Skip to content

[Storage] Change content iterating in _download_async.py, add decompression live tests against compressed dataset #39755

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

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

[Storage] Change content iterating in _download_async.py, add decompression live tests against compressed dataset #39755

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
7 changes: 5 additions & 2 deletions sdk/storage/azure-storage-blob/azure/storage/blob/aio/_download_async.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,8 +46,11 @@
async def process_content(data: Any, start_offset: int, end_offset: int, encryption: Dict[str, Any]) -> bytes:
if data is None:
raise ValueError("Response cannot be None.")
await data.response.load_body()
content = cast(bytes, data.response.body())
if not data.response.is_stream_consumed:
Copy link
Member Author

@vincenttran-msft vincenttran-msft Apr 10, 2025 •
edited
Loading

Choose a reason for hiding this comment

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

Not sure if this exists on old transports... --> therefore may need to do an attribute check instead (but start off with seeing if there is any other way without attribute check)

content = b"".join([d async for d in data])
Copy link
Member Author

Choose a reason for hiding this comment

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

This is a good start-- then test against the 3 transports, then when those work test validate_content

else:
await data.response.read()
content = cast(bytes, data.response.content)
if encryption.get('key') is not None or encryption.get('resolver') is not None:
try:
return decrypt_blob(
Expand Down
23 changes: 23 additions & 0 deletions sdk/storage/azure-storage-blob/tests/test_common_blob.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3531,4 +3531,27 @@ def test_upload_blob_partial_stream_chunked(self, **kwargs):
result = blob.download_blob().readall()
assert result == data[:length]

@pytest.mark.live_test_only
@BlobPreparer()
def test_download_blob_compressed_data_with_decompress(self, **kwargs):
storage_account_name = kwargs.pop("storage_account_name")
storage_account_key = kwargs.pop("storage_account_key")

# Arrange
self._setup(storage_account_name, storage_account_key)
blob_name = self._get_blob_reference()
blob = self.bsc.get_blob_client(self.container_name, blob_name)
compressed_data = b'\x1f\x8b\x08\x00\x00\x00\x00\x00\x00\xff\xcaH\xcd\xc9\xc9WH+\xca\xcfUH\xaf\xca,\x00\x00\x00\x00\xff\xff\x03\x00d\xaa\x8e\xb5\x0f\x00\x00\x00'
decompressed_data = b"hello from gzip"
content_settings = ContentSettings(content_encoding='gzip')

# Act / Assert
blob.upload_blob(data=compressed_data, content_settings=content_settings, overwrite=True)

result = blob.download_blob(decompress=True).readall()
assert result == decompressed_data

result = blob.download_blob(decompress=False).readall()
assert result == compressed_data

# ------------------------------------------------------------------------------
25 changes: 25 additions & 0 deletions sdk/storage/azure-storage-blob/tests/test_common_blob_async.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3510,4 +3510,29 @@ async def test_mock_transport_with_content_validation(self, **kwargs):

blob_data = await (await blob_client.download_blob(validate_content=True)).read()
assert blob_data == b"Hello Async World!" # data is fixed by mock transport

@pytest.mark.live_test_only
@BlobPreparer()
async def test_download_blob_compressed_data_with_decompress(self, **kwargs):
storage_account_name = kwargs.pop("storage_account_name")
storage_account_key = kwargs.pop("storage_account_key")

# Arrange
await self._setup(storage_account_name, storage_account_key)
blob_name = self._get_blob_reference()
blob = self.bsc.get_blob_client(self.container_name, blob_name)
compressed_data = b'\x1f\x8b\x08\x00\x00\x00\x00\x00\x00\xff\xcaH\xcd\xc9\xc9WH+\xca\xcfUH\xaf\xca,\x00\x00\x00\x00\xff\xff\x03\x00d\xaa\x8e\xb5\x0f\x00\x00\x00'
decompressed_data = b"hello from gzip"
content_settings = ContentSettings(content_encoding='gzip')

# Act / Assert
await blob.upload_blob(data=compressed_data, content_settings=content_settings, overwrite=True)

downloaded = await blob.download_blob(decompress=True)
result = await downloaded.readall()
assert result == decompressed_data

downloaded = await blob.download_blob(decompress=False)
result = await downloaded.readall()
assert result == compressed_data
# ------------------------------------------------------------------------------