Merge branch 'feat/p3-storage-trait' into feat/p3-range-zfp-edit

# Conflicts:
#	CHANGELOG.md
#	crates/clawhdf5-format/src/attribute.rs
#	crates/clawhdf5-format/src/btree_v1.rs
#	crates/clawhdf5-format/src/data_layout.rs
#	crates/clawhdf5-format/src/extensible_array.rs
#	crates/clawhdf5-format/src/fixed_array.rs
#	crates/clawhdf5-format/src/fractal_heap.rs
#	crates/clawhdf5-format/src/local_heap.rs
#	crates/clawhdf5-format/src/shared_message.rs
This commit is contained in:
osobh
2026-09-26 14:51:51 -05:00
26 changed files with 3480 additions and 497 deletions
+89 -26
View File
@@ -3,8 +3,8 @@
#[cfg(not(feature = "std"))]
use alloc::vec::Vec;
use crate::addr::to_usize;
use crate::error::FormatError;
use crate::storage::{Storage, read_exact_at};
/// A parsed B-tree v1 node.
#[derive(Debug, Clone)]
@@ -75,13 +75,28 @@ impl BTreeV1Node {
file_data: &[u8],
offset: usize,
offset_size: u8,
length_size: u8,
) -> Result<BTreeV1Node, FormatError> {
Self::parse_in(file_data, offset as u64, offset_size, length_size)
}
/// [`Self::parse`] over any [`Storage`]: one read of the node's header,
/// one of its keys and children.
pub fn parse_in<S: Storage + ?Sized>(
file: &S,
offset: u64,
offset_size: u8,
_length_size: u8,
) -> Result<BTreeV1Node, FormatError> {
// signature(4) + node_type(1) + node_level(1) + entries_used(2) = 8
// + left_sibling(offset_size) + right_sibling(offset_size)
let os = offset_size as usize;
let header_size = 8 + os * 2;
ensure_len(file_data, offset, header_size)?;
let header = read_exact_at(file, offset, header_size)?;
let file_data: &[u8] = &header;
// The header's read checked that `offset + header_size` fits.
let body_start = offset + header_size as u64;
let offset = 0usize;
if &file_data[offset..offset + 4] != b"TREE" {
return Err(FormatError::InvalidBTreeSignature);
@@ -103,31 +118,30 @@ impl BTreeV1Node {
} else {
Some(read_offset(file_data, pos, offset_size)?)
};
pos += os;
// For type 0: keys are offset_size bytes, children are offset_size bytes
// Layout: key[0], child[0], key[1], child[1], ..., key[N-1], child[N-1], key[N]
let eu = entries_used as usize;
let key_size = os; // For type 0, key = offset_size
let needed = eu * (key_size + os) + key_size; // eu children + (eu+1) keys
ensure_len(file_data, pos, needed)?;
let body = read_exact_at(file, body_start, needed)?;
let file_data: &[u8] = &body;
let mut keys = Vec::with_capacity(eu + 1);
let mut children = Vec::with_capacity(eu);
for _i in 0..eu {
// key[i]
let key = read_offset(file_data, pos, offset_size)?;
keys.push(key);
pos += key_size;
// child[i]
let child = read_offset(file_data, pos, offset_size)?;
children.push(child);
pos += os;
if os == 0 {
// What reading the first key reports (and keeps `chunks_exact`
// below from being given a zero size).
return Err(FormatError::InvalidOffsetSize(offset_size));
}
// final key
let key = read_offset(file_data, pos, offset_size)?;
keys.push(key);
// `needed` bytes: key[0], child[0], ..., child[eu - 1], key[eu].
let (pairs, last) = file_data.split_at(eu * (key_size + os));
for pair in pairs.chunks_exact(key_size + os) {
keys.push(read_offset(pair, 0, offset_size)?);
children.push(read_offset(pair, key_size, offset_size)?);
}
keys.push(read_offset(last, 0, offset_size)?);
Ok(BTreeV1Node {
node_type,
@@ -151,11 +165,21 @@ pub fn collect_symbol_table_nodes(
offset_size: u8,
length_size: u8,
) -> Result<Vec<u64>, FormatError> {
collect_symbol_table_nodes_inner(file_data, btree_address, offset_size, length_size, 0)
collect_symbol_table_nodes_in(file_data, btree_address, offset_size, length_size)
}
fn collect_symbol_table_nodes_inner(
file_data: &[u8],
/// [`collect_symbol_table_nodes`] over any [`Storage`]: two reads per node.
pub fn collect_symbol_table_nodes_in<S: Storage + ?Sized>(
file: &S,
btree_address: u64,
offset_size: u8,
length_size: u8,
) -> Result<Vec<u64>, FormatError> {
collect_symbol_table_nodes_inner(file, btree_address, offset_size, length_size, 0)
}
fn collect_symbol_table_nodes_inner<S: Storage + ?Sized>(
file: &S,
btree_address: u64,
offset_size: u8,
length_size: u8,
@@ -165,12 +189,7 @@ fn collect_symbol_table_nodes_inner(
return Err(FormatError::NestingDepthExceeded);
}
let node = BTreeV1Node::parse(
file_data,
to_usize(btree_address)?,
offset_size,
length_size,
)?;
let node = BTreeV1Node::parse_in(file, btree_address, offset_size, length_size)?;
if node.node_type != 0 {
return Err(FormatError::InvalidBTreeNodeType(node.node_type));
@@ -184,7 +203,7 @@ fn collect_symbol_table_nodes_inner(
let mut result = Vec::new();
for &child_addr in &node.children {
let child_snods = collect_symbol_table_nodes_inner(
file_data,
file,
child_addr,
offset_size,
length_size,
@@ -323,4 +342,48 @@ mod tests {
assert_eq!(node.entries_used, 1);
assert_eq!(node.children, vec![0x50]);
}
/// Nodes and trees, cut at every length, parse identically through a
/// `read_at`-only storage.
#[test]
fn storage_parse_matches_slice_parse() {
use crate::storage::CountingStorage;
let nodes = [
build_btree_node(0, 0, &[0, 5, 10], &[0x100, 0x200], None, None, 8),
build_btree_node(0, 0, &[0, 5], &[0x100], Some(0x40), Some(0x80), 4),
build_btree_node(1, 2, &[0, 5], &[0x100], None, Some(0x80), 8),
];
for (n, node) in nodes.iter().enumerate() {
let os = if n == 1 { 4 } else { 8 };
for cut in 0..=node.len() {
let f = &node[..cut];
let storage = CountingStorage::new(f.to_vec());
let want = BTreeV1Node::parse(f, 0, os, 8);
let got = BTreeV1Node::parse_in(&storage, 0, os, 8);
assert_eq!(format!("{got:?}"), format!("{want:?}"));
}
}
let leaf1 = build_btree_node(0, 0, &[0, 5], &[0xA00], None, None, 8);
let leaf2 = build_btree_node(0, 0, &[5, 10], &[0xB00], None, None, 8);
let internal = build_btree_node(0, 1, &[0, 5, 10], &[0, 256], None, None, 8);
let mut file = vec![0u8; 512 + internal.len()];
file[..leaf1.len()].copy_from_slice(&leaf1);
file[256..256 + leaf2.len()].copy_from_slice(&leaf2);
file[512..].copy_from_slice(&internal);
for cut in [file.len(), 300, 260, 100, 10] {
let mut f = file.clone();
if cut < 512 {
// Truncate the leaves, keep the root.
f[cut..512].fill(0);
}
let storage = CountingStorage::new(f.clone());
assert_eq!(
collect_symbol_table_nodes_in(&storage, 512, 8, 8),
collect_symbol_table_nodes(&f, 512, 8, 8)
);
}
let storage = CountingStorage::new(file);
collect_symbol_table_nodes_in(&storage, 512, 8, 8).unwrap();
assert_eq!(storage.reads(), 6);
}
}