feat: implement real-time SSE event architecture with Redis stream integration and add associated validation tests

This commit is contained in:
2569718930@qq.com
2026-05-27 11:03:04 +08:00
parent 820dabfbf3
commit 573768846e
18 changed files with 1379 additions and 22 deletions
+52
View File
@@ -306,6 +306,58 @@ def test_hko_provider_marks_explicit_official_station_as_anchor():
assert snapshot["official_nearby"][0]["station_code"] == "LFS"
def test_hong_kong_cowin_primary_uses_station_6087_history(monkeypatch):
from src.database import runtime_state
requested = {}
class FakeOfficialIntradayObservationRepository:
def load_points(self, *, source_code, station_code, target_date):
requested["source_code"] = source_code
requested["station_code"] = station_code
requested["target_date"] = target_date
if source_code == "cowin_obs" and station_code == "6087":
return [
{"time": "10:40", "temp": 31.1},
{"time": "10:41", "temp": 31.3},
]
return []
monkeypatch.setattr(
runtime_state,
"OfficialIntradayObservationRepository",
FakeOfficialIntradayObservationRepository,
)
snapshot = build_country_network_snapshot(
"hong kong",
{
"cowin_current": {
"temp": 31.3,
"obs_time": "2026-05-27T02:41:00Z",
"istNo": "6087",
"icao": "COWIN6087",
"station_label": "保良局陳守仁小學 1min (CoWIN)",
},
"settlement_current": {
"station_code": "HKO",
"station_name": "HK Observatory",
"observation_time": "2026-05-27T10:40:00+08:00",
"current": {"temp": 31.2},
},
},
)
assert snapshot["airport_primary_current"]["source_code"] == "cowin_obs"
assert snapshot["airport_primary_current"]["station_code"] == "6087"
assert "陳守仁" in snapshot["airport_primary_current"]["station_label"]
assert requested["station_code"] == "6087"
assert snapshot["airport_primary_today_obs"] == [
{"time": "10:40", "temp": 31.1},
{"time": "10:41", "temp": 31.3},
]
def test_moscow_provider_uses_realtime_metar_cluster_not_station_archive_rows():
raw = {
"metar": {
@@ -0,0 +1,55 @@
import pytest
from web.realtime_event_store import RealtimeEventStore
from web.realtime_event_store_factory import create_realtime_event_store
from web.redis_realtime_event_store import RedisRealtimeEventStore
class FakeRedis:
pass
def test_event_store_factory_uses_sqlite_by_default(monkeypatch, tmp_path):
monkeypatch.delenv("POLYWEATHER_EVENT_STORE", raising=False)
store = create_realtime_event_store(db_path=str(tmp_path / "polyweather.db"))
assert isinstance(store, RealtimeEventStore)
def test_event_store_factory_uses_redis_when_configured(monkeypatch):
monkeypatch.setenv("POLYWEATHER_EVENT_STORE", "redis")
store = create_realtime_event_store(redis_client=FakeRedis())
assert isinstance(store, RedisRealtimeEventStore)
def test_event_store_factory_falls_back_to_sqlite_when_redis_is_optional(monkeypatch, tmp_path):
monkeypatch.setenv("POLYWEATHER_EVENT_STORE", "redis")
monkeypatch.setenv("POLYWEATHER_REDIS_REQUIRED", "false")
def broken_redis_store(**_kwargs):
raise RuntimeError("redis down")
store = create_realtime_event_store(
db_path=str(tmp_path / "polyweather.db"),
redis_store_builder=broken_redis_store,
)
assert isinstance(store, RealtimeEventStore)
assert getattr(store, "degraded_from", None) == "redis"
def test_event_store_factory_raises_when_redis_is_required(monkeypatch, tmp_path):
monkeypatch.setenv("POLYWEATHER_EVENT_STORE", "redis")
monkeypatch.setenv("POLYWEATHER_REDIS_REQUIRED", "true")
def broken_redis_store(**_kwargs):
raise RuntimeError("redis down")
with pytest.raises(RuntimeError, match="redis down"):
create_realtime_event_store(
db_path=str(tmp_path / "polyweather.db"),
redis_store_builder=broken_redis_store,
)
+125
View File
@@ -0,0 +1,125 @@
from web.redis_realtime_event_store import RedisRealtimeEventStore
from web.realtime_patch_schema import normalize_observation_patch
class FakeRedis:
def __init__(self):
self.counter = 0
self.entries = []
def eval(self, _script, _numkeys, stream_key, counter_key, *args):
(
maxlen,
event_type,
schema_type,
schema_version,
city,
source,
obs_time,
payload_json,
created_at_ms,
ts,
producer_id,
) = args
self.counter += 1
stream_id = f"{created_at_ms}-{self.counter}"
fields = {
"revision": str(self.counter),
"type": event_type,
"schema_type": schema_type,
"schema_version": str(schema_version),
"city": city,
"source": source,
"obs_time": obs_time,
"payload_json": payload_json,
"created_at_ms": str(created_at_ms),
"ts": str(ts),
"producer_id": producer_id,
}
self.entries.append((stream_id, fields))
trim_to = int(maxlen)
if trim_to > 0 and len(self.entries) > trim_to:
self.entries = self.entries[-trim_to:]
return [self.counter, stream_id]
def get(self, key):
if key == "counter:city_observation_revision":
return str(self.counter)
return None
def xrange(self, stream_key, min="-", max="+", count=None):
rows = list(self.entries)
if count is not None:
rows = rows[: int(count)]
return rows
def _event(city: str, temp: float, source: str = "cwa"):
return normalize_observation_patch(
{
"city": city,
"changes": {
"temp": temp,
"obs_time": "2026-05-27T10:00:00+08:00",
"source": source,
},
}
)
def test_redis_event_store_appends_monotonic_revisions_and_replays_by_city():
store = RedisRealtimeEventStore(redis_client=FakeRedis(), maxlen=10, producer_id="test")
taipei = store.append_event(_event("taipei", 34.2))
seoul = store.append_event(_event("seoul", 21.5, source="amos"))
taipei_next = store.append_event(_event("taipei", 34.4))
assert taipei["revision"] == 1
assert seoul["revision"] == 2
assert taipei_next["revision"] == 3
assert store.latest_revision() == 3
replay = store.replay_events(cities={"taipei"}, since_revision=1, limit=10)
assert [event["revision"] for event in replay] == [3]
assert replay[0]["city"] == "taipei"
assert replay[0]["payload"]["temp"] == 34.4
def test_redis_event_store_preserves_time_contract_on_replay():
store = RedisRealtimeEventStore(redis_client=FakeRedis(), maxlen=10, producer_id="test")
stored = store.append_event(
normalize_observation_patch(
{
"city": "toronto",
"changes": {
"temp": 26,
"obs_time": "2026-05-27T23:16:00Z",
"source": "metar",
},
}
)
)
replayed = store.replay_events(cities={"toronto"}, since_revision=0, limit=10)[0]
assert stored["observed_at_utc"] == "2026-05-27T23:16:00Z"
assert replayed["observed_at_local"] == "2026-05-27T19:16:00-04:00"
assert replayed["city_timezone"] == "America/Toronto"
def test_redis_event_store_reports_replay_gap_when_limit_is_exceeded():
store = RedisRealtimeEventStore(redis_client=FakeRedis(), maxlen=10, producer_id="test")
for temp in [30.0, 30.5, 31.0]:
store.append_event(_event("hong kong", temp, source="hko"))
replay = store.replay_events(cities={"hong kong"}, since_revision=0, limit=2)
assert [event["revision"] for event in replay] == [1, 2]
assert store.replay_requires_resync(
cities={"hong kong"},
since_revision=0,
replay_count=len(replay),
limit=2,
)
+49
View File
@@ -131,3 +131,52 @@ def test_replay_limit_is_bounded():
assert sse_router._bounded_replay_limit(0) == 1
assert sse_router._bounded_replay_limit(500) == 500
assert sse_router._bounded_replay_limit(5000) == 2000
def test_ingest_patch_uses_external_fanout_without_direct_broadcast(monkeypatch):
class FakeExternalStore:
uses_external_live_fanout = True
def __init__(self):
self.started = 0
def start_live_subscription(self, callback):
self.started += 1
self.callback = callback
def append_event(self, event):
return {
**event,
"revision": 12,
}
class FakeManager:
def __init__(self):
self.broadcasted = []
def broadcast_event(self, event):
self.broadcasted.append(event)
return event
store = FakeExternalStore()
manager = FakeManager()
monkeypatch.setattr(sse_router, "event_store", store)
monkeypatch.setattr(sse_router, "sse_manager", manager)
monkeypatch.setattr(sse_router, "_live_subscription_started", False)
response = TestClient(app).post(
"/api/internal/collector-patch",
json={
"city": "taipei",
"changes": {
"temp": 34.2,
"source": "cwa",
"obs_time": "2026-05-27T10:00:00+08:00",
},
},
)
assert response.status_code == 200
assert response.json()["revision"] == 12
assert store.started == 1
assert manager.broadcasted == []
+4
View File
@@ -36,6 +36,10 @@ def test_system_status_returns_summary_shape():
assert payload['probability']['engine_mode'] == 'legacy'
assert 'training_data' in payload
assert 'station_networks' in payload
assert 'realtime' in payload
assert payload['realtime']['store'] in {'sqlite', 'redis', 'degraded_sqlite'}
assert 'latest_revision' in payload['realtime']
assert 'sse_connections' in payload['realtime']
assert 'truth_records' in payload['training_data']
assert 'training_features' in payload['training_data']
assert 'city_coverage' in payload['training_data']