rusackas commented on code in PR #41184:
URL: https://github.com/apache/superset/pull/41184#discussion_r3562158513
##########
superset/common/query_context_processor.py:
##########
@@ -252,9 +254,54 @@ def get_query_result(self, query_object: QueryObject) ->
QueryResult:
This method delegates to the datasource's get_query_result method,
which handles query execution, normalization, time offsets, and
post-processing.
+
+ When the query requests rollup ``grouping_sets`` but the engine does
not
+ support native ``GROUPING SETS``, fall back to one query per level and
+ concatenate the results with ``GROUPING()``-equivalent markers, so the
+ combined result matches the shape the native path produces (SIP.md,
+ phase 3b). Engines that support it run the single native query.
"""
+ if query_object.grouping_sets and not self._supports_grouping_sets():
+ return self._grouping_sets_fallback(query_object)
return self._qc_datasource.get_query_result(query_object)
+ def _supports_grouping_sets(self) -> bool:
+ engine_spec = getattr(self._qc_datasource, "db_engine_spec", None)
+ return bool(engine_spec and engine_spec.supports_grouping_sets)
+
+ def _grouping_sets_fallback(self, query_object: QueryObject) ->
QueryResult:
+ """
+ Emulate a GROUPING SETS query on engines without native support: run
one
+ query per rollup level and concatenate, tagging each level's rows with
+ the same per-column markers the native path emits.
+ """
+ levels = query_object.grouping_sets
+ all_labels = get_column_names_from_columns(query_object.columns)
+ label_to_column = dict(zip(all_labels, query_object.columns,
strict=False))
Review Comment:
Good catch, fixed. `all_labels` now uses `get_column_name` per column so it
lines up positionally with `query_object.columns`, and the zip is strict so a
mismatch would blow up instead of silently mapping the wrong column.
##########
superset/common/query_context_processor.py:
##########
@@ -252,9 +254,54 @@ def get_query_result(self, query_object: QueryObject) ->
QueryResult:
This method delegates to the datasource's get_query_result method,
which handles query execution, normalization, time offsets, and
post-processing.
+
+ When the query requests rollup ``grouping_sets`` but the engine does
not
+ support native ``GROUPING SETS``, fall back to one query per level and
+ concatenate the results with ``GROUPING()``-equivalent markers, so the
+ combined result matches the shape the native path produces (SIP.md,
+ phase 3b). Engines that support it run the single native query.
"""
+ if query_object.grouping_sets and not self._supports_grouping_sets():
+ return self._grouping_sets_fallback(query_object)
return self._qc_datasource.get_query_result(query_object)
+ def _supports_grouping_sets(self) -> bool:
+ engine_spec = getattr(self._qc_datasource, "db_engine_spec", None)
+ return bool(engine_spec and engine_spec.supports_grouping_sets)
+
+ def _grouping_sets_fallback(self, query_object: QueryObject) ->
QueryResult:
+ """
+ Emulate a GROUPING SETS query on engines without native support: run
one
+ query per rollup level and concatenate, tagging each level's rows with
+ the same per-column markers the native path emits.
+ """
+ levels = query_object.grouping_sets
+ all_labels = get_column_names_from_columns(query_object.columns)
+ label_to_column = dict(zip(all_labels, query_object.columns,
strict=False))
+
+ frames: list[pd.DataFrame] = []
+ result: QueryResult | None = None
+ for level in levels:
+ level_labels = set(level)
+ sub_query = copy.copy(query_object)
+ sub_query.grouping_sets = []
+ sub_query.columns = [
+ label_to_column[label] for label in all_labels if label in
level_labels
+ ]
Review Comment:
Good catch, fixed. `all_labels` is derived the same way the native path
labels adhoc columns, so those groupby columns actually make it into the
fallback subqueries instead of getting silently dropped.
--
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]
