codeant-ai-for-open-source[bot] commented on code in PR #41133: URL: https://github.com/apache/superset/pull/41133#discussion_r3486008019
########## superset/tasks/export_dashboard_excel.py: ########## @@ -0,0 +1,246 @@ +# 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. +""" +Celery task that exports every chart on a dashboard to a single multi-sheet +``.xlsx`` file, uploads it to S3, and emails the requesting user a pre-signed +download link. + +The task re-runs each chart's saved query context under the requesting user, +applies the live dashboard filter state, and streams the results row-by-row into +a constant-memory workbook so large dashboards never load all data at once. +""" + +from __future__ import annotations + +import logging +import os +import tempfile +from datetime import datetime, timedelta +from typing import Any + +from celery.exceptions import SoftTimeLimitExceeded +from flask import current_app, g + +from superset import db, security_manager +from superset.charts.data.dashboard_filter_context import ( + apply_dashboard_filter_context, + get_dashboard_filter_context, +) +from superset.charts.schemas import ChartDataQueryContextSchema +from superset.commands.chart.data.get_data_command import ChartDataCommand +from superset.common.chart_data import ChartDataResultFormat, ChartDataResultType +from superset.dashboards.excel_export import email +from superset.dashboards.excel_export.layout import get_charts_in_layout_order +from superset.extensions import celery_app +from superset.utils import json, s3 +from superset.utils.core import override_user +from superset.utils.excel_streaming import StreamingXlsxWriter + +logger = logging.getLogger(__name__) + + +def _chart_label(chart: Any) -> str: + """Human-readable label for a chart in the skipped-charts list.""" + return f"{chart.id} - {chart.slice_name or ''}".strip() + + +def _record_to_row(record: dict[str, Any], colnames: list[str]) -> list[Any]: + return [record.get(col) for col in colnames] + + +def _write_chart_sheets( + writer: StreamingXlsxWriter, + chart: Any, + dashboard_id: int, + active_data_mask: dict[str, Any], +) -> None: + """ + Run a single chart's query and stream its result(s) into the workbook. + + Charts may yield more than one query (e.g. mixed-series charts); each becomes + its own sheet. Raises if the chart cannot be exported, so the caller can skip + it and note it in the email. + """ + json_body = json.loads(chart.query_context) + # Override any stale saved values: we always want full JSON results. + json_body["result_format"] = ChartDataResultFormat.JSON + json_body["result_type"] = ChartDataResultType.FULL + json_body.pop("force", None) + + filter_context = get_dashboard_filter_context( + dashboard_id=dashboard_id, + chart_id=chart.id, + active_data_mask=active_data_mask, + ) + if filter_context.extra_form_data: + apply_dashboard_filter_context(json_body, filter_context.extra_form_data) + + # Jinja macros resolve form data from g.form_data; expose the saved context. + g.form_data = json_body + + query_context = ChartDataQueryContextSchema().load(json_body) + command = ChartDataCommand(query_context) + command.validate() + result = command.run() + + for index, query in enumerate(result["queries"]): + colnames = query.get("colnames") or [] + data = query.get("data") or [] + if index == 0: + name = f"{chart.id} - {chart.slice_name or ''}" + else: + name = f"{chart.id}.{index} - {chart.slice_name or ''}" + writer.add_sheet( + name, + colnames, + (_record_to_row(record, colnames) for record in data), + ) + + +def _build_workbook( + path: str, + dashboard: Any, + active_data_mask: dict[str, Any], + job_id: str, +) -> list[str]: + """Build the workbook on disk; return the list of skipped chart labels.""" + skipped: list[str] = [] + writer = StreamingXlsxWriter(path) + try: + for chart in get_charts_in_layout_order(dashboard): + if not chart.query_context: + skipped.append(_chart_label(chart)) + continue + try: + _write_chart_sheets(writer, chart, dashboard.id, active_data_mask) + except Exception: # pylint: disable=broad-except + logger.exception( + "Skipping chart %s in dashboard export %s", chart.id, job_id + ) + skipped.append(_chart_label(chart)) + + if writer.sheet_count == 0: + writer.add_summary_sheet( + "Export Summary", + ["No chart data could be exported.", *skipped], + ) + finally: + writer.close() + return skipped + + +def _send_failure_email( + user: Any, dashboard_title: str, requested_at: datetime +) -> None: + if not (user and getattr(user, "email", None)): + return Review Comment: **Suggestion:** Add a docstring to this newly added helper function to explain when it sends failure notifications and its parameters. [custom_rule] **Severity Level:** Minor ⚠️ <details> <summary><b>Why it matters? 🤔 </b></summary> This is a newly added Python function and it does not include a docstring in the final file state, so it violates the custom rule that new functions and classes should be documented inline. </details> [](https://app.codeant.ai/fix-in-ide?tool=cursor&prompt_id=32854f33a893429d9c55a05fcc3bb455&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=32854f33a893429d9c55a05fcc3bb455&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 🤖 </b></summary> ```mdx This is a comment left during a code review. **Path:** superset/tasks/export_dashboard_excel.py **Line:** 146:150 **Comment:** *Custom Rule: Add a docstring to this newly added helper function to explain when it sends failure notifications and its parameters. 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%2F41133&comment_hash=30e2b7acec6ec6fde6aff7c4d89243072a593daffbc3905a76361c4ba627bdef&reaction=like'>👍</a> | <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41133&comment_hash=30e2b7acec6ec6fde6aff7c4d89243072a593daffbc3905a76361c4ba627bdef&reaction=dislike'>👎</a> ########## tests/integration_tests/dashboards/api_tests.py: ########## @@ -3279,6 +3280,91 @@ def _base_filter(query): response_roles = [result["text"] for result in response["result"]] assert response_roles == ["Alpha"] + def test_export_xlsx_501_when_bucket_unset(self): + """Dashboard API: export_xlsx returns 501 when the S3 bucket is unset.""" + admin = self.get_user("admin") + dashboard = self.insert_dashboard("xlsx-501", None, [admin.id]) + self.login(ADMIN_USERNAME) + try: + rv = self.client.post(f"api/v1/dashboard/{dashboard.id}/export_xlsx/") + assert rv.status_code == 501 + finally: + db.session.delete(dashboard) + db.session.commit() + + @patch("superset.dashboards.api.export_dashboard_excel") + def test_export_xlsx_404_for_missing_dashboard(self, mock_task): + """Dashboard API: export_xlsx returns 404 for an unknown dashboard.""" + self.login(ADMIN_USERNAME) + with patch.dict( + "flask.current_app.config", + {"EXCEL_EXPORT_S3_BUCKET": "exports"}, + ): + rv = self.client.post("api/v1/dashboard/99999999/export_xlsx/") + assert rv.status_code == 404 + mock_task.apply_async.assert_not_called() + + @patch("superset.dashboards.api.export_dashboard_excel") Review Comment: **Suggestion:** Annotate both method parameters and return type for this newly introduced test function. [custom_rule] **Severity Level:** Minor ⚠️ <details> <summary><b>Why it matters? 🤔 </b></summary> This added test method lacks type hints on its parameters and return value. Since it is new Python code in a changed region, the typing rule applies and the violation is real. </details> [](https://app.codeant.ai/fix-in-ide?tool=cursor&prompt_id=3d368aa0ff564babb1fcf720244d8358&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=3d368aa0ff564babb1fcf720244d8358&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 🤖 </b></summary> ```mdx This is a comment left during a code review. **Path:** tests/integration_tests/dashboards/api_tests.py **Line:** 3307:3307 **Comment:** *Custom Rule: Annotate both method parameters and return type for this newly introduced test function. 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%2F41133&comment_hash=100788372fc22d6bf3d9aaad2daeffbc122e18b18ff5006360f7068a1e46b56a&reaction=like'>👍</a> | <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41133&comment_hash=100788372fc22d6bf3d9aaad2daeffbc122e18b18ff5006360f7068a1e46b56a&reaction=dislike'>👎</a> ########## tests/integration_tests/dashboards/api_tests.py: ########## @@ -3279,6 +3280,91 @@ def _base_filter(query): response_roles = [result["text"] for result in response["result"]] assert response_roles == ["Alpha"] + def test_export_xlsx_501_when_bucket_unset(self): + """Dashboard API: export_xlsx returns 501 when the S3 bucket is unset.""" + admin = self.get_user("admin") + dashboard = self.insert_dashboard("xlsx-501", None, [admin.id]) + self.login(ADMIN_USERNAME) + try: + rv = self.client.post(f"api/v1/dashboard/{dashboard.id}/export_xlsx/") + assert rv.status_code == 501 + finally: + db.session.delete(dashboard) + db.session.commit() + + @patch("superset.dashboards.api.export_dashboard_excel") Review Comment: **Suggestion:** Add parameter and return type annotations to this new patched test method to satisfy the typing requirement. [custom_rule] **Severity Level:** Minor ⚠️ <details> <summary><b>Why it matters? 🤔 </b></summary> This is a newly introduced test method with an untyped mock parameter and no return annotation. That violates the rule requiring new Python code to be fully typed. </details> [](https://app.codeant.ai/fix-in-ide?tool=cursor&prompt_id=7f61d507f6694c7d860fb2c464bca67b&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=7f61d507f6694c7d860fb2c464bca67b&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 🤖 </b></summary> ```mdx This is a comment left during a code review. **Path:** tests/integration_tests/dashboards/api_tests.py **Line:** 3295:3295 **Comment:** *Custom Rule: Add parameter and return type annotations to this new patched test method to satisfy the typing requirement. 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%2F41133&comment_hash=8c9fee509342346a9826985a0966f09a58a5e3ede56a25bb0b9271ec236ab2c0&reaction=like'>👍</a> | <a href='https://app.codeant.ai/feedback?pr_url=https%3A%2F%2Fgithub.com%2Fapache%2Fsuperset%2Fpull%2F41133&comment_hash=8c9fee509342346a9826985a0966f09a58a5e3ede56a25bb0b9271ec236ab2c0&reaction=dislike'>👎</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]
