aminghadersohi commented on code in PR #45912:
URL: https://github.com/apache/superset/pull/45912#discussion_r4450501689
##########
superset-core/src/superset_core/semantic_layers/testing.py:
##########
@@ -272,6 +296,82 @@ def test_imports_and_static_schema(
assert completed.returncode == 0, completed.stdout + completed.stderr
+def _assert_null_placement_witness(
+ query: SemanticQuery,
+ view: SemanticView,
+ expected: pa.Table,
+ *,
+ order_index: int = 0,
+) -> None:
+ """Require a page that observes the selected order key's NULL placement.
+
+ Placement on a later key applies within ties of all preceding keys.
+ Reversing it within those ties must change which rows the page keeps.
+ """
+ assert query.order, "null_placement fixture requires an order"
+ assert len(query.order) > order_index, (
+ "null_placement fixture requires the selected order key"
+ )
+ term: tuple[object, ...] = query.order[order_index]
+ placement: NullPlacement | None = null_placement(term)
+ assert placement is not None, (
+ "null_placement fixture's selected order key requires a NullPlacement"
+ )
+ member: object = term[0]
+ assert isinstance(member, Dimension), (
+ "null_placement fixture must order by a selected dimension"
+ )
+ assert member in query.dimensions, (
+ "null_placement fixture must order by a selected dimension"
+ )
+ prefix: list[str] = []
+ key: object
+ for key, _ in query.order[:order_index]:
+ assert isinstance(key, (Dimension, Metric))
+ assert key in [*query.dimensions, *query.metrics]
+ prefix.append(key.name)
+ assert query.limit is not None
+ assert query.limit > 0
+ full: pa.Table = view.get_table(replace(query, limit=None,
offset=None)).results
+ rows: list[dict[str, object]] = full.to_pylist()
+ values: list[object] = full.column(member.name).to_pylist()
+ assert any(value is None for value in values), (
+ "null_placement fixture requires NULL values of the order key"
+ )
+ assert any(value is not None for value in values), (
+ "null_placement fixture requires non-NULL values of the order key"
+ )
+ groups: dict[tuple[object, ...], list[int]] = {}
+ index: int
+ row: dict[str, object]
+ for index, row in enumerate(rows):
+ groups.setdefault(tuple(row[name] for name in prefix),
[]).append(index)
Review Comment:
STRUCT/LIST prefix dimensions become dict/list values in `to_pylist()`, so
this required case raises `TypeError: unhashable type` even when ordering is
correct. Keep the hashable Arrow scalars as prefix keys.
```suggestion
groups.setdefault(
tuple(full.column(name)[index] for name in prefix), []
).append(index)
```
##########
superset-core/src/superset_core/semantic_layers/testing.py:
##########
@@ -272,6 +296,82 @@ def test_imports_and_static_schema(
assert completed.returncode == 0, completed.stdout + completed.stderr
+def _assert_null_placement_witness(
+ query: SemanticQuery,
+ view: SemanticView,
+ expected: pa.Table,
+ *,
+ order_index: int = 0,
+) -> None:
+ """Require a page that observes the selected order key's NULL placement.
+
+ Placement on a later key applies within ties of all preceding keys.
+ Reversing it within those ties must change which rows the page keeps.
+ """
+ assert query.order, "null_placement fixture requires an order"
+ assert len(query.order) > order_index, (
+ "null_placement fixture requires the selected order key"
+ )
+ term: tuple[object, ...] = query.order[order_index]
+ placement: NullPlacement | None = null_placement(term)
+ assert placement is not None, (
+ "null_placement fixture's selected order key requires a NullPlacement"
+ )
+ member: object = term[0]
+ assert isinstance(member, Dimension), (
+ "null_placement fixture must order by a selected dimension"
+ )
+ assert member in query.dimensions, (
+ "null_placement fixture must order by a selected dimension"
+ )
+ prefix: list[str] = []
+ key: object
+ for key, _ in query.order[:order_index]:
+ assert isinstance(key, (Dimension, Metric))
+ assert key in [*query.dimensions, *query.metrics]
+ prefix.append(key.name)
+ assert query.limit is not None
+ assert query.limit > 0
+ full: pa.Table = view.get_table(replace(query, limit=None,
offset=None)).results
+ rows: list[dict[str, object]] = full.to_pylist()
+ values: list[object] = full.column(member.name).to_pylist()
+ assert any(value is None for value in values), (
+ "null_placement fixture requires NULL values of the order key"
+ )
+ assert any(value is not None for value in values), (
+ "null_placement fixture requires non-NULL values of the order key"
+ )
+ groups: dict[tuple[object, ...], list[int]] = {}
+ index: int
+ row: dict[str, object]
+ for index, row in enumerate(rows):
+ groups.setdefault(tuple(row[name] for name in prefix),
[]).append(index)
+ placed: list[int] = []
+ opposite: list[int] = []
+ indices: list[int]
+ for indices in groups.values():
+ nulls: list[int] = [index for index in indices if values[index] is
None]
+ others: list[int] = [index for index in indices if values[index] is
not None]
+ placed.extend(
+ others + nulls if placement is NullPlacement.LAST else nulls +
others
+ )
+ opposite.extend(
+ nulls + others if placement is NullPlacement.LAST else others +
nulls
+ )
+ assert placed == list(range(full.num_rows)), (
+ f"{member.name}: NULL values must sort {placement.value.lower()}, got
{values}"
+ )
+ start: int = query.offset or 0
+ stop: int = start + query.limit
+ assert sorted(repr(rows[index]) for index in placed[start:stop]) != sorted(
+ repr(rows[index]) for index in opposite[start:stop]
Review Comment:
The full-row check accepts `(A,x),(NULL,y),(NULL,z)` at offset 1/limit 1,
although either placement may return `(NULL,y)` because NULL ties are
unordered. The old key-value check rejected this non-discriminating fixture.
--
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]
