Skip to content
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

Jump to bottom

fix: read_csv for empty lines #11924

Merged
merged 3 commits into from
Oct 22, 2023
Merged

fix: read_csv for empty lines #11924

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
4041636
Fix csv reader
uchiiii Oct 21, 2023
5a19c14
Format
uchiiii Oct 21, 2023
27811d3
Remove print and modify
uchiiii Oct 22, 2023
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: 4 additions & 0 deletions crates/polars-io/src/csv/utils.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -350,6 +350,10 @@ pub fn infer_file_schema_inner(
// keep track so that we can determine the amount of bytes read
end_ptr = line.as_ptr() as usize + line.len();

if line.is_empty() {
continue;
}

if let Some(c) = comment_char {
// line is a comment -> skip
if line[0] == c {
Expand Down
24 changes: 24 additions & 0 deletions py-polars/tests/unit/io/test_csv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -546,6 +546,30 @@ def test_empty_bytes() -> None:
assert_frame_equal(df, pl.DataFrame())


def test_empty_line_with_single_column() -> None:
df = pl.read_csv(
b"a\n\nb\n",
new_columns=["A"],
has_header=False,
comment_char="#",
use_pyarrow=False,
)
expected = pl.DataFrame({"A": ["a", None, "b"]})
assert_frame_equal(df, expected)


def test_empty_line_with_multiple_columns() -> None:
df = pl.read_csv(
b"a,b\n\nc,d\n",
new_columns=["A", "B"],
has_header=False,
comment_char="#",
use_pyarrow=False,
)
expected = pl.DataFrame({"A": ["a", "c"], "B": ["b", "d"]})
assert_frame_equal(df, expected)


def test_csv_quote_char() -> None:
expected = pl.DataFrame(
[
Expand Down