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(rust, python): csv, read escaped "" as missing #5912

Merged
merged 2 commits into from
Dec 27, 2022
Merged

fix(rust, python): csv, read escaped "" as missing #5912

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
31e0874
fix(rust, python): csv, read escaped "" as missing
ritchie46 Dec 27, 2022
1a6b050
dedent
ritchie46 Dec 27, 2022
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
13 changes: 7 additions & 6 deletions polars/polars-io/src/csv/buffer.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -95,7 +95,7 @@ where
let bytes = skip_whitespace(bytes);
return self.parse_bytes(bytes, ignore_errors, needs_escaping);
}
if ignore_errors {
if ignore_errors || bytes.is_empty() {
self.append_null()
} else {
return Err(PolarsError::ComputeError("".into()));
Expand Down Expand Up @@ -349,16 +349,17 @@ impl ParsedBuffer for BooleanChunkedBuilder {
&mut self,
bytes: &[u8],
ignore_errors: bool,
_needs_escaping: bool,
needs_escaping: bool,
) -> PolarsResult<()> {
let bytes = if needs_escaping {
&bytes[1..bytes.len() - 1]
} else {
bytes
};
if bytes.eq_ignore_ascii_case(b"false") {
self.append_value(false);
} else if bytes.eq_ignore_ascii_case(b"true") {
self.append_value(true);
} else if bytes.eq_ignore_ascii_case(b"\"false\"") {
self.append_value(false);
} else if bytes.eq_ignore_ascii_case(b"\"true\"") {
self.append_value(true);
} else if ignore_errors || bytes.is_empty() {
self.append_null();
} else {
Expand Down
22 changes: 22 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 @@ -961,3 +961,25 @@ def test_csv_single_categorical_null() -> None:

assert df.dtypes == [pl.Utf8, pl.Categorical, pl.Utf8]
assert df.to_dict(False) == {"x": ["A"], "y": [None], "z": ["A"]}


def test_csv_quoted_missing() -> None:
csv = '''"col1"|"col2"|"col3"|"col4"
"0"|"Free text with a line
break"|"123"|"456"
"1"|"Free text without a linebreak"|""|"789"
"0"|"Free text with
two
linebreaks"|"101112"|"131415"''' # noqa: W291
assert pl.read_csv(csv.encode(), sep="|", dtypes={"col3": pl.Int32}).to_dict(
False
) == {
"col1": [0, 1, 0],
"col2": [
"Free text with a line\nbreak",
"Free text without a linebreak",
"Free text with \ntwo \nlinebreaks",
],
"col3": [123, None, 101112],
"col4": [456, 789, 131415],
}