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

fix: Fix SO in json inference #18887

Merged
merged 1 commit into from
Sep 24, 2024
Merged

fix: Fix SO in json inference #18887

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
10 changes: 7 additions & 3 deletions crates/polars-json/src/json/infer_schema.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,11 +134,15 @@ pub(crate) fn coerce_dtype<A: Borrow<ArrowDataType>>(datatypes: &[A]) -> ArrowDa
true,
)));
} else if datatypes.len() > 2 {
return coerce_dtype(datatypes);
return datatypes
.iter()
.map(|t| t.borrow().clone())
.reduce(|a, b| coerce_dtype(&[a, b]))
.expect("not empty");
}
let (lhs, rhs) = (datatypes[0].borrow(), datatypes[1].borrow());

return match (lhs, rhs) {
match (lhs, rhs) {
(lhs, rhs) if lhs == rhs => lhs.clone(),
(LargeList(lhs), LargeList(rhs)) => {
let inner = coerce_dtype(&[lhs.dtype(), rhs.dtype()]);
Expand Down Expand Up @@ -171,5 +175,5 @@ pub(crate) fn coerce_dtype<A: Borrow<ArrowDataType>>(datatypes: &[A]) -> ArrowDa
(Null, rhs) => rhs.clone(),
(lhs, Null) => lhs.clone(),
(_, _) => LargeUtf8,
};
}
}
8 changes: 8 additions & 0 deletions py-polars/tests/unit/io/test_json.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -430,3 +430,11 @@ def test_empty_list_json() -> None:
df = pl.read_json(b"[]")
assert df.shape == (0, 0)
assert isinstance(df, pl.DataFrame)


def test_json_infer_3_dtypes() -> None:
# would SO before
df = pl.DataFrame({"a": ["{}", "1", "[1, 2]"]})
out = df.select(pl.col("a").str.json_decode())
assert out["a"].to_list() == [None, ["1"], ["1", "2"]]
assert out.dtypes[0] == pl.List(pl.String)
Loading