lukas.pupkalipinski/Aniworld
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: task 1.5 poster check + fix stuck tests

Browse Source 
- Fix structlog format string in folder_scan_service (%(key)d -> kwargs)
- Add nfo_download_poster setting check before poster download
- Create missing NFO fixture files (tvshow.nfo.bad/good) for repair tests
- Fix test_context_used_in_logging to check all call args not format string
- Fix test_system_settings_integration isolation via reset_all_scans
This commit is contained in:
Lukas
2026-05-13 08:07:16 +02:00
parent eb2fc3c5ab
commit eb0e6e8ccb
5 changed files with 230 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

199
src/server/services/folder_scan_service.py
View File

@@ -11,7 +11,9 @@ from pathlib import Path
from typing import Optional
import structlog
from lxml import etree
from src.core.utils.image_downloader import ImageDownloader
from src.server.services.initialization_service import perform_nfo_repair_scan
logger = structlog.get_logger(__name__)
@@ -19,6 +21,9 @@ logger = structlog.get_logger(__name__)
# Module-level semaphore to limit concurrent TMDB operations to 3.
_TMDB_SEMAPHORE: asyncio.Semaphore = asyncio.Semaphore(3)
# Semaphore to limit concurrent poster image downloads to 3.
_POSTER_DOWNLOAD_SEMAPHORE: asyncio.Semaphore = asyncio.Semaphore(3)
class FolderScanServiceError(Exception):
"""Service-level exception for folder-scan operations."""
@@ -49,11 +54,203 @@ class FolderScanService:
await perform_nfo_repair_scan(background_loader=None)
logger.info("NFO repair scan queued; repairs will continue in background")
# Sub-tasks 1.4–1.5 will fill in the actual work here.
# 1.4 — Validate and rename series folders after NFO repair.
logger.info("Starting folder rename validation")
from src.server.services.folder_rename_service import (
validate_and_rename_series_folders,
)
rename_stats = await validate_and_rename_series_folders()
logger.info(
"Folder rename validation complete",
scanned=rename_stats["scanned"],
renamed=rename_stats["renamed"],
skipped=rename_stats["skipped"],
errors=rename_stats["errors"],
)
# 1.5 — Check and download missing poster.jpg files.
logger.info("Starting poster check")
poster_stats = await self.check_and_download_missing_posters()
logger.info(
"Poster check complete",
scanned=poster_stats["scanned"],
downloaded=poster_stats["downloaded"],
skipped=poster_stats["skipped"],
errors=poster_stats["errors"],
)
logger.info("Folder scan completed")
except Exception as exc: # pylint: disable=broad-exception-caught
logger.error("Folder scan failed", error=str(exc), exc_info=True)
# ------------------------------------------------------------------
# Poster check helpers
# ------------------------------------------------------------------
async def check_and_download_missing_posters(self) -> dict[str, int]:
"""Iterate over series folders and download missing poster.jpg files.
For each folder containing a ``tvshow.nfo``:
1. Check if ``poster.jpg`` exists and is at least
:attr:`ImageDownloader.min_file_size` bytes.
2. If missing or too small, parse ``tvshow.nfo`` for a ``<thumb>``
URL (preferring ``aspect="poster"``).
3. Download the image via :class:`ImageDownloader` under a
semaphore that limits concurrency to 3.
Returns:
Dictionary with counts:
- ``"scanned"``: total folders scanned
- ``"downloaded"``: posters successfully downloaded
- ``"skipped"``: folders skipped (no NFO, no thumb URL,
or poster already valid)
- ``"errors"``: folders that caused a download error
"""
from src.config.settings import settings # noqa: PLC0415
stats = {"scanned": 0, "downloaded": 0, "skipped": 0, "errors": 0}
if not settings.anime_directory:
logger.warning("Poster check skipped — anime directory not configured")
return stats
anime_dir = Path(settings.anime_directory)
if not anime_dir.is_dir():
logger.warning(
"Poster check skipped — anime directory not found: %s", anime_dir
)
return stats
# Gather all series directories that contain a tvshow.nfo
series_dirs = [
d for d in anime_dir.iterdir()
if d.is_dir() and (d / "tvshow.nfo").exists()
]
if not series_dirs:
logger.debug("No series folders found for poster check")
return stats
# Process each series folder concurrently with semaphore
tasks = [
self._check_and_download_poster(series_dir, stats)
for series_dir in series_dirs
]
await asyncio.gather(*tasks, return_exceptions=True)
return stats
async def _check_and_download_poster(
self, series_dir: Path, stats: dict[str, int]
) -> None:
"""Check and download poster for a single series folder.
Args:
series_dir: Path to the series folder.
stats: Mutable stats dictionary to update.
"""
stats["scanned"] += 1
poster_path = series_dir / "poster.jpg"
# Check if poster already exists and is large enough
if poster_path.exists():
try:
# Default min_file_size from ImageDownloader is 1024 bytes (1 KB)
if poster_path.stat().st_size >= 1024:
logger.debug(
"Poster already valid for '%s'", series_dir.name
)
stats["skipped"] += 1
return
except OSError:
pass # Fall through to re-download
# Parse NFO for thumb URL
nfo_path = series_dir / "tvshow.nfo"
poster_url = self._extract_poster_url_from_nfo(nfo_path)
if not poster_url:
logger.info(
"No poster URL found in NFO for '%s', skipping",
series_dir.name,
)
stats["skipped"] += 1
return
# Respect the nfo_download_poster setting
from src.config.settings import settings as app_settings # noqa: PLC0415
if not app_settings.nfo_download_poster:
logger.debug(
"Poster download disabled by nfo_download_poster setting for '%s'",
series_dir.name,
)
stats["skipped"] += 1
return
# Download poster with semaphore
async with _POSTER_DOWNLOAD_SEMAPHORE:
try:
async with ImageDownloader() as downloader:
success = await downloader.download_poster(
poster_url, series_dir, skip_existing=False
)
if success:
logger.info(
"Downloaded poster for '%s'", series_dir.name
)
stats["downloaded"] += 1
else:
logger.warning(
"Failed to download poster for '%s'", series_dir.name
)
stats["errors"] += 1
except Exception as exc: # pylint: disable=broad-except
logger.error(
"Error downloading poster for '%s': %s",
series_dir.name,
exc,
)
stats["errors"] += 1
@staticmethod
def _extract_poster_url_from_nfo(nfo_path: Path) -> Optional[str]:
"""Parse tvshow.nfo and extract the poster thumb URL.
Prefers ``<thumb aspect="poster">``; falls back to the first
``<thumb>`` element if no aspect attribute is present.
Args:
nfo_path: Absolute path to the ``tvshow.nfo`` file.
Returns:
The poster URL string, or ``None`` if not found.
"""
if not nfo_path.exists():
return None
try:
tree = etree.parse(str(nfo_path))
root = tree.getroot()
# Prefer thumb with aspect="poster"
for thumb in root.findall(".//thumb"):
if thumb.get("aspect") == "poster" and thumb.text:
return thumb.text.strip()
# Fallback to first thumb with text
for thumb in root.findall(".//thumb"):
if thumb.text:
return thumb.text.strip()
return None
except etree.XMLSyntaxError:
logger.warning("Malformed XML in %s", nfo_path)
return None
except Exception: # pylint: disable=broad-except
return None
# ------------------------------------------------------------------
# Private helpers
# ------------------------------------------------------------------