Skip to content

fix(decoder): GzipDecoder fallback should decompress when headers lack gzip content type (AI-Triage PR) #895

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
devin-ai-integration wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

fix(decoder): GzipDecoder fallback should decompress when headers lack gzip content type (AI-Triage PR) #895

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
2 changes: 1 addition & 1 deletion airbyte_cdk/sources/declarative/parsers/model_to_component_factory.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2642,7 +2642,7 @@ def create_gzip_decoder(
return CompositeRawDecoder.by_headers(
[({"Content-Encoding", "Content-Type"}, _compressed_response_types, gzip_parser)],
stream_response=True,
fallback_parser=gzip_parser.inner_parser,
fallback_parser=gzip_parser,
)

@staticmethod
Expand Down
20 changes: 20 additions & 0 deletions unit_tests/sources/declarative/decoders/test_composite_decoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -332,6 +332,26 @@ def test_composite_raw_decoder_csv_parser_without_mocked_response():
thread.join(timeout=5) # ensure thread is cleaned up


def test_gzip_decoder_by_headers_fallback_decompresses_when_no_gzip_header(requests_mock):
requests_mock.register_uri(
"GET",
"https://airbyte.io/",
content=generate_csv(should_compress=True),
headers={"Content-Type": "binary/octet-stream"},
)
response = requests.get("https://airbyte.io/", stream=True)

gzip_parser = GzipParser(inner_parser=CsvParser())
composite_raw_decoder = CompositeRawDecoder.by_headers(
[({"Content-Encoding", "Content-Type"}, {"gzip", "application/gzip"}, gzip_parser)],
stream_response=True,
fallback_parser=gzip_parser,
)
parsed_records = list(composite_raw_decoder.decode(response))
assert len(parsed_records) == 3
assert parsed_records[0] == {"id": "1", "name": "John", "age": "28"}


def test_given_response_already_consumed_when_decode_then_no_data_is_returned(requests_mock):
requests_mock.register_uri(
"GET", "https://airbyte.io/", content=json.dumps({"test": "test"}).encode()
Expand Down
Loading