h5rs tools, browser reader, libhdf5 header checks, plugin filters, concurrency benchmark #14

Merged
osobh merged 60 commits from feat/p1-proof into main 2026-09-26 13:14:39 +00:00
3 changed files with 58 additions and 3 deletions
Showing only changes of commit 056092b082 - Show all commits
+33
View File
@@ -29,6 +29,15 @@ version = "1.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b" checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b"
[[package]]
name = "bzip2"
version = "0.6.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f3a53fac24f34a81bc9954b5d6cfce0c21e18ec6959f44f56e8e90e4bb7c346c"
dependencies = [
"libbz2-rs-sys",
]
[[package]] [[package]]
name = "cc" name = "cc"
version = "1.5.1" version = "1.5.1"
@@ -52,12 +61,15 @@ name = "clawhdf5-format"
version = "2.7.0" version = "2.7.0"
dependencies = [ dependencies = [
"byteorder", "byteorder",
"bzip2",
"flate2", "flate2",
"libaec-sys", "libaec-sys",
"lz4_flex", "lz4_flex",
"pco", "pco",
"portable-atomic", "portable-atomic",
"ruzstd",
"sha2", "sha2",
"snap",
"zstd", "zstd",
] ]
@@ -192,6 +204,12 @@ dependencies = [
"pkg-config", "pkg-config",
] ]
[[package]]
name = "libbz2-rs-sys"
version = "0.2.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "34b357333733e8260735ba5894eb928c02ecc69c78715f01a8019e7fa7f2db4c"
[[package]] [[package]]
name = "libc" name = "libc"
version = "0.2.189" version = "0.2.189"
@@ -286,6 +304,15 @@ dependencies = [
"rand_core", "rand_core",
] ]
[[package]]
name = "ruzstd"
version = "0.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a252f5e20f038fe7b4ea53e073e65398d652c864cc162fc77c56c2f13717b888"
dependencies = [
"twox-hash",
]
[[package]] [[package]]
name = "serde" name = "serde"
version = "1.0.229" version = "1.0.229"
@@ -351,6 +378,12 @@ version = "0.3.10"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3a219298ac11a56ea9a6d2120044824d6f01aeb034955e7af7bc16858527deea" checksum = "3a219298ac11a56ea9a6d2120044824d6f01aeb034955e7af7bc16858527deea"
[[package]]
name = "snap"
version = "1.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "199905e6153d6405f9728fe44daace35f8f837bbf830bb6e85fbd5828709a886"
[[package]] [[package]]
name = "syn" name = "syn"
version = "2.0.119" version = "2.0.119"
+1 -1
View File
@@ -12,7 +12,7 @@ description = "Walks an HDF5 file with clawhdf5-format and prints a canonical JS
[workspace] [workspace]
[dependencies] [dependencies]
clawhdf5-format = { path = "../../crates/clawhdf5-format", features = ["lz4", "zstd", "szip", "pcodec"] } clawhdf5-format = { path = "../../crates/clawhdf5-format", features = ["lz4", "zstd", "szip", "pcodec", "plugin-filters"] }
serde_json = "1" serde_json = "1"
sha2 = "0.10" sha2 = "0.10"
+24 -2
View File
@@ -64,10 +64,29 @@ run_step "cargo clippy --all-targets" cargo clippy \
# 3. Clippy over clawhdf5-format's optional features, which the default # 3. Clippy over clawhdf5-format's optional features, which the default
# workspace build never compiles (szip is left out: it needs libaec). # workspace build never compiles (szip is left out: it needs libaec).
# plugin-filters = bitshuffle, bzip2, blosc (and the default-on lzf).
run_step "cargo clippy (format feature matrix)" cargo clippy \ run_step "cargo clippy (format feature matrix)" cargo clippy \
-p clawhdf5-format \ -p clawhdf5-format \
--all-targets \ --all-targets \
--features parallel,lz4,zstd,pcodec,fast-checksum \ --features parallel,lz4,zstd,pcodec,fast-checksum,plugin-filters \
-- -D warnings
# Each plugin filter alone, so none of them leans on another's
# dependencies (bitshuffle and blosc share code).
plugin_filters_alone() {
local f
for f in bitshuffle bzip2 blosc; do
echo "--- $f"
cargo clippy -p clawhdf5-format --all-targets --features "$f" -- -D warnings || return 1
done
}
run_step "cargo clippy (each plugin filter alone)" plugin_filters_alone
# The facade's plugin-filter interop tests only build with the features on.
run_step "cargo clippy (facade plugin filters)" cargo clippy \
-p clawhdf5 \
--all-targets \
--features plugin-filters \
-- -D warnings -- -D warnings
# The HNSW index's parallel bulk build is feature-gated too. # The HNSW index's parallel bulk build is feature-gated too.
@@ -128,7 +147,7 @@ run_step "cargo test" cargo test \
run_step "cargo test (format feature matrix)" cargo test \ run_step "cargo test (format feature matrix)" cargo test \
-p clawhdf5-format \ -p clawhdf5-format \
--features parallel,lz4,zstd,pcodec,fast-checksum --features parallel,lz4,zstd,pcodec,fast-checksum,plugin-filters
run_step "cargo test (ann parallel)" cargo test \ run_step "cargo test (ann parallel)" cargo test \
-p clawhdf5-ann \ -p clawhdf5-ann \
@@ -149,6 +168,9 @@ if "$PYTHON" -c "import h5py" >/dev/null 2>&1 || [ "${CLAWHDF5_REQUIRE_INTEROP:-
# libhdf5's registered plugins) compile and run too. # libhdf5's registered plugins) compile and run too.
run_step "h5py interop (format, ignored tests)" cargo test \ run_step "h5py interop (format, ignored tests)" cargo test \
-p clawhdf5-format --features lz4,zstd --test writer_h5py_tests -- --include-ignored -p clawhdf5-format --features lz4,zstd --test writer_h5py_tests -- --include-ignored
# LZF, bitshuffle, bzip2 and Blosc both ways against h5py + hdf5plugin.
run_step "h5py interop (plugin filters)" cargo test \
-p clawhdf5 --features plugin-filters --test plugin_filters_interop
else else
echo "" echo ""
echo "==> [h5py interop] SKIPPED: no h5py in $PYTHON" echo "==> [h5py interop] SKIPPED: no h5py in $PYTHON"