T-04: Encapsulate geo_service module-level mutable state in GeoCache class

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>
This commit is contained in:
2026-04-23 16:18:09 +02:00
parent fdfd24508f
commit 654dbdb000
10 changed files with 1035 additions and 889 deletions

View File

@@ -1,7 +1,7 @@
"""Geo cache flush background task.
Registers an APScheduler job that periodically persists newly resolved IP
geo entries from the in-memory ``_dirty`` set to the ``geo_cache`` table.
geo entries from the in-memory dirty set to the ``geo_cache`` table.
After Task 2 removed geo cache writes from GET requests, newly resolved IPs
are only held in the in-memory cache until this task flushes them. With the
@@ -15,7 +15,7 @@ from typing import TYPE_CHECKING
import structlog
from app.services import geo_service
from app.services.geo_cache import GeoCache
from app.tasks.db import task_db
from app.utils.runtime_state import get_effective_settings
@@ -33,21 +33,23 @@ GEO_FLUSH_INTERVAL: int = 60
JOB_ID: str = "geo_cache_flush"
async def _run_flush_with_settings(settings: Settings) -> None:
"""Flush the geo service dirty set to the application database.
async def _run_flush_with_resources(geo_cache: GeoCache, settings: Settings) -> None:
"""Flush the geo cache dirty set to the application database.
Args:
geo_cache: The application's GeoCache instance.
settings: The resolved application settings used for database access.
"""
async with task_db(settings) as db:
count = await geo_service.flush_dirty(db)
count = await geo_cache.flush_dirty(db)
if count > 0:
log.debug("geo_cache_flush_ran", flushed=count)
async def _run_flush(app: FastAPI) -> None:
await _run_flush_with_settings(get_effective_settings(app))
geo_cache: GeoCache = app.state.geo_cache
await _run_flush_with_resources(geo_cache, get_effective_settings(app))
def register(app: FastAPI) -> None:
@@ -60,12 +62,13 @@ def register(app: FastAPI) -> None:
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_flush_with_settings,
_run_flush_with_resources,
trigger="interval",
seconds=GEO_FLUSH_INTERVAL,
kwargs={"settings": settings},
kwargs={"geo_cache": geo_cache, "settings": settings},
id=JOB_ID,
replace_existing=True,
)

View File

@@ -10,8 +10,8 @@ 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 :func:`~app.services.geo_service.lookup_batch` which already
handles rate-limit throttling and retries.
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.
"""
@@ -21,7 +21,7 @@ from typing import TYPE_CHECKING
import structlog
from app.services import geo_service
from app.services.geo_cache import GeoCache
from app.tasks.db import task_db
from app.utils.runtime_state import get_effective_settings
@@ -40,16 +40,19 @@ GEO_RE_RESOLVE_INTERVAL: int = 600
JOB_ID: str = "geo_re_resolve"
async def _run_re_resolve_with_resources(settings: Settings, http_session: ClientSession) -> None:
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_service.get_unresolved_ips(db)
unresolved_ips = await geo_cache.get_unresolved_ips(db)
if not unresolved_ips:
log.debug("geo_re_resolve_skip", reason="no_unresolved_ips")
@@ -58,11 +61,11 @@ async def _run_re_resolve_with_resources(settings: Settings, http_session: Clien
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_service.clear_neg_cache()
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_service.lookup_batch(unresolved_ips, http_session, db=db)
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
@@ -75,7 +78,10 @@ async def _run_re_resolve_with_resources(settings: Settings, http_session: Clien
async def _run_re_resolve(app: FastAPI) -> None:
await _run_re_resolve_with_resources(get_effective_settings(app), app.state.http_session)
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:
@@ -91,12 +97,13 @@ def register(app: FastAPI) -> None:
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={"settings": settings, "http_session": app.state.http_session},
kwargs={"geo_cache": geo_cache, "settings": settings, "http_session": app.state.http_session},
id=JOB_ID,
replace_existing=True,
)