From d062edbbe1d05df254d2a5d3a3fb4e2feb810c10 Mon Sep 17 00:00:00 2001
From: Codex <codex@geointel.local>
Date: Tue, 14 Jul 2026 15:31:54 +0200
Subject: [PATCH] fix: use WFS POST for historical land use

---
 .../test_sprint187_temporal_map_foundation.py |  1 +
 docs/CODEX_EXECUTION_LOG.md                   |  1 +
 docs/DATA_SOURCES.md                          |  4 +
 scripts/provision_mol_historical_landuse.py   | 92 ++++++++++++-------
 4 files changed, 67 insertions(+), 31 deletions(-)

diff --git a/backend/tests/test_sprint187_temporal_map_foundation.py b/backend/tests/test_sprint187_temporal_map_foundation.py
index 76ed41f5..85cc8bfe 100644
--- a/backend/tests/test_sprint187_temporal_map_foundation.py
+++ b/backend/tests/test_sprint187_temporal_map_foundation.py
@@ -245,6 +245,7 @@ def test_temporal_frontend_and_official_operator_contracts_exist() -> None:
     assert "/temporal/compare" in temporal_api
     assert "Statbel" in population and "area_weighted_sum" in population
     assert "HistLandgebruik" in landuse and "intersection_area" in landuse
+    assert "<wfs:GetFeature" in landuse and "session.post(" in landuse
     assert "provision_mol_population_history.py" in dockerfile
     assert "provision_mol_historical_landuse.py" in dockerfile
     assert "fake" not in population.lower()
diff --git a/docs/CODEX_EXECUTION_LOG.md b/docs/CODEX_EXECUTION_LOG.md
index 0063cd14..045f2e11 100644
--- a/docs/CODEX_EXECUTION_LOG.md
+++ b/docs/CODEX_EXECUTION_LOG.md
@@ -7801,3 +7801,4 @@ Live deployment correction:
 - Both Tower deploy entry points now wait for the `geointel` container healthcheck, which includes completed startup migrations and backend readiness, before launching the independent migration smoke.
 - The first Statbel upload exposed 3D sector coordinates (`Z=0`) against the canonical 2D PostGIS vector column. The source is valid; GeoIntel now preserves the original artifact, records the Z-feature count and explicitly drops Z only for the 2D query index.
 - Vector upload persistence is now atomic across Dataset, DatasetVersion and VectorFeature rows, with storage cleanup on rollback. This prevents the failed-indexing orphan state observed during the live import.
+- Tower could read the historical WFS capabilities but its gateway rejected XML `FILTER` content embedded in a GET query. The operator now sends the same read-only WFS 2.0 GetFeature request as XML POST; a live two-feature forest page returned successfully before redeployment.
diff --git a/docs/DATA_SOURCES.md b/docs/DATA_SOURCES.md
index d11344f8..c757258c 100644
--- a/docs/DATA_SOURCES.md
+++ b/docs/DATA_SOURCES.md
@@ -55,6 +55,10 @@ These historical map editions support exploratory area evolution, not
 cadastral object lineage. Their feature identities are declared unstable and
 GeoIntel does not fabricate added/removed object counts.
 
+The operator uses standards-compliant WFS 2.0 XML POST requests. This keeps
+the spatial/class filters server-side without exposing a long XML filter in a
+GET query, which the public gateway rejects.
+
 ## OSM
 
 - Naam: OpenStreetMap
diff --git a/scripts/provision_mol_historical_landuse.py b/scripts/provision_mol_historical_landuse.py
index 11da886b..3455110c 100644
--- a/scripts/provision_mol_historical_landuse.py
+++ b/scripts/provision_mol_historical_landuse.py
@@ -78,7 +78,7 @@ def build_session() -> requests.Session:
         status=5,
         backoff_factor=1.0,
         status_forcelist=(429, 500, 502, 503, 504),
-        allowed_methods=frozenset({"GET"}),
+        allowed_methods=frozenset({"GET", "POST"}),
         raise_on_status=True,
     )
     session = requests.Session()
@@ -127,6 +127,54 @@ def wfs_filter_xml(definition: ThemeDefinition, bounds: tuple[float, float, floa
     )
 
 
+def wfs_request_xml(
+    *,
+    collection: str,
+    filter_xml: str,
+    page_size: int,
+    start_index: int,
+) -> str:
+    return (
+        "<?xml version='1.0' encoding='UTF-8'?>"
+        "<wfs:GetFeature service='WFS' version='2.0.0' outputFormat='application/json' "
+        f"count='{page_size}' startIndex='{start_index}' "
+        "xmlns:wfs='http://www.opengis.net/wfs/2.0' "
+        "xmlns:fes='http://www.opengis.net/fes/2.0' "
+        "xmlns:gml='http://www.opengis.net/gml/3.2' "
+        "xmlns:HistLandgebruik='https://geo.api.vlaanderen.be/HistLandgebruik'>"
+        f"<wfs:Query typeNames='{collection}' srsName='EPSG:4326'>{filter_xml}</wfs:Query>"
+        "</wfs:GetFeature>"
+    )
+
+
+def fetch_wfs_page(
+    session: requests.Session,
+    *,
+    collection: str,
+    filter_xml: str,
+    page_size: int,
+    start_index: int,
+    timeout: int,
+) -> list[dict[str, Any]]:
+    response = session.post(
+        WFS_URL,
+        data=wfs_request_xml(
+            collection=collection,
+            filter_xml=filter_xml,
+            page_size=page_size,
+            start_index=start_index,
+        ).encode("utf-8"),
+        headers={"Content-Type": "application/xml; charset=UTF-8", "Accept": "application/json"},
+        timeout=timeout,
+    )
+    response.raise_for_status()
+    payload = response.json()
+    features = payload.get("features") if isinstance(payload, dict) else None
+    if not isinstance(features, list):
+        raise RuntimeError("Historical land-use WFS returned an invalid FeatureCollection")
+    return features
+
+
 def fetch_year(
     session: requests.Session,
     year: int,
@@ -145,23 +193,14 @@ def fetch_year(
         start_index = 0
         seen: set[str] = set()
         while True:
-            response = session.get(
-                WFS_URL,
-                params={
-                    "service": "WFS",
-                    "version": "2.0.0",
-                    "request": "GetFeature",
-                    "typeNames": collection,
-                    "outputFormat": "application/json",
-                    "srsName": "EPSG:4326",
-                    "FILTER": filter_xml,
-                    "count": page_size,
-                    "startIndex": start_index,
-                },
+            page = fetch_wfs_page(
+                session,
+                collection=collection,
+                filter_xml=filter_xml,
+                page_size=page_size,
+                start_index=start_index,
                 timeout=timeout,
             )
-            response.raise_for_status()
-            page = response.json().get("features") or []
             for raw_feature in page:
                 feature_id = str(raw_feature.get("id") or "")
                 if not feature_id or feature_id in seen:
@@ -234,23 +273,14 @@ def write_theme_snapshot(
             )
             output.write(',"features":[')
             while True:
-                response = session.get(
-                    WFS_URL,
-                    params={
-                        "service": "WFS",
-                        "version": "2.0.0",
-                        "request": "GetFeature",
-                        "typeNames": collection,
-                        "outputFormat": "application/json",
-                        "srsName": "EPSG:4326",
-                        "FILTER": filter_xml,
-                        "count": page_size,
-                        "startIndex": start_index,
-                    },
+                page = fetch_wfs_page(
+                    session,
+                    collection=collection,
+                    filter_xml=filter_xml,
+                    page_size=page_size,
+                    start_index=start_index,
                     timeout=timeout,
                 )
-                response.raise_for_status()
-                page = response.json().get("features") or []
                 for raw_feature in page:
                     feature_id = str(raw_feature.get("id") or "")
                     if not feature_id or feature_id in seen: