This is an automated email from the ASF dual-hosted git repository.
alamb pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow-rs.git
The following commit(s) were added to refs/heads/main by this push:
new c194e54dc4 [Variant] Add unshredded `Struct` fast-path for
`variant_get(..., Struct)` (#9597)
c194e54dc4 is described below
commit c194e54dc4e8fcd8b9333eea2528d5db1c1ba912
Author: Konstantin Tarasov <[email protected]>
AuthorDate: Thu Mar 26 18:18:42 2026 -0400
[Variant] Add unshredded `Struct` fast-path for `variant_get(..., Struct)`
(#9597)
# Which issue does this PR close?
<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases.
You can link an issue to this PR using the GitHub syntax.
-->
- Closes #9596.
# Rationale for this change
Check issue
<!--
Why are you proposing this change? If this is already explained clearly
in the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand
your changes and offer better suggestions for fixes.
-->
# What changes are included in this PR?
Reuse `shred_basic_variant` as a fast path for unshredded `Struct`
handling in `variant_get(..., Struct)`
<!--
There is no need to duplicate the description in the issue here but it
is sometimes worth providing a summary of the individual changes in this
PR.
-->
# Are these changes tested?
Yes, added two unit tests to establish safe mode behavior.
<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code
If tests are not included in your PR, please explain why (for example,
are they covered by existing tests)?
-->
# Are there any user-facing changes?
<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
If there are any breaking changes to public APIs, please call them out.
-->
---
parquet-variant-compute/src/variant_get.rs | 90 +++++++++++++++++++++++++++++-
1 file changed, 88 insertions(+), 2 deletions(-)
diff --git a/parquet-variant-compute/src/variant_get.rs
b/parquet-variant-compute/src/variant_get.rs
index 9204dcf708..3e9892cacf 100644
--- a/parquet-variant-compute/src/variant_get.rs
+++ b/parquet-variant-compute/src/variant_get.rs
@@ -213,9 +213,20 @@ fn shredded_get_path(
return Ok(shredded);
}
- // Structs are special. Recurse into each field separately, hoping to
follow the shredding even
- // further, and build up the final struct from those individually shredded
results.
+ // Structs are special.
+ //
+ // For fully unshredded targets (`typed_value` absent), delegate to the
row builder so we
+ // preserve struct-level cast semantics:
+ // - safe mode: non-object rows become NULL structs
+ // - strict mode: non-object rows raise a cast error
+ //
+ // For shredded/partially-shredded targets (`typed_value` present),
recurse into each field
+ // separately to take advantage of deeper shredding in child fields.
if let DataType::Struct(fields) = as_field.data_type() {
+ if target.typed_value_field().is_none() {
+ return shred_basic_variant(target, VariantPath::default(),
Some(as_field));
+ }
+
let children = fields
.iter()
.map(|field| {
@@ -3111,6 +3122,81 @@ mod test {
assert_eq!(inner_values.value(1), 100);
}
+ #[test]
+ fn test_unshredded_struct_safe_cast_non_object_rows_are_null() {
+ let json_strings = vec![r#"{"a": 1, "b": 2}"#, "123", "{}"];
+ let string_array: Arc<dyn Array> =
Arc::new(StringArray::from(json_strings));
+ let variant_array_ref =
ArrayRef::from(json_to_variant(&string_array).unwrap());
+
+ let struct_fields = Fields::from(vec![
+ Field::new("a", DataType::Int32, true),
+ Field::new("b", DataType::Int32, true),
+ ]);
+ let options = GetOptions {
+ path: VariantPath::default(),
+ as_type: Some(Arc::new(Field::new(
+ "result",
+ DataType::Struct(struct_fields),
+ true,
+ ))),
+ cast_options: CastOptions::default(),
+ };
+
+ let result = variant_get(&variant_array_ref, options).unwrap();
+ let struct_result = result.as_struct();
+ let field_a = struct_result
+ .column(0)
+ .as_primitive::<arrow::datatypes::Int32Type>();
+ let field_b = struct_result
+ .column(1)
+ .as_primitive::<arrow::datatypes::Int32Type>();
+
+ // Row 0 is an object, so the struct row is valid with extracted
fields.
+ assert!(!struct_result.is_null(0));
+ assert_eq!(field_a.value(0), 1);
+ assert_eq!(field_b.value(0), 2);
+
+ // Row 1 is a scalar, so safe struct cast should produce a NULL struct
row.
+ assert!(struct_result.is_null(1));
+ assert!(field_a.is_null(1));
+ assert!(field_b.is_null(1));
+
+ // Row 2 is an empty object, so the struct row is valid with missing
fields as NULL.
+ assert!(!struct_result.is_null(2));
+ assert!(field_a.is_null(2));
+ assert!(field_b.is_null(2));
+ }
+
+ #[test]
+ fn test_unshredded_struct_strict_cast_non_object_errors() {
+ let json_strings = vec![r#"{"a": 1, "b": 2}"#, "123"];
+ let string_array: Arc<dyn Array> =
Arc::new(StringArray::from(json_strings));
+ let variant_array_ref =
ArrayRef::from(json_to_variant(&string_array).unwrap());
+
+ let struct_fields = Fields::from(vec![
+ Field::new("a", DataType::Int32, true),
+ Field::new("b", DataType::Int32, true),
+ ]);
+ let options = GetOptions {
+ path: VariantPath::default(),
+ as_type: Some(Arc::new(Field::new(
+ "result",
+ DataType::Struct(struct_fields),
+ true,
+ ))),
+ cast_options: CastOptions {
+ safe: false,
+ ..Default::default()
+ },
+ };
+
+ let err = variant_get(&variant_array_ref, options).unwrap_err();
+ assert!(
+ err.to_string()
+ .contains("Failed to extract struct from variant")
+ );
+ }
+
/// Create comprehensive shredded variant with diverse null patterns and
empty objects
/// Rows: normal values, top-level null, missing field a, missing field b,
empty object
fn create_comprehensive_shredded_variant() -> ArrayRef {
