Skip to content

feat(arrow-avro): accept default value of null for Avro union with null type in any branch position #9487

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

Draft
mzabaluev wants to merge 3 commits into
base: main
Choose a base branch
from
Draft

feat(arrow-avro): accept default value of null for Avro union with null type in any branch position #9487

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
5b246df
fix: allow null default for any unions with null
mzabaluev Feb 1, 2026
665dc60
test: null default resolution, null as second type
mzabaluev Feb 27, 2026
bdce846
test: update nullability rules test
mzabaluev Feb 27, 2026
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
19 changes: 8 additions & 11 deletions arrow-avro/src/codec.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -307,18 +307,18 @@ impl AvroDataType {
}
}

// Handle JSON nulls per-spec: allowed only for `null` type or unions with null FIRST
// Handle JSON nulls per-spec: allowed only for `null` type or unions with null
if default_json.is_null() {
return match self.codec() {
Codec::Null => Ok(AvroLiteral::Null),
Codec::Union(encodings, _, _) if !encodings.is_empty()
&& matches!(encodings[0].codec(), Codec::Null) =>
Codec::Union(encodings, _, _)
if encodings.iter().any(|enc| matches!(enc.codec(), Codec::Null)) =>
{
Ok(AvroLiteral::Null)
}
_ if self.nullability() == Some(Nullability::NullFirst) => Ok(AvroLiteral::Null),
_ if self.nullability().is_some() => Ok(AvroLiteral::Null),
_ => Err(ArrowError::SchemaError(
"JSON null default is only valid for `null` type or for a union whose first branch is `null`"
"JSON null default is only valid for `null` type or for a union with a `null` branch"
.to_string(),
)),
};
Expand Down Expand Up @@ -2946,12 +2946,9 @@ mod tests {
assert_default_stored(&dt_int_nf, &Value::Null);
let mut dt_int_ns =
AvroDataType::new(Codec::Int32, HashMap::new(), Some(Nullability::NullSecond));
let err2 = dt_int_ns.parse_and_store_default(&Value::Null).unwrap_err();
assert!(
err2.to_string()
.contains("JSON null default is only valid for `null` type"),
"unexpected error: {err2}"
);
let lit3 = dt_int_ns.parse_and_store_default(&Value::Null).unwrap();
assert_eq!(lit3, AvroLiteral::Null);
assert_default_stored(&dt_int_ns, &Value::Null);
}

#[test]
Expand Down
7 changes: 6 additions & 1 deletion arrow-avro/src/reader/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2936,14 +2936,15 @@ mod test {
},"default":{"x":7}}),
serde_json::json!({"name":"d_nullable_null","type":["null","int"],"default":null}),
serde_json::json!({"name":"d_nullable_value","type":["int","null"],"default":123}),
serde_json::json!({"name":"d_nullable_null_second","type":["int","null"],"default":null}),
],
);
let actual = read_alltypes_with_reader_schema(path, reader_schema);
let num_rows = actual.num_rows();
assert!(num_rows > 0, "skippable_types.avro should contain rows");
assert_eq!(
actual.num_columns(),
22,
23,
"expected exactly our defaulted fields"
);
let mut arrays: Vec<Arc<dyn Array>> = Vec::with_capacity(22);
Expand Down Expand Up @@ -3070,6 +3071,10 @@ mod test {
arrays.push(Arc::new(Int32Array::from_iter_values(std::iter::repeat_n(
123, num_rows,
))));
arrays.push(Arc::new(Int32Array::from_iter(std::iter::repeat_n(
None::<i32>,
num_rows,
))));
let expected = RecordBatch::try_new(actual.schema(), arrays).unwrap();
assert_eq!(
actual, expected,
Expand Down
Loading