Skip to content

Fix dataframe CSV tests on Windows #39563

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Guflly wants to merge 1 commit into
base: master
Choose a base branch
from
+9 −8
Open

Fix dataframe CSV tests on Windows #39563

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion sdks/python/apache_beam/dataframe/io.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -736,7 +736,7 @@ def open(self, file_handle):
self.empty = self.header = self.footer = None
if not self.binary:
file_handle = TextIOWrapper(
file_handle, encoding=self.kwargs.get("encoding", None))
file_handle, encoding=self.kwargs.get("encoding", None), newline='')
self.file_handle = file_handle

def write_to(self, df, file_handle=None):
Expand Down
15 changes: 8 additions & 7 deletions sdks/python/apache_beam/dataframe/io_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,6 @@
import importlib
import math
import os
import platform
import shutil
import tempfile
import typing
Expand Down Expand Up @@ -65,9 +64,6 @@ class MyRow(typing.NamedTuple):
value: int


@unittest.skipIf(
platform.system() == 'Windows',
'https://github.com/apache/beam/issues/20642')
class IOTest(unittest.TestCase):
def setUp(self):
self._temp_roots = []
Expand Down Expand Up @@ -431,6 +427,11 @@ def test_file_not_found(self):

def test_windowed_write(self):
output = self.temp_dir()

def no_colon_file_naming(*args):
file_name = fileio.default_file_naming('out.csv')(*args)
return file_name.replace(':', '_')

with beam.Pipeline() as p:
pc = (
p | beam.Create([MyRow(timestamp=i, value=i % 3) for i in range(20)])
Expand All @@ -440,18 +441,18 @@ def test_windowed_write(self):
beam.window.FixedWindows(10)).with_output_types(MyRow))

deferred_df = convert.to_dataframe(pc)
deferred_df.to_csv(output + 'out.csv', index=False)
deferred_df.to_csv(output, file_naming=no_colon_file_naming, index=False)

first_window_files = (
f'{output}out.csv-'
f'{datetime.utcfromtimestamp(0).isoformat()}*')
f'{datetime.utcfromtimestamp(0).isoformat().replace(":", "_")}*')
self.assertCountEqual(
['timestamp,value'] + [f'{i},{i % 3}' for i in range(10)],
set(self.read_all_lines(first_window_files, delete=True)))

second_window_files = (
f'{output}out.csv-'
f'{datetime.utcfromtimestamp(10).isoformat()}*')
f'{datetime.utcfromtimestamp(10).isoformat().replace(":", "_")}*')
self.assertCountEqual(
['timestamp,value'] + [f'{i},{i%3}' for i in range(10, 20)],
set(self.read_all_lines(second_window_files, delete=True)))
Expand Down
Loading