Files
clawhdf5/crates/clawhdf5-format/Cargo.toml
T
osobhandClaude Opus 5.5 07094e34a9 feat(format): bitshuffle filter (32008), with its LZ4 and Zstandard modes
hdf5plugin's Bitshuffle failed with UnsupportedFilter(32008). The new
`bitshuffle` feature (pure Rust: lz4_flex, and ruzstd for Zstandard — the
`zstd` feature's libzstd is not needed) decodes all three modes of
bshuf_h5filter.c — transpose only, LZ4 and Zstandard blocks behind the
12-byte header — including the default and explicit block sizes, the
shorter last block rounded down to a multiple of 8 elements, and the
untransposed trailing elements. Sizes read from the chunk are bounded by
the chunk size.

It also encodes: DatasetBuilder::with_bitshuffle(BitshuffleCompression)
or PluginFilter::Bitshuffle { block_size, compression } writes the filter
with hdf5plugin's cd_values and no automatic byte shuffle. ruzstd has one
compression level (about zstd's 1); the requested level is recorded.

The bit transpose is checked bit for bit against a one-bit-at-a-time model
(which matched hdf5plugin's output) and is shared with blosc next.
Interop: hdf5plugin writes none/LZ4/Zstandard at default and explicit
block sizes and levels over the 12-case matrix, read byte for byte; our
three modes at two block sizes read back through hdf5plugin. Both fail
with the decoder removed.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
2026-09-26 00:04:05 -05:00

72 lines
2.6 KiB
TOML

[package]
name = "clawhdf5-format"
version = "2.7.0"
edition = "2024"
rust-version.workspace = true
description = "Pure-Rust HDF5 binary format parsing and writing — no C dependencies"
license = "MIT"
repository = "https://git.redclaw.dev/quantumclaw/clawhdf5"
readme = "README.md"
keywords = ["hdf5", "science", "data", "binary", "no-std"]
categories = ["parser-implementations", "science", "encoding", "no-std"]
[dependencies]
byteorder = { version = "1", default-features = false }
portable-atomic = { version = "1" }
flate2 = { version = "1", default-features = false, features = ["rust_backend"], optional = true }
sha2 = { version = "0.10", default-features = false, optional = true }
rayon = { version = "1", optional = true }
crc32fast = { version = "1", optional = true }
lz4_flex = { version = "0.11", optional = true }
zstd = { version = "0.13", optional = true }
blake3 = { version = "1", optional = true }
libaec-sys = { path = "../libaec-sys", version = "0.1", optional = true }
pco = { version = "1.0", optional = true }
# Pure-Rust Zstandard, for the plugin filters that embed zstd (bitshuffle,
# blosc). The `zstd` feature (filter 32015) links libzstd instead.
ruzstd = { version = "0.9", optional = true }
[dev-dependencies]
half = { workspace = true }
serde_json = "1"
criterion = { workspace = true }
clawhdf5-derive = { path = "../clawhdf5-derive", version = "2.7.0" }
[[bench]]
name = "bench"
harness = false
[features]
# Deflate backend: `zlib-rs` (pure Rust) by default. `fast-deflate` selects
# zlib-ng instead (C, built with cmake); flate2 prefers a C zlib whenever one
# is enabled, so turning it on anywhere in the build overrides the default.
default = ["std", "checksum", "deflate", "provenance", "zlib-rs", "system-zlib-decompress", "lzf"]
std = []
checksum = []
deflate = ["flate2"]
provenance = ["sha2"]
parallel = ["rayon", "std"]
fast-checksum = ["crc32fast"]
fast-deflate = ["flate2/zlib-ng"]
system-zlib = ["flate2/zlib-default"]
system-zlib-decompress = []
# `runtime_detection` gives zlib-rs `std`, which it needs to detect and use
# SIMD at runtime. flate2 enables it by default, but we build flate2 with
# default-features = false, and without it zlib-rs inflates 3.5x slower.
zlib-rs = ["flate2/zlib-rs", "flate2/runtime_detection"]
lz4 = ["lz4_flex"]
zstd = ["dep:zstd"]
blake3_hash = ["blake3"]
szip = ["libaec-sys"]
pcodec = ["dep:pco"]
# Plugin filters, pure Rust. LZF (32000) is h5py's built-in compression; it
# has no dependencies, so it is on by default.
lzf = []
# Bitshuffle (32008), with its LZ4 and Zstandard modes.
bitshuffle = ["lz4_flex", "ruzstd"]
[[bench]]
name = "parallel_decompress_bench"
harness = false
required-features = ["parallel"]