profile_id() db = get_database() db.clear_profile_listenbrainz(profile_id) return jsonify({'success': True}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/profiles/me/listenbrainz/test', methods=['POST']) def test_profile_listenbrainz(): """Test a ListenBrainz token without saving""" try: data = request.json or {} token = data.get('token', '').strip() base_url = data.get('base_url', '').strip() if not token: return jsonify({'success': False, 'error': 'Token is required'}), 400 valid, result = _validate_lb_token(token, base_url) if valid: return jsonify({'success': True, 'username': result}) return jsonify({'success': False, 'error': result}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 # --- Per-Profile Service Credentials API --- @app.route('/api/profiles/me/spotify', methods=['GET']) def get_profile_spotify_creds(): """Get current profile's Spotify credentials (if set)""" try: profile_id = get_current_profile_id() db = get_database() creds = db.get_profile_spotify(profile_id) return jsonify({ 'success': True, 'has_credentials': bool(creds), 'client_id': creds.get('client_id', '') if creds else '', 'redirect_uri': creds.get('redirect_uri', '') if creds else '', # Never return client_secret or tokens to frontend }) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/profiles/me/spotify', methods=['POST']) def save_profile_spotify_creds(): """Save Spotify API credentials for current profile""" try: data = request.json or {} client_id = data.get('client_id', '').strip() client_secret = data.get('client_secret', '').strip() redirect_uri = data.get('redirect_uri', '').strip() if not client_id or not client_secret: return jsonify({'success': False, 'error': 'Client ID and Secret are required'}), 400 profile_id = get_current_profile_id() db = get_database() success = db.set_profile_spotify(profile_id, client_id, client_secret, redirect_uri) if success: metadata_registry.clear_cached_profile_spotify_client(profile_id) return jsonify({'success': True}) return jsonify({'success': False, 'error': 'Failed to save credentials'}), 500 except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/profiles/me/spotify', methods=['DELETE']) def delete_profile_spotify_creds(): """Clear Spotify credentials for current profile (revert to global)""" try: profile_id = get_current_profile_id() db = get_database() with db._get_connection() as conn: cursor = conn.cursor() cursor.execute(""" UPDATE profiles SET spotify_client_id = NULL, spotify_client_secret = NULL, spotify_redirect_uri = NULL, spotify_access_token = NULL, spotify_refresh_token = NULL, updated_at = CURRENT_TIMESTAMP WHERE id = ? """, (profile_id,)) conn.commit() metadata_registry.clear_cached_profile_spotify_client(profile_id) return jsonify({'success': True}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/profiles/me/server-library', methods=['GET']) def get_profile_server_library(): """Get current profile's media server library selection""" try: profile_id = get_current_profile_id() db = get_database() libs = db.get_profile_server_library(profile_id) return jsonify({'success': True, **libs}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/profiles/me/server-library', methods=['POST']) def save_profile_server_library(): """Save media server library/user selection for current profile""" try: data = request.json or {} server_type = data.get('server_type', '') library_id = data.get('library_id') user_id = data.get('user_id') if server_type not in ('plex', 'jellyfin', 'navidrome'): return jsonify({'success': False, 'error': 'Invalid server type'}), 400 profile_id = get_current_profile_id() db = get_database() success = db.set_profile_server_library(profile_id, server_type, library_id, user_id) if success: return jsonify({'success': True}) return jsonify({'success': False, 'error': 'Failed to save library selection'}), 500 except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 # --- Watchlist API Endpoints --- @app.route('/api/watchlist/count', methods=['GET']) def get_watchlist_count(): """Get the number of artists in the watchlist""" try: database = get_database() count = database.get_watchlist_count(profile_id=get_current_profile_id()) # Calculate time until next auto-scanning next_run_in_seconds = automation_engine.get_system_automation_next_run_seconds('scan_watchlist') if automation_engine else 0 return jsonify({ "success": True, "count": count, "next_run_in_seconds": next_run_in_seconds }) except Exception as e: logger.error(f"Error getting watchlist count: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/artists', methods=['GET']) def get_watchlist_artists(): """Get all artists in the watchlist with cached images""" try: database = get_database() watchlist_artists = database.get_watchlist_artists(profile_id=get_current_profile_id()) # Convert to JSON serializable format (images are cached from watchlist scans) artists_data = [] for artist in watchlist_artists: artists_data.append({ "id": artist.id, "spotify_artist_id": artist.spotify_artist_id, "artist_name": artist.artist_name, "date_added": artist.date_added.isoformat() if artist.date_added else None, "last_scan_timestamp": artist.last_scan_timestamp.isoformat() if artist.last_scan_timestamp else None, "created_at": artist.created_at.isoformat() if artist.created_at else None, "updated_at": artist.updated_at.isoformat() if artist.updated_at else None, "image_url": artist.image_url, # Cached during watchlist scans "itunes_artist_id": artist.itunes_artist_id, # For iTunes-only artists "deezer_artist_id": getattr(artist, 'deezer_artist_id', None), "discogs_artist_id": getattr(artist, 'discogs_artist_id', None), "include_albums": artist.include_albums, "include_eps": artist.include_eps, "include_singles": artist.include_singles, "include_live": artist.include_live, "include_remixes": artist.include_remixes, "include_acoustic": artist.include_acoustic, "include_compilations": artist.include_compilations, }) return jsonify({"success": True, "artists": artists_data}) except Exception as e: logger.error(f"Error getting watchlist artists: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/add', methods=['POST']) def add_to_watchlist(): """Add an artist to the watchlist""" try: data = request.get_json() artist_id = data.get('artist_id') artist_name = data.get('artist_name') if not artist_id or not artist_name: return jsonify({"success": False, "error": "Missing artist_id or artist_name"}), 400 database = get_database() # Detect source from ID — check if it's a library DB ID first is_numeric_id = artist_id.isdigit() source = None if is_numeric_id: # Could be a library DB ID, iTunes ID, Deezer ID, or Discogs ID # Check if this is a library DB artist and use their actual source IDs try: conn = database._get_connection() cursor = conn.cursor() cursor.execute(""" SELECT spotify_artist_id, itunes_artist_id, deezer_id, discogs_id FROM artists WHERE id = ? LIMIT 1 """, (artist_id,)) row = cursor.fetchone() conn.close() if row: # Library artist — use the best available source ID fallback = _get_metadata_fallback_source() if fallback == 'discogs' and row['discogs_id']: artist_id = row['discogs_id'] source = 'discogs' elif fallback == 'deezer' and row['deezer_id']: artist_id = row['deezer_id'] source = 'deezer' elif row['spotify_artist_id']: artist_id = row['spotify_artist_id'] source = 'spotify' elif row['itunes_artist_id']: artist_id = row['itunes_artist_id'] source = 'itunes' elif row['deezer_id']: artist_id = row['deezer_id'] source = 'deezer' elif row['discogs_id']: artist_id = row['discogs_id'] source = 'discogs' except Exception as e: logger.debug("watchlist artist source lookup failed: %s", e) if not source: fallback_source = _get_metadata_fallback_source() source = fallback_source if is_numeric_id else 'spotify' success = database.add_artist_to_watchlist(artist_id, artist_name, profile_id=get_current_profile_id(), source=source) if success: # Fetch and cache artist image immediately try: if is_numeric_id: # For numeric IDs, fetch image from the configured fallback source try: if source == 'discogs': # Discogs: fetch artist image from API dc = _get_discogs_client() dc_data = dc.get_artist(artist_id) if dc_data: image_url = dc_data.get('image_url') logger.info(f"Discogs artist image: {image_url[:60] if image_url else 'None'}") elif source == 'deezer' or fallback_source == 'deezer': # Deezer: fetch artist image directly from API dz_resp = requests.get(f'https://api.deezer.com/artist/{artist_id}', timeout=5) if dz_resp.ok: dz_data = dz_resp.json() image_url = dz_data.get('picture_xl') or dz_data.get('picture_big') or dz_data.get('picture_medium') logger.info(f"Deezer artist image: {image_url[:60] if image_url else 'None'}") else: # iTunes: look up album entity for artwork itunes_url = f"https://itunes.apple.com/lookup?id={artist_id}&entity=album&limit=5" logger.info(f"Fetching iTunes artist image: {itunes_url}") resp = requests.get(itunes_url, timeout=5) image_url = None if resp.status_code == 200: resp_data = resp.json() results = resp_data.get('results', []) # Iterate results to find one with artwork for res in results: if 'artworkUrl100' in res: image_url = res['artworkUrl100'].replace('100x100', '600x600') break if image_url: database.update_watchlist_artist_image(artist_id, image_url) logger.warning(f"Cached {fallback_source} artist image for {artist_name}") else: logger.warning(f"No artwork found for {fallback_source} artist {artist_name}") except Exception as fb_error: logger.error(f"Error fetching {fallback_source} artwork: {fb_error}") elif spotify_client and spotify_client.is_authenticated(): # For Spotify artists, fetch from Spotify API artist_data = spotify_client.get_artist(artist_id) if artist_data and 'images' in artist_data and artist_data['images']: # Get medium-sized image (usually the second one, or first if only one) image_url = None if len(artist_data['images']) > 1: image_url = artist_data['images'][1]['url'] else: image_url = artist_data['images'][0]['url'] # Update in database if image_url: database.update_watchlist_artist_image(artist_id, image_url) logger.info(f"Cached artist image for {artist_name}") else: logger.warning(f"No image URL found for {artist_name}") else: logger.warning(f"No images in Spotify data for {artist_name}") else: logger.info("Spotify client not available for fetching artist image") except Exception as img_error: # Don't fail the add operation if image fetch fails logger.error(f"Could not fetch artist image for {artist_name}: {img_error}") # Push updated count to this profile's WebSocket room immediately try: pid = get_current_profile_id() socketio.emit('watchlist:count', _build_watchlist_count_payload(profile_id=pid), room=f'profile:{pid}') except Exception as e: logger.debug("watchlist count emit failed: %s", e) try: if automation_engine: automation_engine.emit('watchlist_artist_added', { 'artist': artist_name, 'artist_id': str(artist_id), }) except Exception as e: logger.debug("watchlist_artist_added emit failed: %s", e) _artmap_cache_invalidate(get_current_profile_id()) return jsonify({"success": True, "message": f"Added {artist_name} to watchlist"}) else: return jsonify({"success": False, "error": "Failed to add artist to watchlist"}), 500 except Exception as e: logger.error(f"Error adding to watchlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/remove', methods=['POST']) def remove_from_watchlist(): """Remove an artist from the watchlist""" try: data = request.get_json() artist_id = data.get('artist_id') if not artist_id: return jsonify({"success": False, "error": "Missing artist_id"}), 400 database = get_database() success = database.remove_artist_from_watchlist(artist_id, profile_id=get_current_profile_id()) if success: # Push updated count to this profile's WebSocket room immediately try: pid = get_current_profile_id() socketio.emit('watchlist:count', _build_watchlist_count_payload(profile_id=pid), room=f'profile:{pid}') except Exception as e: logger.debug("watchlist count emit failed: %s", e) try: if automation_engine: automation_engine.emit('watchlist_artist_removed', { 'artist': data.get('artist_name', str(artist_id)), 'artist_id': str(artist_id), }) except Exception as e: logger.debug("watchlist_artist_removed emit failed: %s", e) _artmap_cache_invalidate(get_current_profile_id()) return jsonify({"success": True, "message": "Removed artist from watchlist"}) else: return jsonify({"success": False, "error": "Failed to remove artist from watchlist"}), 500 except Exception as e: logger.error(f"Error removing from watchlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/add-batch', methods=['POST']) def add_batch_to_watchlist(): """Add multiple artists to the watchlist at once""" try: data = request.get_json() artists = data.get('artists', []) if not artists or not isinstance(artists, list): return jsonify({"success": False, "error": "Missing or invalid artists list"}), 400 database = get_database() added = 0 skipped = 0 for artist in artists: artist_id = artist.get('artist_id') artist_name = artist.get('artist_name') if not artist_id or not artist_name: continue # Check if already watched (by ID or name) if database.is_artist_in_watchlist(artist_id, profile_id=get_current_profile_id(), artist_name=artist_name): skipped += 1 continue is_numeric = artist_id.isdigit() fb_source = _get_metadata_fallback_source() src = fb_source if is_numeric else 'spotify' success = database.add_artist_to_watchlist(artist_id, artist_name, profile_id=get_current_profile_id(), source=src) if success: added += 1 # Cache artist image try: is_numeric_id = artist_id.isdigit() if is_numeric_id: fb_source = _get_metadata_fallback_source() if fb_source == 'deezer': fb_client = _get_metadata_fallback_client() fb_artist = fb_client.get_artist(artist_id) if fb_artist and fb_artist.get('images'): image_url = fb_artist['images'][0].get('url') if image_url: database.update_watchlist_artist_image(artist_id, image_url) else: itunes_url = f"https://itunes.apple.com/lookup?id={artist_id}&entity=album&limit=5" resp = requests.get(itunes_url, timeout=5) if resp.status_code == 200: results = resp.json().get('results', []) for res in results: if 'artworkUrl100' in res: image_url = res['artworkUrl100'].replace('100x100', '600x600') database.update_watchlist_artist_image(artist_id, image_url) break elif spotify_client and spotify_client.is_authenticated(): artist_data = spotify_client.get_artist(artist_id) if artist_data and 'images' in artist_data and artist_data['images']: image_url = artist_data['images'][1]['url'] if len(artist_data['images']) > 1 else artist_data['images'][0]['url'] if image_url: database.update_watchlist_artist_image(artist_id, image_url) except Exception as img_error: logger.error(f"Could not fetch artist image for {artist_name}: {img_error}") return jsonify({ "success": True, "added": added, "skipped": skipped, "message": f"Added {added} artist{'s' if added != 1 else ''} to watchlist ({skipped} already watched)" }) except Exception as e: logger.error(f"Error batch adding to watchlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/library/watchlist-all-unwatched', methods=['POST']) def watchlist_all_unwatched_library_artists(): """Add all unwatched library artists (that have valid external IDs) to the watchlist""" try: database = get_database() active_source = _get_active_discovery_source() # Fetch all unwatched artists in pages (SQLite variable limit safe) unwatched_artists = [] page = 1 page_size = 400 while True: result = database.get_library_artists( search_query='', letter='all', page=page, limit=page_size, watchlist_filter='unwatched', profile_id=get_current_profile_id() ) unwatched_artists.extend(result.get('artists', [])) if not result.get('pagination', {}).get('has_next', False): break page += 1 added = 0 skipped_no_id = 0 skipped_already = 0 # Try the active source's ID first, fall back through every other # supported source. Pre-fix this loop required the active source's # ID and silently dropped library artists that only had iTunes, # Deezer, or Discogs IDs — surfaced as "Library and Watchlist not # syncing correctly" on Discord because the bulk add reported # "Added X" with no breakdown of why others were rejected. from core.watchlist.source_picker import pick_artist_id_for_watchlist for artist in unwatched_artists: artist_id, picked_source = pick_artist_id_for_watchlist(artist, active_source) if not artist_id: skipped_no_id += 1 continue artist_name = artist.get('name', '') if not artist_name: continue # Check if already watched (shouldn't be since we filtered, but safety check) if database.is_artist_in_watchlist(artist_id, profile_id=get_current_profile_id(), artist_name=artist_name): skipped_already += 1 continue success = database.add_artist_to_watchlist(artist_id, artist_name, profile_id=get_current_profile_id(), source=picked_source) if success: added += 1 # Use library thumb_url if available (no HTTP calls needed) if artist.get('image_url'): try: database.update_watchlist_artist_image(artist_id, artist['image_url']) except Exception as e: logger.debug("watchlist artist image update failed: %s", e) total_unwatched = len(unwatched_artists) message_parts = [f"Added {added} artist{'s' if added != 1 else ''} to watchlist"] if skipped_no_id > 0: message_parts.append(f"{skipped_no_id} skipped (no matching ID yet)") return jsonify({ "success": True, "added": added, "skipped_no_id": skipped_no_id, "skipped_already": skipped_already, "total_unwatched": total_unwatched, "message": " — ".join(message_parts) }) except Exception as e: logger.error(f"Error bulk watchlisting library artists: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/remove-batch', methods=['POST']) def remove_batch_from_watchlist(): """Remove multiple artists from the watchlist""" try: data = request.get_json() artist_ids = data.get('artist_ids', []) if not artist_ids or not isinstance(artist_ids, list): return jsonify({"success": False, "error": "Missing or invalid artist_ids"}), 400 database = get_database() removed = 0 for artist_id in artist_ids: if database.remove_artist_from_watchlist(artist_id, profile_id=get_current_profile_id()): removed += 1 return jsonify({ "success": True, "removed": removed, "message": f"Removed {removed} artist{'s' if removed != 1 else ''} from watchlist" }) except Exception as e: logger.error(f"Error batch removing from watchlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/check', methods=['POST']) def check_watchlist_status(): """Check if an artist is in the watchlist""" try: data = request.get_json() artist_id = data.get('artist_id') if not artist_id: return jsonify({"success": False, "error": "Missing artist_id"}), 400 database = get_database() is_watching = database.is_artist_in_watchlist(artist_id, profile_id=get_current_profile_id()) return jsonify({"success": True, "is_watching": is_watching}) except Exception as e: logger.error(f"Error checking watchlist status: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/check-batch', methods=['POST']) def check_watchlist_status_batch(): """Check watchlist status for multiple artists in one request""" try: data = request.get_json() artist_ids = data.get('artist_ids', []) if not artist_ids: return jsonify({"success": False, "error": "Missing artist_ids"}), 400 database = get_database() pid = get_current_profile_id() results = {} for aid in artist_ids: results[aid] = database.is_artist_in_watchlist(aid, profile_id=pid) return jsonify({"success": True, "results": results}) except Exception as e: logger.error(f"Error batch checking watchlist status: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/scan', methods=['POST']) def start_watchlist_scan(): """Start a watchlist scan for new releases""" try: # Check if MetadataService can provide a working client (Spotify OR fallback) from core.metadata.service import MetadataService metadata_service = MetadataService() # Get active provider - will be spotify or the configured fallback active_provider = metadata_service.get_active_provider() provider_info = metadata_service.get_provider_info() # Verify we have at least one working provider if not provider_info['spotify_authenticated'] and not provider_info['itunes_available']: fallback_name = provider_info.get('fallback_source', 'iTunes').capitalize() return jsonify({ "success": False, "error": f"No music provider available. Please authenticate Spotify or ensure {fallback_name} is accessible." }), 400 logger.info(f"Starting watchlist scan with {active_provider} provider") # Check if watchlist is already scanning if is_watchlist_actually_scanning(): return jsonify({"success": False, "error": "Watchlist scan is already in progress."}), 409 # Start the scan in a background thread scan_profile_id = get_current_profile_id() def run_scan(): _ew_state = {} try: global watchlist_scan_state, watchlist_auto_scanning, watchlist_auto_scanning_timestamp from core.watchlist_scanner import WatchlistScanner from database.music_database import get_database # Set flag and timestamp for manual scan import time with watchlist_timer_lock: watchlist_auto_scanning = True watchlist_auto_scanning_timestamp = time.time() logger.info(f"[Manual Watchlist Scan] Flag set at timestamp {watchlist_auto_scanning_timestamp}") # Get list of artists to scan (for the current profile) database = get_database() watchlist_artists = database.get_watchlist_artists(profile_id=scan_profile_id) if not watchlist_artists: watchlist_scan_state['status'] = 'completed' watchlist_scan_state['summary'] = { 'total_artists': 0, 'successful_scans': 0, 'new_tracks_found': 0, 'tracks_added_to_wishlist': 0 } # Reset flag with watchlist_timer_lock: watchlist_auto_scanning = False watchlist_auto_scanning_timestamp = 0 return # Initialize scanner with MetadataService for cross-provider support scanner = WatchlistScanner(metadata_service=metadata_service) # PROACTIVE ID BACKFILLING (cross-provider support) # Before scanning, ensure all artists have IDs for ALL available sources providers_to_backfill = ['itunes', 'deezer'] if spotify_client and spotify_client.is_spotify_authenticated(): providers_to_backfill.append('spotify') try: if config_manager.get('discogs.token', ''): providers_to_backfill.append('discogs') except Exception as e: logger.debug("discogs token backfill check failed: %s", e) for _bf_provider in providers_to_backfill: try: logger.debug(f"Checking for missing {_bf_provider} IDs in watchlist...") scanner._backfill_missing_ids(watchlist_artists, _bf_provider) except Exception as backfill_error: logger.error(f"Error during {_bf_provider} ID backfilling: {backfill_error}") # Continue with next provider try: filled = scanner.backfill_watchlist_artist_images(scan_profile_id) if filled: logger.info(f"Backfilled {filled} watchlist artist images") except Exception as img_err: logger.error(f"Image backfill error: {img_err}") # Initialize detailed progress tracking watchlist_scan_state.update({ 'total_artists': len(watchlist_artists), 'current_artist_index': 0, 'current_artist_name': '', 'current_artist_image_url': '', 'current_phase': 'starting', 'albums_to_check': 0, 'albums_checked': 0, 'current_album': '', 'current_album_image_url': '', 'current_track_name': '', 'tracks_found_this_scan': 0, 'tracks_added_this_scan': 0, 'recent_wishlist_additions': [] }) scan_results = [] # Pause enrichment workers during scan to reduce API contention _ew_state = _pause_enrichment_workers('watchlist scan') scan_results = scanner.scan_watchlist_profile( scan_profile_id, watchlist_artists=watchlist_artists, scan_state=watchlist_scan_state, cancel_check=lambda: watchlist_scan_state.get('cancel_requested', False), ) # Store final results (skip if cancelled — already set by cancel handler) was_cancelled = watchlist_scan_state.get('cancel_requested', False) if not was_cancelled: _artmap_cache_invalidate(scan_profile_id) successful_scans = [r for r in scan_results if r.success] total_new_tracks = sum(r.new_tracks_found for r in successful_scans) total_added_to_wishlist = sum(r.tracks_added_to_wishlist for r in successful_scans) watchlist_scan_state['status'] = 'completed' watchlist_scan_state['results'] = scan_results watchlist_scan_state['completed_at'] = datetime.now() watchlist_scan_state['current_phase'] = 'completed' watchlist_scan_state['summary'] = { 'total_artists': len(scan_results), 'successful_scans': len(successful_scans), 'new_tracks_found': total_new_tracks, 'tracks_added_to_wishlist': total_added_to_wishlist } logger.info(f"Watchlist scan completed: {len(successful_scans)}/{len(scan_results)} artists scanned successfully") logger.info(f"Found {total_new_tracks} new tracks, added {total_added_to_wishlist} to wishlist") else: logger.warning("Watchlist scan cancelled — skipping post-scan steps") # Post-scan steps — skip if cancelled if not was_cancelled: # Populate discovery pool from similar artists logger.info("Starting discovery pool population...") watchlist_scan_state['current_phase'] = 'populating_discovery_pool' try: scanner.populate_discovery_pool(profile_id=scan_profile_id) logger.info("Discovery pool population complete") except Exception as discovery_error: logger.error(f"Error populating discovery pool: {discovery_error}") import traceback traceback.print_exc() # Update ListenBrainz playlists cache logger.info("Starting ListenBrainz playlists update...") watchlist_scan_state['current_phase'] = 'updating_listenbrainz' try: from core.listenbrainz_manager import ListenBrainzManager db = get_database() db_path = str(db.database_path) # Update for all profiles with LB tokens lb_profiles = db.get_profiles_with_listenbrainz() if lb_profiles: for lb_prof in lb_profiles: lb_manager = ListenBrainzManager(db_path, profile_id=lb_prof['id'], token=lb_prof['token'], base_url=lb_prof['base_url']) lb_result = lb_manager.update_all_playlists() if lb_result.get('success'): logger.info(f"ListenBrainz update complete for profile {lb_prof['id']}: {lb_result.get('summary', {})}") else: # Fallback: use global config token lb_manager = ListenBrainzManager(db_path) lb_result = lb_manager.update_all_playlists() if lb_result.get('success'): logger.info(f"ListenBrainz update complete (global): {lb_result.get('summary', {})}") elif lb_result.get('error'): logger.error(f"ListenBrainz update skipped: {lb_result.get('error')}") except Exception as lb_error: logger.error(f"Error updating ListenBrainz: {lb_error}") import traceback traceback.print_exc() # Update current seasonal playlist (weekly refresh) logger.info("Starting seasonal content update...") watchlist_scan_state['current_phase'] = 'updating_seasonal' try: from core.seasonal_discovery import get_seasonal_discovery_service seasonal_service = get_seasonal_discovery_service(spotify_client, database) # Only update the current active season current_season = seasonal_service.get_current_season() if current_season: if seasonal_service.should_populate_seasonal_content(current_season, days_threshold=7): logger.info(f"Updating {current_season} seasonal content...") seasonal_service.populate_seasonal_content(current_season) seasonal_service.curate_seasonal_playlist(current_season) logger.info(f"{current_season.capitalize()} seasonal content updated") else: logger.info(f"{current_season.capitalize()} seasonal content recently updated, skipping") else: logger.warning("ℹ️ No active season at this time") except Exception as seasonal_error: logger.error(f"Error updating seasonal content: {seasonal_error}") import traceback traceback.print_exc() # Generate Last.fm radio playlists (weekly refresh) logger.info("Starting Last.fm radio generation...") watchlist_scan_state['current_phase'] = 'generating_lastfm_radio' try: scanner._generate_lastfm_radio_playlists() logger.info("Last.fm radio generation complete") except Exception as lastfm_error: logger.error(f"Error generating Last.fm radio playlists: {lastfm_error}") # Sync Spotify library cache logger.info("Syncing Spotify library cache...") watchlist_scan_state['current_phase'] = 'syncing_spotify_library' try: scanner.sync_spotify_library_cache(profile_id=scan_profile_id) logger.info("Spotify library cache sync complete") except Exception as lib_error: logger.error(f"Error syncing Spotify library: {lib_error}") except Exception as e: logger.error(f"Error during watchlist scan: {e}") watchlist_scan_state['status'] = 'error' watchlist_scan_state['error'] = str(e) finally: # Resume enrichment workers if we paused them _resume_enrichment_workers(_ew_state, 'watchlist scan') # Clear one-time rescan cutoff after full scan cycle try: scanner._clear_rescan_cutoff() except Exception as e: logger.debug("scanner rescan cutoff clear failed: %s", e) # Always reset flag when scan completes (success or error) with watchlist_timer_lock: watchlist_auto_scanning = False watchlist_auto_scanning_timestamp = 0 logger.info("[Manual Watchlist Scan] Flag reset - scan complete") # Initialize scan state global watchlist_scan_state watchlist_scan_state = { 'status': 'scanning', 'started_at': datetime.now(), 'results': [], 'summary': {}, 'error': None, 'cancel_requested': False } # Start scan in background thread = threading.Thread(target=run_scan) thread.daemon = True thread.start() return jsonify({"success": True, "message": "Watchlist scan started"}) except Exception as e: logger.error(f"Error starting watchlist scan: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/scan/status', methods=['GET']) def get_watchlist_scan_status(): """Get the current status of watchlist scanning""" try: global watchlist_scan_state if 'watchlist_scan_state' not in globals(): return jsonify({ "success": True, "status": "idle", "summary": {} }) # Convert datetime objects to ISO format for JSON serialization state = watchlist_scan_state.copy() if 'started_at' in state and state['started_at']: state['started_at'] = state['started_at'].isoformat() if 'completed_at' in state and state['completed_at']: state['completed_at'] = state['completed_at'].isoformat() # Remove results array - it contains ScanResult objects that aren't JSON serializable # The summary already contains the aggregate data we need if 'results' in state: del state['results'] return jsonify({"success": True, **state}) except Exception as e: logger.error(f"Error getting watchlist scan status: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/scan/cancel', methods=['POST']) def cancel_watchlist_scan(): """Cancel a running watchlist scan""" try: global watchlist_scan_state if watchlist_scan_state.get('status') != 'scanning': return jsonify({"success": False, "error": "No scan is currently running"}), 400 watchlist_scan_state['cancel_requested'] = True logger.info("[Watchlist Scan] Cancel requested by user") return jsonify({"success": True, "message": "Cancel request sent"}) except Exception as e: logger.error(f"Error cancelling watchlist scan: {e}") return jsonify({"success": False, "error": str(e)}), 500 # Similar Artists Update State similar_artists_update_state = { 'status': 'idle', # idle, running, completed, error 'artists_processed': 0, 'total_artists': 0, 'current_artist': None, 'error': None } similar_artists_executor = ThreadPoolExecutor(max_workers=1, thread_name_prefix="SimilarArtistsUpdate") @app.route('/api/watchlist/update-similar-artists', methods=['POST']) def update_similar_artists_endpoint(): """Update similar artists for all watchlist artists (for discovery feature)""" try: global similar_artists_update_state if similar_artists_update_state['status'] == 'running': return jsonify({"success": False, "error": "Similar artists update already in progress"}), 409 if not spotify_client or not spotify_client.is_authenticated(): return jsonify({"success": False, "error": "Spotify client not available"}), 400 # Reset state similar_artists_update_state = { 'status': 'running', 'artists_processed': 0, 'total_artists': 0, 'current_artist': None, 'error': None } # Start update in background similar_artists_executor.submit(_update_similar_artists_worker) return jsonify({"success": True, "message": "Similar artists update started"}) except Exception as e: logger.error(f"Error starting similar artists update: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/similar-artists-status', methods=['GET']) def get_similar_artists_update_status(): """Get status of similar artists update""" try: global similar_artists_update_state return jsonify({"success": True, **similar_artists_update_state}) except Exception as e: logger.error(f"Error getting similar artists status: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/artist//config', methods=['GET', 'POST']) def watchlist_artist_config(artist_id): """Get or update watchlist artist configuration""" try: from database.music_database import get_database database = get_database() if request.method == 'GET': # Get current config from database conn = sqlite3.connect(str(database.database_path)) cursor = conn.cursor() cursor.execute(""" SELECT include_albums, include_eps, include_singles, include_live, include_remixes, include_acoustic, include_compilations, artist_name, image_url, spotify_artist_id, itunes_artist_id, last_scan_timestamp, date_added, include_instrumentals, deezer_artist_id, lookback_days, discogs_artist_id, preferred_metadata_source FROM watchlist_artists WHERE spotify_artist_id = ? OR itunes_artist_id = ? OR deezer_artist_id = ? OR discogs_artist_id = ? """, (artist_id, artist_id, artist_id, artist_id)) result = cursor.fetchone() conn.close() if not result: return jsonify({"success": False, "error": "Artist not found in watchlist"}), 404 # Determine if this is an iTunes or Spotify artist is_itunes_artist = artist_id.isdigit() spotify_id = result[9] # spotify_artist_id from query itunes_id = result[10] # itunes_artist_id from query deezer_id = result[14] # deezer_artist_id from query discogs_id = result[16] # discogs_artist_id from query # Get artist info from Spotify (only for Spotify artists) artist_info = None if not is_itunes_artist and spotify_client and spotify_client.is_authenticated() and spotify_id and not _spotify_rate_limited(): try: from core.api_call_tracker import api_call_tracker api_call_tracker.record_call('spotify', endpoint='artist') artist_data = spotify_client.sp.artist(spotify_id) if artist_data: artist_info = { 'id': artist_data['id'], 'name': artist_data['name'], 'image_url': artist_data['images'][0]['url'] if artist_data.get('images') else None, 'followers': artist_data.get('followers', {}).get('total', 0), 'popularity': artist_data.get('popularity', 0), 'genres': artist_data.get('genres', []) } except Exception as e: logger.error(f"Could not fetch artist info from Spotify: {e}") # Fallback to database info if Spotify fetch failed if not artist_info: artist_info = { 'id': artist_id, 'name': result[7], # artist_name 'image_url': result[8], # image_url 'followers': 0, 'popularity': 0, 'genres': [] } # Enrich with library artist data (banner, bio, style, mood, label) try: conn2 = sqlite3.connect(str(database.database_path)) cur2 = conn2.cursor() # The library `artists` table uses `deezer_id` / `discogs_id` for # those columns; only the `watchlist_artists` table uses the # `_artist_id` suffix for them. Mixing them was producing a # 'no such column' on every watchlist-config GET. cur2.execute(""" SELECT banner_url, summary, style, mood, label, genres FROM artists WHERE spotify_artist_id = ? OR itunes_artist_id = ? OR deezer_id = ? OR discogs_id = ? LIMIT 1 """, (artist_id, artist_id, artist_id, artist_id)) lib_row = cur2.fetchone() if lib_row: artist_info['banner_url'] = lib_row[0] artist_info['summary'] = lib_row[1] artist_info['style'] = lib_row[2] artist_info['mood'] = lib_row[3] artist_info['label'] = lib_row[4] # Backfill genres from library if Spotify didn't provide any if not artist_info.get('genres') and lib_row[5]: try: artist_info['genres'] = json.loads(lib_row[5]) except (json.JSONDecodeError, TypeError): pass # Get recent releases for this watchlist artist cur2.execute(""" SELECT rr.album_name, rr.release_date, rr.album_cover_url, rr.track_count FROM recent_releases rr JOIN watchlist_artists wa ON rr.watchlist_artist_id = wa.id WHERE wa.spotify_artist_id = ? OR wa.itunes_artist_id = ? OR wa.deezer_artist_id = ? ORDER BY rr.release_date DESC LIMIT 6 """, (artist_id, artist_id, artist_id)) releases = [ { 'album_name': r[0], 'release_date': r[1], 'album_cover_url': r[2], 'track_count': r[3], } for r in cur2.fetchall() ] conn2.close() except Exception as e: logger.error(f"Could not enrich artist from library: {e}") releases = [] config = { 'include_albums': bool(result[0]), # Convert INTEGER to boolean 'include_eps': bool(result[1]), 'include_singles': bool(result[2]), 'include_live': bool(result[3]), 'include_remixes': bool(result[4]), 'include_acoustic': bool(result[5]), 'include_compilations': bool(result[6]), 'include_instrumentals': bool(result[13]) if result[13] is not None else False, 'last_scan_timestamp': result[11], 'date_added': result[12], 'lookback_days': result[15] if len(result) > 15 else None, 'preferred_metadata_source': result[17] if len(result) > 17 else None, } from core.metadata.registry import get_primary_source return jsonify({ "success": True, "config": config, "artist": artist_info, "recent_releases": releases, "spotify_artist_id": spotify_id, "itunes_artist_id": itunes_id, "deezer_artist_id": deezer_id, "discogs_artist_id": discogs_id, "watchlist_name": result[7], # Original stored watchlist artist name "global_metadata_source": get_primary_source(), }) else: # POST data = request.get_json() if not data: return jsonify({"success": False, "error": "No data provided"}), 400 include_albums = data.get('include_albums', True) include_eps = data.get('include_eps', True) include_singles = data.get('include_singles', True) include_live = data.get('include_live', False) include_remixes = data.get('include_remixes', False) include_acoustic = data.get('include_acoustic', False) include_compilations = data.get('include_compilations', False) include_instrumentals = data.get('include_instrumentals', False) lookback_days = data.get('lookback_days', None) # None = use global setting # Validate lookback_days if provided if lookback_days is not None: lookback_days = int(lookback_days) if lookback_days != '' else None preferred_metadata_source = data.get('preferred_metadata_source', None) # Validate — only accept known sources, empty string means clear override if preferred_metadata_source == '' or preferred_metadata_source not in ('spotify', 'deezer', 'itunes', 'discogs'): preferred_metadata_source = None # Validate at least one release type is selected if not (include_albums or include_eps or include_singles): return jsonify({"success": False, "error": "At least one release type must be selected"}), 400 # Update database conn = sqlite3.connect(str(database.database_path)) cursor = conn.cursor() # Check if lookback_days changed — if so, clear last_scan_timestamp to force rescan cursor.execute(""" SELECT lookback_days FROM watchlist_artists WHERE spotify_artist_id = ? OR itunes_artist_id = ? OR deezer_artist_id = ? OR discogs_artist_id = ? """, (artist_id, artist_id, artist_id, artist_id)) old_row = cursor.fetchone() old_lookback = old_row[0] if old_row else None lookback_changed = old_lookback != lookback_days cursor.execute(""" UPDATE watchlist_artists SET include_albums = ?, include_eps = ?, include_singles = ?, include_live = ?, include_remixes = ?, include_acoustic = ?, include_compilations = ?, include_instrumentals = ?, lookback_days = ?, preferred_metadata_source = ?, last_scan_timestamp = CASE WHEN ? THEN NULL ELSE last_scan_timestamp END, updated_at = CURRENT_TIMESTAMP WHERE spotify_artist_id = ? OR itunes_artist_id = ? OR deezer_artist_id = ? OR discogs_artist_id = ? """, (int(include_albums), int(include_eps), int(include_singles), int(include_live), int(include_remixes), int(include_acoustic), int(include_compilations), int(include_instrumentals), lookback_days, preferred_metadata_source, lookback_changed, artist_id, artist_id, artist_id, artist_id)) conn.commit() if cursor.rowcount == 0: conn.close() return jsonify({"success": False, "error": "Artist not found in watchlist"}), 404 conn.close() logger.info(f"Updated watchlist config for artist {artist_id}: albums={include_albums}, eps={include_eps}, singles={include_singles}, live={include_live}, remixes={include_remixes}, acoustic={include_acoustic}, compilations={include_compilations}, instrumentals={include_instrumentals}") return jsonify({ "success": True, "message": "Artist configuration updated successfully", "config": { 'include_albums': include_albums, 'include_eps': include_eps, 'include_singles': include_singles, 'include_live': include_live, 'include_remixes': include_remixes, 'include_acoustic': include_acoustic, 'include_compilations': include_compilations, 'include_instrumentals': include_instrumentals, } }) except Exception as e: logger.error(f"Error in watchlist artist config: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/artist//link-provider', methods=['POST']) def watchlist_artist_link_provider(artist_id): """Manually link a watchlist artist to a different Spotify/iTunes artist.""" try: from database.music_database import get_database database = get_database() data = request.get_json() if not data: return jsonify({"success": False, "error": "No data provided"}), 400 new_provider_id = data.get('provider_id', '').strip() provider = data.get('provider', '').strip() valid_providers = ('spotify', 'itunes', 'deezer', 'discogs') if provider not in valid_providers: return jsonify({"success": False, "error": f"Invalid provider. Must be one of: {', '.join(valid_providers)}"}), 400 # Empty provider_id = clear the match for this source is_clear = not new_provider_id conn = sqlite3.connect(str(database.database_path)) cursor = conn.cursor() # Find the watchlist artist row cursor.execute(""" SELECT id, artist_name, spotify_artist_id, itunes_artist_id FROM watchlist_artists WHERE spotify_artist_id = ? OR itunes_artist_id = ? OR deezer_artist_id = ? OR discogs_artist_id = ? """, (artist_id, artist_id, artist_id, artist_id)) row = cursor.fetchone() if not row: conn.close() return jsonify({"success": False, "error": "Artist not found in watchlist"}), 404 watchlist_row_id = row[0] artist_name = row[1] # Check for duplicate — another watchlist artist already has this provider ID col_map = {'spotify': 'spotify_artist_id', 'itunes': 'itunes_artist_id', 'deezer': 'deezer_artist_id', 'discogs': 'discogs_artist_id'} col = col_map[provider] if not is_clear: cursor.execute(f"SELECT id, artist_name FROM watchlist_artists WHERE {col} = ? AND id != ?", (new_provider_id, watchlist_row_id)) duplicate = cursor.fetchone() if duplicate: conn.close() return jsonify({"success": False, "error": f"Another watchlist artist ('{duplicate[1]}') already has this {provider} ID"}), 409 # Set to new ID or NULL (clear) update_val = new_provider_id if not is_clear else None cursor.execute(f"UPDATE watchlist_artists SET {col} = ?, updated_at = CURRENT_TIMESTAMP WHERE id = ?", (update_val, watchlist_row_id)) conn.commit() conn.close() action = 'Cleared' if is_clear else 'Linked' logger.info(f"{action} watchlist artist '{artist_name}' {provider} ID: {new_provider_id or 'NULL'}") return jsonify({ "success": True, "message": f"Linked to {provider} artist successfully", "new_provider_id": new_provider_id }) except Exception as e: logger.error(f"Error linking watchlist artist provider: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/watchlist/global-config', methods=['GET', 'POST']) def watchlist_global_config(): """Get or update global watchlist configuration (overrides per-artist settings)""" try: if request.method == 'GET': config = { 'global_override_enabled': config_manager.get('watchlist.global_override_enabled', False), 'include_albums': config_manager.get('watchlist.global_include_albums', True), 'include_eps': config_manager.get('watchlist.global_include_eps', True), 'include_singles': config_manager.get('watchlist.global_include_singles', True), 'include_live': config_manager.get('watchlist.global_include_live', False), 'include_remixes': config_manager.get('watchlist.global_include_remixes', False), 'include_acoustic': config_manager.get('watchlist.global_include_acoustic', False), 'include_compilations': config_manager.get('watchlist.global_include_compilations', False), 'include_instrumentals': config_manager.get('watchlist.global_include_instrumentals', False), 'exclude_terms': config_manager.get('watchlist.exclude_terms', ''), } return jsonify({"success": True, "config": config}) else: # POST data = request.get_json() if not data: return jsonify({"success": False, "error": "No data provided"}), 400 global_override_enabled = data.get('global_override_enabled', False) include_albums = data.get('include_albums', True) include_eps = data.get('include_eps', True) include_singles = data.get('include_singles', True) include_live = data.get('include_live', False) include_remixes = data.get('include_remixes', False) include_acoustic = data.get('include_acoustic', False) include_compilations = data.get('include_compilations', False) include_instrumentals = data.get('include_instrumentals', False) exclude_terms = data.get('exclude_terms', '') # When override is enabled, validate at least one release type if global_override_enabled and not (include_albums or include_eps or include_singles): return jsonify({"success": False, "error": "At least one release type must be selected"}), 400 config_manager.set('watchlist.global_override_enabled', global_override_enabled) config_manager.set('watchlist.global_include_albums', include_albums) config_manager.set('watchlist.global_include_eps', include_eps) config_manager.set('watchlist.global_include_singles', include_singles) config_manager.set('watchlist.global_include_live', include_live) config_manager.set('watchlist.global_include_remixes', include_remixes) config_manager.set('watchlist.global_include_acoustic', include_acoustic) config_manager.set('watchlist.global_include_compilations', include_compilations) config_manager.set('watchlist.global_include_instrumentals', include_instrumentals) config_manager.set('watchlist.exclude_terms', exclude_terms) logger.info(f"Updated global watchlist config: override={global_override_enabled}, " f"albums={include_albums}, eps={include_eps}, singles={include_singles}, " f"live={include_live}, remixes={include_remixes}, acoustic={include_acoustic}, " f"compilations={include_compilations}, instrumentals={include_instrumentals}, " f"exclude_terms='{exclude_terms}'") return jsonify({ "success": True, "message": "Global watchlist configuration updated", "config": { 'global_override_enabled': global_override_enabled, 'include_albums': include_albums, 'include_eps': include_eps, 'include_singles': include_singles, 'include_live': include_live, 'include_remixes': include_remixes, 'include_acoustic': include_acoustic, 'include_compilations': include_compilations, 'include_instrumentals': include_instrumentals, 'exclude_terms': exclude_terms, } }) except Exception as e: logger.error(f"Error in watchlist global config: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 def _update_similar_artists_worker(): """Background worker to update similar artists for all watchlist artists""" global similar_artists_update_state try: from core.watchlist_scanner import get_watchlist_scanner from database.music_database import get_database import time logger.info("[Similar Artists] Starting similar artists update...") database = get_database() all_profiles = database.get_all_profiles() # Build per-profile artist lists and deduplicate for API calls # artist_key -> (artist_obj, [profile_ids]) artist_profiles = {} for p in all_profiles: for artist in database.get_watchlist_artists(profile_id=p['id']): key = (artist.spotify_artist_id or '', artist.itunes_artist_id or '', artist.artist_name.lower()) if key not in artist_profiles: artist_profiles[key] = (artist, []) artist_profiles[key][1].append(p['id']) if not artist_profiles: similar_artists_update_state['status'] = 'completed' logger.warning("[Similar Artists] No watchlist artists to process") return similar_artists_update_state['total_artists'] = len(artist_profiles) logger.info(f"[Similar Artists] Processing {len(artist_profiles)} unique watchlist artists across {len(all_profiles)} profiles") scanner = get_watchlist_scanner(spotify_client) for idx, (_key, (artist, profile_ids)) in enumerate(artist_profiles.items(), 1): try: similar_artists_update_state['artists_processed'] = idx similar_artists_update_state['current_artist'] = artist.artist_name logger.info(f"[{idx}/{len(artist_profiles)}] Updating similar artists for {artist.artist_name} (profiles: {profile_ids})") # Update similar artists for each profile that watches this artist for pid in profile_ids: scanner.update_similar_artists(artist, limit=10, profile_id=pid) # Rate limiting if idx < len(artist_profiles): time.sleep(2.0) # 2 seconds between artists except Exception as artist_error: logger.error(f"[Similar Artists] Error processing {artist.artist_name}: {artist_error}") continue # Update complete similar_artists_update_state['status'] = 'completed' similar_artists_update_state['current_artist'] = None logger.info(f"[Similar Artists] Update complete! Processed {len(artist_profiles)} artists") except Exception as e: logger.error(f"[Similar Artists] Critical error: {e}") import traceback traceback.print_exc() similar_artists_update_state['status'] = 'error' similar_artists_update_state['error'] = str(e) # --- Watchlist Auto-Scanning System --- watchlist_scan_state = { 'status': 'idle', 'results': [], 'summary': {}, 'error': None } # Watchlist auto-scan logic lives in core/watchlist/auto_scan.py. from core.watchlist import auto_scan as _watchlist_auto_scan def _build_watchlist_auto_scan_deps(): """Build the WatchlistAutoScanDeps bundle from web_server.py globals on each call. The three watchlist globals are exposed via property setters on the deps proxy so the lifted body keeps `name = value` assignment syntax. The callback pairs below rebind the module-level names when those setters fire. """ def _get_flag(): return watchlist_auto_scanning def _set_flag(value): global watchlist_auto_scanning watchlist_auto_scanning = value def _get_ts(): return watchlist_auto_scanning_timestamp def _set_ts(value): global watchlist_auto_scanning_timestamp watchlist_auto_scanning_timestamp = value def _get_state(): return watchlist_scan_state def _set_state(value): global watchlist_scan_state watchlist_scan_state = value return _watchlist_auto_scan.WatchlistAutoScanDeps( app=app, spotify_client=spotify_client, automation_engine=automation_engine, watchlist_timer_lock=watchlist_timer_lock, is_watchlist_actually_scanning=is_watchlist_actually_scanning, pause_enrichment_workers=_pause_enrichment_workers, resume_enrichment_workers=_resume_enrichment_workers, update_automation_progress=_update_automation_progress, add_activity_item=add_activity_item, _get_auto_scanning=_get_flag, _set_auto_scanning=_set_flag, _get_auto_scanning_timestamp=_get_ts, _set_auto_scanning_timestamp=_set_ts, _get_watchlist_scan_state=_get_state, _set_watchlist_scan_state=_set_state, ) def _process_watchlist_scan_automatically(automation_id=None, profile_id=None): return _watchlist_auto_scan.process_watchlist_scan_automatically( automation_id, profile_id, _build_watchlist_auto_scan_deps() ) # --- Metadata Updater System --- from concurrent.futures import ThreadPoolExecutor # Global state for metadata update process metadata_update_state = { 'status': 'idle', 'current_artist': '', 'processed': 0, 'total': 0, 'percentage': 0.0, 'successful': 0, 'failed': 0, 'started_at': None, 'completed_at': None, 'error': None, 'refresh_interval_days': 30 } metadata_update_worker = None metadata_update_runtime_worker = None metadata_update_executor = ThreadPoolExecutor(max_workers=1, thread_name_prefix="metadata_update") from core.workers.metadata_update import WebMetadataUpdateWorker, init as _init_metadata_update_worker _init_metadata_update_worker(metadata_update_state) # =============================== # == DISCOVER PAGE ENDPOINTS == # =============================== def _get_active_discovery_source(): """ Determine which music source is active for discovery. Returns the user's configured primary metadata source. If the selected source requires auth and isn't available, falls back. NOTE: Thin wrapper — canonical logic lives in core.metadata_service.get_primary_source(). """ from core.metadata.registry import get_primary_source return get_primary_source() from core.discovery.hero import ( get_discover_hero as _discover_hero_get, init as _init_discover_hero, ) @app.route('/api/discover/hero', methods=['GET']) def get_discover_hero(): return _discover_hero_get() @app.route('/api/discover/similar-artists', methods=['GET']) def get_discover_similar_artists(): """Get all recommended similar artists (basic data, no enrichment for speed)""" try: database = get_database() active_source = _get_active_discovery_source() similar_artists = database.get_top_similar_artists(limit=200, profile_id=get_current_profile_id(), require_source=active_source) if not similar_artists: return jsonify({"success": True, "artists": [], "source": active_source, "count": 0}) # Artists already filtered by source in SQL result_artists = [] for artist in similar_artists: if active_source == 'spotify': artist_id = artist.similar_artist_spotify_id elif active_source == 'deezer': artist_id = getattr(artist, 'similar_artist_deezer_id', None) or artist.similar_artist_itunes_id else: artist_id = artist.similar_artist_itunes_id artist_data = { "artist_id": artist_id, "spotify_artist_id": artist.similar_artist_spotify_id, "itunes_artist_id": artist.similar_artist_itunes_id, "artist_name": artist.similar_artist_name, "occurrence_count": artist.occurrence_count, "similarity_rank": artist.similarity_rank, "source": active_source, } # Include cached metadata if available if artist.image_url: artist_data["image_url"] = artist.image_url if artist.genres: artist_data["genres"] = artist.genres[:3] if artist.popularity: artist_data["popularity"] = artist.popularity result_artists.append(artist_data) logger.info(f"[Similar Artists] {len(similar_artists)} from DB, {len(result_artists)} valid for {active_source}") return jsonify({ "success": True, "artists": result_artists, "source": active_source, "count": len(result_artists) }) except Exception as e: logger.error(f"Error getting similar artists: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/similar-artists/enrich', methods=['POST']) def enrich_similar_artists(): """Enrich a batch of artist IDs with images/genres from Spotify or iTunes. Uses cached metadata from DB when available, only makes API calls for uncached artists, and saves new results back to DB for future use.""" try: data = request.get_json() artist_ids = data.get('artist_ids', []) source = data.get('source', 'spotify') if not artist_ids: return jsonify({"success": True, "artists": {}}) database = get_database() enriched = {} uncached_ids = [] # Check DB cache first — get all similar artists and index by external ID cached_artists = database.get_top_similar_artists(limit=500, profile_id=get_current_profile_id()) cache_map = {} for artist in cached_artists: if source == 'spotify': ext_id = artist.similar_artist_spotify_id elif source == 'deezer': ext_id = getattr(artist, 'similar_artist_deezer_id', None) or artist.similar_artist_itunes_id else: ext_id = artist.similar_artist_itunes_id if ext_id and ext_id not in cache_map: cache_map[ext_id] = artist for aid in artist_ids[:50]: cached = cache_map.get(aid) if cached and cached.image_url: # Use cached metadata enriched[aid] = { "artist_name": cached.similar_artist_name, "image_url": cached.image_url, "genres": cached.genres[:3] if cached.genres else [], "popularity": cached.popularity or 0 } else: uncached_ids.append(aid) # Only make API calls for uncached artists if uncached_ids: if source == 'spotify' and spotify_client and spotify_client.is_authenticated() and not _spotify_rate_limited(): try: from core.api_call_tracker import api_call_tracker api_call_tracker.record_call('spotify', endpoint='artists_batch') batch_result = spotify_client.sp.artists(uncached_ids[:50]) if batch_result and 'artists' in batch_result: for sp_artist in batch_result['artists']: if sp_artist: img_url = sp_artist['images'][0].get('url') if sp_artist.get('images') else None genres = sp_artist.get('genres', [])[:3] pop = sp_artist.get('popularity', 0) enriched[sp_artist['id']] = { "artist_name": sp_artist.get('name'), "image_url": img_url, "genres": genres, "popularity": pop } # Cache to DB for future use database.update_similar_artist_metadata_by_external_id( sp_artist['id'], 'spotify', image_url=img_url, genres=genres, popularity=pop ) except Exception as e: from core.spotify_client import _detect_and_set_rate_limit _detect_and_set_rate_limit(e, 'enrich_similar_artists') logger.error(f"Error enriching Spotify batch: {e}") else: fallback_client = _get_metadata_fallback_client() fallback_source = _get_metadata_fallback_source() for aid in uncached_ids[:50]: try: fb_artist = fallback_client.get_artist(aid) if fb_artist: img_url = fb_artist.get('images', [{}])[0].get('url') if fb_artist.get('images') else None genres = fb_artist.get('genres', [])[:3] enriched[aid] = { "artist_name": fb_artist.get('name'), "image_url": img_url, "genres": genres, "popularity": 0 } # Cache to DB for future use database.update_similar_artist_metadata_by_external_id( aid, fallback_source, image_url=img_url, genres=genres, popularity=0 ) except Exception as e: logger.debug("similar artist enrichment failed: %s", e) cached_count = len(enriched) - len([aid for aid in uncached_ids if aid in enriched]) api_count = len([aid for aid in uncached_ids if aid in enriched]) if uncached_ids: logger.warning(f"[Enrich] {cached_count} from cache, {api_count} from API ({len(uncached_ids) - api_count} missed)") return jsonify({"success": True, "artists": enriched}) except Exception as e: logger.error(f"Error enriching similar artists: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/spotify-library', methods=['GET']) def get_spotify_library(): """Get cached Spotify library albums with ownership status. Only available when Spotify is authenticated.""" try: # Skip entirely if Spotify is not the active source if not spotify_client or not spotify_client.is_spotify_authenticated(): return jsonify({ "success": True, "albums": [], "total": 0, "offset": 0, "limit": 0, "stats": {"total": 0, "owned": 0, "missing": 0} }) database = get_database() profile_id = get_current_profile_id() offset = request.args.get('offset', 0, type=int) limit = request.args.get('limit', 48, type=int) search = request.args.get('search', '', type=str) status_filter = request.args.get('status', 'all', type=str) sort = request.args.get('sort', 'date_saved', type=str) sort_dir = request.args.get('sort_dir', 'desc', type=str) # Fetch all matching albums (ownership requires post-query computation) all_albums, total = database.get_spotify_library_albums( offset=0, limit=10000, search=search, sort=sort, sort_dir=sort_dir, profile_id=profile_id ) if not all_albums: return jsonify({ "success": True, "albums": [], "total": 0, "offset": offset, "limit": limit, "stats": {"total": 0, "owned": 0, "missing": 0} }) # Cross-reference with local library for ownership status library_spotify_ids = database.get_library_spotify_album_ids(profile_id) library_album_names = database.get_library_album_names() owned_count = 0 for album in all_albums: # Check by Spotify album ID first, then fuzzy match by name if album['spotify_album_id'] in library_spotify_ids: album['in_library'] = True elif (album['artist_name'].lower(), album['album_name'].lower()) in library_album_names: album['in_library'] = True else: album['in_library'] = False if album['in_library']: owned_count += 1 # Apply status filter then paginate if status_filter == 'missing': filtered = [a for a in all_albums if not a['in_library']] elif status_filter == 'owned': filtered = [a for a in all_albums if a['in_library']] else: filtered = all_albums filtered_total = len(filtered) albums = filtered[offset:offset + limit] stats = { 'total': total, 'owned': owned_count, 'missing': total - owned_count, } return jsonify({ "success": True, "albums": albums, "total": filtered_total, "offset": offset, "limit": limit, "stats": stats, }) except Exception as e: logger.error(f"Error getting Spotify library: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/spotify-library/refresh', methods=['POST']) def refresh_spotify_library(): """Manually trigger a re-sync of the Spotify library cache""" try: def _run_sync(): try: from core.watchlist_scanner import get_watchlist_scanner scanner = get_watchlist_scanner(spotify_client) if scanner: # Force full sync by clearing last_sync timestamp database = get_database() database.set_metadata('spotify_library_last_sync', '') database.set_metadata('spotify_library_last_full_sync', '') scanner.sync_spotify_library_cache(profile_id=get_current_profile_id()) logger.info("Manual Spotify library refresh complete") except Exception as e: logger.error(f"Error in manual Spotify library refresh: {e}") import threading thread = threading.Thread(target=_run_sync, daemon=True) thread.start() return jsonify({"success": True, "message": "Spotify library refresh started"}) except Exception as e: logger.error(f"Error starting Spotify library refresh: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/recent-releases', methods=['GET']) def get_discover_recent_releases(): """Get cached recent albums from watchlist and similar artists""" try: database = get_database() # Determine active source active_source = _get_active_discovery_source() # Get cached recent albums filtered by source (max 20) albums = database.get_discovery_recent_albums(limit=20, source=active_source, profile_id=get_current_profile_id()) # Backfill missing cover art from metadata source for album in albums: if not album.get('album_cover_url'): cover = None album_id = album.get('album_deezer_id') or album.get('album_itunes_id') or album.get('album_spotify_id') try: # Try direct ID lookup first if album_id: fallback = _get_metadata_fallback_client() if fallback: album_data = fallback.get_album(str(album_id)) if album_data: imgs = album_data.get('images', []) cover = album_data.get('image_url') or (imgs[0].get('url') if imgs else None) # Fallback: search by name if not cover and album.get('album_name') and album.get('artist_name'): fallback = _get_metadata_fallback_client() if fallback: results = fallback.search_albums(f"{album['artist_name']} {album['album_name']}", limit=1) if results and hasattr(results[0], 'image_url') and results[0].image_url: cover = results[0].image_url album_id = str(results[0].id) if cover: album['album_cover_url'] = cover if album_id: try: database.update_discovery_recent_album_cover(album_id, cover) except Exception as e: logger.debug("recent album cover update failed: %s", e) except Exception as e: logger.debug("recent album cover fetch failed: %s", e) # Filter out blacklisted artists blacklisted = database.get_discovery_blacklist_names() if blacklisted: albums = [a for a in albums if a.get('artist_name', '').lower() not in blacklisted] return jsonify({"success": True, "albums": albums, "source": active_source}) except Exception as e: logger.error(f"Error getting recent releases: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/release-radar', methods=['GET']) def get_discover_release_radar(): """Get release radar playlist - curated selection that stays consistent until next update""" try: database = get_database() # Determine active source - release radar works with any source now active_source = _get_active_discovery_source() # Try source-specific playlist first, then fall back to generic pid = get_current_profile_id() curated_track_ids = database.get_curated_playlist(f'release_radar_{active_source}', profile_id=pid) if not curated_track_ids: curated_track_ids = database.get_curated_playlist('release_radar', profile_id=pid) if curated_track_ids: # Use curated selection - fetch track data from discovery pool filtered by source discovery_tracks = database.get_discovery_pool_tracks(limit=5000, new_releases_only=False, source=active_source, profile_id=pid) # Build lookup dict with source-appropriate IDs tracks_by_id = {} for track in discovery_tracks: if active_source == 'spotify' and track.spotify_track_id: tracks_by_id[track.spotify_track_id] = track elif active_source == 'deezer' and getattr(track, 'deezer_track_id', None): tracks_by_id[track.deezer_track_id] = track elif active_source == 'itunes' and track.itunes_track_id: tracks_by_id[track.itunes_track_id] = track selected_tracks = [] for track_id in curated_track_ids: if track_id in tracks_by_id: track = tracks_by_id[track_id] # Parse track_data_json if it's a string track_data = track.track_data_json if isinstance(track_data, str): try: track_data = json.loads(track_data) except: track_data = None selected_tracks.append({ "track_id": track.spotify_track_id or getattr(track, 'deezer_track_id', None) or track.itunes_track_id, "spotify_track_id": track.spotify_track_id, "itunes_track_id": track.itunes_track_id, "deezer_track_id": getattr(track, 'deezer_track_id', None), "track_name": track.track_name, "artist_name": track.artist_name, "album_name": track.album_name, "album_cover_url": track.album_cover_url, "duration_ms": track.duration_ms, "track_data_json": track_data, "source": track.source }) return jsonify({"success": True, "tracks": selected_tracks, "source": active_source}) # Fallback: no curated playlist exists (shouldn't happen after first scan) return jsonify({"success": True, "tracks": [], "source": active_source}) except Exception as e: logger.error(f"Error getting release radar: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/because-you-listen-to', methods=['GET']) def get_discover_because_you_listen_to(): """Get 'Because You Listen To' sections — personalized by top played artists.""" try: database = get_database() active_source = _get_active_discovery_source() pid = get_current_profile_id() # Fetch pool tracks once for all sections pool_tracks = database.get_discovery_pool_tracks(limit=5000, new_releases_only=False, source=active_source, profile_id=pid) tracks_by_id = {} for t in pool_tracks: if active_source == 'spotify' and t.spotify_track_id: tracks_by_id[t.spotify_track_id] = t elif active_source == 'itunes' and t.itunes_track_id: tracks_by_id[t.itunes_track_id] = t elif active_source == 'deezer' and getattr(t, 'deezer_track_id', None): tracks_by_id[t.deezer_track_id] = t sections = [] for i in range(3): artist_name = database.get_metadata(f'bylt_artist_{i}') if not artist_name: continue track_ids = database.get_curated_playlist(f'because_you_listen_to_{i}', profile_id=pid) if not track_ids: continue tracks = [] for tid in track_ids: t = tracks_by_id.get(tid) if t: tracks.append({ 'id': tid, 'name': t.track_name, 'artist': t.artist_name, 'album': t.album_name, 'image_url': t.album_cover_url, 'duration_ms': t.duration_ms, 'popularity': t.popularity, }) if tracks: # Get artist image artist_image = None try: conn = database._get_connection() cursor = conn.cursor() cursor.execute("SELECT thumb_url FROM artists WHERE LOWER(name) = LOWER(?) LIMIT 1", (artist_name,)) row = cursor.fetchone() if row and row[0]: artist_image = fix_artist_image_url(row[0]) conn.close() except Exception as e: logger.debug("artist image lookup failed: %s", e) sections.append({ 'artist_name': artist_name, 'artist_image': artist_image, 'tracks': tracks, }) return jsonify({'success': True, 'sections': sections}) except Exception as e: logger.error(f"Error getting BYLT: {e}") return jsonify({'success': True, 'sections': []}) @app.route('/api/discover/undiscovered-albums', methods=['GET']) def get_discover_undiscovered_albums(): """Albums by artists you listen to that aren't in your library — from cache.""" try: database = get_database() cache = get_metadata_cache() active_source = _get_active_discovery_source() # Get top played artists top = database.get_top_artists('all', 25) artist_names = [a['name'] for a in top if a.get('name')] if not artist_names: return jsonify({'success': True, 'albums': []}) # Build library album keys for exclusion with database._get_connection() as conn: cursor = conn.cursor() cursor.execute(""" SELECT LOWER(al.title), LOWER(ar.name) FROM albums al JOIN artists ar ON ar.id = al.artist_id """) library_keys = {(r[0].strip(), r[1].strip()) for r in cursor.fetchall()} albums = cache.get_undiscovered_albums(artist_names, library_keys, source=active_source, limit=20) return jsonify({'success': True, 'albums': albums}) except Exception as e: logger.error(f"Undiscovered albums endpoint error: {e}") return jsonify({'success': True, 'albums': []}) @app.route('/api/discover/genre-new-releases', methods=['GET']) def get_discover_genre_new_releases(): """Recent releases matching your top genres — from cache.""" try: database = get_database() cache = get_metadata_cache() genres = database.get_genre_breakdown('all') genre_names = [g['genre'] for g in (genres or [])[:10] if g.get('genre')] if not genre_names: return jsonify({'success': True, 'albums': []}) allowed = _get_genre_allowed_sources() albums = cache.get_genre_new_releases(genre_names, sources=allowed, limit=20) return jsonify({'success': True, 'albums': albums}) except Exception as e: logger.error(f"Genre new releases endpoint error: {e}") return jsonify({'success': True, 'albums': []}) @app.route('/api/discover/label-explorer', methods=['GET']) def get_discover_label_explorer(): """Popular albums from labels in your library — from cache.""" try: database = get_database() cache = get_metadata_cache() with database._get_connection() as conn: cursor = conn.cursor() cursor.execute(""" SELECT DISTINCT label FROM albums WHERE label IS NOT NULL AND label != '' LIMIT 30 """) labels = {r[0] for r in cursor.fetchall()} active_source = _get_active_discovery_source() if not labels: return jsonify({'success': True, 'albums': [], 'labels': []}) albums = cache.get_label_explorer(labels, source=active_source, limit=20) return jsonify({'success': True, 'albums': albums, 'labels': sorted(labels)}) except Exception as e: logger.error(f"Label explorer endpoint error: {e}") return jsonify({'success': True, 'albums': [], 'labels': []}) @app.route('/api/discover/deep-cuts', methods=['GET']) def get_discover_deep_cuts(): """Low-popularity tracks from artists you listen to — from cache.""" try: database = get_database() cache = get_metadata_cache() top = database.get_top_artists('all', 15) artist_names = [a['name'] for a in top if a.get('name')] active_source = _get_active_discovery_source() if not artist_names: return jsonify({'success': True, 'tracks': []}) tracks = cache.get_deep_cuts(artist_names, source=active_source, popularity_cap=30, limit=20) return jsonify({'success': True, 'tracks': tracks}) except Exception as e: logger.error(f"Deep cuts endpoint error: {e}") return jsonify({'success': True, 'tracks': []}) def _get_genre_allowed_sources(): """Get allowed metadata sources for genre features. Spotify authed → ['spotify', 'itunes', 'deezer'] Not authed → ['itunes', 'deezer']""" sources = ['itunes', 'deezer'] if spotify_client and spotify_client.is_spotify_authenticated(): sources.append('spotify') return sources @app.route('/api/discover/genre-explorer', methods=['GET']) def get_discover_genre_explorer(): """Genre landscape from cached artists — highlights unexplored genres.""" try: database = get_database() cache = get_metadata_cache() genres = database.get_genre_breakdown('all') user_genres = {g['genre'] for g in (genres or []) if g.get('genre')} allowed = _get_genre_allowed_sources() data = cache.get_genre_explorer(user_genres, sources=allowed) return jsonify({'success': True, 'genres': data}) except Exception as e: logger.error(f"Genre explorer endpoint error: {e}") return jsonify({'success': True, 'genres': []}) @app.route('/api/discover/genre-deep-dive', methods=['GET']) def get_discover_genre_deep_dive(): """Get artists + albums for a genre — from cache.""" try: genre = request.args.get('genre', '').strip() if not genre: return jsonify({'success': False, 'error': 'genre required'}), 400 cache = get_metadata_cache() allowed = _get_genre_allowed_sources() data = cache.get_genre_deep_dive(genre, sources=allowed) return jsonify({'success': True, **data}) except Exception as e: logger.error(f"Genre albums endpoint error: {e}") return jsonify({'success': True, 'albums': []}) @app.route('/api/discover/resolve-cache-album', methods=['GET']) def resolve_cache_album(): """Look up a real album entity in the cache by name+artist (avoids playlist ID confusion).""" try: name = request.args.get('name', '').strip() artist = request.args.get('artist', '').strip() if not name or not artist: return jsonify({'success': False, 'error': 'name and artist required'}), 400 active_source = _get_active_discovery_source() database = get_database() with database._get_connection() as conn: cursor = conn.cursor() # Strategy 1: exact match, prefer active source cursor.execute(""" SELECT entity_id, source FROM metadata_cache_entities WHERE entity_type = 'album' AND name COLLATE NOCASE = ? COLLATE NOCASE AND artist_name COLLATE NOCASE = ? COLLATE NOCASE ORDER BY CASE WHEN source = ? THEN 0 ELSE 1 END LIMIT 1 """, (name, artist, active_source)) row = cursor.fetchone() if row: return jsonify({'success': True, 'entity_id': row['entity_id'], 'source': row['source']}) # Strategy 2: partial match (handles "Album - Single" vs "Album" naming) cursor.execute(""" SELECT entity_id, source FROM metadata_cache_entities WHERE entity_type = 'album' AND name COLLATE NOCASE LIKE ? COLLATE NOCASE AND artist_name COLLATE NOCASE LIKE ? COLLATE NOCASE ORDER BY CASE WHEN source = ? THEN 0 ELSE 1 END LIMIT 1 """, (f'%{name}%', f'%{artist}%', active_source)) row = cursor.fetchone() if row: return jsonify({'success': True, 'entity_id': row['entity_id'], 'source': row['source']}) # Strategy 3: not in cache — try searching the fallback client directly fallback = _get_metadata_fallback_client() if fallback: try: results = fallback.search_albums(f"{artist} {name}", limit=3) if results: r = results[0] return jsonify({'success': True, 'entity_id': str(r.id), 'source': _get_metadata_fallback_source()}) except Exception as e: logger.debug("fallback album search failed: %s", e) return jsonify({'success': False, 'error': 'Album not found in cache'}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/discover/weekly', methods=['GET']) def get_discover_weekly(): """Get discovery weekly playlist - curated selection that stays consistent until next update""" try: database = get_database() # Determine active source active_source = _get_active_discovery_source() # Try source-specific playlist first, then fall back to generic pid = get_current_profile_id() curated_track_ids = database.get_curated_playlist(f'discovery_weekly_{active_source}', profile_id=pid) if not curated_track_ids: curated_track_ids = database.get_curated_playlist('discovery_weekly', profile_id=pid) if curated_track_ids: # Use curated selection - fetch track data from discovery pool filtered by source discovery_tracks = database.get_discovery_pool_tracks(limit=5000, new_releases_only=False, source=active_source, profile_id=pid) # Build lookup dict with source-appropriate IDs tracks_by_id = {} for track in discovery_tracks: if active_source == 'spotify' and track.spotify_track_id: tracks_by_id[track.spotify_track_id] = track elif active_source == 'deezer' and getattr(track, 'deezer_track_id', None): tracks_by_id[track.deezer_track_id] = track elif active_source == 'itunes' and track.itunes_track_id: tracks_by_id[track.itunes_track_id] = track selected_tracks = [] for track_id in curated_track_ids: if track_id in tracks_by_id: track = tracks_by_id[track_id] # Parse track_data_json if it's a string track_data = track.track_data_json if isinstance(track_data, str): try: track_data = json.loads(track_data) except: track_data = None selected_tracks.append({ "track_id": track.spotify_track_id or getattr(track, 'deezer_track_id', None) or track.itunes_track_id, "spotify_track_id": track.spotify_track_id, "itunes_track_id": track.itunes_track_id, "deezer_track_id": getattr(track, 'deezer_track_id', None), "track_name": track.track_name, "artist_name": track.artist_name, "album_name": track.album_name, "album_cover_url": track.album_cover_url, "duration_ms": track.duration_ms, "track_data_json": track_data, "source": track.source }) return jsonify({"success": True, "tracks": selected_tracks, "source": active_source}) # Fallback: no curated playlist exists (shouldn't happen after first scan) return jsonify({"success": True, "tracks": [], "source": active_source}) except Exception as e: logger.error(f"Error getting discovery weekly: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/refresh', methods=['POST']) def refresh_discover_data(): """ Force refresh discover page data (recent albums cache and curated playlists). Useful for initial setup or when data appears stale. """ try: from core.watchlist_scanner import WatchlistScanner database = get_database() scanner = WatchlistScanner(spotify_client, database) logger.info("[Discover Refresh] Starting forced refresh of discover data...") refresh_pid = get_current_profile_id() # Cache recent albums from watchlist and similar artists logger.info("[Discover Refresh] Caching recent albums...") scanner.cache_discovery_recent_albums(profile_id=refresh_pid) # Curate playlists logger.info("[Discover Refresh] Curating discovery playlists...") scanner.curate_discovery_playlists(profile_id=refresh_pid) # Get counts for response active_source = _get_active_discovery_source() pid = get_current_profile_id() recent_albums = database.get_discovery_recent_albums(limit=100, source=active_source, profile_id=pid) release_radar = database.get_curated_playlist(f'release_radar_{active_source}', profile_id=pid) or [] discovery_weekly = database.get_curated_playlist(f'discovery_weekly_{active_source}', profile_id=pid) or [] logger.info(f"[Discover Refresh] Complete! Recent albums: {len(recent_albums)}, Release Radar: {len(release_radar)} tracks, Discovery Weekly: {len(discovery_weekly)} tracks") return jsonify({ "success": True, "message": "Discover data refreshed", "source": active_source, "recent_albums_count": len(recent_albums), "release_radar_tracks": len(release_radar), "discovery_weekly_tracks": len(discovery_weekly) }) except Exception as e: logger.error(f"Error refreshing discover data: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/diagnose', methods=['GET']) def diagnose_discover_data(): """ Diagnostic endpoint to check the state of discover data. Returns counts of similar artists, discovery pool, recent albums, etc. """ try: database = get_database() active_source = _get_active_discovery_source() pid = get_current_profile_id() with database._get_connection() as conn: cursor = conn.cursor() # Similar artists stats cursor.execute("SELECT COUNT(*) as total FROM similar_artists WHERE profile_id = ?", (pid,)) total_similar = cursor.fetchone()['total'] cursor.execute("SELECT COUNT(*) as count FROM similar_artists WHERE similar_artist_itunes_id IS NOT NULL AND profile_id = ?", (pid,)) similar_with_itunes = cursor.fetchone()['count'] cursor.execute("SELECT COUNT(*) as count FROM similar_artists WHERE similar_artist_spotify_id IS NOT NULL AND profile_id = ?", (pid,)) similar_with_spotify = cursor.fetchone()['count'] # Discovery pool stats cursor.execute("SELECT source, COUNT(*) as count FROM discovery_pool WHERE profile_id = ? GROUP BY source", (pid,)) pool_by_source = {row['source']: row['count'] for row in cursor.fetchall()} # Recent albums stats cursor.execute("SELECT source, COUNT(*) as count FROM discovery_recent_albums WHERE profile_id = ? GROUP BY source", (pid,)) albums_by_source = {row['source']: row['count'] for row in cursor.fetchall()} # Curated playlists cursor.execute("SELECT playlist_type, track_ids_json FROM discovery_curated_playlists WHERE profile_id = ?", (pid,)) playlists = {} for row in cursor.fetchall(): import json track_ids = json.loads(row['track_ids_json']) if row['track_ids_json'] else [] playlists[row['playlist_type']] = len(track_ids) # Watchlist artists cursor.execute("SELECT COUNT(*) as total FROM watchlist_artists WHERE profile_id = ?", (pid,)) total_watchlist = cursor.fetchone()['total'] cursor.execute("SELECT COUNT(*) as count FROM watchlist_artists WHERE itunes_artist_id IS NOT NULL AND profile_id = ?", (pid,)) watchlist_with_itunes = cursor.fetchone()['count'] return jsonify({ "success": True, "active_source": active_source, "similar_artists": { "total": total_similar, "with_itunes_id": similar_with_itunes, "with_spotify_id": similar_with_spotify }, "discovery_pool": pool_by_source, "recent_albums": albums_by_source, "curated_playlists": playlists, "watchlist_artists": { "total": total_watchlist, "with_itunes_id": watchlist_with_itunes } }) except Exception as e: logger.error(f"Error diagnosing discover data: {e}") return jsonify({"success": False, "error": str(e)}), 500 # ======================================== # SEASONAL DISCOVERY ENDPOINTS # ======================================== @app.route('/api/discover/seasonal/current', methods=['GET']) def get_current_seasonal_content(): """Auto-detect and return current season's content""" try: from core.seasonal_discovery import get_seasonal_discovery_service database = get_database() seasonal_service = get_seasonal_discovery_service(spotify_client, database) # Get current season current_season = seasonal_service.get_current_season() if not current_season: return jsonify({"success": True, "season": None, "albums": [], "playlist_available": False}) # Get seasonal config from core.seasonal_discovery import SEASONAL_CONFIG config = SEASONAL_CONFIG[current_season] # Get albums for active source (increased limit for more variety) active_source = _get_active_discovery_source() albums = seasonal_service.get_seasonal_albums(current_season, limit=40, source=active_source) # Check if playlist is curated for active source playlist_track_ids = seasonal_service.get_curated_seasonal_playlist(current_season, source=active_source) return jsonify({ "success": True, "season": current_season, "name": config['name'], "description": config['description'], "icon": config['icon'], "albums": albums, "playlist_available": len(playlist_track_ids) > 0 }) except Exception as e: logger.error(f"Error getting current seasonal content: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/seasonal//albums', methods=['GET']) def get_seasonal_albums(season_key): """Get albums for a specific season""" try: from core.seasonal_discovery import get_seasonal_discovery_service, SEASONAL_CONFIG if season_key not in SEASONAL_CONFIG: return jsonify({"success": False, "error": "Invalid season"}), 400 database = get_database() seasonal_service = get_seasonal_discovery_service(spotify_client, database) active_source = _get_active_discovery_source() albums = seasonal_service.get_seasonal_albums(season_key, limit=40, source=active_source) config = SEASONAL_CONFIG[season_key] return jsonify({ "success": True, "season": season_key, "name": config['name'], "description": config['description'], "icon": config['icon'], "albums": albums }) except Exception as e: logger.error(f"Error getting seasonal albums: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/seasonal//playlist', methods=['GET']) def get_seasonal_playlist(season_key): """Get curated playlist for a specific season""" try: from core.seasonal_discovery import get_seasonal_discovery_service, SEASONAL_CONFIG if season_key not in SEASONAL_CONFIG: return jsonify({"success": False, "error": "Invalid season"}), 400 database = get_database() seasonal_service = get_seasonal_discovery_service(spotify_client, database) # Get curated track IDs for active source active_source = _get_active_discovery_source() track_ids = seasonal_service.get_curated_seasonal_playlist(season_key, source=active_source) if not track_ids: return jsonify({"success": True, "tracks": []}) # Use source-appropriate ID column for lookups track_id_col = 'spotify_track_id' if active_source == 'spotify' else 'itunes_track_id' # Fetch track details from seasonal tracks or discovery pool (filtered by source) tracks = [] with database._get_connection() as conn: cursor = conn.cursor() for track_id in track_ids: # Try seasonal_tracks first (filtered by source) cursor.execute(""" SELECT spotify_track_id, track_name, artist_name, album_name, album_cover_url, duration_ms, popularity, track_data_json FROM seasonal_tracks WHERE spotify_track_id = ? AND source = ? """, (track_id, active_source)) result = cursor.fetchone() if result: track_dict = dict(result) # Parse track_data_json if available if track_dict.get('track_data_json'): try: import json track_dict['track_data_json'] = json.loads(track_dict['track_data_json']) except Exception as e: logger.debug("track_data_json parse: %s", e) tracks.append(track_dict) else: # Try discovery_pool as fallback (filtered by source) cursor.execute(f""" SELECT {track_id_col} as spotify_track_id, track_name, artist_name, album_name, album_cover_url, duration_ms, popularity, track_data_json FROM discovery_pool WHERE {track_id_col} = ? AND source = ? """, (track_id, active_source)) result = cursor.fetchone() if result: track_dict = dict(result) # Parse track_data_json if available if track_dict.get('track_data_json'): try: import json track_dict['track_data_json'] = json.loads(track_dict['track_data_json']) except Exception as e: logger.debug("discovery track_data_json parse: %s", e) tracks.append(track_dict) config = SEASONAL_CONFIG[season_key] return jsonify({ "success": True, "season": season_key, "name": config['name'], "description": config['description'], "icon": config['icon'], "tracks": tracks }) except Exception as e: logger.error(f"Error getting seasonal playlist: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/seasonal/refresh', methods=['POST']) def refresh_seasonal_content(): """Manually trigger seasonal content refresh (admin function)""" try: from core.seasonal_discovery import get_seasonal_discovery_service database = get_database() seasonal_service = get_seasonal_discovery_service(spotify_client, database) # Force populate current season in background thread (bypass 7-day threshold) import threading def populate_all(): try: current_season = seasonal_service.get_current_season() if current_season: logger.info(f"Force-refreshing seasonal content for: {current_season}") seasonal_service.populate_seasonal_content(current_season) seasonal_service.curate_seasonal_playlist(current_season) logger.info(f"Seasonal content refreshed for: {current_season}") else: logger.warning("ℹ️ No active season to refresh") except Exception as e: logger.error(f"Error in background seasonal population: {e}") thread = threading.Thread(target=populate_all, daemon=True) thread.start() return jsonify({"success": True, "message": "Seasonal content refresh started"}) except Exception as e: logger.error(f"Error refreshing seasonal content: {e}") return jsonify({"success": False, "error": str(e)}), 500 # ======================================== # PERSONALIZED PLAYLISTS ENDPOINTS # ======================================== @app.route('/api/discover/personalized/decade/', methods=['GET']) def get_decade_playlist(decade): """Get tracks from a specific decade""" try: from core.personalized_playlists import get_personalized_playlists_service database = get_database() service = get_personalized_playlists_service(database, spotify_client) tracks = service.get_decade_playlist(decade, limit=100) return jsonify({ "success": True, "decade": decade, "tracks": tracks }) except Exception as e: logger.error(f"Error getting decade playlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/personalized/popular-picks', methods=['GET']) def get_popular_picks_playlist(): """Get high popularity tracks from discovery pool""" try: from core.personalized_playlists import get_personalized_playlists_service database = get_database() service = get_personalized_playlists_service(database, spotify_client) tracks = service.get_popular_picks(limit=50) return jsonify({ "success": True, "tracks": tracks }) except Exception as e: logger.error(f"Error getting popular picks playlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/personalized/hidden-gems', methods=['GET']) def get_hidden_gems_playlist(): """Get hidden gems (low popularity) from discovery pool""" try: from core.personalized_playlists import get_personalized_playlists_service database = get_database() service = get_personalized_playlists_service(database, spotify_client) tracks = service.get_hidden_gems(limit=50) return jsonify({ "success": True, "tracks": tracks }) except Exception as e: logger.error(f"Error getting hidden gems playlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/personalized/daily-mixes', methods=['GET']) def get_daily_mixes(): """Get all Daily Mix playlists (hybrid library + discovery)""" try: from core.personalized_playlists import get_personalized_playlists_service database = get_database() service = get_personalized_playlists_service(database, spotify_client) mixes = service.get_all_daily_mixes(max_mixes=4) return jsonify({ "success": True, "mixes": mixes }) except Exception as e: logger.error(f"Error getting daily mixes: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/personalized/discovery-shuffle', methods=['GET']) def get_discovery_shuffle(): """Get Discovery Shuffle playlist - random tracks from discovery pool""" try: from core.personalized_playlists import get_personalized_playlists_service database = get_database() service = get_personalized_playlists_service(database, spotify_client) limit = int(request.args.get('limit', 50)) tracks = service.get_discovery_shuffle(limit=limit) return jsonify({ "success": True, "tracks": tracks }) except Exception as e: logger.error(f"Error getting discovery shuffle playlist: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/artist-blacklist', methods=['GET']) def get_discovery_artist_blacklist(): """Get all blacklisted discovery artists.""" try: database = get_database() entries = database.get_discovery_blacklist() return jsonify({"success": True, "entries": entries}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/artist-blacklist', methods=['POST']) def add_discovery_artist_blacklist(): """Block an artist from appearing in discovery results.""" try: data = request.get_json() or {} artist_name = data.get('artist_name', '').strip() if not artist_name: return jsonify({"success": False, "error": "artist_name is required"}), 400 database = get_database() success = database.add_to_discovery_blacklist( artist_name=artist_name, spotify_id=data.get('spotify_artist_id'), itunes_id=data.get('itunes_artist_id'), deezer_id=data.get('deezer_artist_id'), ) if success: logger.info(f"Blocked artist from discovery: {artist_name}") return jsonify({"success": success}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/artist-blacklist/', methods=['DELETE']) def remove_discovery_artist_blacklist(blacklist_id): """Unblock an artist from discovery.""" try: database = get_database() success = database.remove_from_discovery_blacklist(blacklist_id) return jsonify({"success": success}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 # ── Your Artists (Liked Artists Pool) ── @app.route('/api/discover/your-artists', methods=['GET']) def get_your_artists(): """Get liked artists for the Discover carousel (20 random matched on active source).""" try: database = get_database() profile_id = get_current_profile_id() # Determine active source column — only show artists with THIS source's ID active_source = 'spotify' if spotify_client and spotify_client.is_spotify_authenticated(): active_source = 'spotify' else: fb = _get_metadata_fallback_source() if fb: active_source = fb active_col = {'spotify': 'spotify_artist_id', 'itunes': 'itunes_artist_id', 'deezer': 'deezer_artist_id', 'discogs': 'discogs_artist_id'}.get(active_source, 'spotify_artist_id') # Check if refresh needed (>24h stale or empty) last_fetch = database.get_liked_artists_last_fetch(profile_id) stale = True if last_fetch: from datetime import datetime, timedelta try: if isinstance(last_fetch, str): last_dt = datetime.fromisoformat(last_fetch.replace('Z', '+00:00')) else: last_dt = last_fetch stale = (datetime.now() - last_dt.replace(tzinfo=None)) > timedelta(hours=24) except Exception: stale = True if stale: _trigger_your_artists_refresh(profile_id) database.sync_liked_artists_watchlist_flags(profile_id) # Only return artists matched to the active source result = database.get_liked_artists( profile_id=profile_id, limit=20, random=True, matched_only=True, require_source_id=active_col ) result['stale'] = stale result['success'] = True result['active_source'] = active_source return jsonify(result) except Exception as e: logger.error(f"Error getting your artists: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/your-artists/all', methods=['GET']) def get_your_artists_all(): """Get all liked artists for the View All modal (paginated).""" try: database = get_database() profile_id = get_current_profile_id() page = int(request.args.get('page', 1)) per_page = int(request.args.get('per_page', 50)) search = request.args.get('search', '').strip() source_filter = request.args.get('source', '').strip() sort = request.args.get('sort', 'name') # Same active source filtering as carousel active_source = 'spotify' if spotify_client and spotify_client.is_spotify_authenticated(): active_source = 'spotify' else: fb = _get_metadata_fallback_source() if fb: active_source = fb active_col = {'spotify': 'spotify_artist_id', 'itunes': 'itunes_artist_id', 'deezer': 'deezer_artist_id', 'discogs': 'discogs_artist_id'}.get(active_source, 'spotify_artist_id') database.sync_liked_artists_watchlist_flags(profile_id) result = database.get_liked_artists( profile_id=profile_id, matched_only=True, page=page, per_page=per_page, search=search, source_filter=source_filter or None, sort=sort, require_source_id=active_col ) result['success'] = True result['active_source'] = active_source return jsonify(result) except Exception as e: logger.error(f"Error getting all your artists: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/your-artists/refresh', methods=['POST']) def refresh_your_artists(): """Force-trigger a fetch + match cycle for liked artists. ?clear=true wipes pool first.""" try: profile_id = get_current_profile_id() if request.args.get('clear', '').lower() == 'true': database = get_database() cleared = database.clear_liked_artists(profile_id) logger.info(f"[Your Artists] Cleared {cleared} entries before refresh") _trigger_your_artists_refresh(profile_id) return jsonify({"success": True, "message": "Refresh started"}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/your-artists/sources', methods=['GET']) def get_your_artists_sources(): """Return current source config + which services are connected.""" try: enabled_raw = config_manager.get('discover.your_artists_sources', 'spotify,tidal,lastfm,deezer') enabled = [s.strip() for s in enabled_raw.split(',') if s.strip()] connected = [] # Spotify if spotify_client and spotify_client.is_spotify_authenticated(): connected.append('spotify') # Tidal try: if tidal_client and hasattr(tidal_client, '_ensure_valid_token') and tidal_client._ensure_valid_token(): connected.append('tidal') except Exception as e: logger.debug("tidal auth check failed: %s", e) # Last.fm if config_manager.get('lastfm.api_key', '') and config_manager.get('lastfm.session_key', ''): connected.append('lastfm') # Deezer — OAuth token OR ARL token both count as connected try: deezer_cl = _get_deezer_client() deezer_oauth = deezer_cl and hasattr(deezer_cl, 'is_user_authenticated') and deezer_cl.is_user_authenticated() deezer_arl = (hasattr(download_orchestrator, 'client') and download_orchestrator.client("deezer_dl") and download_orchestrator.client("deezer_dl").is_authenticated()) if deezer_oauth or deezer_arl: connected.append('deezer') except Exception as e: logger.debug("deezer auth check failed: %s", e) return jsonify({"success": True, "enabled": enabled, "connected": connected}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 _your_artists_refresh_lock = threading.Lock() _your_artists_refreshing = False def _trigger_your_artists_refresh(profile_id: int): """Start background fetch + match if not already running.""" global _your_artists_refreshing if _your_artists_refreshing: return with _your_artists_refresh_lock: if _your_artists_refreshing: return _your_artists_refreshing = True def _run(): global _your_artists_refreshing try: _fetch_and_match_liked_artists(profile_id) except Exception as e: logger.error(f"Your artists refresh failed: {e}") import traceback traceback.print_exc() finally: _your_artists_refreshing = False threading.Thread(target=_run, daemon=True, name="YourArtistsRefresh").start() def _fetch_and_match_liked_artists(profile_id: int): """Background worker: fetch from services, deduplicate, match to active source.""" database = get_database() fetched = 0 enabled_raw = config_manager.get('discover.your_artists_sources', 'spotify,tidal,lastfm,deezer') enabled_sources = {s.strip() for s in enabled_raw.split(',') if s.strip()} # 1. Fetch from Spotify (followed artists) try: if 'spotify' not in enabled_sources: logger.warning("[Your Artists] Spotify skipped (disabled in sources config)") elif spotify_client and spotify_client.is_spotify_authenticated(): logger.info("[Your Artists] Fetching followed artists from Spotify...") artists = spotify_client.get_followed_artists() for a in artists: database.upsert_liked_artist( artist_name=a['name'], source_service='spotify', source_id=a['spotify_id'], source_id_type='spotify', image_url=a.get('image_url'), genres=a.get('genres'), profile_id=profile_id ) fetched += len(artists) logger.info(f"[Your Artists] Fetched {len(artists)} from Spotify") except Exception as e: logger.error(f"[Your Artists] Spotify fetch error: {e}") # 2. Fetch from Tidal (favorite artists) try: if 'tidal' not in enabled_sources: logger.warning("[Your Artists] Tidal skipped (disabled in sources config)") elif tidal_client and hasattr(tidal_client, 'get_favorite_artists'): tidal_auth = tidal_client._ensure_valid_token() if hasattr(tidal_client, '_ensure_valid_token') else False if tidal_auth: logger.info("[Your Artists] Fetching favorite artists from Tidal...") artists = tidal_client.get_favorite_artists(limit=200) for a in artists: database.upsert_liked_artist( artist_name=a['name'], source_service='tidal', image_url=a.get('image_url'), profile_id=profile_id ) fetched += len(artists) logger.info(f"[Your Artists] Fetched {len(artists)} from Tidal") except Exception as e: logger.error(f"[Your Artists] Tidal fetch error: {e}") # 3. Fetch from Last.fm (top artists) try: if 'lastfm' not in enabled_sources: logger.warning("[Your Artists] Last.fm skipped (disabled in sources config)") else: lastfm_key = config_manager.get('lastfm.api_key', '') lastfm_secret = config_manager.get('lastfm.api_secret', '') lastfm_session = config_manager.get('lastfm.session_key', '') logger.info(f"[Your Artists] Last.fm credentials: key={'yes' if lastfm_key else 'NO'}, secret={'yes' if lastfm_secret else 'NO'}, session={'yes' if lastfm_session else 'NO'}") if lastfm_key and lastfm_secret and lastfm_session: from core.lastfm_client import LastFMClient lfm = LastFMClient(api_key=lastfm_key, api_secret=lastfm_secret, session_key=lastfm_session) username = lfm.get_authenticated_username() logger.info(f"[Your Artists] Last.fm username resolved: {username or 'NONE'}") if username: logger.info(f"[Your Artists] Fetching top artists from Last.fm ({username})...") artists = lfm.get_user_top_artists(username, period='overall', limit=200) for a in artists: database.upsert_liked_artist( artist_name=a['name'], source_service='lastfm', image_url=a.get('image_url'), profile_id=profile_id ) fetched += len(artists) logger.info(f"[Your Artists] Fetched {len(artists)} from Last.fm") except Exception as e: logger.error(f"[Your Artists] Last.fm fetch error: {e}") # 4. Fetch from Deezer (favorite artists — OAuth or ARL) try: if 'deezer' not in enabled_sources: logger.warning("[Your Artists] Deezer skipped (disabled in sources config)") else: deezer_cl = _get_deezer_client() artists = [] if deezer_cl and hasattr(deezer_cl, 'is_user_authenticated') and deezer_cl.is_user_authenticated(): logger.info("[Your Artists] Fetching favorite artists from Deezer (OAuth)...") artists = deezer_cl.get_user_favorite_artists(limit=200) elif (hasattr(download_orchestrator, 'client') and download_orchestrator.client("deezer_dl") and download_orchestrator.client("deezer_dl").is_authenticated()): logger.info("[Your Artists] Fetching favorite artists from Deezer (ARL)...") artists = download_orchestrator.client("deezer_dl").get_user_favorite_artists(limit=200) for a in artists: database.upsert_liked_artist( artist_name=a['name'], source_service='deezer', source_id=a.get('deezer_id'), source_id_type='deezer', image_url=a.get('image_url'), profile_id=profile_id ) fetched += len(artists) if artists: logger.info(f"[Your Artists] Fetched {len(artists)} from Deezer") except Exception as e: logger.error(f"[Your Artists] Deezer fetch error: {e}") logger.info(f"[Your Artists] Total fetched: {fetched}") # 5. Match pending artists to active source _match_liked_artists_to_all_sources(database, profile_id) from core.artists.liked_match import ( _backfill_liked_artist_images, _match_liked_artists_to_all_sources, ) # ── Your Albums (Liked Albums Pool) ── @app.route('/api/discover/your-albums', methods=['GET']) def get_your_albums(): """Get liked albums with library ownership status, paginated.""" try: database = get_database() profile_id = get_current_profile_id() page = request.args.get('page', 1, type=int) per_page = request.args.get('per_page', 48, type=int) search = request.args.get('search', '', type=str).strip() status_filter = request.args.get('status', 'all', type=str) source_filter = request.args.get('source', '', type=str).strip() sort = request.args.get('sort', 'artist_name', type=str) # Auto-trigger refresh if stale (>24h or empty) last_fetch = database.get_liked_albums_last_fetch(profile_id) stale = True if last_fetch: from datetime import datetime, timedelta try: if isinstance(last_fetch, str): last_dt = datetime.fromisoformat(last_fetch.replace('Z', '+00:00')) else: last_dt = last_fetch stale = (datetime.now() - last_dt.replace(tzinfo=None)) > timedelta(hours=24) except Exception: stale = True if stale: _trigger_your_albums_refresh(profile_id) # Fetch all (ownership check requires full set) all_result = database.get_liked_albums( profile_id=profile_id, page=1, per_page=100000, search=search, source_filter=source_filter or None, sort=sort ) all_albums = all_result['albums'] if not all_albums: return jsonify({ "success": True, "albums": [], "total": 0, "page": page, "per_page": per_page, "stale": stale, "stats": {"total": 0, "owned": 0, "missing": 0} }) # Ownership check — same strategy as Spotify library endpoint library_spotify_ids = database.get_library_spotify_album_ids(profile_id) library_album_names = database.get_library_album_names() owned_count = 0 for album in all_albums: if album.get('spotify_album_id') and album['spotify_album_id'] in library_spotify_ids: album['in_library'] = True elif (album['artist_name'].lower(), album['album_name'].lower()) in library_album_names: album['in_library'] = True else: album['in_library'] = False if album['in_library']: owned_count += 1 # Apply status filter if status_filter == 'missing': filtered = [a for a in all_albums if not a['in_library']] elif status_filter == 'owned': filtered = [a for a in all_albums if a['in_library']] else: filtered = all_albums filtered_total = len(filtered) offset = (page - 1) * per_page albums = filtered[offset:offset + per_page] stats = { 'total': all_result['total'], 'owned': owned_count, 'missing': all_result['total'] - owned_count, } return jsonify({ "success": True, "albums": albums, "total": filtered_total, "page": page, "per_page": per_page, "stale": stale, "stats": stats, }) except Exception as e: logger.error(f"Error getting your albums: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/your-albums/refresh', methods=['POST']) def refresh_your_albums(): """Force-trigger a fetch cycle for liked albums. ?clear=true wipes pool first.""" try: profile_id = get_current_profile_id() if request.args.get('clear', '').lower() == 'true': database = get_database() cleared = database.clear_liked_albums(profile_id) logger.info(f"[Your Albums] Cleared {cleared} entries before refresh") _trigger_your_albums_refresh(profile_id) return jsonify({"success": True, "message": "Refresh started"}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/your-albums/sources', methods=['GET']) def get_your_albums_sources(): """Return current source config + which services are connected (albums).""" try: enabled_raw = config_manager.get('discover.your_albums_sources', 'spotify,tidal,deezer') enabled = [s.strip() for s in enabled_raw.split(',') if s.strip()] connected = [] if spotify_client and spotify_client.is_spotify_authenticated(): connected.append('spotify') try: if tidal_client and hasattr(tidal_client, '_ensure_valid_token') and tidal_client._ensure_valid_token(): connected.append('tidal') except Exception as e: logger.debug("tidal auth check failed: %s", e) try: deezer_cl = _get_deezer_client() deezer_oauth = deezer_cl and hasattr(deezer_cl, 'is_user_authenticated') and deezer_cl.is_user_authenticated() deezer_arl = (hasattr(download_orchestrator, 'client') and download_orchestrator.client("deezer_dl") and download_orchestrator.client("deezer_dl").is_authenticated()) if deezer_oauth or deezer_arl: connected.append('deezer') except Exception as e: logger.debug("deezer auth check failed: %s", e) # Discogs: counts as "connected" when a personal access token is # configured. Username comes from /oauth/identity at fetch time; # not required up front. try: if config_manager.get('discogs.token', ''): connected.append('discogs') except Exception as e: logger.debug("discogs token check failed: %s", e) return jsonify({"success": True, "enabled": enabled, "connected": connected}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 _your_albums_refresh_lock = threading.Lock() _your_albums_refreshing = False def _trigger_your_albums_refresh(profile_id: int): """Start background album fetch if not already running.""" global _your_albums_refreshing if _your_albums_refreshing: return with _your_albums_refresh_lock: if _your_albums_refreshing: return _your_albums_refreshing = True def _run(): global _your_albums_refreshing try: _fetch_liked_albums(profile_id) except Exception as e: logger.error(f"Your albums refresh failed: {e}") import traceback traceback.print_exc() finally: _your_albums_refreshing = False threading.Thread(target=_run, daemon=True, name="YourAlbumsRefresh").start() def _fetch_liked_albums(profile_id: int): """Background worker: fetch liked/saved albums from all connected services.""" database = get_database() fetched = 0 enabled_raw = config_manager.get('discover.your_albums_sources', 'spotify,tidal,deezer') enabled_sources = {s.strip() for s in enabled_raw.split(',') if s.strip()} # 1. Fetch from Spotify (saved albums) try: if 'spotify' not in enabled_sources: logger.warning("[Your Albums] Spotify skipped (disabled in sources config)") elif spotify_client and spotify_client.is_spotify_authenticated(): logger.info("[Your Albums] Fetching saved albums from Spotify...") albums = spotify_client.get_saved_albums() for a in albums: database.upsert_liked_album( album_name=a['album_name'], artist_name=a['artist_name'], source_service='spotify', source_id=a['spotify_album_id'], source_id_type='spotify', image_url=a.get('image_url'), release_date=a.get('release_date'), total_tracks=a.get('total_tracks', 0), profile_id=profile_id ) fetched += len(albums) logger.info(f"[Your Albums] Fetched {len(albums)} from Spotify") except Exception as e: logger.error(f"[Your Albums] Spotify fetch error: {e}") # 2. Fetch from Tidal (favorite albums) try: if 'tidal' not in enabled_sources: logger.warning("[Your Albums] Tidal skipped (disabled in sources config)") elif tidal_client and hasattr(tidal_client, 'get_favorite_albums'): tidal_auth = tidal_client._ensure_valid_token() if hasattr(tidal_client, '_ensure_valid_token') else False if tidal_auth: logger.info("[Your Albums] Fetching favorite albums from Tidal...") albums = tidal_client.get_favorite_albums(limit=500) for a in albums: database.upsert_liked_album( album_name=a['album_name'], artist_name=a['artist_name'], source_service='tidal', source_id=a.get('tidal_id'), source_id_type='tidal', image_url=a.get('image_url'), release_date=a.get('release_date'), total_tracks=a.get('total_tracks', 0), profile_id=profile_id ) fetched += len(albums) logger.info(f"[Your Albums] Fetched {len(albums)} from Tidal") except Exception as e: logger.error(f"[Your Albums] Tidal fetch error: {e}") # 3. Fetch from Deezer (favorite albums — OAuth or ARL) try: if 'deezer' not in enabled_sources: logger.warning("[Your Albums] Deezer skipped (disabled in sources config)") else: deezer_cl = _get_deezer_client() albums = [] if deezer_cl and hasattr(deezer_cl, 'is_user_authenticated') and deezer_cl.is_user_authenticated(): logger.info("[Your Albums] Fetching favorite albums from Deezer (OAuth)...") albums = deezer_cl.get_user_favorite_albums(limit=500) elif (hasattr(download_orchestrator, 'client') and download_orchestrator.client("deezer_dl") and download_orchestrator.client("deezer_dl").is_authenticated()): logger.info("[Your Albums] Fetching favorite albums from Deezer (ARL)...") albums = download_orchestrator.client("deezer_dl").get_user_favorite_albums(limit=500) for a in albums: database.upsert_liked_album( album_name=a['album_name'], artist_name=a['artist_name'], source_service='deezer', source_id=a.get('deezer_id'), source_id_type='deezer', image_url=a.get('image_url'), release_date=a.get('release_date'), total_tracks=a.get('total_tracks', 0), profile_id=profile_id ) fetched += len(albums) if albums: logger.info(f"[Your Albums] Fetched {len(albums)} from Deezer") except Exception as e: logger.error(f"[Your Albums] Deezer fetch error: {e}") # 4. Fetch from Discogs (user's collection) — uses personal access # token from `discogs.token` config. Username resolved via the # `/oauth/identity` endpoint at fetch time. Discogs is physical- # media-first so many releases won't have streaming equivalents, # but the click-context dispatch in the frontend opens the Discogs # release detail and the user can manually trigger a download # search if a digital match exists. try: if 'discogs' not in enabled_sources: logger.warning("[Your Albums] Discogs skipped (disabled in sources config)") elif not config_manager.get('discogs.token', ''): logger.info("[Your Albums] Discogs skipped (no token configured)") else: from core.discogs_client import DiscogsClient discogs_cl = DiscogsClient() if discogs_cl.is_authenticated(): logger.info("[Your Albums] Fetching collection from Discogs...") releases = discogs_cl.get_user_collection() for r in releases: database.upsert_liked_album( album_name=r['album_name'], artist_name=r['artist_name'], source_service='discogs', source_id=str(r['release_id']), source_id_type='discogs', image_url=r.get('image_url'), release_date=r.get('release_date', ''), total_tracks=r.get('total_tracks', 0), profile_id=profile_id ) fetched += len(releases) if releases: logger.info(f"[Your Albums] Fetched {len(releases)} from Discogs") except Exception as e: logger.error(f"[Your Albums] Discogs fetch error: {e}") logger.info(f"[Your Albums] Total fetched: {fetched}") @app.route('/api/discover/your-artists/info/', methods=['GET']) def get_your_artist_info(artist_id): """Get artist info for the Your Artists info modal. Checks library, cache, then API.""" try: artist_name = request.args.get('name', '') result = {'name': artist_name, 'success': True} # 1. Try library DB (has enrichment data) try: database = get_database() conn = database._get_connection() cursor = conn.cursor() # Check by various ID columns cursor.execute(""" SELECT * FROM artists WHERE id = ? OR spotify_artist_id = ? OR itunes_artist_id = ? OR deezer_id = ? OR discogs_id = ? LIMIT 1 """, (artist_id, artist_id, artist_id, artist_id, artist_id)) row = cursor.fetchone() if row: r = dict(row) result.update({ 'name': r.get('name', artist_name), 'genres': json.loads(r['genres']) if r.get('genres') else [], 'summary': r.get('summary', ''), 'image_url': r.get('thumb_url', ''), 'spotify_artist_id': r.get('spotify_artist_id'), 'musicbrainz_id': r.get('musicbrainz_id'), 'deezer_id': r.get('deezer_id'), 'itunes_artist_id': r.get('itunes_artist_id'), 'discogs_id': r.get('discogs_id'), 'lastfm_url': r.get('lastfm_url'), 'tidal_id': r.get('tidal_id'), 'lastfm_listeners': r.get('lastfm_listeners', 0), 'lastfm_playcount': r.get('lastfm_playcount', 0), }) return jsonify(result) except Exception as e: logger.debug("library artist lookup failed: %s", e) # 2. Try metadata cache try: conn = database._get_connection() cursor = conn.cursor() cursor.execute(""" SELECT raw_json, image_url FROM metadata_cache_entities WHERE entity_type = 'artist' AND entity_id = ? LIMIT 1 """, (artist_id,)) row = cursor.fetchone() if row and row['raw_json']: cached = json.loads(row['raw_json']) result.update({ 'name': cached.get('name', artist_name), 'genres': cached.get('genres', []), 'image_url': row['image_url'] or cached.get('image_url', ''), 'popularity': cached.get('popularity', 0), 'followers': cached.get('followers', {}).get('total', 0) if isinstance(cached.get('followers'), dict) else cached.get('followers', 0), }) return jsonify(result) except Exception as e: logger.debug("metadata cache lookup failed: %s", e) # 3. Try Spotify API directly (genres, image, followers) try: if spotify_client and spotify_client.is_spotify_authenticated() and not artist_id.isdigit(): from core.api_call_tracker import api_call_tracker api_call_tracker.record_call('spotify', endpoint='artist') artist_data = spotify_client.sp.artist(artist_id) if artist_data: result.update({ 'name': artist_data.get('name', artist_name), 'genres': artist_data.get('genres', []), 'image_url': artist_data['images'][0]['url'] if artist_data.get('images') else '', 'spotify_artist_id': artist_data.get('id'), 'popularity': artist_data.get('popularity', 0), 'followers': artist_data.get('followers', {}).get('total', 0), }) except Exception as e: logger.debug(f"Spotify artist lookup failed for {artist_id}: {e}") # 4. Last.fm: bio, listeners, playcount (skip if name is too short/generic) try: _lfm_name = result.get('name') or artist_name if _lfm_name and len(_lfm_name) > 1 and lastfm_worker and lastfm_worker.client: lfm_info = lastfm_worker.client.get_artist_info(_lfm_name) if lfm_info: bio = lfm_info.get('bio', {}) if isinstance(bio, dict): summary = bio.get('summary', '') else: summary = str(bio) if bio else '' if summary and not result.get('summary'): result['summary'] = summary stats = lfm_info.get('stats', {}) if stats: result['lastfm_listeners'] = int(stats.get('listeners', 0)) result['lastfm_playcount'] = int(stats.get('playcount', 0)) if not result.get('genres'): tags = lfm_info.get('tags', {}).get('tag', []) if tags: result['genres'] = [t.get('name', '') for t in tags[:5] if isinstance(t, dict)] lfm_url = lfm_info.get('url') if lfm_url: result['lastfm_url'] = lfm_url except Exception as e: logger.debug(f"Last.fm artist info failed for {artist_name}: {e}") # 5. Return combined info return jsonify(result) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/image-proxy', methods=['GET']) def image_proxy(): """Proxy external images to avoid CORS issues for canvas rendering.""" url = request.args.get('url', '') if not url or not url.startswith('http'): return '', 400 host = urlparse(url).hostname or '' allowed_hosts = [ 'i.scdn.co', 'mosaic.scdn.co', # Spotify 'lastfm.freetls.fastly.net', 'lastfm-img2.akamaized.net', # Last.fm 'e-cdns-images.dzcdn.net', 'cdns-images.dzcdn.net', 'api.deezer.com', # Deezer 'is1-ssl.mzstatic.com', 'is2-ssl.mzstatic.com', 'is3-ssl.mzstatic.com', 'is4-ssl.mzstatic.com', 'is5-ssl.mzstatic.com', # iTunes/Apple 'img.discogs.com', 'i.discogs.com', # Discogs 'localhost', '127.0.0.1', 'host.docker.internal', # Local/Docker media servers ] if not any(host == h or host.endswith('.' + h) for h in allowed_hosts) and not is_internal_image_host(url): return '', 403 try: resp = requests.get(url, timeout=10, stream=True, headers={ 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36', 'Referer': 'https://www.deezer.com/', }) if resp.status_code != 200: return '', resp.status_code content_type = resp.headers.get('Content-Type', 'image/jpeg') if not content_type.startswith('image/'): return '', 400 return Response( resp.content, content_type=content_type, headers={ 'Cache-Control': 'public, max-age=86400', 'Access-Control-Allow-Origin': '*', } ) except Exception: return '', 502 from core.artists.map import ( _artmap_cache_invalidate, _artmap_cache_get, _artmap_cache_set, get_artist_map_data as _artists_map_get_artist_map_data, get_artist_map_genre_list as _artists_map_get_artist_map_genre_list, get_artist_map_genres as _artists_map_get_artist_map_genres, get_artist_map_explore as _artists_map_get_artist_map_explore, ) @app.route('/api/discover/artist-map', methods=['GET']) def get_artist_map_data(): return _artists_map_get_artist_map_data() @app.route('/api/discover/artist-map/genre-list', methods=['GET']) def get_artist_map_genre_list(): return _artists_map_get_artist_map_genre_list() @app.route('/api/discover/artist-map/genres', methods=['GET']) def get_artist_map_genres(): return _artists_map_get_artist_map_genres() @app.route('/api/discover/artist-map/explore', methods=['GET']) def get_artist_map_explore(): return _artists_map_get_artist_map_explore() @app.route('/api/discover/build-playlist/search-artists', methods=['GET']) def search_artists_for_playlist(): """Search for artists to use as seeds for custom playlist building""" try: query = request.args.get('query', '').strip() if not query: return jsonify({"success": False, "error": "Query required"}), 400 artists = [] if _is_hydrabase_active(): artist_objs = hydrabase_client.search_artists(query, limit=10) for artist in artist_objs: artists.append({ 'id': artist.id, 'name': artist.name, 'image_url': artist.image_url }) else: if hydrabase_worker and dev_mode_enabled: hydrabase_worker.enqueue(query, 'artists') # Try Spotify first, fall back to iTunes if spotify_client.sp and not _spotify_rate_limited(): try: artist_results = spotify_client.search_artists(query, limit=10) for artist in artist_results: artists.append({ 'id': artist.id, 'name': artist.name, 'image_url': artist.image_url }) except Exception as e: logger.warning(f"Spotify artist search failed, falling back to iTunes: {e}") if not artists: fallback = _get_metadata_fallback_client() artist_objs = fallback.search_artists(query, limit=10) for artist in artist_objs: # Fallback artist search may not return images — grab from album art image = artist.image_url if not image: image = fallback._get_artist_image_from_albums(artist.id) artists.append({ 'id': artist.id, 'name': artist.name, 'image_url': image }) if artists: # Re-rank: boost exact name matches to the top query_lower = query.lower().strip() artists.sort(key=lambda a: (0 if a['name'].lower().strip() == query_lower else 1)) return jsonify({ "success": True, "artists": artists }) except Exception as e: logger.error(f"Error searching for artists: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/build-playlist/generate', methods=['POST']) def generate_custom_playlist(): """Generate custom playlist from seed artists""" try: from core.personalized_playlists import get_personalized_playlists_service data = request.get_json() seed_artist_ids = data.get('seed_artist_ids', []) if not seed_artist_ids or len(seed_artist_ids) < 1 or len(seed_artist_ids) > 5: return jsonify({ "success": False, "error": "Please provide between 1 and 5 seed artists" }), 400 database = get_database() service = get_personalized_playlists_service(database, spotify_client) playlist_size = int(data.get('playlist_size', 50)) result = service.build_custom_playlist(seed_artist_ids, playlist_size=playlist_size) if result.get('error') and not result.get('tracks'): return jsonify({"success": False, "error": result['error']}), 400 return jsonify({ "success": True, "playlist": result }) except Exception as e: logger.error(f"Error generating custom playlist: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/decades/available', methods=['GET']) def get_available_decades(): """Get list of decades that have content in discovery pool""" try: database = get_database() with database._get_connection() as conn: cursor = conn.cursor() # Get distinct decades from discovery pool cursor.execute(""" SELECT DISTINCT (CAST(SUBSTR(release_date, 1, 4) AS INTEGER) / 10) * 10 as decade, COUNT(*) as track_count FROM discovery_pool WHERE release_date IS NOT NULL AND CAST(SUBSTR(release_date, 1, 4) AS INTEGER) >= 1950 AND CAST(SUBSTR(release_date, 1, 4) AS INTEGER) <= 2029 GROUP BY decade HAVING track_count >= 10 ORDER BY decade ASC """) rows = cursor.fetchall() decades = [] for row in rows: decades.append({ 'year': row[0], 'track_count': row[1] }) return jsonify({ "success": True, "decades": decades }) except Exception as e: logger.error(f"Error getting available decades: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/decade/', methods=['GET']) def get_discover_decade_playlist(decade): """Get tracks from a specific decade for discovery page""" try: from core.personalized_playlists import get_personalized_playlists_service database = get_database() service = get_personalized_playlists_service(database, spotify_client) tracks = service.get_decade_playlist(decade, limit=50) if not tracks: return jsonify({ "success": True, "tracks": [], "decade": decade, "message": f"No tracks found for the {decade}s" }), 200 # Convert to Spotify format for modal compatibility spotify_tracks = [] for track in tracks: spotify_tracks.append({ 'id': track.get('spotify_track_id', track.get('id')), 'name': track.get('track_name', track.get('name')), 'artists': [track.get('artist_name', 'Unknown')], 'album': { 'name': track.get('album_name', 'Unknown'), 'images': [{'url': track.get('album_cover_url')}] if track.get('album_cover_url') else [] }, 'duration_ms': track.get('duration_ms', 0) }) return jsonify({ "success": True, "tracks": spotify_tracks, "decade": decade }) except Exception as e: logger.error(f"Error getting decade playlist: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/genres/available', methods=['GET']) def get_available_genres(): """Get list of genres that have content in discovery pool""" try: from core.personalized_playlists import get_personalized_playlists_service database = get_database() service = get_personalized_playlists_service(database, spotify_client) genres = service.get_available_genres() return jsonify({ "success": True, "genres": genres }) except Exception as e: logger.error(f"Error getting available genres: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/genre/', methods=['GET']) def get_discover_genre_playlist(genre_name): """Get tracks from a specific genre for discovery page""" try: from core.personalized_playlists import get_personalized_playlists_service database = get_database() service = get_personalized_playlists_service(database, spotify_client) tracks = service.get_genre_playlist(genre_name, limit=50) if not tracks: return jsonify({ "success": True, "tracks": [], "genre": genre_name, "message": f"No tracks found for {genre_name}" }), 200 # Convert to Spotify format for modal compatibility spotify_tracks = [] for track in tracks: spotify_tracks.append({ 'id': track.get('spotify_track_id', track.get('id')), 'name': track.get('track_name', track.get('name')), 'artists': [track.get('artist_name', 'Unknown')], 'album': { 'name': track.get('album_name', 'Unknown'), 'images': [{'url': track.get('album_cover_url')}] if track.get('album_cover_url') else [] }, 'duration_ms': track.get('duration_ms', 0) }) return jsonify({ "success": True, "tracks": spotify_tracks, "genre": genre_name }) except Exception as e: logger.error(f"Error getting genre playlist: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 # =============================== # LISTENBRAINZ DISCOVER ENDPOINTS # =============================== def _get_profile_lb_manager(): """Create a profile-aware ListenBrainzManager for the current user. Always uses the actual profile_id so each profile has its own playlist cache.""" from core.listenbrainz_manager import ListenBrainzManager profile_id = get_current_profile_id() token, base_url, username, source = _get_lb_credentials_for_profile(profile_id) return ListenBrainzManager(str(get_database().database_path), profile_id=profile_id, token=token, base_url=base_url), username, source def _get_lb_discover_playlists(playlist_type): """Shared logic for the 3 LB discover endpoints""" lb_manager, username, source = _get_profile_lb_manager() # Check if cache is empty - if so, populate it on first load if not lb_manager.has_cached_playlists(): if not lb_manager.client.is_authenticated(): return jsonify({ "success": False, "error": "Not authenticated", "playlists": [], "count": 0, "username": None }) logger.warning(f"Cache empty for profile {lb_manager.profile_id}, populating ListenBrainz playlists...") lb_manager.update_all_playlists() playlists = lb_manager.get_cached_playlists(playlist_type) formatted_playlists = [] for playlist in playlists: formatted_playlists.append({ "playlist": { "identifier": f"https://listenbrainz.org/playlist/{playlist['playlist_mbid']}", "title": playlist['title'], "creator": playlist['creator'], "annotation": playlist.get('annotation', {}), "track": [] } }) return jsonify({ "success": True, "playlists": formatted_playlists, "count": len(formatted_playlists), "username": username, "source": source }) @app.route('/api/discover/listenbrainz/created-for', methods=['GET']) def get_listenbrainz_created_for(): """Get playlists created for the user by ListenBrainz (from cache)""" try: return _get_lb_discover_playlists('created_for') except Exception as e: logger.error(f"Error getting cached ListenBrainz created-for playlists: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/listenbrainz/user-playlists', methods=['GET']) def get_listenbrainz_user_playlists(): """Get user's own ListenBrainz playlists (from cache)""" try: return _get_lb_discover_playlists('user') except Exception as e: logger.error(f"Error getting cached ListenBrainz user playlists: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/listenbrainz/collaborative', methods=['GET']) def get_listenbrainz_collaborative(): """Get collaborative ListenBrainz playlists (from cache)""" try: return _get_lb_discover_playlists('collaborative') except Exception as e: logger.error(f"Error getting cached ListenBrainz collaborative playlists: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/listenbrainz/playlist/', methods=['GET']) def get_listenbrainz_playlist_tracks(playlist_mbid): """Get tracks from a specific ListenBrainz playlist (from cache, with on-demand refresh)""" try: lb_manager, username, source = _get_profile_lb_manager() tracks = lb_manager.get_cached_tracks(playlist_mbid) if not tracks: # Cache miss or stale entry with no tracks — try fetching from LB API if lb_manager.client.is_authenticated(): logger.debug(f"Cache miss for playlist {playlist_mbid}, fetching from ListenBrainz...") # Remove stale playlist row (if any) so _update_playlist doesn't # skip due to matching track_count with 0 actual tracks existing_type = lb_manager.get_playlist_type(playlist_mbid) or 'created_for' lb_manager.delete_cached_playlist(playlist_mbid) full_playlist = lb_manager.client.get_playlist_details(playlist_mbid) if full_playlist: lb_manager._update_playlist(full_playlist, existing_type) tracks = lb_manager.get_cached_tracks(playlist_mbid) if not tracks: return jsonify({ "success": False, "error": "Playlist not found in cache" }), 404 return jsonify({ "success": True, "tracks": tracks, "track_count": len(tracks) }) except Exception as e: logger.error(f"Error getting cached ListenBrainz playlist tracks: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 # Manual refresh endpoint for ListenBrainz @app.route('/api/discover/listenbrainz/refresh', methods=['POST']) def refresh_listenbrainz(): """Manually refresh ListenBrainz playlists cache""" try: lb_manager, username, source = _get_profile_lb_manager() result = lb_manager.update_all_playlists() return jsonify(result) except Exception as e: logger.error(f"Error refreshing ListenBrainz: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 # ======================================== # LAST.FM TRACK RADIO # ======================================== @app.route('/api/lastfm/configured', methods=['GET']) def lastfm_configured(): """Return whether a Last.fm API key is configured (used to gate the Radio section).""" lf = lastfm_worker.client if lastfm_worker else None return jsonify({"configured": bool(lf and lf.api_key)}) @app.route('/api/lastfm/search/tracks', methods=['GET']) def lastfm_search_tracks(): """Search Last.fm for tracks matching a query string. Query params: q: search query (track name, artist name, or both) Returns: JSON list of {name, artist, mbid, listeners} """ try: q = request.args.get('q', '').strip() if not q or len(q) < 2: return jsonify({"success": False, "error": "Query too short", "results": []}), 400 lf = lastfm_worker.client if lastfm_worker else None if not lf or not lf.api_key: return jsonify({"success": False, "error": "Last.fm not configured", "results": []}), 400 # Use raw API call to get multiple results (search_track only returns best match) data = lf._make_request('track.search', {'track': q, 'limit': 8}) if not data: return jsonify({"success": True, "results": []}) raw = data.get('results', {}).get('trackmatches', {}).get('track', []) if not isinstance(raw, list): raw = [raw] if raw else [] results = [] for t in raw: # Last.fm image array: [{#text: url, size: small/medium/large/extralarge}] image_url = lf.get_best_image(t.get('image', [])) results.append({ 'name': t.get('name', ''), 'artist': t.get('artist', ''), 'mbid': t.get('mbid', ''), 'listeners': int(t.get('listeners', 0)), 'image_url': image_url or '', }) return jsonify({"success": True, "results": results}) except Exception as e: logger.error(f"Error searching Last.fm tracks: {e}") return jsonify({"success": False, "error": str(e), "results": []}), 500 @app.route('/api/lastfm/radio/generate', methods=['POST']) def lastfm_radio_generate(): """Generate a Last.fm Radio playlist from a seed track. Body JSON: track_name: seed track title artist_name: seed artist name Creates/updates a 'lastfm_radio' playlist in the DB and adds it to listenbrainz_playlist_states in 'fresh' phase, ready for discovery. Returns: {success, playlist_mbid, title, track_count} """ try: data = request.get_json() or {} track_name = (data.get('track_name') or '').strip() artist_name = (data.get('artist_name') or '').strip() if not track_name or not artist_name: return jsonify({"success": False, "error": "track_name and artist_name are required"}), 400 lf = lastfm_worker.client if lastfm_worker else None if not lf or not lf.api_key: return jsonify({"success": False, "error": "Last.fm not configured"}), 400 # Fetch similar tracks from Last.fm similar = lf.get_similar_tracks(artist_name, track_name, limit=25) if not similar: return jsonify({"success": False, "error": "No similar tracks found on Last.fm"}), 404 # Persist to DB via manager lb_manager, _username, _source = _get_profile_lb_manager() playlist_mbid = lb_manager.save_lastfm_radio_playlist(track_name, artist_name, similar) title = f"Last.fm Radio: {track_name} by {artist_name}" # Build playlist dict that mirrors the LB playlist format expected by the discovery pipeline playlist_data = { 'identifier': f"lastfm_radio/{playlist_mbid}", 'name': title, 'title': title, 'creator': 'Last.fm', 'tracks': [ { 'track_name': t['name'], 'artist_name': t['artist'], 'album_name': '', 'duration_ms': 0, } for t in similar ], } # Upsert into in-memory state (fresh phase — not yet discovered) state_key = _lb_state_key(playlist_mbid) if state_key not in listenbrainz_playlist_states: listenbrainz_playlist_states[state_key] = { 'playlist_mbid': playlist_mbid, 'playlist': playlist_data, 'phase': 'fresh', 'status': 'fresh', 'discovery_progress': 0, 'spotify_matches': 0, 'spotify_total': len(similar), 'discovery_results': [], 'created_at': time.time(), 'last_accessed': time.time(), } else: # Refresh existing state (new seed data) but preserve phase if already discovered state = listenbrainz_playlist_states[state_key] if state['phase'] not in ('discovering',): state['playlist'] = playlist_data state['spotify_total'] = len(similar) state['last_accessed'] = time.time() logger.info(f"Last.fm Radio generated: '{title}' ({len(similar)} tracks) → {playlist_mbid}") return jsonify({ "success": True, "playlist_mbid": playlist_mbid, "title": title, "track_count": len(similar), }) except Exception as e: logger.error(f"Error generating Last.fm radio: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/discover/listenbrainz/lastfm-radio', methods=['GET']) def get_listenbrainz_lastfm_radio(): """Get cached Last.fm Radio playlists (from DB cache). Does NOT require ListenBrainz authentication — Last.fm Radio playlists are generated independently of the LB account. """ try: lb_manager, username, source = _get_profile_lb_manager() playlists = lb_manager.get_cached_playlists('lastfm_radio') formatted = [ { "playlist": { "identifier": f"https://listenbrainz.org/playlist/{p['playlist_mbid']}", "title": p['title'], "creator": p['creator'], "annotation": p.get('annotation', {}), "track": [], } } for p in playlists ] return jsonify({"success": True, "playlists": formatted, "count": len(formatted), "username": username, "source": source}) except Exception as e: logger.error(f"Error getting Last.fm radio playlists: {e}") import traceback traceback.print_exc() return jsonify({"success": False, "error": str(e)}), 500 # ======================================== # LISTENBRAINZ PLAYLIST MANAGEMENT (Discovery System) # ======================================== def _lb_state_key(playlist_mbid, profile_id=None): """Build profile-scoped key for listenbrainz_playlist_states""" if profile_id is None: profile_id = get_current_profile_id() return f"{profile_id}:{playlist_mbid}" @app.route('/api/listenbrainz/playlists', methods=['GET']) def get_all_listenbrainz_playlists(): """Get all stored ListenBrainz playlists for frontend hydration (scoped to current profile)""" try: playlists = [] current_time = time.time() profile_id = get_current_profile_id() prefix = f"{profile_id}:" for state_key, state in listenbrainz_playlist_states.items(): if not state_key.startswith(prefix): continue # Update access time when requested state['last_accessed'] = current_time playlist_mbid = state_key[len(prefix):] # Return essential data for card recreation playlist_info = { 'playlist_mbid': playlist_mbid, 'playlist': state['playlist'], 'phase': state['phase'], 'status': state['status'], 'discovery_progress': state['discovery_progress'], 'spotify_matches': state['spotify_matches'], 'spotify_total': state['spotify_total'], 'converted_spotify_playlist_id': state.get('converted_spotify_playlist_id'), 'download_process_id': state.get('download_process_id'), 'created_at': state['created_at'], 'last_accessed': state['last_accessed'] } playlists.append(playlist_info) logger.info(f"Returning {len(playlists)} stored ListenBrainz playlists for profile {profile_id}") return jsonify({"playlists": playlists}) except Exception as e: logger.error(f"Error getting ListenBrainz playlists: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/state/', methods=['GET']) def get_listenbrainz_playlist_state(playlist_mbid): """Get specific ListenBrainz playlist state (detailed version)""" try: state_key = _lb_state_key(playlist_mbid) if state_key not in listenbrainz_playlist_states: return jsonify({"error": "ListenBrainz playlist not found"}), 404 state = listenbrainz_playlist_states[state_key] state['last_accessed'] = time.time() # Return full state information (including results for modal hydration) response = { 'playlist_mbid': playlist_mbid, 'playlist': state['playlist'], 'phase': state['phase'], 'status': state['status'], 'discovery_progress': state['discovery_progress'], 'spotify_matches': state['spotify_matches'], 'spotify_total': state['spotify_total'], 'discovery_results': state['discovery_results'], 'sync_playlist_id': state.get('sync_playlist_id'), 'converted_spotify_playlist_id': state.get('converted_spotify_playlist_id'), 'download_process_id': state.get('download_process_id'), 'sync_progress': state.get('sync_progress', {}), 'created_at': state['created_at'], 'last_accessed': state['last_accessed'] } return jsonify(response) except Exception as e: logger.error(f"Error getting ListenBrainz playlist state: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/reset/', methods=['POST']) def reset_listenbrainz_playlist(playlist_mbid): """Reset ListenBrainz playlist to fresh phase (clear discovery/sync data)""" try: state_key = _lb_state_key(playlist_mbid) if state_key not in listenbrainz_playlist_states: return jsonify({"error": "ListenBrainz playlist not found"}), 404 state = listenbrainz_playlist_states[state_key] # Stop any active discovery if 'discovery_future' in state and state['discovery_future']: state['discovery_future'].cancel() # Reset state to fresh (preserve original playlist data) state['phase'] = 'fresh' state['status'] = 'cached' state['discovery_results'] = [] state['discovery_progress'] = 0 state['spotify_matches'] = 0 state['sync_playlist_id'] = None state['converted_spotify_playlist_id'] = None state['sync_progress'] = {} state['discovery_future'] = None state['last_accessed'] = time.time() logger.info(f"Reset ListenBrainz playlist to fresh: {state['playlist']['title']}") return jsonify({"success": True, "phase": "fresh"}) except Exception as e: logger.error(f"Error resetting ListenBrainz playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/remove/', methods=['POST']) def remove_listenbrainz_playlist(playlist_mbid): """Remove ListenBrainz playlist from state (doesn't affect cache)""" try: state_key = _lb_state_key(playlist_mbid) if state_key not in listenbrainz_playlist_states: return jsonify({"error": "ListenBrainz playlist not found"}), 404 state = listenbrainz_playlist_states[state_key] # Stop any active discovery if 'discovery_future' in state and state['discovery_future']: state['discovery_future'].cancel() # Remove from state del listenbrainz_playlist_states[state_key] logger.info(f"Removed ListenBrainz playlist from state: {playlist_mbid}") return jsonify({"success": True}) except Exception as e: logger.error(f"Error removing ListenBrainz playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/discovery/start/', methods=['POST']) def start_listenbrainz_discovery(playlist_mbid): """Initialize and start Spotify discovery process for a ListenBrainz playlist""" try: data = request.get_json() playlist_data = data.get('playlist') if not playlist_data: return jsonify({"error": "Playlist data required"}), 400 # Create or update state state_key = _lb_state_key(playlist_mbid) if state_key not in listenbrainz_playlist_states: # Initialize new state listenbrainz_playlist_states[state_key] = { 'playlist_mbid': playlist_mbid, 'playlist': playlist_data, 'phase': 'discovering', 'status': 'discovering', 'discovery_progress': 0, 'spotify_matches': 0, 'spotify_total': len(playlist_data.get('tracks', [])), 'discovery_results': [], 'created_at': time.time(), 'last_accessed': time.time() } logger.info(f"Created new ListenBrainz playlist state: {playlist_data.get('name', 'Unknown')}") else: # State already exists, update it state = listenbrainz_playlist_states[state_key] if state['phase'] == 'discovering': return jsonify({"error": "Discovery already in progress"}), 400 # Reset for new discovery state['phase'] = 'discovering' state['status'] = 'discovering' state['discovery_progress'] = 0 state['spotify_matches'] = 0 state['discovery_results'] = [] state['last_accessed'] = time.time() state = listenbrainz_playlist_states[state_key] # Add activity for discovery start playlist_name = playlist_data.get('name', 'Unknown Playlist') track_count = len(playlist_data.get('tracks', [])) add_activity_item("", "ListenBrainz Discovery Started", f"'{playlist_name}' - {track_count} tracks", "Now") # Start discovery worker (pass state_key for profile-scoped state access) future = listenbrainz_discovery_executor.submit(_run_listenbrainz_discovery_worker, state_key) state['discovery_future'] = future logger.info(f"Started Spotify discovery for ListenBrainz playlist: {playlist_name}") return jsonify({"success": True, "message": "Discovery started"}) except Exception as e: logger.error(f"Error starting ListenBrainz discovery: {e}") import traceback traceback.print_exc() return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/discovery/status/', methods=['GET']) def get_listenbrainz_discovery_status(playlist_mbid): """Get real-time discovery status for a ListenBrainz playlist""" try: state_key = _lb_state_key(playlist_mbid) if state_key not in listenbrainz_playlist_states: return jsonify({"error": "ListenBrainz playlist not found"}), 404 state = listenbrainz_playlist_states[state_key] state['last_accessed'] = time.time() response = { 'phase': state['phase'], 'status': state['status'], 'progress': state['discovery_progress'], 'spotify_matches': state['spotify_matches'], 'spotify_total': state['spotify_total'], 'results': state['discovery_results'], 'complete': state['phase'] == 'discovered' } return jsonify(response) except Exception as e: logger.error(f"Error getting ListenBrainz discovery status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/update-phase/', methods=['POST']) def update_listenbrainz_phase(playlist_mbid): """Update ListenBrainz playlist phase (for phase transitions and persistence)""" try: state_key = _lb_state_key(playlist_mbid) if state_key not in listenbrainz_playlist_states: return jsonify({"error": "ListenBrainz playlist not found"}), 404 data = request.get_json() or {} new_phase = data.get('phase') if not new_phase: return jsonify({"error": "Phase is required"}), 400 state = listenbrainz_playlist_states[state_key] state['phase'] = new_phase state['last_accessed'] = time.time() # Update download process ID if provided (for download persistence) if 'download_process_id' in data: state['download_process_id'] = data['download_process_id'] logger.info(f"Updated ListenBrainz download_process_id: {data['download_process_id']}") # Update converted Spotify playlist ID if provided (for download persistence) if 'converted_spotify_playlist_id' in data: state['converted_spotify_playlist_id'] = data['converted_spotify_playlist_id'] logger.info(f"Updated ListenBrainz converted_spotify_playlist_id: {data['converted_spotify_playlist_id']}") logger.info(f"Updated ListenBrainz playlist {playlist_mbid} phase to: {new_phase}") return jsonify({ "success": True, "phase": new_phase }) except Exception as e: logger.error(f"Error updating ListenBrainz playlist phase: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/discovery/update_match', methods=['POST']) def update_listenbrainz_discovery_match(): """Update a ListenBrainz discovery result with manually selected Spotify track""" try: data = request.get_json() identifier = data.get('identifier') # playlist_mbid track_index = data.get('track_index') spotify_track = data.get('spotify_track') if not identifier or track_index is None or not spotify_track: return jsonify({'error': 'Missing required fields'}), 400 # Get the state (identifier is playlist_mbid) state = listenbrainz_playlist_states.get(_lb_state_key(identifier)) if not state: return jsonify({'error': 'Discovery state not found'}), 404 # Update the discovery result if track_index < len(state['discovery_results']): result = state['discovery_results'][track_index] # Was previously not found, now found if result['status_class'] == 'not-found' and spotify_track: state['spotify_matches'] += 1 # Was previously found, now not found elif result['status_class'] == 'found' and not spotify_track: state['spotify_matches'] -= 1 # Update result result['status'] = 'Found' if spotify_track else 'Not Found' result['status_class'] = 'found' if spotify_track else 'not-found' result['spotify_track'] = spotify_track.get('name', '') if spotify_track else '' # Join all artists (matching YouTube/Tidal/Beatport format) artists = spotify_track.get('artists', []) if spotify_track else [] result['spotify_artist'] = _join_artist_names(artists) if isinstance(artists, list) else _extract_artist_name(artists) # Album comes as a string from the frontend fix modal album = spotify_track.get('album', '') if spotify_track else '' result['spotify_album'] = album if isinstance(album, str) else album.get('name', '') if isinstance(album, dict) else '' result['spotify_id'] = spotify_track.get('id', '') if spotify_track else '' if spotify_track: # Store spotify_data in the same format as other platforms. # Manual match from the fix modal — build a rich spotify_data # (album as dict with image info) matching the normal discovery # shape, and explicitly clear any prior wing-it flag since the # user picked a real metadata match. result['spotify_data'] = _build_fix_modal_spotify_data(spotify_track) else: result['spotify_data'] = None result['wing_it_fallback'] = False result['manual_match'] = True logger.info(f"Updated ListenBrainz match for track {track_index}: {result['status']}") return jsonify({'success': True}) else: return jsonify({'error': 'Invalid track index'}), 400 except Exception as e: logger.error(f"Error updating ListenBrainz discovery match: {e}") import traceback traceback.print_exc() return jsonify({'error': str(e)}), 500 def convert_listenbrainz_results_to_spotify_tracks(discovery_results): """Convert ListenBrainz discovery results to Spotify tracks format for sync""" spotify_tracks = [] for result in discovery_results: # Support both data formats: spotify_data (manual fixes) and individual fields (automatic discovery) if result.get('spotify_data'): spotify_data = result['spotify_data'] # Create track object matching the expected format track = { 'id': spotify_data['id'], 'name': spotify_data['name'], 'artists': spotify_data['artists'], 'album': spotify_data['album'], 'duration_ms': spotify_data.get('duration_ms', 0) } if spotify_data.get('track_number'): track['track_number'] = spotify_data['track_number'] if spotify_data.get('disc_number'): track['disc_number'] = spotify_data['disc_number'] spotify_tracks.append(track) elif result.get('spotify_track') and result.get('status_class') == 'found': # Build from individual fields (automatic discovery format) track = { 'id': result.get('spotify_id', 'unknown'), 'name': result.get('spotify_track', 'Unknown Track'), 'artists': [result.get('spotify_artist', 'Unknown Artist')] if result.get('spotify_artist') else ['Unknown Artist'], 'album': result.get('spotify_album', 'Unknown Album'), 'duration_ms': 0 } spotify_tracks.append(track) logger.info(f"Converted {len(spotify_tracks)} ListenBrainz matches to Spotify tracks for sync") return spotify_tracks @app.route('/api/wing-it/sync', methods=['POST']) def wing_it_sync(): """Sync a playlist to the media server using raw track names — no metadata discovery.""" try: data = request.get_json() tracks_raw = data.get('tracks', []) playlist_name = data.get('playlist_name', 'Wing It Playlist') if not tracks_raw: return jsonify({"error": "No tracks provided"}), 400 # Convert raw tracks to dicts — _run_sync_task expects dicts with .get() sync_tracks = [] for t in tracks_raw: artist_name = '' if isinstance(t.get('artists'), list) and t['artists']: a = t['artists'][0] artist_name = a.get('name', str(a)) if isinstance(a, dict) else str(a) elif t.get('artist_name'): artist_name = t['artist_name'] album_name = '' if isinstance(t.get('album'), dict): album_name = t['album'].get('name', '') elif isinstance(t.get('album'), str): album_name = t['album'] elif t.get('album_name'): album_name = t['album_name'] sync_tracks.append({ 'id': t.get('id', f"wing_it_{len(sync_tracks)}"), 'name': t.get('name', t.get('track_name', 'Unknown')), 'artists': [{'name': artist_name}] if artist_name else [{'name': 'Unknown'}], 'album': album_name, 'duration_ms': t.get('duration_ms', 0), }) if not sync_tracks: return jsonify({"error": "No valid tracks to sync"}), 400 sync_playlist_id = f"wing_it_sync_{int(time.time())}" add_activity_item("", "Wing It Sync Started", f"'{playlist_name}' — {len(sync_tracks)} tracks", "Now") with sync_lock: sync_states[sync_playlist_id] = {"status": "starting", "progress": {}} # Pass wing_it flag via sync state so _run_sync_task can skip wishlist with sync_lock: sync_states[sync_playlist_id]['wing_it'] = True future = sync_executor.submit(_run_sync_task, sync_playlist_id, playlist_name, sync_tracks, None, get_current_profile_id()) active_sync_workers[sync_playlist_id] = future logger.info(f"[Wing It] Started sync for: {playlist_name} ({len(sync_tracks)} tracks)") return jsonify({"success": True, "sync_playlist_id": sync_playlist_id}) except Exception as e: logger.error(f"Error in Wing It sync: {e}", exc_info=True) return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/sync/start/', methods=['POST']) def start_listenbrainz_sync(playlist_mbid): """Start sync process for a ListenBrainz playlist using discovered Spotify tracks""" try: state_key = _lb_state_key(playlist_mbid) if state_key not in listenbrainz_playlist_states: return jsonify({"error": "ListenBrainz playlist not found"}), 404 state = listenbrainz_playlist_states[state_key] state['last_accessed'] = time.time() # Update access time if state['phase'] not in ['discovered', 'sync_complete', 'download_complete']: return jsonify({"error": "ListenBrainz playlist not ready for sync"}), 400 # Convert discovery results to Spotify tracks format spotify_tracks = convert_listenbrainz_results_to_spotify_tracks(state['discovery_results']) if not spotify_tracks: return jsonify({"error": "No Spotify matches found for sync"}), 400 # Create a temporary playlist ID for sync tracking sync_playlist_id = f"listenbrainz_{playlist_mbid}" playlist_name = state['playlist']['name'] # Add activity for sync start add_activity_item("", "ListenBrainz Sync Started", f"'{playlist_name}' - {len(spotify_tracks)} tracks", "Now") # Update ListenBrainz state state['phase'] = 'syncing' state['sync_playlist_id'] = sync_playlist_id state['sync_progress'] = {} # Start the sync using existing sync infrastructure sync_data = { 'playlist_id': sync_playlist_id, 'playlist_name': playlist_name, 'tracks': spotify_tracks } with sync_lock: sync_states[sync_playlist_id] = {"status": "starting", "progress": {}} # Submit sync task future = sync_executor.submit(_run_sync_task, sync_playlist_id, sync_data['playlist_name'], spotify_tracks, None, get_current_profile_id()) active_sync_workers[sync_playlist_id] = future logger.info(f"Started ListenBrainz sync for: {playlist_name} ({len(spotify_tracks)} tracks)") return jsonify({"success": True, "sync_playlist_id": sync_playlist_id}) except Exception as e: logger.error(f"Error starting ListenBrainz sync: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/sync/status/', methods=['GET']) def get_listenbrainz_sync_status(playlist_mbid): """Get sync status for a ListenBrainz playlist""" try: state_key = _lb_state_key(playlist_mbid) if state_key not in listenbrainz_playlist_states: return jsonify({"error": "ListenBrainz playlist not found"}), 404 state = listenbrainz_playlist_states[state_key] state['last_accessed'] = time.time() # Update access time sync_playlist_id = state.get('sync_playlist_id') if not sync_playlist_id: return jsonify({"error": "No sync in progress"}), 404 # Get sync status from existing sync infrastructure with sync_lock: sync_state = sync_states.get(sync_playlist_id, {}) response = { 'phase': state['phase'], 'sync_status': sync_state.get('status', 'unknown'), 'progress': sync_state.get('progress', {}), 'complete': sync_state.get('status') == 'finished', 'error': sync_state.get('error') } # Update ListenBrainz state if sync completed if sync_state.get('status') == 'finished': state['phase'] = 'sync_complete' state['sync_progress'] = sync_state.get('progress', {}) # Add activity for sync completion playlist_name = state.get('playlist', {}).get('name', 'Unknown Playlist') add_activity_item("", "Sync Complete", f"ListenBrainz playlist '{playlist_name}' synced successfully", "Now") elif sync_state.get('status') == 'error': state['phase'] = 'discovered' # Revert on error playlist_name = state.get('playlist', {}).get('name', 'Unknown Playlist') add_activity_item("", "Sync Failed", f"ListenBrainz playlist '{playlist_name}' sync failed", "Now") return jsonify(response) except Exception as e: logger.error(f"Error getting ListenBrainz sync status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/listenbrainz/sync/cancel/', methods=['POST']) def cancel_listenbrainz_sync(playlist_mbid): """Cancel sync for a ListenBrainz playlist""" try: state_key = _lb_state_key(playlist_mbid) if state_key not in listenbrainz_playlist_states: return jsonify({"error": "ListenBrainz playlist not found"}), 404 state = listenbrainz_playlist_states[state_key] state['last_accessed'] = time.time() # Update access time sync_playlist_id = state.get('sync_playlist_id') if sync_playlist_id: # Cancel the sync using existing sync infrastructure with sync_lock: sync_states[sync_playlist_id] = {"status": "cancelled"} # Clean up sync worker if sync_playlist_id in active_sync_workers: del active_sync_workers[sync_playlist_id] # Revert ListenBrainz state state['phase'] = 'discovered' state['sync_playlist_id'] = None state['sync_progress'] = {} return jsonify({"success": True, "message": "ListenBrainz sync cancelled"}) except Exception as e: logger.error(f"Error cancelling ListenBrainz sync: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/metadata/start', methods=['POST']) def start_metadata_update(): """Start the metadata update process - EXACT copy of dashboard.py logic""" global metadata_update_worker, metadata_update_runtime_worker, metadata_update_state try: # Check if already running if metadata_update_state['status'] == 'running': return jsonify({"success": False, "error": "Metadata update already running"}), 400 # Get refresh interval from request data = request.get_json() or {} refresh_interval_days = data.get('refresh_interval_days', 30) # Check active server and client availability - EXACTLY like dashboard.py active_server = config_manager.get_active_media_server() # Get appropriate media client - Support all three servers if active_server == "jellyfin": media_client = media_server_engine.client('jellyfin') if not media_client: add_activity_item("", "Metadata Update", "Jellyfin client not available", "Now") return jsonify({"success": False, "error": "Jellyfin client not available"}), 400 elif active_server == "navidrome": media_client = media_server_engine.client('navidrome') if not media_client: add_activity_item("", "Metadata Update", "Navidrome client not available", "Now") return jsonify({"success": False, "error": "Navidrome client not available"}), 400 else: # plex media_client = media_server_engine.client('plex') if not media_client: add_activity_item("", "Metadata Update", "Plex client not available", "Now") return jsonify({"success": False, "error": "Plex client not available"}), 400 logger.debug("Plex connection details: active_server=%s client=%s", active_server, media_client) if hasattr(media_client, 'server') and media_client.server: logger.debug( "Plex server details: url=%s name=%s", getattr(media_client.server, '_baseurl', 'NO_URL'), getattr(media_client.server, 'friendlyName', 'NO_NAME'), ) # Check available libraries try: sections = media_client.server.library.sections() logger.debug("Available Plex libraries: %s", [(s.title, s.type) for s in sections]) except Exception as e: logger.debug("Error getting Plex libraries: %s", e) else: logger.debug("Plex server is NOT connected!") # Check Spotify client - EXACTLY like dashboard.py if not spotify_client: add_activity_item("", "Metadata Update", "Spotify client not available", "Now") return jsonify({"success": False, "error": "Spotify client not available"}), 400 # Reset state metadata_update_state.update({ 'status': 'running', 'current_artist': 'Loading artists...', 'processed': 0, 'total': 0, 'percentage': 0.0, 'successful': 0, 'failed': 0, 'started_at': datetime.now(), 'completed_at': None, 'error': None, 'refresh_interval_days': refresh_interval_days }) # Start the metadata update worker - EXACTLY like dashboard.py def run_metadata_update(): global metadata_update_runtime_worker try: metadata_worker = WebMetadataUpdateWorker( None, # Artists will be loaded in the worker thread - EXACTLY like dashboard.py media_client, spotify_client, active_server, refresh_interval_days ) metadata_update_runtime_worker = metadata_worker metadata_worker.run() except Exception as e: logger.error(f"Error in metadata update worker: {e}") metadata_update_state['status'] = 'error' metadata_update_state['error'] = str(e) add_activity_item("", "Metadata Error", str(e), "Now") finally: metadata_update_runtime_worker = None metadata_update_worker = metadata_update_executor.submit(run_metadata_update) add_activity_item("", "Metadata Update", "Loading artists from library...", "Now") return jsonify({"success": True}) except Exception as e: logger.error(f"Error starting metadata update: {e}") metadata_update_state['status'] = 'error' metadata_update_state['error'] = str(e) return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/metadata/stop', methods=['POST']) def stop_metadata_update(): """Stop the metadata update process""" global metadata_update_state try: if metadata_update_state['status'] == 'running': metadata_update_state['status'] = 'stopping' metadata_update_state['current_artist'] = 'Stopping...' add_activity_item("", "Metadata Update", "Stopping metadata update process", "Now") return jsonify({"success": True}) except Exception as e: logger.error(f"Error stopping metadata update: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/metadata/status', methods=['GET']) def get_metadata_update_status(): """Get current metadata update status""" try: # Return a copy of the state with datetime serialization state_copy = metadata_update_state.copy() # Convert datetime objects to ISO format for JSON serialization if state_copy.get('started_at'): state_copy['started_at'] = state_copy['started_at'].isoformat() if state_copy.get('completed_at'): state_copy['completed_at'] = state_copy['completed_at'].isoformat() return jsonify({"success": True, "status": state_copy}) except Exception as e: logger.error(f"Error getting metadata update status: {e}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/active-media-server', methods=['GET']) def get_active_media_server(): """Get the currently active media server""" try: active_server = config_manager.get_active_media_server() return jsonify({"success": True, "active_server": active_server}) except Exception as e: logger.error(f"Error getting active media server: {e}") return jsonify({"success": False, "error": str(e)}), 500 # ================================= # # BEATPORT API ENDPOINTS # # ================================= # @app.route('/api/beatport/genres', methods=['GET']) def get_beatport_genres(): """Get current Beatport genres with images dynamically scraped from homepage""" try: logger.info("API request for Beatport genres") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Get query parameters include_images = request.args.get('include_images', 'false').lower() == 'true' # Discover genres dynamically if include_images: logger.info("Including genre images in response (slower)") genres = scraper.discover_genres_with_images(include_images=True) else: logger.info("Returning genres without images (faster)") genres = scraper.discover_genres_from_homepage() logger.info(f"Successfully discovered {len(genres)} Beatport genres") return jsonify({ "success": True, "genres": genres, "count": len(genres), "includes_images": include_images }) except Exception as e: logger.error(f"Error fetching Beatport genres: {e}") return jsonify({ "success": False, "error": str(e), "genres": [], "count": 0 }), 500 @app.route('/api/beatport/genre///tracks', methods=['GET']) def get_beatport_genre_tracks(genre_slug, genre_id): """Get tracks for a specific Beatport genre""" try: logger.info(f"API request for {genre_slug} genre tracks (ID: {genre_id})") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Get query parameters limit = int(request.args.get('limit', '100')) enrich = request.args.get('enrich', 'true').lower() != 'false' # Create genre dict for scraper genre = { 'name': genre_slug.replace('-', ' ').title(), 'slug': genre_slug, 'id': genre_id } # Scrape tracks for this genre tracks = scraper.scrape_genre_charts(genre, limit=limit, enrich=enrich) logger.info(f"Successfully scraped {len(tracks)} tracks for {genre_slug}") return jsonify({ "success": True, "tracks": tracks, "genre": genre, "count": len(tracks) }) except Exception as e: logger.error(f"Error fetching tracks for {genre_slug}: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "count": 0 }), 500 @app.route('/api/beatport/chart/extract', methods=['POST']) def extract_beatport_chart_tracks(): """Extract tracks from a specific Beatport chart URL""" try: data = request.get_json() chart_url = data.get('chart_url') chart_name = data.get('chart_name', 'Unknown Chart') limit = int(data.get('limit', 100)) if not chart_url: return jsonify({ "success": False, "error": "chart_url is required", "tracks": [], "count": 0 }), 400 enrich = data.get('enrich', True) logger.info(f"API request to extract tracks from chart: {chart_name}") logger.info(f"Chart URL: {chart_url}") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() if enrich: # Full extraction + enrichment (legacy synchronous path) tracks = scraper.extract_tracks_from_chart(chart_url, chart_name, limit) else: # Extract raw track list only (no per-track enrichment) soup = scraper.get_page(chart_url) tracks = [] if soup: tracks = scraper.extract_tracks_from_chart_table(soup, chart_name, limit) if len(tracks) < 10: general_tracks = scraper.extract_tracks_from_page(soup, f"New Chart: {chart_name}", limit) if len(general_tracks) > len(tracks): tracks = general_tracks if len(tracks) < 10: table_tracks = scraper.extract_tracks_from_table_format(soup, chart_name, limit) if len(table_tracks) > len(tracks): tracks = table_tracks logger.info(f"Successfully extracted {len(tracks)} tracks from chart: {chart_name}") return jsonify({ "success": True, "tracks": tracks, "chart_name": chart_name, "chart_url": chart_url, "count": len(tracks) }) except Exception as e: logger.error(f"Error extracting tracks from chart: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "count": 0 }), 500 @app.route('/api/beatport/genre///top-10', methods=['GET']) def get_beatport_genre_top_10(genre_slug, genre_id): """Get top 10 tracks for a specific Beatport genre""" try: logger.info(f"API request for {genre_slug} genre top 10 tracks (ID: {genre_id})") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Create genre dict for scraper genre = { 'name': genre_slug.replace('-', ' ').title(), 'slug': genre_slug, 'id': genre_id } # Scrape top 10 tracks for this genre tracks = scraper.scrape_genre_top_10(genre) logger.info(f"Successfully scraped {len(tracks)} top 10 tracks for {genre_slug}") return jsonify({ "success": True, "tracks": tracks, "genre": genre, "count": len(tracks) }) except Exception as e: logger.error(f"Error fetching top 10 tracks for {genre_slug}: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "count": 0 }), 500 @app.route('/api/beatport/genre///releases-top-10', methods=['GET']) def get_beatport_genre_releases_top_10(genre_slug, genre_id): """Get top 10 releases for a specific Beatport genre""" try: logger.info(f"API request for {genre_slug} genre top 10 releases (ID: {genre_id})") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Create genre dict for scraper genre = { 'name': genre_slug.replace('-', ' ').title(), 'slug': genre_slug, 'id': genre_id } # Scrape top 10 releases for this genre releases = scraper.scrape_genre_releases(genre, limit=10) logger.info(f"Successfully scraped {len(releases)} top 10 releases for {genre_slug}") return jsonify({ "success": True, "tracks": releases, "genre": genre, "count": len(releases) }) except Exception as e: logger.error(f"Error fetching top 10 releases for {genre_slug}: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "count": 0 }), 500 @app.route('/api/beatport/genre///releases-top-100', methods=['GET']) def get_beatport_genre_releases_top_100(genre_slug, genre_id): """Get top 100 releases for a specific Beatport genre""" try: logger.info(f"API request for {genre_slug} genre top 100 releases (ID: {genre_id})") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Get query parameters limit = int(request.args.get('limit', '100')) # Create genre dict for scraper genre = { 'name': genre_slug.replace('-', ' ').title(), 'slug': genre_slug, 'id': genre_id } # Scrape top releases for this genre releases = scraper.scrape_genre_releases(genre, limit=limit) logger.info(f"Successfully scraped {len(releases)} top 100 releases for {genre_slug}") return jsonify({ "success": True, "tracks": releases, "genre": genre, "count": len(releases) }) except Exception as e: logger.error(f"Error fetching top 100 releases for {genre_slug}: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "count": 0 }), 500 @app.route('/api/beatport/genre///staff-picks', methods=['GET']) def get_beatport_genre_staff_picks(genre_slug, genre_id): """Get staff picks for a specific Beatport genre""" try: logger.info(f"API request for {genre_slug} genre staff picks (ID: {genre_id})") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Get query parameters limit = int(request.args.get('limit', '50')) # Create genre dict for scraper genre = { 'name': genre_slug.replace('-', ' ').title(), 'slug': genre_slug, 'id': genre_id } # Scrape staff picks for this genre tracks = scraper.scrape_genre_staff_picks(genre, limit=limit) logger.info(f"Successfully scraped {len(tracks)} staff picks for {genre_slug}") return jsonify({ "success": True, "tracks": tracks, "genre": genre, "count": len(tracks) }) except Exception as e: logger.error(f"Error fetching staff picks for {genre_slug}: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "count": 0 }), 500 @app.route('/api/beatport/genre///hype-top-10', methods=['GET']) def get_beatport_genre_hype_top_10(genre_slug, genre_id): """Get hype top 10 tracks for a specific Beatport genre""" try: logger.info(f"API request for {genre_slug} genre hype top 10 (ID: {genre_id})") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Create genre dict for scraper genre = { 'name': genre_slug.replace('-', ' ').title(), 'slug': genre_slug, 'id': genre_id } # Scrape hype top 10 for this genre tracks = scraper.scrape_genre_hype_top_10(genre) logger.info(f"Successfully scraped {len(tracks)} hype top 10 tracks for {genre_slug}") return jsonify({ "success": True, "tracks": tracks, "genre": genre, "count": len(tracks) }) except Exception as e: logger.error(f"Error fetching hype top 10 for {genre_slug}: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "count": 0 }), 500 @app.route('/api/beatport/genre///hype-top-100', methods=['GET']) def get_beatport_genre_hype_top_100(genre_slug, genre_id): """Get hype top 100 tracks for a specific Beatport genre""" try: logger.info(f"API request for {genre_slug} genre hype top 100 (ID: {genre_id})") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Create genre dict for scraper genre = { 'name': genre_slug.replace('-', ' ').title(), 'slug': genre_slug, 'id': genre_id } # Scrape hype top 100 for this genre tracks = scraper.scrape_genre_hype_charts(genre, limit=100) logger.info(f"Successfully scraped {len(tracks)} hype top 100 tracks for {genre_slug}") return jsonify({ "success": True, "tracks": tracks, "genre": genre, "count": len(tracks) }) except Exception as e: logger.error(f"Error fetching hype top 100 for {genre_slug}: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "count": 0 }), 500 @app.route('/api/beatport/genre///hype-picks', methods=['GET']) def get_beatport_genre_hype_picks(genre_slug, genre_id): """Get hype picks for a specific Beatport genre""" try: logger.info(f"API request for {genre_slug} genre hype picks (ID: {genre_id})") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Get query parameters limit = int(request.args.get('limit', '50')) # Create genre dict for scraper genre = { 'name': genre_slug.replace('-', ' ').title(), 'slug': genre_slug, 'id': genre_id } # Scrape hype picks for this genre tracks = scraper.scrape_genre_hype_picks(genre, limit=limit) logger.info(f"Successfully scraped {len(tracks)} hype picks for {genre_slug}") return jsonify({ "success": True, "tracks": tracks, "genre": genre, "count": len(tracks) }) except Exception as e: logger.error(f"Error fetching hype picks for {genre_slug}: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "count": 0 }), 500 @app.route('/api/beatport/genre///latest-releases', methods=['GET']) def get_beatport_genre_latest_releases(genre_slug, genre_id): """Get latest releases for a specific Beatport genre""" try: logger.info(f"API request for {genre_slug} genre latest releases (ID: {genre_id})") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Get query parameters limit = int(request.args.get('limit', '50')) # Create genre dict for scraper genre = { 'name': genre_slug.replace('-', ' ').title(), 'slug': genre_slug, 'id': genre_id } # Scrape latest releases for this genre tracks = scraper.scrape_genre_latest_releases(genre, limit=limit) logger.info(f"Successfully scraped {len(tracks)} latest releases for {genre_slug}") return jsonify({ "success": True, "tracks": tracks, "genre": genre, "count": len(tracks) }) except Exception as e: logger.error(f"Error fetching latest releases for {genre_slug}: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "count": 0 }), 500 @app.route('/api/beatport/genre///new-charts', methods=['GET']) def get_beatport_genre_new_charts(genre_slug, genre_id): """Get new charts for a specific Beatport genre""" try: logger.info(f"API request for {genre_slug} genre new charts (ID: {genre_id})") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Get query parameters limit = int(request.args.get('limit', '50')) # Create genre dict for scraper genre = { 'name': genre_slug.replace('-', ' ').title(), 'slug': genre_slug, 'id': genre_id } # Scrape new charts for this genre tracks = scraper.scrape_genre_new_charts(genre, limit=limit) logger.info(f"Successfully scraped {len(tracks)} new charts for {genre_slug}") return jsonify({ "success": True, "tracks": tracks, "genre": genre, "count": len(tracks) }) except Exception as e: logger.error(f"Error fetching new charts for {genre_slug}: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "count": 0 }), 500 @app.route('/api/beatport/genre///hero', methods=['GET']) def get_beatport_genre_hero(genre_slug, genre_id): """Get hero slider data for a specific Beatport genre with 1-hour caching""" try: logger.info(f"API request for {genre_slug} genre hero slider (ID: {genre_id})") # Check cache first (1-hour TTL like other genre data) cache_key = f"hero_{genre_slug}_{genre_id}" cached_data = get_cached_beatport_data('genre', cache_key, genre_slug) if cached_data: logger.info(f"Returning cached hero data for {genre_slug}") return jsonify({ "success": True, "releases": cached_data, "count": len(cached_data), "genre_slug": genre_slug, "genre_id": genre_id, "cached": True, "cache_timestamp": time.time() }) # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Scrape hero slider data hero_releases = scraper.scrape_genre_hero_slider(genre_slug, genre_id) if hero_releases: # Cache the data (1-hour TTL) set_cached_beatport_data('genre', cache_key, hero_releases, genre_slug) logger.info(f"Successfully scraped and cached {len(hero_releases)} hero releases for {genre_slug}") return jsonify({ "success": True, "releases": hero_releases, "count": len(hero_releases), "genre_slug": genre_slug, "genre_id": genre_id, "cached": False, "scrape_timestamp": time.time() }) else: logger.info(f"No hero releases found for {genre_slug}") return jsonify({ "success": False, "releases": [], "count": 0, "genre_slug": genre_slug, "genre_id": genre_id, "message": "No hero releases found" }) except Exception as e: logger.error(f"Error fetching hero data for {genre_slug}: {e}") return jsonify({ "success": False, "error": str(e), "releases": [], "count": 0, "genre_slug": genre_slug, "genre_id": genre_id }), 500 @app.route('/api/beatport/genre///top-10-lists', methods=['GET']) def get_beatport_genre_top10_lists(genre_slug, genre_id): """Get Top 10 lists (Beatport + Hype) for a specific genre with 1-hour caching""" try: logger.info(f"API request for {genre_slug} Top 10 lists (ID: {genre_id})") # Check cache first (1-hour TTL) cached_data = get_cached_beatport_data('genre', 'top_10_lists', genre_slug) if cached_data: logger.info(f"Returning cached Top 10 lists for {genre_slug}") cached_data['success'] = True cached_data['cached'] = True return jsonify(cached_data) # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Scrape Top 10 lists from genre page top10_data = scraper.scrape_genre_top10_tracks(genre_slug, genre_id) if not top10_data['beatport_top10'] and not top10_data['hype_top10']: return jsonify({ "success": False, "error": "No Top 10 tracks found for this genre", "beatport_top10": [], "hype_top10": [], "beatport_count": 0, "hype_count": 0, "has_hype_section": False, "genre_slug": genre_slug, "genre_id": genre_id, "cached": False }) # Prepare response data response_data = { "beatport_top10": top10_data['beatport_top10'], "hype_top10": top10_data['hype_top10'], "beatport_count": len(top10_data['beatport_top10']), "hype_count": len(top10_data['hype_top10']), "has_hype_section": top10_data['has_hype_section'], "total_tracks": top10_data['total_tracks'], "genre_slug": genre_slug, "genre_id": genre_id, "cached": False, "cache_ttl": 3600 # 1 hour } # Cache the data (1-hour TTL) set_cached_beatport_data('genre', 'top_10_lists', response_data, genre_slug) logger.info(f"Successfully fetched {response_data['beatport_count']} Beatport + {response_data['hype_count']} Hype Top 10 tracks for {genre_slug}") response_data['success'] = True return jsonify(response_data) except Exception as e: logger.error(f"Error fetching Top 10 lists for {genre_slug}: {e}") return jsonify({ "success": False, "error": str(e), "beatport_top10": [], "hype_top10": [], "beatport_count": 0, "hype_count": 0, "has_hype_section": False, "genre_slug": genre_slug, "genre_id": genre_id, "cached": False }), 500 @app.route('/api/beatport/genre///top-10-releases', methods=['GET']) def get_beatport_genre_top10_releases(genre_slug, genre_id): """Get Top 10 releases for a specific genre using .partial-artwork elements with 1-hour caching""" try: logger.info(f"API request for {genre_slug} Top 10 releases (ID: {genre_id})") # Check cache first (1-hour TTL) cached_data = get_cached_beatport_data('genre', 'top_10_releases', genre_slug) if cached_data: logger.info(f"Returning cached Top 10 releases for {genre_slug}") cached_data['success'] = True cached_data['cached'] = True return jsonify(cached_data) # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Scrape Top 10 releases from genre page releases = scraper.scrape_genre_top10_releases(genre_slug, genre_id) if not releases: return jsonify({ "success": False, "error": "No Top 10 releases found for this genre", "releases": [], "releases_count": 0, "genre_slug": genre_slug, "genre_id": genre_id, "cached": False }) # Prepare response data response_data = { "releases": releases, "releases_count": len(releases), "genre_slug": genre_slug, "genre_id": genre_id, "cached": False, "cache_ttl": 3600 # 1 hour } # Cache the data (1-hour TTL) set_cached_beatport_data('genre', 'top_10_releases', response_data, genre_slug) logger.info(f"Successfully fetched {response_data['releases_count']} Top 10 releases for {genre_slug}") response_data['success'] = True return jsonify(response_data) except Exception as e: logger.error(f"Error fetching Top 10 releases for {genre_slug}: {e}") return jsonify({ "success": False, "error": str(e), "releases": [], "releases_count": 0, "genre_slug": genre_slug, "genre_id": genre_id, "cached": False }), 500 @app.route('/api/beatport/genre///sections', methods=['GET']) def get_beatport_genre_sections(genre_slug, genre_id): """Discover all available sections for a specific Beatport genre""" try: logger.info(f"API request for {genre_slug} genre sections discovery (ID: {genre_id})") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Create genre dict for scraper genre = { 'name': genre_slug.replace('-', ' ').title(), 'slug': genre_slug, 'id': genre_id } # Discover sections for this genre sections = scraper.discover_genre_page_sections(genre) logger.info(f"Successfully discovered sections for {genre_slug}") return jsonify({ "success": True, "sections": sections, "genre": genre }) except Exception as e: logger.error(f"Error discovering sections for {genre_slug}: {e}") return jsonify({ "success": False, "error": str(e), "sections": {} }), 500 @app.route('/api/beatport/top-100', methods=['GET']) def get_beatport_top_100(): """Get Beatport Top 100 tracks""" try: logger.info("API request for Beatport Top 100") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Get query parameters limit = int(request.args.get('limit', '100')) enrich = request.args.get('enrich', 'true').lower() != 'false' # Scrape Top 100 tracks = scraper.scrape_top_100(limit=limit, enrich=enrich) logger.info(f"Successfully scraped {len(tracks)} tracks from Beatport Top 100") return jsonify({ "success": True, "tracks": tracks, "chart_name": "Beatport Top 100", "count": len(tracks) }) except Exception as e: logger.error(f"Error fetching Beatport Top 100: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "count": 0 }), 500 @app.route('/api/beatport/genre-image//', methods=['GET']) def get_beatport_genre_image(genre_slug, genre_id): """Get image for a specific Beatport genre""" try: logger.info(f"API request for {genre_slug} genre image") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Construct genre URL genre_url = f"{scraper.base_url}/genre/{genre_slug}/{genre_id}" # Get genre image image_url = scraper.get_genre_image(genre_url) if image_url: logger.info(f"Found image for {genre_slug}") return jsonify({ "success": True, "image_url": image_url, "genre_slug": genre_slug, "genre_id": genre_id }) else: logger.info(f"No image found for {genre_slug}") return jsonify({ "success": False, "image_url": None, "genre_slug": genre_slug, "genre_id": genre_id }) except Exception as e: logger.error(f"Error fetching image for {genre_slug}: {e}") return jsonify({ "success": False, "error": str(e), "image_url": None }), 500 @app.route('/api/beatport/hype-top-100', methods=['GET']) def get_beatport_hype_top_100(): """Get Beatport Hype Top 100 - Improved with fixed URL""" try: logger.info("API request for Beatport Hype Top 100") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Get query parameters limit = int(request.args.get('limit', '100')) enrich = request.args.get('enrich', 'true').lower() != 'false' # Scrape Hype Top 100 using improved method tracks = scraper.scrape_hype_top_100(limit=limit, enrich=enrich) logger.info(f"Successfully scraped {len(tracks)} tracks from Beatport Hype Top 100") return jsonify({ "success": True, "tracks": tracks, "chart_name": "Beatport Hype Top 100", "count": len(tracks) }) except Exception as e: logger.error(f"Error fetching Beatport Hype Top 100: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "count": 0 }), 500 @app.route('/api/beatport/top-100-releases', methods=['GET']) def get_beatport_top_100_releases(): """Get Beatport Top 100 Releases - New endpoint""" try: logger.info("API request for Beatport Top 100 Releases") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Get query parameters limit = int(request.args.get('limit', '100')) # Scrape Top 100 Releases using new method tracks = scraper.scrape_top_100_releases(limit=limit) logger.info(f"Successfully scraped {len(tracks)} tracks from Beatport Top 100 Releases") return jsonify({ "success": True, "tracks": tracks, "chart_name": "Top 100 New Releases", "count": len(tracks) }) except Exception as e: logger.error(f"Error fetching Beatport Top 100 Releases: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "count": 0 }), 500 @app.route('/api/beatport/homepage/new-releases', methods=['GET']) def get_beatport_homepage_new_releases(): """Get Beatport New Releases from homepage section""" try: limit = int(request.args.get('limit', 40)) logger.info(f"🆕 API request for Beatport homepage New Releases (limit: {limit})") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Get new releases from homepage new_releases = scraper.scrape_new_releases(limit=limit) logger.info(f"Successfully extracted {len(new_releases)} new releases from homepage") return jsonify({ "success": True, "tracks": new_releases, "track_count": len(new_releases), "source": "beatport_homepage_new_releases" }) except Exception as e: logger.error(f"Error getting Beatport homepage new releases: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "track_count": 0 }), 500 @app.route('/api/beatport/homepage/hype-picks', methods=['GET']) def get_beatport_homepage_hype_picks(): """Get Beatport Hype Picks from homepage section""" try: limit = int(request.args.get('limit', 40)) logger.info(f"API request for Beatport homepage Hype Picks (limit: {limit})") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Get hype picks from homepage hype_picks = scraper.scrape_hype_picks_homepage(limit=limit) logger.info(f"Successfully extracted {len(hype_picks)} hype picks from homepage") return jsonify({ "success": True, "tracks": hype_picks, "track_count": len(hype_picks), "source": "beatport_homepage_hype_picks" }) except Exception as e: logger.error(f"Error getting Beatport homepage hype picks: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "track_count": 0 }), 500 @app.route('/api/beatport/homepage/top-10-releases', methods=['GET']) def get_beatport_homepage_top_10_releases(): """Get Beatport Top 10 Releases from homepage section""" try: limit = int(request.args.get('limit', 10)) logger.info(f"API request for Beatport homepage Top 10 Releases (limit: {limit})") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Get top 10 releases from homepage top_10_releases = scraper.scrape_top_10_releases_homepage(limit=limit) logger.info(f"Successfully extracted {len(top_10_releases)} top 10 releases from homepage") return jsonify({ "success": True, "tracks": top_10_releases, "track_count": len(top_10_releases), "source": "beatport_homepage_top_10_releases" }) except Exception as e: logger.error(f"Error getting Beatport homepage top 10 releases: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "track_count": 0 }), 500 @app.route('/api/beatport/homepage/top-10-lists', methods=['GET']) def get_beatport_homepage_top10_lists(): """Get Beatport Top 10 Lists from homepage - both Beatport Top 10 and Hype Top 10""" try: logger.info("API request for Beatport homepage Top 10 Lists") # Check cache first cached_data = get_cached_beatport_data('homepage', 'top_10_lists') if cached_data: logger.info("Returning cached top 10 lists data") response = jsonify(cached_data) return add_cache_headers(response, 3600) # 1 hour # Cache miss - scrape fresh data logger.info("Cache miss - scraping fresh top 10 lists data...") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Get top 10 lists from homepage top10_lists = scraper.scrape_homepage_top10_lists() logger.info(f"Successfully extracted Beatport Top 10: {len(top10_lists['beatport_top10'])}, Hype Top 10: {len(top10_lists['hype_top10'])}") # Prepare response data response_data = { "success": True, "beatport_top10": top10_lists["beatport_top10"], "hype_top10": top10_lists["hype_top10"], "beatport_count": len(top10_lists["beatport_top10"]), "hype_count": len(top10_lists["hype_top10"]), "source": "beatport_homepage_top10_lists" } # Cache the successful response set_cached_beatport_data('homepage', 'top_10_lists', response_data) response = jsonify(response_data) return add_cache_headers(response, 3600) # 1 hour except Exception as e: logger.error(f"Error getting Beatport homepage top 10 lists: {e}") return jsonify({ "success": False, "error": str(e), "beatport_top10": [], "hype_top10": [], "beatport_count": 0, "hype_count": 0 }), 500 @app.route('/api/beatport/homepage/top-10-releases-cards', methods=['GET']) def get_beatport_homepage_top10_releases_cards(): """Get Beatport Top 10 Releases CARDS from homepage (not individual tracks)""" try: logger.info("API request for Beatport homepage Top 10 Releases CARDS") # Check cache first cached_data = get_cached_beatport_data('homepage', 'top_10_releases') if cached_data: logger.info("Returning cached top 10 releases data") response = jsonify(cached_data) return add_cache_headers(response, 3600) # 1 hour # Cache miss - scrape fresh data logger.info("Cache miss - scraping fresh top 10 releases data...") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Get top 10 releases from homepage top10_releases = scraper.scrape_homepage_top10_releases() logger.info(f"API extracted {len(top10_releases)} Top 10 Release Cards") # Debug: Log first release if any if top10_releases: logger.info(f"First release: {top10_releases[0].get('title', 'No title')} by {top10_releases[0].get('artist', 'No artist')}") else: logger.warning("No releases found by scraper") # Prepare response data response_data = { "success": True, "releases": top10_releases, "releases_count": len(top10_releases), "source": "beatport_homepage_top10_releases_cards" } # Cache the successful response set_cached_beatport_data('homepage', 'top_10_releases', response_data) response = jsonify(response_data) return add_cache_headers(response, 3600) # 1 hour except Exception as e: logger.error(f"Error getting Beatport homepage Top 10 Releases cards: {e}") import traceback logger.error(f"Full traceback: {traceback.format_exc()}") return jsonify({ "success": False, "error": str(e), "releases": [], "releases_count": 0 }), 500 @app.route('/api/beatport/scrape-releases', methods=['POST']) def scrape_beatport_releases(): """General scraper endpoint - takes release URLs and returns tracks""" try: data = request.get_json() if not data: return jsonify({ "success": False, "error": "No JSON data provided", "tracks": [], "track_count": 0 }), 400 release_urls = data.get('release_urls', []) source_name = data.get('source_name', 'General Release Scraper') if not release_urls: return jsonify({ "success": False, "error": "No release URLs provided", "tracks": [], "track_count": 0 }), 400 logger.info(f"API request to scrape {len(release_urls)} release URLs with source: {source_name}") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Use our new general scraper function tracks = scraper.scrape_multiple_releases(release_urls, source_name) logger.info(f"Successfully extracted {len(tracks)} tracks from {len(release_urls)} releases") # Apply text cleaning to track data cleaned_tracks = [] for track in tracks: cleaned_track = track.copy() if 'title' in cleaned_track: cleaned_track['title'] = clean_beatport_text(cleaned_track['title']) if 'artist' in cleaned_track: cleaned_track['artist'] = clean_beatport_text(cleaned_track['artist']) if 'label' in cleaned_track: cleaned_track['label'] = clean_beatport_text(cleaned_track['label']) cleaned_tracks.append(cleaned_track) return jsonify({ "success": True, "tracks": cleaned_tracks, "track_count": len(cleaned_tracks), "source": source_name, "release_urls_processed": len(release_urls) }) except Exception as e: logger.error(f"Error scraping releases: {e}") import traceback logger.error(f"Full traceback: {traceback.format_exc()}") return jsonify({ "success": False, "error": str(e), "tracks": [], "track_count": 0 }), 500 @app.route('/api/beatport/release-metadata', methods=['POST']) def get_beatport_release_metadata(): """Fetch structured release metadata for direct download modal (skip discovery)""" try: data = request.get_json() if not data: return jsonify({"success": False, "error": "No JSON data provided"}), 400 release_url = data.get('release_url', '') if not release_url: return jsonify({"success": False, "error": "No release_url provided"}), 400 logger.info(f"API request for release metadata: {release_url}") scraper = BeatportUnifiedScraper() result = scraper.get_release_metadata(release_url) if not result.get('success'): return jsonify(result), 404 # Apply text cleaning album = result['album'] artist = result['artist'] album['name'] = clean_beatport_text(album['name']) artist['name'] = clean_beatport_text(artist['name']) for track in result['tracks']: track['name'] = clean_beatport_text(track['name']) for a in track.get('artists', []): a['name'] = clean_beatport_text(a['name']) # Update the embedded album name too track['album']['name'] = album['name'] logger.info(f"Release metadata: {album['name']} by {artist['name']} ({len(result['tracks'])} tracks)") return jsonify(result) except Exception as e: logger.error(f"Error getting release metadata: {e}") import traceback logger.error(f"Full traceback: {traceback.format_exc()}") return jsonify({"success": False, "error": str(e)}), 500 # Active enrichment tasks — progress tracked here, polled by frontend _enrichment_tasks = {} # enrichment_id -> {completed, total, current_track, done, tracks, error} _enrichment_tasks_lock = threading.Lock() @app.route('/api/beatport/enrich-tracks', methods=['POST']) def enrich_beatport_tracks(): """Start Beatport track enrichment. Returns immediately; poll /enrich-progress for updates.""" try: data = request.get_json() if not data: return jsonify({"success": False, "error": "No JSON data provided"}), 400 tracks = data.get('tracks', []) if not tracks: return jsonify({"success": False, "error": "No tracks provided"}), 400 enrichment_id = data.get('enrichment_id', str(uuid.uuid4())) logger.info(f"Enriching {len(tracks)} Beatport tracks with per-track metadata (id: {enrichment_id})") # --- Check enrichment cache (fast, do before spawning background) --- cached_results = {} uncached_tracks = [] uncached_indices = [] mcache = get_metadata_cache() for i, track in enumerate(tracks): url = track.get('url') or track.get('track_url') or '' if url: cached = mcache.get_entity('beatport', 'track', url) if cached: cached_results[i] = cached continue uncached_tracks.append(track) uncached_indices.append(i) cache_hits = len(cached_results) cache_misses = len(uncached_tracks) logger.info(f"Enrichment cache: {cache_hits} hits, {cache_misses} misses") # All cached — return immediately (no background task needed) if cache_misses == 0: merged = [None] * len(tracks) for idx, d in cached_results.items(): merged[idx] = d for i in range(len(merged)): if merged[i] is None: merged[i] = tracks[i] return jsonify({"success": True, "tracks": merged}) # --- Initialize progress tracker and start background task --- with _enrichment_tasks_lock: _enrichment_tasks[enrichment_id] = { 'completed': cache_hits, 'total': len(tracks), 'current_track': f'{cache_hits} tracks (cached)' if cache_hits > 0 else '', 'done': False, 'tracks': None, 'error': None, } def _run_enrichment(): try: def on_progress(completed, total, track_name): new_completed = cache_hits + completed with _enrichment_tasks_lock: task = _enrichment_tasks.get(enrichment_id) if task: task['completed'] = new_completed task['current_track'] = track_name else: logger.warning(f"on_progress: task {enrichment_id} not found in _enrichment_tasks!") scraper = BeatportUnifiedScraper() newly_enriched = scraper.enrich_chart_tracks(uncached_tracks, progress_callback=on_progress) # Clean and cache for track in newly_enriched: if track.get('title'): track['title'] = clean_beatport_text(track['title']) if track.get('artist'): track['artist'] = clean_beatport_text(track['artist']) if track.get('release_name'): track['release_name'] = clean_beatport_text(track['release_name']) if track.get('label'): track['label'] = clean_beatport_text(track['label']) url = track.get('url') or track.get('track_url') or '' if url: mcache.store_entity('beatport', 'track', url, track) # Merge in original order merged = [None] * len(tracks) for idx, d in cached_results.items(): merged[idx] = d for j, idx in enumerate(uncached_indices): if j < len(newly_enriched): merged[idx] = newly_enriched[j] for i in range(len(merged)): if merged[i] is None: merged[i] = tracks[i] logger.info(f"Enriched {len(merged)} tracks ({cache_hits} cached, {cache_misses} scraped)") with _enrichment_tasks_lock: task = _enrichment_tasks.get(enrichment_id) if task: task['done'] = True task['tracks'] = merged task['completed'] = len(tracks) except Exception as e: logger.error(f"Error enriching tracks: {e}") import traceback logger.error(f"Full traceback: {traceback.format_exc()}") with _enrichment_tasks_lock: task = _enrichment_tasks.get(enrichment_id) if task: task['done'] = True task['error'] = str(e) task['tracks'] = tracks # Return originals as fallback threading.Thread(target=_run_enrichment, daemon=True).start() return jsonify({"success": True, "enrichment_id": enrichment_id, "async": True}) except Exception as e: logger.error(f"Error starting enrichment: {e}") import traceback logger.error(f"Full traceback: {traceback.format_exc()}") return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/beatport/enrich-progress/', methods=['GET']) def get_enrichment_progress(enrichment_id): """Poll enrichment progress. Returns current state; includes tracks when done.""" with _enrichment_tasks_lock: task = _enrichment_tasks.get(enrichment_id) if not task: return jsonify({"success": False, "error": "Unknown enrichment ID"}), 404 result = { 'success': True, 'completed': task['completed'], 'total': task['total'], 'current_track': task['current_track'], 'done': task['done'], } if task['done']: result['tracks'] = task['tracks'] result['error'] = task['error'] # Clean up — task is finished del _enrichment_tasks[enrichment_id] resp = jsonify(result) resp.headers['Cache-Control'] = 'no-store' return resp @app.route('/api/beatport/homepage/featured-charts', methods=['GET']) def get_beatport_homepage_featured_charts(): """Get Beatport Featured Charts from homepage section""" try: limit = int(request.args.get('limit', 20)) logger.info(f"API request for Beatport homepage Featured Charts (limit: {limit})") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Get featured charts from homepage featured_charts = scraper.scrape_featured_charts(limit=limit) logger.info(f"Successfully extracted {len(featured_charts)} featured charts from homepage") return jsonify({ "success": True, "tracks": featured_charts, "track_count": len(featured_charts), "source": "beatport_homepage_featured_charts" }) except Exception as e: logger.error(f"Error getting Beatport homepage featured charts: {e}") return jsonify({ "success": False, "error": str(e), "tracks": [], "track_count": 0 }), 500 @app.route('/api/beatport/chart-sections', methods=['GET']) def get_beatport_chart_sections(): """Get dynamically discovered Beatport chart sections""" try: logger.info("API request for Beatport chart sections discovery") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Discover chart sections dynamically chart_sections = scraper.discover_chart_sections() logger.info("Successfully discovered chart sections") return jsonify({ "success": True, "chart_sections": chart_sections, "summary": chart_sections.get('summary', {}) }) except Exception as e: logger.error(f"Error discovering Beatport chart sections: {e}") return jsonify({ "success": False, "error": str(e), "chart_sections": {}, "summary": {} }), 500 @app.route('/api/beatport/dj-charts-improved', methods=['GET']) def get_beatport_dj_charts_improved(): """Get Beatport DJ Charts using improved method""" try: logger.info("API request for Beatport DJ Charts (improved)") # Initialize the Beatport scraper scraper = BeatportUnifiedScraper() # Get query parameters limit = int(request.args.get('limit', '20')) # Scrape DJ Charts using improved method charts = scraper.scrape_dj_charts(limit=limit) logger.info(f"Successfully scraped {len(charts)} DJ charts") return jsonify({ "success": True, "charts": charts, "chart_name": "Beatport DJ Charts", "count": len(charts) }) except Exception as e: logger.error(f"Error fetching Beatport DJ Charts: {e}") return jsonify({ "success": False, "error": str(e), "charts": [], "count": 0 }), 500 @app.route('/api/beatport/hype-picks') def get_beatport_hype_picks(): """Get Beatport Hype Picks for the rebuild slider grid (EXACT same pattern as new-releases)""" try: logger.info("Fetching Beatport hype picks...") # Check cache first cached_data = get_cached_beatport_data('homepage', 'hype_picks') if cached_data: logger.info("Returning cached hype picks data") response = jsonify(cached_data) return add_cache_headers(response, 3600) # 1 hour # Cache miss - scrape fresh data logger.info("Cache miss - scraping fresh hype picks data...") # Initialize scraper scraper = BeatportUnifiedScraper() # Get page and extract releases soup = scraper.get_page(scraper.base_url) if not soup: raise Exception("Could not fetch Beatport homepage") # Extract hype pick cards using data-testid selector (equivalent to new-releases CSS selector) hype_pick_cards = soup.select('[data-testid="hype-picks"]') releases = [] logger.info(f"Found {len(hype_pick_cards)} hype pick cards") for _i, card in enumerate(hype_pick_cards[:100]): # Limit to 100 for 10 slides (same as new-releases) release_data = {} # Extract title (exact same logic as new-releases) title_elem = card.select_one('[class*="title"], [class*="Title"], h1, h2, h3, h4, h5, h6') if title_elem: title_text = title_elem.get_text(strip=True) if title_text and len(title_text) > 2 and title_text not in ['Hype Picks', 'Buy', 'Play']: release_data['title'] = title_text # Extract artist (exact same logic as new-releases) artist_elem = card.select_one('[class*="artist"], [class*="Artist"], a[href*="/artist/"]') if artist_elem: artist_text = artist_elem.get_text(strip=True) if artist_text and len(artist_text) > 1: release_data['artist'] = artist_text # Extract label (exact same logic as new-releases) label_elem = card.select_one('[class*="label"], [class*="Label"], a[href*="/label/"]') if label_elem: label_text = label_elem.get_text(strip=True) if label_text and len(label_text) > 1: release_data['label'] = label_text # Extract URL (exact same logic as new-releases) url_link = card.select_one('a[href*="/release/"]') if url_link: href = url_link.get('href') if href: release_data['url'] = urljoin(scraper.base_url, href) # Extract image (exact same logic as new-releases) img = card.select_one('img') if img: src = img.get('src') or img.get('data-src') or img.get('data-lazy-src') if src: release_data['image_url'] = src # URL fallback for title (exact same logic as new-releases) if not release_data.get('title') and release_data.get('url'): url_parts = release_data['url'].split('/release/') if len(url_parts) > 1: slug = url_parts[1].split('/')[0] release_data['title'] = slug.replace('-', ' ').title() # Only add if we have essential data (exact same logic as new-releases) if release_data.get('title') and release_data.get('url'): # Add fallbacks for missing data (exact same logic as new-releases) if not release_data.get('artist'): release_data['artist'] = 'Various Artists' if not release_data.get('label'): release_data['label'] = 'Unknown Label' releases.append(release_data) logger.info(f"Successfully extracted {len(releases)} hype picks") # Prepare response data response_data = { 'success': True, 'releases': releases, 'count': len(releases), 'slides': (len(releases) + 9) // 10, # Calculate number of slides needed (same as new-releases) 'timestamp': datetime.now().isoformat() } # Cache the successful response set_cached_beatport_data('homepage', 'hype_picks', response_data) response = jsonify(response_data) return add_cache_headers(response, 3600) # 1 hour except Exception as e: logger.error(f"Error getting Beatport hype picks: {e}") return jsonify({ 'success': False, 'error': str(e), 'releases': [], 'count': 0 }), 500 @app.route('/api/beatport/discovery/start/', methods=['POST']) def start_beatport_discovery(url_hash): """Start Spotify discovery for Beatport chart tracks""" import json try: logger.info(f"Starting Beatport discovery for: {url_hash}") # Get chart data from request body data = request.get_json() or {} logger.debug(f"Raw request data: {data}") chart_data = data.get('chart_data') logger.debug(f"Chart data extracted: {chart_data is not None}") # Debug logging if chart_data: logger.debug(f"Chart data keys: {list(chart_data.keys()) if isinstance(chart_data, dict) else 'Not a dict'}") logger.debug(f"Chart name: {chart_data.get('name') if isinstance(chart_data, dict) else 'N/A'}") if isinstance(chart_data, dict) and 'tracks' in chart_data: logger.debug(f"Number of tracks: {len(chart_data['tracks'])}") if chart_data['tracks']: logger.debug(f"First track: {chart_data['tracks'][0]}") else: logger.warning("No chart data received") if not chart_data or not chart_data.get('tracks'): return jsonify({"error": "Chart data with tracks is required"}), 400 # Initialize Beatport chart state (similar to YouTube) if url_hash not in beatport_chart_states: beatport_chart_states[url_hash] = { 'chart': chart_data, 'phase': 'fresh', 'discovery_results': [], 'discovery_progress': 0, 'spotify_matches': 0, 'spotify_total': len(chart_data['tracks']), 'status': 'fresh', 'last_accessed': time.time() } state = beatport_chart_states[url_hash] state['last_accessed'] = time.time() if state['phase'] == 'discovering': return jsonify({"error": "Discovery already in progress"}), 400 # Update phase to discovering state['phase'] = 'discovering' state['status'] = 'discovering' state['discovery_progress'] = 0 state['spotify_matches'] = 0 # Add activity for discovery start chart_name = chart_data.get('name', 'Unknown Chart') track_count = len(chart_data['tracks']) add_activity_item("", "Beatport Discovery Started", f"'{chart_name}' - {track_count} tracks", "Now") # Start discovery worker (capture profile ID while we have Flask context) beatport_chart_states[url_hash]['_profile_id'] = get_current_profile_id() future = beatport_discovery_executor.submit(_run_beatport_discovery_worker, url_hash) state['discovery_future'] = future logger.info(f"Started Spotify discovery for Beatport chart: {chart_name}") return jsonify({"success": True, "message": "Discovery started", "status": "discovering"}) except Exception as e: logger.error(f"Error starting Beatport discovery: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/beatport/discovery/status/', methods=['GET']) def get_beatport_discovery_status(url_hash): """Get real-time discovery status for a Beatport chart""" try: if url_hash not in beatport_chart_states: return jsonify({"error": "Beatport chart not found"}), 404 state = beatport_chart_states[url_hash] state['last_accessed'] = time.time() response = { 'phase': state['phase'], 'status': state['status'], 'progress': state['discovery_progress'], 'spotify_matches': state['spotify_matches'], 'spotify_total': state['spotify_total'], 'results': state['discovery_results'], 'complete': state['phase'] == 'discovered' } return jsonify(response) except Exception as e: logger.error(f"Error getting Beatport discovery status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/beatport/discovery/update_match', methods=['POST']) def update_beatport_discovery_match(): """Update a Beatport discovery result with manually selected Spotify track""" try: data = request.get_json() identifier = data.get('identifier') # url_hash track_index = data.get('track_index') spotify_track = data.get('spotify_track') if not identifier or track_index is None or not spotify_track: return jsonify({'error': 'Missing required fields'}), 400 # Get the state state = beatport_chart_states.get(identifier) if not state: return jsonify({'error': 'Discovery state not found'}), 404 if track_index >= len(state['discovery_results']): return jsonify({'error': 'Invalid track index'}), 400 # Update the result result = state['discovery_results'][track_index] old_status = result.get('status') # Update with user-selected track result['status'] = 'Found' result['status_class'] = 'found' result['spotify_track'] = spotify_track['name'] result['spotify_artist'] = _join_artist_names(spotify_track['artists']) if isinstance(spotify_track['artists'], list) else _extract_artist_name(spotify_track['artists']) result['spotify_album'] = spotify_track['album'] result['spotify_id'] = spotify_track['id'] # Format duration (Beatport doesn't show duration in table, but store it anyway) duration_ms = spotify_track.get('duration_ms', 0) if duration_ms: minutes = duration_ms // 60000 seconds = (duration_ms % 60000) // 1000 result['duration'] = f"{minutes}:{seconds:02d}" else: result['duration'] = '0:00' # IMPORTANT: Also set spotify_data for sync/download compatibility. # Manual match from the fix modal — build a rich spotify_data (album # as dict with image info) matching the normal discovery shape, and # explicitly clear any prior wing-it flag since the user picked a # real metadata match. result['spotify_data'] = _build_fix_modal_spotify_data(spotify_track) result['wing_it_fallback'] = False result['manual_match'] = True # Flag for tracking # Update match count if status changed from not found/error if old_status != 'found' and old_status != 'Found': state['spotify_matches'] = state.get('spotify_matches', 0) + 1 logger.info(f"Manual match updated: beatport - {identifier} - track {track_index}") logger.info(f" → {result['spotify_artist']} - {result['spotify_track']}") return jsonify({'success': True, 'result': result}) except Exception as e: logger.error(f"Error updating Beatport discovery match: {e}") return jsonify({'error': str(e)}), 500 def clean_beatport_text(text): """Clean Beatport track/artist text for proper spacing""" if not text: return text import re # Fix common spacing issues text = re.sub(r'([a-z$!@#%&*])([A-Z])', r'\1 \2', text) # Add space between lowercase/symbols and uppercase text = re.sub(r'([a-zA-Z]),([a-zA-Z])', r'\1, \2', text) # Add space after comma text = re.sub(r'([a-zA-Z])(Mix|Remix|Extended|Version)\b', r'\1 \2', text) # Fix mix types text = re.sub(r'\s+', ' ', text) # Collapse multiple spaces text = text.strip() return text # Beatport discovery worker logic lives in core/discovery/beatport.py. from core.discovery import beatport as _discovery_beatport def _build_beatport_discovery_deps(): """Build the BeatportDiscoveryDeps bundle from web_server.py globals on each call.""" return _discovery_beatport.BeatportDiscoveryDeps( beatport_chart_states=beatport_chart_states, spotify_client=spotify_client, matching_engine=matching_engine, pause_enrichment_workers=_pause_enrichment_workers, resume_enrichment_workers=_resume_enrichment_workers, get_active_discovery_source=_get_active_discovery_source, get_metadata_fallback_client=_get_metadata_fallback_client, clean_beatport_text=clean_beatport_text, get_discovery_cache_key=_get_discovery_cache_key, get_database=get_database, validate_discovery_cache_artist=_validate_discovery_cache_artist, spotify_rate_limited=_spotify_rate_limited, discovery_score_candidates=_discovery_score_candidates, get_metadata_cache=get_metadata_cache, build_discovery_wing_it_stub=_build_discovery_wing_it_stub, add_activity_item=add_activity_item, sync_discovery_results_to_mirrored=_sync_discovery_results_to_mirrored, ) def _run_beatport_discovery_worker(url_hash): return _discovery_beatport.run_beatport_discovery_worker( url_hash, _build_beatport_discovery_deps() ) @app.route('/api/beatport/sync/start/', methods=['POST']) def start_beatport_sync(url_hash): """Start sync process for a Beatport chart using discovered Spotify tracks""" try: logger.info(f"Beatport sync start requested for: {url_hash}") if url_hash not in beatport_chart_states: logger.warning(f"Beatport chart not found: {url_hash}") return jsonify({"error": "Beatport chart not found"}), 404 state = beatport_chart_states[url_hash] state['last_accessed'] = time.time() # Update access time logger.info(f"Beatport chart state: phase={state.get('phase')}, has_discovery_results={len(state.get('discovery_results', []))}") if state['phase'] not in ['discovered', 'sync_complete', 'download_complete']: logger.info(f"Beatport chart not ready for sync: {state['phase']}") return jsonify({"error": "Beatport chart not ready for sync"}), 400 # Convert discovery results to Spotify tracks format spotify_tracks = convert_beatport_results_to_spotify_tracks(state['discovery_results']) if not spotify_tracks: return jsonify({"error": "No Spotify matches found for sync"}), 400 # Create a temporary playlist ID for sync tracking sync_playlist_id = f"beatport_sync_{url_hash}_{int(time.time())}" # Initialize sync state state['sync_playlist_id'] = sync_playlist_id state['phase'] = 'syncing' state['sync_progress'] = {'status': 'starting', 'progress': 0} # Create sync job using existing infrastructure sync_data = { 'id': sync_playlist_id, 'name': state['chart']['name'], 'tracks': spotify_tracks, 'source': 'beatport', 'source_id': url_hash } # Add to sync states using existing sync system with sync_lock: sync_states[sync_playlist_id] = {"status": "starting", "progress": {}} # Start sync in background using existing thread pool future = sync_executor.submit(_run_sync_task, sync_playlist_id, sync_data['name'], spotify_tracks, None, get_current_profile_id()) state['sync_future'] = future logger.info(f"Started Beatport sync for chart: {state['chart']['name']}") return jsonify({"success": True, "sync_id": sync_playlist_id}) except Exception as e: logger.error(f"Error starting Beatport sync: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/beatport/sync/status/', methods=['GET']) def get_beatport_sync_status(url_hash): """Get sync status for a Beatport chart""" try: if url_hash not in beatport_chart_states: return jsonify({"error": "Beatport chart not found"}), 404 state = beatport_chart_states[url_hash] state['last_accessed'] = time.time() # Update access time sync_playlist_id = state.get('sync_playlist_id') if not sync_playlist_id: return jsonify({"error": "No sync process found"}), 404 # Get sync status from sync states sync_state = sync_states.get(sync_playlist_id, {}) response = { 'status': sync_state.get('status', 'unknown'), 'progress': sync_state.get('progress', {}), 'sync_id': sync_playlist_id, 'complete': sync_state.get('status') == 'finished', 'error': sync_state.get('error') } # Check if sync completed successfully if sync_state.get('status') == 'finished': state['phase'] = 'sync_complete' # Extract playlist ID from sync result result = sync_state.get('result', {}) state['converted_spotify_playlist_id'] = result.get('spotify_playlist_id') chart_name = state.get('chart', {}).get('name', 'Unknown Chart') add_activity_item("", "Sync Complete", f"Beatport chart '{chart_name}' synced successfully", "Now") elif sync_state.get('status') == 'error': state['phase'] = 'discovered' # Revert on error chart_name = state.get('chart', {}).get('name', 'Unknown Chart') add_activity_item("", "Sync Failed", f"Beatport chart '{chart_name}' sync failed", "Now") return jsonify(response) except Exception as e: logger.error(f"Error getting Beatport sync status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/beatport/sync/cancel/', methods=['POST']) def cancel_beatport_sync(url_hash): """Cancel sync for a Beatport chart""" try: if url_hash not in beatport_chart_states: return jsonify({"error": "Beatport chart not found"}), 404 state = beatport_chart_states[url_hash] state['last_accessed'] = time.time() # Update access time sync_playlist_id = state.get('sync_playlist_id') if sync_playlist_id and sync_playlist_id in sync_states: # Cancel the sync using existing sync infrastructure with sync_lock: sync_states[sync_playlist_id] = {"status": "cancelled"} # Cancel future if still running if 'sync_future' in state and state['sync_future']: state['sync_future'].cancel() # Revert Beatport state state['phase'] = 'discovered' state['sync_playlist_id'] = None state['sync_progress'] = {} logger.warning(f"Cancelled Beatport sync for: {url_hash}") return jsonify({"success": True}) except Exception as e: logger.error(f"Error cancelling Beatport sync: {e}") return jsonify({"error": str(e)}), 500 # =================================================================== # BEATPORT CHART PERSISTENCE API ENDPOINTS # =================================================================== @app.route('/api/beatport/charts', methods=['GET']) def get_beatport_charts(): """Get all persistent Beatport chart states for frontend hydration""" try: charts = [] current_time = time.time() # Clean up old charts (older than 24 hours) to_remove = [] for chart_hash, state in beatport_chart_states.items(): last_accessed = state.get('last_accessed', 0) if current_time - last_accessed > 86400: # 24 hours to_remove.append(chart_hash) else: # Include in response chart_info = { 'hash': chart_hash, 'name': state['chart']['name'], 'track_count': len(state['chart']['tracks']), 'phase': state.get('phase', 'fresh'), 'discovery_progress': state.get('discovery_progress', 0), 'spotify_matches': state.get('spotify_matches', 0), 'spotify_total': state.get('spotify_total', 0), 'converted_spotify_playlist_id': state.get('converted_spotify_playlist_id'), 'download_process_id': state.get('download_process_id'), 'last_accessed': last_accessed, 'chart_data': state['chart'] # Full chart data for restoration } charts.append(chart_info) # Remove old charts for chart_hash in to_remove: del beatport_chart_states[chart_hash] logger.info(f"Cleaned up old Beatport chart: {chart_hash}") logger.info(f"Returning {len(charts)} Beatport charts for hydration") return jsonify(charts) except Exception as e: logger.error(f"Error getting Beatport charts: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/beatport/charts/status/', methods=['GET']) def get_beatport_chart_status(chart_hash): """Get individual Beatport chart status with full state data""" try: if chart_hash not in beatport_chart_states: return jsonify({"error": "Beatport chart not found"}), 404 state = beatport_chart_states[chart_hash] state['last_accessed'] = time.time() # Update access time # Return full state including discovery results for modal restoration response = { 'hash': chart_hash, 'phase': state.get('phase', 'fresh'), 'status': state.get('status', 'fresh'), 'discovery_progress': state.get('discovery_progress', 0), 'spotify_matches': state.get('spotify_matches', 0), 'spotify_total': state.get('spotify_total', 0), 'discovery_results': state.get('discovery_results', []), 'converted_spotify_playlist_id': state.get('converted_spotify_playlist_id'), 'download_process_id': state.get('download_process_id'), 'sync_playlist_id': state.get('sync_playlist_id'), 'sync_progress': state.get('sync_progress', {}), 'chart_data': state['chart'] # Full chart data } return jsonify(response) except Exception as e: logger.error(f"Error getting Beatport chart status: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/beatport/charts/update-phase/', methods=['POST']) def update_beatport_chart_phase(chart_hash): """Update Beatport chart phase (for modal close operations and reset)""" try: if chart_hash not in beatport_chart_states: return jsonify({"error": "Beatport chart not found"}), 404 data = request.get_json() or {} new_phase = data.get('phase') is_reset = data.get('reset', False) if not new_phase: return jsonify({"error": "Phase is required"}), 400 state = beatport_chart_states[chart_hash] state['phase'] = new_phase state['last_accessed'] = time.time() # Handle reset operation - clear discovery data if is_reset and new_phase == 'fresh': state['discovery_results'] = [] state['discovery_progress'] = 0 state['spotify_matches'] = 0 state['status'] = 'fresh' state['converted_spotify_playlist_id'] = None state['download_process_id'] = None state['sync_playlist_id'] = None state['sync_progress'] = {} logger.info(f"Reset Beatport chart {chart_hash} to fresh state") else: # Handle other phase updates (like download phase transitions) converted_playlist_id = data.get('converted_spotify_playlist_id') if converted_playlist_id: state['converted_spotify_playlist_id'] = converted_playlist_id download_process_id = data.get('download_process_id') if download_process_id: state['download_process_id'] = download_process_id logger.info(f"Updated Beatport chart {chart_hash} phase to: {new_phase}") return jsonify({"success": True, "phase": new_phase}) except Exception as e: logger.error(f"Error updating Beatport chart phase: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/beatport/charts/delete/', methods=['DELETE']) def delete_beatport_chart(chart_hash): """Delete a Beatport chart from backend storage""" try: if chart_hash not in beatport_chart_states: return jsonify({"error": "Beatport chart not found"}), 404 chart_name = beatport_chart_states[chart_hash]['chart']['name'] del beatport_chart_states[chart_hash] logger.info(f"Deleted Beatport chart: {chart_name}") return jsonify({"success": True, "message": f"Deleted chart: {chart_name}"}) except Exception as e: logger.error(f"Error deleting Beatport chart: {e}") return jsonify({"error": str(e)}), 500 # ── Mirrored Playlists ──────────────────────────────────────────────── @app.route('/api/mirror-playlist', methods=['POST']) def mirror_playlist_endpoint(): """Save or update a mirrored playlist.""" try: data = request.get_json() if not data: return jsonify({"error": "No data received"}), 400 source = data.get('source') source_playlist_id = data.get('source_playlist_id') name = data.get('name') tracks = data.get('tracks', []) if not all([source, source_playlist_id, name]): return jsonify({"error": "source, source_playlist_id, and name are required"}), 400 database = get_database() profile_id = get_current_profile_id() playlist_id = database.mirror_playlist( source=source, source_playlist_id=str(source_playlist_id), name=name, tracks=tracks, profile_id=profile_id, description=data.get('description'), owner=data.get('owner'), image_url=data.get('image_url') ) if playlist_id is None: return jsonify({"error": "Failed to mirror playlist"}), 500 try: if automation_engine: automation_engine.emit('mirrored_playlist_created', { 'playlist_name': name, 'source': source, 'track_count': str(len(tracks)), }) except Exception as e: logger.debug("mirrored_playlist_created emit failed: %s", e) return jsonify({"success": True, "playlist_id": playlist_id}) except Exception as e: logger.error(f"Error mirroring playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/mirrored-playlists', methods=['GET']) def get_mirrored_playlists_endpoint(): """List all mirrored playlists for the active profile.""" try: database = get_database() profile_id = get_current_profile_id() playlists = database.get_mirrored_playlists(profile_id=profile_id) for pl in playlists: counts = database.get_mirrored_playlist_status_counts(pl['id']) pl['discovered_count'] = counts['discovered'] pl['total_count'] = counts['total'] pl['wishlisted_count'] = counts['wishlisted'] pl['in_library_count'] = counts['in_library'] return jsonify(playlists) except Exception as e: logger.error(f"Error getting mirrored playlists: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/mirrored-playlists/', methods=['GET']) def get_mirrored_playlist_endpoint(playlist_id): """Get a mirrored playlist with its tracks.""" try: database = get_database() playlist = database.get_mirrored_playlist(playlist_id) if not playlist: return jsonify({"error": "Playlist not found"}), 404 playlist['tracks'] = database.get_mirrored_playlist_tracks(playlist_id) return jsonify(playlist) except Exception as e: logger.error(f"Error getting mirrored playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/mirrored-playlists/', methods=['DELETE']) def delete_mirrored_playlist_endpoint(playlist_id): """Delete a mirrored playlist.""" try: database = get_database() if database.delete_mirrored_playlist(playlist_id): return jsonify({"success": True}) return jsonify({"error": "Playlist not found"}), 404 except Exception as e: logger.error(f"Error deleting mirrored playlist: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/mirrored-playlists//clear-discovery', methods=['POST']) def clear_mirrored_discovery_endpoint(playlist_id): """Clear discovery data for all tracks in a mirrored playlist, including discovery cache.""" try: database = get_database() # Clear discovery cache entries for these tracks so re-discovery does fresh lookups try: tracks = database.get_mirrored_playlist_tracks(playlist_id) if tracks: conn = database._get_connection() cursor = conn.cursor() for t in tracks: cache_key = _get_discovery_cache_key(t.get('track_name', ''), t.get('artist_name', '')) cursor.execute( "DELETE FROM discovery_match_cache WHERE normalized_title = ? AND normalized_artist = ?", (cache_key[0], cache_key[1]) ) conn.commit() logger.info(f"Cleared discovery cache for {len(tracks)} tracks in playlist {playlist_id}") except Exception as cache_err: logger.warning(f"Error clearing discovery cache: {cache_err}") cleared = database.clear_mirrored_playlist_discovery(playlist_id) return jsonify({"success": True, "cleared": cleared}) except Exception as e: logger.error(f"Error clearing mirrored discovery: {e}") return jsonify({"error": str(e)}), 500 # ==================== Discovery Pool ==================== @app.route('/api/discovery-pool', methods=['GET']) def get_discovery_pool(): """List matched and failed discovery tracks, optionally filtered by playlist.""" try: database = get_database() profile_id = get_current_profile_id() playlist_id = request.args.get('playlist_id', type=int) matched = database.get_discovery_pool_matched() failed = database.get_discovery_pool_failed(profile_id=profile_id, playlist_id=playlist_id) stats = database.get_discovery_pool_stats(profile_id=profile_id) # Playlist list for the filter dropdown playlists = database.get_mirrored_playlists(profile_id=profile_id) playlist_options = [{'id': p['id'], 'name': p['name']} for p in playlists] return jsonify({ 'matched': matched, 'failed': failed, 'stats': stats, 'playlists': playlist_options, }) except Exception as e: logger.error(f"Error getting discovery pool: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/discovery-pool/fix', methods=['POST']) def fix_discovery_pool_track(): """Manually fix a failed discovery by linking a mirrored track to a Spotify/iTunes result.""" try: data = request.get_json() track_id = data.get('track_id') spotify_track = data.get('spotify_track') if not track_id or not spotify_track: return jsonify({"error": "track_id and spotify_track required"}), 400 database = get_database() # Build matched_data in the same format as the discovery flow artists = spotify_track.get('artists', []) album_raw = spotify_track.get('album', '') image_url = spotify_track.get('image_url', '') if not image_url and isinstance(album_raw, dict): images = album_raw.get('images', []) image_url = images[0].get('url', '') if images else '' # Ensure album carries the artwork too — download pipeline checks # album.images / album.image_url when extracting cover art. if isinstance(album_raw, dict): album_obj = dict(album_raw) if image_url and not album_obj.get('image_url'): album_obj['image_url'] = image_url if image_url and not album_obj.get('images'): album_obj['images'] = [{'url': image_url}] else: album_obj = {'name': album_raw or ''} if image_url: album_obj['image_url'] = image_url album_obj['images'] = [{'url': image_url}] matched_data = { 'id': spotify_track.get('id', ''), 'name': spotify_track.get('name', ''), 'artists': [{'name': a} if isinstance(a, str) else a for a in artists], 'album': album_obj, 'duration_ms': spotify_track.get('duration_ms', 0), 'image_url': image_url, 'source': 'spotify', } # Update the mirrored track's extra_data extra_data = { 'discovered': True, 'provider': 'spotify', 'confidence': 1.0, 'matched_data': matched_data, 'manual_match': True, } database.update_mirrored_track_extra_data(track_id, extra_data) # Also save to discovery cache so future discoveries hit the cache # Need to get the track's original name/artist for the cache key try: conn = database._get_connection() cursor = conn.cursor() cursor.execute("SELECT track_name, artist_name FROM mirrored_playlist_tracks WHERE id = ?", (track_id,)) row = cursor.fetchone() if row: cache_key = _get_discovery_cache_key(row['track_name'], row['artist_name']) database.save_discovery_cache_match( cache_key[0], cache_key[1], _get_active_discovery_source(), 1.0, matched_data, row['track_name'], row['artist_name'] ) except Exception as e: logger.debug("discovery cache match save failed: %s", e) return jsonify({"success": True}) except Exception as e: logger.error(f"Error fixing discovery pool track: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/discovery-pool/cache/', methods=['DELETE']) def delete_discovery_pool_cache_entry(entry_id): """Remove a single entry from the discovery match cache.""" try: database = get_database() if database.delete_discovery_cache_entry(entry_id): return jsonify({"success": True}) return jsonify({"error": "Entry not found"}), 404 except Exception as e: logger.error(f"Error deleting discovery cache entry: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/discovery-pool/rematch', methods=['POST']) def rematch_discovery_pool_track(): """Replace a discovery cache entry with a new match chosen by the user.""" try: data = request.get_json() cache_id = data.get('cache_id') original_title = (data.get('original_title') or '').strip() original_artist = (data.get('original_artist') or '').strip() spotify_track = data.get('spotify_track') if not cache_id: return jsonify({"error": "cache_id required"}), 400 database = get_database() # If no spotify_track provided, just delete the cache entry (phase 1 of rematch) if not spotify_track: database.delete_discovery_cache_entry(cache_id) return jsonify({"success": True, "action": "cache_cleared"}) # spotify_track provided — delete old cache and save new match (phase 2) database.delete_discovery_cache_entry(cache_id) # Build cache entry in same format as discovery flow artists = spotify_track.get('artists', []) album_raw = spotify_track.get('album', '') album_obj = album_raw if isinstance(album_raw, dict) else {'name': album_raw or ''} image_url = spotify_track.get('image_url', '') if not image_url and isinstance(album_raw, dict): images = album_raw.get('images', []) image_url = images[0].get('url', '') if images else '' matched_data = { 'id': spotify_track.get('id', ''), 'name': spotify_track.get('name', ''), 'artists': [{'name': a} if isinstance(a, str) else a for a in artists], 'album': album_obj, 'duration_ms': spotify_track.get('duration_ms', 0), 'image_url': image_url, 'source': 'spotify', } # Save to discovery cache normalized_title = matching_engine.normalize_string(original_title) if original_title else '' normalized_artist = matching_engine.normalize_string(original_artist) if original_artist else '' database.save_discovery_cache_match( normalized_title=normalized_title, normalized_artist=normalized_artist, provider='spotify', confidence=1.0, matched_data=matched_data, original_title=original_title, original_artist=original_artist, ) return jsonify({"success": True, "action": "rematched", "name": spotify_track.get('name', '')}) except Exception as e: logger.error(f"Error in discovery pool rematch: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/mirrored-playlists//prepare-discovery', methods=['POST']) def prepare_mirrored_discovery(playlist_id): """Register a mirrored playlist into youtube_playlist_states so the YouTube discovery pipeline can run.""" try: database = get_database() playlist = database.get_mirrored_playlist(playlist_id) if not playlist: return jsonify({"error": "Playlist not found"}), 404 tracks_data = database.get_mirrored_playlist_tracks(playlist_id) url_hash = f"mirrored_{playlist_id}" # Build track list in the format the YouTube discovery worker expects tracks = [] for t in tracks_data: # Parse extra_data if present extra = None if t.get('extra_data'): try: extra = json.loads(t['extra_data']) if isinstance(t['extra_data'], str) else t['extra_data'] except (json.JSONDecodeError, TypeError): pass tracks.append({ 'id': t.get('source_track_id') or f"mirrored_{t['id']}", 'db_track_id': t['id'], 'name': t['track_name'], 'artists': [t['artist_name']], 'album': t.get('album_name', ''), 'duration_ms': t.get('duration_ms', 0), 'extra_data': extra, }) # Determine current active metadata source for provider-mismatch detection _current_provider = _get_active_discovery_source() _use_spotify = (_current_provider == 'spotify') and spotify_client and spotify_client.is_spotify_authenticated() # Check for cached discovery results in extra_data pre_discovered_results = [] pre_discovered_count = 0 has_pending = False for idx, track in enumerate(tracks): extra = track.get('extra_data') if extra and extra.get('discovered'): cached_provider = extra.get('provider', 'spotify') # If the cached result was discovered by a different provider than the # currently active one, treat it as pending so re-discovery uses the # correct source (IDs, album data, images differ between providers). if cached_provider != _current_provider: has_pending = True dur = track.get('duration_ms', 0) pre_discovered_results.append({ 'index': idx, 'yt_track': track['name'], 'yt_artist': track['artists'][0] if track['artists'] else 'Unknown', 'status': 'Provider changed', 'status_class': 'not-found', 'spotify_track': '', 'spotify_artist': '', 'spotify_album': '', 'duration': f"{int(dur) // 60000}:{(int(dur) % 60000) // 1000:02d}" if dur else '0:00', 'confidence': 0, }) continue # Previously found match — provider matches current source matched = extra.get('matched_data', {}) artists_raw = matched.get('artists', []) if artists_raw and isinstance(artists_raw[0], dict): artist_str = ', '.join(a.get('name', '') for a in artists_raw) else: artist_str = ', '.join(str(a) for a in artists_raw) if artists_raw else '' album_raw = matched.get('album', '') album_str = album_raw.get('name', '') if isinstance(album_raw, dict) else (str(album_raw) if album_raw else '') dur = track.get('duration_ms', 0) result = { 'index': idx, 'yt_track': track['name'], 'yt_artist': track['artists'][0] if track['artists'] else 'Unknown', 'status': 'Found', 'status_class': 'found', 'spotify_track': matched.get('name', ''), 'spotify_artist': artist_str, 'spotify_album': album_str, 'duration': f"{int(dur) // 60000}:{(int(dur) % 60000) // 1000:02d}" if dur else '0:00', 'discovery_source': extra.get('provider', 'spotify'), 'confidence': extra.get('confidence', 0), 'matched_data': matched, 'spotify_data': matched, } if extra.get('manual_match'): result['manual_match'] = True pre_discovered_results.append(result) pre_discovered_count += 1 elif extra and extra.get('discovery_attempted'): # Previously attempted but not found — also retry if provider changed cached_provider = extra.get('provider', 'spotify') if cached_provider != _current_provider: has_pending = True dur = track.get('duration_ms', 0) pre_discovered_results.append({ 'index': idx, 'yt_track': track['name'], 'yt_artist': track['artists'][0] if track['artists'] else 'Unknown', 'status': 'Provider changed' if cached_provider != _current_provider else 'Not Found', 'status_class': 'not-found', 'spotify_track': '', 'spotify_artist': '', 'spotify_album': '', 'duration': f"{int(dur) // 60000}:{(int(dur) % 60000) // 1000:02d}" if dur else '0:00', 'discovery_source': cached_provider, 'confidence': 0, }) elif not extra or (not extra.get('discovered') and not extra.get('discovery_attempted')): # New track — no discovery data yet has_pending = True dur = track.get('duration_ms', 0) pre_discovered_results.append({ 'index': idx, 'yt_track': track['name'], 'yt_artist': track['artists'][0] if track['artists'] else 'Unknown', 'status': '🆕 Pending', 'status_class': 'not-found', 'spotify_track': '', 'spotify_artist': '', 'spotify_album': '', 'duration': f"{int(dur) // 60000}:{(int(dur) % 60000) // 1000:02d}" if dur else '0:00', 'confidence': 0, }) # Only treat as cached if at least one track was discovered by the current provider has_cached = any( t.get('extra_data') and (t['extra_data'].get('discovered') or t['extra_data'].get('discovery_attempted')) and t['extra_data'].get('provider', 'spotify') == _current_provider for t in tracks ) playlist_data = { 'id': url_hash, 'name': playlist['name'], 'tracks': tracks, 'track_count': len(tracks), 'url': f"mirrored://{playlist['source']}/{playlist['source_playlist_id']}", 'source': playlist['source'] } youtube_playlist_states[url_hash] = { 'playlist': playlist_data, 'phase': 'discovered' if has_cached else 'fresh', 'discovery_results': pre_discovered_results if has_cached else [], 'discovery_progress': 100 if has_cached else 0, 'spotify_matches': pre_discovered_count if has_cached else 0, 'spotify_total': len(tracks), 'status': 'complete' if has_cached else 'parsed', 'url': playlist_data['url'], 'sync_playlist_id': None, 'converted_spotify_playlist_id': None, 'download_process_id': None, 'created_at': time.time(), 'last_accessed': time.time(), 'discovery_future': None, 'sync_progress': {} } logger.info(f"Prepared mirrored playlist for discovery: {playlist['name']} ({len(tracks)} tracks, cached={has_cached}, matches={pre_discovered_count})") return jsonify({ "success": True, "url_hash": url_hash, "from_cache": has_cached, "cached_matches": pre_discovered_count, "total_tracks": len(tracks), "has_pending": has_pending, }) except Exception as e: logger.error(f"Error preparing mirrored discovery: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/mirrored-playlists//retry-failed-discovery', methods=['POST']) def retry_failed_mirrored_discovery(playlist_id): """Re-run discovery only for tracks that failed or are pending in a mirrored playlist.""" try: url_hash = f"mirrored_{playlist_id}" state = youtube_playlist_states.get(url_hash) if not state: return jsonify({"error": "Discovery state not found. Run discovery first."}), 404 if state.get('phase') == 'discovering': return jsonify({"error": "Discovery already in progress"}), 400 tracks = state['playlist']['tracks'] results = state.get('discovery_results', []) # Build set of found track indices found_indices = set() kept_results = [] for r in results: if r.get('status_class') == 'found': found_indices.add(r.get('index', -1)) kept_results.append(r) already_found = len(found_indices) retry_count = len(tracks) - already_found if retry_count == 0: return jsonify({"success": True, "retry_count": 0, "already_found": already_found, "message": "All tracks already found"}) # Flag found tracks to skip, clear flag on others for i, track in enumerate(tracks): track['skip_discovery'] = (i in found_indices) # Keep only found results, remove failed/pending state['discovery_results'] = kept_results state['phase'] = 'discovering' state['status'] = 'discovering' state['discovery_progress'] = 0 # spotify_matches stays at found count (already_found) state['spotify_matches'] = already_found # Clear discovery_attempted in DB for failed tracks so they're retryable try: db = get_database() for i, track in enumerate(tracks): if i not in found_indices: db_track_id = track.get('db_track_id') if db_track_id: db.update_mirrored_track_extra_data(db_track_id, { 'discovered': False, 'discovery_attempted': False, }) except Exception as db_err: logger.error(f"Error clearing discovery_attempted in DB: {db_err}") # Submit worker future = youtube_discovery_executor.submit(_run_youtube_discovery_worker, url_hash) state['discovery_future'] = future logger.error(f"Retrying failed discovery for {url_hash}: {retry_count} tracks to retry, {already_found} already found") return jsonify({ "success": True, "retry_count": retry_count, "already_found": already_found, }) except Exception as e: logger.error(f"Error retrying failed discovery: {e}") return jsonify({"error": str(e)}), 500 @app.route('/api/mirrored-playlists/discovery-states', methods=['GET']) def get_mirrored_discovery_states(): """Return discovery states for any mirrored playlists that have active/completed discoveries.""" try: states = [] for url_hash, state in youtube_playlist_states.items(): if not url_hash.startswith('mirrored_'): continue states.append({ 'url_hash': url_hash, 'playlist_id': int(url_hash.replace('mirrored_', '')), 'playlist': state['playlist'], 'phase': state['phase'], 'status': state.get('status', ''), 'discovery_progress': state.get('discovery_progress', 0), 'spotify_matches': state.get('spotify_matches', 0), 'spotify_total': state.get('spotify_total', 0), 'discovery_results': state.get('discovery_results', []), 'converted_spotify_playlist_id': state.get('converted_spotify_playlist_id'), 'download_process_id': state.get('download_process_id'), }) return jsonify({"states": states}) except Exception as e: logger.error(f"Error getting mirrored discovery states: {e}") return jsonify({"error": str(e)}), 500 # ================================================================================================ # PLAYLIST EXPLORER # ================================================================================================ # Playlist explorer build-tree route lives in core/playlists/explorer.py. from core.playlists import explorer as _playlists_explorer def _build_playlist_explorer_deps(): """Build the PlaylistExplorerDeps bundle from web_server.py globals on each call.""" return _playlists_explorer.PlaylistExplorerDeps( request=request, flask_response=Response, flask_jsonify=jsonify, spotify_client=spotify_client, get_database=get_database, get_active_discovery_source=_get_active_discovery_source, get_metadata_fallback_client=_get_metadata_fallback_client, get_metadata_fallback_source=_get_metadata_fallback_source, get_metadata_cache=get_metadata_cache, ) @app.route('/api/playlist-explorer/build-tree', methods=['POST']) def playlist_explorer_build_tree(): return _playlists_explorer.playlist_explorer_build_tree(_build_playlist_explorer_deps()) @app.route('/api/playlist-explorer/album-tracks/', methods=['GET']) def playlist_explorer_album_tracks(album_id): """Fetch track listing for an album. Works with active metadata source. Caches results.""" try: # Determine source spotify_available = spotify_client and spotify_client.is_spotify_authenticated() source_name = 'spotify' if spotify_available else _get_metadata_fallback_source() client = spotify_client if spotify_available else _get_metadata_fallback_client() if not client: return jsonify({"success": False, "error": "No metadata source available"}), 400 # Check cache cache = get_metadata_cache() cache_key = f"album_tracks_{album_id}" if cache: cached = cache.get_entity(source_name, 'album_tracks', cache_key) if cached and isinstance(cached, dict) and cached.get('tracks'): return jsonify(cached) album_data = client.get_album(album_id) if not album_data: return jsonify({"success": False, "error": "Album not found"}), 404 tracks_raw = album_data.get('tracks', {}).get('items', []) tracks = [] for t in tracks_raw: artists = ', '.join(a.get('name', '') for a in t.get('artists', [])) tracks.append({ 'name': t.get('name', 'Unknown'), 'track_number': t.get('track_number', 0), 'disc_number': t.get('disc_number', 1), 'duration_ms': t.get('duration_ms', 0), 'artists': artists, }) result = {"success": True, "name": album_data.get('name', ''), "tracks": tracks} # Store in cache if cache and tracks: try: cache.store_entity(source_name, 'album_tracks', cache_key, result) except Exception as e: logger.debug("album_tracks cache store failed: %s", e) return jsonify(result) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 def convert_beatport_results_to_spotify_tracks(discovery_results): """Convert Beatport discovery results to Spotify tracks format for sync""" spotify_tracks = [] for result in discovery_results: # Support both data formats: spotify_data (manual fixes) and individual fields (automatic discovery) if result.get('spotify_data'): spotify_data = result['spotify_data'] # Convert artists from objects to strings if needed artists = spotify_data['artists'] if isinstance(artists, list) and len(artists) > 0: if isinstance(artists[0], dict) and 'name' in artists[0]: # Convert from [{'name': 'Artist'}] to ['Artist'] artists = [artist['name'] for artist in artists] track = { 'id': spotify_data['id'], 'name': spotify_data['name'], 'artists': artists, 'album': spotify_data['album'], 'source': 'beatport' } if spotify_data.get('track_number'): track['track_number'] = spotify_data['track_number'] if spotify_data.get('disc_number'): track['disc_number'] = spotify_data['disc_number'] spotify_tracks.append(track) elif result.get('spotify_track') and result.get('status_class') == 'found': # Build from individual fields (automatic discovery format) album_val = result.get('spotify_album', '') album_dict = album_val if isinstance(album_val, dict) else { 'name': album_val or result.get('spotify_track', 'Unknown Album'), 'album_type': 'single', 'images': [], 'release_date': '', 'total_tracks': 1, } spotify_tracks.append({ 'id': result.get('spotify_id', 'unknown'), 'name': result.get('spotify_track', 'Unknown Track'), 'artists': [result.get('spotify_artist', 'Unknown Artist')] if result.get('spotify_artist') else ['Unknown Artist'], 'album': album_dict, 'source': 'beatport' }) return spotify_tracks # Beatport download missing tracks is handled frontend-only (like YouTube) # No backend endpoint needed - uses existing download modal infrastructure # --- Docker Helper Functions --- def docker_resolve_url(url): """ Resolve localhost URLs to Docker host when running in container """ import os if os.path.exists('/.dockerenv') and 'localhost' in url: return url.replace('localhost', 'host.docker.internal') return url # --- Main Execution --- def start_oauth_callback_servers(): """Start dedicated OAuth callback servers for Spotify and Tidal""" import threading from http.server import HTTPServer, BaseHTTPRequestHandler import urllib.parse # Spotify callback server (port 8888 — for direct/local access only) _oauth_logger = get_logger("oauth_callback") class SpotifyCallbackHandler(BaseHTTPRequestHandler): def do_GET(self): try: parsed_url = urllib.parse.urlparse(self.path) # Health check at root — lets users verify the server is running if parsed_url.path == '/': self.send_response(200) self.send_header('Content-type', 'text/plain') self.end_headers() self.wfile.write(b'SoulSync Spotify OAuth callback server is running. Callback URL: /callback') return # Only process requests to /callback — ignore everything else if parsed_url.path != '/callback': self.send_response(404) self.send_header('Content-type', 'text/plain') self.end_headers() self.wfile.write(b'Not found. Spotify callback is at /callback') return query_params = urllib.parse.parse_qs(parsed_url.query) _oauth_logger.info(f"Spotify callback received: {self.path}") if 'code' in query_params: auth_code = query_params['code'][0] _oauth_logger.info(f"Received Spotify authorization code: {auth_code[:10]}...") # Manually trigger the token exchange using spotipy's auth manager try: from spotipy.oauth2 import SpotifyOAuth from config.settings import config_manager # Get Spotify config config = config_manager.get_spotify_config() configured_uri = config.get('redirect_uri', "http://127.0.0.1:8888/callback") _oauth_logger.info(f"Using redirect_uri for token exchange: {configured_uri}") # Create auth manager and exchange code for token auth_manager = SpotifyOAuth( client_id=config['client_id'], client_secret=config['client_secret'], redirect_uri=configured_uri, scope="user-library-read user-read-private playlist-read-private playlist-read-collaborative user-read-email user-follow-read", cache_path='config/.spotify_cache' ) # Extract the authorization code and exchange it for tokens token_info = auth_manager.get_access_token(auth_code) if token_info: # Reinitialize the global client with new tokens global spotify_client clear_cached_metadata_client("spotify") spotify_client = get_spotify_client() if spotify_client.is_spotify_authenticated(): # Clear rate limit ban + post-ban cooldown so Spotify is usable immediately from core.spotify_client import _clear_rate_limit _clear_rate_limit() spotify_client._invalidate_auth_cache() # Invalidate status cache so next poll picks up the new connection invalidate_metadata_status_caches() # Refresh enrichment worker's client so it picks up new auth if spotify_enrichment_worker and hasattr(spotify_enrichment_worker, 'client'): spotify_enrichment_worker.client.reload_config() spotify_enrichment_worker.client._invalidate_auth_cache() add_activity_item("", "Spotify Auth Complete", "Successfully authenticated with Spotify", "Now") self.send_response(200) self.send_header('Content-type', 'text/html') self.end_headers() self.wfile.write(_spotify_auth_result_page("You can close this window.", authenticated=True).encode("utf-8")) else: _oauth_logger.warning("Spotify token exchange succeeded but authentication validation failed") spotify_client._invalidate_auth_cache() invalidate_metadata_status_caches() add_activity_item("", "Spotify Auth Warning", "OAuth completed, but Spotify did not confirm an authenticated session", "Now") self.send_response(200) self.send_header('Content-type', 'text/html') self.end_headers() self.wfile.write(_spotify_auth_result_page( "Spotify authorization completed, but SoulSync could not confirm an authenticated Spotify session. You can close this window and try Authenticate again.", authenticated=False, ).encode("utf-8")) else: raise Exception("Failed to exchange authorization code for access token") except Exception as e: _oauth_logger.error(f"Spotify token processing error: {e}") add_activity_item("", "Spotify Auth Failed", f"Token processing failed: {str(e)}", "Now") self.send_response(400) self.send_header('Content-type', 'text/html') self.end_headers() self.wfile.write(f'

Spotify Authentication Failed

{str(e)}

'.encode()) elif 'error' in query_params: error = query_params['error'][0] _oauth_logger.error(f"Spotify OAuth error returned by Spotify: {error}") _oauth_logger.error(f"Full callback URL: {self.path}") add_activity_item("", "Spotify Auth Failed", f"Spotify returned error: {error}", "Now") self.send_response(400) self.send_header('Content-type', 'text/html') self.end_headers() self.wfile.write(f'

Spotify Authentication Failed

Spotify returned error: {error}

'.encode()) else: # No code AND no error — callback was hit without OAuth params _oauth_logger.error("Spotify callback received without OAuth parameters (no code or error)") _oauth_logger.error(f"Path: {self.path} | Query params: {query_params}") _oauth_logger.error("This usually means the redirect lost its query parameters (reverse proxy issue)") self.send_response(400) self.send_header('Content-type', 'text/html') self.end_headers() msg = ( '

Spotify Authentication Failed

' '

The callback was received but no authorization code or error was included.

' '

If you are using a reverse proxy: Your proxy may be stripping query parameters ' 'during the redirect. Try setting your Spotify redirect URI to use port 8008 instead ' '(e.g. https://yourdomain.com/callback) — the main app handles callbacks too.

' ) self.wfile.write(msg.encode()) except Exception as e: # Top-level catch-all — ensures we ALWAYS send an HTTP response. # Without this, BaseHTTPRequestHandler silently closes the connection # on unhandled exceptions, producing ERR_EMPTY_RESPONSE in the browser. _oauth_logger.error(f"Unhandled error in Spotify callback handler: {e}", exc_info=True) try: self.send_response(500) self.send_header('Content-type', 'text/html') self.end_headers() self.wfile.write(f'

Internal Server Error

{str(e)}

'.encode()) except Exception as _e: _oauth_logger.debug("oauth response write: %s", _e) def log_message(self, format, *args): pass # Suppress BaseHTTPRequestHandler access logs (we use our own logger) # Start Spotify callback server def run_spotify_server(): _env_val = os.environ.get('SOULSYNC_SPOTIFY_CALLBACK_PORT') spotify_port = int(_env_val) if _env_val else 8888 if _env_val: logger.info(f"[OAuth] SOULSYNC_SPOTIFY_CALLBACK_PORT={_env_val!r} — binding Spotify callback server on port {spotify_port}") else: logger.info(f"[OAuth] SOULSYNC_SPOTIFY_CALLBACK_PORT not set — using default port {spotify_port}") try: bind_addr = ('0.0.0.0', spotify_port) spotify_server = HTTPServer(bind_addr, SpotifyCallbackHandler) _oauth_logger.info(f"Spotify OAuth callback server listening on {bind_addr[0]}:{bind_addr[1]}") logger.info(f"Started Spotify OAuth callback server on {bind_addr[0]}:{bind_addr[1]}") spotify_server.serve_forever() except OSError as e: _oauth_logger.error(f"Failed to start Spotify callback server on port {spotify_port}: {e} — port may already be in use") logger.error(f"Failed to start Spotify callback server on port {spotify_port}: {e}") except Exception as e: _oauth_logger.error(f"Failed to start Spotify callback server: {e}") logger.error(f"Failed to start Spotify callback server: {e}") # Tidal callback server class TidalCallbackHandler(BaseHTTPRequestHandler): def do_GET(self): logger.info("TIDAL CALLBACK SERVER RECEIVED REQUEST ") parsed_url = urllib.parse.urlparse(self.path) query_params = urllib.parse.parse_qs(parsed_url.query) logger.info(f"Callback path: {self.path}") if 'code' in query_params: auth_code = query_params['code'][0] logger.info(f"Received Tidal authorization code: {auth_code[:10]}...") # Exchange the authorization code for tokens try: from core.tidal_client import TidalClient # Create a temporary client and set the stored PKCE values temp_client = TidalClient() # Restore the PKCE values from the auth request global tidal_oauth_state with tidal_oauth_lock: temp_client.code_verifier = tidal_oauth_state["code_verifier"] temp_client.code_challenge = tidal_oauth_state["code_challenge"] logger.info(f"Restored PKCE - verifier: {temp_client.code_verifier[:20] if temp_client.code_verifier else 'None'}... challenge: {temp_client.code_challenge[:20] if temp_client.code_challenge else 'None'}...") success = temp_client.fetch_token_from_code(auth_code) if success: # Reinitialize the global tidal client with new tokens global tidal_client tidal_client = TidalClient() if tidal_enrichment_worker: tidal_enrichment_worker.client = tidal_client add_activity_item("", "Tidal Auth Complete", "Successfully authenticated with Tidal", "Now") self.send_response(200) self.send_header('Content-type', 'text/html') self.end_headers() self.wfile.write(b'

Tidal Authentication Successful!

You can close this window.

') else: raise Exception("Failed to exchange authorization code for tokens") except Exception as e: logger.error(f"Tidal token processing error: {e}") add_activity_item("", "Tidal Auth Failed", f"Token processing failed: {str(e)}", "Now") self.send_response(400) self.send_header('Content-type', 'text/html') self.end_headers() self.wfile.write(f'

Tidal Authentication Failed

{str(e)}

'.encode()) else: error = query_params.get('error', ['Unknown error'])[0] logger.error(f"Tidal OAuth error: {error}") add_activity_item("", "Tidal Auth Failed", f"OAuth error: {error}", "Now") self.send_response(400) self.send_header('Content-type', 'text/html') self.end_headers() self.wfile.write(f'

Tidal Authentication Failed

{error}

'.encode()) def log_message(self, format, *args): pass # Suppress server logs def run_tidal_server(): _env_val = os.environ.get('SOULSYNC_TIDAL_CALLBACK_PORT') tidal_port = int(_env_val) if _env_val else 8889 if _env_val: logger.info(f"[OAuth] SOULSYNC_TIDAL_CALLBACK_PORT={_env_val!r} — binding Tidal callback server on port {tidal_port}") else: logger.info(f"[OAuth] SOULSYNC_TIDAL_CALLBACK_PORT not set — using default port {tidal_port}") try: tidal_server = HTTPServer(('0.0.0.0', tidal_port), TidalCallbackHandler) logger.info(f"Started Tidal OAuth callback server on port {tidal_port}") logger.info(f"Tidal server listening on all interfaces, port {tidal_port}") tidal_server.serve_forever() except Exception as e: logger.error(f"Failed to start Tidal callback server: {e}") import traceback logger.error(f"Full error: {traceback.format_exc()}") # Start both servers in background threads spotify_thread = threading.Thread(target=run_spotify_server, daemon=True) tidal_thread = threading.Thread(target=run_tidal_server, daemon=True) spotify_thread.start() tidal_thread.start() logger.info("OAuth callback servers started") # ================================================================================================ # MUSICBRAINZ ENRICHMENT - PHASE 5 WEB UI INTEGRATION # ================================================================================================ # --- MusicBrainz Worker Initialization --- mb_worker = None try: from database.music_database import MusicDatabase mb_db = MusicDatabase() mb_worker = MusicBrainzWorker( database=mb_db, app_name="SoulSync", app_version="1.0", contact_email="" ) # Start worker automatically (can be paused via UI) mb_worker.start() if config_manager.get('musicbrainz_enrichment_paused', False): mb_worker.pause() logger.info("MusicBrainz enrichment worker initialized (paused — restored from config)") else: logger.info("MusicBrainz enrichment worker initialized and started") except Exception as e: logger.error(f"MusicBrainz worker initialization failed: {e}") mb_worker = None # MusicBrainz status / pause / resume routes are now served by the # generic enrichment blueprint registered in core/enrichment/api.py # under /api/enrichment/musicbrainz/{status,pause,resume}. # ================================================================================================ # END MUSICBRAINZ INTEGRATION # ================================================================================================ # ================================================================================================ # AUDIODB ENRICHMENT - ARTIST METADATA & IMAGES # ================================================================================================ # --- AudioDB Worker Initialization --- audiodb_worker = None try: from database.music_database import MusicDatabase audiodb_db = MusicDatabase() audiodb_worker = AudioDBWorker(database=audiodb_db) audiodb_worker.start() if config_manager.get('audiodb_enrichment_paused', False): audiodb_worker.pause() logger.info("AudioDB enrichment worker initialized (paused — restored from config)") else: logger.info("AudioDB enrichment worker initialized and started") except Exception as e: logger.error(f"AudioDB worker initialization failed: {e}") audiodb_worker = None # AudioDB status / pause / resume routes are now served by the # generic enrichment blueprint at /api/enrichment/audiodb/{status,pause,resume}. # ================================================================================================ # END AUDIODB INTEGRATION # ================================================================================================ # --- Discogs Worker Initialization --- discogs_worker = None try: from core.discogs_worker import DiscogsWorker from database.music_database import MusicDatabase discogs_db = MusicDatabase() discogs_worker = DiscogsWorker(database=discogs_db) discogs_worker.start() if config_manager.get('discogs_enrichment_paused', False): discogs_worker.pause() logger.info("Discogs enrichment worker initialized (paused — restored from config)") else: logger.info("Discogs enrichment worker initialized and started") except Exception as e: logger.error(f"Discogs worker initialization failed: {e}") discogs_worker = None # Discogs status / pause / resume routes are now served by the # generic enrichment blueprint at /api/enrichment/discogs/{status,pause,resume}. # ================================================================================================ # DEEZER ENRICHMENT INTEGRATION # ================================================================================================ # --- Deezer Worker Initialization --- deezer_worker = None try: from database.music_database import MusicDatabase deezer_db = MusicDatabase() deezer_worker = DeezerWorker(database=deezer_db) deezer_worker.start() if config_manager.get('deezer_enrichment_paused', False): deezer_worker.pause() logger.info("Deezer enrichment worker initialized (paused — restored from config)") else: logger.info("Deezer enrichment worker initialized and started") except Exception as e: logger.error(f"Deezer worker initialization failed: {e}") deezer_worker = None # Deezer status / pause / resume routes are now served by the # generic enrichment blueprint at /api/enrichment/deezer/{status,pause,resume}. # ================================================================================================ # END DEEZER INTEGRATION # ================================================================================================ # ================================================================================================ # SPOTIFY ENRICHMENT INTEGRATION # ================================================================================================ # --- Spotify Worker Initialization --- # The Spotify enrichment worker calls `/v1/search` continuously to match library # tracks against Spotify's catalog. After Spotify's February 2026 API tightening # (search limit cut from 50→10, sustained-rate detection more aggressive), running # this worker when the user has chosen a non-Spotify primary metadata source # (Deezer, iTunes, Discogs, Hydrabase) generates dead API traffic that triggers # multi-hour 429 bans and disrupts the user's actual selected source. # # Gate the worker at boot: only auto-start when Spotify is the configured primary # source. Users on other sources can manually unpause the worker from settings if # they explicitly want background Spotify enrichment. spotify_enrichment_worker = None try: from core.metadata_service import get_primary_source as _get_primary_source from database.music_database import MusicDatabase spotify_enrichment_db = MusicDatabase() spotify_enrichment_worker = SpotifyWorker(database=spotify_enrichment_db) _primary = _get_primary_source() _user_paused = config_manager.get('spotify_enrichment_paused', False) if _user_paused or _primary != 'spotify': spotify_enrichment_worker.paused = True # Set BEFORE start() to prevent race condition spotify_enrichment_worker.start() if not spotify_enrichment_worker.paused: logger.info("Spotify enrichment worker initialized and started") elif _user_paused: logger.info("Spotify enrichment worker initialized (paused — restored from config)") else: logger.info(f"Spotify enrichment worker initialized (paused — primary metadata source is '{_primary}', not Spotify)") except Exception as e: logger.error(f"Spotify enrichment worker initialization failed: {e}") spotify_enrichment_worker = None # --- API Rate Monitor Endpoints --- @app.route('/api/rate-monitor/history/', methods=['GET']) def get_rate_monitor_history(service_key): """Get 24-hour minute-bucketed call history for a service. Used by the detail modal graph.""" try: from core.api_call_tracker import api_call_tracker, RATE_LIMITS history = api_call_tracker.get_24h_history(service_key) return jsonify({ 'service': service_key, 'rate_limit': RATE_LIMITS.get(service_key.split(':')[0], 60), 'history': history, }) except Exception as e: return jsonify({'error': str(e)}), 500 # Spotify status / pause / resume routes are now served by the # generic enrichment blueprint at /api/enrichment/spotify/{status,pause,resume}. # The rate-limit guard, auto-pause token cleanup, and yield-override behavior # are encoded on the EnrichmentService descriptor (see core/enrichment/services.py). # ================================================================================================ # END SPOTIFY ENRICHMENT INTEGRATION # ================================================================================================ # ================================================================================================ # ITUNES ENRICHMENT INTEGRATION # ================================================================================================ # --- iTunes Worker Initialization --- itunes_enrichment_worker = None try: from database.music_database import MusicDatabase itunes_enrichment_db = MusicDatabase() itunes_enrichment_worker = iTunesWorker(database=itunes_enrichment_db) itunes_enrichment_worker.start() if config_manager.get('itunes_enrichment_paused', False): itunes_enrichment_worker.pause() logger.info("iTunes enrichment worker initialized (paused — restored from config)") else: logger.info("iTunes enrichment worker initialized and started") except Exception as e: logger.error(f"iTunes enrichment worker initialization failed: {e}") itunes_enrichment_worker = None # iTunes status / pause / resume routes are now served by the # generic enrichment blueprint at /api/enrichment/itunes/{status,pause,resume}. # ================================================================================================ # END ITUNES ENRICHMENT INTEGRATION # ================================================================================================ # ================================================================================================ # LAST.FM ENRICHMENT WORKER # ================================================================================================ lastfm_worker = None try: from database.music_database import MusicDatabase lastfm_db = MusicDatabase() lastfm_worker = LastFMWorker(database=lastfm_db) lastfm_worker.start() if config_manager.get('lastfm_enrichment_paused', False): lastfm_worker.pause() logger.info("Last.fm enrichment worker initialized (paused — restored from config)") else: logger.info("Last.fm enrichment worker initialized and started") except Exception as e: logger.error(f"Last.fm worker initialization failed: {e}") lastfm_worker = None # Last.fm status / pause / resume routes are now served by the # generic enrichment blueprint at /api/enrichment/lastfm/{status,pause,resume}. # The auto-pause token cleanup + yield-override behavior is encoded on the # EnrichmentService descriptor (see core/enrichment/services.py). @app.route('/api/artist//lastfm-top-tracks', methods=['GET']) def get_artist_lastfm_top_tracks(artist_id): """Get top tracks for an artist from Last.fm (lazy-loaded by frontend).""" try: artist_name = request.args.get('name', '') if not artist_name: return jsonify({'success': False, 'error': 'Artist name required'}), 400 if not lastfm_worker or not lastfm_worker.client: return jsonify({'success': True, 'tracks': []}) limit = int(request.args.get('limit', 100)) tracks = lastfm_worker.client.get_artist_top_tracks(artist_name, limit=min(limit, 100)) return jsonify({'success': True, 'tracks': tracks}) except Exception as e: logger.error(f"Error fetching Last.fm top tracks: {e}") return jsonify({'success': True, 'tracks': []}) # ================================================================================================ @app.route('/api/lastfm/auth-url', methods=['GET']) def lastfm_auth_url(): """Get the Last.fm authorization URL for scrobbling.""" try: api_key = config_manager.get('lastfm.api_key', '') if not api_key: return jsonify({'success': False, 'error': 'Last.fm API key not configured'}), 400 # Build callback URL callback = request.host_url.rstrip('/') + '/api/lastfm/callback' auth_url = f"https://www.last.fm/api/auth/?api_key={api_key}&cb={callback}" return jsonify({'success': True, 'url': auth_url}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/lastfm/callback', methods=['GET']) def lastfm_callback(): """Last.fm auth callback — exchanges token for session key.""" try: token = request.args.get('token') if not token: return "Error: No token received from Last.fm", 400 api_key = config_manager.get('lastfm.api_key', '') api_secret = config_manager.get('lastfm.api_secret', '') if not api_key or not api_secret: return "Error: Last.fm API key and secret must be configured in Settings", 400 from core.lastfm_client import LastFMClient client = LastFMClient(api_key=api_key, api_secret=api_secret) session_key = client.get_session_key(token) if session_key: config_manager.set('lastfm.session_key', session_key) return """

Last.fm Scrobbling Authorized!

You can close this window and return to SoulSync.

""" else: return "Error: Failed to get session key from Last.fm. Check your API key and secret.", 400 except Exception as e: return f"Error: {e}", 500 # END LAST.FM ENRICHMENT INTEGRATION # ================================================================================================ # ================================================================================================ # GENIUS ENRICHMENT WORKER # ================================================================================================ genius_worker = None try: from database.music_database import MusicDatabase genius_db = MusicDatabase() genius_worker = GeniusWorker(database=genius_db) if config_manager.get('genius_enrichment_paused', False): genius_worker.paused = True genius_worker.start() if genius_worker.paused: logger.info("Genius enrichment worker initialized (paused — restored from config)") else: logger.info("Genius enrichment worker initialized and started") except Exception as e: logger.error(f"Genius worker initialization failed: {e}") genius_worker = None # --- Genius API Endpoints --- # Genius status / pause / resume routes are now served by the # generic enrichment blueprint at /api/enrichment/genius/{status,pause,resume}. # The auto-pause token cleanup + yield-override behavior is encoded on the # EnrichmentService descriptor (see core/enrichment/services.py). # ================================================================================================ # END GENIUS ENRICHMENT INTEGRATION # ================================================================================================ # ================================================================================================ # TIDAL ENRICHMENT WORKER # ================================================================================================ tidal_enrichment_worker = None try: from database.music_database import MusicDatabase tidal_enrich_db = MusicDatabase() tidal_enrichment_worker = TidalWorker(database=tidal_enrich_db, client=tidal_client) tidal_enrichment_worker.start() if config_manager.get('tidal_enrichment_paused', False): tidal_enrichment_worker.pause() logger.info("Tidal enrichment worker initialized (paused — restored from config)") else: logger.info("Tidal enrichment worker initialized and started") except Exception as e: logger.error(f"Tidal worker initialization failed: {e}") tidal_enrichment_worker = None # Tidal status / pause / resume routes are now served by the # generic enrichment blueprint at /api/enrichment/tidal/{status,pause,resume}. # The 'authenticated': False fallback field is encoded on the # EnrichmentService descriptor (see core/enrichment/services.py). # ================================================================================================ # QOBUZ ENRICHMENT WORKER # ================================================================================================ qobuz_enrichment_worker = None try: from database.music_database import MusicDatabase from core.qobuz_client import QobuzClient qobuz_enrich_db = MusicDatabase() qobuz_enrich_client = QobuzClient() # Separate client instance for thread safety qobuz_enrichment_worker = QobuzWorker(database=qobuz_enrich_db, client=qobuz_enrich_client) qobuz_enrichment_worker.start() if config_manager.get('qobuz_enrichment_paused', False): qobuz_enrichment_worker.pause() logger.info("Qobuz enrichment worker initialized (paused — restored from config)") else: logger.info("Qobuz enrichment worker initialized and started") except Exception as e: logger.error(f"Qobuz worker initialization failed: {e}") qobuz_enrichment_worker = None _init_service_search( spotify_worker=spotify_enrichment_worker, itunes_worker=itunes_enrichment_worker, musicbrainz_worker=mb_worker, lastfm_worker_obj=lastfm_worker, genius_worker_obj=genius_worker, tidal_worker=tidal_enrichment_worker, qobuz_worker=qobuz_enrichment_worker, discogs_worker_obj=discogs_worker, audiodb_worker_obj=audiodb_worker, ) # Qobuz status / pause / resume routes are now served by the # generic enrichment blueprint at /api/enrichment/qobuz/{status,pause,resume}. # The 'authenticated': False fallback field is encoded on the # EnrichmentService descriptor (see core/enrichment/services.py). # ================================================================================================ # END TIDAL/QOBUZ ENRICHMENT INTEGRATION # ================================================================================================ # ================================================================================================ # HYDRABASE P2P MIRROR WORKER # ================================================================================================ # --- Hydrabase Worker & Client Initialization --- hydrabase_worker = None hydrabase_client = None try: def _get_hydrabase_ws_and_lock(): return (_hydrabase_ws, _hydrabase_lock) hydrabase_worker = HydrabaseWorker(get_ws_and_lock=_get_hydrabase_ws_and_lock) hydrabase_worker.start() hydrabase_client = HydrabaseClient(get_ws_and_lock=_get_hydrabase_ws_and_lock) logger.info("Hydrabase P2P mirror worker and metadata client initialized") # Update API blueprint references if hasattr(app, 'soulsync'): app.soulsync['hydrabase_client'] = hydrabase_client app.soulsync['hydrabase_worker'] = hydrabase_worker except Exception as e: logger.error(f"Hydrabase initialization failed: {e}") hydrabase_worker = None hydrabase_client = None register_runtime_clients( hydrabase_client=hydrabase_client, dev_mode_enabled_provider=lambda: dev_mode_enabled, ) _init_connection_test( download_orchestrator_obj=download_orchestrator, qobuz_worker=qobuz_enrichment_worker, hydrabase_client_obj=hydrabase_client, docker_resolve_url_fn=docker_resolve_url, docker_resolve_path_fn=docker_resolve_path, ) _init_discovery_scoring(matching_engine_obj=matching_engine) _init_discover_hero(get_metadata_fallback_client_fn=_get_metadata_fallback_client) _init_download_validation( matching_engine_obj=matching_engine, download_orchestrator_obj=download_orchestrator, ) _init_wishlist_failed( engine=automation_engine, download_orchestrator_obj=download_orchestrator, sweep_fn=_sweep_empty_download_directories, ) _init_redownload( resolve_library_file_path_fn=_resolve_library_file_path, attempt_download_with_candidates_fn=_attempt_download_with_candidates, executor=missing_download_executor, ) _init_debug_info( soulsync_version=SOULSYNC_VERSION, direct_run=_DIRECT_RUN, status_cache=_status_cache, qobuz_worker=qobuz_enrichment_worker, download_batches_dict=download_batches, sync_states_dict=sync_states, youtube_playlist_states_dict=youtube_playlist_states, tidal_discovery_states_dict=tidal_discovery_states, download_orchestrator_obj=download_orchestrator, log_path=_log_path, log_dir=_log_dir, flask_app=app, get_database_fn=get_database, tidal_client_getter=lambda: tidal_client, ) metadata_registry.register_profile_spotify_credentials_provider( lambda profile_id: get_database().get_profile_spotify(profile_id) ) _init_download_monitor( make_context_key=_make_context_key, on_download_completed=_on_download_completed, download_track_worker=_download_track_worker, run_post_processing_worker=_run_post_processing_worker, start_next_batch_of_downloads=_start_next_batch_of_downloads, orphaned_download_keys=_orphaned_download_keys, missing_download_executor_obj=missing_download_executor, download_orchestrator_obj=download_orchestrator, ) # --- Hydrabase Auto-Reconnect --- try: _hydra_cfg = config_manager.get_hydrabase_config() if _hydra_cfg.get('auto_connect') and _hydra_cfg.get('url') and _hydra_cfg.get('api_key'): import websocket as _ws_mod _auto_ws = _ws_mod.create_connection( _hydra_cfg['url'], header={"x-api-key": _hydra_cfg['api_key']}, timeout=10 ) _hydrabase_ws = _auto_ws # Don't auto-enable dev mode — user must explicitly activate dev mode # Auto-connect just establishes the WebSocket for fallback/search tab use logger.info(f"Hydrabase auto-connected to {_hydra_cfg['url']}") except Exception as e: logger.error(f"Hydrabase auto-reconnect failed: {e}") # --- Hydrabase Worker API Endpoints --- @app.route('/api/hydrabase-worker/status', methods=['GET']) def hydrabase_worker_status(): """Get Hydrabase P2P mirror worker status for UI polling""" try: if hydrabase_worker is None: return jsonify({ 'enabled': False, 'running': False, 'paused': False, 'queue_size': 0, 'stats': {'sent': 0, 'dropped': 0, 'errors': 0} }), 200 status = hydrabase_worker.get_stats() return jsonify(status), 200 except Exception as e: logger.error(f"Error getting Hydrabase worker status: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/hydrabase-worker/pause', methods=['POST']) def hydrabase_worker_pause(): """Pause Hydrabase P2P mirror worker""" try: if hydrabase_worker is None: return jsonify({'error': 'Hydrabase worker not initialized'}), 400 hydrabase_worker.pause() logger.info("Hydrabase worker paused via UI") return jsonify({'status': 'paused'}), 200 except Exception as e: logger.error(f"Error pausing Hydrabase worker: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/hydrabase-worker/resume', methods=['POST']) def hydrabase_worker_resume(): """Resume Hydrabase P2P mirror worker""" try: if hydrabase_worker is None: return jsonify({'error': 'Hydrabase worker not initialized'}), 400 hydrabase_worker.resume() logger.info("Hydrabase worker resumed via UI") return jsonify({'status': 'running'}), 200 except Exception as e: logger.error(f"Error resuming Hydrabase worker: {e}") return jsonify({'error': str(e)}), 500 # ================================================================================================ # END HYDRABASE P2P MIRROR WORKER # ================================================================================================ # ================================================================================================ # LIBRARY REPAIR WORKER # ================================================================================================ from core.repair_worker import RepairWorker # =================================================================== # SoulID Worker — generates deterministic soul IDs for library entities # =================================================================== soulid_worker = None try: from core.soulid_worker import SoulIDWorker from database.music_database import MusicDatabase soulid_db = MusicDatabase() soulid_worker = SoulIDWorker(database=soulid_db) soulid_worker.start() logger.info("SoulID worker initialized and started") except Exception as e: logger.error(f"SoulID worker initialization failed: {e}") soulid_worker = None @app.route('/api/soulid/status', methods=['GET']) def soulid_status(): """Get SoulID worker status for UI polling.""" try: if soulid_worker is None: return jsonify({ 'enabled': False, 'running': False, 'paused': False, 'idle': False, 'current_item': None, 'stats': {} }) return jsonify(soulid_worker.get_stats()) except Exception as e: return jsonify({'error': str(e)}), 500 # =================================================================== # Listening Stats Worker — polls media servers for play data # =================================================================== listening_stats_worker = None try: from core.listening_stats_worker import ListeningStatsWorker from database.music_database import MusicDatabase listening_stats_db = MusicDatabase() listening_stats_worker = ListeningStatsWorker( database=listening_stats_db, config_manager=config_manager, media_server_engine=media_server_engine, ) listening_stats_worker.start() logger.info("Listening stats worker initialized and started") except Exception as e: logger.error(f"Listening stats worker initialization failed: {e}") listening_stats_worker = None # --- Stats API Endpoints --- # Logic lives in core/stats/queries.py — these routes are thin handlers. from core.stats import queries as _stats_queries @app.route('/api/stats/cached', methods=['GET']) def stats_cached(): """Get all pre-computed stats for a time range from cache. Instant response.""" try: time_range = request.args.get('range', '7d') data = _stats_queries.get_cached_stats(get_database(), fix_artist_image_url, time_range) return jsonify({'success': True, **data}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/stats/overview', methods=['GET']) def stats_overview(): """Get aggregate listening stats for a time range.""" try: time_range = request.args.get('range', 'all') data = _stats_queries.get_overview(get_database(), time_range) return jsonify({'success': True, **data}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/stats/top-artists', methods=['GET']) def stats_top_artists(): """Get top artists by play count.""" try: time_range = request.args.get('range', 'all') limit = int(request.args.get('limit', 10)) artists = _stats_queries.get_top_artists(get_database(), fix_artist_image_url, time_range, limit) return jsonify({'success': True, 'artists': artists}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/stats/top-albums', methods=['GET']) def stats_top_albums(): """Get top albums by play count.""" try: time_range = request.args.get('range', 'all') limit = int(request.args.get('limit', 10)) albums = _stats_queries.get_top_albums(get_database(), fix_artist_image_url, time_range, limit) return jsonify({'success': True, 'albums': albums}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/stats/top-tracks', methods=['GET']) def stats_top_tracks(): """Get top tracks by play count.""" try: time_range = request.args.get('range', 'all') limit = int(request.args.get('limit', 10)) tracks = _stats_queries.get_top_tracks(get_database(), fix_artist_image_url, time_range, limit) return jsonify({'success': True, 'tracks': tracks}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/stats/timeline', methods=['GET']) def stats_timeline(): """Get play count per time period for chart rendering.""" try: time_range = request.args.get('range', '30d') granularity = request.args.get('granularity', 'day') data = _stats_queries.get_timeline(get_database(), time_range, granularity) return jsonify({'success': True, 'timeline': data}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/stats/genres', methods=['GET']) def stats_genres(): """Get genre distribution by play count.""" try: time_range = request.args.get('range', 'all') data = _stats_queries.get_genres(get_database(), time_range) return jsonify({'success': True, 'genres': data}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/stats/library-health', methods=['GET']) def stats_library_health(): """Get library health metrics.""" try: data = _stats_queries.get_library_health(get_database()) return jsonify({'success': True, **data}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/stats/db-storage', methods=['GET']) def stats_db_storage(): """Get database storage breakdown by table.""" try: data = _stats_queries.get_db_storage(get_database()) return jsonify({'success': True, **data}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/stats/library-disk-usage', methods=['GET']) def stats_library_disk_usage(): """Library on-disk size + per-format breakdown. Reads `tracks.file_size` populated by the deep scan from data the media server already returns. Returns ``has_data: false`` on fresh installs that haven't run a deep scan since the migration — UI shows "Run a Deep Scan to populate" in that case. """ try: data = _stats_queries.get_library_disk_usage(get_database()) return jsonify({'success': True, **data}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/stats/recent', methods=['GET']) def stats_recent(): """Get recently played tracks.""" try: limit = int(request.args.get('limit', 20)) tracks = _stats_queries.get_recent_tracks(get_database(), limit) return jsonify({'success': True, 'tracks': tracks}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/stats/resolve-track', methods=['POST']) def stats_resolve_track(): """Resolve a track by title+artist to get its file_path for playback.""" try: data = request.get_json() title = data.get('title', '') artist = data.get('artist', '') if not title: return jsonify({'success': False, 'error': 'Title required'}), 400 track = _stats_queries.resolve_track(get_database(), fix_artist_image_url, title, artist) if track is None: return jsonify({'success': False, 'error': 'Track not found in library'}) return jsonify({'success': True, 'track': track}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/listening-stats/sync', methods=['POST']) def listening_stats_sync(): """Trigger an immediate listening stats poll.""" try: if not listening_stats_worker: return jsonify({'success': False, 'error': 'Listening stats worker not initialized'}), 400 _stats_queries.trigger_listening_sync(listening_stats_worker) return jsonify({'success': True, 'message': 'Sync started'}) except Exception as e: return jsonify({'success': False, 'error': str(e)}), 500 @app.route('/api/listening-stats/status', methods=['GET']) def listening_stats_status(): """Get listening stats worker status.""" try: return jsonify(_stats_queries.get_listening_status(listening_stats_worker)) except Exception as e: return jsonify({'error': str(e)}), 500 # =================================================================== # Repair Worker — Library maintenance and repair jobs # =================================================================== repair_worker = None try: from database.music_database import MusicDatabase repair_db = MusicDatabase() transfer_path = docker_resolve_path(config_manager.get('soulseek.transfer_path', './Transfer')) repair_worker = RepairWorker(database=repair_db, transfer_folder=transfer_path) repair_worker.set_config_manager(config_manager) repair_worker.set_metadata_enhancer(_enhance_file_metadata) # --- Repair Job Progress Tracking (live progress like automation cards) --- repair_job_progress_states = {} # job_id (str) -> state dict repair_job_progress_lock = threading.Lock() def _repair_job_start(job_id, display_name): with repair_job_progress_lock: repair_job_progress_states[job_id] = { 'status': 'running', 'display_name': display_name, 'progress': 0, 'phase': 'Starting...', 'current_item': '', 'processed': 0, 'total': 0, 'log': [{'type': 'info', 'text': f'Starting {display_name}'}], 'started_at': datetime.now(timezone.utc).isoformat(), 'finished_at': None, } def _repair_job_progress(job_id, **kwargs): with repair_job_progress_lock: state = repair_job_progress_states.get(job_id) if not state: return for k, v in kwargs.items(): if k == 'log_line': state['log'].append({'type': kwargs.get('log_type', 'info'), 'text': v}) if len(state['log']) > 50: state['log'] = state['log'][-50:] elif k == 'scanned': state['processed'] = v if state.get('total', 0) > 0: state['progress'] = round(v / state['total'] * 100) elif k == 'total': state['total'] = v if state.get('processed', 0) > 0 and v > 0: state['progress'] = round(state['processed'] / v * 100) elif k != 'log_type': state[k] = v def _repair_job_finish(job_id, status, result): with repair_job_progress_lock: state = repair_job_progress_states.get(job_id) if not state: return state['status'] = status state['progress'] = 100 state['finished_at'] = datetime.now(timezone.utc).isoformat() skipped_dedup = getattr(result, 'findings_skipped_dedup', 0) or 0 existing_part = f' ({skipped_dedup} already existed)' if skipped_dedup else '' summary = f'Done: {result.scanned} scanned, {result.auto_fixed} fixed, {result.findings_created} findings{existing_part}, {result.errors} errors' state['log'].append({'type': 'success' if status == 'finished' else 'error', 'text': summary}) try: socketio.emit('repair:progress', {job_id: dict(state)}) except Exception as e: logger.debug("repair progress emit failed: %s", e) repair_worker.register_progress_callbacks(_repair_job_start, _repair_job_progress, _repair_job_finish) # Store refs for WebSocket push loop repair_worker._progress_lock_ref = repair_job_progress_lock repair_worker._progress_states_ref = repair_job_progress_states repair_worker.start() logger.info("Repair worker initialized and started") except Exception as e: logger.error(f"Repair worker initialization failed: {e}") repair_worker = None # --- Repair Worker API Endpoints --- @app.route('/api/repair/status', methods=['GET']) def repair_status(): """Get repair worker status""" try: if repair_worker is None: return jsonify({ 'enabled': False, 'running': False, 'paused': True, 'idle': False, 'current_item': None, 'current_job': None, 'findings_pending': 0, 'stats': {'scanned': 0, 'repaired': 0, 'skipped': 0, 'errors': 0, 'pending': 0}, 'progress': {} }), 200 status = repair_worker.get_stats() return jsonify(status), 200 except Exception as e: logger.error(f"Error getting repair status: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/repair/toggle', methods=['POST']) def repair_toggle(): """Toggle master enable/disable""" try: if repair_worker is None: return jsonify({'error': 'Repair worker not initialized'}), 400 new_state = repair_worker.toggle() logger.info("Repair worker %s via UI", "enabled" if new_state else "disabled") return jsonify({'enabled': new_state}), 200 except Exception as e: logger.error(f"Error toggling repair worker: {e}") return jsonify({'error': str(e)}), 500 # Backward compat aliases @app.route('/api/repair/pause', methods=['POST']) def repair_pause(): try: if repair_worker is None: return jsonify({'error': 'Repair worker not initialized'}), 400 repair_worker.pause() return jsonify({'status': 'paused'}), 200 except Exception as e: return jsonify({'error': str(e)}), 500 @app.route('/api/repair/resume', methods=['POST']) def repair_resume(): try: if repair_worker is None: return jsonify({'error': 'Repair worker not initialized'}), 400 repair_worker.resume() return jsonify({'status': 'running'}), 200 except Exception as e: return jsonify({'error': str(e)}), 500 @app.route('/api/repair/jobs', methods=['GET']) def repair_jobs_list(): """Get all jobs with config and last run info""" try: if repair_worker is None: return jsonify({'jobs': []}), 200 jobs = repair_worker.get_all_job_info() return jsonify({'jobs': jobs}), 200 except Exception as e: logger.error(f"Error getting repair jobs: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/repair/jobs//toggle', methods=['POST']) def repair_job_toggle(job_id): """Enable/disable a specific job""" try: if repair_worker is None: return jsonify({'error': 'Repair worker not initialized'}), 400 data = request.get_json(silent=True) or {} enabled = data.get('enabled') if enabled is None: # Toggle — get current state and flip it config = repair_worker.get_job_config(job_id) enabled = not config.get('enabled', False) repair_worker.set_job_enabled(job_id, enabled) logger.info("Repair job %s %s via UI", job_id, "enabled" if enabled else "disabled") return jsonify({'job_id': job_id, 'enabled': enabled}), 200 except Exception as e: logger.error(f"Error toggling repair job {job_id}: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/repair/jobs//settings', methods=['PUT']) def repair_job_settings(job_id): """Update job interval and/or settings""" try: if repair_worker is None: return jsonify({'error': 'Repair worker not initialized'}), 400 data = request.get_json(silent=True) or {} interval_hours = data.get('interval_hours') settings = data.get('settings') repair_worker.set_job_settings(job_id, interval_hours=interval_hours, settings=settings) logger.info("Repair job %s settings updated via UI", job_id) return jsonify({'success': True}), 200 except Exception as e: logger.error(f"Error updating repair job settings {job_id}: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/repair/jobs//run', methods=['POST']) def repair_job_run(job_id): """Trigger immediate run of a specific job""" try: if repair_worker is None: return jsonify({'error': 'Repair worker not initialized'}), 400 repair_worker.run_job_now(job_id) logger.info("Repair job %s triggered manually via UI", job_id) return jsonify({'success': True, 'job_id': job_id}), 200 except Exception as e: logger.error(f"Error running repair job {job_id}: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/repair/findings', methods=['GET']) def repair_findings_list(): """Get paginated findings with filters""" try: if repair_worker is None: return jsonify({'items': [], 'total': 0, 'page': 0, 'limit': 50}), 200 job_id = request.args.get('job_id') status = request.args.get('status') severity = request.args.get('severity') page = int(request.args.get('page', 0)) limit = int(request.args.get('limit', 50)) result = repair_worker.get_findings( job_id=job_id, status=status, severity=severity, page=page, limit=limit ) # Fix Plex/Jellyfin relative thumb URLs in finding details for item in result.get('items', []): details = item.get('details') if details and isinstance(details, dict): for key in ('album_thumb_url', 'artist_thumb_url'): if details.get(key): details[key] = fix_artist_image_url(details[key]) return jsonify(result), 200 except Exception as e: logger.error(f"Error getting repair findings: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/repair/findings/counts', methods=['GET']) def repair_findings_counts(): """Get findings counts by status""" try: if repair_worker is None: return jsonify({'pending': 0, 'resolved': 0, 'dismissed': 0, 'total': 0}), 200 counts = repair_worker.get_findings_counts() return jsonify(counts), 200 except Exception as e: logger.error(f"Error getting findings counts: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/repair/cache-health', methods=['GET']) def repair_cache_health(): """Get metadata cache health stats for the repair dashboard""" try: cache = get_metadata_cache() return jsonify(cache.get_health_stats()), 200 except Exception as e: logger.error(f"Error getting cache health: {e}") return jsonify({}), 500 @app.route('/api/repair/findings//fix', methods=['POST']) def repair_finding_fix(finding_id): """Execute the actual fix action for a finding""" try: if repair_worker is None: return jsonify({'error': 'Repair worker not initialized'}), 400 data = request.get_json(silent=True) or {} fix_action = data.get('fix_action') # e.g. 'staging' or 'delete' for orphan files result = repair_worker.fix_finding(finding_id, fix_action=fix_action) return jsonify(result), 200 if result.get('success') else 400 except Exception as e: logger.error(f"Error fixing finding {finding_id}: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/repair/findings//resolve', methods=['POST']) def repair_finding_resolve(finding_id): """Resolve a finding with optional action""" try: if repair_worker is None: return jsonify({'error': 'Repair worker not initialized'}), 400 data = request.get_json(silent=True) or {} action = data.get('action') success = repair_worker.resolve_finding(finding_id, action) return jsonify({'success': success}), 200 except Exception as e: logger.error(f"Error resolving finding {finding_id}: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/repair/findings//dismiss', methods=['POST']) def repair_finding_dismiss(finding_id): """Dismiss a finding""" try: if repair_worker is None: return jsonify({'error': 'Repair worker not initialized'}), 400 success = repair_worker.dismiss_finding(finding_id) return jsonify({'success': success}), 200 except Exception as e: logger.error(f"Error dismissing finding {finding_id}: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/repair/findings/bulk-fix', methods=['POST']) def repair_findings_bulk_fix(): """Bulk fix all pending fixable findings matching filters""" try: if repair_worker is None: return jsonify({'error': 'Repair worker not initialized'}), 400 data = request.get_json(silent=True) or {} job_id = data.get('job_id') or None severity = data.get('severity') or None finding_ids = data.get('ids') or None fix_action = data.get('fix_action') or None result = repair_worker.bulk_fix_findings( job_id=job_id, severity=severity, finding_ids=finding_ids, fix_action=fix_action ) return jsonify({ 'success': True, 'fixed': result.get('fixed', 0), 'failed': result.get('failed', 0), 'total': result.get('total', 0), 'errors': result.get('errors', []) }), 200 except Exception as e: logger.error(f"Error bulk fixing findings: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/repair/findings/bulk', methods=['POST']) def repair_findings_bulk(): """Bulk resolve or dismiss findings""" try: if repair_worker is None: return jsonify({'error': 'Repair worker not initialized'}), 400 data = request.get_json(silent=True) or {} finding_ids = data.get('ids', []) action = data.get('action', 'dismiss') if not finding_ids: return jsonify({'error': 'No finding IDs provided'}), 400 count = repair_worker.bulk_update_findings(finding_ids, action) return jsonify({'success': True, 'updated': count}), 200 except Exception as e: logger.error(f"Error bulk updating findings: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/repair/findings/clear', methods=['POST']) def repair_findings_clear(): """Clear (delete) findings, optionally filtered by job_id and/or status""" try: if repair_worker is None: return jsonify({'error': 'Repair worker not initialized'}), 400 data = request.get_json(silent=True) or {} job_id = data.get('job_id') status = data.get('status') count = repair_worker.clear_findings(job_id=job_id, status=status) return jsonify({'success': True, 'deleted': count}), 200 except Exception as e: logger.error(f"Error clearing findings: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/repair/history', methods=['GET']) def repair_history(): """Get job run history""" try: if repair_worker is None: return jsonify({'runs': []}), 200 job_id = request.args.get('job_id') limit = int(request.args.get('limit', 50)) runs = repair_worker.get_history(job_id=job_id, limit=limit) return jsonify({'runs': runs}), 200 except Exception as e: logger.error(f"Error getting repair history: {e}") return jsonify({'error': str(e)}), 500 @app.route('/api/repair/progress', methods=['GET']) def repair_job_progress(): """Get current repair job progress states (for initial page load)""" try: if repair_worker is None: return jsonify({}), 200 lock = getattr(repair_worker, '_progress_lock_ref', None) states = getattr(repair_worker, '_progress_states_ref', None) if lock is None or states is None: return jsonify({}), 200 with lock: result = {} for jid, state in states.items(): cp = dict(state) cp['log'] = list(state['log']) result[jid] = cp return jsonify(result), 200 except Exception as e: logger.error(f"Error getting repair progress: {e}") return jsonify({'error': str(e)}), 500 # ================================================================================================ # END LIBRARY REPAIR WORKER # ================================================================================================ # ================================================================================================ # IMPORT / STAGING SYSTEM # ================================================================================================ def _build_import_route_runtime(): return _ImportRouteRuntime( post_process_matched_download=_post_process_matched_download, add_activity_item=add_activity_item, automation_engine=automation_engine, hydrabase_worker=hydrabase_worker, dev_mode_enabled=dev_mode_enabled, import_singles_executor=import_singles_executor, build_album_import_match_payload=build_album_import_match_payload, process_single_import_file=lambda runtime, file_info: _process_single_import_file(file_info), logger=logger, ) @app.route('/api/import/staging/files', methods=['GET']) def import_staging_files(): payload, status = _import_staging_files(_build_import_route_runtime()) return jsonify(payload), status @app.route('/api/import/staging/groups', methods=['GET']) def import_staging_groups(): payload, status = _import_staging_groups(_build_import_route_runtime()) return jsonify(payload), status @app.route('/api/import/staging/hints', methods=['GET']) def import_staging_hints(): payload, status = _import_staging_hints(_build_import_route_runtime()) return jsonify(payload), status @app.route('/api/import/search/albums', methods=['GET']) def import_search_albums(): payload, status = _import_search_albums( _build_import_route_runtime(), request.args.get('q', ''), request.args.get('limit', 12), ) return jsonify(payload), status @app.route('/api/import/album/match', methods=['POST']) def import_album_match(): payload, status = _import_album_match(_build_import_route_runtime(), request.get_json() or {}) return jsonify(payload), status @app.route('/api/import/album/process', methods=['POST']) def import_album_process(): payload, status = _import_album_process(_build_import_route_runtime(), request.get_json() or {}) return jsonify(payload), status @app.route('/api/import/search/tracks', methods=['GET']) def import_search_tracks(): payload, status = _import_search_tracks( _build_import_route_runtime(), request.args.get('q', ''), request.args.get('limit', 10), ) return jsonify(payload), status def _process_single_import_file(file_info): return _import_process_single_import_file(_build_import_route_runtime(), file_info) @app.route('/api/import/singles/process', methods=['POST']) def import_singles_process(): data = request.get_json() or {} payload, status = _import_singles_process(_build_import_route_runtime(), data.get('files', [])) return jsonify(payload), status # Auto-Import Worker auto_import_worker = None try: from core.auto_import_worker import AutoImportWorker _ai_db = get_database() _ai_staging = docker_resolve_path(config_manager.get('import.staging_path', './Staging')) _ai_transfer = docker_resolve_path(config_manager.get('soulseek.transfer_path', './Transfer')) auto_import_worker = AutoImportWorker( database=_ai_db, staging_path=_ai_staging, transfer_path=_ai_transfer, process_callback=_post_process_matched_download, config_manager=config_manager, automation_engine=automation_engine, ) if config_manager.get('auto_import.enabled', False): auto_import_worker.start() logger.info("Auto-import worker started") else: logger.info("Auto-import worker initialized (disabled)") except Exception as _ai_err: logger.error(f"Auto-import worker init failed: {_ai_err}") @app.route('/api/auto-import/status', methods=['GET']) def auto_import_status(): if not auto_import_worker: return jsonify({"success": False, "error": "Auto-import not available"}), 500 return jsonify({"success": True, **auto_import_worker.get_status()}) @app.route('/api/auto-import/toggle', methods=['POST']) def auto_import_toggle(): if not auto_import_worker: return jsonify({"success": False, "error": "Auto-import not available"}), 500 data = request.get_json() or {} enabled = data.get('enabled', not auto_import_worker.running) if enabled: config_manager.set('auto_import.enabled', True) if not auto_import_worker.running: auto_import_worker.start() else: config_manager.set('auto_import.enabled', False) auto_import_worker.stop() return jsonify({"success": True, "enabled": enabled}) @app.route('/api/auto-import/settings', methods=['GET', 'POST']) def auto_import_settings(): if request.method == 'GET': return jsonify({ "success": True, "enabled": config_manager.get('auto_import.enabled', False), "scan_interval": config_manager.get('auto_import.scan_interval', 60), "confidence_threshold": config_manager.get('auto_import.confidence_threshold', 0.9), "auto_process": config_manager.get('auto_import.auto_process', True), }) data = request.get_json() or {} for key in ['enabled', 'scan_interval', 'confidence_threshold', 'auto_process']: if key in data: config_manager.set(f'auto_import.{key}', data[key]) return jsonify({"success": True}) @app.route('/api/auto-import/results', methods=['GET']) def auto_import_results(): if not auto_import_worker: return jsonify({"success": False, "error": "Auto-import not available"}), 500 status_filter = request.args.get('status') limit = request.args.get('limit', 50, type=int) results = auto_import_worker.get_results(status_filter=status_filter, limit=limit) return jsonify({"success": True, "results": results}) @app.route('/api/auto-import/approve/', methods=['POST']) def auto_import_approve(item_id): if not auto_import_worker: return jsonify({"success": False, "error": "Auto-import not available"}), 500 return jsonify(auto_import_worker.approve_item(item_id)) @app.route('/api/auto-import/reject/', methods=['POST']) def auto_import_reject(item_id): if not auto_import_worker: return jsonify({"success": False, "error": "Auto-import not available"}), 500 return jsonify(auto_import_worker.reject_item(item_id)) @app.route('/api/auto-import/scan-now', methods=['POST']) def auto_import_scan_now(): """Trigger an immediate scan cycle. Routes through `trigger_scan()`, the canonical entry point shared with the worker's timer loop. Pre-refactor this endpoint spawned a fresh `_scan_cycle` thread per click — emergent parallelism that grew unbounded with each click and produced racy access to candidate-tracking state. Post-refactor: - Manual triggers + the timer loop share one scan-lock, so only one scan runs at a time - Per-candidate processing happens on the worker's bounded `ThreadPoolExecutor` (default 3 workers — predictable concurrency, configurable via `auto_import.max_workers`) - Multiple "Scan Now" clicks while a scan is in flight no-op instead of stacking up parallel scanners Runs the scan in a background thread so the HTTP response returns immediately — `trigger_scan()` itself is fast (just enumeration + submit), but a slow filesystem walk on a large staging dir could still hold the request thread for seconds. Detached thread is safe: scan-lock prevents duplicate work, executor handles per-candidate processing. """ if not auto_import_worker: return jsonify({"success": False, "error": "Auto-import not available"}), 500 if not auto_import_worker.running: return jsonify({"success": False, "error": "Auto-import is not running"}), 400 threading.Thread( target=auto_import_worker.trigger_scan, daemon=True, name='AutoImportScanNow', ).start() return jsonify({"success": True}) @app.route('/api/auto-import/approve-all', methods=['POST']) def auto_import_approve_all(): """Approve all pending review items.""" if not auto_import_worker: return jsonify({"success": False, "error": "Auto-import not available"}), 500 try: results = auto_import_worker.get_results(status_filter='pending_review', limit=200) count = 0 for r in results: result = auto_import_worker.approve_item(r['id']) if result.get('success'): count += 1 return jsonify({"success": True, "count": count}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/auto-import/clear-completed', methods=['POST']) def auto_import_clear_completed(): """Remove completed/imported items from history. `processing` rows are included so zombie entries (server restarted mid-import → `_record_in_progress` row never got finalized) get swept. Live in-flight imports are protected by intersecting against `_snapshot_active()` — anything currently registered in the worker's `_active_imports` map keeps its row. `pending_review` is left out so user still has to approve/reject those explicitly. """ if not auto_import_worker: return jsonify({"success": False, "error": "Auto-import not available"}), 500 try: active_hashes = {e['folder_hash'] for e in auto_import_worker._snapshot_active()} db = get_database() with db._get_connection() as conn: cursor = conn.cursor() base_sql = ( "DELETE FROM auto_import_history " "WHERE status IN ('completed', 'approved', 'failed', " "'needs_identification', 'rejected', 'processing')" ) if active_hashes: placeholders = ','.join('?' * len(active_hashes)) cursor.execute( f"{base_sql} AND folder_hash NOT IN ({placeholders})", tuple(active_hashes), ) else: cursor.execute(base_sql) count = cursor.rowcount conn.commit() return jsonify({"success": True, "count": count}) except Exception as e: return jsonify({"success": False, "error": str(e)}), 500 @app.route('/api/import/staging/suggestions', methods=['GET']) def import_staging_suggestions(): payload, status = _import_staging_suggestions() return jsonify(payload), status # ================================================================================================ # END IMPORT / STAGING SYSTEM # ================================================================================================ # ================================================================================================ # WEBSOCKET (SOCKET.IO) EVENT HANDLERS AND BACKGROUND EMITTERS # ================================================================================================ def _build_status_payload(): """Build the same status payload used by GET /status, reading from the cache.""" download_mode = config_manager.get('download_source.mode', 'hybrid') soulseek_data = dict(_status_cache.get('soulseek', {})) soulseek_data['source'] = download_mode metadata_status = get_metadata_status_snapshot(spotify_client=spotify_client) # Count active downloads for nav badge active_dl_count = 0 try: with tasks_lock: for t in download_tasks.values(): if t.get('status') in ('downloading', 'searching', 'post_processing', 'queued', 'pending'): active_dl_count += 1 except Exception as e: logger.debug("active download count failed: %s", e) return { 'metadata_source': metadata_status['metadata_source'], 'spotify': metadata_status['spotify'], 'media_server': _status_cache.get('media_server', {}), 'soulseek': soulseek_data, 'active_media_server': config_manager.get_active_media_server(), 'enrichment': _get_enrichment_status(), 'active_downloads': active_dl_count, } def _build_watchlist_count_payload(profile_id=1): """Build the same payload used by GET /api/watchlist/count.""" try: database = get_database() count = database.get_watchlist_count(profile_id=profile_id) except Exception: count = 0 next_run_in_seconds = automation_engine.get_system_automation_next_run_seconds('scan_watchlist') if automation_engine else 0 return { 'success': True, 'count': count, 'next_run_in_seconds': next_run_in_seconds } def _hydrabase_reconnect_loop(): """Background thread that monitors Hydrabase connection and auto-reconnects if needed.""" global _hydrabase_ws _consecutive_failures = 0 while not globals().get('IS_SHUTTING_DOWN', False): socketio.sleep(30) try: # Only attempt reconnect if auto_connect is enabled hydra_cfg = config_manager.get_hydrabase_config() if not hydra_cfg.get('auto_connect') or not hydra_cfg.get('url') or not hydra_cfg.get('api_key'): _consecutive_failures = 0 continue # Check if already connected try: if _hydrabase_ws is not None and _hydrabase_ws.connected: _consecutive_failures = 0 continue except Exception as e: logger.debug("hydrabase socket check: %s", e) # Disconnected with auto_connect enabled — try to reconnect # Back off: 30s, 60s, 120s, max 300s between attempts backoff = min(30 * (2 ** _consecutive_failures), 300) if _consecutive_failures > 0: socketio.sleep(backoff - 30) # Already slept 30s at top of loop import websocket try: with _hydrabase_lock: if _hydrabase_ws: try: _hydrabase_ws.close() except Exception as e: logger.debug("hydrabase reconnect close: %s", e) ws = websocket.create_connection( hydra_cfg['url'], header={"x-api-key": hydra_cfg['api_key']}, timeout=10 ) _hydrabase_ws = ws _consecutive_failures = 0 logger.info(f"[Hydrabase] Auto-reconnected to {hydra_cfg['url']}") except Exception as e: _consecutive_failures += 1 if _consecutive_failures <= 3: logger.error(f"[Hydrabase] Reconnect attempt failed ({_consecutive_failures}): {e}") elif _consecutive_failures == 4: logger.error("[Hydrabase] Reconnect failing repeatedly — suppressing further logs until success") except Exception as e: logger.debug("hydrabase monitor loop: %s", e) def _emit_service_status_loop(): """Background thread that pushes service status every 5 seconds.""" while not globals().get('IS_SHUTTING_DOWN', False): socketio.sleep(5) try: socketio.emit('status:update', _build_status_payload()) except Exception as e: logger.debug(f"Error emitting service status: {e}") def _emit_watchlist_count_loop(): """Background thread that pushes watchlist count every 10 seconds to each profile room.""" while not globals().get('IS_SHUTTING_DOWN', False): socketio.sleep(10) try: database = get_database() profiles = database.get_all_profiles() for profile in profiles: pid = profile['id'] socketio.emit('watchlist:count', _build_watchlist_count_payload(profile_id=pid), room=f'profile:{pid}') except Exception as e: logger.debug(f"Error emitting watchlist count: {e}") def _emit_download_status_loop(): """Background thread that pushes download batch status every 2 seconds to subscribed rooms.""" while not globals().get('IS_SHUTTING_DOWN', False): socketio.sleep(2) try: live_transfers_lookup = get_cached_transfer_data() with tasks_lock: for batch_id, batch in download_batches.items(): try: status_data = _build_batch_status_data( batch_id, batch, live_transfers_lookup ) socketio.emit('downloads:batch_update', { 'batch_id': batch_id, 'data': status_data }, room=f'batch:{batch_id}') except Exception as e: logger.debug(f"Error building batch status for {batch_id}: {e}") except Exception as e: logger.debug(f"Error in download status emit loop: {e}") # --- Socket.IO event handlers --- @socketio.on('connect') def handle_connect(): logger.info("WebSocket client connected") @socketio.on('disconnect') def handle_disconnect(): logger.info("WebSocket client disconnected") @socketio.on('downloads:subscribe') def handle_download_subscribe(data): """Client subscribes to download batch updates by joining rooms.""" batch_ids = data.get('batch_ids', []) for bid in batch_ids: join_room(f'batch:{bid}') logger.debug(f"Client subscribed to batches: {batch_ids}") @socketio.on('downloads:unsubscribe') def handle_download_unsubscribe(data): """Client unsubscribes from download batch updates by leaving rooms.""" batch_ids = data.get('batch_ids', []) for bid in batch_ids: leave_room(f'batch:{bid}') logger.debug(f"Client unsubscribed from batches: {batch_ids}") @socketio.on('profile:join') def handle_profile_join(data): """Client joins a profile room for scoped WebSocket emits (watchlist/wishlist counts).""" profile_id = data.get('profile_id') if profile_id: # Leave any previous profile rooms old_id = data.get('old_profile_id') if old_id: leave_room(f'profile:{old_id}') join_room(f'profile:{profile_id}') logger.debug(f"Client joined profile room: profile:{profile_id}") # --- Phase 2: Dashboard emitters --- def _emit_system_stats_loop(): """Background thread that pushes system stats every 10 seconds.""" while not globals().get('IS_SHUTTING_DOWN', False): socketio.sleep(10) try: socketio.emit('dashboard:stats', _build_system_stats()) except Exception as e: logger.debug(f"Error emitting system stats: {e}") def _emit_activity_feed_loop(): """Background thread that pushes activity feed every 2 seconds.""" while not globals().get('IS_SHUTTING_DOWN', False): socketio.sleep(2) try: with activity_feed_lock: activities = activity_feed[-10:][::-1] socketio.emit('dashboard:activity', {'activities': activities}) except Exception as e: logger.debug(f"Error emitting activity feed: {e}") def _emit_db_stats_loop(): """Background thread that pushes database stats every 10 seconds.""" while not globals().get('IS_SHUTTING_DOWN', False): socketio.sleep(10) try: db = get_database() stats = db.get_database_info_for_server() socketio.emit('dashboard:db_stats', stats) except Exception as e: logger.debug(f"Error emitting db stats: {e}") def _emit_wishlist_count_loop(): """Background thread that pushes wishlist count every 10 seconds to each profile room.""" while not globals().get('IS_SHUTTING_DOWN', False): socketio.sleep(10) try: from core.wishlist_service import get_wishlist_service ws = get_wishlist_service() database = get_database() profiles = database.get_all_profiles() for profile in profiles: pid = profile['id'] count = ws.get_wishlist_count(profile_id=pid) socketio.emit('dashboard:wishlist_count', {'count': count}, room=f'profile:{pid}') except Exception as e: logger.debug(f"Error emitting wishlist count: {e}") # Note: Toasts are NOT on a timer — they emit instantly from add_activity_item() # --- Phase 3: Enrichment sidebar worker emitters --- def _has_active_downloads(): """Check if any download batches are currently active.""" try: with tasks_lock: for batch_data in download_batches.values(): if batch_data.get('phase') not in ('complete', 'error', 'cancelled', None): return True except Exception as e: logger.debug("active downloads check failed: %s", e) return False # Track whether we auto-paused workers so we only resume ones we paused (not user-paused ones) _download_auto_paused = set() _download_yield_override = set() # Workers the user explicitly resumed during downloads — don't re-pause # --------------------------------------------------------------------------- # Enrichment service registry # --------------------------------------------------------------------------- # Generic ``/api/enrichment//{status,pause,resume}`` routes that # replace 30 near-identical per-service routes scattered through this file. # The old per-service routes still exist below as a fallback during the # soak period; PR-2 deletes them once the dashboard has cut over to the # generic ones. See `core/enrichment/services.py` for the registry. from core.enrichment.api import ( configure as _configure_enrichment_api, create_blueprint as _create_enrichment_blueprint, ) from core.enrichment.services import ( EnrichmentService as _EnrichmentService, register_services as _register_enrichment_services, ) def _spotify_resume_pre_check(): """Mirror the inline Spotify rate-limit guard from the legacy ``/api/spotify-enrichment/resume`` route. Returns ``(429, message)`` to short-circuit when banned, ``None`` when ok.""" try: if _spotify_rate_limited(): return (429, 'Cannot resume while Spotify is rate limited') except Exception as e: logger.debug("spotify rate-limit pre-check failed: %s", e) return None _register_enrichment_services([ _EnrichmentService( id='musicbrainz', display_name='MusicBrainz', worker_getter=lambda: mb_worker, config_paused_key='musicbrainz_enrichment_paused', ), _EnrichmentService( id='audiodb', display_name='AudioDB', worker_getter=lambda: audiodb_worker, config_paused_key='audiodb_enrichment_paused', ), _EnrichmentService( id='discogs', display_name='Discogs', worker_getter=lambda: discogs_worker, config_paused_key='discogs_enrichment_paused', ), _EnrichmentService( id='deezer', display_name='Deezer', worker_getter=lambda: deezer_worker, config_paused_key='deezer_enrichment_paused', ), _EnrichmentService( id='spotify', display_name='Spotify', worker_getter=lambda: spotify_enrichment_worker, config_paused_key='spotify_enrichment_paused', pre_resume_check=_spotify_resume_pre_check, auto_pause_token='spotify-enrichment', ), _EnrichmentService( id='itunes', display_name='iTunes', worker_getter=lambda: itunes_enrichment_worker, config_paused_key='itunes_enrichment_paused', ), _EnrichmentService( id='lastfm', display_name='Last.fm', worker_getter=lambda: lastfm_worker, config_paused_key='lastfm_enrichment_paused', auto_pause_token='lastfm-enrichment', ), _EnrichmentService( id='genius', display_name='Genius', worker_getter=lambda: genius_worker, config_paused_key='genius_enrichment_paused', auto_pause_token='genius-enrichment', ), _EnrichmentService( id='tidal', display_name='Tidal', worker_getter=lambda: tidal_enrichment_worker, config_paused_key='tidal_enrichment_paused', extra_status_defaults={'authenticated': False}, ), _EnrichmentService( id='qobuz', display_name='Qobuz', worker_getter=lambda: qobuz_enrichment_worker, config_paused_key='qobuz_enrichment_paused', extra_status_defaults={'authenticated': False}, ), ]) _configure_enrichment_api( config_set=lambda key, value: config_manager.set(key, value), auto_paused_discard=lambda token: _download_auto_paused.discard(token), yield_override_add=lambda token: _download_yield_override.add(token), ) app.register_blueprint(_create_enrichment_blueprint()) def _emit_rate_monitor_loop(): """Background thread that pushes API call rate data every 1 second for speedometer gauges. Also includes enrichment worker status so the combined cards have everything.""" # Map rate monitor service keys to enrichment status keys _enrichment_key_map = { 'spotify': 'spotify_enrichment', 'itunes': 'itunes_enrichment', 'deezer': 'deezer_enrichment', 'lastfm': 'lastfm', 'genius': 'genius', 'musicbrainz': 'musicbrainz', 'audiodb': 'audiodb', 'discogs': 'discogs', 'tidal': 'tidal_enrichment', 'qobuz': 'qobuz_enrichment', } while not globals().get('IS_SHUTTING_DOWN', False): socketio.sleep(1) try: from core.api_call_tracker import api_call_tracker payload = api_call_tracker.get_all_rates() # Merge enrichment worker status into each service try: enrichment = _get_enrichment_status() for svc_key, entry in payload.items(): enr_key = _enrichment_key_map.get(svc_key) enr = enrichment.get(enr_key) if enr_key else None if enr: entry['worker'] = { 'status': 'not_configured' if not enr.get('configured') else 'paused' if enr.get('paused') else 'idle' if enr.get('idle') else 'running' if enr.get('running') else 'stopped', 'yield_reason': enr.get('yield_reason', ''), 'calls_1h': enr.get('calls_1h', 0), 'calls_24h': enr.get('calls_24h', 0), } if svc_key == 'spotify' and enr.get('daily_budget'): entry['worker']['daily_budget'] = enr['daily_budget'] except Exception as e: logger.debug("enrichment worker status build failed: %s", e) # Add Spotify rate limit state try: spotify_status = get_spotify_status(spotify_client=spotify_client) rl_info = spotify_status.get('rate_limit') if spotify_status.get('rate_limited') and rl_info: payload['spotify']['rate_limited'] = True payload['spotify']['rl_remaining'] = rl_info.get('remaining_seconds', 0) payload['spotify']['rl_endpoint'] = rl_info.get('endpoint', '') except Exception as e: logger.debug("spotify rate-limit status read failed: %s", e) socketio.emit('rate-monitor:update', payload) except Exception as e: logger.debug(f"Error emitting rate monitor: {e}") def _emit_enrichment_status_loop(): """Background thread that pushes all enrichment worker statuses every 2 seconds. Also auto-pauses rate-limited enrichment workers during active downloads.""" workers = { 'musicbrainz': lambda: mb_worker, 'audiodb': lambda: audiodb_worker, 'discogs': lambda: discogs_worker, 'deezer': lambda: deezer_worker, 'spotify-enrichment': lambda: spotify_enrichment_worker, 'itunes-enrichment': lambda: itunes_enrichment_worker, 'lastfm-enrichment': lambda: lastfm_worker, 'genius-enrichment': lambda: genius_worker, 'tidal-enrichment': lambda: tidal_enrichment_worker, 'qobuz-enrichment': lambda: qobuz_enrichment_worker, 'hydrabase': lambda: hydrabase_worker, 'soulid': lambda: soulid_worker, 'listening-stats': lambda: listening_stats_worker, 'repair': lambda: repair_worker, } # Workers to auto-pause during downloads (rate-limit sensitive services) yield_workers = { 'spotify-enrichment': lambda: spotify_enrichment_worker, 'lastfm-enrichment': lambda: lastfm_worker, 'genius-enrichment': lambda: genius_worker, } while not globals().get('IS_SHUTTING_DOWN', False): socketio.sleep(2) # Auto-pause/resume rate-limited workers during downloads try: downloading = _has_active_downloads() if not downloading: _download_yield_override.clear() # Reset overrides when downloads finish for name, get_w in yield_workers.items(): w = get_w() if w is None: continue if downloading and not w.paused and name not in _download_yield_override: w.paused = True _download_auto_paused.add(name) logger.debug(f"Auto-paused {name} during active downloads") elif not downloading and name in _download_auto_paused: # Don't override an explicit user pause. If config says the worker # was paused via the UI, leave it paused and just drop the auto-pause # marker so the next auto-pause/resume cycle behaves normally. config_key = f"{name.replace('-', '_')}_paused" user_paused = config_manager.get(config_key, False) _download_auto_paused.discard(name) if not user_paused: w.paused = False logger.debug(f"Auto-resumed {name} after downloads finished") else: logger.debug(f"Downloads finished but {name} remains paused by user") except Exception as e: logger.debug(f"Error in download-yield check: {e}") for name, get_worker in workers.items(): try: worker = get_worker() if worker is None: continue status = worker.get_stats() # Flag workers that were auto-paused for downloads if name in _download_auto_paused: status['yield_reason'] = 'downloads' socketio.emit(f'enrichment:{name}', status) except Exception as e: logger.debug(f"Error emitting {name} status: {e}") def _emit_tool_progress_loop(): """Background thread that pushes all tool progress statuses every 1 second.""" while not globals().get('IS_SHUTTING_DOWN', False): socketio.sleep(1) # Stream status try: with stream_lock: socketio.emit('tool:stream', { "status": stream_state["status"], "progress": stream_state["progress"], "track_info": stream_state["track_info"], "error_message": stream_state["error_message"] }) except Exception as e: logger.debug(f"Error emitting stream status: {e}") # Quality Scanner try: with quality_scanner_lock: socketio.emit('tool:quality-scanner', dict(quality_scanner_state)) except Exception as e: logger.debug(f"Error emitting quality scanner status: {e}") # Duplicate Cleaner (add computed space_freed_mb) try: with duplicate_cleaner_lock: state_copy = duplicate_cleaner_state.copy() state_copy["space_freed_mb"] = duplicate_cleaner_state["space_freed"] / (1024 * 1024) socketio.emit('tool:duplicate-cleaner', state_copy) except Exception as e: logger.debug(f"Error emitting duplicate cleaner status: {e}") # Retag try: with retag_lock: socketio.emit('tool:retag', dict(retag_state)) except Exception as e: logger.debug(f"Error emitting retag status: {e}") # DB Update try: with db_update_lock: socketio.emit('tool:db-update', dict(db_update_state)) except Exception as e: logger.debug(f"Error emitting db update status: {e}") # Metadata Update (match HTTP wrapper: {success, status}) try: state_copy = metadata_update_state.copy() if state_copy.get('started_at'): state_copy['started_at'] = state_copy['started_at'].isoformat() if state_copy.get('completed_at'): state_copy['completed_at'] = state_copy['completed_at'].isoformat() socketio.emit('tool:metadata', {"success": True, "status": state_copy}) except Exception as e: logger.debug(f"Error emitting metadata status: {e}") # Logs (format activity_feed same as HTTP endpoint) try: with activity_feed_lock: recent = activity_feed[-50:][::-1] formatted = [] for a in recent: ts = a.get('time', 'Unknown') icon = a.get('icon', '•') title = a.get('title', 'Activity') sub = a.get('subtitle', '') formatted.append(f"[{ts}] {icon} {title} - {sub}" if sub else f"[{ts}] {icon} {title}") if not formatted: formatted = ["No recent activity.", "Sync and download operations..."] socketio.emit('tool:logs', {'logs': formatted}) except Exception as e: logger.debug(f"Error emitting logs: {e}") def _emit_live_log_loop(): """Background thread that tails app.log and pushes new lines via WebSocket.""" _last_pos = {} # {source: file_position} _active_source = 'app' log_map = { 'app': Path(_log_path), 'acoustid': _log_dir / 'acoustid.log', 'post_processing': _log_dir / 'post_processing.log', 'source_reuse': _log_dir / 'source_reuse.log', } while not globals().get('IS_SHUTTING_DOWN', False): socketio.sleep(0.5) try: # Read which source clients want (stored by subscribe handler) source = getattr(_emit_live_log_loop, '_source', 'app') log_path = log_map.get(source, log_map['app']) if not os.path.exists(log_path): continue file_size = os.path.getsize(log_path) last_pos = _last_pos.get(source, 0) # File was truncated or rotated if file_size < last_pos: last_pos = 0 if file_size == last_pos: continue # No new data new_lines = [] with open(log_path, 'r', encoding='utf-8', errors='replace') as f: f.seek(last_pos) for line in f: stripped = line.rstrip() if stripped: new_lines.append(stripped) _last_pos[source] = f.tell() if new_lines: # Cap at 50 lines per push to avoid flooding socketio.emit('logs:live', { 'lines': new_lines[-50:], 'source': source, }) except Exception as e: logger.debug(f"Error in live log emitter: {e}") _emit_live_log_loop._source = 'app' @socketio.on('logs:subscribe') def handle_logs_subscribe(data): """Client subscribes to live log stream with optional source.""" source = data.get('source', 'app') _emit_live_log_loop._source = source join_room('logs:live') @socketio.on('logs:unsubscribe') def handle_logs_unsubscribe(data): leave_room('logs:live') @socketio.on('sync:subscribe') def handle_sync_subscribe(data): for pid in data.get('playlist_ids', []): join_room(f'sync:{pid}') @socketio.on('sync:unsubscribe') def handle_sync_unsubscribe(data): for pid in data.get('playlist_ids', []): leave_room(f'sync:{pid}') @socketio.on('discovery:subscribe') def handle_discovery_subscribe(data): for pid in data.get('ids', []): join_room(f'discovery:{pid}') @socketio.on('discovery:unsubscribe') def handle_discovery_unsubscribe(data): for pid in data.get('ids', []): leave_room(f'discovery:{pid}') def _emit_sync_progress_loop(): """Push sync progress to subscribed rooms every 1 second.""" while not globals().get('IS_SHUTTING_DOWN', False): socketio.sleep(1) try: with sync_lock: for pid, state in list(sync_states.items()): try: socketio.emit('sync:progress', { 'playlist_id': pid, **state }, room=f'sync:{pid}') except Exception as e: logger.debug("sync progress emit failed: %s", e) except Exception as e: logger.debug(f"Error in sync progress loop: {e}") def _emit_discovery_progress_loop(): """Push discovery progress to subscribed rooms every 1 second.""" platform_states = { 'tidal': lambda: tidal_discovery_states, 'deezer': lambda: deezer_discovery_states, 'youtube': lambda: youtube_playlist_states, 'beatport': lambda: beatport_chart_states, 'listenbrainz': lambda: listenbrainz_playlist_states, 'spotify_public': lambda: spotify_public_discovery_states, } while not globals().get('IS_SHUTTING_DOWN', False): socketio.sleep(1) for platform_name, get_states in platform_states.items(): try: states_dict = get_states() for pid, state in list(states_dict.items()): try: phase = state.get('phase', '') if phase in ('', 'idle'): continue payload = { 'platform': platform_name, 'id': pid, 'phase': state.get('phase'), 'status': state.get('status', 'unknown'), 'progress': state.get('discovery_progress', 0), 'discovery_progress': state.get('discovery_progress', {}), 'spotify_matches': state.get('spotify_matches', 0), 'spotify_total': state.get('spotify_total', 0), 'results': state.get('discovery_results', state.get('results', [])), 'complete': state.get('phase') == 'discovered', } socketio.emit('discovery:progress', payload, room=f'discovery:{pid}') except Exception as e: logger.debug("discovery progress emit failed: %s", e) except Exception as e: logger.debug(f"Error in {platform_name} discovery loop: {e}") def _emit_scan_status_loop(): """Push watchlist and media scan status every 2 seconds.""" while not globals().get('IS_SHUTTING_DOWN', False): socketio.sleep(2) # Watchlist scan try: state = watchlist_scan_state.copy() if state.get('started_at'): state['started_at'] = state['started_at'].isoformat() if state.get('completed_at'): state['completed_at'] = state['completed_at'].isoformat() state.pop('results', None) socketio.emit('scan:watchlist', {"success": True, **state}) except Exception as e: logger.debug(f"Error emitting watchlist scan: {e}") # Media scan try: if web_scan_manager: scan_status = web_scan_manager.get_scan_status() socketio.emit('scan:media', {"success": True, "status": scan_status}) except Exception as e: logger.debug(f"Error emitting media scan: {e}") # Wishlist stats (auto-processing detection + countdown refresh) try: next_run = automation_engine.get_system_automation_next_run_seconds('process_wishlist') if automation_engine else 0 socketio.emit('wishlist:stats', { "is_auto_processing": is_wishlist_actually_processing(), "next_run_in_seconds": next_run, }) except Exception as e: logger.debug(f"Error emitting wishlist stats: {e}") def _emit_automation_progress_loop(): """Push automation:progress events every 1 second for running automations.""" _auto_progress.emit_progress_loop( socketio, is_shutting_down=lambda: globals().get('IS_SHUTTING_DOWN', False), ) def _emit_repair_progress_loop(): """Push repair:progress events every 1 second for running repair jobs.""" while not globals().get('IS_SHUTTING_DOWN', False): socketio.sleep(1) try: if repair_worker is None: continue # Access the progress states set up during repair worker init lock = getattr(repair_worker, '_progress_lock_ref', None) states = getattr(repair_worker, '_progress_states_ref', None) if lock is None or states is None: continue with lock: active = {} stale = [] now = datetime.now() for jid, state in states.items(): if state['status'] == 'running': cp = dict(state) cp['log'] = list(state['log']) active[jid] = cp elif state['status'] in ('finished', 'error') and state.get('finished_at'): try: finished_time = datetime.fromisoformat(state['finished_at']) if (now - finished_time).total_seconds() > 60: stale.append(jid) except (ValueError, TypeError): stale.append(jid) # Still include recently finished states so frontend sees final state if jid not in stale: cp = dict(state) cp['log'] = list(state['log']) active[jid] = cp for jid in stale: del states[jid] if active: socketio.emit('repair:progress', active) except Exception as e: logger.debug(f"Error emitting repair progress: {e}") # ================================================================================================ # END WEBSOCKET HANDLERS # ================================================================================================ _runtime_start_lock = threading.Lock() _runtime_started = False def start_runtime_services(): """Start one-time server background services for direct and WSGI launches.""" global _runtime_started with _runtime_start_lock: if _runtime_started: return logger.info("Starting SoulSync runtime services...") # Dump SOULSYNC_* env vars for diagnostics (helps debug Docker/Unraid env issues) _soulsync_env = {k: v for k, v in os.environ.items() if k.startswith('SOULSYNC_')} if _soulsync_env: logger.info(f"[Startup] SOULSYNC environment variables: {_soulsync_env}") else: logger.warning("[Startup] No SOULSYNC_* environment variables detected") # Start OAuth callback servers logger.info("Starting OAuth callback servers...") start_oauth_callback_servers() # Startup diagnostics: Check and recover stuck flags logger.info("Running startup diagnostics...") stuck_flags_recovered = check_and_recover_stuck_flags() if stuck_flags_recovered: logger.warning("Recovered stuck flags from previous session") else: logger.warning("No stuck flags detected - system healthy") # Start simple background monitor when server starts logger.info("Starting simple background monitor...") start_simple_background_monitor() logger.info("Simple background monitor started (includes automatic search cleanup)") # Wishlist/watchlist timers are now managed by AutomationEngine system automations # Pre-build import suggestions cache in background logger.info("Pre-building import suggestions cache...") start_import_suggestions_cache() # Initialize app start time for uptime tracking app.start_time = time.time() # Register action handlers and start automation engine _register_automation_handlers() if automation_engine: try: logger.info("Starting automation engine...") automation_engine.start() logger.info("Automation engine started") try: automation_engine.emit('app_started', {}) except Exception as e: logger.debug("app_started emit failed: %s", e) except AttributeError as e: logger.error(f"Automation engine failed to start: {e}") logger.info(" If using Docker, check that your volume mount is /app/data (not /app/database)") logger.error(f"Automation engine start error (possible stale Docker volume): {e}") except Exception as e: logger.error(f"Automation engine failed to start: {e}") logger.error(f"Automation engine start error: {e}") # Add startup activity add_activity_item("", "System Started", "SoulSync Web UI Server initialized", "Now") # Start WebSocket background emitters logger.info("Starting WebSocket background emitters...") # Phase 1: Global pollers socketio.start_background_task(_emit_service_status_loop) socketio.start_background_task(_emit_watchlist_count_loop) socketio.start_background_task(_emit_download_status_loop) # Phase 2: Dashboard pollers socketio.start_background_task(_emit_system_stats_loop) socketio.start_background_task(_emit_activity_feed_loop) socketio.start_background_task(_emit_db_stats_loop) socketio.start_background_task(_emit_wishlist_count_loop) # Phase 3: Enrichment sidebar workers socketio.start_background_task(_emit_enrichment_status_loop) # Phase 4: Tool progress pollers socketio.start_background_task(_emit_tool_progress_loop) # Phase 5: Sync/discovery progress + scans socketio.start_background_task(_emit_sync_progress_loop) socketio.start_background_task(_emit_discovery_progress_loop) socketio.start_background_task(_emit_scan_status_loop) # Phase 6: Automation progress socketio.start_background_task(_emit_automation_progress_loop) # Phase 7: Repair job progress socketio.start_background_task(_emit_repair_progress_loop) # Hydrabase auto-reconnect monitor socketio.start_background_task(_hydrabase_reconnect_loop) # API Rate Monitor — 1s push for speedometer gauges socketio.start_background_task(_emit_rate_monitor_loop) # Live log tail — streams new log lines to the log viewer socketio.start_background_task(_emit_live_log_loop) logger.info("WebSocket emitters started (Phase 1-7: global/dashboard/enrichment/tools/sync/automations/repair + rate monitor + live logs)") _runtime_started = True # Direct execution: python web_server.py (dev/Windows fallback) # Production should use: gunicorn -c gunicorn.conf.py wsgi:application if _DIRECT_RUN: web_run_host = os.environ.get('SOULSYNC_WEB_BIND_HOST', '0.0.0.0') web_run_port = int(os.environ.get('SOULSYNC_WEB_BIND_PORT', '8008')) display_host = '127.0.0.1' if web_run_host in {'0.0.0.0', '::'} else web_run_host logger.info("Starting SoulSync Web UI Server...") logger.info(f"Open your browser and navigate to http://{display_host}:{web_run_port}") logger.info("Tip: For production, use gunicorn -c gunicorn.conf.py wsgi:application") start_runtime_services() socketio.run(app, host=web_run_host, port=web_run_port, debug=False, allow_unsafe_werkzeug=True)