From e6583aad52f44deb229277d03cb4f74bcd9bc5ba Mon Sep 17 00:00:00 2001
From: amercader <amercadero@gmail.com>
Date: Thu, 9 May 2024 16:24:02 +0200
Subject: [PATCH] [#56] [#56] Initial e2e scheming support test

---
 ckanext/dcat/tests/test_scheming_support.py | 94 +++++++++++++++++++++
 1 file changed, 94 insertions(+)
 create mode 100644 ckanext/dcat/tests/test_scheming_support.py

diff --git a/ckanext/dcat/tests/test_scheming_support.py b/ckanext/dcat/tests/test_scheming_support.py
new file mode 100644
index 00000000..cbba044e
--- /dev/null
+++ b/ckanext/dcat/tests/test_scheming_support.py
@@ -0,0 +1,94 @@
+import pytest
+
+from rdflib.namespace import RDF
+
+from ckan.tests.helpers import call_action
+
+from ckanext.dcat import utils
+from ckanext.dcat.processors import RDFSerializer
+from ckanext.dcat.profiles import (
+    DCAT,
+    DCT,
+    ADMS,
+    XSD,
+    VCARD,
+    FOAF,
+    SCHEMA,
+    SKOS,
+    LOCN,
+    GSP,
+    OWL,
+    SPDX,
+    GEOJSON_IMT,
+    DISTRIBUTION_LICENSE_FALLBACK_CONFIG,
+)
+from ckanext.dcat.tests.utils import BaseSerializeTest
+
+
+@pytest.mark.usefixtures("with_plugins", "clean_db")
+@pytest.mark.ckan_config("ckan.plugins", "dcat scheming_datasets")
+@pytest.mark.ckan_config(
+    "scheming.dataset_schemas", "ckanext.dcat.schemas:dcat_ap_2.1.yaml"
+)
+@pytest.mark.ckan_config("scheming.presets", "ckanext.scheming:presets.json")
+class TestSchemingSupport(BaseSerializeTest):
+    def test_e2e_ckan_to_dcat(self):
+        """
+        Create a dataset using the scheming schema, check that fields
+        are exposed in the DCAT RDF graph
+        """
+
+        dataset_dict = {
+            # Core fields
+            "name": "test-dataset",
+            "title": "Test DCAT dataset",
+            "notes": "Lorem ipsum",
+            "url": "http://example.org/ds1",
+            "version": "1.0b",
+            "tags": [{"name": "Tag 1"}, {"name": "Tag 2"}],
+            # Standard fields
+            "version_notes": "Some version notes",
+            # List fields (lists)
+            "conforms_to": ["Standard 1", "Standard 2"],
+            # Repeating subfields
+            "contact": [
+                {"name": "Contact 1", "email": "contact1@example.org"},
+                {"name": "Contact 2", "email": "contact2@example.org"},
+            ],
+            # TODO: resources
+        }
+
+        dataset = call_action("package_create", **dataset_dict)
+
+        # Make sure schema was used
+        assert dataset["conforms_to"][0] == "Standard 1"
+        assert dataset["contact"][0]["name"] == "Contact 1"
+
+        s = RDFSerializer(profiles=["euro_dcat_ap"])
+        g = s.g
+
+        dataset_ref = s.graph_from_dataset(dataset)
+
+        assert str(dataset_ref) == utils.dataset_uri(dataset)
+
+        # Core fields
+        assert self._triple(g, dataset_ref, RDF.type, DCAT.Dataset)
+        assert self._triple(g, dataset_ref, DCT.title, dataset["title"])
+        assert self._triple(g, dataset_ref, DCT.description, dataset["notes"])
+
+        # Standard fields
+        assert self._triple(g, dataset_ref, ADMS.versionNotes, dataset["version_notes"])
+
+        # List fields
+        # TODO helper function
+        conforms = [t for t in g.triples((dataset_ref, DCT.conformsTo, None))]
+        assert len(conforms) == len(dataset["conforms_to"])
+        for index, item in enumerate(conforms):
+            assert str(item[2]) == dataset["conforms_to"][index]
+
+        # Repeating subfields
+
+        contact_details = [t for t in g.triples((dataset_ref, DCAT.contactPoint, None))]
+
+        # TODO this will fail
+        assert len(contact_details) == len(dataset["contact"])