Skip to content

Chunked HTTP get to avoid memory issues #761

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
merged 3 commits into from
Jul 14, 2025
Merged

Chunked HTTP get to avoid memory issues #761

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f60ae41
WIP
maddenp-cu Jul 11, 2025
765fc65
WIP
maddenp-cu Jul 11, 2025
4c981f1
Merge branch 'main' into chunked-http-get
maddenp-cu Jul 14, 2025
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
11 changes: 6 additions & 5 deletions src/uwtools/tests/utils/test_tasks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,9 +112,9 @@ def test_utils_tasks_filecopy__source_http(code, expected, src, tmp_path):
with patch.object(tasks, "requests") as requests:
response = requests.get()
response.status_code = code
response.content = b"data"
response.iter_content.return_value = iter([b"f", b"o", b"o"])
tasks.filecopy(src=src, dst=dst)
requests.get.assert_called_with(src, allow_redirects=True, timeout=3)
requests.get.assert_called_with(src, allow_redirects=True, stream=True, timeout=3)
assert dst.is_file() is expected


Expand Down Expand Up @@ -238,12 +238,13 @@ def test_utils_tasks_filecopy_http(ready_task, tmp_path):
patch.object(tasks.requests, "get") as get,
patch.object(tasks, "existing_http", wraps=ready_task) as existing_http,
):
response = Mock(status_code=200, content=b"data")
response = Mock(status_code=200)
response.iter_content.return_value = iter([b"f", b"o", b"o"])
get.return_value = response
tasks.filecopy_http(url=url, dst=dst)
existing_http.assert_called_once_with(url)
get.assert_called_once_with(url, allow_redirects=True, timeout=3)
assert dst.exists()
get.assert_called_once_with(url, allow_redirects=True, stream=True, timeout=3)
assert dst.read_bytes() == b"foo"


def test_utils_tasks_filecopy_local(tmp_path):
Expand Down
6 changes: 4 additions & 2 deletions src/uwtools/utils/tasks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -182,9 +182,11 @@ def filecopy_http(url: str, dst: Path, check: bool = True):
yield asset(dst, dst.is_file)
yield existing_http(url) if check else None
dst.parent.mkdir(parents=True, exist_ok=True)
response = requests.get(url, allow_redirects=True, timeout=3)
response = requests.get(url, allow_redirects=True, stream=True, timeout=3)
if (code := response.status_code) == HTTPStatus.OK:
dst.write_bytes(response.content)
with dst.open(mode="wb") as f:
for chunk in response.iter_content(chunk_size=8192):
f.write(chunk)
else:
log.error("Could not get '%s', HTTP status was: %s", url, code)

Expand Down