fix: datetime with timezone excel export (#25318)

Co-authored-by: Michael S. Molina <70410625+michael-s-molina@users.noreply.github.com>
This commit is contained in:
Beto Dealmeida 2023-09-21 13:11:59 -07:00 committed by GitHub
parent 5b3910db97
commit 5ebcd2a5f6
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 36 additions and 0 deletions

View File

@ -22,6 +22,11 @@ import pandas as pd
def df_to_excel(df: pd.DataFrame, **kwargs: Any) -> Any:
output = io.BytesIO()
# timezones are not supported
for column in df.select_dtypes(include=["datetimetz"]).columns:
df[column] = df[column].astype(str)
# pylint: disable=abstract-class-instantiated
with pd.ExcelWriter(output, engine="xlsxwriter") as writer:
df.to_excel(writer, **kwargs)

View File

@ -0,0 +1,31 @@
# 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.
from datetime import datetime, timezone
import pandas as pd
from superset.utils.excel import df_to_excel
def test_timezone_conversion() -> None:
"""
Test that columns with timezones are converted to a string.
"""
df = pd.DataFrame({"dt": [datetime(2023, 1, 1, 0, 0, tzinfo=timezone.utc)]})
contents = df_to_excel(df)
assert pd.read_excel(contents)["dt"][0] == "2023-01-01 00:00:00+00:00"