feat(provenance): govern source snapshots and data inputs

backend/tests/test_qa_service.py

@@ -1,11 +1,11 @@
 from __future__ import annotations
 
 import json
+from hashlib import sha256
 from pathlib import Path
-from types import SimpleNamespace
 from uuid import uuid4
 
-from app.models import Area, Dataset
+from app.models import Dataset, SourceRegistry, SourceSnapshot
 from app.services.qa_service import QaService
 
 
@@ -46,6 +46,47 @@ def _write_features(path: Path, features: list[dict]) -> None:
     path.write_text(json.dumps({"type": "FeatureCollection", "features": features}), encoding="utf-8")
 
 
+def _authoritative_reference(dataset: Dataset) -> Dataset:
+    """Give QA reference fixtures the same durable authority proof as GRB."""
+
+    source_id = uuid4()
+    snapshot_id = uuid4()
+    checksum = sha256(Path(str(dataset.storage_path)).read_bytes()).hexdigest()
+    source = SourceRegistry(
+        id=source_id,
+        source_key="grb",
+        display_name="GRB test reference",
+        classification="authoritative",
+        authority_name="Digitaal Vlaanderen",
+        authority_scope_json={"zone": "Flanders"},
+        usage_policy_json={"ground_truth_allowed": True, "validation_authority": {"building_validation": "primary"}},
+    )
+    snapshot = SourceSnapshot(
+        id=snapshot_id,
+        source_registry_id=source_id,
+        snapshot_key=f"qa-grb-{dataset.id}",
+        checksum_sha256=checksum,
+        ingest_status="ingested",
+        freshness_status="current",
+    )
+    dataset.source = "grb"
+    dataset.source_name = "grb"
+    dataset.dataset_role = "reference"
+    dataset.status = "ready"
+    dataset.checksum_sha256 = checksum
+    dataset.source_registry_id = source_id
+    dataset.source_snapshot_id = snapshot_id
+    dataset.data_contract_key = "geointel.vector.geojson"
+    dataset.data_contract_version = "1.0.0"
+    dataset.validation_status = "passed"
+    dataset.provenance_status = "complete"
+    dataset.lineage_status = "complete"
+    dataset.quarantine_status = "not_quarantined"
+    dataset.source_registry = source
+    dataset.source_snapshot = snapshot
+    return dataset
+
+
 def test_qa_compare_candidate_with_reference_returns_metrics(tmp_path) -> None:
     project_id = uuid4()
     candidate_id = uuid4()
@@ -66,7 +107,7 @@ def test_qa_compare_candidate_with_reference_returns_metrics(tmp_path) -> None:
         crs="EPSG:4326",
         metadata_json={"crs_assumed": False},
     )
-    reference = Dataset(
+    reference = _authoritative_reference(Dataset(
         id=reference_id,
         project_id=project_id,
         name="reference.geojson",
@@ -75,7 +116,7 @@ def test_qa_compare_candidate_with_reference_returns_metrics(tmp_path) -> None:
         storage_path=str(reference_path),
         crs="EPSG:4326",
         metadata_json={"crs_assumed": False},
-    )
+    ))
 
     result = QaService.compare_candidate_with_reference(
         db=FakeSession([candidate, reference]),
@@ -117,7 +158,7 @@ def test_qa_compare_candidate_with_reference_returns_feature_level_evidence(tmp_
         crs="EPSG:4326",
         metadata_json={"crs_assumed": False},
     )
-    reference = Dataset(
+    reference = _authoritative_reference(Dataset(
         id=reference_id,
         project_id=project_id,
         name="reference.geojson",
@@ -126,7 +167,7 @@ def test_qa_compare_candidate_with_reference_returns_feature_level_evidence(tmp_
         storage_path=str(reference_path),
         crs="EPSG:4326",
         metadata_json={"crs_assumed": False},
-    )
+    ))
 
     result = QaService.compare_candidate_with_reference(
         db=FakeSession([candidate, reference]),