mirror of
https://github.com/Hestia-Homes/Model.git
synced 2026-06-08 11:17:27 +00:00
3998ef586c
Add Coordinates value object + GeospatialRepository port + GeospatialS3Repository adapter. Resolves a Property's lon/lat from the partitioned Ordnance Survey Open-UPRN parquet (filename_meta -> partition -> UPRN row). A Repo, not a Fetcher (ADR-0011): no live OS API call. The parquet reader is injected, so it's unit-tested against fixture parquets with no S3/network; returns None when the UPRN is uncovered or absent. pyright strict clean. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
71 lines
2.1 KiB
Python
71 lines
2.1 KiB
Python
"""GeospatialRepo resolves a Property's coordinates from the OS Open-UPRN data.
|
|
|
|
A reference-data lookup, not a Fetcher (ADR-0011): no live OS API call. The
|
|
adapter reads the partitioned Open-UPRN parquet via an injected reader, so the
|
|
test exercises the partition lookup + filter against real fixture parquets with
|
|
no network.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from collections.abc import Callable
|
|
from pathlib import Path
|
|
|
|
import pandas as pd
|
|
|
|
from domain.geospatial.coordinates import Coordinates
|
|
from repositories.geospatial.geospatial_s3_repository import GeospatialS3Repository
|
|
|
|
|
|
def _reader(base: Path) -> Callable[[str], pd.DataFrame]:
|
|
def read(key: str) -> pd.DataFrame:
|
|
return pd.read_parquet(base / key)
|
|
|
|
return read
|
|
|
|
|
|
def _write_open_uprn(base: Path) -> None:
|
|
spatial = base / "spatial"
|
|
spatial.mkdir(parents=True, exist_ok=True)
|
|
pd.DataFrame(
|
|
{"lower": [0], "upper": [100000], "filenames": ["0_100000.parquet"]}
|
|
).to_parquet(spatial / "filename_meta.parquet")
|
|
pd.DataFrame(
|
|
{
|
|
"UPRN": [12345, 12346],
|
|
"LATITUDE": [51.5074, 51.6000],
|
|
"LONGITUDE": [-0.1278, -0.2000],
|
|
}
|
|
).to_parquet(spatial / "0_100000.parquet")
|
|
|
|
|
|
def test_coordinates_for_returns_lon_lat(tmp_path: Path) -> None:
|
|
# Arrange
|
|
_write_open_uprn(tmp_path)
|
|
repo = GeospatialS3Repository(_reader(tmp_path))
|
|
|
|
# Act
|
|
coords = repo.coordinates_for(12345)
|
|
|
|
# Assert
|
|
assert coords == Coordinates(longitude=-0.1278, latitude=51.5074)
|
|
|
|
|
|
def test_coordinates_for_returns_none_when_uprn_absent(tmp_path: Path) -> None:
|
|
# Arrange
|
|
_write_open_uprn(tmp_path)
|
|
repo = GeospatialS3Repository(_reader(tmp_path))
|
|
|
|
# Act / Assert — uprn inside the partition range but not present in the data
|
|
assert repo.coordinates_for(99999) is None
|
|
|
|
|
|
def test_coordinates_for_returns_none_when_no_partition_covers_uprn(
|
|
tmp_path: Path,
|
|
) -> None:
|
|
# Arrange
|
|
_write_open_uprn(tmp_path)
|
|
repo = GeospatialS3Repository(_reader(tmp_path))
|
|
|
|
# Act / Assert — uprn beyond every partition's range
|
|
assert repo.coordinates_for(500000) is None
|