From 1885fed4bd6967350f4dc5a3d28d14595952b216 Mon Sep 17 00:00:00 2001 From: Lukas Date: Sun, 22 Feb 2026 17:32:40 +0100 Subject: [PATCH] clean Temp files after download and on server start --- docs/instructions.md | 295 +----------------------- src/core/providers/aniworld_provider.py | 28 +++ src/core/providers/enhanced_provider.py | 31 +++ src/server/fastapi_app.py | 24 +- 4 files changed, 84 insertions(+), 294 deletions(-) diff --git a/docs/instructions.md b/docs/instructions.md index a9f0d0b..4f98392 100644 --- a/docs/instructions.md +++ b/docs/instructions.md @@ -121,296 +121,5 @@ For each task completed: --- -### Task 0: Populate all required NFO tags during normal creation - -**Goal:** Ensure `create_tvshow_nfo()` writes every required tag from the start, so newly created NFOs are complete and never require a repair pass. All missing fields must be mapped inside `_tmdb_to_nfo_model()` in `src/core/services/nfo_service.py`. - -**Required tags currently missing from creation path:** - -| Field | Current state | Fix | -| --------------- | ---------------------- | --------------------------------------------------- | -| `originaltitle` | Never set | `tmdb_data.get("original_name")` | -| `year` | Never set | Extract 4-digit year from `first_air_date` | -| `plot` | May be empty | `tmdb_data.get("overview")` | -| `runtime` | Never set | `tmdb_data.get("episode_run_time", [None])[0]` | -| `premiered` | Never set | `tmdb_data.get("first_air_date")` | -| `status` | Never set | `tmdb_data.get("status")` | -| `imdbid` | Only `imdb_id` written | Add explicit `imdbid` field alongside `imdb_id` | -| `genre` | Not checked | Map each `tmdb_data["genres"]` entry | -| `studio` | Not checked | Map each `tmdb_data["networks"]` entry | -| `country` | Never set | `tmdb_data.get("origin_country", [])` | -| `actor` | Not checked | Map each `credits["cast"]` entry | -| `watched` | Pydantic default | Set explicitly to `False` | -| `tagline` | Never set | `tmdb_data.get("tagline")` | -| `outline` | Never set | Set equal to `plot` (same `overview` source) | -| `sorttitle` | Never set | Set equal to `title` | -| `dateadded` | Never set | `datetime.now().strftime("%Y-%m-%d %H:%M:%S")` | -| `mpaa` | Never set | Extract US rating from `content_ratings` via helper | - -**Implementation steps:** - -1. Open `src/core/services/nfo_service.py` — read the full file before making any changes -2. In `_tmdb_to_nfo_model()`, add assignments for all fields listed above and pass them to `TVShowNFO(...)` -3. Add `_extract_mpaa_rating(content_ratings)` helper — mirrors existing `_extract_fsk_rating` but looks for country code `"US"`; refactor both into `_extract_rating_by_country(content_ratings, country_code: str)` to eliminate duplication -4. Add `from datetime import datetime` import if not already present -5. No changes needed to `update_tvshow_nfo()` — it re-calls `_tmdb_to_nfo_model()` already -6. If `TVShowNFO` Pydantic model is missing fields (`originaltitle`, `outline`, `sorttitle`, `dateadded`, `mpaa`, `country`, `watched`), add them with `Optional[...]` defaults of `None` / `False` -7. Open `src/core/utils/nfo_generator.py` — read the full file before making changes -8. Confirm `_add_element` calls exist (ungated) for: `tagline`, `outline`, `sorttitle`, `dateadded`, `originaltitle`, `year`, `runtime`, `premiered`, `status`, `country`, `imdbid` -9. Verify `mpaa` fallback: prefer `fsk` when `nfo_prefer_fsk_rating=True` AND `fsk is not None`; otherwise write `mpaa` -10. Verify `_add_element` does NOT suppress `"false"` strings — `watched=False` must appear as `false` -11. Keep both files under 500 lines; if `nfo_service.py` exceeds limit, extract `_tmdb_to_nfo_model` into `src/core/utils/nfo_mapper.py` - -**Validation steps:** - -- Read the updated `_tmdb_to_nfo_model()` and confirm all 17 fields are explicitly assigned -- Read the updated `nfo_generator.py` and confirm every field has a corresponding `_add_element` call -- Delete a real series' `tvshow.nfo`, trigger creation, open result and cross-check every tag against `tvshow.nfo.good` -- Confirm no wildcard imports added (`from module import *`) -- Confirm both files stay under 500 lines (`wc -l src/core/services/nfo_service.py src/core/utils/nfo_generator.py`) - -**Test steps** — create `tests/unit/test_nfo_creation_tags.py`: - -- `test_tmdb_to_nfo_model_sets_originaltitle` -- `test_tmdb_to_nfo_model_sets_year_from_first_air_date` -- `test_tmdb_to_nfo_model_sets_plot_from_overview` -- `test_tmdb_to_nfo_model_sets_runtime` -- `test_tmdb_to_nfo_model_sets_premiered` -- `test_tmdb_to_nfo_model_sets_status` -- `test_tmdb_to_nfo_model_sets_imdbid` -- `test_tmdb_to_nfo_model_sets_genres` -- `test_tmdb_to_nfo_model_sets_studios_from_networks` -- `test_tmdb_to_nfo_model_sets_country` -- `test_tmdb_to_nfo_model_sets_actors` -- `test_tmdb_to_nfo_model_sets_watched_false` -- `test_tmdb_to_nfo_model_sets_tagline` -- `test_tmdb_to_nfo_model_sets_outline_from_overview` -- `test_tmdb_to_nfo_model_sets_sorttitle_from_name` -- `test_tmdb_to_nfo_model_sets_dateadded` -- `test_tmdb_to_nfo_model_sets_mpaa_from_content_ratings` -- `test_extract_rating_by_country_returns_us_rating` -- `test_extract_rating_by_country_returns_none_when_no_match` -- `test_extract_rating_by_country_handles_empty_results` -- `test_generate_nfo_includes_all_required_tags` — generate XML from a fully-populated `TVShowNFO`; parse with `lxml`; assert every required tag present -- `test_generate_nfo_writes_watched_false` — assert `false` not omitted -- `test_generate_nfo_minimal_model_does_not_crash` -- `test_generate_nfo_writes_fsk_over_mpaa_when_prefer_fsk` — both set, prefer_fsk=True → FSK value written -- `test_generate_nfo_writes_mpaa_when_no_fsk` — `fsk=None`, `mpaa="TV-14"`, prefer_fsk=True → `TV-14` - -```bash -conda run -n AniWorld python -m pytest tests/unit/test_nfo_creation_tags.py -v --tb=short -conda run -n AniWorld python -m pytest tests/ -v --tb=short -``` - -**Documentation steps:** - -- Update `docs/NFO_GUIDE.md` — add "Tag Reference" table: tag → TMDB source field → optional/required -- Add entry in `docs/CHANGELOG.md` under `[Unreleased]` -- Update `docs/ARCHITECTURE.md` under the NFO services section to reflect new fields and the `_extract_rating_by_country` helper - -**Commit step:** - -```bash -git add src/core/services/nfo_service.py src/core/utils/nfo_generator.py tests/unit/test_nfo_creation_tags.py docs/ -git commit -m "feat: write all required NFO tags on creation" -``` - -### Task 1: Create `NfoRepairService` — detect missing/empty NFO tags - -**Goal:** Implement a service that parses an existing `tvshow.nfo` file and determines whether required tags are missing or empty, compared to the Kodi/Jellyfin standard defined in `tvshow.nfo.good`. - -**Required tags to check** (must be present and non-empty): - -- `title`, `originaltitle`, `year`, `plot`, `runtime`, `premiered`, `status` -- `imdbid` (not just `imdb_id`) -- At least one `genre`, `studio`, `country`, `actor/name` -- `watched` - -**Implementation steps:** - -1. Create `src/core/services/nfo_repair_service.py` (max 500 lines, type hints, docstrings) -2. Define `REQUIRED_TAGS: dict[str, str]` — XPath expression → human-readable label for each required tag -3. Implement `def parse_nfo_tags(nfo_path: Path) -> dict` — uses `lxml.etree.parse()`, returns tag→value(s), silent on parse errors -4. Implement `def find_missing_tags(nfo_path: Path) -> list[str]` — calls `parse_nfo_tags()`, returns list of tag names that are absent or have empty text -5. Implement `def nfo_needs_repair(nfo_path: Path) -> bool` — returns `bool(find_missing_tags(nfo_path))` -6. Implement class `NfoRepairService`: - - `__init__(self, nfo_service: NFOService)` — inject existing `NFOService` - - `async def repair_series(self, series_path: Path, series_name: str) -> bool` — calls `nfo_needs_repair()`, logs which tags are missing, calls `nfo_service.update_tvshow_nfo(series_path, series_name)`, returns `True` if repair was triggered -7. Add structured logging at INFO level for: repair triggered (with list of missing tags), repair skipped, repair completed - -**Validation steps:** - -- Manually verify `find_missing_tags()` returns correct results when given `tvshow.nfo.bad` as input -- Manually verify `find_missing_tags()` returns an empty list when given `tvshow.nfo.good` as input -- Check that no imports are wildcard (`from module import *`) -- Check file stays under 500 lines - -**Test steps** — create `tests/unit/test_nfo_repair_service.py`: - -- `test_find_missing_tags_with_bad_nfo` — use fixture copying `tvshow.nfo.bad`; assert all 13 expected missing tags are returned -- `test_find_missing_tags_with_good_nfo` — use fixture copying `tvshow.nfo.good`; assert empty list returned -- `test_nfo_needs_repair_returns_true_for_bad_nfo` -- `test_nfo_needs_repair_returns_false_for_good_nfo` -- `test_repair_series_calls_update_when_nfo_needs_repair` — mock `NFOService.update_tvshow_nfo`; assert it is called exactly once -- `test_repair_series_skips_when_nfo_is_complete` — mock `NFOService.update_tvshow_nfo`; assert it is NOT called -- `test_parse_nfo_tags_handles_missing_file_gracefully` — pass nonexistent path; expect empty dict or graceful return -- `test_parse_nfo_tags_handles_malformed_xml_gracefully` — pass file with invalid XML; expect graceful return - -**Run tests:** - -```bash -conda run -n AniWorld python -m pytest tests/unit/test_nfo_repair_service.py -v --tb=short -``` - -**Documentation steps:** - -- Add entry for `NfoRepairService` in `docs/ARCHITECTURE.md` under the NFO services section -- Add entry in `docs/CHANGELOG.md` under a new `[Unreleased]` section - -**Commit step:** - -``` -git add src/core/services/nfo_repair_service.py tests/unit/test_nfo_repair_service.py docs/ -git commit -m "feat: add NfoRepairService for missing NFO tag detection" -``` - ---- - -### Task 2: Add `perform_nfo_repair_scan()` startup hook in `initialization_service.py` - -**Goal:** Add a new async function that runs every startup (not run-once), scans all series folders for NFOs with missing tags, and queues repair tasks via `BackgroundLoaderService`. - -**Implementation steps:** - -1. Open `src/server/services/initialization_service.py` -2. Add import for `NfoRepairService` from `src.core.services.nfo_repair_service` -3. Implement `async def perform_nfo_repair_scan(background_loader=None) -> None`: - - Guard: if `not settings.tmdb_api_key` → log warning and return early - - Guard: if `not settings.anime_directory` → log warning and return early - - Create `NfoRepairService` instance using `NFOServiceFactory` (follow same pattern as existing `perform_nfo_scan_if_needed()`) - - Iterate all subdirectories in `settings.anime_directory` - - For each series folder that contains a `tvshow.nfo`: call `nfo_needs_repair(nfo_path)` - - If repair needed: queue via `background_loader.add_series_loading_task()` (non-blocking), or call `repair_service.repair_series()` directly if no background_loader provided - - Log summary at INFO level: `"NFO repair scan complete: X of Y series queued for repair"` -4. Keep function under 60 lines; extract helpers if needed - -**Validation steps:** - -- Read the function and confirm it does NOT use a run-once DB flag (unlike `perform_nfo_scan_if_needed`) -- Confirm both guards (tmdb_api_key, anime_directory) are present -- Confirm the function is async and uses `await` where needed -- Confirm `initialization_service.py` stays under 500 lines after the addition - -**Test steps** — add to `tests/unit/test_initialization_service.py` (create if not exists): - -- `test_perform_nfo_repair_scan_skips_without_tmdb_api_key` — patch `settings.tmdb_api_key = ""`; assert no repair is attempted -- `test_perform_nfo_repair_scan_skips_without_anime_directory` — patch `settings.anime_directory = ""`; assert no repair is attempted -- `test_perform_nfo_repair_scan_queues_deficient_series` — create temp dir with one bad NFO; mock `NfoRepairService.nfo_needs_repair` returning True; assert background_loader is called -- `test_perform_nfo_repair_scan_skips_complete_series` — create temp dir with one good NFO; mock `nfo_needs_repair` returning False; assert background_loader NOT called - -**Run tests:** - -```bash -conda run -n AniWorld python -m pytest tests/unit/test_initialization_service.py -v --tb=short -``` - -**Documentation steps:** - -- Update `docs/ARCHITECTURE.md` startup sequence diagram/description to include the new `perform_nfo_repair_scan` step -- Add note in `docs/CONFIGURATION.md` that `tmdb_api_key` is required for the repair scan - -**Commit step:** - -``` -git add src/server/services/initialization_service.py tests/unit/test_initialization_service.py docs/ -git commit -m "feat: add perform_nfo_repair_scan startup hook" -``` - ---- - -### Task 3: Wire `perform_nfo_repair_scan` into `fastapi_app.py` lifespan - -**Goal:** Call the new repair scan on every application startup, after the existing NFO creation scan. - -**Implementation steps:** - -1. Open `src/server/fastapi_app.py` -2. Add `perform_nfo_repair_scan` to the existing import from `src.server.services.initialization_service` -3. In the `lifespan()` async context manager, after the line `await perform_nfo_scan_if_needed()`, add: - ``` - await perform_nfo_repair_scan(background_loader) - ``` - (pass the `background_loader` instance so repairs are queued non-blocking) -4. Confirm the call is inside the startup block (before `yield`), not in the shutdown block - -**Validation steps:** - -- Read `fastapi_app.py` and confirm ordering: `perform_nfo_scan_if_needed` runs before `perform_nfo_repair_scan` -- Confirm `background_loader` is instantiated before the repair scan call -- Start the server locally and check logs for `"NFO repair scan"` log lines -- Confirm app boot completes without errors even if TMDB key is missing - -**Test steps** — add to `tests/integration/test_nfo_repair_startup.py` (new file): - -- `test_startup_triggers_nfo_repair_scan` — use TestClient with lifespan; mock `perform_nfo_repair_scan`; assert it was called once during startup -- `test_startup_repair_scan_receives_background_loader` — assert `perform_nfo_repair_scan` is called with a non-None `background_loader` argument - -**Run tests:** - -```bash -conda run -n AniWorld python -m pytest tests/integration/test_nfo_repair_startup.py -v --tb=short -``` - -**Full regression test — run all tests and confirm nothing broken:** - -```bash -conda run -n AniWorld python -m pytest tests/ -v --tb=short -``` - -**Documentation steps:** - -- Update startup sequence in `docs/ARCHITECTURE.md` to add the new step after `perform_nfo_scan_if_needed` -- Update `docs/CHANGELOG.md` unreleased section with the wiring change - -**Commit step:** - -``` -git add src/server/fastapi_app.py tests/integration/test_nfo_repair_startup.py docs/ -git commit -m "feat: wire NFO repair scan into app startup lifespan" -``` - ---- - -### Task 4: End-to-end validation of NFO repair - -**Goal:** Prove the full flow works with a real (or realistic) deficient NFO file. - -**Validation steps:** - -1. Copy `tvshow.nfo.bad` into a test series folder inside `settings.anime_directory` -2. Ensure `tmdb_api_key` is configured in `data/config.json` -3. Start the server: `conda run -n AniWorld python -m uvicorn src.server.fastapi_app:app --host 127.0.0.1 --port 8000 --reload` -4. Wait for background tasks to complete (check WebSocket or logs) -5. Open the repaired `tvshow.nfo` and confirm all previously missing tags are now present and non-empty -6. Restart the server and confirm the repair scan runs again but does NOT re-queue series whose NFO is already complete (verify via logs: `"0 of Y series queued for repair"`) -7. Place `tvshow.nfo.good` in the same folder; restart; confirm it is NOT queued for repair - -**Run full test suite one final time:** - -```bash -conda run -n AniWorld python -m pytest tests/ -v --tb=short -``` - -**Final documentation steps:** - -- Review `docs/NFO_GUIDE.md` and add a section "Automatic NFO Repair" explaining the startup scan, which tags are checked, and how to trigger a manual repair via the API (`/api/nfo/update/{series}`) -- Update `docs/CHANGELOG.md` to move all unreleased entries under a dated release heading `[1.x.x] - 2026-02-22` - -**Final commit step:** - -``` -git add docs/ -git commit -m "docs: document NFO repair feature" -``` - ---- +1. ✅ On each download make sure the Temp files are deleted. +2. ✅ on each server start clean Temp folder diff --git a/src/core/providers/aniworld_provider.py b/src/core/providers/aniworld_provider.py index 19f743a..bfac3b3 100644 --- a/src/core/providers/aniworld_provider.py +++ b/src/core/providers/aniworld_provider.py @@ -21,6 +21,31 @@ from yt_dlp.utils import DownloadCancelled from ..interfaces.providers import Providers from .base_provider import Loader + +def _cleanup_temp_file(temp_path: str) -> None: + """Clean up a temp file and any associated partial download files. + + Removes the temp file itself and any yt-dlp partial files + (e.g. ``.part``) that may have been left behind. + + Args: + temp_path: Absolute or relative path to the temp file. + """ + paths_to_remove = [temp_path] + # yt-dlp writes partial fragments to .part + paths_to_remove.extend( + str(p) for p in Path(temp_path).parent.glob( + Path(temp_path).name + ".*" + ) + ) + for path in paths_to_remove: + if os.path.exists(path): + try: + os.remove(path) + logging.debug(f"Removed temp file: {path}") + except OSError as exc: + logging.warning(f"Failed to remove temp file {path}: {exc}") + # Imported shared provider configuration from .provider_config import ( ANIWORLD_HEADERS, @@ -345,17 +370,20 @@ class AniworldLoader(Loader): f"Broken pipe error with provider {provider}: {e}. " f"This usually means the stream connection was closed." ) + _cleanup_temp_file(temp_path) continue except Exception as e: logging.error( f"YoutubeDL download failed with provider {provider}: " f"{type(e).__name__}: {e}" ) + _cleanup_temp_file(temp_path) continue break # If we get here, all providers failed logging.error("All download providers failed") + _cleanup_temp_file(temp_path) self.clear_cache() return False diff --git a/src/core/providers/enhanced_provider.py b/src/core/providers/enhanced_provider.py index 21731ac..34ad3d7 100644 --- a/src/core/providers/enhanced_provider.py +++ b/src/core/providers/enhanced_provider.py @@ -43,6 +43,33 @@ from .provider_config import ( ) +def _cleanup_temp_file( + temp_path: str, + logger: Optional[logging.Logger] = None, +) -> None: + """Remove a temp file and any associated yt-dlp partial files. + + Args: + temp_path: Path to the primary temp file. + logger: Optional logger for diagnostic messages. + """ + _log = logger or logging.getLogger(__name__) + candidates = [temp_path] + # yt-dlp creates fragment files like .part + candidates.extend( + str(p) for p in Path(temp_path).parent.glob( + Path(temp_path).name + ".*" + ) + ) + for path in candidates: + if os.path.exists(path): + try: + os.remove(path) + _log.debug(f"Removed temp file: {path}") + except OSError as exc: + _log.warning(f"Failed to remove temp file {path}: {exc}") + + class EnhancedAniWorldLoader(Loader): """Aniworld provider with retry and recovery strategies. @@ -596,9 +623,13 @@ class EnhancedAniWorldLoader(Loader): except Exception as e: self.logger.warning(f"Provider {provider_name} failed: {e}") + # Clean up any partial temp files left by this failed attempt + _cleanup_temp_file(temp_path, self.logger) self.download_stats['retried_downloads'] += 1 continue + # All providers failed – make sure no temp remnants are left behind + _cleanup_temp_file(temp_path, self.logger) return False def _perform_ytdl_download( diff --git a/src/server/fastapi_app.py b/src/server/fastapi_app.py index 33dc727..b38ad2c 100644 --- a/src/server/fastapi_app.py +++ b/src/server/fastapi_app.py @@ -126,7 +126,29 @@ async def lifespan(_application: FastAPI): startup_error = None try: logger.info("Starting FastAPI application...") - + + # Clean up any leftover temp download files from a previous run + try: + import shutil as _shutil + _temp_dir = Path(__file__).resolve().parents[2] / "Temp" + if _temp_dir.exists(): + _removed = 0 + for _item in _temp_dir.iterdir(): + try: + if _item.is_file(): + _item.unlink() + elif _item.is_dir(): + _shutil.rmtree(_item) + _removed += 1 + except OSError as _exc: + logger.warning("Could not remove temp item %s: %s", _item, _exc) + logger.info("Cleaned %d item(s) from Temp folder on startup", _removed) + else: + _temp_dir.mkdir(parents=True, exist_ok=True) + logger.debug("Created Temp folder: %s", _temp_dir) + except Exception as _exc: + logger.warning("Failed to clean Temp folder on startup: %s", _exc) + # Initialize database first (required for other services) try: from src.server.database.connection import init_db