hughhhh commented on code in PR #42284: URL: https://github.com/apache/superset/pull/42284#discussion_r3657988777
########## superset/common/form_data_query_context.py: ########## @@ -0,0 +1,227 @@ +# 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]], +) -> 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}``. Only ``SIMPLE`` WHERE-clause filters are + convertible here; free-form ``SQL`` filters have no ``{col, op, val}`` + equivalent and are handled separately (see :func:`freeform_where_having`). + """ + result: list[dict[str, Any]] = [] + for flt in adhoc_filters or []: + if ( + flt.get("expressionType") == "SIMPLE" + and (flt.get("clause") or "WHERE").upper() == "WHERE" + ): + 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 Review Comment: Confirmed intentional — this fixes a real bug (an earlier reviewer flagged that a stale, present-but-empty `columns: []` was silently dropping `groupby` and changing the aggregation). Now that `preview_utils._build_query_columns` delegates to the shared `columns_from_form_data`, the MCP compile/preview path gets the same fix. Added an MCP-path test (`test_build_query_columns_empty_columns_key_keeps_groupby`) calling `preview_utils._build_query_columns({"groupby": ["country"], "columns": []})` and asserting `["country"]`. -- 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]
