Files
planet/backend/tests/test_location_pipeline.py
linkong e1984c7a35 release: bump version to 0.49.0
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-08 17:42:27 +08:00

430 lines
14 KiB
Python

"""Tests for the shared location resolution pipeline.
Validates the abstraction itself: the protocol contract, the orchestrator,
each built-in resolver, and the pluggability promise (a custom resolver can
be slotted in without touching consumers).
"""
from __future__ import annotations
import json
from pathlib import Path
import pytest
from app.services.location import (
InheritFromAnotherEntityResolver,
LocationCandidate,
LocationPipeline,
LocationQuery,
NominatimResolver,
RegistryResolver,
ResolverOutput,
SourceCoordinatesResolver,
)
# ── Test fixtures ────────────────────────────────────────────────────
@pytest.fixture
def tmp_registry(tmp_path: Path) -> Path:
payload = {
"locations": [
{
"canonical_name": "Test Site Alpha",
"aliases": ["alpha", "alpha-one", "Acme HQ"],
"operator": "Acme Networks",
"site": "Acme HQ",
"city": "Lyon",
"country": "France",
"latitude": 45.764,
"longitude": 4.8357,
"precision": "site",
"confidence": 0.92,
"source_note": "Test fixture",
"verified_at": "2026-05-08",
},
{
"canonical_name": "Test Site Bravo",
"aliases": ["bravo"],
"operator": "Acme Networks",
"site": "Bravo POP",
"city": "Berlin",
"country": "Germany",
"latitude": 52.52,
"longitude": 13.405,
"precision": "city",
"confidence": 0.85,
},
],
"city_fallbacks": [
{
"city": "Bhutan-Capital",
"country": "Bhutan",
"latitude": 27.4728,
"longitude": 89.639,
"precision": "city",
"confidence": 0.5,
}
],
}
path = tmp_path / "registry.json"
path.write_text(json.dumps(payload), encoding="utf-8")
return path
# ── SourceCoordinatesResolver ────────────────────────────────────────
def test_source_coordinates_resolver_passes_through_valid_coordinates():
resolver = SourceCoordinatesResolver()
query = LocationQuery(
name="Acme HQ",
source_latitude=45.0,
source_longitude=4.0,
country="France",
)
output = resolver.resolve(query)
assert len(output.candidates) == 1
candidate = output.candidates[0]
assert candidate.latitude == 45.0
assert candidate.longitude == 4.0
assert candidate.precision == "precise"
assert candidate.source == "source_coordinates"
assert candidate.needs_confirmation is False
def test_source_coordinates_resolver_skips_zero_coordinates():
resolver = SourceCoordinatesResolver()
output = resolver.resolve(
LocationQuery(name="X", source_latitude=0.0, source_longitude=0.0)
)
assert output.candidates == ()
def test_source_coordinates_resolver_skips_when_missing():
resolver = SourceCoordinatesResolver()
output = resolver.resolve(LocationQuery(name="X"))
assert output.candidates == ()
# ── RegistryResolver ─────────────────────────────────────────────────
def test_registry_resolver_matches_alias(tmp_registry):
resolver = RegistryResolver(registry_path=tmp_registry)
resolver.reload()
output = resolver.resolve(
LocationQuery(name="alpha", country="France")
)
candidates = list(output.candidates)
assert candidates, "should match registry entry"
assert any(c.matched_location_name == "Test Site Alpha" for c in candidates)
alpha = next(c for c in candidates if c.matched_location_name == "Test Site Alpha")
assert alpha.precision == "site"
assert alpha.confidence == pytest.approx(0.92)
assert alpha.needs_confirmation is True
assert alpha.location_verified_at is None
def test_registry_resolver_filters_country_mismatch(tmp_registry):
resolver = RegistryResolver(registry_path=tmp_registry)
resolver.reload()
# alpha is in France; query says Spain → should reject
output = resolver.resolve(
LocationQuery(name="alpha", country="Spain")
)
assert all(
c.matched_location_name != "Test Site Alpha" for c in output.candidates
)
def test_registry_resolver_emits_city_fallback_candidate(tmp_registry):
resolver = RegistryResolver(registry_path=tmp_registry)
resolver.reload()
output = resolver.resolve(
LocationQuery(city="Bhutan-Capital", country="Bhutan")
)
candidates = list(output.candidates)
assert candidates, "city fallback should fire"
assert any(c.source == "local_registry_city" for c in candidates)
# ── NominatimResolver ───────────────────────────────────────────────
def test_nominatim_resolver_calls_geocoder_with_plan_queries():
calls = []
def fake_geocoder(query: str):
calls.append(query)
return {
"lat": "12.34",
"lon": "56.78",
"display_name": "Test City, Country",
"address": {"city": "Test City", "country": "Country"},
}
def plan(query: LocationQuery):
return [
("primary query", ("name",)),
("secondary query", ("city",)),
]
resolver = NominatimResolver(
query_plan_builder=plan,
geocoder=fake_geocoder,
)
output = resolver.resolve(LocationQuery(name="X", country="Country"))
assert calls == ["primary query", "secondary query"]
assert output.attempted_queries == ("primary query", "secondary query")
assert len(output.candidates) == 2
assert all(c.precision == "city" for c in output.candidates)
assert all(c.needs_confirmation for c in output.candidates)
def test_nominatim_resolver_skips_when_geocoder_returns_none():
resolver = NominatimResolver(
query_plan_builder=lambda q: [("only", ("name",))],
geocoder=lambda q: None,
)
output = resolver.resolve(LocationQuery(name="X"))
assert output.candidates == ()
assert output.attempted_queries == ("only",)
def test_nominatim_resolver_swallows_exceptions_per_query():
def boom(query):
raise RuntimeError("network down")
resolver = NominatimResolver(
query_plan_builder=lambda q: [("a", ()), ("b", ())],
geocoder=boom,
)
output = resolver.resolve(LocationQuery(name="X"))
assert output.candidates == ()
assert output.attempted_queries == ("a", "b")
# ── InheritFromAnotherEntityResolver ────────────────────────────────
def test_inherit_resolver_returns_provided_candidate():
sentinel = LocationCandidate(
latitude=10.0,
longitude=20.0,
display_name="Inherited",
precision="city",
confidence=0.7,
query="inherit::test",
source="inherited",
source_note=None,
matched_fields=("collector",),
needs_confirmation=False,
)
resolver = InheritFromAnotherEntityResolver(
source_lookup=lambda q: sentinel
)
output = resolver.resolve(LocationQuery(name="X"))
assert output.candidates == (sentinel,)
def test_inherit_resolver_skips_when_lookup_returns_none():
resolver = InheritFromAnotherEntityResolver(source_lookup=lambda q: None)
assert resolver.resolve(LocationQuery(name="X")).candidates == ()
# ── LocationPipeline orchestration ──────────────────────────────────
def test_pipeline_aggregates_candidates_across_resolvers(tmp_registry):
pipeline = LocationPipeline(
[
SourceCoordinatesResolver(),
RegistryResolver(registry_path=tmp_registry),
NominatimResolver(
query_plan_builder=lambda q: [("nominatim attempt", ("name",))],
geocoder=lambda q: {
"lat": "1.0",
"lon": "2.0",
"display_name": "Online City",
"address": {"city": "Online City", "country": "France"},
},
),
]
)
pipeline.resolvers[1].reload()
candidates, attempted = pipeline.collect_candidates(
LocationQuery(
name="alpha",
country="France",
source_latitude=44.0,
source_longitude=5.0,
)
)
sources = {c.source for c in candidates}
assert "source_coordinates" in sources
assert "local_registry" in sources
assert "nominatim_online_geocode" in sources
assert "nominatim attempt" in attempted
def test_pipeline_dedupes_by_source_and_coordinates():
same = LocationCandidate(
latitude=1.0,
longitude=2.0,
display_name="dup",
precision="city",
confidence=0.5,
query="x",
source="dup_source",
source_note=None,
matched_fields=(),
needs_confirmation=False,
)
class _DupResolver:
name = "dup_source"
def resolve(self, query):
return ResolverOutput(candidates=(same, same))
pipeline = LocationPipeline([_DupResolver()])
candidates, _ = pipeline.collect_candidates(LocationQuery(name="X"))
assert len(candidates) == 1
def test_registry_short_aliases_do_not_match_inside_larger_tokens(tmp_path: Path):
registry_path = tmp_path / "registry.json"
registry_path.write_text(
json.dumps(
{
"locations": [
{
"canonical_name": "Aurora",
"aliases": ["Aurora", "ANL"],
"site": "DOE/SC/Argonne National Laboratory",
"country": "United States",
"city": "Lemont",
"latitude": 41.713,
"longitude": -87.982,
"precision": "site",
},
{
"canonical_name": "Venado",
"aliases": ["Venado"],
"site": "DOE/NNSA/LANL",
"country": "United States",
"city": "Los Alamos",
"latitude": 35.8443,
"longitude": -106.2872,
"precision": "site",
},
],
"city_fallbacks": [],
}
),
encoding="utf-8",
)
resolver = RegistryResolver(registry_path=registry_path)
resolver.reload()
output = resolver.resolve(
LocationQuery(
name="Venado",
country="United States",
extra={"site": "DOE/NNSA/LANL"},
)
)
assert len(output.candidates) == 1
assert output.candidates[0].matched_location_name == "Venado"
def test_pipeline_resolve_best_returns_highest_priority():
online = LocationCandidate(
latitude=10.0,
longitude=20.0,
display_name="online",
precision="city",
confidence=0.9,
query="x",
source="nominatim_online_geocode",
source_note=None,
matched_fields=(),
needs_confirmation=True,
)
source = LocationCandidate(
latitude=11.0,
longitude=21.0,
display_name="src",
precision="precise",
confidence=1.0,
query="x",
source="source_coordinates",
source_note=None,
matched_fields=(),
needs_confirmation=False,
)
class _StubResolver:
def __init__(self, c, name):
self._c = c
self.name = name
def resolve(self, query):
return ResolverOutput(candidates=(self._c,))
pipeline = LocationPipeline(
[
_StubResolver(online, "online"),
_StubResolver(source, "src"),
]
)
result = pipeline.resolve_best(LocationQuery(name="X"))
assert result.location is source, "source_coordinates should beat nominatim"
def test_pipeline_returns_diagnostic_when_nothing_resolves():
pipeline = LocationPipeline([SourceCoordinatesResolver()])
result = pipeline.resolve_best(LocationQuery(name="X", country="Bhutan"))
assert result.location is None
assert result.diagnostic is not None
assert result.diagnostic.country == "Bhutan"
def test_pluggability_custom_resolver_works_without_changing_pipeline():
"""Validates the abstraction promise: a new algorithm = a new class."""
class _PeeringDBStubResolver:
name = "fake_peeringdb"
def resolve(self, query):
asn = (query.extra or {}).get("asn")
if asn != 174:
return ResolverOutput()
return ResolverOutput(
candidates=(
LocationCandidate(
latitude=1.0,
longitude=2.0,
display_name="Cogent HQ",
precision="site",
confidence=0.8,
query=f"peeringdb::{asn}",
source="peeringdb_stub",
source_note="Stub for testing",
matched_fields=("asn",),
needs_confirmation=False,
),
)
)
pipeline = LocationPipeline([_PeeringDBStubResolver()])
candidates, _ = pipeline.collect_candidates(
LocationQuery(name="X", extra={"asn": 174})
)
assert len(candidates) == 1
assert candidates[0].source == "peeringdb_stub"