mikebridge commented on code in PR #45395:
URL: https://github.com/apache/superset/pull/45395#discussion_r4330703167
##########
superset-core/src/superset_core/semantic_layers/testing.py:
##########
@@ -59,3 +78,250 @@ def semantic_layer_registration(monkeypatch:
pytest.MonkeyPatch) -> None:
integration lane. Use in isolated provider test processes, not a live host.
"""
monkeypatch.setattr(decorators, "semantic_layer", _registration)
+
+
+# Keep test data and provider construction in the provider's own fixtures. This
+# suite consumes the real SDK types rather than a copy of a factory signature.
+class SemanticProviderConformance:
+ """Subclass in a ``Test...`` class and supply the documented provider
fixtures.
+
+ Query fixtures seed discriminating data and provide independent expected
+ Arrow tables for identity, grain, NULL, grouped OR, and order-before-limit.
+ Error fixtures call real provider methods against controlled backend
outcomes.
+ See the provider author guide for every fixture and the limits of this
suite.
+ """
+
+ def test_catalog_identity(
+ self, semantic_view: SemanticView, semantic_reloaded_view: SemanticView
+ ) -> None:
+ """Stable selections survive reloads without ambiguous catalog
members."""
+ assert semantic_view.uid()
+ assert semantic_view.uid() == semantic_reloaded_view.uid()
+ assert _catalog(semantic_view) == _catalog(semantic_reloaded_view)
+
+ @pytest.mark.parametrize(
+ "case", ["identity", "grain", "null", "not_null", "or", "order_limit"]
+ )
+ def test_query_outputs(
+ self,
+ case: str,
+ semantic_view: SemanticView,
+ semantic_query_cases: Mapping[str, tuple[SemanticQuery, pa.Table]],
+ ) -> None:
+ """Compare executed results, including column names and row order."""
+ query: SemanticQuery
+ expected: pa.Table
+ query, expected = semantic_query_cases[case]
+ assert expected.num_rows > 0, (
+ f"{case} must distinguish a correct result from no data"
+ )
+ assert query.order or expected.num_rows == 1, (
+ f"{case}: multi-row fixtures need explicit order"
+ )
+ assert set(query.dimensions) <= semantic_view.get_dimensions()
+ assert set(query.metrics) <= semantic_view.get_metrics()
+ if case == "grain":
+ assert any(dimension.grain is not None for dimension in
query.dimensions)
Review Comment:
Thanks. I don't think this is a real gap. The grain case doesn't stop at
checking that the query has a grained dimension: the test then runs the query
and compares the provider's result with the fixture's expected Arrow table,
including column names and row order. If a provider picks the wrong grain
variant, the bucketed rows differ and the comparison fails.
Requiring a second variant of the same dimension in the catalog would also
wrongly fail providers that only expose one grain. Making the expected table
actually tell grains apart is the fixture author's job, just as the existing
`num_rows > 0` guard covers the no-data case. Leaving this as is.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
