Skip to content
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

Jump to bottom

GH-37555: [Python] Update get_file_info_selector to ignore base directory #37558

Merged
merged 8 commits into from
Sep 14, 2023
Merged

GH-37555: [Python] Update get_file_info_selector to ignore base directory #37558

Changes from 2 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
66221fa
Update tests
AlenkaF Sep 5, 2023
e23b8fe
Two more missing test updates
AlenkaF Sep 5, 2023
5d5183d
Restore the tests and update get_file_info_selector in FSSpecHandler
AlenkaF Sep 11, 2023
ed54953
Add back an empty line in the tests
AlenkaF Sep 11, 2023
f3d35fe
Change code in get_file_info_selector to read with start/end
AlenkaF Sep 12, 2023
6796b99
Use strip instead of start/end
AlenkaF Sep 13, 2023
f8e133f
Add a test for issue 36983
AlenkaF Sep 13, 2023
1ab5f00
Remove the test for issue 36983
AlenkaF Sep 14, 2023
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
18 changes: 10 additions & 8 deletions python/pyarrow/tests/test_fs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -703,6 +703,10 @@ def test_get_file_info_with_selector(fs, pathfn):
# on the s3fs/fsspec version combo, it includes the base_dir
# (https://github.com/dask/s3fs/issues/393)
assert (len(infos) == 4) or (len(infos) == 5)
elif fs.type_name in ["py::fsspec+file", 'py::fsspec+memory']:
# fsspec also lists root dir
# GH-37555
AlenkaF marked this conversation as resolved.
Show resolved Hide resolved
assert len(infos) == 6
else:
assert len(infos) == 5

Expand All @@ -713,9 +717,9 @@ def test_get_file_info_with_selector(fs, pathfn):
elif (info.path.rstrip("/").endswith(dir_a) or
info.path.rstrip("/").endswith(dir_b)):
assert info.type == FileType.Directory
elif (fs.type_name == "py::fsspec+s3" and
elif ("py::fsspec" in fs.type_name and
info.path.rstrip("/").endswith("selector-dir")):
# s3fs can include base dir, see above
# fsspec can include base dir, see above
assert info.type == FileType.Directory
else:
raise ValueError('unexpected path {}'.format(info.path))
Expand All @@ -725,12 +729,10 @@ def test_get_file_info_with_selector(fs, pathfn):
selector = FileSelector(base_dir, recursive=False)

infos = fs.get_file_info(selector)
if fs.type_name == "py::fsspec+s3":
# s3fs only lists directories if they are not empty
# + for s3fs 0.5.2 all directories are dropped because of buggy
# side-effect of previous find() call
# (https://github.com/dask/s3fs/issues/410)
assert (len(infos) == 3) or (len(infos) == 2)
if fs.type_name in ["py::fsspec+file", 'py::fsspec+memory']:
# fsspec also lists root dir
# GH-37555
assert len(infos) == 5
else:
assert len(infos) == 4

Expand Down
Loading