NZ: both editions, from manually downloaded files

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
+- NZ: 2017 and 2020 as variants, resolving the manual downloads from the cache folder
 - 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

fiboa_cli/datasets/nz.py

@@ -1,3 +1,5 @@
+import os
+
 import pandas as pd
 from vecorel_cli.vecorel.extensions import ADMIN_DIVISION
 
@@ -6,7 +8,17 @@
 
 
 class NZCropConverter(FiboaBaseConverter):
-    data_access = "Download manually from https://data.mfe.govt.nz/layer/105407-irrigated-land-area-raw-2020-update/"
+    data_access = """
+    Download manually (Koordinates login required) and place the zip in the cache folder:
+    - 2020: https://data.mfe.govt.nz/layer/105407-irrigated-land-area-raw-2020-update/ (mfe-irrigated-land-area-raw-2020-update-SHP.zip)
+    - 2017: https://data.mfe.govt.nz/layer/90838-irrigated-land-area-2017/ (mfe-irrigated-land-area-2017-SHP.zip)
+    Alternatively pass the zip with the `-i` CLI parameter.
+    """
+    variants = {
+        # keys are the cache filenames vecorel resolves before attempting a download
+        "2020": {"mfe-irrigated-land-area-raw-2020-update-SHP.zip": ["*.shp"]},
+        "2017": {"mfe-irrigated-land-area-2017-SHP.zip": ["*.shp"]},
+    }
 
     id = "nz"
     short_name = "New Zealand"
@@ -20,6 +32,22 @@ class NZCropConverter(FiboaBaseConverter):
 created in 2017. The current update has incorporated data from the 2019 – 2020 irrigation season.
     """
 
+    def download_files(self, uris, cache_folder=None):
+        """The sources are manual downloads (Koordinates login): resolve the bare
+        filenames from ``variants`` against the cache folder instead of the cwd."""
+        _, cache_dir = self.get_cache(cache_folder)
+        resolved = {}
+        for uri, target in uris.items():
+            if "://" not in uri and not os.path.isabs(uri) and not os.path.exists(uri):
+                cached = os.path.join(cache_dir, uri)
+                if not os.path.exists(cached):
+                    raise FileNotFoundError(
+                        f"{uri} is a manual download; place it in {cache_dir} (see data_access)"
+                    )
+                uri = cached
+            resolved[uri] = target
+        return super().download_files(resolved, cache_folder)
+
     provider = "Aqualinc Research Limited <https://environment.govt.nz/publications/national-irrigated-land-spatial-dataset-2020-update>"
     license = "CC-BY-4.0"
     extensions = {ADMIN_DIVISION}