Files
BanGUI/backend/app/tasks/geo_cache_cleanup.py
Lukas 7ec80fdeec refactor(logging): replace structlog with stdlib logging compat layer
- Remove structlog dependency from backend/pyproject.toml
- Add app.utils.logging_compat shim for keyword-arg logging API
- Add app.utils.json_formatter for JSON log output with extra fields
- Update all backend modules to use logging_compat.get_logger()
- Update docstrings in log_sanitizer.py and json_formatter.py
- Update test comment in test_async_utils.py
- Record 406 failing tests in Docs/Tasks.md for tracking
2026-05-10 13:37:54 +02:00

136 lines
4.6 KiB
Python

"""Geo cache cleanup background task.
Registers an APScheduler job that periodically removes stale entries from the
``geo_cache`` table — entries that have not been referenced in the configured
retention period (default: 90 days). This prevents unbounded growth of the
database file and maintains query performance on geo lookups.
When a stale IP is encountered again after purge, it will be re-resolved from
the MaxMind database or ip-api.com (if configured), which is acceptable.
Correlation IDs are propagated through the task using :mod:`app.utils.correlation`
so that task logs can be correlated across runs.
"""
from __future__ import annotations
import uuid
from datetime import UTC, datetime, timedelta
from typing import TYPE_CHECKING
from app.utils.logging_compat import get_logger
from app.repositories import geo_cache_repo
from app.tasks.db import task_db
from app.tasks.timeout_utils import run_with_timeout
from app.utils.correlation import get_correlation_id, reset_correlation_id, set_correlation_id
from app.utils.runtime_state import get_effective_settings
if TYPE_CHECKING:
from fastapi import FastAPI
from app.config import Settings
log = get_logger(__name__)
#: How long to retain geo cache entries (days). Configurable tuning constant.
GEO_CACHE_RETENTION_DAYS: int = 90
#: How often the cleanup job fires (seconds). Default: once per day.
GEO_CLEANUP_INTERVAL: int = 24 * 60 * 60
#: Stable APScheduler job ID — ensures re-registration replaces, not duplicates.
JOB_ID: str = "geo_cache_cleanup"
#: Maximum seconds to allow for geo cache cleanup to complete.
TASK_TIMEOUT_SECONDS: int = 60
async def _run_cleanup_with_resources(
settings: Settings,
correlation_id: str | None = None,
) -> None:
"""Delete stale entries from the geo cache.
Calculates a cutoff timestamp (now - retention period) and removes all
entries with ``last_seen`` before that time. Logs the operation result.
Args:
settings: The resolved application settings used for database access.
correlation_id: Optional correlation ID for log correlation.
"""
if correlation_id is None:
correlation_id = str(uuid.uuid4())
token = set_correlation_id(correlation_id)
try:
await _do_cleanup_with_settings(settings)
finally:
reset_correlation_id(token)
async def _do_cleanup_with_settings(settings: Settings) -> None:
"""Inner cleanup logic that runs with correlation context set."""
async def _do_cleanup() -> None:
cutoff_dt = datetime.now(UTC) - timedelta(days=GEO_CACHE_RETENTION_DAYS)
cutoff_iso = cutoff_dt.strftime("%Y-%m-%dT%H:%M:%SZ")
async with task_db(settings) as db:
deleted = await geo_cache_repo.delete_stale_entries(db, cutoff_iso)
await db.commit()
if deleted > 0:
log.info(
"geo_cache_cleanup_ran",
correlation_id=get_correlation_id(),
deleted=deleted,
retention_days=GEO_CACHE_RETENTION_DAYS,
)
else:
log.debug(
"geo_cache_cleanup_ran",
correlation_id=get_correlation_id(),
deleted=deleted,
retention_days=GEO_CACHE_RETENTION_DAYS,
)
await run_with_timeout("geo_cache_cleanup", _do_cleanup(), TASK_TIMEOUT_SECONDS)
async def _run_cleanup(app: FastAPI) -> None:
"""Run cleanup with application settings."""
await _run_cleanup_with_resources(get_effective_settings(app))
def register(app: FastAPI) -> None:
"""Add (or replace) the geo cache cleanup job in the application scheduler.
Must be called after the scheduler has been started (i.e., inside the
lifespan handler, after ``scheduler.start()``).
Args:
app: The :class:`fastapi.FastAPI` application instance whose
``app.state.scheduler`` will receive the job.
"""
settings = get_effective_settings(app)
scheduler = getattr(app.state, "scheduler", None)
if scheduler is None:
# In tests or standalone usage, scheduler may not be on app.state yet.
# Use a no-op fallback — the heartbeat won't be registered but no crash.
log.warning("geo_cache_cleanup_no_scheduler")
return
scheduler.add_job(
_run_cleanup_with_resources,
trigger="interval",
seconds=GEO_CLEANUP_INTERVAL,
kwargs={"settings": settings},
id=JOB_ID,
replace_existing=True,
)
log.info(
"geo_cache_cleanup_scheduled",
interval_seconds=GEO_CLEANUP_INTERVAL,
retention_days=GEO_CACHE_RETENTION_DAYS,
)