mirror of
https://github.com/Hestia-Homes/Model.git
synced 2026-07-12 13:29:04 +00:00
118 lines
5 KiB
Python
118 lines
5 KiB
Python
from __future__ import annotations
|
|
|
|
from collections.abc import Callable
|
|
from dataclasses import dataclass
|
|
from typing import Any, Optional, Protocol
|
|
|
|
from datatypes.epc.domain.epc_property_data import EpcPropertyData
|
|
from domain.geospatial.spatial_reference import SpatialReference
|
|
from repositories.geospatial.geospatial_repository import GeospatialRepository
|
|
from repositories.unit_of_work import UnitOfWork
|
|
|
|
|
|
class EpcFetcher(Protocol):
|
|
"""The slice of the New-EPC-API client Ingestion needs (e.g. EpcClientService)."""
|
|
|
|
def get_by_uprn(self, uprn: int) -> Optional[EpcPropertyData]: ...
|
|
|
|
|
|
class SolarFetcher(Protocol):
|
|
"""The slice of the Google Solar client Ingestion needs (e.g. GoogleSolarApiClient)."""
|
|
|
|
def get_building_insights(
|
|
self, longitude: float, latitude: float
|
|
) -> dict[str, Any]: ...
|
|
|
|
|
|
@dataclass
|
|
class _Fetched:
|
|
"""One property's externally-fetched source data, awaiting the write phase."""
|
|
|
|
property_id: int
|
|
uprn: int
|
|
epc: Optional[EpcPropertyData]
|
|
solar_insights: Optional[dict[str, Any]]
|
|
spatial: Optional[SpatialReference]
|
|
|
|
|
|
class IngestionOrchestrator:
|
|
"""Stage 1: acquire a batch's external source data and persist it.
|
|
|
|
Runs in two phases so a DB connection is never held during external IO
|
|
(ADR-0012): **fetch** the whole batch — read each UPRN, fetch its EPC,
|
|
resolve its spatial reference (coordinates + planning protections) from the
|
|
Geospatial reference Repo, thread the coordinates into the Solar fetcher —
|
|
with *no unit open*; then **write** the batch in one Unit of Work and commit
|
|
once. Fetchers never call each other (ADR-0011); the orchestrator threads
|
|
the coordinate. The coordinates drive the Solar fetch transiently; the whole
|
|
spatial reference is cached per-UPRN in the transactional store so Modelling
|
|
reads the planning protections back off the Property (ADR-0020).
|
|
|
|
The geospatial repo reads S3 reference data, not the transactional store, so
|
|
it is injected separately rather than taken from the unit.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
*,
|
|
unit_of_work: Callable[[], UnitOfWork],
|
|
epc_fetcher: EpcFetcher,
|
|
geospatial_repo: GeospatialRepository,
|
|
solar_fetcher: SolarFetcher,
|
|
) -> None:
|
|
self._unit_of_work = unit_of_work
|
|
self._epc_fetcher = epc_fetcher
|
|
self._geospatial_repo = geospatial_repo
|
|
self._solar_fetcher = solar_fetcher
|
|
|
|
def run(self, property_ids: list[int]) -> None:
|
|
uprns = self._uprns_for(property_ids)
|
|
fetched = [self._fetch(property_id, uprn) for property_id, uprn in uprns]
|
|
self._persist(fetched)
|
|
|
|
def _uprns_for(self, property_ids: list[int]) -> list[tuple[int, int]]:
|
|
# A short read unit; properties with no UPRN (e.g. landlord_property_id
|
|
# only) are skipped — a later Site-Notes path covers them.
|
|
with self._unit_of_work() as uow:
|
|
properties = uow.property.get_many(property_ids)
|
|
return [
|
|
(property_id, prop.identity.uprn)
|
|
for property_id, prop in zip(property_ids, properties, strict=True)
|
|
if prop.identity.uprn is not None
|
|
]
|
|
|
|
def _fetch(self, property_id: int, uprn: int) -> _Fetched:
|
|
# No unit open here — this is the external-IO phase. One spatial
|
|
# reference lookup yields the coordinates (which drive the Solar fetch)
|
|
# and the planning protections (cached for Modelling, ADR-0020).
|
|
epc = self._epc_fetcher.get_by_uprn(uprn)
|
|
solar_insights: Optional[dict[str, Any]] = None
|
|
spatial: Optional[SpatialReference] = self._geospatial_repo.spatial_for(uprn)
|
|
if spatial is not None and spatial.coordinates is not None:
|
|
solar_insights = self._solar_fetcher.get_building_insights(
|
|
spatial.coordinates.longitude, spatial.coordinates.latitude
|
|
)
|
|
return _Fetched(property_id, uprn, epc, solar_insights, spatial)
|
|
|
|
def _persist(self, fetched: list[_Fetched]) -> None:
|
|
with self._unit_of_work() as uow:
|
|
for item in fetched:
|
|
if item.epc is not None:
|
|
uow.epc.save(item.epc, property_id=item.property_id)
|
|
# The live `solar` table is keyed by UPRN and needs the fetch's
|
|
# coordinates; insights are only set when those coordinates were
|
|
# resolved, so spatial.coordinates is non-None alongside them.
|
|
if (
|
|
item.solar_insights is not None
|
|
and item.spatial is not None
|
|
and item.spatial.coordinates is not None
|
|
):
|
|
uow.solar.save(
|
|
item.uprn,
|
|
longitude=item.spatial.coordinates.longitude,
|
|
latitude=item.spatial.coordinates.latitude,
|
|
insights=item.solar_insights,
|
|
)
|
|
if item.spatial is not None:
|
|
uow.spatial.save(item.uprn, item.spatial)
|
|
uow.commit()
|