mirror of
https://github.com/Hestia-Homes/Model.git
synced 2026-07-12 13:29:04 +00:00
269aade481
- unit tests for resolve_group_ambiguity (distinct addresses withheld, same-address re-listing kept, order preserved) - Postgres integration tests for upsert_all's backstop dedup - ADR-0057 recording the "confirm UPRNs before finalise" decision Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
70 lines
2.4 KiB
Python
70 lines
2.4 KiB
Python
"""Unit tests for ``resolve_group_ambiguity`` (ADR-0057).
|
|
|
|
Each address is matched independently, so one UPRN can be the best match for
|
|
two *different* addresses (a coarse EPC record absorbing several real
|
|
addresses). Withholding that UPRN is a pure function of a postcode group's
|
|
``(uprn, normalised_address)`` pairs — no S3, EPC API, or scoring needed — so
|
|
it is unit-tested directly here.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from backend.address2UPRN.scoring import resolve_group_ambiguity
|
|
|
|
|
|
def test_distinct_addresses_sharing_one_uprn_are_withheld() -> None:
|
|
# Flat 1 and Flat 2 both matched the same coarse EPC UPRN — distinct
|
|
# addresses, so both are withheld rather than silently merged.
|
|
result = resolve_group_ambiguity(
|
|
[
|
|
("100", "flat 1 42 moreton road"),
|
|
("100", "flat 2 42 moreton road"),
|
|
]
|
|
)
|
|
assert result == [(None, "ambiguous_duplicate"), (None, "ambiguous_duplicate")]
|
|
|
|
|
|
def test_same_address_listed_twice_keeps_the_uprn() -> None:
|
|
# A genuine re-listing of one property (identical normalised address) is a
|
|
# real duplicate, not an ambiguous match — the UPRN is kept on both.
|
|
result = resolve_group_ambiguity(
|
|
[
|
|
("100", "42 moreton road"),
|
|
("100", "42 moreton road"),
|
|
]
|
|
)
|
|
assert result == [("100", "matched"), ("100", "matched")]
|
|
|
|
|
|
def test_distinct_uprns_are_each_matched() -> None:
|
|
result = resolve_group_ambiguity(
|
|
[
|
|
("100", "42 moreton road"),
|
|
("101", "44 moreton road"),
|
|
]
|
|
)
|
|
assert result == [("100", "matched"), ("101", "matched")]
|
|
|
|
|
|
def test_none_uprn_is_unmatched() -> None:
|
|
result = resolve_group_ambiguity([(None, "99 nowhere lane")])
|
|
assert result == [(None, "unmatched")]
|
|
|
|
|
|
def test_order_is_preserved_across_mixed_group() -> None:
|
|
# A withheld pair, an unmatched row, and a clean match — all in one group;
|
|
# the output aligns positionally with the input.
|
|
result = resolve_group_ambiguity(
|
|
[
|
|
("100", "flat 1 42 moreton road"), # ambiguous (with row 3)
|
|
(None, "no epc candidate"), # unmatched
|
|
("100", "flat 2 42 moreton road"), # ambiguous (with row 0)
|
|
("200", "sole match road"), # matched
|
|
]
|
|
)
|
|
assert result == [
|
|
(None, "ambiguous_duplicate"),
|
|
(None, "unmatched"),
|
|
(None, "ambiguous_duplicate"),
|
|
("200", "matched"),
|
|
]
|