hughhhh commented on code in PR #42284: URL: https://github.com/apache/superset/pull/42284#discussion_r3675636626
########## superset/common/form_data_query_context.py: ########## @@ -0,0 +1,247 @@ +# 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. +""" +Synthesize a query context from a chart's saved form data (``params``). + +A chart's ``query_context`` is normally generated client-side by each viz +plugin's ``buildQuery`` and only persisted when the chart is (re-)saved in +Explore. Charts that predate that behavior keep their ``params`` (form data) but +carry no ``query_context``, so server-side consumers that need to run the query +(e.g. the dashboard Excel export) have nothing to execute. + +This module rebuilds a best-effort query context from the form data — columns, +metrics, filters (including free-form SQL and the time range), ordering and time +grain — mirroring the shared parts of the viz plugins' ``buildQuery``. It does +**not** reproduce plugin post-processing (pivot, contribution/percent +transforms, rolling/forecast) or multi-query fan-out, so callers must restrict it +to viz types whose data maps faithfully to a single plain query. +""" + +from __future__ import annotations + +from typing import Any + +from superset.utils import json + + +def adhoc_filters_to_query_filters( + adhoc_filters: list[dict[str, Any]], + where_only: bool = False, +) -> list[dict[str, Any]]: + """ + Convert ``SIMPLE`` adhoc filters into QueryObject filter clauses. + + Adhoc filters use ``{subject, operator, comparator}`` while a query object + expects ``{col, op, val}``; free-form ``SQL`` filters have no ``{col, op, + val}`` equivalent and are handled separately (see + :func:`freeform_where_having`). + + By default all ``SIMPLE`` filters are converted (the behavior the MCP + compile/preview path relies on). Pass ``where_only=True`` to convert only + ``WHERE``-clause filters, matching the frontend's ``processFilters`` — the + dashboard export uses this so it applies the same rows the chart shows and + does not additionally filter on ``SIMPLE`` ``HAVING`` clauses. + """ + result: list[dict[str, Any]] = [] + for flt in adhoc_filters or []: + if flt.get("expressionType") != "SIMPLE": + continue + if where_only and (flt.get("clause") or "WHERE").upper() != "WHERE": + continue + result.append( + { + "col": flt.get("subject"), + "op": flt.get("operator"), + "val": flt.get("comparator"), + } + ) + return result + + +def freeform_where_having(form_data: dict[str, Any]) -> dict[str, str]: + """ + Collect free-form SQL predicates into a query ``extras`` mapping. + + Mirrors ``processFilters`` on the frontend: ``SQL`` adhoc filters (and a + legacy top-level ``where``) join into ``extras.where`` / ``extras.having`` by + clause, so a chart restricted by a custom SQL predicate exports the same rows + it displays instead of the full, unrestricted result. + """ + where: list[str] = [] + having: list[str] = [] + if form_data.get("where"): + where.append(form_data["where"]) + for flt in form_data.get("adhoc_filters") or []: + if flt.get("expressionType") == "SQL" and flt.get("sqlExpression"): + clause = (flt.get("clause") or "WHERE").upper() + (having if clause == "HAVING" else where).append(flt["sqlExpression"]) + + extras: dict[str, str] = {} + if where: + extras["where"] = " AND ".join(f"({clause})" for clause in where) + if having: + extras["having"] = " AND ".join(f"({clause})" for clause in having) + return extras + + +def columns_from_form_data(form_data: dict[str, Any]) -> list[Any]: + """ + Derive the query's grouping/raw columns from form data. + + Handles raw-mode tables (``all_columns``/``columns``), an ``x_axis`` (string + or adhoc column), and ``groupby`` dimensions, de-duplicating while preserving + order. + """ + if form_data.get("query_mode") == "raw" and ( + form_data.get("all_columns") or form_data.get("columns") + ): + return list(form_data.get("all_columns") or form_data.get("columns") or []) + + groupby_columns: list[Any] = form_data.get("groupby") or [] + raw_columns: list[Any] = form_data.get("columns") or [] + # Prefer explicit raw columns only when they are actually present; a stale + # empty ``columns: []`` key must not shadow the group-by dimensions (which + # would silently drop the grouping and change the aggregation). + columns = raw_columns.copy() if raw_columns else groupby_columns.copy() + + x_axis = form_data.get("x_axis") + if isinstance(x_axis, str) and x_axis and x_axis not in columns: + columns.insert(0, x_axis) + elif isinstance(x_axis, dict): + col_name = x_axis.get("column_name") + if col_name and col_name not in columns: + columns.insert(0, col_name) + return columns + + +def orderby_from_form_data( + form_data: dict[str, Any], metrics: list[Any] +) -> list[list[Any]]: + """ + Derive ordering so a ``row_limit`` returns the chart's top-N, not an + arbitrary N. + + Raw-mode tables order by ``order_by_cols`` (stored as JSON ``[col, asc]`` + pairs). Aggregate charts order by the configured sort metric + (``timeseries_limit_metric``, or the first metric when ``sort_by_metric`` is + set), otherwise fall back to the first metric descending — matching the + table/pie ``buildQuery`` defaults. + """ + if order_by_cols := form_data.get("order_by_cols") or []: + parsed: list[list[Any]] = [] + for col in order_by_cols: + if isinstance(col, str): + try: + col = json.loads(col) + except (TypeError, ValueError): + continue + parsed.append(col) + return parsed + + if not metrics: + return [] + + order_desc = form_data.get("order_desc", True) + sort_metric = form_data.get("timeseries_limit_metric") or ( + metrics[0] if form_data.get("sort_by_metric") else None + ) + if sort_metric is not None: + return [[sort_metric, not order_desc]] + # No explicit sort metric: default to the first metric, descending. + return [[metrics[0], False]] + + +def build_query_context_from_form_data( + form_data: dict[str, Any], + datasource: dict[str, Any], + viz_type: str | None = None, +) -> dict[str, Any]: + """ + Build a query-context payload (the JSON shape ``ChartDataQueryContextSchema`` + loads) from a chart's form data and datasource reference. + + :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. + """ + metrics = list(form_data.get("metrics") or []) Review Comment: Fixed in 25658110ba. The rebuild now mirrors `getQueryMode` (a new `is_raw_query_mode`: explicit `query_mode`, else `all_columns` presence) and in raw mode uses only the selected columns while ignoring the stale `metrics`/`groupby` — so no accidental aggregation, grouping, or metric-based `orderby`. Added regression tests, including one for the `Publishers With Most Titles`-style raw table (all_columns + stale metrics/groupby → columns only, metrics=[], orderby=[]). ########## superset/common/form_data_query_context.py: ########## @@ -0,0 +1,247 @@ +# 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. +""" +Synthesize a query context from a chart's saved form data (``params``). + +A chart's ``query_context`` is normally generated client-side by each viz +plugin's ``buildQuery`` and only persisted when the chart is (re-)saved in +Explore. Charts that predate that behavior keep their ``params`` (form data) but +carry no ``query_context``, so server-side consumers that need to run the query +(e.g. the dashboard Excel export) have nothing to execute. + +This module rebuilds a best-effort query context from the form data — columns, +metrics, filters (including free-form SQL and the time range), ordering and time +grain — mirroring the shared parts of the viz plugins' ``buildQuery``. It does +**not** reproduce plugin post-processing (pivot, contribution/percent +transforms, rolling/forecast) or multi-query fan-out, so callers must restrict it +to viz types whose data maps faithfully to a single plain query. +""" + +from __future__ import annotations + +from typing import Any + +from superset.utils import json + + +def adhoc_filters_to_query_filters( + adhoc_filters: list[dict[str, Any]], + where_only: bool = False, +) -> list[dict[str, Any]]: + """ + Convert ``SIMPLE`` adhoc filters into QueryObject filter clauses. + + Adhoc filters use ``{subject, operator, comparator}`` while a query object + expects ``{col, op, val}``; free-form ``SQL`` filters have no ``{col, op, + val}`` equivalent and are handled separately (see + :func:`freeform_where_having`). + + By default all ``SIMPLE`` filters are converted (the behavior the MCP + compile/preview path relies on). Pass ``where_only=True`` to convert only + ``WHERE``-clause filters, matching the frontend's ``processFilters`` — the + dashboard export uses this so it applies the same rows the chart shows and + does not additionally filter on ``SIMPLE`` ``HAVING`` clauses. + """ + result: list[dict[str, Any]] = [] + for flt in adhoc_filters or []: + if flt.get("expressionType") != "SIMPLE": + continue + if where_only and (flt.get("clause") or "WHERE").upper() != "WHERE": + continue + result.append( + { + "col": flt.get("subject"), + "op": flt.get("operator"), + "val": flt.get("comparator"), + } + ) + return result + + +def freeform_where_having(form_data: dict[str, Any]) -> dict[str, str]: + """ + Collect free-form SQL predicates into a query ``extras`` mapping. + + Mirrors ``processFilters`` on the frontend: ``SQL`` adhoc filters (and a + legacy top-level ``where``) join into ``extras.where`` / ``extras.having`` by + clause, so a chart restricted by a custom SQL predicate exports the same rows + it displays instead of the full, unrestricted result. + """ + where: list[str] = [] + having: list[str] = [] + if form_data.get("where"): + where.append(form_data["where"]) + for flt in form_data.get("adhoc_filters") or []: + if flt.get("expressionType") == "SQL" and flt.get("sqlExpression"): + clause = (flt.get("clause") or "WHERE").upper() + (having if clause == "HAVING" else where).append(flt["sqlExpression"]) + + extras: dict[str, str] = {} + if where: + extras["where"] = " AND ".join(f"({clause})" for clause in where) + if having: + extras["having"] = " AND ".join(f"({clause})" for clause in having) + return extras + + +def columns_from_form_data(form_data: dict[str, Any]) -> list[Any]: + """ + Derive the query's grouping/raw columns from form data. + + Handles raw-mode tables (``all_columns``/``columns``), an ``x_axis`` (string + or adhoc column), and ``groupby`` dimensions, de-duplicating while preserving + order. + """ + if form_data.get("query_mode") == "raw" and ( + form_data.get("all_columns") or form_data.get("columns") + ): + return list(form_data.get("all_columns") or form_data.get("columns") or []) + + groupby_columns: list[Any] = form_data.get("groupby") or [] + raw_columns: list[Any] = form_data.get("columns") or [] + # Prefer explicit raw columns only when they are actually present; a stale + # empty ``columns: []`` key must not shadow the group-by dimensions (which + # would silently drop the grouping and change the aggregation). + columns = raw_columns.copy() if raw_columns else groupby_columns.copy() + + x_axis = form_data.get("x_axis") + if isinstance(x_axis, str) and x_axis and x_axis not in columns: + columns.insert(0, x_axis) + elif isinstance(x_axis, dict): + col_name = x_axis.get("column_name") + if col_name and col_name not in columns: + columns.insert(0, col_name) + return columns + + +def orderby_from_form_data( + form_data: dict[str, Any], metrics: list[Any] +) -> list[list[Any]]: + """ + Derive ordering so a ``row_limit`` returns the chart's top-N, not an + arbitrary N. + + Raw-mode tables order by ``order_by_cols`` (stored as JSON ``[col, asc]`` + pairs). Aggregate charts order by the configured sort metric + (``timeseries_limit_metric``, or the first metric when ``sort_by_metric`` is + set), otherwise fall back to the first metric descending — matching the + table/pie ``buildQuery`` defaults. + """ + if order_by_cols := form_data.get("order_by_cols") or []: + parsed: list[list[Any]] = [] + for col in order_by_cols: + if isinstance(col, str): + try: + col = json.loads(col) + except (TypeError, ValueError): + continue + parsed.append(col) + return parsed + + if not metrics: + return [] + + order_desc = form_data.get("order_desc", True) Review Comment: Good catch. Made it viz-specific in 25658110ba: `orderby_from_form_data` now defaults `order_desc` to False (ascending) for Table and True (descending) for Pie/others, matching the plugins — so a table with `timeseries_limit_metric` and no saved `order_desc` sorts ascending in the export too, keeping bottom-N under a row limit. Added a regression test (Table + timeseries_limit_metric, no order_desc → `[[metric, True]]`). ########## superset/common/form_data_query_context.py: ########## @@ -0,0 +1,247 @@ +# 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. +""" +Synthesize a query context from a chart's saved form data (``params``). + +A chart's ``query_context`` is normally generated client-side by each viz +plugin's ``buildQuery`` and only persisted when the chart is (re-)saved in +Explore. Charts that predate that behavior keep their ``params`` (form data) but +carry no ``query_context``, so server-side consumers that need to run the query +(e.g. the dashboard Excel export) have nothing to execute. + +This module rebuilds a best-effort query context from the form data — columns, +metrics, filters (including free-form SQL and the time range), ordering and time +grain — mirroring the shared parts of the viz plugins' ``buildQuery``. It does +**not** reproduce plugin post-processing (pivot, contribution/percent +transforms, rolling/forecast) or multi-query fan-out, so callers must restrict it +to viz types whose data maps faithfully to a single plain query. +""" + +from __future__ import annotations + +from typing import Any + +from superset.utils import json + + +def adhoc_filters_to_query_filters( + adhoc_filters: list[dict[str, Any]], + where_only: bool = False, +) -> list[dict[str, Any]]: + """ + Convert ``SIMPLE`` adhoc filters into QueryObject filter clauses. + + Adhoc filters use ``{subject, operator, comparator}`` while a query object + expects ``{col, op, val}``; free-form ``SQL`` filters have no ``{col, op, + val}`` equivalent and are handled separately (see + :func:`freeform_where_having`). + + By default all ``SIMPLE`` filters are converted (the behavior the MCP + compile/preview path relies on). Pass ``where_only=True`` to convert only + ``WHERE``-clause filters, matching the frontend's ``processFilters`` — the + dashboard export uses this so it applies the same rows the chart shows and + does not additionally filter on ``SIMPLE`` ``HAVING`` clauses. + """ + result: list[dict[str, Any]] = [] + for flt in adhoc_filters or []: + if flt.get("expressionType") != "SIMPLE": + continue + if where_only and (flt.get("clause") or "WHERE").upper() != "WHERE": + continue + result.append( + { + "col": flt.get("subject"), + "op": flt.get("operator"), + "val": flt.get("comparator"), + } + ) + return result + + +def freeform_where_having(form_data: dict[str, Any]) -> dict[str, str]: + """ + Collect free-form SQL predicates into a query ``extras`` mapping. + + Mirrors ``processFilters`` on the frontend: ``SQL`` adhoc filters (and a + legacy top-level ``where``) join into ``extras.where`` / ``extras.having`` by + clause, so a chart restricted by a custom SQL predicate exports the same rows + it displays instead of the full, unrestricted result. + """ + where: list[str] = [] + having: list[str] = [] + if form_data.get("where"): + where.append(form_data["where"]) + for flt in form_data.get("adhoc_filters") or []: + if flt.get("expressionType") == "SQL" and flt.get("sqlExpression"): + clause = (flt.get("clause") or "WHERE").upper() + (having if clause == "HAVING" else where).append(flt["sqlExpression"]) + + extras: dict[str, str] = {} + if where: + extras["where"] = " AND ".join(f"({clause})" for clause in where) + if having: + extras["having"] = " AND ".join(f"({clause})" for clause in having) + return extras + + +def columns_from_form_data(form_data: dict[str, Any]) -> list[Any]: + """ + Derive the query's grouping/raw columns from form data. + + Handles raw-mode tables (``all_columns``/``columns``), an ``x_axis`` (string + or adhoc column), and ``groupby`` dimensions, de-duplicating while preserving + order. + """ + if form_data.get("query_mode") == "raw" and ( + form_data.get("all_columns") or form_data.get("columns") + ): + return list(form_data.get("all_columns") or form_data.get("columns") or []) + + groupby_columns: list[Any] = form_data.get("groupby") or [] + raw_columns: list[Any] = form_data.get("columns") or [] + # Prefer explicit raw columns only when they are actually present; a stale + # empty ``columns: []`` key must not shadow the group-by dimensions (which + # would silently drop the grouping and change the aggregation). + columns = raw_columns.copy() if raw_columns else groupby_columns.copy() + + x_axis = form_data.get("x_axis") + if isinstance(x_axis, str) and x_axis and x_axis not in columns: + columns.insert(0, x_axis) + elif isinstance(x_axis, dict): + col_name = x_axis.get("column_name") + if col_name and col_name not in columns: + columns.insert(0, col_name) + return columns + + +def orderby_from_form_data( + form_data: dict[str, Any], metrics: list[Any] +) -> list[list[Any]]: + """ + Derive ordering so a ``row_limit`` returns the chart's top-N, not an + arbitrary N. + + Raw-mode tables order by ``order_by_cols`` (stored as JSON ``[col, asc]`` + pairs). Aggregate charts order by the configured sort metric + (``timeseries_limit_metric``, or the first metric when ``sort_by_metric`` is + set), otherwise fall back to the first metric descending — matching the + table/pie ``buildQuery`` defaults. + """ + if order_by_cols := form_data.get("order_by_cols") or []: + parsed: list[list[Any]] = [] + for col in order_by_cols: + if isinstance(col, str): + try: + col = json.loads(col) + except (TypeError, ValueError): + continue + parsed.append(col) + return parsed + + if not metrics: + return [] + + order_desc = form_data.get("order_desc", True) + sort_metric = form_data.get("timeseries_limit_metric") or ( + metrics[0] if form_data.get("sort_by_metric") else None + ) + if sort_metric is not None: + return [[sort_metric, not order_desc]] + # No explicit sort metric: default to the first metric, descending. + return [[metrics[0], False]] + + +def build_query_context_from_form_data( + form_data: dict[str, Any], + datasource: dict[str, Any], + viz_type: str | None = None, +) -> dict[str, Any]: + """ + Build a query-context payload (the JSON shape ``ChartDataQueryContextSchema`` + loads) from a chart's form data and datasource reference. + + :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. + """ + metrics = list(form_data.get("metrics") or []) + # Single-metric charts (e.g. Big Number) store ``metric`` rather than + # ``metrics``. + if not metrics and form_data.get("metric"): + metrics = [form_data["metric"]] + # ``percent_metrics`` are intentionally not carried: the chart shows them as a + # "% of total" produced by contribution post-processing, which this rebuild + # does not apply, so adding them as plain metrics would export raw aggregates + # that don't match the chart. Review Comment: Agreed — silently omitting visible columns is worse than skipping. In 25658110ba a non-empty `percent_metrics` is now treated like the other `_UNSUPPORTED_PROCESSING_KEYS`: the chart is skipped and listed for re-save rather than rebuilt. Added it to the parametrized skip test. -- 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]
