gabotorresruiz commented on code in PR #45431:
URL: https://github.com/apache/superset/pull/45431#discussion_r4362662497
##########
superset/connectors/sqla/models.py:
##########
@@ -2593,26 +2593,86 @@ def has_extra_cache_key_calls(self, query_obj:
QueryObjectDict) -> bool: # noqa
templatable_statements.append(extras["where"])
if "having" in extras:
templatable_statements.append(extras["having"])
- if columns := query_obj.get("columns"):
- calculated_columns: dict[str, Any] = {
- c.column_name: c.expression for c in self.columns if
c.expression
- }
- for column_ in columns:
- if utils.is_adhoc_column(column_):
- templatable_statements.append(column_["sqlExpression"])
- elif isinstance(column_, str) and column_ in
calculated_columns:
- templatable_statements.append(calculated_columns[column_])
- if metrics := query_obj.get("metrics"):
- metrics_by_name: dict[str, Any] = {
- m.metric_name: m.expression for m in self.metrics
- }
- for metric in metrics:
- if utils.is_adhoc_metric(metric) and (
- sql := metric.get("sqlExpression")
- ):
- templatable_statements.append(sql)
- elif isinstance(metric, str) and metric in metrics_by_name:
- templatable_statements.append(metrics_by_name[metric])
+ calculated_columns: dict[str, Any] = {
+ c.column_name: c.expression for c in self.columns if c.expression
+ }
+ calculated_columns_by_verbose_name: dict[str, Any] = {
+ c.verbose_name: c.expression
+ for c in self.columns
+ if c.expression and c.verbose_name
+ }
+ metrics_by_name: dict[str, Any] = {
+ m.metric_name: m.expression for m in self.metrics
+ }
+
+ def column_expression(column_: Any) -> Any:
+ """The templatable expression behind an adhoc or calculated
column."""
+ if utils.is_adhoc_column(column_):
+ return column_["sqlExpression"]
Review Comment:
Confirmed on `5ac3a687a3`. The `groupby` instance was the more valuable of
the two finds, since `get_sqla_query` prefers `groupby` over `columns` whenever
both are set, so that was the shape more charts actually send.
Your `series_columns` reasoning holds too. It only becomes
`series_column_labels` (`helpers.py:5014`), and those labels just pick a subset
of the expressions already built from `groupby`/`columns`
(`helpers.py:5209-5210`), so it never contributes an expression of its own and
the entries it selects from are the ones you just gated. Agreed on keeping the
drift question out of this PR.
##########
superset/connectors/sqla/models.py:
##########
@@ -2593,26 +2593,86 @@ def has_extra_cache_key_calls(self, query_obj:
QueryObjectDict) -> bool: # noqa
templatable_statements.append(extras["where"])
if "having" in extras:
templatable_statements.append(extras["having"])
- if columns := query_obj.get("columns"):
- calculated_columns: dict[str, Any] = {
- c.column_name: c.expression for c in self.columns if
c.expression
- }
- for column_ in columns:
- if utils.is_adhoc_column(column_):
- templatable_statements.append(column_["sqlExpression"])
- elif isinstance(column_, str) and column_ in
calculated_columns:
- templatable_statements.append(calculated_columns[column_])
- if metrics := query_obj.get("metrics"):
- metrics_by_name: dict[str, Any] = {
- m.metric_name: m.expression for m in self.metrics
- }
- for metric in metrics:
- if utils.is_adhoc_metric(metric) and (
- sql := metric.get("sqlExpression")
- ):
- templatable_statements.append(sql)
- elif isinstance(metric, str) and metric in metrics_by_name:
- templatable_statements.append(metrics_by_name[metric])
+ calculated_columns: dict[str, Any] = {
+ c.column_name: c.expression for c in self.columns if c.expression
+ }
+ calculated_columns_by_verbose_name: dict[str, Any] = {
+ c.verbose_name: c.expression
+ for c in self.columns
+ if c.expression and c.verbose_name
+ }
+ metrics_by_name: dict[str, Any] = {
+ m.metric_name: m.expression for m in self.metrics
+ }
+
+ def column_expression(column_: Any) -> Any:
+ """The templatable expression behind an adhoc or calculated
column."""
+ if utils.is_adhoc_column(column_):
+ return column_["sqlExpression"]
+ if isinstance(column_, str):
+ return calculated_columns.get(column_)
+ return None
+
+ def metric_expression(metric: Any) -> Any:
+ """The templatable expression behind an adhoc or saved metric."""
+ if utils.is_adhoc_metric(metric):
+ if sql_expression := metric.get("sqlExpression"):
+ return sql_expression
+ # A SIMPLE adhoc metric has no expression of its own, but
+ # ``adhoc_metric_to_sqla`` wraps its aggregate around the
+ # column's rendered expression, so a macro in a calculated
+ # column reaches the SQL through it.
+ metric_column = metric.get("column") or {}
+ column_name = metric_column.get("column_name")
+ return calculated_columns.get(column_name) if column_name else
None
+ if isinstance(metric, str):
+ return metrics_by_name.get(metric)
+ return None
+
+ def filter_expression(flt: Any) -> Any:
+ """The templatable expression a filter's ``col`` resolves to."""
+ col = flt.get("col")
+ if expression := column_expression(col):
+ return expression
+ if isinstance(col, str):
+ # A filter column that is not a column name is resolved against
+ # the columns' verbose names (right-click "Drill to detail by"
+ # passes those) and then against the saved metrics, for a
+ # filter that becomes a HAVING clause.
+ return calculated_columns_by_verbose_name.get(
+ col
+ ) or metrics_by_name.get(col)
+ return None
+
+ for column_ in query_obj.get("columns") or []:
+ if expression := column_expression(column_):
+ templatable_statements.append(expression)
+ for metric in query_obj.get("metrics") or []:
+ if expression := metric_expression(metric):
+ templatable_statements.append(expression)
+ # ``get_sqla_query`` renders these through the same template processor
as
+ # the columns and metrics above, so a macro in them must trigger the
+ # extraction too, otherwise two users whose rendered SQL differs share
a
+ # cache key:
+ # - an adhoc metric in ``orderby``, or an ``orderby`` entry naming a
+ # saved metric or calculated column not selected by the query
+ # - ``series_limit_metric`` (and its legacy
``timeseries_limit_metric``
+ # alias), via ``_get_series_orderby``
+ # - a filter whose ``col`` resolves to a calculated column or a saved
+ # metric
+ for order_by in query_obj.get("orderby") or []:
+ entry = order_by[0] if isinstance(order_by, (list, tuple)) else
order_by
+ if expression := metric_expression(entry) or
column_expression(entry):
+ templatable_statements.append(expression)
+ for limit_metric in (
+ query_obj.get("series_limit_metric"),
+ query_obj.get("timeseries_limit_metric"),
+ ):
+ if expression := metric_expression(limit_metric):
+ templatable_statements.append(expression)
+ for flt in query_obj.get("filter") or []:
+ if isinstance(flt, dict) and (expression :=
filter_expression(flt)):
+ templatable_statements.append(expression)
Review Comment:
Good catch, and the `main_dttm_col` hop is the better half of this. I
checked the fallback against the renderer for every shape I could reach, and it
matches `get_sqla_query` on all of them: a `granularity` naming a non-temporal
column, one naming a column that is not on the dataset at all, and
`main_dttm_col` unset.
One value where the two guards part company, which I left as a nit on the
block itself.
--
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]
