Skip to content

refactor: share leaf-level parquet read plan assembly with the row filter #23427

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

Closed
adriangb wants to merge 2 commits into from
Closed

refactor: share leaf-level parquet read plan assembly with the row filter #23427

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
653a70b
refactor: collapse repeated root-level plan construction into a helper
adriangb Jul 9, 2026
636a115
refactor: share leaf-level read plan assembly with the row filter
adriangb Jul 9, 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
117 changes: 65 additions & 52 deletions datafusion/datasource-parquet/src/projection_read_plan.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -363,18 +363,7 @@ pub(crate) fn build_projection_read_plan(
root_indices.sort_unstable();
root_indices.dedup();

let projection_mask =
ProjectionMask::roots(schema_descr, root_indices.iter().copied());
let projected_schema = Arc::new(
file_schema
.project(&root_indices)
.expect("valid column indices"),
);

return ParquetReadPlan {
projection_mask,
projected_schema,
};
return root_level_plan(&root_indices, file_schema, schema_descr);
}

// secondary fast path: if the schema has no struct columns, we can skip
Expand All @@ -393,19 +382,7 @@ pub(crate) fn build_projection_read_plan(
root_indices.sort_unstable();
root_indices.dedup();

let projection_mask =
ProjectionMask::roots(schema_descr, root_indices.iter().copied());

let projected_schema = Arc::new(
file_schema
.project(&root_indices)
.expect("valid column indices"),
);

return ParquetReadPlan {
projection_mask,
projected_schema,
};
return root_level_plan(&root_indices, file_schema, schema_descr);
}

let mut all_root_indices = Vec::new();
Expand All @@ -426,46 +403,82 @@ pub(crate) fn build_projection_read_plan(
// when no struct field accesses were found, fall back to root-level projection
// to match the performance of the simple path
if all_struct_accesses.is_empty() {
let projection_mask =
ProjectionMask::roots(schema_descr, all_root_indices.iter().copied());
let projected_schema = Arc::new(
file_schema
.project(&all_root_indices)
.expect("valid column indices"),
);

return ParquetReadPlan {
projection_mask,
projected_schema,
};
return root_level_plan(&all_root_indices, file_schema, schema_descr);
}

let leaf_indices = {
let mut out =
leaf_indices_for_roots(all_root_indices.iter().copied(), schema_descr);
let struct_leaf_indices =
resolve_struct_field_leaves(&all_struct_accesses, file_schema, schema_descr);
let (read_plan, _leaf_indices) = assemble_read_plan(
&all_root_indices,
&all_struct_accesses,
file_schema,
schema_descr,
);

out.extend_from_slice(&struct_leaf_indices);
out.sort_unstable();
out.dedup();
read_plan
}

out
};
/// Builds a leaf-level [`ParquetReadPlan`] covering `root_indices` in full plus
/// the individual leaves reached by `struct_field_accesses`.
///
/// `root_indices` must be sorted, deduplicated indices into `file_schema`.
///
/// Also returns the resolved Parquet leaf indices, sorted and deduplicated, so
/// callers can size the columns the decoder will read.
pub(crate) fn assemble_read_plan(
root_indices: &[usize],
struct_field_accesses: &[StructFieldAccess],
file_schema: &Schema,
schema_descr: &SchemaDescriptor,
) -> (ParquetReadPlan, Vec<usize>) {
let mut leaf_indices =
leaf_indices_for_roots(root_indices.iter().copied(), schema_descr);
leaf_indices.extend_from_slice(&resolve_struct_field_leaves(
struct_field_accesses,
file_schema,
schema_descr,
));
leaf_indices.sort_unstable();
leaf_indices.dedup();

let projection_mask =
ProjectionMask::leaves(schema_descr, leaf_indices.iter().copied());

let projected_schema =
build_filter_schema(file_schema, &all_root_indices, &all_struct_accesses);
build_filter_schema(file_schema, root_indices, struct_field_accesses);

(
ParquetReadPlan {
projection_mask,
projected_schema,
},
leaf_indices,
)
}

/// Builds a [`ParquetReadPlan`] that decodes whole root columns.
///
/// `root_indices` must be sorted, deduplicated indices into `file_schema`. Every
/// leaf below each root is decoded, and the projected schema keeps each root
/// field's full type. Callers that need to decode only some leaves of a struct
/// root must build the plan from leaf indices instead.
fn root_level_plan(
root_indices: &[usize],
file_schema: &Schema,
schema_descr: &SchemaDescriptor,
) -> ParquetReadPlan {
let projection_mask =
ProjectionMask::roots(schema_descr, root_indices.iter().copied());
let projected_schema = Arc::new(
file_schema
.project(root_indices)
.expect("valid column indices"),
);

ParquetReadPlan {
projection_mask,
projected_schema,
}
}

pub(crate) fn leaf_indices_for_roots<I>(
fn leaf_indices_for_roots<I>(
root_indices: I,
schema_descr: &SchemaDescriptor,
) -> Vec<usize>
Expand All @@ -491,7 +504,7 @@ where
/// For every `StructFieldAccess`, finds the leaf columns in the Parquet schema
/// whose path matches the struct root name + field path. This avoids reading all
/// leaves of a struct when only specific fields are needed
pub(crate) fn resolve_struct_field_leaves(
fn resolve_struct_field_leaves(
accesses: &[StructFieldAccess],
file_schema: &Schema,
schema_descr: &SchemaDescriptor,
Expand Down Expand Up @@ -530,7 +543,7 @@ pub(crate) fn resolve_struct_field_leaves(
/// For struct columns accessed via `get_field`, a pruned struct type is created
/// containing only the fields along the access path. Note: it must match the schema
/// that the Parquet reader produces when projecting specific struct leaves
pub(crate) fn build_filter_schema(
fn build_filter_schema(
file_schema: &Schema,
regular_indices: &[usize],
struct_field_accesses: &[StructFieldAccess],
Expand Down
31 changes: 4 additions & 27 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 @@ -86,8 +86,7 @@ use datafusion_physical_plan::metrics;
use super::ParquetFileMetrics;
use super::supported_predicates::supports_list_predicates;
use crate::projection_read_plan::{
ParquetReadPlan, PushdownChecker, PushdownColumns, build_filter_schema,
leaf_indices_for_roots, resolve_struct_field_leaves,
ParquetReadPlan, PushdownChecker, PushdownColumns, assemble_read_plan,
};

/// A "compiled" predicate passed to `ParquetRecordBatchStream` to perform
Expand Down Expand Up @@ -269,38 +268,16 @@ pub(crate) fn build_parquet_read_plan(
return Ok(None);
};

let root_indices = &required_columns.required_columns;

let mut leaf_indices =
leaf_indices_for_roots(root_indices.iter().copied(), schema_descr);

let struct_leaf_indices = resolve_struct_field_leaves(
let (read_plan, leaf_indices) = assemble_read_plan(
&required_columns.required_columns,
&required_columns.struct_field_accesses,
file_schema,
schema_descr,
);
leaf_indices.extend_from_slice(&struct_leaf_indices);
leaf_indices.sort_unstable();
leaf_indices.dedup();

let required_bytes = size_of_columns(&leaf_indices, metadata)?;

let projection_mask =
ProjectionMask::leaves(schema_descr, leaf_indices.iter().copied());

let projected_schema = build_filter_schema(
file_schema,
root_indices,
&required_columns.struct_field_accesses,
);

Ok(Some((
ParquetReadPlan {
projection_mask,
projected_schema,
},
required_bytes,
)))
Ok(Some((read_plan, required_bytes)))
}

/// Checks if a predicate expression can be pushed down to the parquet decoder.
Expand Down
Loading