JP: four editions, and a date per parcel

CHANGELOG.md

@@ -11,6 +11,7 @@ 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
+- JP: editions 2021-2024, each with the determination date of the parcel rather than a constant
 - PerFileBaseConverter: convert a multi-file source one file at a time and merge the parts, so a dataset larger than memory can be converted; used by the Spain-wide converter
 - FiboaDuckDBBaseConverter: convert a source that is already Parquet with SQL, without loading it into memory
 - Update vecorel-cli to v0.2.17:

fiboa_cli/datasets/jp.py

@@ -1,14 +1,13 @@
-import pandas as pd
+from fiboa_cli.conversion.duckdb import FiboaDuckDBBaseConverter
 
-from ..conversion.fiboa_converter import FiboaBaseConverter
 
-
-class JPConverter(FiboaBaseConverter):
+class JPConverter(FiboaDuckDBBaseConverter):
     variants = {
         "2024": "https://data.source.coop/pacificspatial/field-polygon-jp/parquet/jp_field_polygons_2024.parquet",
         "2023": "https://data.source.coop/pacificspatial/field-polygon-jp/parquet/jp_field_polygons_2023.parquet",
         "2022": "https://data.source.coop/pacificspatial/field-polygon-jp/parquet/jp_field_polygons_2022.parquet",
         "2021": "https://data.source.coop/pacificspatial/field-polygon-jp/parquet/jp_field_polygons_2021.parquet",
+        "test": "./tests/data-files/convert/jp/jp_field_polygons_2024.parquet",
     }
 
     id = "jp"
@@ -32,21 +31,13 @@ class JPConverter(FiboaBaseConverter):
         "local_government_cd": "admin_local_code",
         "issue_year": "determination:datetime",
     }
+    # SQL migrations (DuckDB converter): per-feature determination date from the issue year
     column_migrations = {
-        "issue_year": lambda col: pd.to_datetime(col, format="%Y"),
+        "issue_year": "make_timestamp(CAST(issue_year AS INTEGER), 1, 1, 0, 0, 0) AT TIME ZONE 'UTC'",
     }
-
     missing_schemas = {
         "properties": {
             "land_type_en": {"type": "string"},
             "admin_local_code": {"type": "string"},
         }
     }
-
-    def convert(self, *args, **kwargs):
-        # Open only these columns to limit memory usage
-        super().convert(
-            *args,
-            columns=["GEOM", "polygon_uuid", "land_type_en", "local_government_cd", "issue_year"],
-            **kwargs,
-        )