feat: synchronize regional official time series

backend/tests/test_sprint194_regional_timeseries.py

@@ -0,0 +1,146 @@
+from __future__ import annotations
+
+import argparse
+import importlib.util
+import io
+import json
+from pathlib import Path
+import sys
+import zipfile
+
+
+ROOT = Path(__file__).resolve().parents[2]
+SCRIPTS = ROOT / "scripts"
+if str(SCRIPTS) not in sys.path:
+    sys.path.insert(0, str(SCRIPTS))
+
+
+def load_script(name: str):
+    path = SCRIPTS / name
+    module_name = f"test_{path.stem}"
+    spec = importlib.util.spec_from_file_location(module_name, path)
+    assert spec is not None
+    assert spec.loader is not None
+    module = importlib.util.module_from_spec(spec)
+    sys.modules[module_name] = module
+    spec.loader.exec_module(module)
+    return module
+
+
+def population_archive() -> bytes:
+    text = "\n".join(
+        (
+            "CD_REFNIS|CD_SECTOR|TOTAL|TX_DESCR_SECTOR_NL|TX_DESCR_NL",
+            "13025|13025A00-|120|Mol centrum|Mol",
+            "13008|13008A00-|240|Geel centrum|Geel",
+            "11002|11002A00-|360|Antwerpen centrum|Antwerpen",
+        )
+    )
+    buffer = io.BytesIO()
+    with zipfile.ZipFile(buffer, "w") as archive:
+        archive.writestr("population.csv", text)
+    return buffer.getvalue()
+
+
+def test_population_operator_filters_to_the_approved_scope() -> None:
+    module = load_script("provision_mol_population_history.py")
+    regional = module.GEOGRAPHIC_SCOPES["kempen-transport-region"]
+    mol = module.GEOGRAPHIC_SCOPES["mol"]
+
+    regional_rows = module.population_rows(population_archive(), regional)
+    mol_rows = module.population_rows(population_archive(), mol)
+
+    assert set(regional_rows) == {"13025A00-", "13008A00-"}
+    assert regional_rows["13008A00-"]["municipality"] == "Geel"
+    assert regional_rows["13008A00-"]["nis_code"] == "13008"
+    assert set(mol_rows) == {"13025A00-"}
+    assert module.series_key(regional) == "statbel:population-statistical-sector:kempen-transport-region"
+    assert module.series_key(mol) == "statbel:population-statistical-sector:mol"
+
+
+def test_population_operator_resolves_the_persisted_scope_boundary(tmp_path: Path) -> None:
+    module = load_script("provision_mol_population_history.py")
+    scope = module.GEOGRAPHIC_SCOPES["kempen-transport-region"]
+    scope_dir = tmp_path / scope.key
+    scope_dir.mkdir(parents=True)
+    boundary = scope_dir / "boundary.geojson"
+    boundary.write_text('{"type":"FeatureCollection","features":[]}', encoding="utf-8")
+    manifest = scope_dir / "kempen_transport_region_scope_manifest.json"
+    manifest.write_text(
+        json.dumps(
+            {
+                "status": "complete",
+                "scope_key": scope.key,
+                "boundary_filename": boundary.name,
+            }
+        ),
+        encoding="utf-8",
+    )
+    args = argparse.Namespace(boundary_path=None, scope_output_root=tmp_path)
+
+    assert module.resolve_boundary_path(args, scope) == boundary
+
+
+def test_regional_coordinator_builds_explicit_population_and_forest_commands(tmp_path: Path) -> None:
+    module = load_script("provision_regional_timeseries.py")
+    scope = module.GEOGRAPHIC_SCOPES["kempen-transport-region"]
+    args = argparse.Namespace(
+        output_root=tmp_path / "time-series",
+        fetch_only=False,
+        force=False,
+        skip_population=False,
+        skip_landuse=False,
+        base_url="http://backend:8000",
+        population_years="2021,2025",
+        landuse_years="2013,2025",
+        request_timeout=300,
+        import_timeout=3600,
+        max_landuse_features=500000,
+    )
+
+    commands = dict(module.build_operator_commands(args, scope, tmp_path / "boundary.geojson"))
+
+    assert set(commands) == {"population", "forest"}
+    assert commands["population"][0] == sys.executable
+    assert "--scope" in commands["population"]
+    assert "kempen-transport-region" in commands["population"]
+    assert scope.project_name in commands["population"]
+    assert commands["forest"][0] == sys.executable
+    assert "--max-features" in commands["forest"]
+    assert ",".join(scope.nis_codes) in commands["forest"]
+    assert "--force" not in commands["population"]
+    assert "--fetch-only" not in commands["forest"]
+
+
+def test_regional_forest_provenance_does_not_claim_one_municipality() -> None:
+    module = load_script("provision_official_landuse_timeseries.py")
+
+    regional = module.scope_identity("Kempen (28 gemeenten)", "13001,13008,13025")
+    municipal = module.scope_identity("Mol", "13025")
+
+    assert regional == {
+        "scope_display_name": "Kempen (28 gemeenten)",
+        "member_nis_codes": ["13001", "13008", "13025"],
+        "municipality": None,
+        "nis_code": None,
+    }
+    assert municipal["municipality"] == "Mol"
+    assert municipal["nis_code"] == "13025"
+
+
+def test_regional_timeseries_operator_is_packaged_and_release_checked() -> None:
+    dockerfile = (ROOT / "deploy/unraid/Dockerfile.all-in-one").read_text(encoding="utf-8")
+    readiness = (ROOT / "scripts/run_readiness_check.sh").read_text(encoding="utf-8")
+
+    assert "COPY scripts/provision_regional_timeseries.py" in dockerfile
+    assert "py_compile scripts/provision_regional_timeseries.py" in readiness
+
+
+def test_end_user_dataset_sources_are_human_readable() -> None:
+    display = (ROOT / "frontend/src/lib/datasetDisplay.ts").read_text(encoding="utf-8")
+    workspace = (ROOT / "frontend/src/components/map/MapWorkspace.tsx").read_text(encoding="utf-8")
+
+    assert "department_omgeving_land_use: 'Departement Omgeving'" in display
+    assert "statbel: 'Statbel'" in display
+    assert "getDatasetSourceDisplayName(activeThemeDataset)" in workspace
+    assert "dataset ? getDatasetSourceDisplayName(dataset)" in workspace