Add data file to database sync functionality

- Add get_all_series_from_data_files() to SeriesApp
- Sync series from data files to DB on startup
- Add unit tests for new SeriesApp method
- Add integration tests for sync functionality
- Update documentation
This commit is contained in:
2025-12-13 09:32:57 +01:00
parent 86eaa8a680
commit 684337fd0c
6 changed files with 855 additions and 0 deletions

View File

@@ -599,3 +599,56 @@ class SeriesApp:
looks up series by their unique key, not by folder name.
"""
return self.list.get_by_key(key)
def get_all_series_from_data_files(self) -> List[Serie]:
"""
Get all series from data files in the anime directory.
Scans the directory_to_search for all 'data' files and loads
the Serie metadata from each file. This method is synchronous
and can be wrapped with asyncio.to_thread if needed for async
contexts.
Returns:
List of Serie objects found in data files. Returns an empty
list if no data files are found or if the directory doesn't
exist.
Example:
series_app = SeriesApp("/path/to/anime")
all_series = series_app.get_all_series_from_data_files()
for serie in all_series:
print(f"Found: {serie.name} (key={serie.key})")
"""
logger.info(
"Scanning for data files in directory: %s",
self.directory_to_search
)
# Create a fresh SerieList instance for file-based loading
# This ensures we get all series from data files without
# interfering with the main instance's state
try:
temp_list = SerieList(
self.directory_to_search,
db_session=None, # Force file-based loading
skip_load=False # Allow automatic loading
)
except Exception as e:
logger.error(
"Failed to scan directory for data files: %s",
str(e),
exc_info=True
)
return []
# Get all series from the temporary list
all_series = temp_list.get_all()
logger.info(
"Found %d series from data files in %s",
len(all_series),
self.directory_to_search
)
return all_series

View File

@@ -41,6 +41,78 @@ from src.server.services.websocket_service import get_websocket_service
# module-level globals. This makes testing and multi-instance hosting safer.
async def _sync_series_to_database(
anime_directory: str,
logger
) -> int:
"""
Sync series from data files to the database.
Scans the anime directory for data files and adds any new series
to the database. Existing series are skipped (no duplicates).
Args:
anime_directory: Path to the anime directory with data files
logger: Logger instance for logging operations
Returns:
Number of new series added to the database
"""
try:
import asyncio
from src.core.entities.SerieList import SerieList
from src.core.SeriesApp import SeriesApp
from src.server.database.connection import get_db_session
# Get all series from data files using SeriesApp
series_app = SeriesApp(anime_directory)
all_series = await asyncio.to_thread(
series_app.get_all_series_from_data_files
)
if not all_series:
logger.info("No series found in data files to sync")
return 0
logger.info(
"Found %d series in data files, syncing to database...",
len(all_series)
)
async with get_db_session() as db:
serie_list = SerieList(
anime_directory,
db_session=db,
skip_load=True
)
added_count = 0
for serie in all_series:
result = await serie_list.add_to_db(serie, db)
if result:
added_count += 1
logger.debug(
"Added series to database: %s (key=%s)",
serie.name,
serie.key
)
# Commit happens automatically via get_db_session context
logger.info(
"Synced %d new series to database (skipped %d existing)",
added_count,
len(all_series) - added_count
)
return added_count
except Exception as e:
logger.warning(
"Failed to sync series to database: %s",
e,
exc_info=True
)
return 0
@asynccontextmanager
async def lifespan(app: FastAPI):
"""Manage application lifespan (startup and shutdown)."""
@@ -104,6 +176,11 @@ async def lifespan(app: FastAPI):
download_service = get_download_service()
await download_service.initialize()
logger.info("Download service initialized and queue restored")
# Sync series from data files to database
await _sync_series_to_database(
settings.anime_directory, logger
)
else:
logger.info(
"Download service initialization skipped - "