sadpandajoe commented on code in PR #43771:
URL: https://github.com/apache/superset/pull/43771#discussion_r4203089075
##########
superset/mcp_service/chart/schemas.py:
##########
@@ -3867,6 +5073,134 @@ def _normalize_chart_request_input(data: Any) -> Any:
config.pop("viz_type", None)
elif config.get("chart_type") != "table":
config.pop("viz_type", None)
+
+ if config.get("chart_type") == "xy":
+ # Native Timeseries form data uses ``x_axis`` for the semantic
+ # query column, while the typed MCP contract uses the same spelling
+ # for AxisConfig presentation state. Disambiguate before the
+ # discriminated union runs: scalars and native query-column objects
+ # become ``x``; title/format/scale mappings remain ``x_axis``.
+ if "x_axis" in config and config["x_axis"] is not None:
+ native_x_axis = config["x_axis"]
+ is_native_column = not isinstance(native_x_axis, dict) or bool(
+ {
+ "column",
+ "column_name",
+ "columnName",
+ "expressionType",
+ "sqlExpression",
+ }
+ & set(native_x_axis)
+ )
+ if is_native_column:
+ if "x" in config:
+ raise ValueError(
+ "XY config cannot provide both semantic x and
native "
+ "x_axis query columns"
+ )
+ if isinstance(native_x_axis, dict):
+ allowed_x_axis_keys = {
+ "column",
+ "column_name",
+ "columnName",
+ "columnType",
+ "expressionType",
+ "label",
+ "sqlExpression",
+ "timeGrain",
+ }
+ if unknown := set(native_x_axis) - allowed_x_axis_keys:
+ raise ValueError(
+ "Unknown XY native x_axis field(s): "
+ + ", ".join(sorted(unknown))
+ )
+ expression_type = native_x_axis.get("expressionType")
+ if expression_type == "SIMPLE":
+ column = native_x_axis.get("column")
+ if isinstance(column, dict):
+ column = XYNativeMetricColumn.model_validate(
+ column
+ ).column_name
+ native_x_axis = {
+ "name": native_x_axis.get("column_name")
+ or native_x_axis.get("columnName")
+ or column,
+ }
+ elif (
+ expression_type == "SQL"
+ and native_x_axis.get("columnType") == "BASE_AXIS"
+ ):
+ native_x_axis = {
+ "name": native_x_axis.get("sqlExpression"),
Review Comment:
The XY native-axis normalizer accepts `timeGrain` for a `BASE_AXIS` SQL
x-axis (line 5110) but rebuilds the axis as only `name`/`label`, so the grain
is dropped. A native line-chart config with
`x_axis={"expressionType":"SQL","columnType":"BASE_AXIS","sqlExpression":"ds","label":"ds","timeGrain":"P1M"}`
and no panel-level `time_grain` validates, but the generated/updated chart
queries an unbucketed `ds` instead of monthly aggregates. Should the grain be
carried over to `config.time_grain` here, or rejected as unsupported?
##########
superset/mcp_service/chart/chart_utils.py:
##########
@@ -1694,6 +1772,790 @@ def map_bubble_config(config: BubbleChartConfig) ->
Dict[str, Any]:
return form_data
+def map_sunburst_config(config: SunburstChartConfig) -> Dict[str, Any]:
+ """Map typed Sunburst config to the ECharts ``sunburst_v2`` form_data.
+
+ The frontend control panel stores hierarchy levels under ``columns`` and
+ metrics under singular ``metric`` / ``secondary_metric`` keys. Its
+ buildQuery adds primary-metric descending ordering when ``sort_by_metric``
+ is enabled; server-side query builders mirror that transform separately.
+ """
+ form_data: Dict[str, Any] = {
+ "viz_type": "sunburst_v2",
+ "columns": [dimension.name for dimension in config.hierarchy],
+ "metric": create_metric_object(config.metric),
+ "sort_by_metric": config.sort_by_metric,
+ "row_limit": config.row_limit,
+ "show_labels": config.show_labels,
+ "show_labels_threshold": config.show_labels_threshold,
+ "show_total": config.show_total,
+ "show_null_values": config.show_null_values,
+ "label_type": config.label_type,
+ "number_format": config.number_format,
+ "date_format": config.date_format,
+ }
+ if config.secondary_metric is not None:
+ form_data["secondary_metric"] =
create_metric_object(config.secondary_metric)
+ if config.color_scheme is not None:
+ form_data["color_scheme"] = config.color_scheme
+ if config.linear_color_scheme is not None:
+ form_data["linear_color_scheme"] = config.linear_color_scheme
+ if config.time_range is not None:
+ form_data["time_range"] = config.time_range
+ if config.temporal_column is not None:
+ form_data["granularity_sqla"] = config.temporal_column
+ if config.time_grain is not None:
+ form_data["time_grain_sqla"] = config.time_grain
+
+ _copy_sunburst_native_envelope(form_data, config)
+
+ add_currency_format(form_data, config.currency_format)
+ _add_adhoc_filters(form_data, config.filters)
+ return form_data
+
+
+# Sunburst fields with explicit omission/clear semantics. Mapper defaults must
+# not overwrite same-viz state when the typed field was omitted, while explicit
+# clears must also beat the shared preservation registry on cross-viz updates.
+# Required query roles (hierarchy and metric) are deliberately absent: a full
+# replacement always updates them.
+_SUNBURST_UPDATE_FIELD_KEYS: dict[str, str] = {
+ "time_range": "time_range",
+ "time_grain": "time_grain_sqla",
+ "temporal_column": "granularity_sqla",
+ "sort_by_metric": "sort_by_metric",
+ "row_limit": "row_limit",
+ "color_scheme": "color_scheme",
+ "linear_color_scheme": "linear_color_scheme",
+ "show_labels": "show_labels",
+ "show_labels_threshold": "show_labels_threshold",
+ "show_total": "show_total",
+ "show_null_values": "show_null_values",
+ "label_type": "label_type",
+ "number_format": "number_format",
+ "date_format": "date_format",
+ "currency_format": "currency_format",
+ "extra_form_data": "extra_form_data",
+ "url_params": "url_params",
+ "standardized_form_data": "standardizedFormData",
+}
+
+
+# Presentation controls emitted sparsely by chart mappers need three-way update
+# semantics: omitted preserves saved native state, an explicit value replaces
+# it, and explicit ``None``/``False`` clears a truthy saved value when the
mapper
+# has no canonical false/null representation. Query roles are intentionally
+# absent: a replacement config always owns those through the plugin contract.
+# Paths below also cover nested axis/legend models so an omitted nested
property
+# is not mistaken for an explicit clear of the whole control.
+_MODELED_UPDATE_CONTROL_PATHS: dict[str, dict[str, tuple[tuple[str, ...],
...]]] = {
+ "GaugeChartConfig": {
+ key: ((key,),)
+ for key in (
+ "sort_by_metric",
+ "row_limit",
+ "min_val",
+ "max_val",
+ "color_scheme",
+ "font_size",
+ "number_format",
+ "currency_format",
+ "value_formatter",
+ "start_angle",
+ "end_angle",
+ "show_pointer",
+ "animation",
+ "show_axis_tick",
+ "show_split_line",
+ "split_number",
+ "show_progress",
+ "overlap",
+ "round_cap",
+ "intervals",
+ "interval_color_indices",
+ "time_range",
+ "granularity_sqla",
+ )
+ },
+ "PieChartConfig": {
+ "color_scheme": (("color_scheme",),),
+ "show_labels": (("show_labels",),),
+ "show_legend": (("show_legend",),),
+ "legendOrientation": (("legend_orientation",),),
+ "label_type": (("label_type",),),
+ "number_format": (("number_format",),),
+ "date_format": (("date_format",),),
+ "sort_by_metric": (("sort_by_metric",),),
+ "row_limit": (("row_limit",),),
+ "donut": (("donut",),),
+ "show_total": (("show_total",),),
+ "labels_outside": (("labels_outside",),),
+ "outerRadius": (("outer_radius",),),
+ "innerRadius": (("inner_radius",),),
+ "currency_format": (("currency_format",),),
+ },
+ "TableChartConfig": {
+ "order_by_cols": (("sort_by",),),
+ "row_limit": (("row_limit",),),
+ "color_scheme": (("color_scheme",),),
+ "column_config": (("column_config",),),
+ },
+ "XYChartConfig": {
+ "row_limit": (("row_limit",),),
+ "series_limit": (("series_limit",),),
+ "stack": (("stacked",),),
+ "orientation": (("orientation",),),
+ "x_axis_title": (("x_axis", "title"),),
+ "x_axis_format": (("x_axis", "format"),),
+ "y_axis_title": (("y_axis", "title"),),
+ "y_axis_format": (("y_axis", "format"),),
+ "y_axis_scale": (("y_axis", "scale"),),
+ "show_legend": (("legend", "show"),),
+ "legendOrientation": (("legend", "position"), ("legend_orientation",)),
+ "x_axis_time_format": (("x_axis_time_format",),),
+ "show_value": (("show_value",),),
+ "currency_format": (("currency_format",),),
+ "color_scheme": (("color_scheme",),),
+ },
+ "HistogramChartConfig": {
+ "bins": (("bins",),),
+ "normalize": (("normalize",),),
+ "cumulative": (("cumulative",),),
+ "row_limit": (("row_limit",),),
+ },
+ "BoxPlotChartConfig": {
+ "whiskerOptions": (
+ ("whisker_type",),
+ ("percentile_low",),
+ ("percentile_high",),
+ ),
+ "row_limit": (("row_limit",),),
+ "number_format": (("number_format",),),
+ "date_format": (("date_format",),),
+ },
+ "GanttChartConfig": {
+ "tooltip_columns": (("tooltip_columns",),),
+ "tooltip_metrics": (("tooltip_metrics",),),
+ "order_by_cols": (("order_by",),),
+ "row_limit": (("row_limit",),),
+ },
+ "WaterfallChartConfig": {
+ "show_total": (("show_total",),),
+ "show_legend": (("show_legend",),),
+ "increase_label": (("increase_label",),),
+ "decrease_label": (("decrease_label",),),
+ "total_label": (("total_label",),),
+ "x_axis_time_format": (("x_axis_time_format",),),
+ "y_axis_format": (("y_axis_format",),),
+ "currency_format": (("currency_format",),),
+ "row_limit": (("row_limit",),),
+ },
+ "BigNumberChartConfig": {
+ "subheader": (("subheader",),),
+ "y_axis_format": (("y_axis_format",),),
+ "time_format": (("time_format",),),
+ "currency_format": (("currency_format",),),
+ "color_scheme": (("color_scheme",),),
+ "start_y_axis_at_zero": (("start_y_axis_at_zero",),),
+ "compare_lag": (("compare_lag",),),
+ "aggregation": (("aggregation",),),
+ },
+ "HandlebarsChartConfig": {
+ "row_limit": (("row_limit",),),
+ "order_desc": (("order_desc",),),
+ "styleTemplate": (("style_template",),),
+ },
+ "PivotTableChartConfig": {
+ "aggregateFunction": (("aggregate_function",),),
+ "rowTotals": (("show_row_totals",),),
+ "colTotals": (("show_column_totals",),),
+ "transposePivot": (("transpose",),),
+ "combineMetric": (("combine_metric",),),
+ "valueFormat": (("value_format",),),
+ "date_format": (("date_format",),),
+ "currency_format": (("currency_format",),),
+ "row_limit": (("row_limit",),),
+ },
+ "InteractivePivotChartConfig": {
+ "order_desc": (("sort_descending",),),
+ "row_limit": (("row_limit",),),
+ "rowGroupCounts": (("show_row_group_counts",),),
+ "rowTotals": (("show_row_totals",),),
+ "colTotals": (("show_column_totals",),),
+ "colSubTotals": (("show_column_subtotals",),),
+ "valueFormat": (("value_format",),),
+ "date_format": (("date_format",),),
+ "currency_format": (("currency_format",),),
+ "colOrder": (("column_sort",),),
+ "allow_render_html": (("allow_render_html",),),
+ "expand_pivot_groups": (("expand_pivot_groups",),),
+ "time_compare": (("comparison_period",),),
+ "comparison_type": (("comparison_type",),),
+ },
+ "MixedTimeseriesChartConfig": {
+ "seriesType": (("primary_kind",),),
+ "area": (("primary_kind",),),
+ "seriesTypeB": (("secondary_kind",),),
+ "areaB": (("secondary_kind",),),
+ "show_legend": (("show_legend",),),
+ "legendOrientation": (("legend_orientation",),),
+ "show_value": (("show_value",),),
+ "color_scheme": (("color_scheme",),),
+ "currency_format": (("currency_format",),),
+ "currency_format_secondary": (("currency_format_secondary",),),
+ "xAxisTitle": (("x_axis", "title"),),
+ "x_axis_time_format": (("x_axis", "format"),),
+ "yAxisTitle": (("y_axis", "title"),),
+ "y_axis_format": (("y_axis", "format"),),
+ "logAxis": (("y_axis", "scale"),),
+ "yAxisTitleSecondary": (("y_axis_secondary", "title"),),
+ "y_axis_format_secondary": (("y_axis_secondary", "format"),),
+ "logAxisSecondary": (("y_axis_secondary", "scale"),),
+ "row_limit": (("row_limit",),),
+ },
+}
+
+
+def _model_path_was_set(config: Any, path: tuple[str, ...]) -> bool:
+ """Return whether every component of a Pydantic model path was supplied."""
+ current = config
+ for field_name in path:
+ if field_name not in getattr(current, "model_fields_set", set()):
+ return False
+ current = getattr(current, field_name, None)
+ if current is None:
+ # An explicit null parent clears all of its mapped descendants.
+ return True
+ return True
+
+
+def _apply_modeled_update_semantics(
+ existing_form_data: Mapping[str, Any],
+ new_form_data: Dict[str, Any],
+ config: Any,
+) -> set[str]:
+ """Preserve truly omitted modeled controls and return explicit clears."""
+ explicit_clears: set[str] = set()
+ controls = _MODELED_UPDATE_CONTROL_PATHS.get(type(config).__name__, {})
+ for form_key, paths in controls.items():
+ if any(_model_path_was_set(config, path) for path in paths):
+ if form_key not in new_form_data:
+ explicit_clears.add(form_key)
+ continue
+ if form_key in existing_form_data:
+ new_form_data[form_key] = existing_form_data[form_key]
+ else:
+ new_form_data.pop(form_key, None)
+ return explicit_clears
+
+
+_TEMPORAL_FORM_DATA_KEYS = frozenset(
+ {
+ "granularity",
+ "granularity_sqla",
+ "since",
+ "time_grain",
+ "time_grain_sqla",
+ "time_range",
+ "until",
+ }
+)
+
+
+def _is_temporal_filter(filter_: Any) -> bool:
+ """Return whether a native, adhoc, or legacy filter carries a time
range."""
+ return isinstance(filter_, dict) and (
+ filter_.get("operator") == FilterOperator.TEMPORAL_RANGE.value
+ or filter_.get("op") == FilterOperator.TEMPORAL_RANGE.value
+ or filter_.get("col") in {"__time_col", "__time_grain", "__time_range"}
+ )
+
+
+def _without_temporal_filters(value: Any) -> Any:
+ """Copy a filter list without temporal predicates, preserving other
shapes."""
+ if not isinstance(value, list):
+ return value
+ return [filter_ for filter_ in value if not _is_temporal_filter(filter_)]
+
+
+def _scrub_temporal_form_data(form_data: Mapping[str, Any]) -> Dict[str, Any]:
+ """Remove every source capable of reconstructing explicitly cleared time
state."""
+ scrubbed = dict(form_data)
+ for key in _TEMPORAL_FORM_DATA_KEYS:
+ scrubbed.pop(key, None)
+ scrubbed.pop(MCP_DASHBOARD_TIME_FILTER_SUBJECT, None)
+
+ for key in ("adhoc_filters", "extra_filters", "filters"):
+ if key in scrubbed:
+ scrubbed[key] = _without_temporal_filters(scrubbed[key])
+
+ extra_form_data = scrubbed.get("extra_form_data")
+ if isinstance(extra_form_data, dict):
+ cleaned_extra = dict(extra_form_data)
+ for key in _TEMPORAL_FORM_DATA_KEYS:
+ cleaned_extra.pop(key, None)
+ for key in ("adhoc_filters", "extra_filters", "filters"):
+ if key in cleaned_extra:
+ cleaned_extra[key] =
_without_temporal_filters(cleaned_extra[key])
+ scrubbed["extra_form_data"] = cleaned_extra
+ elif extra_form_data is None:
+ scrubbed.pop("extra_form_data", None)
+ return scrubbed
+
+
+# One bounded registry owns state that may survive a form-data replacement.
+# Query roles and plugin-specific controls are deliberately absent. This keeps
+# cross-viz transitions preview/save-safe without chart-by-chart allowlists
that
+# can drift as new plugins are registered.
+FORM_DATA_UPDATE_PRESERVE_KEYS: dict[str, frozenset[str]] = {
+ "envelope": frozenset(
+ {
+ "dashboardId",
+ "dashboards",
+ "datasource",
+ "extra_form_data",
+ "slice_id",
+ "slice_name",
+ "standardizedFormData",
+ "url_params",
+ }
+ ),
+ "presentation": frozenset(
+ {
+ "color_scheme",
+ "currency_format",
+ "date_format",
+ "legendOrientation",
+ "linear_color_scheme",
+ "number_format",
+ "show_legend",
+ }
+ ),
+ "filters": frozenset({"adhoc_filters", "extra_filters", "filters"}),
+ "time": frozenset(
+ {
+ "granularity_sqla",
+ "since",
+ "time_grain_sqla",
+ "time_range",
+ "until",
+ }
+ ),
+}
+_FORM_DATA_UPDATE_PRESERVE_KEYS = frozenset().union(
+ *FORM_DATA_UPDATE_PRESERVE_KEYS.values()
+)
+
+
+_SAVED_PREDICATE_FORM_DATA_KEYS = frozenset(
+ {"adhoc_filters", "extra_filters", "filters", "having", "where"}
+)
+
+
+def _merge_preserved_adhoc_filters(
+ existing_form_data: Mapping[str, Any],
+ new_form_data: Mapping[str, Any],
+ *,
+ drop_existing_temporal: bool,
+) -> list[Any] | None:
+ """Merge omitted structured filters while removing stale time bindings."""
+ previous = existing_form_data.get("adhoc_filters")
+ generated = new_form_data.get("adhoc_filters")
+ if not isinstance(previous, list):
+ return list(generated) if isinstance(generated, list) else None
+
+ previous_binding =
existing_form_data.get(MCP_DASHBOARD_TIME_FILTER_SUBJECT)
+ new_binding = new_form_data.get(MCP_DASHBOARD_TIME_FILTER_SUBJECT)
+ merged: list[Any] = []
+ for filter_ in previous:
+ is_temporal = (
+ isinstance(filter_, dict)
+ and filter_.get("operator") == FilterOperator.TEMPORAL_RANGE.value
+ )
+ stale_generated_binding = (
+ is_temporal
+ and previous_binding
+ and previous_binding != new_binding
+ and filter_.get("subject") == previous_binding
+ and filter_.get("comparator") == NO_TIME_RANGE
+ )
+ if (drop_existing_temporal and is_temporal) or stale_generated_binding:
+ continue
+ merged.append(filter_)
+
+ for filter_ in generated if isinstance(generated, list) else []:
+ if isinstance(filter_, dict):
+ same_filter = any(
+ isinstance(previous_filter, dict)
+ and previous_filter.get("clause") == filter_.get("clause")
+ and previous_filter.get("expressionType")
+ == filter_.get("expressionType")
+ and previous_filter.get("subject") == filter_.get("subject")
+ and previous_filter.get("operator") == filter_.get("operator")
+ for previous_filter in merged
+ )
+ if same_filter:
+ continue
+ elif filter_ in merged:
+ continue
+ merged.append(filter_)
+ return merged
+
+
+def _merge_allowlisted_form_data(
+ existing_form_data: Mapping[str, Any],
+ new_form_data: Mapping[str, Any],
+) -> Dict[str, Any]:
+ """Start from mapped target state and add only registry-approved
omissions."""
+ merged = dict(new_form_data)
+ for key in _FORM_DATA_UPDATE_PRESERVE_KEYS:
+ if key not in merged and key in existing_form_data:
+ merged[key] = existing_form_data[key]
+ return merged
+
+
+def merge_form_data_for_update(
+ existing_form_data: Dict[str, Any],
+ new_form_data: Dict[str, Any],
+ config: Any,
+ *,
+ dataset_rebind: bool = False,
+) -> Dict[str, Any]:
+ """Merge mapped updates without leaking query roles across visualizations.
+
+ Same-viz updates retain native controls outside the simplified MCP schema
by
+ starting from saved form data. Cross-viz updates remain bounded by the
+ shared preservation registry. Explicit clears are applied last.
+
+ A dataset rebind prunes every dataset-bound role from the saved state and
+ then merges as a same-dataset update, unless the owning plugin declares a
+ strict rebind contract (``strict_dataset_rebind``), in which case its
+ ``merge_update_form_data`` hook receives ``dataset_rebind=True``. Plugins
+ that declare ``owns_update_merge`` merge same-viz updates themselves;
+ every other update takes the shared overlay and then the plugin's
+ ``finalize_update_form_data`` hook.
+ """
+ from superset.mcp_service.chart.registry import plugin_for_viz_type
+
+ plugin = plugin_for_viz_type(new_form_data.get("viz_type"))
+ if dataset_rebind and not (plugin is not None and
plugin.strict_dataset_rebind):
+ existing_form_data = scrub_dataset_bound_form_data(
+ existing_form_data,
+ target_viz_type=new_form_data.get("viz_type"),
+ )
+ dataset_rebind = False
+
+ same_viz = existing_form_data.get("viz_type") ==
new_form_data.get("viz_type")
+ if same_viz and plugin is not None and (dataset_rebind or
plugin.owns_update_merge):
+ plugin_merged = plugin.merge_update_form_data(
+ existing_form_data,
+ new_form_data,
+ config,
+ dataset_rebind=dataset_rebind,
+ )
+ if plugin_merged is not None:
+ return plugin_merged
+ if dataset_rebind:
+ # A strict rebind never inherits saved state the plugin did not merge.
+ return dict(new_form_data)
+
+ merged = overlay_update_form_data(existing_form_data, new_form_data,
config)
+ if plugin is not None:
+ merged = plugin.finalize_update_form_data(
+ existing_form_data, new_form_data, merged, config
+ )
+ return merged
+
+
+def overlay_update_form_data(
+ existing_form_data: Dict[str, Any],
+ new_form_data: Dict[str, Any],
+ config: Any,
+) -> Dict[str, Any]:
+ """Overlay a same-dataset update on the saved state with shared
semantics."""
+ same_viz = existing_form_data.get("viz_type") ==
new_form_data.get("viz_type")
+ explicit_control_clears = (
+ _apply_modeled_update_semantics(existing_form_data, new_form_data,
config)
+ if same_viz
+ else set()
+ )
+ if same_viz:
+ from superset.mcp_service.chart.registry import (
+ query_role_keys_for_viz_type,
+ )
+
+ # Strip every target-owned query role first, then overlay the mapper's
+ # complete replacement. This removes mutually exclusive aliases (for
+ # example Pie ``metrics`` vs ``metric`` and raw vs aggregate table
+ # roles) without dropping unmodeled native presentation controls.
+ query_role_keys = query_role_keys_for_viz_type(
+ str(new_form_data.get("viz_type"))
+ )
+ merged = {
+ key: value
+ for key, value in existing_form_data.items()
+ if key not in query_role_keys
Review Comment:
On a same-viz update every key in the plugin's `query_role_keys` is dropped
from the saved form data before the mapper output is overlaid, and `groupby`
for XY charts is not one of the modeled controls that gets restored. A saved
line chart grouped by `region` that receives `update_chart` with the same
`x`/`y` and `stacked: true` but no `group_by` will have its regional series
collapsed into one aggregate series. Is dropping the saved grouping on omission
intended (with only an explicit `group_by: []` meant to clear it)? If so it
seems worth calling out in UPDATING.md; otherwise should `groupby` be preserved
when `group_by` is unset?
##########
superset/common/form_data_query_context.py:
##########
@@ -288,71 +427,1309 @@ def _pie_contribution_post_processing(metrics:
list[Any]) -> list[dict[str, Any]
]
-def build_query_context_from_form_data(
- form_data: dict[str, Any],
- datasource: dict[str, Any],
- viz_type: str | None = None,
+def _as_list(value: Any) -> list[Any]:
+ """Return the frontend ``ensureIsArray`` representation of a value."""
+ if value is None:
+ return []
+ return list(value) if isinstance(value, (list, tuple)) else [value]
+
+
+def _label(value: Any, *, metric: bool = False) -> str:
+ """Resolve a frontend-compatible query-field label."""
+ try:
+ return get_metric_name(value) if metric else get_column_name(value)
+ except (AttributeError, KeyError, TypeError, ValueError):
+ if isinstance(value, Mapping):
+ return str(
+ value.get("label")
+ or value.get("column_name")
+ or value.get("sqlExpression")
+ or value
+ )
+ return str(value)
+
+
+def _deduplicate_fields(values: list[Any], *, metric: bool = False) ->
list[Any]:
+ """Deduplicate query fields by their frontend-visible label."""
+ result: list[Any] = []
+ labels: set[str] = set()
+ for value in values:
+ if value is None or value == "":
+ continue
+ label = _label(value, metric=metric)
+ if label in labels:
+ continue
+ labels.add(label)
+ result.append(value)
+ return result
+
+
+def retain_mixed_timeseries_secondary_form_data(
+ form_data: Mapping[str, Any],
) -> dict[str, Any]:
- """
- Build a query-context payload (the JSON shape
``ChartDataQueryContextSchema``
- loads) from a chart's form data and datasource reference.
+ """Mirror ``retainFormDataSuffix(formData, '_b')`` exactly.
- :param form_data: The chart's saved ``params`` parsed to a dict.
- :param datasource: ``{"id": <int>, "type": "table"}`` datasource reference.
- :param viz_type: The chart's viz type, used for viz-specific handling.
- :returns: A single-query query-context dict.
+ Suffixed values are installed first, including falsey values, and shared
+ unsuffixed controls fill only keys that query B did not explicitly set.
"""
- columns, metrics = _columns_and_metrics(form_data, viz_type)
-
- # SIMPLE adhoc filters (+ legacy top-level ``filters``) become query
filters;
- # free-form SQL predicates go into ``extras``. Only ``WHERE``-clause SIMPLE
- # filters are applied (matching the chart), so the export never filters on
a
- # ``HAVING`` clause the chart itself ignores.
- filters = adhoc_filters_to_query_filters(
- form_data.get("adhoc_filters", []), where_only=True
- )
- for flt in form_data.get("filters") or []:
- if isinstance(flt, dict) and flt.get("col") is not None:
- filters.append(flt)
+ secondary: dict[str, Any] = {}
+ for key, value in form_data.items():
+ if key.endswith("_b"):
+ secondary[key[:-2]] = value
+ for key, value in form_data.items():
+ if not key.endswith("_b") and key not in secondary:
+ secondary[key] = value
+ secondary_filter_keys = {
+ "adhoc_filters": "adhoc_filters_b",
+ "extra_filters": "extra_filters_b",
+ "filters": "filters_b",
+ "having": "having_b",
+ "where": "where_b",
+ }
+ if any(suffixed in form_data for suffixed in
secondary_filter_keys.values()):
+ # The frontend exposes adhoc_filters_b, while saved/server payloads can
+ # carry equivalent legacy aliases. Treat the family atomically: an
+ # explicit clear in any B alias must not be repopulated by query A's
+ # differently named filter representation.
+ for primary, suffixed in secondary_filter_keys.items():
+ if suffixed not in form_data:
+ secondary.pop(primary, None)
+ return secondary
- extras = freeform_where_having(form_data)
- if form_data.get("time_grain_sqla"):
- extras["time_grain_sqla"] = form_data["time_grain_sqla"]
- # Prefer the modern ``time_range``; fall back to the legacy
``since``/``until``
- # pair (older charts store the range that way) before defaulting to no
filter.
- time_range = form_data.get("time_range")
- if not time_range and (form_data.get("since") or form_data.get("until")):
- time_range = f"{form_data.get('since') or ''} :
{form_data.get('until') or ''}"
- time_range = time_range or "No filter"
+def _base_query_object( # noqa: C901
+ form_data: dict[str, Any],
+ *,
+ row_limit: int | None,
+ order_desc: bool | None,
+ filters_prepared: bool,
+) -> dict[str, Any]:
+ """Build the shared frontend-equivalent portion of a QueryObject."""
+ columns, metrics, orderby = query_fields_from_form_data(form_data)
query: dict[str, Any] = {
"columns": columns,
"metrics": metrics,
- "orderby": orderby_from_form_data(form_data, metrics, viz_type),
- "filters": filters,
- "time_range": time_range,
}
+ if orderby:
+ query["orderby"] = orderby
+
+ if filters_prepared:
+ query["filters"] = list(form_data.get("filters") or [])
+ for clause in ("where", "having"):
+ if form_data.get(clause):
+ query[clause] = form_data[clause]
+ if form_data.get("extras"):
+ query["extras"] = dict(form_data["extras"])
+ else:
+ filters = adhoc_filters_to_query_filters(
+ form_data.get("adhoc_filters", []), where_only=True
+ )
+ filters.extend(
+ filter_
+ for filter_ in form_data.get("filters") or []
+ if isinstance(filter_, dict) and filter_.get("col") is not None
+ )
+ query["filters"] = filters
+ if extras := freeform_where_having(form_data):
+ query["extras"] = extras
+
+ extras = dict(query.get("extras") or {})
+ if form_data.get("time_grain_sqla") is not None:
+ extras["time_grain_sqla"] = form_data["time_grain_sqla"]
if extras:
query["extras"] = extras
- if viz_type == "pie" and (
- post_processing := _pie_contribution_post_processing(metrics)
+
+ effective_limit = row_limit if row_limit is not None else
form_data.get("row_limit")
+ if effective_limit is not None:
+ query["row_limit"] = effective_limit
+ if form_data.get("row_offset") is not None:
+ query["row_offset"] = form_data["row_offset"]
+ if order_desc is not None:
+ query["order_desc"] = order_desc
+ elif "order_desc" in form_data and form_data["order_desc"] is not None:
+ query["order_desc"] = form_data["order_desc"]
+
+ time_range = form_data.get("time_range")
+ if not time_range and (form_data.get("since") or form_data.get("until")):
+ time_range = f"{form_data.get('since') or ''} :
{form_data.get('until') or ''}"
+ if time_range:
+ query["time_range"] = time_range
+ for key in ("since", "until", "annotation_layers", "url_params",
"custom_params"):
+ if form_data.get(key) is not None:
+ query[key] = form_data[key]
+
+ granularity = form_data.get("granularity") or
form_data.get("granularity_sqla")
+ if granularity:
+ query["granularity"] = granularity
+ series_limit = form_data.get("series_limit", form_data.get("limit"))
+ if series_limit is not None:
+ query["series_limit"] = series_limit
+ series_limit_metric = form_data.get("series_limit_metric")
+ if series_limit_metric is None:
+ series_limit_metric = form_data.get("timeseries_limit_metric")
+ if series_limit_metric is not None:
+ query["series_limit_metric"] = series_limit_metric
+ if form_data.get("group_others_when_limit_reached") is not None:
+ query["group_others_when_limit_reached"] = form_data[
+ "group_others_when_limit_reached"
+ ]
+ return query
+
+
+def _temporalized_columns(form_data: dict[str, Any], columns: list[Any]) ->
list[Any]:
+ """Apply the pivot BASE_AXIS temporal-column contract."""
+ time_grain = form_data.get("time_grain_sqla")
+ temporal_lookup = form_data.get("temporal_columns_lookup") or {}
+ result: list[Any] = []
+ for column in columns:
+ if (
+ isinstance(column, str)
+ and time_grain
+ and (
+ temporal_lookup.get(column)
+ or form_data.get("granularity_sqla") == column
+ )
+ ):
+ result.append(
+ {
+ "timeGrain": time_grain,
+ "columnType": "BASE_AXIS",
+ "sqlExpression": column,
+ "label": column,
+ "expressionType": "SQL",
+ }
+ )
+ else:
+ result.append(column)
+ return result
+
+
+def _box_temporalized_columns(
+ form_data: dict[str, Any], columns: list[Any]
+) -> list[Any]:
+ """Convert only physical columns confirmed temporal by Box Plot
metadata."""
+ time_grain = form_data.get("time_grain_sqla")
+ temporal_lookup = form_data.get("temporal_columns_lookup")
+ if not time_grain or not isinstance(temporal_lookup, Mapping):
+ return columns
+ return [
+ {
+ "timeGrain": time_grain,
+ "columnType": "BASE_AXIS",
+ "sqlExpression": column,
+ "label": column,
+ "expressionType": "SQL",
+ }
+ if isinstance(column, str) and temporal_lookup.get(column) is True
+ else column
+ for column in columns
+ ]
+
+
+def _table_temporalized_columns(
+ form_data: dict[str, Any], columns: list[Any]
+) -> list[Any]:
+ """Promote the first temporal table group-by to the frontend BASE_AXIS.
+
+ Table's builder treats only physical columns named in
+ ``temporal_columns_lookup`` as temporal and moves the first match to the
+ front. Later temporal dimensions remain ordinary group-bys.
+ """
+ time_grain = form_data.get("time_grain_sqla")
+ temporal_lookup = form_data.get("temporal_columns_lookup") or {}
+ if not time_grain or not isinstance(temporal_lookup, Mapping):
+ return columns
+
+ temporal_column: dict[str, Any] | None = None
+ remaining: list[Any] = []
+ for column in columns:
+ if (
+ temporal_column is None
+ and isinstance(column, str)
+ and temporal_lookup.get(column)
+ ):
+ temporal_column = {
+ "timeGrain": time_grain,
+ "columnType": "BASE_AXIS",
+ "sqlExpression": column,
+ "label": column,
+ "expressionType": "SQL",
+ "isColumnReference": True,
+ }
+ else:
+ remaining.append(column)
+ return [temporal_column, *remaining] if temporal_column else columns
+
+
+def _histogram_query(form_data: dict[str, Any], query: dict[str, Any]) -> None:
+ groupby = _as_list(form_data.get("groupby"))
+ column = form_data.get("column")
+ query["columns"] = [*groupby, *([column] if column is not None else [])]
+ query["post_processing"] = [
+ {
+ "operation": "histogram",
+ "options": {
+ "column": _label(column),
+ "groupby": [_label(value) for value in groupby],
+ "bins": int(form_data.get("bins", 5)),
+ "cumulative": form_data.get("cumulative", False),
+ "normalize": form_data.get("normalize", False),
+ },
+ }
+ ]
+ if any(
+ isinstance(filter_, dict) and filter_.get("clause") == "HAVING"
+ for filter_ in form_data.get("adhoc_filters") or []
+ ):
+ query["metrics"] = [
+ {
+ "expressionType": "SQL",
+ "sqlExpression": "COUNT(*)",
+ "label": "COUNT(*)",
+ }
+ ]
+ else:
+ query["metrics"] = []
+
+
+def _box_plot_query(form_data: dict[str, Any], query: dict[str, Any]) -> None:
+ distributed = _as_list(form_data.get("columns"))
+ if not distributed and form_data.get("granularity_sqla"):
+ distributed = [form_data["granularity_sqla"]]
+ groupby = _as_list(form_data.get("groupby"))
+ query["columns"] = [*_box_temporalized_columns(form_data, distributed),
*groupby]
+ query["series_columns"] = groupby
+ whisker = form_data.get("whiskerOptions")
+ if not whisker:
+ query["post_processing"] = []
+ return
+ whisker_type = "tukey"
+ percentiles: list[int] | None = None
+ if whisker == "Min/max (no outliers)":
+ whisker_type = "min/max"
+ elif isinstance(whisker, str) and whisker.endswith(" percentiles"):
+ low, high = whisker.removesuffix(" percentiles").split("/", 1)
+ whisker_type = "percentile"
+ percentiles = [int(low), int(high)]
+ query["post_processing"] = [
+ {
+ "operation": "boxplot",
+ "options": {
+ "whisker_type": whisker_type,
+ "percentiles": percentiles,
+ "groupby": [_label(value) for value in groupby],
+ "metrics": [_label(value, metric=True) for value in
query["metrics"]],
+ },
+ }
+ ]
+
+
+_PIVOT_ADDITIVE_AGGREGATES = frozenset({"SUM", "COUNT", "MIN", "MAX"})
+
+
+def _all_metrics_additive(metrics: list[Any]) -> bool:
+ """Mirror Pivot's conservative additive-metric fast-path."""
+ return bool(metrics) and all(
+ isinstance(metric, Mapping)
+ and metric.get("expressionType") == "SIMPLE"
+ and metric.get("aggregate") in _PIVOT_ADDITIVE_AGGREGATES
+ for metric in metrics
+ )
+
+
+def _pivot_grouping_sets(
+ form_data: dict[str, Any], rows: list[Any], columns: list[Any]
+) -> list[list[str]]:
+ """Enumerate the rollup levels requested by Pivot's frontend builder."""
+ row_prefixes = [[], *(rows[: index + 1] for index in range(len(rows)))]
+ column_prefixes = [
+ [],
+ *(columns[: index + 1] for index in range(len(columns))),
+ ]
+ show_values_as = form_data.get("showValuesAs")
+ needs_rows_collapsed = show_values_as in {"percent_col", "percent_total"}
+ needs_columns_collapsed = show_values_as in {"percent_row",
"percent_total"}
+
+ def row_prefix_needed(prefix: list[Any]) -> bool:
+ if len(prefix) == len(rows):
+ return True
+ if not prefix:
+ return bool(form_data.get("colTotals")) or needs_rows_collapsed
+ return bool(form_data.get("rowSubTotals"))
+
+ def column_prefix_needed(prefix: list[Any]) -> bool:
+ if len(prefix) == len(columns):
+ return True
+ if not prefix:
+ return bool(form_data.get("rowTotals")) or needs_columns_collapsed
+ return bool(form_data.get("colSubTotals"))
+
+ levels = [
+ (row_prefix, column_prefix)
+ for row_prefix in row_prefixes
+ if row_prefix_needed(row_prefix)
+ for column_prefix in column_prefixes
+ if column_prefix_needed(column_prefix)
+ ]
+ if form_data.get("combineMetric"):
+ metrics_layout = form_data.get("metricsLayout")
+
+ def forced_denominator(level: tuple[list[Any], list[Any]]) -> bool:
+ row_prefix, column_prefix = level
+ return (needs_rows_collapsed and not row_prefix) or (
+ needs_columns_collapsed and not column_prefix
+ )
+
+ if metrics_layout == "ROWS":
+ levels = [
+ level
+ for level in levels
+ if len(level[0]) == len(rows) or forced_denominator(level)
+ ]
+ else:
+ levels = [
+ level
+ for level in levels
+ if len(level[1]) == len(columns) or forced_denominator(level)
+ ]
+
+ return [
+ [_label(value) for value in _deduplicate_fields([*row_prefix,
*column_prefix])]
+ for row_prefix, column_prefix in levels
+ ]
+
+
+def _pivot_query(form_data: dict[str, Any], query: dict[str, Any]) -> None:
+ rows = _as_list(form_data.get("groupbyRows"))
+ columns = _as_list(form_data.get("groupbyColumns"))
+ if form_data.get("transposePivot"):
+ rows, columns = columns, rows
+ query["columns"] = _temporalized_columns(
+ form_data, _deduplicate_fields([*rows, *columns])
+ )
+ metric = query.get("series_limit_metric") or next(
+ iter(query.get("metrics") or []), None
+ )
+ query["orderby"] = (
+ [[metric, not bool(query.get("order_desc", True))]]
+ if metric is not None
+ else []
+ )
+ if not _all_metrics_additive(query.get("metrics") or []):
+ query["grouping_sets"] = _pivot_grouping_sets(form_data, rows, columns)
+
+
+def _waterfall_query(form_data: dict[str, Any], query: dict[str, Any]) -> None:
+ x_axis = form_data.get("x_axis") or form_data.get("granularity_sqla")
+ columns = [*_as_list(x_axis), *_as_list(form_data.get("groupby"))]
+ query["columns"] = _deduplicate_fields(columns)
+ query["orderby"] = [[column, True] for column in query["columns"]]
+
+
+def _gantt_query(form_data: dict[str, Any], query: dict[str, Any]) -> None:
+ groupby = _as_list(form_data.get("series"))
+ orderby = query_fields_from_form_data(form_data)[2]
+ columns = [
+ form_data.get("start_time"),
+ form_data.get("end_time"),
+ form_data.get("y_axis"),
+ *groupby,
+ *_as_list(form_data.get("tooltip_columns")),
+ *(entry[0] for entry in orderby if entry),
+ ]
+ query["columns"] = _deduplicate_fields(columns)
+ query["metrics"] = _as_list(form_data.get("tooltip_metrics"))
+ query["orderby"] = orderby
+ query["series_columns"] = groupby
+
+
+def _normalize_query_orderby(query: dict[str, Any]) -> None:
+ """Mirror ``normalizeOrderBy`` while retaining limit-direction controls."""
+ orderby = query.get("orderby")
+ if (
+ isinstance(orderby, list)
+ and orderby
+ and isinstance(orderby[0], (list, tuple))
+ and len(orderby[0]) == 2
+ and orderby[0][0]
+ and isinstance(orderby[0][1], bool)
+ ):
+ return
+ metric = (
+ query.get("series_limit_metric")
+ or query.get("legacy_order_by")
+ or next(iter(query.get("metrics") or []), None)
+ )
+ if metric is None:
+ query.pop("orderby", None)
+ return
+ query["orderby"] = [[metric, not bool(query.get("order_desc", True))]]
+
+
+_TIME_COMPARISON_TYPES = frozenset({"values", "difference", "percentage",
"ratio"})
+
+
+def _metric_offset_map(
+ form_data: dict[str, Any],
+ metric_labels: list[str],
+ offsets: list[Any] | None = None,
+) -> dict[str, str]:
+ """Return the frontend time-comparison metric label map."""
+ if form_data.get("comparison_type") not in _TIME_COMPARISON_TYPES:
+ return {}
+ return {
+ f"{metric}__{offset}": metric
+ for metric in metric_labels
+ for offset in (
+ offsets if offsets is not None else
_as_list(form_data.get("time_compare"))
+ )
+ }
+
+
+def _table_time_offsets(form_data: dict[str, Any]) -> list[Any]:
+ """Resolve Table custom/inherited shifts like its frontend query
adapter."""
+ raw_offsets = _as_list(form_data.get("time_compare"))
+ offsets = [offset for offset in raw_offsets if offset not in {"custom",
"inherit"}]
+ if "custom" in raw_offsets and form_data.get("start_date_offset") is not
None:
+ offsets.append(form_data["start_date_offset"])
+ extra_form_data = form_data.get("extra_form_data")
+ if isinstance(extra_form_data, Mapping) and
extra_form_data.get("time_compare"):
+ inherited = extra_form_data["time_compare"]
+ if inherited not in offsets:
+ offsets = [inherited]
+ return offsets
+
+
+def _x_axis_column(form_data: Mapping[str, Any]) -> Any | None:
+ """Return a supported x-axis column, excluding legacy granularity.
+
+ ``column_name`` mappings are retained for old server/native payloads. Big
+ Number uses the stricter frontend predicate below.
+ """
+ x_axis = form_data.get("x_axis")
+ if isinstance(x_axis, str):
+ return x_axis if x_axis else None
+ if isinstance(x_axis, Mapping):
+ if isinstance(column_name := x_axis.get("column_name"), str) and
column_name:
+ return column_name
+ # Frontend SQL adhoc columns remain objects in the QueryObject.
+ return x_axis if x_axis else None
+ return None
+
+
+def _frontend_x_axis_column(form_data: Mapping[str, Any]) -> Any | None:
+ """Mirror ``isQueryFormColumn`` for physical and SQL adhoc columns."""
+ x_axis = form_data.get("x_axis")
+ if isinstance(x_axis, str):
+ return x_axis if x_axis else None
+ if (
+ isinstance(x_axis, Mapping)
+ and "sqlExpression" in x_axis
+ and "label" in x_axis
+ and x_axis.get("expressionType") in {None, "SQL"}
+ ):
+ return x_axis
+ return None
+
+
+def normalize_time_column(
+ form_data: Mapping[str, Any], query: dict[str, Any]
+) -> dict[str, Any]:
+ """Apply the final shared frontend ``normalizeTimeColumn`` mutator."""
+ x_axis = _frontend_x_axis_column(form_data)
+ columns = query.get("columns")
+ if x_axis is None or not isinstance(columns, list):
+ return query
+
+ axis_index: int | None = None
+ for index, column in enumerate(columns):
+ if isinstance(x_axis, str) and isinstance(column, str) and column ==
x_axis:
+ axis_index = index
+ break
+ if (
+ isinstance(x_axis, Mapping)
+ and isinstance(column, Mapping)
+ and column.get("sqlExpression") == x_axis.get("sqlExpression")
+ ):
+ axis_index = index
+ break
+ if axis_index is None:
+ return query
+
+ normalized = dict(query)
+ normalized_columns = list(columns)
+ grain = (query.get("extras") or {}).get("time_grain_sqla")
+ if isinstance(columns[axis_index], Mapping):
+ normalized_axis = {
+ "columnType": "BASE_AXIS",
+ **({"timeGrain": grain} if grain is not None else {}),
+ **columns[axis_index],
+ }
+ else:
+ normalized_axis = {
+ "columnType": "BASE_AXIS",
+ "sqlExpression": x_axis,
+ "label": x_axis,
+ "expressionType": "SQL",
+ "isColumnReference": True,
+ **({"timeGrain": grain} if grain is not None else {}),
+ }
+ normalized_columns[axis_index] = normalized_axis
+ normalized["columns"] = normalized_columns
+ normalized.pop("is_timeseries", None)
+ return normalized
+
+
+def _finalize_query_objects(
+ form_data: Mapping[str, Any], queries: list[dict[str, Any]]
+) -> list[dict[str, Any]]:
+ """Run shared query-context mutators after every visualization adapter."""
+ return [normalize_time_column(form_data, query) for query in queries]
+
+
+def _x_axis_label(
+ form_data: Mapping[str, Any], *, frontend_strict: bool = False
+) -> str | None:
+ """Mirror getXAxisColumn/getXAxisLabel for explicit and legacy axes."""
+ explicit = (
+ _frontend_x_axis_column(form_data)
+ if frontend_strict
+ else _x_axis_column(form_data)
+ )
+ if explicit:
+ return _label(explicit)
+ if form_data.get("granularity_sqla"):
+ return DTTM_ALIAS
+ return None
+
+
+def _rename_operator(
+ form_data: dict[str, Any],
+ query: dict[str, Any],
+ *,
+ x_axis_label: str | None,
+) -> dict[str, Any] | None:
+ """Mirror the ECharts ``renameOperator`` for Timeseries and Mixed
charts."""
+ metrics = list(query.get("metrics") or [])
+ metric_labels = [_label(metric, metric=True) for metric in metrics]
+ series_columns = query.get("series_columns")
+ columns = _as_list(
+ series_columns if series_columns is not None else query.get("columns")
+ )
+ time_offsets = _as_list(form_data.get("time_compare"))
+ offset_map = _metric_offset_map(form_data, metric_labels)
+ is_time_comparison = bool(offset_map)
+ truncate_metric = form_data.get("truncate_metric")
+
+ should_rename = (
+ bool(metrics)
+ and bool(x_axis_label)
+ and (
+ is_time_comparison
+ or (
+ (bool(columns) or len(time_offsets) > 1)
+ and "truncate_metric" in form_data
+ and bool(truncate_metric)
+ )
+ )
+ )
+ if not should_rename:
+ return None
+
+ renamed: dict[str, str | None] = {}
+ comparison_type = form_data.get("comparison_type")
+ if is_time_comparison:
+ for metric_with_offset, metric_only in offset_map.items():
+ offset_label = next(
+ (
+ str(offset)
+ for offset in time_offsets
+ if metric_with_offset.endswith(f"__{offset}")
+ ),
+ None,
+ )
+ source = (
+ metric_with_offset
+ if comparison_type == "values"
+ else f"{comparison_type}__{metric_only}__{metric_with_offset}"
+ )
+ renamed[source] = (
+ f"{metric_only}, {offset_label}" if len(metrics) > 1 else
offset_label
+ )
+
+ if (
+ comparison_type not in {"difference", "percentage", "ratio"}
+ and len(metrics) == 1
+ and not renamed
):
+ renamed[metric_labels[0]] = None
+ if not renamed:
+ return None
+ return {
+ "operation": "rename",
+ "options": {"columns": renamed, "level": 0, "inplace": True},
+ }
+
+
+def _timeseries_post_processing( # noqa: C901
+ form_data: dict[str, Any],
+ query: dict[str, Any],
+ *,
+ x_axis_label: str | None,
+ groupby: list[Any],
+ mixed: bool,
+ sort_metric: Any = None,
+) -> tuple[list[dict[str, Any]], list[Any]]:
+ """Build the Timeseries/Mixed operator pipeline in frontend order."""
+ metric_labels = [_label(value, metric=True) for value in
query.get("metrics") or []]
+ sort_metric_label = (
+ _label(sort_metric, metric=True) if sort_metric is not None else None
+ )
+ offset_map = _metric_offset_map(form_data, metric_labels)
+ time_offsets = _as_list(form_data.get("time_compare")) if offset_map else
[]
+ post_processing: list[dict[str, Any]] = []
+
+ if x_axis_label and metric_labels:
+ aggregate_labels = (
+ [*offset_map.values(), *offset_map] if offset_map else
list(metric_labels)
+ )
+ if not offset_map and sort_metric_label is not None:
+ aggregate_labels.append(sort_metric_label)
+ post_processing.append(
+ {
+ "operation": "pivot",
+ "options": {
+ "index": [x_axis_label],
+ "columns": [_label(value) for value in groupby],
+ "aggregates": {
+ label: {"operator": "mean"} for label in
aggregate_labels
+ },
+ "drop_missing_columns": not form_data.get(
+ "show_empty_columns", False
+ ),
+ },
+ }
+ )
+
+ if form_data.get("resample_method") and form_data.get("resample_rule"):
+ zero_fill = form_data["resample_method"] == "zerofill"
+ post_processing.append(
+ {
+ "operation": "resample",
+ "options": {
+ "method": "asfreq" if zero_fill else
form_data["resample_method"],
+ "rule": form_data["resample_rule"],
+ "fill_value": 0 if zero_fill else None,
+ **(
+ {"fill_time_range": True}
+ if form_data.get("resample_fill_time_range")
+ else {}
+ ),
+ },
+ }
+ )
+
+ rolling_labels = (
+ [*offset_map.values(), *offset_map] if offset_map else metric_labels
+ )
+ columns_map = {label: label for label in rolling_labels}
+ rolling_type = form_data.get("rolling_type")
+ if rolling_type == "cumsum":
+ post_processing.append(
+ {
+ "operation": "cum",
+ "options": {"operator": "sum", "columns": columns_map},
+ }
+ )
+ elif rolling_type in {"sum", "mean", "std"}:
+ post_processing.append(
+ {
+ "operation": "rolling",
+ "options": {
+ "rolling_type": rolling_type,
+ "window": int(form_data.get("rolling_periods") or 1),
+ "min_periods": int(form_data.get("min_periods") or 0),
+ "columns": columns_map,
+ },
+ }
+ )
+
+ comparison_type = form_data.get("comparison_type")
+ if offset_map and comparison_type != "values":
+ post_processing.append(
+ {
+ "operation": "compare",
+ "options": {
+ "source_columns": list(offset_map.values()),
+ "compare_columns": list(offset_map),
+ "compare_type": comparison_type,
+ "drop_original_columns": True,
+ },
+ }
+ )
+
+ if not mixed and form_data.get("contributionMode"):
+ post_processing.append(
+ {
+ "operation": "contribution",
+ "options": {
+ "orientation": form_data["contributionMode"],
+ "time_shifts": time_offsets,
+ },
+ }
+ )
+
+ if rename := _rename_operator(form_data, query, x_axis_label=x_axis_label):
+ post_processing.append(rename)
+
+ if not mixed:
+ sortable = {
+ x_axis_label or "",
+ *metric_labels,
+ sort_metric_label or "",
+ }
+ if (
+ "x_axis_sort" in form_data
+ and "x_axis_sort_asc" in form_data
+ and form_data.get("x_axis_sort") in sortable
+ and not groupby
+ ):
+ options: dict[str, Any] = {"ascending":
form_data.get("x_axis_sort_asc")}
+ if form_data.get("x_axis_sort") == x_axis_label:
+ options["is_sort_index"] = True
+ else:
+ options["by"] = form_data.get("x_axis_sort")
+ post_processing.append({"operation": "sort", "options": options})
+
+ post_processing.append({"operation": "flatten"})
+ if not mixed and form_data.get("forecastEnabled") and x_axis_label:
+ x_axis = _x_axis_column(form_data)
+ axis_grain = x_axis.get("timeGrain") if isinstance(x_axis, Mapping)
else None
+ time_grain = (
+ axis_grain
+ or (query.get("extras") or {}).get("time_grain_sqla")
+ or form_data.get("time_grain_sqla")
+ or "P1D"
+ )
+ post_processing.append(
+ {
+ "operation": "prophet",
+ "options": {
+ "time_grain": time_grain,
+ "periods": int(form_data.get("forecastPeriods") or 0),
+ "confidence_interval": float(
+ form_data.get("forecastInterval") or 0
+ ),
+ "yearly_seasonality":
form_data.get("forecastSeasonalityYearly"),
+ "weekly_seasonality":
form_data.get("forecastSeasonalityWeekly"),
+ "daily_seasonality":
form_data.get("forecastSeasonalityDaily"),
+ "index": x_axis_label,
+ },
+ }
+ )
+ return post_processing, time_offsets
+
+
+def _timeseries_query(form_data: dict[str, Any], query: dict[str, Any]) ->
None:
+ groupby = _as_list(form_data.get("groupby"))
+ x_axis = _x_axis_column(form_data)
+ x_axis_label = _x_axis_label(form_data)
+ query["columns"] = _deduplicate_fields([*_as_list(x_axis), *groupby])
+ query["series_columns"] = groupby
+ if not x_axis:
+ query["is_timeseries"] = True
+
+ # Timeseries includes its sort-only metric in the SELECT when no series is
+ # present. This lets the post-processing sort operator use a metric not
+ # otherwise displayed.
+ sort_metric = form_data.get("timeseries_limit_metric")
+ if isinstance(sort_metric, list):
+ sort_metric = next(iter(sort_metric), None)
+ if (
+ not groupby
+ and sort_metric is not None
+ and _label(sort_metric, metric=True) == form_data.get("x_axis_sort")
+ and _label(sort_metric, metric=True)
+ not in {_label(metric, metric=True) for metric in query.get("metrics")
or []}
+ ):
+ extra_metric = sort_metric
+ else:
+ extra_metric = None
+ _normalize_query_orderby(query)
+ post_processing, time_offsets = _timeseries_post_processing(
+ form_data,
+ query,
+ x_axis_label=x_axis_label,
+ groupby=groupby,
+ mixed=form_data.get("viz_type") == "mixed_timeseries",
+ sort_metric=extra_metric,
+ )
+ if extra_metric is not None:
+ query.setdefault("metrics", []).append(extra_metric)
+ query["post_processing"] = post_processing
+ query["time_offsets"] = time_offsets
+ if form_data.get("viz_type") != "mixed_timeseries":
+ query["time_compare_full_range"] = bool(
+ time_offsets and form_data.get("time_compare_full_range")
+ )
+
+
+def _big_number_queries(
+ form_data: dict[str, Any], query: dict[str, Any]
+) -> list[dict[str, Any]]:
+ """Mirror Big Number with Trendline's one/two-query contract."""
+ # Saved/native Big Number payloads can carry the temporal binding as a
+ # ``{"column_name": ...}`` mapping, which the strict frontend predicate
does
+ # not recognize; keep grouping by it rather than falling back to a total.
+ frontend_x_axis = _frontend_x_axis_column(form_data)
+ explicit_x_axis = frontend_x_axis or _x_axis_column(form_data)
+ time_column = _as_list(explicit_x_axis)
+ x_axis_label = (
+ _label(explicit_x_axis)
+ if explicit_x_axis
+ else _x_axis_label(form_data, frontend_strict=True)
+ )
+ query["columns"] = time_column
+ if time_column and frontend_x_axis is None:
+ # A native ``{"column_name": ...}`` axis groups by its temporal column
+ # but is not rewritten by normalize_time_column, so drop the legacy
+ # granularity binding here rather than bucketing the same dimension
+ # twice.
+ query.pop("granularity", None)
+ extras = query.get("extras")
+ if isinstance(extras, dict):
+ extras.pop("time_grain_sqla", None)
+ if not extras:
+ query.pop("extras", None)
+ elif not time_column:
+ query["is_timeseries"] = True
+ metric_labels = [_label(value, metric=True) for value in
query.get("metrics") or []]
+ post_processing: list[dict[str, Any]] = []
+ if x_axis_label and metric_labels:
+ post_processing.append(
+ {
+ "operation": "pivot",
+ "options": {
+ "index": [x_axis_label],
+ "columns": [],
+ "aggregates": {
+ label: {"operator": "mean"} for label in metric_labels
+ },
+ "drop_missing_columns": not form_data.get(
+ "show_empty_columns", False
+ ),
+ },
+ }
+ )
+ if form_data.get("resample_method") and form_data.get("resample_rule"):
+ zero_fill = form_data["resample_method"] == "zerofill"
+ post_processing.append(
+ {
+ "operation": "resample",
+ "options": {
+ "method": "asfreq" if zero_fill else
form_data["resample_method"],
+ "rule": form_data["resample_rule"],
+ "fill_value": 0 if zero_fill else None,
+ **(
+ {"fill_time_range": True}
+ if form_data.get("resample_fill_time_range")
+ else {}
+ ),
+ },
+ }
+ )
+ rolling_type = form_data.get("rolling_type")
+ columns_map = {label: label for label in metric_labels}
+ if rolling_type == "cumsum":
+ post_processing.append(
+ {"operation": "cum", "options": {"operator": "sum", "columns":
columns_map}}
+ )
+ elif rolling_type in {"sum", "mean", "std"}:
+ post_processing.append(
+ {
+ "operation": "rolling",
+ "options": {
+ "rolling_type": rolling_type,
+ "window": int(form_data.get("rolling_periods") or 1),
+ "min_periods": int(form_data.get("min_periods") or 0),
+ "columns": columns_map,
+ },
+ }
+ )
+ post_processing.append({"operation": "flatten"})
+ query["post_processing"] = post_processing
+ queries = [query]
+ if form_data.get("aggregation") == "raw":
+ overall = dict(query)
+ overall.update(
+ {
+ "columns": [],
+ "is_timeseries": False,
+ "post_processing": [],
+ }
+ )
+ queries.append(overall)
+ return queries
+
+
+def _table_queries( # noqa: C901
+ form_data: dict[str, Any], query: dict[str, Any]
+) -> list[dict[str, Any]]:
+ if is_raw_query_mode(form_data):
+ # The extractor already applies the raw-mode contract, including native
+ # ``order_by_cols`` parsing. Do not synthesize metric ordering.
+ query["columns"] = list(
+ form_data.get("all_columns") or form_data.get("columns") or []
+ )
+ query["metrics"] = []
+ if raw_orderby := orderby_from_form_data(form_data, [], "table"):
+ query["orderby"] = raw_orderby
+ else:
+ query.pop("orderby", None)
+ return [query]
+
+ metrics = list(query.get("metrics") or [])
+ query["columns"] = _table_temporalized_columns(
+ form_data, list(query.get("columns") or [])
+ )
+ percent_metrics = _as_list(form_data.get("percent_metrics"))
+ for metric in percent_metrics:
+ if _label(metric, metric=True) not in {
+ _label(existing, metric=True) for existing in metrics
+ }:
+ metrics.append(metric)
+ query["metrics"] = metrics
+ query["orderby"] = orderby_from_form_data(form_data, metrics, "table")
+ post_processing: list[dict[str, Any]] = []
+ resolved_offsets = _table_time_offsets(form_data)
+ comparison_enabled = (
+ form_data.get("comparison_type") in _TIME_COMPARISON_TYPES
+ and bool(metrics)
+ and bool(_as_list(form_data.get("time_compare")))
+ )
+ contribution: dict[str, Any] | None = None
+ if percent_metrics:
+ base_labels = [_label(metric, metric=True) for metric in
percent_metrics]
+ labels = [
+ label
+ for metric_label in base_labels
+ for label in (
+ [
+ metric_label,
+ *(f"{metric_label}__{offset}" for offset in
resolved_offsets),
+ ]
+ if comparison_enabled
+ else [metric_label]
+ )
+ ]
+ labels = list(dict.fromkeys(labels))
+ contribution = {
+ "operation": "contribution",
+ "options": {
+ "columns": labels,
+ "rename_columns": [f"%{label}" for label in labels],
+ },
+ }
+ post_processing.append(contribution)
+
+ metric_labels = [_label(metric, metric=True) for metric in metrics]
+ offset_map = _metric_offset_map(form_data, metric_labels, resolved_offsets)
+ time_offsets = resolved_offsets if offset_map else []
+ if offset_map and form_data.get("comparison_type") != "values":
+ post_processing.append(
+ {
+ "operation": "compare",
+ "options": {
+ "source_columns": list(offset_map.values()),
+ "compare_columns": list(offset_map),
+ "compare_type": form_data.get("comparison_type"),
+ "drop_original_columns": True,
+ },
+ }
+ )
+ if post_processing:
query["post_processing"] = post_processing
- # ``granularity`` does two jobs downstream: it names the temporal column
the
- # time range filters on, and it is the column ``time_grain_sqla`` buckets
- # (``models/helpers.py`` swaps a selected column for its timestamp
expression
- # when that column equals ``granularity``). Only the first job depends on
- # there being an active range, so set it whenever form data carries one —
- # matching ``extractExtras.ts``, which sets it unconditionally. Gating it
on
- # ``time_range`` dropped the bucketing, so an ordinary "all-time totals by
- # month" chart exported one row per raw timestamp instead of one per month.
- if granularity := form_data.get("granularity") or
form_data.get("granularity_sqla"):
+ else:
+ query.pop("post_processing", None)
+ query["time_offsets"] = time_offsets
+
+ is_download = form_data.get("result_format") in {"csv", "xlsx"} or (
+ form_data.get("result_format") == "json"
+ and form_data.get("result_type") == "results"
+ )
+ if is_download:
+ if form_data.get("row_limit") is not None:
+ query["row_limit"] = int(form_data["row_limit"])
+ query["row_offset"] = 0
+ elif form_data.get("server_pagination"):
+ page_size = int(form_data.get("server_page_length") or 0)
+ configured_limit = int(form_data.get("row_limit") or 0)
+ query["row_limit"] = (
+ min(page_size, configured_limit) if configured_limit else page_size
Review Comment:
The preserved native pagination overrides the explicit compile/preview row
cap here. With a saved Table that has `server_pagination=true` and
`server_page_length=0`, a requested `row_limit` of 2 gives `min(0, 2)` = 0, so
`QueryObjectFactory` falls back to the deployment default row limit and the
two-row compile sample becomes a full-sized query. Should the explicit caller
limit win when the page length is 0 (e.g. only apply the `min` when `page_size`
is positive)?
--
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]
