Files
clawhdf5/crates/clawhdf5-format/src/ea_writer.rs
T
osobhandClaude Opus 5.5 afae86f3ea fix(format): write layout v4 chunk dimensions in the fewest bytes
libhdf5 encodes a version-4 layout's chunk dimensions in (log2(max) +
8) / 8 bytes, and HDF5 2.0.0 (h5py 3.16) refuses any other width:
"stored chunk dimension encoding length does not match value calculated
from chunk dimensions". The writer rounded 3 bytes up to 4, so h5py
could not open a dataset we wrote with a chunk dimension from 65 536 to
16 777 215, for every chunk index (single chunk, fixed and extensible
array, v2 B-tree). The three encoders now share push_v4_chunk_dims,
which writes the exact width.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
2026-09-26 01:27:22 -05:00

329 lines
12 KiB
Rust

//! Extensible Array writer: serialize EA layout messages and build EA structures.
#[cfg(not(feature = "std"))]
extern crate alloc;
#[cfg(not(feature = "std"))]
use alloc::{vec, vec::Vec};
use crate::checksum::jenkins_lookup3;
use crate::chunked_write::{
WrittenChunk, filtered_chunk_size_len, push_addr, push_index_element, push_v4_chunk_dims,
};
/// Serialize a v4 Extensible Array layout message.
pub(crate) fn serialize_v4_extensible_array(
chunk_dims: &[u32],
ea_address: u64,
offset_size: u8,
element_size: u32,
) -> Vec<u8> {
let mut buf = Vec::new();
buf.push(4); // version
buf.push(2); // class = chunked
buf.push(0x00); // flags
let ndims = chunk_dims.len() as u8 + 1;
buf.push(ndims);
push_v4_chunk_dims(&mut buf, chunk_dims, element_size);
// chunk index type = 4 (Extensible Array)
buf.push(4);
// EA creation parameters (must match AEHD and HDF5 C library defaults)
buf.push(MAX_NELMTS_BITS);
buf.push(IDX_BLK_ELMTS);
buf.push(SUP_BLK_MIN_DATA_PTRS);
buf.push(DATA_BLK_MIN_ELMTS);
buf.push(MAX_DBLK_PAGE_NELMTS_BITS);
// EA header address
match offset_size {
4 => buf.extend_from_slice(&(ea_address as u32).to_le_bytes()),
8 => buf.extend_from_slice(&ea_address.to_le_bytes()),
_ => unreachable!("unexpected offset size: {offset_size}"),
}
buf
}
// EA creation parameters — the HDF5 library's defaults for chunk indexes
// (`H5D_EARRAY_*`); the layout message above and the header must agree.
const MAX_NELMTS_BITS: u8 = 32;
const IDX_BLK_ELMTS: u8 = 4;
const SUP_BLK_MIN_DATA_PTRS: u8 = 4;
const DATA_BLK_MIN_ELMTS: u8 = 16;
const MAX_DBLK_PAGE_NELMTS_BITS: u8 = 10;
/// One data block of the array: its first element (relative to the end of
/// the index block's own elements), element count, and address when it is
/// allocated.
struct DataBlock {
start: usize,
nelmts: usize,
addr: Option<u64>,
}
/// Build a complete Extensible Array at a known absolute address.
///
/// `slots[i]` is the element at linear index `i` (see `chunk_grid`); `None`
/// marks an unallocated chunk. The first `IDX_BLK_ELMTS` elements live in
/// the index block, the rest in data blocks grouped by super block level
/// exactly as `H5EA__hdr_init` sizes them: level `u` has `2^(u/2)` data
/// blocks of `DATA_BLK_MIN_ELMTS * 2^ceil(u/2)` elements. The data blocks of
/// the first levels are addressed straight from the index block; later
/// levels go through a super block (EASB). Data blocks larger than a page
/// (`2^MAX_DBLK_PAGE_NELMTS_BITS` elements) are paged, with their page-init
/// bits kept in the owning super block. Only blocks holding a defined element
/// are allocated; the rest keep the undefined address, as in a file the
/// library wrote.
pub fn build_extensible_array_at(
slots: &[Option<WrittenChunk>],
offset_size: u8,
length_size: u8,
has_filters: bool,
ea_base_address: u64,
) -> Vec<u8> {
let os = offset_size as usize;
let chunk_size_bytes = has_filters.then(|| filtered_chunk_size_len(slots));
let elem_size = os + chunk_size_bytes.map_or(0, |n| n + 4);
let client_id: u8 = if has_filters { 1 } else { 0 };
let arr_off_size = (MAX_NELMTS_BITS as usize).div_ceil(8);
let page_nelmts = 1usize << MAX_DBLK_PAGE_NELMTS_BITS;
let idx_blk = IDX_BLK_ELMTS as usize;
// Elements past the last defined one are never realised
// (`max_idx_set` is one past the highest index ever set).
let max_idx_set = slots.iter().rposition(Option::is_some).map_or(0, |i| i + 1);
let slots = &slots[..max_idx_set];
let defined_in = |start: usize, n: usize| -> bool {
let lo = idx_blk.saturating_add(start).min(slots.len());
let hi = idx_blk
.saturating_add(start)
.saturating_add(n)
.min(slots.len());
slots[lo..hi].iter().any(Option::is_some)
};
// Super block levels: (ndblks, dblk_nelmts, first element).
let log2_dmin = (DATA_BLK_MIN_ELMTS as u32).trailing_zeros() as usize;
let nsblks = 1 + MAX_NELMTS_BITS as usize - log2_dmin;
let ndblk_addrs = 2 * (SUP_BLK_MIN_DATA_PTRS as usize - 1);
let mut levels: Vec<(usize, usize, usize)> = Vec::with_capacity(nsblks);
let mut start = 0usize;
for u in 0..nsblks {
let ndblks = 1usize << (u / 2);
let nelmts = (DATA_BLK_MIN_ELMTS as usize) << u.div_ceil(2);
levels.push((ndblks, nelmts, start));
// Saturate: on 32-bit targets the last levels only need to compare
// as "beyond the end".
start = start.saturating_add(ndblks.saturating_mul(nelmts));
}
// Levels whose data blocks the index block addresses directly.
let mut direct_levels = 0;
let mut n = 0;
while n < ndblk_addrs {
n += levels[direct_levels].0;
direct_levels += 1;
}
let nsblk_addrs = nsblks - direct_levels;
let dblk_size = |nelmts: usize| -> usize {
let prefix = 4 + 1 + 1 + os + arr_off_size + 4;
if nelmts > page_nelmts {
prefix + (nelmts / page_nelmts) * (page_nelmts * elem_size + 4)
} else {
prefix + nelmts * elem_size
}
};
let sblk_bitmap_len = |ndblks: usize, nelmts: usize| -> usize {
if nelmts > page_nelmts {
ndblks * (nelmts / page_nelmts).div_ceil(8)
} else {
0
}
};
// Plan addresses: header, index block, the direct data blocks, then each
// allocated super block followed by its allocated data blocks.
let aehd_size = 4 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 6 * length_size as usize + os + 4;
let aeib_address = ea_base_address + aehd_size as u64;
let aeib_size = 4 + 1 + 1 + os + idx_blk * elem_size + ndblk_addrs * os + nsblk_addrs * os + 4;
let mut cursor = aeib_address + aeib_size as u64;
let mut ndata_blks = 0u64;
let mut data_blk_size = 0u64;
let mut nsuper_blks = 0u64;
let mut super_blk_size = 0u64;
let mut realized = idx_blk as u64;
let mut plan_dblk = |cursor: &mut u64, start: usize, nelmts: usize| -> DataBlock {
let addr = defined_in(start, nelmts).then(|| {
let a = *cursor;
let size = dblk_size(nelmts) as u64;
*cursor += size;
ndata_blks += 1;
data_blk_size += size;
realized += nelmts as u64;
a
});
DataBlock {
start,
nelmts,
addr,
}
};
let mut direct: Vec<DataBlock> = Vec::with_capacity(ndblk_addrs);
for &(ndblks, nelmts, first) in &levels[..direct_levels] {
for k in 0..ndblks {
direct.push(plan_dblk(&mut cursor, first + k * nelmts, nelmts));
}
}
// (super block address, level, its data blocks)
let mut supers: Vec<(Option<u64>, usize, Vec<DataBlock>)> = Vec::with_capacity(nsblk_addrs);
for (u, &(ndblks, nelmts, first)) in levels.iter().enumerate().skip(direct_levels) {
if !defined_in(first, ndblks.saturating_mul(nelmts)) {
supers.push((None, u, Vec::new()));
continue;
}
let sb_size =
4 + 1 + 1 + os + arr_off_size + sblk_bitmap_len(ndblks, nelmts) + ndblks * os + 4;
let sb_addr = cursor;
cursor += sb_size as u64;
nsuper_blks += 1;
super_blk_size += sb_size as u64;
let dblks = (0..ndblks)
.map(|k| plan_dblk(&mut cursor, first + k * nelmts, nelmts))
.collect();
supers.push((Some(sb_addr), u, dblks));
}
let slot = |i: usize| slots.get(i).and_then(Option::as_ref);
let write_length = |buf: &mut Vec<u8>, val: u64| match length_size {
4 => buf.extend_from_slice(&(val as u32).to_le_bytes()),
_ => buf.extend_from_slice(&val.to_le_bytes()),
};
let write_addr_opt = |buf: &mut Vec<u8>, addr: Option<u64>| match addr {
Some(a) => push_addr(buf, a, offset_size),
None => buf.extend(core::iter::repeat_n(0xFF, os)),
};
let block_prefix = |buf: &mut Vec<u8>, sig: &[u8; 4], block_off: usize| {
buf.extend_from_slice(sig);
buf.push(0); // version
buf.push(client_id);
push_addr(buf, ea_base_address, offset_size);
buf.extend_from_slice(&(block_off as u64).to_le_bytes()[..arr_off_size]);
};
// Serialise one data block (paged or not) onto `out`.
let write_dblk = |out: &mut Vec<u8>, db: &DataBlock| {
let at = out.len();
block_prefix(out, b"EADB", db.start);
let first = idx_blk + db.start;
if db.nelmts > page_nelmts {
// Paged: the prefix carries only its own checksum; each page
// follows with one of its own.
let sum = jenkins_lookup3(&out[at..]);
out.extend_from_slice(&sum.to_le_bytes());
for p in 0..db.nelmts / page_nelmts {
let page_at = out.len();
for e in 0..page_nelmts {
let i = first + p * page_nelmts + e;
push_index_element(out, slot(i), offset_size, chunk_size_bytes);
}
let sum = jenkins_lookup3(&out[page_at..]);
out.extend_from_slice(&sum.to_le_bytes());
}
} else {
for i in first..first + db.nelmts {
push_index_element(out, slot(i), offset_size, chunk_size_bytes);
}
let sum = jenkins_lookup3(&out[at..]);
out.extend_from_slice(&sum.to_le_bytes());
}
debug_assert_eq!(out.len() - at, dblk_size(db.nelmts));
};
// Header (EAHD). The six statistics are, in order: super blocks, their
// bytes, data blocks, their bytes, max index set, elements realised.
let mut out = Vec::with_capacity((cursor - ea_base_address) as usize);
out.extend_from_slice(b"EAHD");
out.push(0); // version
out.push(client_id);
out.push(elem_size as u8);
out.push(MAX_NELMTS_BITS);
out.push(IDX_BLK_ELMTS);
out.push(DATA_BLK_MIN_ELMTS);
out.push(SUP_BLK_MIN_DATA_PTRS);
out.push(MAX_DBLK_PAGE_NELMTS_BITS);
write_length(&mut out, nsuper_blks);
write_length(&mut out, super_blk_size);
write_length(&mut out, ndata_blks);
write_length(&mut out, data_blk_size);
write_length(&mut out, max_idx_set as u64);
write_length(&mut out, realized);
push_addr(&mut out, aeib_address, offset_size);
let sum = jenkins_lookup3(&out);
out.extend_from_slice(&sum.to_le_bytes());
debug_assert_eq!(out.len(), aehd_size);
// Index block (EAIB): inline elements, data block and super block
// addresses.
let ib_start = out.len();
out.extend_from_slice(b"EAIB");
out.push(0);
out.push(client_id);
push_addr(&mut out, ea_base_address, offset_size);
for i in 0..idx_blk {
push_index_element(&mut out, slot(i), offset_size, chunk_size_bytes);
}
for db in &direct {
write_addr_opt(&mut out, db.addr);
}
for (sb_addr, _, _) in &supers {
write_addr_opt(&mut out, *sb_addr);
}
let sum = jenkins_lookup3(&out[ib_start..]);
out.extend_from_slice(&sum.to_le_bytes());
debug_assert_eq!(out.len() - ib_start, aeib_size);
for db in direct.iter().filter(|d| d.addr.is_some()) {
write_dblk(&mut out, db);
}
for (sb_addr, u, dblks) in &supers {
if sb_addr.is_none() {
continue;
}
let (ndblks, nelmts, first) = levels[*u];
let sb_start = out.len();
block_prefix(&mut out, b"EASB", first);
if nelmts > page_nelmts {
// Page-init bits, `npages` per data block, packed MSB-first
// (`H5VM_bit_set`): every page of an allocated data block is
// written.
let npages = nelmts / page_nelmts;
let mut bitmap = vec![0u8; sblk_bitmap_len(ndblks, nelmts)];
for (k, db) in dblks.iter().enumerate() {
if db.addr.is_some() {
for p in 0..npages {
let bit = k * npages + p;
bitmap[bit / 8] |= 0x80 >> (bit % 8);
}
}
}
out.extend_from_slice(&bitmap);
}
for db in dblks {
write_addr_opt(&mut out, db.addr);
}
let sum = jenkins_lookup3(&out[sb_start..]);
out.extend_from_slice(&sum.to_le_bytes());
for db in dblks.iter().filter(|d| d.addr.is_some()) {
write_dblk(&mut out, db);
}
}
debug_assert_eq!(out.len() as u64, cursor - ea_base_address);
out
}