Skip to content

refactor: Optimize required_columns from BTreeSet to Vec in struct PushdownChecker #19678

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

Open
kumarUjjawal wants to merge 2 commits into
base: main
Choose a base branch
from
+21 −8
Open

refactor: Optimize required_columns from BTreeSet to Vec in struct PushdownChecker #19678

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8c2462e
refactor: Optimize required_columns from BTreeSet to Vec in struct Pu…
kumarUjjawal Jan 7, 2026
2a51524
use dedup and update comments
kumarUjjawal Jan 12, 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
29 changes: 21 additions & 8 deletions datafusion/datasource-parquet/src/row_filter.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -276,7 +276,7 @@ struct PushdownChecker<'schema> {
/// Does the expression reference any columns not present in the file schema?
projected_columns: bool,
/// Indices into the file schema of columns required to evaluate the expression.
required_columns: BTreeSet<usize>,
required_columns: Vec<usize>,
/// Tracks the nested column behavior found during traversal.
nested_behavior: NestedColumnSupport,
/// Whether nested list columns are supported by the predicate semantics.
Expand All @@ -290,7 +290,7 @@ impl<'schema> PushdownChecker<'schema> {
Self {
non_primitive_columns: false,
projected_columns: false,
required_columns: BTreeSet::default(),
required_columns: Vec::new(),
nested_behavior: NestedColumnSupport::PrimitiveOnly,
allow_list_columns,
file_schema,
Expand All @@ -307,7 +307,8 @@ impl<'schema> PushdownChecker<'schema> {
}
};

self.required_columns.insert(idx);
// Duplicates are handled by dedup() in into_sorted_columns()
self.required_columns.push(idx);
let data_type = self.file_schema.field(idx).data_type();

if DataType::is_nested(data_type) {
Expand Down Expand Up @@ -355,6 +356,21 @@ impl<'schema> PushdownChecker<'schema> {
fn prevents_pushdown(&self) -> bool {
self.non_primitive_columns || self.projected_columns
}

/// Consumes the checker and returns sorted, deduplicated column indices
/// wrapped in a `PushdownColumns` struct.
///
/// This method sorts the column indices and removes duplicates. The sort
/// is required because downstream code relies on column indices being in
/// ascending order for correct schema projection.
fn into_sorted_columns(mut self) -> PushdownColumns {
self.required_columns.sort_unstable();
self.required_columns.dedup();
PushdownColumns {
required_columns: self.required_columns,
nested: self.nested_behavior,
}
}
}

impl TreeNodeVisitor<'_> for PushdownChecker<'_> {
Expand Down Expand Up @@ -392,7 +408,7 @@ enum NestedColumnSupport {

#[derive(Debug)]
Copy link
Contributor

@kosiew kosiew Jan 12, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is there a reason to remove
#[derive(Debug)]
?

struct PushdownColumns {
required_columns: BTreeSet<usize>,
required_columns: Vec<usize>,
nested: NestedColumnSupport,
}

Expand All @@ -411,10 +427,7 @@ fn pushdown_columns(
let allow_list_columns = supports_list_predicates(expr);
let mut checker = PushdownChecker::new(file_schema, allow_list_columns);
expr.visit(&mut checker)?;
Ok((!checker.prevents_pushdown()).then_some(PushdownColumns {
required_columns: checker.required_columns,
nested: checker.nested_behavior,
}))
Ok((!checker.prevents_pushdown()).then(|| checker.into_sorted_columns()))
}

fn leaf_indices_for_roots(
Expand Down