remote/sqlite-utils
1
0
Fork 0
mirror of https://github.com/simonw/sqlite-utils.git synced 2026-10-24 02:07:08 +02:00
Code Issues Projects Releases Packages Wiki Activity

Preserve carriage returns in quoted CSV/TSV fields (#895)

Browse source 
When reading CSV or TSV files through rows_from_file() or the CLI insert command, io.TextIOWrapper defaulted to universal-newline mode (newline=None), causing carriage returns (\r\n or lone \r) embedded inside quoted fields to be silently translated to \n before csv.reader could process them.

Setting newline='' in TextIOWrapper preserves carriage returns in quoted fields according to the Python standard library csv module specification.

Fixes #895
This commit is contained in:
agustin18 2026-10-03 23:08:20 +00:00
commit c27092220d
4 changed files with 49 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

15
tests/test_cli_insert.py
View file

@ -235,6 +235,21 @@ def test_insert_csv_tsv(content, options, db_path, tmpdir):
assert [{"foo": "1", "bar": "2", "baz": "cat,dog"}] == list(db.table("data").rows)
@pytest.mark.parametrize("fmt_opt", (["--csv"], ["--tsv"]))
def test_insert_csv_tsv_preserves_carriage_returns_in_quoted_fields(fmt_opt, db_path):
delimiter = "\t" if "--tsv" in fmt_opt else ","
content = f'id{delimiter}v\r\n1{delimiter}"line1\r\nline2"\r\n'
result = CliRunner().invoke(
cli.cli,
["insert", db_path, "data", "-"] + fmt_opt + ["--no-detect-types"],
catch_exceptions=False,
input=content.encode("utf-8"),
)
assert result.exit_code == 0
db = Database(db_path)
assert list(db.table("data").rows) == [{"id": "1", "v": "line1\r\nline2"}]
@pytest.mark.parametrize("empty_null", (True, False))
def test_insert_csv_empty_null(db_path, empty_null):
options = ["--csv", "--no-detect-types"]