BE-VLG: campaigns 2018-2026, and a real field id

CHANGELOG.md

@@ -36,6 +36,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 - ES-CL: the ITACyL server is https-only, the 2025 shapefiles sit in province subfolders, and C_REFREC is the identifier
 - A test refuses a fixture above 5 MB, committed or merely lying in the fixture folder, because a failing convert test downloads the real source there
 - ES-MD: find RECINTO.shp wherever the archive puts it
+- BE-VLG: editions 2018-2026; REF_ID is published as block_id and the row index identifies the field, the QGIS styles table in the 2026 GeoPackage is skipped, and the 2020 archive is read as cp1252 with its CRS declared
 - FI: one variant per year (2020-2025) instead of a hard-coded 2023, with the year in the cache name
 - AT: extract the archive instead of reading the GeoPackage through /vsizip, which never finished for 2018
 - SK: KODKD is the LPIS block code (non-unique, sometimes empty), so it is kept as block_id and the row index identifies the field

fiboa_cli/datasets/be_vlg.py

@@ -7,9 +7,12 @@
 
 
 class Converter(AdminConverterMixin, AddHCATMixin, FiboaBaseConverter):
+    # Each archive holds one GeoPackage, but not under the name of the zip
+    # (2020 least of all), so glob for it rather than deriving it.
     variants = {
-        str(k): {PREFIX + v: [v.replace("_GPKG.zip", ".gpkg")]}
+        str(k): {PREFIX + v: ["*.gpkg"]}
         for k, v in (
+            (2026, "agpa_2026_2026-06-02_public.zip"),
             (2025, "Landbouwgebruikspercelen_2025_-_Voorlopig_(extractie_02-06-2025)_GPKG.zip"),
             (2024, "Landbouwgebruikspercelen_2024_-_Definitief_(extractie_27-03-2025)_GPKG.zip"),
             (2023, "Landbouwgebruikspercelen_2023_-_Definitief_(extractie_28-03-2024)_GPKG.zip"),
@@ -34,17 +37,54 @@ class Converter(AdminConverterMixin, AddHCATMixin, FiboaBaseConverter):
     attribution = "Bron: Dept. LV"
     license = "Licentie modellicentie-gratis-hergebruik/v1.0 <https://data.vlaanderen.be/id/licentie/modellicentie-gratis-hergebruik/v1.0>"
 
+    # Fix cp1252 encoding for 2020
+    CP1252_EDITIONS = {"2020"}
+
+    def layer_filter(self, layer, uri):
+        # The 2026 GeoPackage carries a QGIS "layer_styles" table whose single
+        # row was read as a field.
+        return layer != "layer_styles"
+
+    def read_data(self, paths, **kwargs):
+        if self.variant in self.CP1252_EDITIONS:
+            kwargs["encoding"] = "cp1252"
+        return super().read_data(paths, **kwargs)
+
+    # the 2026 "agpa" edition renamed every column to English
+    RENAMES_2026 = {
+        "reference_id": "REF_ID",
+        "maincrop_code": "GWSCOD_H",
+        "maincrop_title": "GWSNAM_H",
+        "area_ha": "GRAF_OPP",
+    }
+
+    LAMBERT_72 = "EPSG:31370"
+
+    def migrate(self, gdf):
+        if gdf.crs is None or gdf.crs.to_epsg() is None:
+            gdf = gdf.set_crs(self.LAMBERT_72, allow_override=True)
+        if "maincrop_code" in gdf.columns:
+            gdf = gdf.rename(columns=self.RENAMES_2026)
+            if "BT_OMSCH" not in gdf.columns:  # no farm-typology column any more
+                gdf["BT_OMSCH"] = None
+        return super().migrate(gdf)
+
+    index_as_id = True
     columns = {
         "geometry": "geometry",
+        "id": "id",
         "BT_OMSCH": "typology",
         "GRAF_OPP": "metrics:area",
-        "REF_ID": "id",
+        "REF_ID": "block_id",
         "GWSCOD_H": "crop:code",
         "GWSNAM_H": "crop:name",
     }
-    column_additions = {
-        "determination:datetime": "2024-03-28T00:00:00Z",
-    }
+    use_variant_as_determination = True
     ec_mapping_csv = "be_vlg_2021.csv"
 
-    missing_schemas = {"properties": {"typology": {"type": "string"}}}
+    missing_schemas = {
+        "properties": {
+            "typology": {"type": "string"},
+            "block_id": {"type": "string"},
+        }
+    }