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 d2da4c86e5 implement `Metadata::retain` (#10695)
d2da4c86e5 is described below
commit d2da4c86e5c584400efca9d49ce823d47d59929b
Author: RIchard Baah <[email protected]>
AuthorDate: Tue Aug 18 15:25:39 2026 -0400
implement `Metadata::retain` (#10695)
# 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 #10683.
# Rationale for this change
see #10683
<!--
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?
implements `retain` on metadata. The underlying BTreeMap is allocation
free unless the `Arc` pointer is shared
<!--
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
<!--
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)?
If this PR claims a performance improvement, please include evidence
such as benchmark results.
-->
# Are there any user-facing changes?
yes, new `retain` method on the metadata struct
<!--
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.
-->
---
arrow-schema/src/metadata.rs | 62 ++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 62 insertions(+)
diff --git a/arrow-schema/src/metadata.rs b/arrow-schema/src/metadata.rs
index 38cd811910..36400686fc 100644
--- a/arrow-schema/src/metadata.rs
+++ b/arrow-schema/src/metadata.rs
@@ -162,6 +162,23 @@ impl Metadata {
pub fn values(&self) -> impl Iterator<Item = &String> {
self.iter().map(|(_, value)| value)
}
+
+ /// Retains only the entries for which `f(&key, &mut value)` returns
`true`.
+ ///
+ /// Entries for which `f` returns `false` are removed. Retained entries
+ /// remain in their original (sorted) order.
+ ///
+ /// Clones the underlying map if (and only if) it is shared.
+ pub fn retain<F>(&mut self, mut f: F)
+ where
+ F: FnMut(&String, &mut String) -> bool,
+ {
+ let Some(map) = self.0.as_mut() else { return };
+ Arc::make_mut(map).retain(&mut f);
+ if map.is_empty() {
+ self.0 = None;
+ }
+ }
}
/// Iterator over the entries of a [`Metadata`], sorted by key.
@@ -486,6 +503,51 @@ mod tests {
assert_eq!(format!("{:?}", Metadata::new()), "{}");
}
+ #[test]
+ fn test_retain() {
+ let mut metadata =
+ Metadata::from([("a", "1"), ("b", "2"), ("c", "3"), ("d", "4"),
("e", "5")]);
+
+ metadata.retain(|k, _| -> bool { k >= &String::from("c") });
+
+ let result_map = Metadata::from([("c", "3"), ("d", "4"), ("e", "5")]);
+ assert_eq!(metadata, result_map)
+ }
+
+ #[test]
+ fn test_retain_empty() {
+ let mut metadata = Metadata::new();
+ metadata.retain(|_, _| -> bool { true });
+ assert!(metadata.is_empty())
+ }
+
+ #[test]
+ fn test_retain_all_removed() {
+ let mut metadata = Metadata::from([("a", "1"), ("b", "2"), ("c",
"3")]);
+ metadata.retain(|_, _| false);
+ assert!(metadata.is_empty());
+ assert!(metadata.0.is_none());
+ }
+
+ #[test]
+ fn test_retain_copy_on_write() {
+ let mut metadata = Metadata::from([("a", "1"), ("b", "2"), ("c",
"3")]);
+ let clone = metadata.clone();
+
+ // both share the same Arc before any mutation:
+ assert!(Arc::ptr_eq(
+ metadata.0.as_ref().expect("non-empty"),
+ clone.0.as_ref().expect("non-empty"),
+ ));
+
+ // retain clones the shared map, leaving the clone untouched:
+ metadata.retain(|k, _| k != "a");
+ assert_eq!(metadata.len(), 2);
+ assert_eq!(clone.len(), 3);
+ assert!(!metadata.contains_key("a"));
+ assert!(clone.contains_key("a"));
+ }
+
#[test]
#[cfg(feature = "serde")]
fn test_serde_round_trip() {
