codeant-ai-for-open-source[bot] commented on code in PR #41184: URL: https://github.com/apache/superset/pull/41184#discussion_r3565321633
########## superset-frontend/plugins/plugin-chart-pivot-table/test/plugin/utilities.test.ts: ########## @@ -0,0 +1,446 @@ +/* + * 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. + */ + +import { TimeGranularity } from '@superset-ui/core'; +import buildGroupbyCombinations, { + isAdditiveMetric, + allMetricsAdditive, + additiveReducerFor, + synthesizeAdditiveLevels, + splitGroupingSetsResult, + groupingMarkerLabel, +} from '../../src/plugin/utilities'; +import { PivotTableQueryFormData, MetricsLayoutEnum } from '../../src/types'; + +const baseFormData = { + groupbyRows: ['row1', 'row2'], + groupbyColumns: ['col1', 'col2'], + metrics: ['metric1', 'metric2'], + tableRenderer: 'Table With Subtotal', + colOrder: 'key_a_to_z', + rowOrder: 'key_a_to_z', + aggregateFunction: 'Sum', + metricsLayout: MetricsLayoutEnum.ROWS, + transposePivot: false, + rowSubtotalPosition: true, + colSubtotalPosition: true, + colTotals: true, + colSubTotals: true, + rowTotals: true, + rowSubTotals: true, + valueFormat: 'SMART_NUMBER', + datasource: '5__table', + viz_type: 'my_chart', + width: 800, + height: 600, + combineMetric: false, + verboseMap: {}, + columnFormats: {}, + currencyFormats: {}, + metricColorFormatters: [], + dateFormatters: {}, + setDataMask: () => {}, + legacy_order_by: 'count', + order_desc: true, + margin: 0, + time_grain_sqla: TimeGranularity.MONTH, + temporal_columns_lookup: { col1: true }, + currencyFormat: { symbol: 'USD', symbolPosition: 'prefix' }, +} as unknown as PivotTableQueryFormData; + +test('should build all combinations for basic pivot table', () => { + const combinations = buildGroupbyCombinations(baseFormData); + + expect(combinations).toEqual([ + { rows: [], columns: [] }, + { rows: [], columns: ['col1'] }, + { rows: [], columns: ['col1', 'col2'] }, + { rows: ['row1'], columns: [] }, + { rows: ['row1'], columns: ['col1'] }, + { rows: ['row1'], columns: ['col1', 'col2'] }, + { rows: ['row1', 'row2'], columns: [] }, + { rows: ['row1', 'row2'], columns: ['col1'] }, + { rows: ['row1', 'row2'], columns: ['col1', 'col2'] }, + ]); + + expect(combinations).toHaveLength(9); +}); + +test('should handle transposed pivot correctly', () => { + const modifiedFormData = { + ...baseFormData, + transposePivot: true, + }; + + const combinations = buildGroupbyCombinations(modifiedFormData); + + expect(combinations).toEqual([ + { rows: [], columns: [] }, + { rows: [], columns: ['row1'] }, + { rows: [], columns: ['row1', 'row2'] }, + { rows: ['col1'], columns: [] }, + { rows: ['col1'], columns: ['row1'] }, + { rows: ['col1'], columns: ['row1', 'row2'] }, + { rows: ['col1', 'col2'], columns: [] }, + { rows: ['col1', 'col2'], columns: ['row1'] }, + { rows: ['col1', 'col2'], columns: ['row1', 'row2'] }, + ]); +}); + +test('should filter combinations when combineMetric is true with ROWS layout', () => { + const modifiedFormData = { + ...baseFormData, + combineMetric: true, + metricsLayout: MetricsLayoutEnum.ROWS, + }; + + const combinations = buildGroupbyCombinations(modifiedFormData); + + expect(combinations).toEqual([ + { rows: ['row1', 'row2'], columns: [] }, + { rows: ['row1', 'row2'], columns: ['col1'] }, + { rows: ['row1', 'row2'], columns: ['col1', 'col2'] }, + ]); + + expect(combinations).toHaveLength(3); +}); + +test('should filter combinations when combineMetric is true with COLUMNS layout', () => { + const modifiedFormData = { + ...baseFormData, + combineMetric: true, + metricsLayout: MetricsLayoutEnum.COLUMNS, + }; + + const combinations = buildGroupbyCombinations(modifiedFormData); + + expect(combinations).toEqual([ + { rows: [], columns: ['col1', 'col2'] }, + { rows: ['row1'], columns: ['col1', 'col2'] }, + { rows: ['row1', 'row2'], columns: ['col1', 'col2'] }, + ]); + + expect(combinations).toHaveLength(3); +}); + +test('should handle single dimension in rows only', () => { + const modifiedFormData = { + ...baseFormData, + groupbyRows: ['row'], + groupbyColumns: [], + }; + + const combinations = buildGroupbyCombinations(modifiedFormData); + + expect(combinations).toEqual([ + { rows: [], columns: [] }, + { rows: ['row'], columns: [] }, + ]); + + expect(combinations).toHaveLength(2); +}); + +test('should handle single dimension in columns only', () => { + const modifiedFormData = { + ...baseFormData, + groupbyRows: [], + groupbyColumns: ['col'], + }; + + const combinations = buildGroupbyCombinations(modifiedFormData); + + expect(combinations).toEqual([ + { rows: [], columns: [] }, + { rows: [], columns: ['col'] }, + ]); + + expect(combinations).toHaveLength(2); +}); + +test('should handle empty groupby arrays', () => { + const modifiedFormData = { + ...baseFormData, + groupbyRows: [], + groupbyColumns: [], + }; + + const combinations = buildGroupbyCombinations(modifiedFormData); + + expect(combinations).toEqual([{ rows: [], columns: [] }]); + + expect(combinations).toHaveLength(1); +}); + +test('should work with combineMetric and transposed pivot', () => { + const modifiedFormData = { + ...baseFormData, + transposePivot: true, + combineMetric: true, + metricsLayout: MetricsLayoutEnum.COLUMNS, + }; + + const combinations = buildGroupbyCombinations(modifiedFormData); + + expect(combinations).toEqual([ + { rows: [], columns: ['row1', 'row2'] }, + { rows: ['col1'], columns: ['row1', 'row2'] }, + { rows: ['col1', 'col2'], columns: ['row1', 'row2'] }, + ]); +}); + +test('should handle combineMetric with empty arrays correctly', () => { + const modifiedFormData = { + ...baseFormData, + groupbyRows: [], + groupbyColumns: ['col'], + combineMetric: true, + metricsLayout: MetricsLayoutEnum.ROWS, + }; + + const combinations = buildGroupbyCombinations(modifiedFormData); + + expect(combinations).toEqual([ + { rows: [], columns: [] }, + { rows: [], columns: ['col'] }, + ]); +}); + +test('should work with large number of dimensions', () => { + const modifiedFormData = { + ...baseFormData, + groupbyRows: ['r1', 'r2', 'r3', 'r4'], + groupbyColumns: ['c1', 'c2', 'c3'], + }; + + const combinations = buildGroupbyCombinations(modifiedFormData); + + expect(combinations).toHaveLength(20); + + expect(combinations).toContainEqual({ rows: [], columns: [] }); + expect(combinations).toContainEqual({ + rows: ['r1', 'r2', 'r3', 'r4'], + columns: ['c1', 'c2', 'c3'], + }); +}); + +test('isAdditiveMetric: SIMPLE metrics with additive aggregates are additive', () => { + expect( + isAdditiveMetric({ + expressionType: 'SIMPLE', + aggregate: 'SUM', + column: { column_name: 'num' }, + label: 'sum_num', + } as any), + ).toBe(true); + expect( + isAdditiveMetric({ + expressionType: 'SIMPLE', + aggregate: 'COUNT', + column: { column_name: 'num' }, + label: 'count_num', + } as any), + ).toBe(true); +}); + +test('isAdditiveMetric: non-additive aggregates, SQL, and saved metrics are not additive', () => { + expect( + isAdditiveMetric({ + expressionType: 'SIMPLE', + aggregate: 'AVG', + column: { column_name: 'num' }, + label: 'avg_num', + } as any), + ).toBe(false); + expect( + isAdditiveMetric({ + expressionType: 'SIMPLE', + aggregate: 'COUNT_DISTINCT', + column: { column_name: 'name' }, + label: 'distinct_names', + } as any), + ).toBe(false); + expect( + isAdditiveMetric({ + expressionType: 'SQL', + sqlExpression: 'SUM(a) / SUM(b)', + label: 'ratio', + } as any), + ).toBe(false); + // saved-metric reference: aggregate unknown from form data -> non-additive + expect(isAdditiveMetric('count' as any)).toBe(false); Review Comment: **Suggestion:** Replace the string `any` cast with a properly typed saved-metric reference value accepted by `isAdditiveMetric`. [custom_rule] **Severity Level:** Minor ๐งน <details> <summary><b>Why it matters? โญ </b></summary> The code uses `as any` on a string literal in TypeScript. That is exactly the prohibited pattern under the no-any rule. </details> <details> <summary><b>Rule source ๐ </b></summary> .cursor/rules/dev-standard.mdc (line 16) </details> [](https://app.codeant.ai/fix-in-ide?tool=cursor&prompt_id=b3e1a2aab75f4edd8c301da4eff6aa9c&service=github&base_url=https%3A%2F%2Fgithub.com&org=apache&repo=apache%2Fsuperset) [](https://app.codeant.ai/fix-in-ide?tool=vscode-claude&prompt_id=b3e1a2aab75f4edd8c301da4eff6aa9c&service=github&base_url=https%3A%2F%2Fgithub.com&org=apache&repo=apache%2Fsuperset) *(Use Cmd/Ctrl + Click for best experience)* <details> <summary><b>Prompt for AI Agent ๐ค </b></summary> ```mdx This is a comment left during a code review. **Path:** superset-frontend/plugins/plugin-chart-pivot-table/test/plugin/utilities.test.ts **Line:** 285:286 **Comment:** *Custom Rule: Replace the string `any` cast with a properly typed saved-metric reference value accepted by `isAdditiveMetric`. Validate the correctness of the flagged issue. If correct, How can I resolve this? If you propose a fix, implement it and please make it concise. Once fix is implemented, also check other comments on the same PR, and ask user if the user wants to fix the rest of the comments as well. if said yes, then fetch all the comments validate the correctness and implement a minimal fix ``` </details> <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41184&comment_hash=b75a7bee0d9a495c6caa8675cef4d9fd9ab589bdea6d7df4b2a146df9a7516fd&reaction=like'>๐</a> | <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41184&comment_hash=b75a7bee0d9a495c6caa8675cef4d9fd9ab589bdea6d7df4b2a146df9a7516fd&reaction=dislike'>๐</a> ########## superset/common/grouping_sets.py: ########## @@ -0,0 +1,117 @@ +# 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. + +""" +SQL building blocks for the pivot-table non-additive totals optimization +(SIP.md, phase 3b). When a datasource engine reports +``supports_grouping_sets``, the N per-rollup-level queries can be collapsed into +a single ``GROUPING SETS`` query: the database computes every level in one scan, +and each returned row is attributed to its level via ``GROUPING()`` markers. + +These are the engine-agnostic SQL primitives. Wiring them into the query context +(emitting one query and splitting the result back into per-level results) is the +remaining integration; see SIP.md. +""" + +from __future__ import annotations + +from collections.abc import Sequence +from typing import Final + +import pandas as pd +from sqlalchemy import func, tuple_ +from sqlalchemy.sql.elements import ColumnElement + +# Suffix for the per-column GROUPING() marker columns added to a GROUPING SETS +# query. Chosen to be unlikely to collide with a real metric/column label. +GROUPING_MARKER_SUFFIX: Final = "__superset_grouping" + + +def grouping_marker_label(column_label: str) -> str: + """The output label of the GROUPING() marker for a groupby column.""" + return f"{column_label}{GROUPING_MARKER_SUFFIX}" + + +def grouping_sets_clause( + groups: Sequence[Sequence[ColumnElement]], +) -> ColumnElement: + """ + Build a ``GROUP BY GROUPING SETS (...)`` clause from rollup column groups. + + Each group is the set of columns grouped at one rollup level; the empty + group ``()`` is the grand total. For example, groups ``[[a, b], [a], []]`` + produce ``GROUPING SETS ((a, b), (a), ())``. + + :param groups: one column list per rollup level + :return: a clause element suitable for ``select(...).group_by(...)`` + """ + return func.grouping_sets(*[tuple_(*group) for group in groups]) + + +def grouping_id_column(column: ColumnElement, label: str) -> ColumnElement: + """ + Build a ``GROUPING(col) AS label`` marker column. + + In a ``GROUPING SETS`` result, ``GROUPING(col)`` is ``0`` when ``col`` is + part of the row's grouping level and ``1`` when it has been rolled up + (aggregated away). Selecting one marker per groupby column lets the caller + attribute each returned row to its rollup level when splitting the single + result back into per-level results. + + :param column: the groupby column to probe + :param label: the output label for the marker (see ``grouping_marker_label``) + :return: the labelled ``GROUPING(col)`` column + """ + return func.grouping(column).label(label) + + +def split_grouping_sets_result( + df: pd.DataFrame, + levels: Sequence[Sequence[str]], + groupby_columns: Sequence[str], +) -> list[pd.DataFrame]: + """ + Split a combined ``GROUPING SETS`` result into one DataFrame per rollup + level, the inverse of {@link grouping_sets_clause}. + + Each row of ``df`` carries a ``GROUPING()`` marker per groupby column (named + by ``grouping_marker_label``): ``0`` if the column is grouped at that row's + level, ``1`` if it was rolled up. A row belongs to a level iff its markers + are ``0`` exactly for that level's columns. Marker columns are dropped from + the returned frames so each looks like an ordinary per-level query result. + + :param df: the combined query result, including marker columns + :param levels: the grouped-column list for each rollup level (same order as + passed to ``grouping_sets_clause``) + :param groupby_columns: every groupby column that has a marker + :return: one DataFrame per level, in ``levels`` order + """ + markers = [grouping_marker_label(col) for col in groupby_columns] + results: list[pd.DataFrame] = [] + for level in levels: + grouped = set(level) + mask = pd.Series(True, index=df.index) Review Comment: **Suggestion:** Add a type annotation for this boolean mask series to keep local data-shaping variables explicitly typed under the custom rule. [custom_rule] **Severity Level:** Minor ๐งน <details> <summary><b>Why it matters? โญ </b></summary> This newly introduced local variable is also plainly annotatable, and the code omits a type hint, so the suggestion accurately identifies a rule violation. </details> <details> <summary><b>Rule source ๐ </b></summary> .cursor/rules/dev-standard.mdc (line 28) </details> [](https://app.codeant.ai/fix-in-ide?tool=cursor&prompt_id=1836d796f234402cae413e37ab3a8128&service=github&base_url=https%3A%2F%2Fgithub.com&org=apache&repo=apache%2Fsuperset) [](https://app.codeant.ai/fix-in-ide?tool=vscode-claude&prompt_id=1836d796f234402cae413e37ab3a8128&service=github&base_url=https%3A%2F%2Fgithub.com&org=apache&repo=apache%2Fsuperset) *(Use Cmd/Ctrl + Click for best experience)* <details> <summary><b>Prompt for AI Agent ๐ค </b></summary> ```mdx This is a comment left during a code review. **Path:** superset/common/grouping_sets.py **Line:** 107:107 **Comment:** *Custom Rule: Add a type annotation for this boolean mask series to keep local data-shaping variables explicitly typed under the custom rule. Validate the correctness of the flagged issue. If correct, How can I resolve this? If you propose a fix, implement it and please make it concise. Once fix is implemented, also check other comments on the same PR, and ask user if the user wants to fix the rest of the comments as well. if said yes, then fetch all the comments validate the correctness and implement a minimal fix ``` </details> <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41184&comment_hash=5c3e55d3e7dc707fe21d805618879b34549d15d62b12c83b417bddfeb436f099&reaction=like'>๐</a> | <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41184&comment_hash=5c3e55d3e7dc707fe21d805618879b34549d15d62b12c83b417bddfeb436f099&reaction=dislike'>๐</a> ########## superset/common/grouping_sets.py: ########## @@ -0,0 +1,117 @@ +# 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. + +""" +SQL building blocks for the pivot-table non-additive totals optimization +(SIP.md, phase 3b). When a datasource engine reports +``supports_grouping_sets``, the N per-rollup-level queries can be collapsed into +a single ``GROUPING SETS`` query: the database computes every level in one scan, +and each returned row is attributed to its level via ``GROUPING()`` markers. + +These are the engine-agnostic SQL primitives. Wiring them into the query context +(emitting one query and splitting the result back into per-level results) is the +remaining integration; see SIP.md. +""" + +from __future__ import annotations + +from collections.abc import Sequence +from typing import Final + +import pandas as pd +from sqlalchemy import func, tuple_ +from sqlalchemy.sql.elements import ColumnElement + +# Suffix for the per-column GROUPING() marker columns added to a GROUPING SETS +# query. Chosen to be unlikely to collide with a real metric/column label. +GROUPING_MARKER_SUFFIX: Final = "__superset_grouping" + + +def grouping_marker_label(column_label: str) -> str: + """The output label of the GROUPING() marker for a groupby column.""" + return f"{column_label}{GROUPING_MARKER_SUFFIX}" + + +def grouping_sets_clause( + groups: Sequence[Sequence[ColumnElement]], +) -> ColumnElement: + """ + Build a ``GROUP BY GROUPING SETS (...)`` clause from rollup column groups. + + Each group is the set of columns grouped at one rollup level; the empty + group ``()`` is the grand total. For example, groups ``[[a, b], [a], []]`` + produce ``GROUPING SETS ((a, b), (a), ())``. + + :param groups: one column list per rollup level + :return: a clause element suitable for ``select(...).group_by(...)`` + """ + return func.grouping_sets(*[tuple_(*group) for group in groups]) + + +def grouping_id_column(column: ColumnElement, label: str) -> ColumnElement: + """ + Build a ``GROUPING(col) AS label`` marker column. + + In a ``GROUPING SETS`` result, ``GROUPING(col)`` is ``0`` when ``col`` is + part of the row's grouping level and ``1`` when it has been rolled up + (aggregated away). Selecting one marker per groupby column lets the caller + attribute each returned row to its rollup level when splitting the single + result back into per-level results. + + :param column: the groupby column to probe + :param label: the output label for the marker (see ``grouping_marker_label``) + :return: the labelled ``GROUPING(col)`` column + """ + return func.grouping(column).label(label) + + +def split_grouping_sets_result( + df: pd.DataFrame, + levels: Sequence[Sequence[str]], + groupby_columns: Sequence[str], +) -> list[pd.DataFrame]: + """ + Split a combined ``GROUPING SETS`` result into one DataFrame per rollup + level, the inverse of {@link grouping_sets_clause}. + + Each row of ``df`` carries a ``GROUPING()`` marker per groupby column (named + by ``grouping_marker_label``): ``0`` if the column is grouped at that row's + level, ``1`` if it was rolled up. A row belongs to a level iff its markers + are ``0`` exactly for that level's columns. Marker columns are dropped from + the returned frames so each looks like an ordinary per-level query result. + + :param df: the combined query result, including marker columns + :param levels: the grouped-column list for each rollup level (same order as + passed to ``grouping_sets_clause``) + :param groupby_columns: every groupby column that has a marker + :return: one DataFrame per level, in ``levels`` order + """ + markers = [grouping_marker_label(col) for col in groupby_columns] Review Comment: **Suggestion:** Add an explicit type annotation for this derived collection variable to satisfy the rule requiring type hints on relevant annotatable variables. [custom_rule] **Severity Level:** Minor ๐งน <details> <summary><b>Why it matters? โญ </b></summary> This new local variable is a clearly annotatable list and is left untyped in newly added Python code, which matches the custom rule requiring type hints on relevant variables. </details> <details> <summary><b>Rule source ๐ </b></summary> .cursor/rules/dev-standard.mdc (line 28) </details> [](https://app.codeant.ai/fix-in-ide?tool=cursor&prompt_id=b3119cd55c034cb5b88be461e58bc0ac&service=github&base_url=https%3A%2F%2Fgithub.com&org=apache&repo=apache%2Fsuperset) [](https://app.codeant.ai/fix-in-ide?tool=vscode-claude&prompt_id=b3119cd55c034cb5b88be461e58bc0ac&service=github&base_url=https%3A%2F%2Fgithub.com&org=apache&repo=apache%2Fsuperset) *(Use Cmd/Ctrl + Click for best experience)* <details> <summary><b>Prompt for AI Agent ๐ค </b></summary> ```mdx This is a comment left during a code review. **Path:** superset/common/grouping_sets.py **Line:** 103:103 **Comment:** *Custom Rule: Add an explicit type annotation for this derived collection variable to satisfy the rule requiring type hints on relevant annotatable variables. Validate the correctness of the flagged issue. If correct, How can I resolve this? If you propose a fix, implement it and please make it concise. Once fix is implemented, also check other comments on the same PR, and ask user if the user wants to fix the rest of the comments as well. if said yes, then fetch all the comments validate the correctness and implement a minimal fix ``` </details> <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41184&comment_hash=b494a9099c22f5fc19f1148826c70b44305393c84c01a7422c5b1599a920cd74&reaction=like'>๐</a> | <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41184&comment_hash=b494a9099c22f5fc19f1148826c70b44305393c84c01a7422c5b1599a920cd74&reaction=dislike'>๐</a> ########## superset/common/grouping_sets.py: ########## @@ -0,0 +1,117 @@ +# 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. + +""" +SQL building blocks for the pivot-table non-additive totals optimization +(SIP.md, phase 3b). When a datasource engine reports +``supports_grouping_sets``, the N per-rollup-level queries can be collapsed into +a single ``GROUPING SETS`` query: the database computes every level in one scan, +and each returned row is attributed to its level via ``GROUPING()`` markers. + +These are the engine-agnostic SQL primitives. Wiring them into the query context +(emitting one query and splitting the result back into per-level results) is the +remaining integration; see SIP.md. +""" + +from __future__ import annotations + +from collections.abc import Sequence +from typing import Final + +import pandas as pd +from sqlalchemy import func, tuple_ +from sqlalchemy.sql.elements import ColumnElement + +# Suffix for the per-column GROUPING() marker columns added to a GROUPING SETS +# query. Chosen to be unlikely to collide with a real metric/column label. +GROUPING_MARKER_SUFFIX: Final = "__superset_grouping" + + +def grouping_marker_label(column_label: str) -> str: + """The output label of the GROUPING() marker for a groupby column.""" + return f"{column_label}{GROUPING_MARKER_SUFFIX}" + + +def grouping_sets_clause( + groups: Sequence[Sequence[ColumnElement]], +) -> ColumnElement: + """ + Build a ``GROUP BY GROUPING SETS (...)`` clause from rollup column groups. + + Each group is the set of columns grouped at one rollup level; the empty + group ``()`` is the grand total. For example, groups ``[[a, b], [a], []]`` + produce ``GROUPING SETS ((a, b), (a), ())``. + + :param groups: one column list per rollup level + :return: a clause element suitable for ``select(...).group_by(...)`` + """ + return func.grouping_sets(*[tuple_(*group) for group in groups]) + + +def grouping_id_column(column: ColumnElement, label: str) -> ColumnElement: + """ + Build a ``GROUPING(col) AS label`` marker column. + + In a ``GROUPING SETS`` result, ``GROUPING(col)`` is ``0`` when ``col`` is + part of the row's grouping level and ``1`` when it has been rolled up + (aggregated away). Selecting one marker per groupby column lets the caller + attribute each returned row to its rollup level when splitting the single + result back into per-level results. + + :param column: the groupby column to probe + :param label: the output label for the marker (see ``grouping_marker_label``) + :return: the labelled ``GROUPING(col)`` column + """ + return func.grouping(column).label(label) + + +def split_grouping_sets_result( + df: pd.DataFrame, + levels: Sequence[Sequence[str]], + groupby_columns: Sequence[str], +) -> list[pd.DataFrame]: + """ + Split a combined ``GROUPING SETS`` result into one DataFrame per rollup + level, the inverse of {@link grouping_sets_clause}. + + Each row of ``df`` carries a ``GROUPING()`` marker per groupby column (named + by ``grouping_marker_label``): ``0`` if the column is grouped at that row's + level, ``1`` if it was rolled up. A row belongs to a level iff its markers + are ``0`` exactly for that level's columns. Marker columns are dropped from + the returned frames so each looks like an ordinary per-level query result. + + :param df: the combined query result, including marker columns + :param levels: the grouped-column list for each rollup level (same order as + passed to ``grouping_sets_clause``) + :param groupby_columns: every groupby column that has a marker + :return: one DataFrame per level, in ``levels`` order + """ + markers = [grouping_marker_label(col) for col in groupby_columns] + results: list[pd.DataFrame] = [] + for level in levels: + grouped = set(level) Review Comment: **Suggestion:** Annotate this set variable with its element type so the new code consistently applies type hints to relevant local variables. [custom_rule] **Severity Level:** Minor ๐งน <details> <summary><b>Why it matters? โญ </b></summary> This is a new local variable whose type can be annotated, but no type hint is present. That is a real instance of the type-hint rule violation. </details> <details> <summary><b>Rule source ๐ </b></summary> .cursor/rules/dev-standard.mdc (line 28) </details> [](https://app.codeant.ai/fix-in-ide?tool=cursor&prompt_id=d8ef087e6d994f319f554aaa5c8aba44&service=github&base_url=https%3A%2F%2Fgithub.com&org=apache&repo=apache%2Fsuperset) [](https://app.codeant.ai/fix-in-ide?tool=vscode-claude&prompt_id=d8ef087e6d994f319f554aaa5c8aba44&service=github&base_url=https%3A%2F%2Fgithub.com&org=apache&repo=apache%2Fsuperset) *(Use Cmd/Ctrl + Click for best experience)* <details> <summary><b>Prompt for AI Agent ๐ค </b></summary> ```mdx This is a comment left during a code review. **Path:** superset/common/grouping_sets.py **Line:** 106:106 **Comment:** *Custom Rule: Annotate this set variable with its element type so the new code consistently applies type hints to relevant local variables. Validate the correctness of the flagged issue. If correct, How can I resolve this? If you propose a fix, implement it and please make it concise. Once fix is implemented, also check other comments on the same PR, and ask user if the user wants to fix the rest of the comments as well. if said yes, then fetch all the comments validate the correctness and implement a minimal fix ``` </details> <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41184&comment_hash=c732a3404d472185458224a53f0758d610add23183c65b12849526255a0cf83f&reaction=like'>๐</a> | <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41184&comment_hash=c732a3404d472185458224a53f0758d610add23183c65b12849526255a0cf83f&reaction=dislike'>๐</a> ########## superset/common/query_context_processor.py: ########## @@ -252,9 +256,60 @@ def get_query_result(self, query_object: QueryObject) -> QueryResult: This method delegates to the datasource's get_query_result method, which handles query execution, normalization, time offsets, and post-processing. + + When the query requests rollup ``grouping_sets`` but the engine does not + support native ``GROUPING SETS``, fall back to one query per level and + concatenate the results with ``GROUPING()``-equivalent markers, so the + combined result matches the shape the native path produces (SIP.md, + phase 3b). Engines that support it run the single native query. """ + if query_object.grouping_sets and not self._supports_grouping_sets(): + return self._grouping_sets_fallback(query_object) return self._qc_datasource.get_query_result(query_object) + def _supports_grouping_sets(self) -> bool: + engine_spec: BaseEngineSpec | None = getattr( + self._qc_datasource, "db_engine_spec", None + ) + return bool(engine_spec and engine_spec.supports_grouping_sets) + + def _grouping_sets_fallback(self, query_object: QueryObject) -> QueryResult: + """ + Emulate a GROUPING SETS query on engines without native support: run one + query per rollup level and concatenate, tagging each level's rows with + the same per-column markers the native path emits. + """ + levels: list[list[str]] = query_object.grouping_sets + # Use the same label derivation as the native path (physical column name + # or adhoc column label) so both column kinds are represented and each + # label maps back to its own column, in the same order as the source + # list. + all_labels: list[str] = [get_column_name(col) for col in query_object.columns] + label_to_column = dict(zip(all_labels, query_object.columns, strict=True)) + + frames: list[pd.DataFrame] = [] + result: QueryResult | None = None + for level in levels: + level_labels = set(level) Review Comment: **Suggestion:** Add an explicit type annotation for this set variable to keep new local variables consistently typed. [custom_rule] **Severity Level:** Minor ๐งน <details> <summary><b>Why it matters? โญ </b></summary> This is a newly added local variable in Python code, and it can be explicitly annotated for static typing. The lack of a type hint matches the custom rule. </details> <details> <summary><b>Rule source ๐ </b></summary> .cursor/rules/dev-standard.mdc (line 28) </details> [](https://app.codeant.ai/fix-in-ide?tool=cursor&prompt_id=0aafdd509e8d4d2998fdbe0d89d284aa&service=github&base_url=https%3A%2F%2Fgithub.com&org=apache&repo=apache%2Fsuperset) [](https://app.codeant.ai/fix-in-ide?tool=vscode-claude&prompt_id=0aafdd509e8d4d2998fdbe0d89d284aa&service=github&base_url=https%3A%2F%2Fgithub.com&org=apache&repo=apache%2Fsuperset) *(Use Cmd/Ctrl + Click for best experience)* <details> <summary><b>Prompt for AI Agent ๐ค </b></summary> ```mdx This is a comment left during a code review. **Path:** superset/common/query_context_processor.py **Line:** 293:293 **Comment:** *Custom Rule: Add an explicit type annotation for this set variable to keep new local variables consistently typed. Validate the correctness of the flagged issue. If correct, How can I resolve this? If you propose a fix, implement it and please make it concise. Once fix is implemented, also check other comments on the same PR, and ask user if the user wants to fix the rest of the comments as well. if said yes, then fetch all the comments validate the correctness and implement a minimal fix ``` </details> <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41184&comment_hash=2883dd409d4bb1414225604e213d6a922e3b7e1e5bf9c0f7e516c71843b00bbe&reaction=like'>๐</a> | <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41184&comment_hash=2883dd409d4bb1414225604e213d6a922e3b7e1e5bf9c0f7e516c71843b00bbe&reaction=dislike'>๐</a> ########## superset/common/query_context_processor.py: ########## @@ -252,9 +256,60 @@ def get_query_result(self, query_object: QueryObject) -> QueryResult: This method delegates to the datasource's get_query_result method, which handles query execution, normalization, time offsets, and post-processing. + + When the query requests rollup ``grouping_sets`` but the engine does not + support native ``GROUPING SETS``, fall back to one query per level and + concatenate the results with ``GROUPING()``-equivalent markers, so the + combined result matches the shape the native path produces (SIP.md, + phase 3b). Engines that support it run the single native query. """ + if query_object.grouping_sets and not self._supports_grouping_sets(): + return self._grouping_sets_fallback(query_object) return self._qc_datasource.get_query_result(query_object) + def _supports_grouping_sets(self) -> bool: + engine_spec: BaseEngineSpec | None = getattr( + self._qc_datasource, "db_engine_spec", None + ) + return bool(engine_spec and engine_spec.supports_grouping_sets) + + def _grouping_sets_fallback(self, query_object: QueryObject) -> QueryResult: + """ + Emulate a GROUPING SETS query on engines without native support: run one + query per rollup level and concatenate, tagging each level's rows with + the same per-column markers the native path emits. + """ + levels: list[list[str]] = query_object.grouping_sets + # Use the same label derivation as the native path (physical column name + # or adhoc column label) so both column kinds are represented and each + # label maps back to its own column, in the same order as the source + # list. + all_labels: list[str] = [get_column_name(col) for col in query_object.columns] + label_to_column = dict(zip(all_labels, query_object.columns, strict=True)) Review Comment: **Suggestion:** Add an explicit type annotation for this mapping so static type checking can validate key/value usage. [custom_rule] **Severity Level:** Minor ๐งน <details> <summary><b>Why it matters? โญ </b></summary> This is newly introduced Python code in a modified file, and the local mapping variable can be annotated to satisfy the type-hint rule. The suggestion correctly identifies an omitted type hint on an annotatable variable. </details> <details> <summary><b>Rule source ๐ </b></summary> .cursor/rules/dev-standard.mdc (line 28) </details> [](https://app.codeant.ai/fix-in-ide?tool=cursor&prompt_id=6e481d46188046cead535dd509b9c49d&service=github&base_url=https%3A%2F%2Fgithub.com&org=apache&repo=apache%2Fsuperset) [](https://app.codeant.ai/fix-in-ide?tool=vscode-claude&prompt_id=6e481d46188046cead535dd509b9c49d&service=github&base_url=https%3A%2F%2Fgithub.com&org=apache&repo=apache%2Fsuperset) *(Use Cmd/Ctrl + Click for best experience)* <details> <summary><b>Prompt for AI Agent ๐ค </b></summary> ```mdx This is a comment left during a code review. **Path:** superset/common/query_context_processor.py **Line:** 288:288 **Comment:** *Custom Rule: Add an explicit type annotation for this mapping so static type checking can validate key/value usage. Validate the correctness of the flagged issue. If correct, How can I resolve this? If you propose a fix, implement it and please make it concise. Once fix is implemented, also check other comments on the same PR, and ask user if the user wants to fix the rest of the comments as well. if said yes, then fetch all the comments validate the correctness and implement a minimal fix ``` </details> <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41184&comment_hash=f07d2a8670d1f33d82e898aac8a182938924a5c7d3220bf2ac71a2588b2b9078&reaction=like'>๐</a> | <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41184&comment_hash=f07d2a8670d1f33d82e898aac8a182938924a5c7d3220bf2ac71a2588b2b9078&reaction=dislike'>๐</a> ########## superset-frontend/plugins/plugin-chart-pivot-table/test/plugin/transformProps.test.ts: ########## @@ -64,36 +63,73 @@ const chartProps = new ChartProps<QueryFormData>({ theme: supersetTheme, Review Comment: **Suggestion:** Replace this `any` cast with the concrete return type of `transformProps` so the test remains type-safe. [custom_rule] **Severity Level:** Minor ๐งน <details> <summary><b>Why it matters? โญ </b></summary> The code explicitly casts the transform result to `any`, which matches the custom rule violation for TypeScript code using `any` instead of a concrete type. </details> <details> <summary><b>Rule source ๐ </b></summary> .cursor/rules/dev-standard.mdc (line 16) </details> [](https://app.codeant.ai/fix-in-ide?tool=cursor&prompt_id=65f58aaea0724244a242e07d3ee33669&service=github&base_url=https%3A%2F%2Fgithub.com&org=apache&repo=apache%2Fsuperset) [](https://app.codeant.ai/fix-in-ide?tool=vscode-claude&prompt_id=65f58aaea0724244a242e07d3ee33669&service=github&base_url=https%3A%2F%2Fgithub.com&org=apache&repo=apache%2Fsuperset) *(Use Cmd/Ctrl + Click for best experience)* <details> <summary><b>Prompt for AI Agent ๐ค </b></summary> ```mdx This is a comment left during a code review. **Path:** superset-frontend/plugins/plugin-chart-pivot-table/test/plugin/transformProps.test.ts **Line:** 63:63 **Comment:** *Custom Rule: Replace this `any` cast with the concrete return type of `transformProps` so the test remains type-safe. Validate the correctness of the flagged issue. If correct, How can I resolve this? If you propose a fix, implement it and please make it concise. Once fix is implemented, also check other comments on the same PR, and ask user if the user wants to fix the rest of the comments as well. if said yes, then fetch all the comments validate the correctness and implement a minimal fix ``` </details> <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41184&comment_hash=f694e50b82c66df01be21ea5cee8a1aebec8c71c48d0be1ce2b6c5736ef0de7a&reaction=like'>๐</a> | <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41184&comment_hash=f694e50b82c66df01be21ea5cee8a1aebec8c71c48d0be1ce2b6c5736ef0de7a&reaction=dislike'>๐</a> ########## superset-frontend/plugins/plugin-chart-pivot-table/test/plugin/transformProps.test.ts: ########## @@ -64,36 +63,73 @@ const chartProps = new ChartProps<QueryFormData>({ theme: supersetTheme, }); -test('should transform chart props for viz', () => { - expect(transformProps(chartProps)).toEqual({ - width: 800, - height: 600, - groupbyRows: ['row1', 'row2'], - groupbyColumns: ['col1', 'col2'], - metrics: ['metric1', 'metric2'], - tableRenderer: 'Table With Subtotal', - colOrder: 'key_a_to_z', - rowOrder: 'key_a_to_z', - aggregateFunction: 'Sum', - transposePivot: true, - combineMetric: true, - rowSubtotalPosition: true, - colSubtotalPosition: true, +test('should pass through formData props for viz', () => { + const result = transformProps(chartProps) as any; + expect(result.width).toBe(800); + expect(result.height).toBe(600); + expect(result.groupbyRows).toEqual(['row1', 'row2']); + expect(result.groupbyColumns).toEqual(['col1', 'col2']); + expect(result.metrics).toEqual(['metric1', 'metric2']); + expect(result.metricsLayout).toBe(MetricsLayoutEnum.COLUMNS); + expect(result.currencyFormat).toEqual({ Review Comment: **Suggestion:** Type this callback parameter with the concrete item shape instead of `any`. [custom_rule] **Severity Level:** Minor ๐งน <details> <summary><b>Why it matters? โญ </b></summary> The callback parameter is typed as `any`, which is directly prohibited by the no-any-types rule. </details> <details> <summary><b>Rule source ๐ </b></summary> .cursor/rules/dev-standard.mdc (line 16) </details> [](https://app.codeant.ai/fix-in-ide?tool=cursor&prompt_id=1158f6d6540a475689e952c355b01665&service=github&base_url=https%3A%2F%2Fgithub.com&org=apache&repo=apache%2Fsuperset) [](https://app.codeant.ai/fix-in-ide?tool=vscode-claude&prompt_id=1158f6d6540a475689e952c355b01665&service=github&base_url=https%3A%2F%2Fgithub.com&org=apache&repo=apache%2Fsuperset) *(Use Cmd/Ctrl + Click for best experience)* <details> <summary><b>Prompt for AI Agent ๐ค </b></summary> ```mdx This is a comment left during a code review. **Path:** superset-frontend/plugins/plugin-chart-pivot-table/test/plugin/transformProps.test.ts **Line:** 74:74 **Comment:** *Custom Rule: Type this callback parameter with the concrete item shape instead of `any`. Validate the correctness of the flagged issue. If correct, How can I resolve this? If you propose a fix, implement it and please make it concise. Once fix is implemented, also check other comments on the same PR, and ask user if the user wants to fix the rest of the comments as well. if said yes, then fetch all the comments validate the correctness and implement a minimal fix ``` </details> <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41184&comment_hash=881dd6afee054f246ccbc4ba797b4d8a5524ddecf15948f948daeb807018dfee&reaction=like'>๐</a> | <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41184&comment_hash=881dd6afee054f246ccbc4ba797b4d8a5524ddecf15948f948daeb807018dfee&reaction=dislike'>๐</a> -- 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]
