Add governed Statbel edition probe

2026-07-16 22:14:48 +02:00
parent 9059db3445
commit da2371d662
23 changed files with 805 additions and 28 deletions
@@ -34,8 +34,10 @@
  <Config Name="Orthophoto WMS URL" Target="ORTHOPHOTO_WMS_URL" Default="https://geo.api.vlaanderen.be/OMWRGBMRVL/wms" Mode="" Description="Official Digitaal Vlaanderen most-recent winter orthophoto WMS endpoint." Type="Variable" Display="advanced" Required="true" Mask="false">https://geo.api.vlaanderen.be/OMWRGBMRVL/wms</Config>
  <Config Name="Orthophoto Resolution (m)" Target="ORTHOPHOTO_RESOLUTION_M" Default="1.0" Mode="" Description="Requested analysis sampling in metres per pixel. Keep at 1.0 for the active building model profile." Type="Variable" Display="advanced" Required="true" Mask="false">1.0</Config>
  <Config Name="Orthophoto Maximum Side (m)" Target="ORTHOPHOTO_MAX_SIDE_M" Default="1024" Mode="" Description="Safety limit for each selected rectangle side before external acquisition and local inference." Type="Variable" Display="advanced" Required="true" Mask="false">1024</Config>
-  <Config Name="Official Catalog Edition Probe" Target="SOURCE_CATALOG_PROBE_ENABLED" Default="true" Mode="" Description="Allow explicit read-only GRB, orthophoto and ALZ edition checks. This never imports provider data." Type="Variable" Display="advanced" Required="true" Mask="false">true</Config>
+  <Config Name="Official Catalog Edition Probe" Target="SOURCE_CATALOG_PROBE_ENABLED" Default="true" Mode="" Description="Allow explicit read-only GRB, orthophoto, Statbel and ALZ edition checks. This never imports provider data." Type="Variable" Display="advanced" Required="true" Mask="false">true</Config>
  <Config Name="GRB Catalog WFS URL" Target="SOURCE_CATALOG_GRB_WFS_URL" Default="https://geo.api.vlaanderen.be/GRB/wfs" Mode="" Description="Official GRB WFS used only for capabilities and linked ISO metadata checks." Type="Variable" Display="advanced" Required="true" Mask="false">https://geo.api.vlaanderen.be/GRB/wfs</Config>
+  <Config Name="Statbel DCAT URL" Target="SOURCE_CATALOG_STATBEL_DCAT_URL" Default="https://doc.statbel.be/publications/DCAT/DCAT_opendata_datasets.ttl" Mode="" Description="Exact official Statbel Turtle catalog used only to identify population-by-sector releases and distribution identities." Type="Variable" Display="advanced" Required="true" Mask="false">https://doc.statbel.be/publications/DCAT/DCAT_opendata_datasets.ttl</Config>
+  <Config Name="Statbel Catalog Maximum Response (MiB)" Target="SOURCE_CATALOG_STATBEL_MAX_RESPONSE_MB" Default="5" Mode="" Description="Separate bounded response limit for the official Statbel DCAT Turtle catalog; linked data files are never downloaded." Type="Variable" Display="advanced" Required="true" Mask="false">5</Config>
  <Config Name="ALZ Release Page URL" Target="SOURCE_CATALOG_ALZ_RELEASE_URL" Default="https://landbouwcijfers.vlaanderen.be/open-geodata-landbouwgebruikspercelen" Mode="" Description="Exact official ALZ publication page used only to identify definitive and provisional agricultural parcel editions." Type="Variable" Display="advanced" Required="true" Mask="false">https://landbouwcijfers.vlaanderen.be/open-geodata-landbouwgebruikspercelen</Config>
  <Config Name="Catalog Probe Timeout (seconds)" Target="SOURCE_CATALOG_PROBE_TIMEOUT_SECONDS" Default="10" Mode="" Description="Per-request timeout for explicit read-only official catalog checks." Type="Variable" Display="advanced" Required="true" Mask="false">10</Config>
  <Config Name="Catalog Probe Maximum Response (MiB)" Target="SOURCE_CATALOG_PROBE_MAX_RESPONSE_MB" Default="2" Mode="" Description="Maximum capabilities or ISO metadata response size accepted by a catalog probe." Type="Variable" Display="advanced" Required="true" Mask="false">2</Config>
@@ -33,10 +33,12 @@ ORTHOPHOTO_MIN_SIDE_M=128
 ORTHOPHOTO_MAX_SIDE_M=1024
 ORTHOPHOTO_CACHE_TTL_HOURS=24

-# Explicit read-only edition checks for GRB, orthophoto and ALZ publications.
-# No feature, raster or ALZ archive is downloaded by these probes.
+# Explicit read-only edition checks for GRB, orthophoto, Statbel and ALZ publications.
+# No feature, raster, Statbel distribution or ALZ archive is downloaded by these probes.
 SOURCE_CATALOG_PROBE_ENABLED=true
 SOURCE_CATALOG_GRB_WFS_URL=https://geo.api.vlaanderen.be/GRB/wfs
+SOURCE_CATALOG_STATBEL_DCAT_URL=https://doc.statbel.be/publications/DCAT/DCAT_opendata_datasets.ttl
+SOURCE_CATALOG_STATBEL_MAX_RESPONSE_MB=5
 SOURCE_CATALOG_ALZ_RELEASE_URL=https://landbouwcijfers.vlaanderen.be/open-geodata-landbouwgebruikspercelen
 SOURCE_CATALOG_PROBE_TIMEOUT_SECONDS=10
 SOURCE_CATALOG_PROBE_MAX_RESPONSE_MB=2
@@ -29,6 +29,8 @@ ORTHOPHOTO_MAX_SIDE_M="${ORTHOPHOTO_MAX_SIDE_M:-1024}"
 ORTHOPHOTO_CACHE_TTL_HOURS="${ORTHOPHOTO_CACHE_TTL_HOURS:-24}"
 SOURCE_CATALOG_PROBE_ENABLED="${SOURCE_CATALOG_PROBE_ENABLED:-true}"
 SOURCE_CATALOG_GRB_WFS_URL="${SOURCE_CATALOG_GRB_WFS_URL:-https://geo.api.vlaanderen.be/GRB/wfs}"
+SOURCE_CATALOG_STATBEL_DCAT_URL="${SOURCE_CATALOG_STATBEL_DCAT_URL:-https://doc.statbel.be/publications/DCAT/DCAT_opendata_datasets.ttl}"
+SOURCE_CATALOG_STATBEL_MAX_RESPONSE_MB="${SOURCE_CATALOG_STATBEL_MAX_RESPONSE_MB:-5}"
 SOURCE_CATALOG_ALZ_RELEASE_URL="${SOURCE_CATALOG_ALZ_RELEASE_URL:-https://landbouwcijfers.vlaanderen.be/open-geodata-landbouwgebruikspercelen}"
 SOURCE_CATALOG_PROBE_TIMEOUT_SECONDS="${SOURCE_CATALOG_PROBE_TIMEOUT_SECONDS:-10}"
 SOURCE_CATALOG_PROBE_MAX_RESPONSE_MB="${SOURCE_CATALOG_PROBE_MAX_RESPONSE_MB:-2}"
@@ -134,6 +136,8 @@ docker run -d \
  -e ORTHOPHOTO_CACHE_TTL_HOURS="$ORTHOPHOTO_CACHE_TTL_HOURS" \
  -e SOURCE_CATALOG_PROBE_ENABLED="$SOURCE_CATALOG_PROBE_ENABLED" \
  -e SOURCE_CATALOG_GRB_WFS_URL="$SOURCE_CATALOG_GRB_WFS_URL" \
+  -e SOURCE_CATALOG_STATBEL_DCAT_URL="$SOURCE_CATALOG_STATBEL_DCAT_URL" \
+  -e SOURCE_CATALOG_STATBEL_MAX_RESPONSE_MB="$SOURCE_CATALOG_STATBEL_MAX_RESPONSE_MB" \
  -e SOURCE_CATALOG_ALZ_RELEASE_URL="$SOURCE_CATALOG_ALZ_RELEASE_URL" \
  -e SOURCE_CATALOG_PROBE_TIMEOUT_SECONDS="$SOURCE_CATALOG_PROBE_TIMEOUT_SECONDS" \
  -e SOURCE_CATALOG_PROBE_MAX_RESPONSE_MB="$SOURCE_CATALOG_PROBE_MAX_RESPONSE_MB" \