Files
geointel/scripts/provision_mol_population_history.py
T
Codex d0a8a3ad15
GeoIntel CI / docs-smoke (push) Canceled after 0s
GeoIntel CI / contract-smoke (push) Canceled after 0s
Add governed Statbel release promotion
2026-07-17 00:19:47 +02:00

830 lines
36 KiB
Python

"""Provision official annual Statbel population snapshots for an approved scope.
The command joins annual population totals to the matching official
statistical-sector geometries, clips the result to an approved geographic
scope and imports each year
through the existing GeoIntel upload API. It never runs during application
startup and it never synthesizes missing population values.
Mol remains the backwards-compatible default. The canonical regional operator
uses ``--scope kempen-transport-region`` and the persisted official scope
boundary produced by ``provision_geographic_scope.py``.
"""
from __future__ import annotations
import argparse
import csv
from dataclasses import dataclass
from hashlib import sha256
import io
import json
import os
import sys
import zipfile
from datetime import datetime, timezone
from pathlib import Path
from typing import Any
import requests
from pyproj import Transformer
from requests.adapters import HTTPAdapter
from shapely.geometry import mapping, shape
from shapely.ops import transform
from shapely.validation import make_valid
from urllib.parse import unquote, urlsplit
from urllib3.util.retry import Retry
from geographic_scopes import GEOGRAPHIC_SCOPES, GeographicScope
from statbel_population_preflight import (
MAX_GEOMETRY_ARCHIVE_BYTES,
MAX_POPULATION_ARCHIVE_BYTES,
StatbelPreflightError,
validate_geometry_source_url,
validate_population_source_url,
validate_statbel_release,
write_manifest,
)
MUNICIPALITY_NAME = "Mol"
MUNICIPALITY_NIS_CODE = "13025"
PROJECT_NAME = "Mol Municipality Workbench"
SERIES_KEY = "statbel:population-statistical-sector:mol"
ATTRIBUTION = "Bron: Statbel, bevolking per statistische sector, CC BY 4.0"
DEFAULT_API_URL = "http://127.0.0.1:8000"
DEFAULT_OUTPUT_DIR = Path("/app/storage/operator-data/mol-population-history")
DEFAULT_BOUNDARY_PATH = Path("/app/storage/operator-data/mol-municipality/mol_municipality_boundary.geojson")
DEFAULT_SCOPE_KEY = "mol"
DEFAULT_SCOPE_OUTPUT_ROOT = Path("/app/storage/operator-data/geographic-scopes")
DEFAULT_REGIONAL_OUTPUT_ROOT = Path("/app/storage/operator-data/official-population")
SECTOR_URL = (
"https://statbel.fgov.be/sites/default/files/files/opendata/Statistische%20sectoren/"
"sh_statbel_statistical_sectors_31370_{year}0101.geojson.zip"
)
POPULATION_URLS = {
2021: "https://statbel.fgov.be/sites/default/files/files/opendata/bevolking/sectoren/OPENDATA_SECTOREN_2021.zip",
2022: "https://statbel.fgov.be/sites/default/files/files/opendata/bevolking/sectoren/OPENDATA_SECTOREN_2022.zip",
2023: "https://statbel.fgov.be/sites/default/files/files/opendata/bevolking/sectoren/OPENDATA_SECTOREN_2023.zip",
2024: "https://statbel.fgov.be/sites/default/files/files/opendata/bevolking/sectoren/OPENDATA_SECTOREN_2024.zip",
2025: "https://statbel.fgov.be/sites/default/files/files/opendata/bevolking/sectoren/OPENDATA_SECTOREN_2025_NEW.zip",
}
POPULATION_LAYOUTS = {year: ("new" if year == 2025 else "standard") for year in POPULATION_URLS}
@dataclass(frozen=True)
class PopulationReleaseConfig:
year: int
layout: str
population_url: str
geometry_url: str
def resolve_release_config(
year: int,
*,
population_url: str | None = None,
geometry_url: str | None = None,
layout: str | None = None,
) -> PopulationReleaseConfig:
overrides = (population_url, geometry_url, layout)
if any(value is not None for value in overrides):
if not all(value is not None for value in overrides):
raise ValueError("Population URL, geometry URL and population layout must be supplied together")
release = PopulationReleaseConfig(
year=year,
layout=str(layout),
population_url=str(population_url),
geometry_url=str(geometry_url),
)
elif year in POPULATION_URLS:
release = PopulationReleaseConfig(
year=year,
layout=POPULATION_LAYOUTS[year],
population_url=POPULATION_URLS[year],
geometry_url=SECTOR_URL.format(year=year),
)
else:
raise ValueError(f"Unsupported population year without an explicit governed release: {year}")
validate_population_source_url(release.population_url, release.year, release.layout)
validate_geometry_source_url(release.geometry_url, release.year)
return release
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(description="Provision official annual Statbel population snapshots.")
parser.add_argument("--scope", choices=sorted(GEOGRAPHIC_SCOPES), default=DEFAULT_SCOPE_KEY)
parser.add_argument("--base-url", default=os.environ.get("GEOINTEL_INTERNAL_API_URL", DEFAULT_API_URL))
parser.add_argument("--project-name", default=None)
parser.add_argument("--area-name", default=None, help="Case-insensitive fragment identifying the persisted Area.")
parser.add_argument("--years", default="2021,2022,2023,2024,2025")
parser.add_argument(
"--population-url",
help="Exact official Statbel ZIP URL for one explicitly governed release; requires the other release flags",
)
parser.add_argument(
"--geometry-url",
help="Exact matching official statistical-sector GeoJSON ZIP URL for one explicitly governed release",
)
parser.add_argument("--population-layout", choices=("standard", "new"))
parser.add_argument("--output-dir", type=Path, default=None)
parser.add_argument("--boundary-path", type=Path, default=None)
parser.add_argument(
"--scope-output-root",
type=Path,
default=Path(os.environ.get("GEOINTEL_SCOPE_OUTPUT_ROOT", DEFAULT_SCOPE_OUTPUT_ROOT)),
)
parser.add_argument("--request-timeout", type=int, default=180)
parser.add_argument("--import-timeout", type=int, default=900)
parser.add_argument("--force", action="store_true")
parser.add_argument("--fetch-only", action="store_true")
return parser.parse_args()
def build_session() -> requests.Session:
retry = Retry(
total=5,
connect=5,
read=5,
status=5,
backoff_factor=1.0,
status_forcelist=(429, 500, 502, 503, 504),
allowed_methods=frozenset({"GET"}),
raise_on_status=True,
)
session = requests.Session()
session.headers.update({"User-Agent": "GeoIntel-Official-Population-Operator/1.0"})
adapter = HTTPAdapter(max_retries=retry)
session.mount("https://", adapter)
session.mount("http://", adapter)
return session
def download_archive(
session: requests.Session,
*,
url: str,
year: int,
layout: str | None,
max_bytes: int,
timeout: int,
) -> bytes:
with session.get(url, timeout=timeout, stream=True) as response:
response.raise_for_status()
if layout is None:
validate_geometry_source_url(response.url, year)
else:
validate_population_source_url(response.url, year, layout)
content_length = response.headers.get("Content-Length")
if content_length:
try:
advertised_size = int(content_length)
except ValueError as exc:
raise RuntimeError(f"Official source returned an invalid Content-Length for {url}") from exc
if advertised_size <= 0 or advertised_size > max_bytes:
raise RuntimeError(f"Official source archive exceeds the {max_bytes}-byte download limit")
chunks: list[bytes] = []
size = 0
for chunk in response.iter_content(chunk_size=1024 * 1024):
if not chunk:
continue
size += len(chunk)
if size > max_bytes:
raise RuntimeError(f"Official source archive exceeds the {max_bytes}-byte download limit")
chunks.append(chunk)
if size <= 0:
raise RuntimeError(f"Official source archive is empty: {url}")
return b"".join(chunks)
def response_data(response: requests.Response) -> Any:
try:
payload = response.json()
except ValueError as exc:
raise RuntimeError(f"GeoIntel API returned non-JSON ({response.status_code}): {response.text[:300]}") from exc
if not response.ok:
raise RuntimeError(f"GeoIntel API failed ({response.status_code}): {json.dumps(payload, ensure_ascii=False)[:800]}")
if not isinstance(payload, dict) or "data" not in payload:
raise RuntimeError("GeoIntel API response does not use the canonical data envelope")
return payload["data"]
def list_paginated_items(session: requests.Session, url: str, *, timeout: int) -> list[dict[str, Any]]:
items: list[dict[str, Any]] = []
offset = 0
total: int | None = None
while total is None or offset < total:
page = response_data(session.get(url, params={"limit": 200, "offset": offset}, timeout=timeout))
page_items = page.get("items") if isinstance(page, dict) else None
if not isinstance(page_items, list):
raise RuntimeError(f"GeoIntel list response for {url} has no items array")
page_total = int(page.get("total", len(page_items)))
if total is None:
total = page_total
elif page_total != total:
raise RuntimeError("GeoIntel pagination total changed while reading the population workspace")
items.extend(page_items)
if not page_items:
break
offset += len(page_items)
if total is not None and len(items) != total:
raise RuntimeError(f"GeoIntel list response for {url} returned {len(items)} of {total} items")
return items
def series_key(scope: GeographicScope) -> str:
return f"statbel:population-statistical-sector:{scope.key}"
def resolve_output_dir(args: argparse.Namespace, scope: GeographicScope) -> Path:
if args.output_dir is not None:
return args.output_dir
legacy = os.environ.get("MOL_POPULATION_OUTPUT_DIR")
if scope.key == "mol" and legacy:
return Path(legacy)
if scope.key == "mol":
return DEFAULT_OUTPUT_DIR
return DEFAULT_REGIONAL_OUTPUT_ROOT / scope.key
def resolve_boundary_path(args: argparse.Namespace, scope: GeographicScope) -> Path:
if args.boundary_path is not None:
return args.boundary_path
legacy = os.environ.get("MOL_BOUNDARY_PATH")
if scope.key == "mol" and legacy:
return Path(legacy)
if scope.key == "mol" and DEFAULT_BOUNDARY_PATH.exists():
return DEFAULT_BOUNDARY_PATH
scope_dir = args.scope_output_root / scope.key
manifest_path = scope_dir / f"{scope.key.replace('-', '_')}_scope_manifest.json"
if not manifest_path.exists():
raise RuntimeError(
f"Official scope manifest is missing at {manifest_path}; run provision_geographic_scope.py --scope {scope.key} first"
)
manifest = json.loads(manifest_path.read_text(encoding="utf-8"))
if manifest.get("scope_key") != scope.key or manifest.get("status") != "complete":
raise RuntimeError(f"Official scope manifest at {manifest_path} is incomplete or belongs to another scope")
boundary_path = scope_dir / str(manifest.get("boundary_filename") or "")
if not boundary_path.is_file():
raise RuntimeError(f"Official scope boundary referenced by {manifest_path} is missing")
return boundary_path
def load_boundary(path: Path, scope: GeographicScope):
if not path.exists():
raise RuntimeError(f"Boundary for {scope.display_name} is missing at {path}")
payload = json.loads(path.read_text(encoding="utf-8"))
features = payload.get("features") or []
if len(features) != 1:
raise RuntimeError(f"Boundary artifact for {scope.display_name} must contain exactly one feature")
boundary = shape(features[0]["geometry"])
if not boundary.is_valid:
boundary = make_valid(boundary)
if boundary.is_empty or not boundary.is_valid:
raise RuntimeError(f"Boundary artifact for {scope.display_name} is invalid")
return boundary
def zip_member_json(content: bytes) -> dict[str, Any]:
with zipfile.ZipFile(io.BytesIO(content)) as archive:
member = next((name for name in archive.namelist() if name.lower().endswith(".geojson")), None)
if not member:
raise RuntimeError("Statbel sector archive contains no GeoJSON file")
return json.loads(archive.read(member).decode("utf-8"))
def population_rows(content: bytes, scope: GeographicScope) -> dict[str, dict[str, Any]]:
with zipfile.ZipFile(io.BytesIO(content)) as archive:
member = next((name for name in archive.namelist() if name.lower().endswith((".txt", ".csv"))), None)
if not member:
raise RuntimeError("Statbel population archive contains no text table")
raw = archive.read(member)
try:
text = raw.decode("utf-8-sig")
except UnicodeDecodeError:
text = raw.decode("cp1252")
required = {"CD_REFNIS", "CD_SECTOR", "TOTAL", "TX_DESCR_SECTOR_NL", "TX_DESCR_NL"}
reader = csv.DictReader(io.StringIO(text), delimiter="|")
missing_columns = sorted(required - set(reader.fieldnames or ()))
if missing_columns:
raise RuntimeError(f"Statbel population table is missing required columns: {', '.join(missing_columns)}")
return scoped_population_rows(list(reader), scope)
def scoped_population_rows(source_rows: list[dict[str, Any]], scope: GeographicScope) -> dict[str, dict[str, Any]]:
members = {member.nis_code: member.name for member in scope.members}
rows: dict[str, dict[str, Any]] = {}
seen: set[str] = set()
for row_number, row in enumerate(source_rows, start=2):
nis_code = str(row.get("CD_REFNIS") or "").strip()
sector_code = str(row.get("CD_SECTOR") or "").strip().upper()
total_raw = str(row.get("TOTAL") if row.get("TOTAL") is not None else "").strip()
if (
len(nis_code) != 5
or not nis_code.isdigit()
or len(sector_code) != 9
or not sector_code[:5].isdigit()
or not total_raw.isdigit()
):
raise RuntimeError(f"Statbel population row {row_number} has invalid code or TOTAL values")
if sector_code in seen:
raise RuntimeError(f"Statbel population table contains duplicate sector {sector_code}")
seen.add(sector_code)
if nis_code not in members:
continue
rows[sector_code] = {
"population_total": int(total_raw),
"sector_name_nl": row.get("TX_DESCR_SECTOR_NL"),
"municipality_name_nl": row.get("TX_DESCR_NL"),
"municipality": members[nis_code],
"nis_code": nis_code,
}
if not rows:
raise RuntimeError(f"Statbel population table contains no usable sectors for {scope.display_name}")
return rows
def build_snapshot(
year: int,
sector_payload: dict[str, Any],
population: dict[str, dict[str, Any]],
boundary,
scope: GeographicScope,
preflight_manifest: dict[str, Any] | None = None,
) -> dict[str, Any]:
transformer = Transformer.from_crs("EPSG:31370", "EPSG:4326", always_xy=True)
member_codes = set(scope.nis_codes)
features: list[dict[str, Any]] = []
missing_population = 0
for source_feature in sector_payload.get("features") or []:
properties = source_feature.get("properties") or {}
if str(properties.get("cd_munty_refnis") or "") not in member_codes:
continue
sector_code = str(properties.get("cd_sector") or "").strip()
population_values = population.get(sector_code)
if not population_values:
missing_population += 1
continue
geometry = transform(transformer.transform, shape(source_feature["geometry"]))
if not geometry.is_valid:
geometry = make_valid(geometry)
geometry = geometry.intersection(boundary)
if geometry.is_empty:
continue
if not geometry.is_valid:
geometry = make_valid(geometry)
combined = {
**properties,
**population_values,
"source_name": "statbel",
"source_feature_id": sector_code,
"reference_layer_name": "population",
"authority_level": "authoritative",
"municipality": population_values["municipality"],
"nis_code": population_values["nis_code"],
"observation_year": year,
"attribution": ATTRIBUTION,
}
features.append({"type": "Feature", "id": sector_code, "geometry": mapping(geometry), "properties": combined})
if missing_population:
raise RuntimeError(f"Statbel geometry has {missing_population} sectors without population rows for {year}")
if not features:
raise RuntimeError(f"No joined population sectors were produced for {year}")
spatial_population_total = sum(int(feature["properties"]["population_total"]) for feature in features)
accounting = (preflight_manifest or {}).get("scope_accounting") or {}
if accounting:
expected_count = int(accounting.get("spatial_sector_count") or 0)
expected_total = int(accounting.get("spatial_population_total") or -1)
if len(features) != expected_count or spatial_population_total != expected_total:
raise RuntimeError(
f"Derived snapshot accounting differs from the passed Statbel preflight for {year}: "
f"features {len(features)}/{expected_count}, population {spatial_population_total}/{expected_total}"
)
return {
"type": "FeatureCollection",
"name": f"Statbel population by statistical sector - {scope.display_name} {year}",
"features": features,
"coverage_scope": scope.key,
"scope_type": scope.scope_type,
"member_count": len(scope.members),
"member_nis_codes": list(scope.nis_codes),
"geometry_clipped_to_area": True,
"observation_year": year,
"missing_population_sector_count": missing_population,
"spatial_population_total": spatial_population_total,
"unlocated_population_row_count": int(accounting.get("unlocated_row_count") or 0),
"unlocated_population_total": int(accounting.get("unlocated_population_total") or 0),
"accounted_population_total": int(accounting.get("accounted_population_total") or spatial_population_total),
"population_accounting_limitation": (
"Statbel ZZZZ rows cannot be mapped and are excluded from spatial selection metrics."
),
"attribution": ATTRIBUTION,
}
def sha256_path(path: Path) -> str:
digest = sha256()
with path.open("rb") as handle:
for chunk in iter(lambda: handle.read(1024 * 1024), b""):
digest.update(chunk)
return digest.hexdigest()
def write_bytes_atomic(path: Path, content: bytes) -> None:
path.parent.mkdir(parents=True, exist_ok=True)
temporary = path.with_suffix(path.suffix + ".tmp")
temporary.write_bytes(content)
temporary.replace(path)
def write_text_atomic(path: Path, content: str) -> None:
path.parent.mkdir(parents=True, exist_ok=True)
temporary = path.with_suffix(path.suffix + ".tmp")
temporary.write_text(content, encoding="utf-8")
temporary.replace(path)
def snapshot_path(output_dir: Path, scope: GeographicScope, year: int) -> Path:
return output_dir / f"{scope.key.replace('-', '_')}_statbel_population_{year}.geojson"
def preflight_manifest_path(output_dir: Path, scope: GeographicScope, year: int) -> Path:
return output_dir / f"{scope.key.replace('-', '_')}_statbel_population_{year}.preflight.json"
def previous_snapshot_path(output_dir: Path, scope: GeographicScope, year: int) -> Path | None:
prefix = f"{scope.key.replace('-', '_')}_statbel_population_"
available: list[tuple[int, Path]] = []
for path in output_dir.glob(f"{prefix}*.geojson"):
suffix = path.stem.removeprefix(prefix)
if suffix.isdigit() and int(suffix) < year and path.is_file():
available.append((int(suffix), path))
return max(available, key=lambda item: item[0])[1] if available else None
def load_preflight_manifest(path: Path, snapshot: Path, year: int, scope: GeographicScope) -> dict[str, Any]:
try:
manifest = json.loads(path.read_text(encoding="utf-8"))
except (OSError, UnicodeDecodeError, json.JSONDecodeError) as exc:
raise RuntimeError(f"Statbel preflight manifest is unreadable at {path}") from exc
release = manifest.get("release") or {}
accounting = manifest.get("scope_accounting") or {}
derived = (manifest.get("artifacts") or {}).get("derived_snapshot") or {}
if (
manifest.get("status") != "passed"
or manifest.get("import_eligible") is not True
or int(release.get("year") or 0) != year
or accounting.get("scope_key") != scope.key
or derived.get("sha256") != sha256_path(snapshot)
):
raise RuntimeError(f"Statbel preflight manifest at {path} does not authorize the retained snapshot")
for artifact_name in ("population", "geometry"):
artifact = (manifest.get("artifacts") or {}).get(artifact_name) or {}
retained_path = Path(str(artifact.get("retained_path") or ""))
if (
not retained_path.is_file()
or artifact.get("archive_sha256") != sha256_path(retained_path)
or int(artifact.get("archive_size_bytes") or -1) != retained_path.stat().st_size
):
raise RuntimeError(
f"Statbel preflight manifest at {path} does not authorize the retained {artifact_name} archive"
)
return manifest
def stage_release(
*,
year: int,
population_content: bytes,
geometry_content: bytes,
output_dir: Path,
boundary,
scope: GeographicScope,
release: PopulationReleaseConfig | None = None,
) -> tuple[Path, Path, dict[str, Any]]:
active_release = release or resolve_release_config(year)
if active_release.year != year:
raise ValueError("Population release year does not match the staged year")
result = validate_statbel_release(
year=year,
layout=active_release.layout,
population_content=population_content,
population_url=active_release.population_url,
geometry_content=geometry_content,
geometry_url=active_release.geometry_url,
scope=scope,
baseline_snapshot=previous_snapshot_path(output_dir, scope, year),
)
raw_dir = output_dir / "raw" / str(year)
population_archive_path = raw_dir / Path(unquote(urlsplit(active_release.population_url).path)).name
geometry_archive_path = raw_dir / Path(unquote(urlsplit(active_release.geometry_url).path)).name
write_bytes_atomic(population_archive_path, population_content)
write_bytes_atomic(geometry_archive_path, geometry_content)
manifest = dict(result.manifest)
manifest["artifacts"] = {
**manifest["artifacts"],
"population": {
**manifest["artifacts"]["population"],
"retained_path": str(population_archive_path),
},
"geometry": {
**manifest["artifacts"]["geometry"],
"retained_path": str(geometry_archive_path),
},
}
population = scoped_population_rows(list(result.population.rows.values()), scope)
path = snapshot_path(output_dir, scope, year)
snapshot = build_snapshot(
year,
result.geometry.payload,
population,
boundary,
scope,
preflight_manifest=manifest,
)
write_text_atomic(path, json.dumps(snapshot, ensure_ascii=False, separators=(",", ":")))
manifest["artifacts"]["derived_snapshot"] = {
"retained_path": str(path),
"size_bytes": path.stat().st_size,
"sha256": sha256_path(path),
"feature_count": len(snapshot["features"]),
}
manifest_path = preflight_manifest_path(output_dir, scope, year)
write_manifest(manifest_path, manifest)
return path, manifest_path, manifest
def locate_workspace(
session: requests.Session,
base_url: str,
project_name: str,
area_name: str,
timeout: int,
):
projects = list_paginated_items(session, f"{base_url}/api/v1/projects", timeout=timeout)
project = next((item for item in projects if item.get("name") == project_name), None)
if not project:
raise RuntimeError(f"Project {project_name!r} is missing")
project_id = str(project["id"])
areas = list_paginated_items(session, f"{base_url}/api/v1/projects/{project_id}/areas", timeout=timeout)
area_fragment = area_name.strip().casefold()
matches = [item for item in areas if area_fragment in str(item.get("name") or "").casefold()]
if len(matches) != 1:
raise RuntimeError(f"Expected one official Area matching {area_name!r}, received {len(matches)}")
datasets = list_paginated_items(session, f"{base_url}/api/v1/projects/{project_id}/datasets", timeout=timeout)
return project_id, str(matches[0]["id"]), datasets
def upload_snapshot(
session: requests.Session,
base_url: str,
project_id: str,
area_id: str,
year: int,
path: Path,
timeout: int,
scope: GeographicScope,
preflight_path: Path,
release: PopulationReleaseConfig | None = None,
) -> dict[str, Any]:
active_release = release or resolve_release_config(year)
if active_release.year != year:
raise ValueError("Population release year does not match the upload year")
observed_at = f"{year}-01-01T00:00:00Z"
preflight = load_preflight_manifest(preflight_path, path, year, scope)
accounting = preflight["scope_accounting"]
source_metadata = {
"provider": "Statbel",
"authority_level": "authoritative",
"coverage_scope": scope.key,
"scope_type": scope.scope_type,
"scope_display_name": scope.display_name,
"member_count": len(scope.members),
"member_nis_codes": list(scope.nis_codes),
"geometry_clipped_to_area": True,
"attribution": ATTRIBUTION,
"license": "CC BY 4.0",
"temporal_series_label": "Officiële bevolkingscijfers per statistische sector",
"observation_date_precision": "year",
"identity_stable": False,
"identity_limitation": "Statistical-sector codes and boundaries can change between annual editions.",
"population_layout": preflight["release"]["population_layout"],
"population_accounting": accounting,
"spatial_population_limitation": (
"ZZZZ population rows have no geometry and are excluded from spatial selection metrics."
),
"selection_aggregation": {
"method": "area_weighted_sum",
"property": "population_total",
"label": "Inwoners",
"unit": "inwoners",
"warning_only_when_estimate": True,
"warning": "Bevolking binnen een gedeeltelijke statistische sector is oppervlaktegewogen en blijft een schatting.",
},
}
provenance_metadata = {
"operator_tool": "provision_mol_population_history.py",
"operator_explicit_fetch": True,
"scope_key": scope.key,
"geometry_clipped_to_area": True,
"sector_geometry_url": active_release.geometry_url,
"population_url": active_release.population_url,
"population_layout": preflight["release"]["population_layout"],
"preflight_manifest_path": str(preflight_path),
"preflight_manifest_sha256": sha256_path(preflight_path),
"population_archive_sha256": preflight["artifacts"]["population"]["archive_sha256"],
"sector_archive_sha256": preflight["artifacts"]["geometry"]["archive_sha256"],
"derived_snapshot_sha256": preflight["artifacts"]["derived_snapshot"]["sha256"],
"generated_at": datetime.now(timezone.utc).isoformat(),
}
with path.open("rb") as handle:
response = session.post(
f"{base_url}/api/v1/projects/{project_id}/datasets/upload",
data={
"dataset_type": "vector",
"source": "operator_official_import",
"dataset_role": "reference",
"source_name": "statbel",
"reference_layer_name": "population",
"source_metadata_json": json.dumps(source_metadata, ensure_ascii=False),
"provenance_metadata_json": json.dumps(provenance_metadata, ensure_ascii=False),
"area_id": area_id,
"temporal_series_key": series_key(scope),
"observed_at": observed_at,
"valid_from": observed_at,
"valid_to": f"{year}-12-31T23:59:59Z",
"temporal_granularity": "year",
"source_version": str(year),
},
files={"file": (path.name, handle, "application/geo+json")},
timeout=timeout,
)
return response_data(response)
def main() -> int:
args = parse_args()
scope = GEOGRAPHIC_SCOPES[args.scope]
project_name = args.project_name or scope.project_name
area_name = args.area_name or scope.area_name
try:
years = sorted({int(value.strip()) for value in args.years.split(",") if value.strip()})
except ValueError:
print(json.dumps({"status": "error", "message": "Years must be comma-separated integers"}), file=sys.stderr)
return 2
custom_release_requested = any((args.population_url, args.geometry_url, args.population_layout))
if not years or (custom_release_requested and len(years) != 1):
message = "An explicit governed release requires exactly one population year" if custom_release_requested else "No years requested"
print(json.dumps({"status": "error", "message": message}), file=sys.stderr)
return 2
try:
releases = {
year: resolve_release_config(
year,
population_url=args.population_url if custom_release_requested else None,
geometry_url=args.geometry_url if custom_release_requested else None,
layout=args.population_layout if custom_release_requested else None,
)
for year in years
}
except (ValueError, StatbelPreflightError) as exc:
print(json.dumps({"status": "error", "message": str(exc)}, ensure_ascii=False), file=sys.stderr)
return 2
output_dir = resolve_output_dir(args, scope)
output_dir.mkdir(parents=True, exist_ok=True)
results: list[dict[str, Any]] = []
try:
boundary_path = resolve_boundary_path(args, scope)
boundary = load_boundary(boundary_path, scope)
prepared: list[dict[str, Any]] = []
with build_session() as source_session:
for year in years:
release = releases[year]
path = snapshot_path(output_dir, scope, year)
manifest_path = preflight_manifest_path(output_dir, scope, year)
preflight_status = "passed"
if args.force or not path.exists():
geometry_content = download_archive(
source_session,
url=release.geometry_url,
year=year,
layout=None,
max_bytes=MAX_GEOMETRY_ARCHIVE_BYTES,
timeout=args.request_timeout,
)
population_content = download_archive(
source_session,
url=release.population_url,
year=year,
layout=release.layout,
max_bytes=MAX_POPULATION_ARCHIVE_BYTES,
timeout=args.request_timeout,
)
path, manifest_path, _manifest = stage_release(
year=year,
population_content=population_content,
geometry_content=geometry_content,
output_dir=output_dir,
boundary=boundary,
scope=scope,
release=release,
)
elif manifest_path.is_file():
load_preflight_manifest(manifest_path, path, year, scope)
else:
preflight_status = "legacy_existing_only"
payload = json.loads(path.read_text(encoding="utf-8"))
prepared.append(
{
"year": year,
"path": path,
"manifest_path": manifest_path if manifest_path.is_file() else None,
"feature_count": len(payload.get("features") or []),
"preflight_status": preflight_status,
}
)
if args.fetch_only:
results = [
{
"year": item["year"],
"path": str(item["path"]),
"preflight_manifest_path": str(item["manifest_path"]) if item["manifest_path"] else None,
"preflight_status": item["preflight_status"],
"feature_count": item["feature_count"],
"status": "prepared" if item["preflight_status"] == "passed" else "legacy_cached",
}
for item in prepared
]
else:
base_url = args.base_url.rstrip("/")
with requests.Session() as api_session:
project_id, area_id, existing = locate_workspace(
api_session,
base_url,
project_name,
area_name,
args.import_timeout,
)
for item in prepared:
year = int(item["year"])
path = item["path"]
observed_at = f"{year}-01-01T00:00:00+00:00"
dataset = next(
(
item
for item in existing
if item.get("temporal_series_key") == series_key(scope)
and str(item.get("observed_at") or "").startswith(observed_at[:10])
),
None,
)
if dataset:
results.append({"year": year, "dataset_id": dataset["id"], "feature_count": dataset.get("feature_count"), "status": "existing"})
continue
if item["preflight_status"] != "passed" or item["manifest_path"] is None:
raise RuntimeError(
f"Statbel {year} has only a legacy cached snapshot; rerun with --force to create preflight evidence before import"
)
dataset = upload_snapshot(
api_session,
base_url,
project_id,
area_id,
year,
path,
args.import_timeout,
scope,
item["manifest_path"],
releases[year],
)
results.append({"year": year, "dataset_id": dataset["id"], "feature_count": dataset.get("feature_count"), "status": "imported"})
except (OSError, RuntimeError, requests.RequestException, ValueError, KeyError, zipfile.BadZipFile) as exc:
payload = {"status": "error", "message": str(exc)}
if isinstance(exc, StatbelPreflightError):
payload.update({"error_code": exc.code, "details": exc.details})
print(json.dumps(payload, ensure_ascii=False), file=sys.stderr)
return 1
print(
json.dumps(
{
"status": "ok",
"scope": scope.key,
"display_name": scope.display_name,
"member_count": len(scope.members),
"series": series_key(scope),
"snapshots": results,
},
ensure_ascii=False,
indent=2,
)
)
return 0
if __name__ == "__main__":
sys.exit(main())