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

fix windows path (#660) #673

Merged
merged 10 commits into from
Jul 3, 2024
Merged

fix windows path (#660) #673

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
de5d60f
fix windows path
parthban-db Jun 11, 2024
16dc404
added an extra variable for system specific path to use pathlib.Path …
parthban-db Jun 12, 2024
bf00c9b
added test for local path mkdir function
parthban-db Jun 12, 2024
647de83
added comment for why we needs two paths
parthban-db Jun 12, 2024
3b4e22e
added commands for venv activation according to OS
parthban-db Jun 17, 2024
bc276ae
added _init_ implementations in each child class of _Path
parthban-db Jun 17, 2024
5dab757
test case added for dbfs path not changing according to OS
parthban-db Jun 17, 2024
be8ebf7
add test for Volumes
parthban-db Jul 2, 2024
43db8c7
format
parthban-db Jul 2, 2024
67d22ef
Merge branch 'main' into fix-windows-path
parthban-db Jul 3, 2024
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
20 changes: 11 additions & 9 deletions databricks/sdk/mixins/files.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -267,7 +267,9 @@ def __repr__(self) -> str:
class _Path(ABC):

def __init__(self, path: str):
self._path = pathlib.Path(str(path).replace('dbfs:', '').replace('file:', ''))
"""Posix Path for API Compatibility in windows and OS Specific Path(System Path) for using pathlib.Path functions."""
self._path = pathlib.PurePosixPath(str(path).replace('dbfs:', '').replace('file:', ''))
self._system_path = pathlib.Path(self._path)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It'd be good to add a comment explaining why we need self._path to be PurePosixPath and why we need self._system_path


@property
def is_local(self) -> bool:
Expand Down Expand Up @@ -337,18 +339,18 @@ def child(self, path: str) -> Self:
return _LocalPath(str(self._path / path))

def _is_dir(self) -> bool:
return self._path.is_dir()
return self._system_path.is_dir()

def mkdir(self):
self._path.mkdir(mode=0o755, parents=True, exist_ok=True)
self._system_path.mkdir(mode=0o755, parents=True, exist_ok=True)

def exists(self) -> bool:
return self._path.exists()
return self._system_path.exists()

def open(self, *, read=False, write=False, overwrite=False):
# make local fs follow the similar semantics as DBFS
self._path.parent.mkdir(mode=0o755, parents=True, exist_ok=True)
return self._path.open(mode='wb' if overwrite else 'rb' if read else 'xb')
self._system_path.parent.mkdir(mode=0o755, parents=True, exist_ok=True)
return self._system_path.open(mode='wb' if overwrite else 'rb' if read else 'xb')

def list(self, recursive=False) -> Generator[files.FileInfo, None, None]:
if not self.is_dir:
Expand All @@ -359,7 +361,7 @@ def list(self, recursive=False) -> Generator[files.FileInfo, None, None]:
modification_time=int(st.st_mtime_ns / 1e6),
)
return
queue = deque([self._path])
queue = deque([self._system_path])
while queue:
path = queue.popleft()
for leaf in path.iterdir():
Expand All @@ -379,12 +381,12 @@ def delete(self, *, recursive=False):
if recursive:
for leaf in self.list(recursive=True):
_LocalPath(leaf.path).delete()
self._path.rmdir()
self._system_path.rmdir()
else:
kw = {}
if sys.version_info[:2] > (3, 7):
kw['missing_ok'] = True
self._path.unlink(**kw)
self._system_path.unlink(**kw)

def __repr__(self) -> str:
return f'<_LocalPath {self._path}>'
Expand Down
8 changes: 8 additions & 0 deletions tests/test_dbfs_mixins.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,3 +70,11 @@ def test_fs_path_invalid(config):
with pytest.raises(ValueError) as e:
dbfs_ext._path('s3://path/to/file')
assert 'unsupported scheme "s3"' in str(e.value)


def test_dbfs_local_path_mkdir(config, tmp_path):
from databricks.sdk import WorkspaceClient

w = WorkspaceClient(config=config)
w.dbfs._path(f'file:{tmp_path}/test_dir').mkdir()
assert w.dbfs.exists(f'file:{tmp_path}/test_dir')
Loading