aminghadersohi commented on code in PR #45681:
URL: https://github.com/apache/superset/pull/45681#discussion_r4385175135
##########
superset/models/helpers.py:
##########
@@ -3994,6 +4019,201 @@ def get_rendered_sql(
def text(self, clause: str) -> TextClause:
return self.db_engine_spec.get_text_clause(clause)
+ def _get_rls_schema(self) -> str:
+ """Resolve RLS tables with the same schema policy as SQL
expressions."""
+ return get_rls_schema(
+ self.database,
+ self.catalog,
+ self.schema,
+ self.sql or "",
+ self.template_params_dict,
+ )
+
+ def _get_filter_column(
+ self,
+ name: str,
+ columns_by_name: dict[str, "TableColumn"],
+ ) -> Optional["TableColumn"]:
+ """Resolve real names before the first matching verbose filter
label."""
+ col = columns_by_name.get(name)
+ if col is not None:
+ return col
+ return next((col for col in self.columns if col.verbose_name == name),
None)
+
+ def _get_query_sql_expressions( # noqa: C901
+ self,
+ query_obj: QueryObjectDict,
+ template_processor: BaseTemplateProcessor,
+ granularity: str | None,
+ ) -> list[str]:
+ """Find SQL-bearing chart fields without building a chart or its
prequeries."""
+ columns_by_name = {col.column_name: col for col in self.columns}
+ columns = {name: col.expression for name, col in
columns_by_name.items()}
+ metrics = {metric.metric_name: metric.expression for metric in
self.metrics}
+ selected_columns = query_obj.get("columns") or []
+ selected_metrics = query_obj.get("metrics") or []
+ adhoc_columns_by_label = {
+ col.get("label"): col
+ for col in selected_columns
+ if utils.is_adhoc_column(col)
+ }
+ metric_labels = {utils.get_metric_name(metric) for metric in
selected_metrics}
+ expressions: list[str] = []
+
+ def add(value: Any, metric: bool = False) -> None:
+ """Resolve stored references in the namespace used by the query
sink."""
+ if isinstance(value, str):
+ references = metrics if metric else columns
+ expressions.append(references.get(value) or value)
+ elif isinstance(value, dict):
+ if sql := value.get("sqlExpression"):
+ sql = template_processor.process_template(sql)
+ # Adhoc columns can name a saved calculated column after
+ # rendering. SQL metrics use their SQL literally instead.
+ expressions.append(
+ sql if metric else columns.get(sql.strip()) or sql
+ )
+ add(value.get("column"))
+ add(value.get("column_name"))
+
+ def add_orderby(value: Any) -> None:
+ """ORDER BY prefers selected labels before stored metric/column
names."""
+ if isinstance(value, str):
+ if value in metric_labels:
+ # Selected metrics have already been collected.
+ return
+ if value in adhoc_columns_by_label:
+ add(adhoc_columns_by_label[value])
+ return
+ add(
+ value,
+ metric=utils.is_adhoc_metric(value)
+ or (isinstance(value, str) and value in metrics),
+ )
+
+ def add_filter(value: Any) -> None:
+ """Filters accept verbose column names before stored metric
names."""
+ if not isinstance(value, str):
+ add(value)
+ elif value == utils.DTTM_ALIAS and query_obj.get("is_timeseries",
True):
+ add(granularity)
+ elif (col := self._get_filter_column(value, columns_by_name)) is
not None:
+ expressions.append(col.expression or value)
+ elif value in metrics:
+ add(value, metric=True)
+ elif value in adhoc_columns_by_label:
+ add(adhoc_columns_by_label[value])
+
+ for value in query_obj.get("groupby") or selected_columns:
+ add(value)
+ for metric_value in selected_metrics:
+ add(metric_value, metric=True)
+ for orderby_value, _ascending in query_obj.get("orderby") or []:
+ add_orderby(orderby_value)
+ for flt in query_obj.get("filter") or []:
+ add_filter(flt.get("col"))
+ series_limit = query_obj.get("series_limit") or (
+ query_obj.get("timeseries_limit")
+ if query_obj.get("is_timeseries", True)
+ else 0
+ )
+ add(
+ (
+ query_obj.get("series_limit_metric")
+ or query_obj.get("timeseries_limit_metric")
+ )
+ if series_limit
+ else None,
+ metric=True,
+ )
+ add(granularity)
+ if (
+ granularity
+ and self.always_filter_main_dttm
+ and self.main_dttm_col in self.dttm_cols
+ and self.main_dttm_col != granularity
+ ):
+ add(self.main_dttm_col)
+ extras = query_obj.get("extras") or {}
+ expressions.extend(
+ extras[key] for key in ("where", "having") if extras.get(key)
+ )
+ if (
+ query_obj.get("apply_fetch_values_predicate")
+ and self.fetch_values_predicate
+ ):
+ expressions.append(self.fetch_values_predicate)
+ return expressions
+
+ def _get_query_rls_cache_keys(
+ self,
+ query_obj: QueryObjectDict,
+ default_schema: str | None = None,
+ resolve_catalog: Callable[[], str | None] | None = None,
+ ) -> list[str]:
+ """Collect expression-only RLS rules without building or executing SQL.
+
+ Only subquery expressions need table discovery. Reuse the
+ datasource SQL's resolved schema, or resolve it once for physical
datasets.
+ Do not exclude the dataset's own id: an independent expression
subquery is
+ not constrained by the outer query's RLS.
+ """
+ from superset.utils.rls import collect_rls_predicates_for_sql
+
+ if not query_obj or not is_feature_enabled("ALLOW_ADHOC_SUBQUERY"):
+ return []
+ resolve_catalog = resolve_catalog or
cache(self.database.get_default_catalog)
+ extras = query_obj.get("extras") or {}
+ granularity = query_obj.get("granularity")
+ if granularity is not None and granularity not in self.dttm_cols:
+ granularity = self.main_dttm_col
+ template_kwargs = {
+ key: query_obj.get(key)
+ for key in (
+ "columns",
+ "groupby",
+ "metrics",
+ "row_limit",
+ "row_offset",
+ "filter",
+ )
+ }
+ template_kwargs.update(
+ time_column=granularity,
+ time_grain=extras.get("time_grain_sqla"),
+ table_columns=[col.column_name for col in self.columns],
+ )
+ template_kwargs.update(self.template_params_dict)
+ template_processor = self.get_template_processor(**template_kwargs)
+ predicates: set[str] = set()
+ for expression in self._get_query_sql_expressions(
+ query_obj, template_processor, granularity
+ ):
+ expression = template_processor.process_template(expression)
Review Comment:
Correction to my reply above: at ef4a77e10ace36e546c51e740a16f9db1342926e
the collector still does not fully match execution.
Remaining: bare column-name references with no stored expression are still
rendered as templates. `superset/models/helpers.py:4075`
(`add_expression(references.get(value) or value)`) and `:4110`
(`add_expression(col.expression or value)`) pass the name itself to the
template processor; execution never renders a bare column name. With
`ALLOW_ADHOC_SUBQUERY` and `ENABLE_TEMPLATE_PROCESSING` on, a chart on a plain
column named `a{#b`, `a{%b` or `{{ 1/0 }}` (in columns/groupby, a filter `col`,
or orderby) executes successfully, but `get_extra_cache_keys` raises
`TemplateSyntaxError`/`ZeroDivisionError` before the cache lookup. I reproduced
this on both SqlaTable and Query at that head. I had listed helpers.py:4075 as
not affected, which was wrong.
Your two cases do hold at that head, on both datasources: a raw `MAX('{{ x
}}')` collects without raising, and the `{% if false %}`-comment-wrapped
subquery contributes each user's predicate, so two users with different RLS
rules get different cache keys. I checked adhoc columns (including
`expressionType: SQL` and the x-axis), groupby, SQL metrics, orderby by metric
and by adhoc label, filters by adhoc column and by label, WHERE, HAVING and
series-limit metrics.
Regression tests:
`tests/unit_tests/connectors/sqla/virtual_dataset_connections_test.py::test_adhoc_metric_literal_template_cache_request`
and `::test_single_render_subquery_cache_keys_are_user_scoped` pass at
ef4a77e10ace36e546c51e740a16f9db1342926e and fail (16 of 25 with the
stored-expression controls) with the dc56dcc7f9d2a66b952e2c552be45331ca92d39b
helper. No test covers bare column names with template delimiters yet.
Siblings checked:
- superset/models/helpers.py:4075 — not fixed: bare names fall back to
`value` and are rendered (see Remaining).
- superset/models/helpers.py:4110 — not fixed: filter columns without an
expression render the bare name (see Remaining).
- superset/models/helpers.py:4081 — fixed in
ef4a77e10ace36e546c51e740a16f9db1342926e
- superset/models/helpers.py:4198 — fixed in
ef4a77e10ace36e546c51e740a16f9db1342926e
--
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]
