mirror of
https://github.com/zvx-echo6/central.git
synced 2026-05-21 18:14:44 +02:00
feat(3-J): enrichment framework + GeocoderEnricher + NoOpBackend + FIRMS pilot
First of three PRs for v0.5.0 (J: framework; K: real geocoder backends +
doc revisions; L: operator events tab + per-adapter render + events-map fix).
Design pivot: the Phase 2 "no enrichment, upstream verbatim" reading of
Matt's principle is reframed — consumers can't do follow-up lookups, they
only see what's on the wire, so whatever Central doesn't enrich is
effectively missing downstream. Enrichment is now expected. The producer-doc
§2/§10.1 rewrite lands in PR K; this PR builds the framework PR K documents.
New package src/central/enrichment/:
- base.py Enricher Protocol (name + async enrich(location) -> dict).
- geocoder.py GeocoderEnricher + GeocoderBackend Protocol + the locked
GEOCODER_FIELDS set (name, city, county, state, country,
postal_code, timezone, landclass, elevation_m) + all_null_bundle().
- cache.py EnrichmentCache — stdlib sqlite3 off the event loop via
asyncio.to_thread (no async-sqlite dep). Keyed on
(enricher_name, lat_4dp, lon_4dp); per-enricher TTL (24h
default); fresh connection per op (sqlite3 isn't thread-safe
to share). Cache even all-null; never cache backend failures.
- backends/no_op.py NoOpBackend — all-null bundle, the PR J default.
Provenance: enrichment results land under event.data["_enriched"][<name>];
everything else in data stays upstream verbatim.
Wiring:
- adapter.py enrichment_locations: list[tuple[str,str]] = [] class attr.
Empty (default) = publish as-is, no enrichment.
- config_models.py EnrichmentConfig (enricher_class, backend_class,
backend_settings, cache_ttl_s). Read once at startup.
- supervisor.py build_enrichers() + apply_enrichment(); enrichment runs
after dedup, before wrap_event, in the poll loop. Class-name
registries for enricher/backend resolution (PR K extends).
- firms.py enrichment_locations = [("latitude","longitude")] — pilot.
Enrichment config is read once at supervisor startup; hot-reload is out of
scope for PR J (noted in EnrichmentConfig + build_enrichers docstrings).
Tests (16 new):
- test_enrichment_framework.py (9): parent-dir/table init, cache miss->hit,
TTL expiry, 4dp rounding, nearby-coord collapse, concurrent-set single-row,
backend-failure all-null-not-cached (retries), success cached (one backend
call), all-null cached.
- test_geocoder_enricher.py (5): NoOp all-null, field-set == GEOCODER_FIELDS,
null-coords short-circuit (no backend call), name=="geocoder", sequential
same-coords single backend call.
- test_firms.py (+2): enrichment_locations declared + paths resolve to floats
in a real event (structural, not literal); event through supervisor
apply_enrichment emerges with data._enriched.geocoder == all-null bundle.
Verification: full pytest 495 passed (was 479; +16). grep for
subject_for_event/_ADAPTER_REGISTRY clean. Module imports cleanly.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
parent
765c07aa7f
commit
d960d1f5e0
13 changed files with 685 additions and 1 deletions
|
|
@ -421,3 +421,58 @@ class TestApplyConfig:
|
|||
assert adapter._satellites == ["VIIRS_NOAA20_NRT"]
|
||||
|
||||
await adapter.shutdown()
|
||||
|
||||
|
||||
class TestEnrichmentIntegration:
|
||||
"""FIRMS is the PR J enrichment pilot."""
|
||||
|
||||
def test_enrichment_locations_declared_and_resolvable(self, temp_db_path, mock_config_store):
|
||||
"""FIRMS declares enrichment_locations and the declared paths actually
|
||||
resolve to coordinates in a real event's data — verified structurally,
|
||||
not by hardcoding the literal tuple."""
|
||||
locations = getattr(FIRMSAdapter, "enrichment_locations")
|
||||
assert isinstance(locations, list) and len(locations) >= 1
|
||||
for tup in locations:
|
||||
assert isinstance(tup, tuple) and len(tup) == 2
|
||||
assert all(isinstance(p, str) for p in tup)
|
||||
|
||||
config = make_adapter_config()
|
||||
adapter = FIRMSAdapter(
|
||||
config=config,
|
||||
config_store=mock_config_store,
|
||||
cursor_db_path=temp_db_path,
|
||||
)
|
||||
rows = adapter._parse_csv(SAMPLE_CSV, "VIIRS_SNPP_NRT")
|
||||
event = adapter._row_to_event(rows[0], "VIIRS_SNPP_NRT")
|
||||
# Every declared (lat_path, lon_path) must resolve to a float in data.
|
||||
for lat_path, lon_path in locations:
|
||||
assert isinstance(event.data.get(lat_path), float)
|
||||
assert isinstance(event.data.get(lon_path), float)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_event_passes_through_supervisor_enrichment(
|
||||
self, tmp_path, temp_db_path, mock_config_store
|
||||
):
|
||||
"""A FIRMS event run through the supervisor's enrichment stage emerges
|
||||
with data._enriched.geocoder populated (all-null under NoOpBackend)."""
|
||||
from central.config_models import EnrichmentConfig
|
||||
from central.enrichment.geocoder import all_null_bundle
|
||||
from central.supervisor import apply_enrichment, build_enrichers
|
||||
|
||||
config = make_adapter_config()
|
||||
adapter = FIRMSAdapter(
|
||||
config=config,
|
||||
config_store=mock_config_store,
|
||||
cursor_db_path=temp_db_path,
|
||||
)
|
||||
rows = adapter._parse_csv(SAMPLE_CSV, "VIIRS_SNPP_NRT")
|
||||
event = adapter._row_to_event(rows[0], "VIIRS_SNPP_NRT")
|
||||
assert "_enriched" not in event.data
|
||||
|
||||
enrichers = build_enrichers(
|
||||
EnrichmentConfig(), cache_db_path=tmp_path / "enrichment_cache.db"
|
||||
)
|
||||
await apply_enrichment(event, adapter.enrichment_locations, enrichers)
|
||||
|
||||
assert "_enriched" in event.data
|
||||
assert event.data["_enriched"]["geocoder"] == all_null_bundle()
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue