gkneighb commented on code in PR #41860:
URL: https://github.com/apache/superset/pull/41860#discussion_r3575563008
##########
superset/mcp_service/chart/chart_utils.py:
##########
@@ -891,6 +893,64 @@ def map_pie_config(config: PieChartConfig) -> Dict[str,
Any]:
return form_data
+def map_histogram_config(config: "HistogramChartConfig") -> Dict[str, Any]:
+ """Map histogram config to Superset form_data (viz_type histogram_v2).
+
+ Matches the frontend Histogram buildQuery contract: a single ``column``
+ string to bin, ``groupby`` name list for series, plus bins/normalize/
+ cumulative passed straight through to the histogram post-processing
+ operator.
+ """
+ form_data: Dict[str, Any] = {
+ "viz_type": "histogram_v2",
+ "column": config.column.name,
+ "groupby": [g.name for g in (config.groupby or [])],
+ "bins": config.bins,
+ "normalize": config.normalize,
+ "cumulative": config.cumulative,
+ "row_limit": config.row_limit,
+ }
+ _add_adhoc_filters(form_data, config.filters)
+ return form_data
+
+
+# The exact strings the frontend boxplotOperator understands; the percentile
+# variant must match its PERCENTILE_REGEX: "<low>/<high> percentiles".
+_WHISKER_TYPE_TO_OPTION = {
+ "tukey": "Tukey",
Review Comment:
Declining, standing rationale: constants, locals, and test lambdas with
inferable types are unannotated across this codebase; mypy passes. Identical
future findings will be declined the same way.
##########
superset/mcp_service/chart/plugins/histogram.py:
##########
@@ -0,0 +1,186 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements. See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership. The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied. See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+"""Histogram chart type plugin."""
+
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import Any, ClassVar
+
+from superset.mcp_service.chart.chart_utils import (
+ _summarize_filters,
+ map_histogram_config,
+)
+from superset.mcp_service.chart.plugin import BaseChartPlugin
+from superset.mcp_service.chart.schemas import ColumnRef, HistogramChartConfig
+from superset.mcp_service.chart.validation.dataset_validator import
DatasetValidator
+from superset.mcp_service.common.error_schemas import ChartGenerationError
+
+
+class HistogramChartPlugin(BaseChartPlugin):
+ """Plugin for histogram chart type."""
+
+ chart_type = "histogram"
+ display_name = "Histogram"
+ native_viz_types: ClassVar[Mapping[str, str]] = {
+ "histogram_v2": "Histogram",
+ }
+
+ def pre_validate(
+ self,
+ config: dict[str, Any],
+ ) -> ChartGenerationError | None:
+ if "column" not in config:
+ return ChartGenerationError(
+ error_type="missing_histogram_fields",
+ message="Histogram missing required field: 'column'",
+ details=(
+ "Histograms bin the values of a single numeric column "
+ "into frequency buckets"
+ ),
+ suggestions=[
+ "Add 'column' field: {'name': 'numeric_column'}",
+ "Example: {'chart_type': 'histogram', "
+ "'column': {'name': 'trip_duration'}, 'bins': 10}",
+ ],
+ error_code="MISSING_HISTOGRAM_FIELDS",
+ )
+ return None
+
+ def extract_column_refs(self, config: Any) -> list[ColumnRef]:
+ if not isinstance(config, HistogramChartConfig):
+ return []
+ refs: list[ColumnRef] = [config.column]
+ refs.extend(config.groupby or [])
+ if config.filters:
+ for f in config.filters:
+ refs.append(ColumnRef(name=f.column))
+ return refs
+
+ def to_form_data(
+ self, config: Any, dataset_id: int | str | None = None
+ ) -> dict[str, Any]:
+ return map_histogram_config(config)
+
+ def generate_name(self, config: Any, dataset_name: str | None = None) ->
str:
+ what = f"Distribution of {config.column.label or config.column.name}"
+ if config.groupby:
+ what += " by " + ", ".join(g.label or g.name for g in
config.groupby)
+ context = _summarize_filters(config.filters)
+ return self._with_context(what, context)
+
+ def post_map_validate(
+ self,
+ config: Any,
+ form_data: dict[str, Any],
+ dataset_id: int | str | None = None,
+ ) -> ChartGenerationError | None:
+ """Require a numeric binned column, mirroring the Explore UI.
+
+ The frontend control panel restricts the histogram column to
+ ``GenericDataType.Numeric``; without this check an LLM picking a
+ text column passes pre-validation and only fails at query time.
+ """
+ if not isinstance(config, HistogramChartConfig) or dataset_id is None:
+ return None
+
+ dataset_context = DatasetValidator._get_dataset_context(dataset_id)
+ if dataset_context is None:
+ return None
+
+ col_info = next(
+ (
+ col
+ for col in dataset_context.available_columns
+ if col["name"].lower() == (config.column.name or "").lower()
+ ),
+ None,
+ )
+ if col_info is None:
+ # Column existence is validated separately; don't double-report.
+ return None
+
+ numeric_types = ["INTEGER", "FLOAT", "DOUBLE", "DECIMAL", "NUMERIC"]
Review Comment:
Superseded in 39ec6d334b — the list was replaced by a stem-matching helper
(see the sibling thread); the local is inside a small typed closure now.
##########
superset/mcp_service/chart/plugins/box_plot.py:
##########
@@ -0,0 +1,145 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements. See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership. The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied. See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+"""Box plot chart type plugin."""
+
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import Any, ClassVar
+
+from superset.mcp_service.chart.chart_utils import (
+ _summarize_filters,
+ map_box_plot_config,
+)
+from superset.mcp_service.chart.plugin import BaseChartPlugin
+from superset.mcp_service.chart.schemas import BoxPlotChartConfig, ColumnRef
+from superset.mcp_service.chart.validation.dataset_validator import
DatasetValidator
+from superset.mcp_service.common.error_schemas import ChartGenerationError
+
+
+class BoxPlotChartPlugin(BaseChartPlugin):
+ """Plugin for box plot chart type."""
+
+ chart_type = "box_plot"
+ display_name = "Box Plot"
+ native_viz_types: ClassVar[Mapping[str, str]] = {
+ "box_plot": "Box Plot",
+ }
+
+ def pre_validate(
+ self,
+ config: dict[str, Any],
+ ) -> ChartGenerationError | None:
+ missing_fields = []
+ if "metrics" not in config:
+ missing_fields.append("'metrics' (values whose spread is plotted)")
+ if "distribute_across" not in config:
+ missing_fields.append(
+ "'distribute_across' (columns forming one box per value)"
+ )
+
+ if missing_fields:
+ return ChartGenerationError(
+ error_type="missing_box_plot_fields",
+ message=(
+ f"Box plot missing required fields: {',
'.join(missing_fields)}"
+ ),
+ details=(
+ "Box plots show the distribution of one or more metrics "
+ "across the values of the distribute_across columns"
+ ),
+ suggestions=[
+ "Add 'metrics': [{'name': 'value_column', 'aggregate':
'AVG'}]",
+ "Add 'distribute_across': [{'name': 'category_column'}]",
+ "Example: {'chart_type': 'box_plot', 'metrics': "
+ "[{'name': 'fare', 'aggregate': 'AVG'}], "
+ "'distribute_across': [{'name': 'day_of_week'}]}",
+ ],
+ error_code="MISSING_BOX_PLOT_FIELDS",
+ )
+ return None
+
+ def extract_column_refs(self, config: Any) -> list[ColumnRef]:
+ if not isinstance(config, BoxPlotChartConfig):
+ return []
+ refs: list[ColumnRef] = []
+ refs.extend(config.metrics)
+ refs.extend(config.distribute_across)
+ refs.extend(config.dimensions or [])
+ if config.filters:
+ for f in config.filters:
+ refs.append(ColumnRef(name=f.column))
+ return refs
+
+ def to_form_data(
+ self, config: Any, dataset_id: int | str | None = None
+ ) -> dict[str, Any]:
+ return map_box_plot_config(config)
+
+ def generate_name(self, config: Any, dataset_name: str | None = None) ->
str:
+ metric_names = ", ".join(m.label or m.name for m in config.metrics)
+ across = ", ".join(c.label or c.name for c in config.distribute_across)
+ what = f"{metric_names} distribution by {across}"
+ context = _summarize_filters(config.filters)
+ return self._with_context(what, context)
+
+ def resolve_viz_type(self, config: Any) -> str:
+ return "box_plot"
+
+ def normalize_column_refs(self, config: Any, dataset_context: Any) -> Any:
+ config_dict = config.model_dump()
+
+ for metric in config_dict.get("metrics") or []:
+ if metric.get("sql_expression"):
+ continue
+ if metric.get("saved_metric"):
+ metric["name"] = DatasetValidator.get_canonical_metric_name(
+ metric["name"], dataset_context
+ )
+ else:
+ metric["name"] = DatasetValidator.get_canonical_column_name(
+ metric["name"], dataset_context
+ )
+ for key in ("distribute_across", "dimensions"):
+ for col in config_dict.get(key) or []:
+ if not col.get("sql_expression") and not
col.get("saved_metric"):
+ col["name"] = DatasetValidator.get_canonical_column_name(
+ col["name"], dataset_context
+ )
+ DatasetValidator.normalize_filters(config_dict, dataset_context)
+ return BoxPlotChartConfig.model_validate(config_dict)
+
+ def schema_error_hint(self) -> ChartGenerationError | None:
+ return ChartGenerationError(
+ error_type="box_plot_validation_error",
+ message="Box plot configuration validation failed",
+ details=(
+ "The box plot configuration is missing required fields or "
+ "has invalid structure"
+ ),
+ suggestions=[
+ "Ensure 'metrics' is a non-empty list with 'name' and
'aggregate'",
Review Comment:
Fixed in 39ec6d334b — suggestions now state aggregate or saved_metric=True.
##########
superset/mcp_service/chart/plugins/histogram.py:
##########
@@ -0,0 +1,186 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements. See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership. The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied. See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+"""Histogram chart type plugin."""
+
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import Any, ClassVar
+
+from superset.mcp_service.chart.chart_utils import (
+ _summarize_filters,
+ map_histogram_config,
+)
+from superset.mcp_service.chart.plugin import BaseChartPlugin
+from superset.mcp_service.chart.schemas import ColumnRef, HistogramChartConfig
+from superset.mcp_service.chart.validation.dataset_validator import
DatasetValidator
+from superset.mcp_service.common.error_schemas import ChartGenerationError
+
+
+class HistogramChartPlugin(BaseChartPlugin):
+ """Plugin for histogram chart type."""
+
+ chart_type = "histogram"
+ display_name = "Histogram"
+ native_viz_types: ClassVar[Mapping[str, str]] = {
+ "histogram_v2": "Histogram",
+ }
+
+ def pre_validate(
+ self,
+ config: dict[str, Any],
+ ) -> ChartGenerationError | None:
+ if "column" not in config:
+ return ChartGenerationError(
+ error_type="missing_histogram_fields",
+ message="Histogram missing required field: 'column'",
+ details=(
+ "Histograms bin the values of a single numeric column "
+ "into frequency buckets"
+ ),
+ suggestions=[
+ "Add 'column' field: {'name': 'numeric_column'}",
+ "Example: {'chart_type': 'histogram', "
+ "'column': {'name': 'trip_duration'}, 'bins': 10}",
+ ],
+ error_code="MISSING_HISTOGRAM_FIELDS",
+ )
+ return None
+
+ def extract_column_refs(self, config: Any) -> list[ColumnRef]:
+ if not isinstance(config, HistogramChartConfig):
+ return []
+ refs: list[ColumnRef] = [config.column]
+ refs.extend(config.groupby or [])
+ if config.filters:
+ for f in config.filters:
+ refs.append(ColumnRef(name=f.column))
+ return refs
+
+ def to_form_data(
+ self, config: Any, dataset_id: int | str | None = None
+ ) -> dict[str, Any]:
+ return map_histogram_config(config)
+
+ def generate_name(self, config: Any, dataset_name: str | None = None) ->
str:
+ what = f"Distribution of {config.column.label or config.column.name}"
+ if config.groupby:
+ what += " by " + ", ".join(g.label or g.name for g in
config.groupby)
+ context = _summarize_filters(config.filters)
+ return self._with_context(what, context)
+
+ def post_map_validate(
+ self,
+ config: Any,
+ form_data: dict[str, Any],
+ dataset_id: int | str | None = None,
+ ) -> ChartGenerationError | None:
+ """Require a numeric binned column, mirroring the Explore UI.
+
+ The frontend control panel restricts the histogram column to
+ ``GenericDataType.Numeric``; without this check an LLM picking a
+ text column passes pre-validation and only fails at query time.
+ """
+ if not isinstance(config, HistogramChartConfig) or dataset_id is None:
+ return None
+
+ dataset_context = DatasetValidator._get_dataset_context(dataset_id)
+ if dataset_context is None:
+ return None
+
+ col_info = next(
+ (
+ col
+ for col in dataset_context.available_columns
+ if col["name"].lower() == (config.column.name or "").lower()
+ ),
+ None,
+ )
+ if col_info is None:
+ # Column existence is validated separately; don't double-report.
+ return None
+
+ numeric_types = ["INTEGER", "FLOAT", "DOUBLE", "DECIMAL", "NUMERIC"]
+ if col_info.get("is_numeric", False) or (
+ col_info.get("type", "").upper() in numeric_types
+ ):
+ return None
Review Comment:
Confirmed and fixed in 39ec6d334b — the fallback now stem-matches
(INT/FLOAT/DOUBLE/DECIMAL/NUMERIC/REAL/NUMBER), covering BIGINT, SMALLINT,
REAL, NUMBER, and DOUBLE PRECISION spellings.
--
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]
