Skip to content

fix(file-based): populate failure_type, internal_message, and exception on CSV encoding error #1053

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
+12 −7
Draft

fix(file-based): populate failure_type, internal_message, and exception on CSV encoding error #1053

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 airbyte_cdk/sources/file_based/file_types/csv_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,9 +73,12 @@ def read_data(
headers, raw_headers = self._read_and_validate_headers(
fp, config_format, dialect_name
)
except UnicodeError:
except UnicodeError as e:
raise AirbyteTracedException(
message=f"{FileBasedSourceError.ENCODING_ERROR.value} Expected encoding: {config_format.encoding}",
message=f"File contains bytes that cannot be decoded with the configured {config_format.encoding} encoding.",
internal_message=str(e),
failure_type=FailureType.config_error,
exception=e,
)

rows_to_skip = (
Expand Down
12 changes: 7 additions & 5 deletions unit_tests/sources/file_based/file_types/test_csv_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -648,15 +648,17 @@ def test_read_data_with_encoding_error(self) -> None:
self._stream_reader.open_file.return_value = (
CsvFileBuilder().with_data(["something"]).build()
)
self._csv_reader._read_and_validate_headers = Mock(
side_effect=UnicodeDecodeError("encoding", b"", 0, 1, "reason")
)
unicode_error = UnicodeDecodeError("utf-8", b"\xff", 0, 1, "invalid start byte")
self._csv_reader._read_and_validate_headers = Mock(side_effect=unicode_error)

with pytest.raises(AirbyteTracedException) as ate:
data_generator = self._read_data()
assert len(list(data_generator)) == 0
list(data_generator)

assert "encoding" in ate.value.message
assert "utf8" in ate.value.message
assert ate.value.failure_type == FailureType.config_error
assert ate.value.internal_message == str(unicode_error)
assert ate.value._exception is unicode_error
assert self._csv_reader._read_and_validate_headers.called

def _read_data(self) -> Generator[Dict[str, str], None, None]:
Expand Down
Loading