Skip to content

fix(csv-parser): Parse CSVs with inferred schema when column names contain leading/trailing whitespace #718

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

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
+16 −2
Open

fix(csv-parser): Parse CSVs with inferred schema when column names contain leading/trailing whitespace #718

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
144d937
strip whitespace
eferm Aug 21, 2025
f207fd8
add unit test
eferm Aug 21, 2025
571a46f
rename
eferm Aug 21, 2025
5f6b9a8
remove unnecessary strip
eferm Aug 21, 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
4 changes: 2 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 @@ -128,7 +128,7 @@ def _get_headers(self, fp: IOBase, config_format: CsvFormat, dialect_name: str)
# Then read the header
self._skip_rows(fp, config_format.skip_rows_before_header)
reader = csv.reader(fp, dialect=dialect_name) # type: ignore
headers = list(next(reader))
headers = [header.strip() for header in next(reader)]

fp.seek(0)
return headers
Expand Down Expand Up @@ -209,7 +209,7 @@ async def infer_schema(
failure_type=FailureType.config_error,
)
schema = {
header.strip(): {"type": type_inferred.infer()}
header: {"type": type_inferred.infer()}
for header, type_inferred in type_inferrer_by_field.items()
}
data_generator.close()
Expand Down
14 changes: 14 additions & 0 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 @@ -658,6 +658,20 @@ def test_read_data_with_encoding_error(self) -> None:
assert "encoding" in ate.value.message
assert self._csv_reader._get_headers.called

def test_read_data_strips_leading_and_trailing_whitespace_in_header(self) -> None:
self._stream_reader.open_file.return_value = (
CsvFileBuilder()
.with_data(
[
"header1 ,\theader2",
"1,2",
]
)
.build()
)
data_generator = self._read_data()
assert list(data_generator) == [{"header1": "1", "header2": "2"}]

def _read_data(self) -> Generator[Dict[str, str], None, None]:
data_generator = self._csv_reader.read_data(
self._config,
Expand Down
Loading