diff --git a/requirements/base.txt b/requirements/base.txt index 30dc9c0a9187c..1e9183f479379 100644 --- a/requirements/base.txt +++ b/requirements/base.txt @@ -278,6 +278,8 @@ wtforms==2.3.3 # wtforms-json wtforms-json==0.3.3 # via apache-superset +xlsxwriter==3.0.3 + # via apache-superset # The following packages are considered to be unsafe in a requirements file: # setuptools diff --git a/setup.py b/setup.py index 0e45eb5fdb14f..0fddbfb1b0ce2 100644 --- a/setup.py +++ b/setup.py @@ -121,6 +121,7 @@ def get_git_sha() -> str: "tabulate>=0.8.9, <0.9", "typing-extensions>=4, <5", "wtforms-json", + "xlsxwriter", ], extras_require={ "athena": ["pyathena[pandas]>=2, <3"], @@ -173,8 +174,6 @@ def get_git_sha() -> str: "thumbnails": ["Pillow>=9.1.1, <10.0.0"], "vertica": ["sqlalchemy-vertica-python>=0.5.9, < 0.6"], "netezza": ["nzalchemy>=11.0.2"], - "xls": ["xlwt>=1.3.0, < 1.4"], - "xlsx": ["xlsxwriter>=3.0.0, < 3.1"], }, python_requires="~=3.8", author="Apache Software Foundation", diff --git a/superset-frontend/src/explore/components/useExploreAdditionalActionsMenu/index.jsx b/superset-frontend/src/explore/components/useExploreAdditionalActionsMenu/index.jsx index f75f102459369..f448abdeda3b7 100644 --- a/superset-frontend/src/explore/components/useExploreAdditionalActionsMenu/index.jsx +++ b/superset-frontend/src/explore/components/useExploreAdditionalActionsMenu/index.jsx @@ -41,7 +41,6 @@ const MENU_KEYS = { EXPORT_TO_CSV: 'export_to_csv', EXPORT_TO_CSV_PIVOTED: 'export_to_csv_pivoted', EXPORT_TO_JSON: 'export_to_json', - EXPORT_TO_XLS: 'export_to_xls', EXPORT_TO_XLSX: 'export_to_xlsx', DOWNLOAD_AS_IMAGE: 'download_as_image', SHARE_SUBMENU: 'share_submenu', @@ -159,29 +158,15 @@ export const useExploreAdditionalActionsMenu = ( }), [latestQueryFormData], ); - const exportXLS = useCallback( - () => - canDownloadCSV - ? exportChart({ - formData: latestQueryFormData, - ownState, - resultType: 'full', - resultFormat: 'xls', - }) - : null, - [canDownloadCSV, latestQueryFormData], - ); - const exportXLSX = useCallback( + + const exportExcel = useCallback( () => - canDownloadCSV - ? exportChart({ - formData: latestQueryFormData, - ownState, - resultType: 'full', - resultFormat: 'xlsx', - }) - : null, - [canDownloadCSV, latestQueryFormData], + exportChart({ + formData: latestQueryFormData, + resultType: 'results', + resultFormat: 'xlsx', + }), + [latestQueryFormData], ); const copyLink = useCallback(async () => { @@ -218,14 +203,9 @@ export const useExploreAdditionalActionsMenu = ( setIsDropdownVisible(false); setOpenSubmenus([]); - break; - case MENU_KEYS.EXPORT_TO_XLS: - exportXLS(); - setIsDropdownVisible(false); - setOpenSubmenus([]); break; case MENU_KEYS.EXPORT_TO_XLSX: - exportXLSX(); + exportExcel(); setIsDropdownVisible(false); setOpenSubmenus([]); break; @@ -332,18 +312,15 @@ export const useExploreAdditionalActionsMenu = ( }> {t('Export to .JSON')} - }> - {t('Export to .XLS')} - - }> - {t('Export to .XLSX')} - } > {t('Download as image')} + }> + {t('Export to Excel')} + diff --git a/superset/charts/data/api.py b/superset/charts/data/api.py index fc0f3f3a16643..0418472982fdf 100644 --- a/superset/charts/data/api.py +++ b/superset/charts/data/api.py @@ -45,12 +45,7 @@ from superset.extensions import event_logger from superset.utils.async_query_manager import AsyncQueryTokenException from superset.utils.core import create_zip, get_user_id, json_int_dttm_ser -from superset.views.base import ( - CsvResponse, - generate_download_headers, - XlsResponse, - XlsxResponse, -) +from superset.views.base import CsvResponse, generate_download_headers, XlsxResponse from superset.views.base_api import statsd_metrics if TYPE_CHECKING: @@ -355,27 +350,26 @@ def _send_chart_response( if not result["queries"]: return self.response_400(_("Empty query result")) + is_csv_format = result_format == ChartDataResultFormat.CSV + if len(result["queries"]) == 1: # return single query results data = result["queries"][0]["data"] - if result_format == ChartDataResultFormat.CSV: + if is_csv_format: return CsvResponse(data, headers=generate_download_headers("csv")) - elif result_format == ChartDataResultFormat.XLS: - return XlsResponse(data, headers=generate_download_headers("xls")) - elif result_format == ChartDataResultFormat.XLSX: - return XlsxResponse(data, headers=generate_download_headers("xlsx")) - # return multi-query results bundled as a zip file + return XlsxResponse(data, headers=generate_download_headers("xlsx")) - def _process_data(d: Any) -> Any: + # return multi-query results bundled as a zip file + def _process_data(query_data: Any) -> Any: if result_format == ChartDataResultFormat.CSV: encoding = current_app.config["CSV_EXPORT"].get("encoding", "utf-8") - return d.encode(encoding) - return d + return query_data.encode(encoding) + return query_data files = { - f"query_{idx + 1}.{result_format}": _process_data(result["data"]) - for idx, result in enumerate(result["queries"]) + f"query_{idx + 1}.{result_format}": _process_data(query["data"]) + for idx, query in enumerate(result["queries"]) } return Response( create_zip(files), diff --git a/superset/common/chart_data.py b/superset/common/chart_data.py index 1cbe982b07c2a..659a640159378 100644 --- a/superset/common/chart_data.py +++ b/superset/common/chart_data.py @@ -25,16 +25,11 @@ class ChartDataResultFormat(str, Enum): CSV = "csv" JSON = "json" - XLS = "xls" XLSX = "xlsx" - @classmethod - def excel(cls) -> Set["ChartDataResultFormat"]: - return {cls.XLS, cls.XLSX} - @classmethod def table_like(cls) -> Set["ChartDataResultFormat"]: - return {cls.CSV} | {cls.XLS, cls.XLSX} + return {cls.CSV} | {cls.XLSX} class ChartDataResultType(str, Enum): diff --git a/superset/common/query_context_processor.py b/superset/common/query_context_processor.py index f0fba43e02dc8..747b1aebcd3f1 100644 --- a/superset/common/query_context_processor.py +++ b/superset/common/query_context_processor.py @@ -452,16 +452,14 @@ def get_data(self, df: pd.DataFrame) -> Union[str, List[Dict[str, Any]]]: verbose_map = self._qc_datasource.data.get("verbose_map", {}) if verbose_map: df.columns = [verbose_map.get(column, column) for column in columns] - if self._query_context.result_type == ChartDataResultFormat.CSV: + + result = None + if self._query_context.result_format == ChartDataResultFormat.CSV: result = csv.df_to_escaped_csv( df, index=include_index, **config["CSV_EXPORT"] ) - else: - result = excel.df_to_excel( - df, - excel_format=self._query_context.result_format, - **config["EXCEL_EXPORT"], - ) + elif self._query_context.result_format == ChartDataResultFormat.XLSX: + result = excel.df_to_excel(df, **config["EXCEL_EXPORT"]) return result or "" return df.to_dict(orient="records") diff --git a/superset/utils/excel.py b/superset/utils/excel.py index 595e3276f0c77..1f68031b6497b 100644 --- a/superset/utils/excel.py +++ b/superset/utils/excel.py @@ -1,18 +1,29 @@ +# 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 io from typing import Any import pandas as pd -from superset.common.chart_data import ChartDataResultFormat - -def df_to_excel( - df: pd.DataFrame, - excel_format: ChartDataResultFormat = ChartDataResultFormat.XLSX, - **kwargs: Any -) -> bytes: +def df_to_excel(df: pd.DataFrame, **kwargs: Any) -> Any: output = io.BytesIO() - engine = "xlwt" if excel_format == ChartDataResultFormat.XLS else "xlsxwriter" - with pd.ExcelWriter(output, engine=engine) as writer: + # pylint: disable=abstract-class-instantiated + with pd.ExcelWriter(output, engine="xlsxwriter") as writer: df.to_excel(writer, **kwargs) + return output.getvalue() diff --git a/superset/views/base.py b/superset/views/base.py index eb01c50c0283a..8eb7e58693938 100644 --- a/superset/views/base.py +++ b/superset/views/base.py @@ -666,15 +666,6 @@ class CsvResponse(Response): default_mimetype = "text/csv" -class XlsResponse(Response): - """ - Override Response to use xls mimetype - """ - - charset = "utf-8" - default_mimetype = "application/vnd.ms-excel" - - class XlsxResponse(Response): """ Override Response to use xlsx mimetype diff --git a/superset/views/core.py b/superset/views/core.py index cfa5ab2218503..dfe57c7e50f24 100755 --- a/superset/views/core.py +++ b/superset/views/core.py @@ -152,7 +152,6 @@ json_errors_response, json_success, validate_sqlatable, - XlsResponse, XlsxResponse, ) from superset.views.sql_lab.schemas import SqlJsonPayloadSchema @@ -497,12 +496,6 @@ def generate_json( viz_obj.get_csv(), headers=generate_download_headers("csv") ) - if response_type == ChartDataResultFormat.XLS: - return XlsResponse( - viz_obj.get_excel(ChartDataResultFormat(response_type)), - headers=generate_download_headers("xls"), - ) - if response_type == ChartDataResultFormat.XLSX: return XlsxResponse( viz_obj.get_excel(ChartDataResultFormat(response_type)), diff --git a/tests/integration_tests/charts/data/api_tests.py b/tests/integration_tests/charts/data/api_tests.py index e9b4f4d1c617d..48ce6cc91d2ab 100644 --- a/tests/integration_tests/charts/data/api_tests.py +++ b/tests/integration_tests/charts/data/api_tests.py @@ -246,44 +246,52 @@ def test_with_query_result_type__200(self): assert rv.status_code == 200 @pytest.mark.usefixtures("load_birth_names_dashboard_with_slices") - @pytest.mark.parametrize("result_format", ["csv", "xls", "xlsx"]) - def test_empty_request_with_table_like_result_format(self, result_format): + def test_empty_request_with_csv_result_format(self): """ - Chart data API: Test empty chart data with table like result format + Chart data API: Test empty chart data with CSV result format """ - self.query_context_payload["result_format"] = result_format + self.query_context_payload["result_format"] = "csv" self.query_context_payload["queries"] = [] rv = self.post_assert_metric(CHART_DATA_URI, self.query_context_payload, "data") assert rv.status_code == 400 @pytest.mark.usefixtures("load_birth_names_dashboard_with_slices") - @pytest.mark.parametrize( - "result_format,mimetype", - [ - ("csv", "text/csv"), - ("xls", "application/vnd.ms-excel"), - ( - "xlsx", - "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", - ) - ] - ) - def test_with_table_like_result_format(self, result_format, mimetype): + def test_empty_request_with_excel_result_format(self): + """ + Chart data API: Test empty chart data with Excel result format + """ + self.query_context_payload["result_format"] = "xlsx" + self.query_context_payload["queries"] = [] + rv = self.post_assert_metric(CHART_DATA_URI, self.query_context_payload, "data") + assert rv.status_code == 400 + + @pytest.mark.usefixtures("load_birth_names_dashboard_with_slices") + def test_with_csv_result_format(self): """ - Chart data API: Test chart data with table like result format + Chart data API: Test chart data with CSV result format """ - self.query_context_payload["result_format"] = result_format + self.query_context_payload["result_format"] = "csv" + rv = self.post_assert_metric(CHART_DATA_URI, self.query_context_payload, "data") + assert rv.status_code == 200 + assert rv.mimetype == "text/csv" + + @pytest.mark.usefixtures("load_birth_names_dashboard_with_slices") + def test_with_excel_result_format(self): + """ + Chart data API: Test chart data with Excel result format + """ + self.query_context_payload["result_format"] = "xlsx" + mimetype = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet" rv = self.post_assert_metric(CHART_DATA_URI, self.query_context_payload, "data") assert rv.status_code == 200 assert rv.mimetype == mimetype @pytest.mark.usefixtures("load_birth_names_dashboard_with_slices") - @pytest.mark.parametrize("result_format", ["csv", "xls", "xlsx"]) - def test_with_multi_query_table_like_result_format(self, result_format): + def test_with_multi_query_csv_result_format(self): """ - Chart data API: Test chart data with multi-query table like result format + Chart data API: Test chart data with multi-query CSV result format """ - self.query_context_payload["result_format"] = result_format + self.query_context_payload["result_format"] = "csv" self.query_context_payload["queries"].append( self.query_context_payload["queries"][0] ) @@ -291,22 +299,43 @@ def test_with_multi_query_table_like_result_format(self, result_format): assert rv.status_code == 200 assert rv.mimetype == "application/zip" zipfile = ZipFile(BytesIO(rv.data), "r") - assert zipfile.namelist() == [ - f"query_1.{result_format}", - f"query_2.{result_format}", - ] + assert zipfile.namelist() == ["query_1.csv", "query_2.csv"] @pytest.mark.usefixtures("load_birth_names_dashboard_with_slices") - @pytest.mark.parametrize("result_format", ["csv", "xls", "xlsx"]) - def test_with_table_like_result_format_when_actor_not_permitted_for__403( - self, result_format - ): + def test_with_multi_query_excel_result_format(self): + """ + Chart data API: Test chart data with multi-query Excel result format + """ + self.query_context_payload["result_format"] = "xlsx" + self.query_context_payload["queries"].append( + self.query_context_payload["queries"][0] + ) + rv = self.post_assert_metric(CHART_DATA_URI, self.query_context_payload, "data") + assert rv.status_code == 200 + assert rv.mimetype == "application/zip" + zipfile = ZipFile(BytesIO(rv.data), "r") + assert zipfile.namelist() == ["query_1.xlsx", "query_2.xlsx"] + + @pytest.mark.usefixtures("load_birth_names_dashboard_with_slices") + def test_with_csv_result_format_when_actor_not_permitted_for_csv__403(self): + """ + Chart data API: Test chart data with CSV result format + """ + self.logout() + self.login(username="gamma_no_csv") + self.query_context_payload["result_format"] = "csv" + + rv = self.post_assert_metric(CHART_DATA_URI, self.query_context_payload, "data") + assert rv.status_code == 403 + + @pytest.mark.usefixtures("load_birth_names_dashboard_with_slices") + def test_with_excel_result_format_when_actor_not_permitted_for_excel__403(self): """ - Chart data API: Test chart data with table like result format + Chart data API: Test chart data with Excel result format """ self.logout() self.login(username="gamma_no_csv") - self.query_context_payload["result_format"] = result_format + self.query_context_payload["result_format"] = "xlsx" rv = self.post_assert_metric(CHART_DATA_URI, self.query_context_payload, "data") assert rv.status_code == 403