Lukas
654dbdb000
Create GeoCache class with all mutable state as instance attributes: - _cache, _neg_cache, _dirty, _geoip_reader, _geoip_initialized, _cache_lock - All public methods: lookup(), lookup_batch(), lookup_cached_only(), flush_dirty(), load_from_db(), clear(), etc. Initialization & Dependency Injection: - Instantiate GeoCache in startup.py and store on app.state.geo_cache - Add get_geo_cache() dependency function in dependencies.py - Inject into routes and tasks via FastAPI's dependency system Backward Compatibility: - Maintain module-level functions in geo_service.py as deprecated wrappers - All old callers continue to work through _default_geo_cache instance - Remove test-escape-hatch functions (clear_cache, clear_neg_cache moved to methods) Background Tasks: - Update geo_cache_flush.py and geo_re_resolve.py to receive GeoCache instance - Tasks now operate on injected instance rather than module globals Tests: - Refactor test_geo_service.py with geo_cache fixture providing fresh instances - Update patch paths to target GeoCache methods correctly - Fix internal state assertions to access instance attributes Documentation: - Update Architekture.md to document GeoCache as managed stateful service - Describe cache lifecycle (load on startup, flush periodically, re-resolve stale) - Note process-local limitations for multi-worker deployments Fixes violation of Single Responsibility Principle: module no longer owns both lookup logic and cache lifecycle management. Cache is now a first-class injectable service with transparent lifecycle. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
111 lines
3.9 KiB
Python
111 lines
3.9 KiB
Python
"""Geo re-resolve background task.
|
|
|
|
Registers an APScheduler job that periodically retries IP addresses in the
|
|
``geo_cache`` table whose ``country_code`` is ``NULL``. These are IPs that
|
|
previously failed to resolve (e.g. due to ip-api.com rate limiting) and were
|
|
recorded as negative entries.
|
|
|
|
The task runs every 10 minutes. On each invocation it:
|
|
|
|
1. Queries all ``NULL``-country rows from ``geo_cache``.
|
|
2. Clears the in-memory negative cache so those IPs are eligible for a fresh
|
|
API attempt.
|
|
3. Delegates to :meth:`~app.services.geo_cache.GeoCache.lookup_batch` which
|
|
already handles rate-limit throttling and retries.
|
|
4. Logs how many IPs were retried and how many resolved successfully.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import TYPE_CHECKING
|
|
|
|
import structlog
|
|
|
|
from app.services.geo_cache import GeoCache
|
|
from app.tasks.db import task_db
|
|
from app.utils.runtime_state import get_effective_settings
|
|
|
|
if TYPE_CHECKING:
|
|
from aiohttp import ClientSession
|
|
from fastapi import FastAPI
|
|
|
|
from app.config import Settings
|
|
|
|
log: structlog.stdlib.BoundLogger = structlog.get_logger()
|
|
|
|
#: How often the re-resolve job fires (seconds). 10 minutes.
|
|
GEO_RE_RESOLVE_INTERVAL: int = 600
|
|
|
|
#: Stable APScheduler job ID — ensures re-registration replaces, not duplicates.
|
|
JOB_ID: str = "geo_re_resolve"
|
|
|
|
|
|
async def _run_re_resolve_with_resources(
|
|
geo_cache: GeoCache, settings: Settings, http_session: ClientSession
|
|
) -> None:
|
|
"""Query NULL-country IPs from the database and re-resolve them.
|
|
|
|
Args:
|
|
geo_cache: The application's GeoCache instance.
|
|
settings: The resolved application settings used for database access.
|
|
http_session: The shared aiohttp session used for external lookups.
|
|
"""
|
|
async with task_db(settings) as db:
|
|
# Fetch all IPs with NULL country_code from the persistent cache.
|
|
unresolved_ips = await geo_cache.get_unresolved_ips(db)
|
|
|
|
if not unresolved_ips:
|
|
log.debug("geo_re_resolve_skip", reason="no_unresolved_ips")
|
|
return
|
|
|
|
log.info("geo_re_resolve_start", unresolved=len(unresolved_ips))
|
|
|
|
# Clear the negative cache so these IPs are eligible for fresh API calls.
|
|
await geo_cache.clear_neg_cache()
|
|
|
|
# lookup_batch handles throttling, retries, and persistence when db is
|
|
# passed. This is a background task so DB writes are allowed.
|
|
results = await geo_cache.lookup_batch(unresolved_ips, http_session, db=db)
|
|
|
|
resolved_count: int = sum(
|
|
1 for info in results.values() if info.country_code is not None
|
|
)
|
|
log.info(
|
|
"geo_re_resolve_complete",
|
|
retried=len(unresolved_ips),
|
|
resolved=resolved_count,
|
|
)
|
|
|
|
|
|
async def _run_re_resolve(app: FastAPI) -> None:
|
|
geo_cache: GeoCache = app.state.geo_cache
|
|
await _run_re_resolve_with_resources(
|
|
geo_cache, get_effective_settings(app), app.state.http_session
|
|
)
|
|
|
|
|
|
def register(app: FastAPI) -> None:
|
|
"""Add (or replace) the geo re-resolve job in the application scheduler.
|
|
|
|
Must be called after the scheduler has been started (i.e., inside the
|
|
lifespan handler, after ``scheduler.start()``).
|
|
|
|
The first invocation is deferred by one full interval so the initial
|
|
blocklist prewarm has time to finish before re-resolve kicks in.
|
|
|
|
Args:
|
|
app: The :class:`fastapi.FastAPI` application instance whose
|
|
``app.state.scheduler`` will receive the job.
|
|
"""
|
|
geo_cache: GeoCache = app.state.geo_cache
|
|
settings = get_effective_settings(app)
|
|
app.state.scheduler.add_job(
|
|
_run_re_resolve_with_resources,
|
|
trigger="interval",
|
|
seconds=GEO_RE_RESOLVE_INTERVAL,
|
|
kwargs={"geo_cache": geo_cache, "settings": settings, "http_session": app.state.http_session},
|
|
id=JOB_ID,
|
|
replace_existing=True,
|
|
)
|
|
log.info("geo_re_resolve_scheduled", interval_seconds=GEO_RE_RESOLVE_INTERVAL)
|