Model/tests/orchestration/fakes.py
Khalim Conn-Kowlessar 48a488d1e9 refactor(orchestration): wire stages onto the UnitOfWork; per-stage commit (#1138)
Replaces the handler's whole-pipeline Session (one transaction across all
three stages, connection pinned during Ingestion's external IO) with a
Unit-of-Work per stage (ADR-0012, added here). Each stage runs its batch in
one unit and commits once; any property raising aborts the batch and the
subtask fails noisily.

- BaselineOrchestrator(unit_of_work, rebaseliner): one unit for the batch,
  commit once. Raise on a pre-SAP10 property leaves the unit uncommitted.
- IngestionOrchestrator(unit_of_work, epc_fetcher, geospatial_repo,
  solar_fetcher): fetch/write split — phase 1 fetches the whole batch (EPC /
  coords / solar) with NO unit open; phase 2 writes in one unit and commits.
  The connection is never held during external IO. Geospatial S3 repo stays
  injected (reference data, not transactional).
- Handler: module-scoped engine (pool reused across warm invocations) + a UoW
  factory; whole-pipeline `with Session` gone. `build_first_run_pipeline`
  composes on the factory. Source clients still behind the raising seam.
- ADR-0012 records the decision (per-stage boundary, all-or-nothing batch,
  idempotent re-run, fetch/write split, module-scoped engine). Modelling stub
  left untouched (no-op, no DB) per the ADR.

Tests: orchestrators on a shared FakeUnitOfWork (assert persisted batch +
exactly-once commit + no-commit-on-raise). New real-DB E2E integration test:
real PostgresUnitOfWork, Ingestion writes the EPC → Baseline reads it back
through the repo → re-run replaces, not duplicates (1 EPC row, 1 baseline row
after two runs). 121 pass in tests/; pyright strict clean; AAA.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-05-31 09:54:47 +00:00

110 lines
3.6 KiB
Python

"""In-memory fakes for orchestrator unit tests (no DB, no network).
A `FakeUnitOfWork` exposes dict-backed fake repos and records commits, so a
test can drive an orchestrator and then assert what was persisted and that the
batch committed exactly once (ADR-0012)."""
from __future__ import annotations
from types import TracebackType
from typing import Any, Optional
from datatypes.epc.domain.epc_property_data import EpcPropertyData
from domain.baseline.baseline_performance import BaselinePerformance
from domain.property.property import Property
from repositories.baseline.baseline_repository import BaselineRepository
from repositories.epc.epc_repository import EpcRepository
from repositories.property.property_repository import PropertyRepository
from repositories.solar.solar_repository import SolarRepository
from repositories.unit_of_work import UnitOfWork
class FakePropertyRepo(PropertyRepository):
def __init__(self, by_id: dict[int, Property]) -> None:
self._by_id = by_id
def get(self, property_id: int) -> Property:
return self._by_id[property_id]
class FakeEpcRepo(EpcRepository):
def __init__(self, by_property: Optional[dict[int, EpcPropertyData]] = None) -> None:
self.saved: list[tuple[EpcPropertyData, Optional[int]]] = []
self._by_property = by_property or {}
def save(
self,
data: EpcPropertyData,
property_id: Optional[int] = None,
portfolio_id: Optional[int] = None,
) -> int:
self.saved.append((data, property_id))
if property_id is not None:
self._by_property[property_id] = data
return len(self.saved)
def get(self, epc_property_id: int) -> EpcPropertyData: # pragma: no cover
raise NotImplementedError
def get_for_property(self, property_id: int) -> Optional[EpcPropertyData]:
return self._by_property.get(property_id)
class FakeSolarRepo(SolarRepository):
def __init__(self) -> None:
self.saved: list[tuple[int, dict[str, Any]]] = []
def save(self, property_id: int, insights: dict[str, Any]) -> None:
self.saved.append((property_id, insights))
def get(self, property_id: int) -> Optional[dict[str, Any]]: # pragma: no cover
raise NotImplementedError
class FakeBaselineRepo(BaselineRepository):
def __init__(self) -> None:
self.saved: list[tuple[BaselinePerformance, int]] = []
def save(self, baseline: BaselinePerformance, property_id: int) -> int:
self.saved.append((baseline, property_id))
return len(self.saved)
def get_for_property(
self, property_id: int
) -> Optional[BaselinePerformance]: # pragma: no cover
raise NotImplementedError
class FakeUnitOfWork(UnitOfWork):
"""A unit that holds in-memory repos and counts commits."""
def __init__(
self,
*,
property: FakePropertyRepo,
epc: Optional[FakeEpcRepo] = None,
solar: Optional[FakeSolarRepo] = None,
baseline: Optional[FakeBaselineRepo] = None,
) -> None:
self.property = property
self.epc = epc or FakeEpcRepo()
self.solar = solar or FakeSolarRepo()
self.baseline = baseline or FakeBaselineRepo()
self.commits = 0
def __enter__(self) -> "FakeUnitOfWork":
return self
def __exit__(
self,
exc_type: Optional[type[BaseException]],
exc: Optional[BaseException],
tb: Optional[TracebackType],
) -> None:
return None
def commit(self) -> None:
self.commits += 1
def rollback(self) -> None:
return None