Initial public release

backend/tests/test_sprint184_detection_qa_coverage.py

@@ -0,0 +1,124 @@
+from __future__ import annotations
+
+from uuid import uuid4
+
+import pytest
+from pyproj import Transformer
+from shapely.geometry import box
+
+from app.core.errors import AppError
+from app.services.detection_qa_service import DetectionQaService
+from app.services.qa_service import QaService
+
+
+def test_tile_coverage_transforms_projected_manifest_bounds_to_epsg4326() -> None:
+    dataset_id = uuid4()
+    to_lambert = Transformer.from_crs("EPSG:4326", "EPSG:31370", always_xy=True)
+    left, bottom = to_lambert.transform(5.11, 51.18)
+    right, top = to_lambert.transform(5.13, 51.20)
+    manifest = {
+        "source_dataset_id": str(dataset_id),
+        "crs": "EPSG:31370",
+        "tiles": [{"bounds": [left, bottom, right, top], "crs": "EPSG:31370"}],
+    }
+
+    coverage = DetectionQaService.build_tile_coverage(
+        manifest,
+        manifest_path="/app/storage/tiles/manifest.json",
+        expected_dataset_id=dataset_id,
+    )
+
+    min_x, min_y, max_x, max_y = coverage.geometry.bounds
+    assert min_x == pytest.approx(5.11, abs=0.001)
+    assert min_y == pytest.approx(51.18, abs=0.001)
+    assert max_x == pytest.approx(5.13, abs=0.001)
+    assert max_y == pytest.approx(51.20, abs=0.001)
+    assert coverage.tile_count == 1
+
+
+def test_tile_coverage_rejects_manifest_for_different_dataset() -> None:
+    manifest = {
+        "source_dataset_id": str(uuid4()),
+        "crs": "EPSG:4326",
+        "tiles": [{"bounds": [5.0, 51.0, 5.1, 51.1]}],
+    }
+
+    with pytest.raises(AppError) as exc_info:
+        DetectionQaService.build_tile_coverage(
+            manifest,
+            manifest_path="/app/storage/tiles/manifest.json",
+            expected_dataset_id=uuid4(),
+        )
+
+    assert exc_info.value.code == "DETECTION_QA_COVERAGE_MISMATCH"
+
+
+def test_coverage_filter_reports_outside_and_boundary_clipped_population() -> None:
+    dataset_id = uuid4()
+    coverage = DetectionQaService.build_tile_coverage(
+        {
+            "source_dataset_id": str(dataset_id),
+            "crs": "EPSG:4326",
+            "tiles": [{"bounds": [0.0, 0.0, 1.0, 1.0]}],
+        },
+        manifest_path="/app/storage/tiles/manifest.json",
+        expected_dataset_id=dataset_id,
+    )
+
+    population = DetectionQaService.filter_population(
+        [
+            ({"id": "inside"}, box(0.1, 0.1, 0.2, 0.2)),
+            ({"id": "crossing"}, box(0.8, 0.8, 1.2, 1.2)),
+            ({"id": "outside"}, box(2.0, 2.0, 3.0, 3.0)),
+        ],
+        coverage,
+    )
+
+    assert population.raw_count == 3
+    assert population.evaluated_count == 2
+    assert population.excluded_outside_count == 1
+    assert population.clipped_boundary_count == 1
+    assert population.geometries[1][1].bounds == pytest.approx((0.8, 0.8, 1.0, 1.0))
+
+
+def test_coverage_filter_preserves_prefiltered_database_population_count() -> None:
+    dataset_id = uuid4()
+    coverage = DetectionQaService.build_tile_coverage(
+        {
+            "source_dataset_id": str(dataset_id),
+            "crs": "EPSG:4326",
+            "tiles": [{"bounds": [0.0, 0.0, 1.0, 1.0]}],
+        },
+        manifest_path="/app/storage/tiles/manifest.json",
+        expected_dataset_id=dataset_id,
+    )
+
+    population = DetectionQaService.filter_population(
+        [
+            ({"id": "inside"}, box(0.1, 0.1, 0.2, 0.2)),
+            ({"id": "crossing"}, box(0.8, 0.8, 1.2, 1.2)),
+        ],
+        coverage,
+        raw_count=3,
+    )
+
+    assert population.raw_count == 3
+    assert population.evaluated_count == 2
+    assert population.excluded_outside_count == 1
+    assert population.clipped_boundary_count == 1
+
+
+def test_iou_matching_keeps_exact_results_with_many_spatially_disjoint_references() -> None:
+    references = [({"id": f"outside-{index}"}, box(index + 10, 10, index + 10.5, 10.5)) for index in range(100)]
+    references.append(({"id": "match"}, box(0.0, 0.0, 1.0, 1.0)))
+
+    evidence = QaService._match_io_u_evidence(
+        [({"id": "candidate"}, box(0.0, 0.0, 1.0, 1.0))],
+        references,
+        0.5,
+    )
+
+    assert evidence.matches == 1
+    assert evidence.false_positives == 0
+    assert evidence.false_negatives == 100
+    assert evidence.match_evidence[0]["reference_feature_id"] == "match"