Model/tests/backend/app/modelling/test_batching.py

from backend.app.modelling.batching import pack_postcode_batches
from backend.app.modelling.property_filters import FilteredProperty


def _properties(postcode: str, count: int, start_id: int) -> list[FilteredProperty]:
    return [
        FilteredProperty(property_id=start_id + i, postcode=postcode)
        for i in range(count)
    ]


def test_postcodes_are_never_split_across_batches() -> None:
    # arrange — 30 + 30 + 10 with a cap of 50: the second postcode won't fit
    # alongside the first, the third rides with the second
    properties = (
        _properties("B93 8SU", 30, start_id=0)
        + _properties("M20 4TF", 30, start_id=100)
        + _properties("SW1A 1AA", 10, start_id=200)
    )

    # act
    batches = pack_postcode_batches(properties, batch_size=50)

    # assert
    assert [len(b) for b in batches] == [30, 40]
    for batch in batches:
        for postcode in {p.postcode for p in batch}:
            in_batch = [p for p in batch if p.postcode == postcode]
            everywhere = [p for p in properties if p.postcode == postcode]
            assert len(in_batch) == len(everywhere)  # whole postcode, one batch


def test_an_oversized_postcode_becomes_its_own_batch() -> None:
    # arrange — one postcode alone exceeds the cap; neighbours are unaffected
    properties = _properties("B93 8SU", 60, start_id=0) + _properties(
        "M20 4TF", 20, start_id=100
    )

    # act
    batches = pack_postcode_batches(properties, batch_size=50)

    # assert
    assert [len(b) for b in batches] == [60, 20]