Removed redundant encoding patches.

CHANGELOG.md

@@ -10,6 +10,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 - Update vecorel-cli to v0.2.17:
   - GeoJSON is read as UTF-8 as the format mandates, instead of the platform locale (cp1252 on Windows mangled umlauts)
   - GeoJSON files with a byte order mark no longer fail to read
+  - Drop the per-converter UTF-8 workarounds in de_bw and de_he, now redundant
 - Converter for Spain (whole), based on the FEGA 2025+ data
 - Add Italy Tuscany (IT-1) basd on EuroCrops v2
 - Suuport multiple years for CZ

fiboa_cli/datasets/de_bw.py

@@ -43,10 +43,6 @@ class DEBWConverter(AdminConverterMixin, DEIACSMixin, FiboaBaseConverter):
 
     page_size = 50_000
 
-    # read_geojson calls open() without an encoding, so it follows the platform locale:
-    # UTF-8 on Linux/macOS, cp1252 on Windows, which would turn "Grünland" into mojibake.
-    open_options = dict(encoding="utf-8")
-
     columns = {
         "geometry": "geometry",
         "Geo-ID": "id",

fiboa_cli/datasets/de_he.py

@@ -40,7 +40,6 @@ class DEHEConverter(AdminConverterMixin, DEIACSMixin, FiboaBaseConverter):
         "declaredArea": "metrics:area",  # in hectares, hence the area_is_in_ha default
         "validFrom": "determination:datetime",
     }
-    open_options = dict(encoding="utf-8")
     column_migrations = {
         "validFrom": lambda col: pd.to_datetime(col, format="%d.%m.%Y"),
     }

fiboa_cli/datasets/es_cat.py

@@ -54,6 +54,8 @@ class ESCatConverter(FiboaBaseConverter):
         "crop:code": "crop:code",
         "crop:name_en": "crop:name_en",
     }
+    # Tells GDAL how the shapefile variants are encoded, since a shapefile does not have to say.
+    # Unrelated to the GeoJSON encoding that vecorel-cli handles, so it is still needed here.
     open_options = dict(encoding="utf-8")
     column_migrations = {
         "campanya": lambda col: pd.to_datetime(col, format="%Y"),