Thanks to visit codestin.com
Credit goes to github.com

Skip to content

fix: Blob.from_string parse gcs uri with regex #1170

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

Merged
cojenco merged 2 commits into from
Oct 31, 2023
Merged

fix: Blob.from_string parse gcs uri with regex #1170

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3b7155d
fix: Blob.from_string parse storage uri with regex
cojenco Oct 20, 2023
af523d0
Merge branch 'main' into from_string
cojenco Oct 30, 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
13 changes: 7 additions & 6 deletions google/cloud/storage/blob.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,7 +134,9 @@
"Blob.download_as_string() is deprecated and will be removed in future. "
"Use Blob.download_as_bytes() instead."
)

_GS_URL_REGEX_PATTERN = re.compile(
r"(?P<scheme>gs)://(?P<bucket_name>[a-z0-9_.-]+)/(?P<object_name>.+)"
)

_DEFAULT_CHUNKSIZE = 104857600 # 1024 * 1024 B * 100 = 100 MB
_MAX_MULTIPART_SIZE = 8388608 # 8 MB
Expand Down Expand Up @@ -403,12 +405,11 @@ def from_string(cls, uri, client=None):
"""
from google.cloud.storage.bucket import Bucket

scheme, netloc, path, query, frag = urlsplit(uri)
if scheme != "gs":
match = _GS_URL_REGEX_PATTERN.match(uri)
if not match:
raise ValueError("URI scheme must be gs")

bucket = Bucket(client, name=netloc)
return cls(path[1:], bucket)
bucket = Bucket(client, name=match.group("bucket_name"))
return cls(match.group("object_name"), bucket)

def generate_signed_url(
self,
Expand Down
14 changes: 11 additions & 3 deletions tests/unit/test_blob.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5819,13 +5819,21 @@ def test_from_string_w_valid_uri(self):
from google.cloud.storage.blob import Blob

client = self._make_client()
uri = "gs://BUCKET_NAME/b"
blob = Blob.from_string(uri, client)
basic_uri = "gs://bucket_name/b"
blob = Blob.from_string(basic_uri, client)

self.assertIsInstance(blob, Blob)
self.assertIs(blob.client, client)
self.assertEqual(blob.name, "b")
self.assertEqual(blob.bucket.name, "BUCKET_NAME")
self.assertEqual(blob.bucket.name, "bucket_name")

nested_uri = "gs://bucket_name/path1/path2/b#name"
blob = Blob.from_string(nested_uri, client)

self.assertIsInstance(blob, Blob)
self.assertIs(blob.client, client)
self.assertEqual(blob.name, "path1/path2/b#name")
self.assertEqual(blob.bucket.name, "bucket_name")

def test_from_string_w_invalid_uri(self):
from google.cloud.storage.blob import Blob
Expand Down