Jens
faeb58ef6d
GeoIntel release gates / Compile, test, contracts and builds (push) Successful in 1m49s
GeoIntel release gates / Python and npm vulnerability policy (push) Successful in 21s
GeoIntel release gates / Production AI image, SBOM and container scan (push) Successful in 5m39s
GeoIntel release gates / Deploy exact gated revision to Unraid (push) Failing after 58m43s
62 lines
1.9 KiB
Python
62 lines
1.9 KiB
Python
"""A rectangle across a municipal boundary must not return the same object twice.
|
|
|
|
Partitioned selection de-duplicated ``total_feature_count`` on
|
|
``source_feature_id`` but returned the raw rows. A feature present in two
|
|
municipal partitions was therefore drawn twice on the map and counted once in
|
|
the headline, so the number on the panel disagreed with the geometry beside it.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from uuid import uuid4
|
|
|
|
from app.services.vector_feature_service import VectorFeatureService
|
|
|
|
|
|
class _Row:
|
|
def __init__(self, source_feature_id, row_id=None, dataset_id=None):
|
|
self.source_feature_id = source_feature_id
|
|
self.id = row_id or uuid4()
|
|
self.dataset_id = dataset_id or uuid4()
|
|
|
|
|
|
def _ids(rows):
|
|
return [row.source_feature_id or str(row.id) for row in rows]
|
|
|
|
|
|
def test_a_feature_in_two_partitions_is_returned_once() -> None:
|
|
shared = "grb-building-42"
|
|
rows = [_Row(shared), _Row("grb-building-7"), _Row(shared)]
|
|
|
|
kept = VectorFeatureService.deduplicate_rows(rows)
|
|
|
|
assert _ids(kept) == [shared, "grb-building-7"]
|
|
|
|
|
|
def test_the_first_occurrence_wins_so_the_result_is_stable() -> None:
|
|
first = _Row("dup")
|
|
second = _Row("dup")
|
|
|
|
assert VectorFeatureService.deduplicate_rows([first, second])[0] is first
|
|
assert VectorFeatureService.deduplicate_rows([second, first])[0] is second
|
|
|
|
|
|
def test_rows_without_a_source_id_fall_back_to_their_own_identity() -> None:
|
|
"""Two distinct rows with no source id are two distinct features."""
|
|
|
|
rows = [_Row(None), _Row(None)]
|
|
|
|
assert len(VectorFeatureService.deduplicate_rows(rows)) == 2
|
|
|
|
|
|
def test_an_empty_source_id_is_not_treated_as_a_shared_identity() -> None:
|
|
rows = [_Row(""), _Row("")]
|
|
|
|
assert len(VectorFeatureService.deduplicate_rows(rows)) == 2
|
|
|
|
|
|
def test_deduplication_leaves_a_clean_population_untouched() -> None:
|
|
rows = [_Row("a"), _Row("b"), _Row("c")]
|
|
|
|
assert VectorFeatureService.deduplicate_rows(rows) == rows
|