quantumclaw/clawhdf5
3
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

fix(format): parse compound datatype versions 1 and 2 correctly

Browse Source 
Compound datasets written with default libver bounds (datatype message
version 1, i.e. plain h5py.File(path, 'w')) could not be read: the v1 member
layout has 28 bytes of legacy array fields after the byte offset
(dimensionality 1, reserved 3, permutation 4, reserved 4, four sizes 16) and
the parser skipped 24, so every following member was read 4 bytes off. v2 was
also wrong: it keeps the 8-byte name padding and has no array fields.

Found by adding a default-libver axis to the h5py-generated-file tests (HDF5
2.0 raised the default low bound to 1.8, so "default" files are a distinct
format path from libver='latest'). Adds byte-level v1/v2 regression tests, a
truncation test, and fuzz corpus seeds for v1 compound and native complex.

Co-Authored-By: Claude Fable 5.1 <[email protected]>
This commit is contained in:
osobh
2026-09-19 05:36:22 -07:00
co-authored by Claude Fable 5.1
parent a8ab9ca054
commit 926dc457e0
4 changed files with 137 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/clawhdf5-format/tests/writer_h5py_tests.rs
+34 -6
View File
@@ -235,17 +235,31 @@ fn h5py_reads_our_array_dataset() {
#[test]
#[ignore = "requires Python h5py module"]
fn read_h5py_generated_compound() {
let path = std::env::temp_dir().join("clawhdf5_h5py_compound.h5");
check_h5py_generated_compound("latest", ", libver='latest'");
}
/// Same file written with h5py's default format bounds. HDF5 2.0 raised the
/// default low bound to 1.8, so "default" files exercise different on-disk
/// structures than both `libver='latest'` and pre-2.0 defaults.
#[test]
#[ignore = "requires Python h5py module"]
fn read_h5py_generated_compound_default_libver() {
check_h5py_generated_compound("default", "");
}
fn check_h5py_generated_compound(tag: &str, libver_kw: &str) {
let path = std::env::temp_dir().join(format!("clawhdf5_h5py_compound_{tag}.h5"));
let gen_script = format!(
r#"
import h5py, numpy as np
dt = np.dtype([('x', 'f8'), ('y', 'f8'), ('id', 'i4')])
data = np.array([(1.0, 2.0, 10), (3.0, 4.0, 20)], dtype=dt)
f = h5py.File('{}', 'w', libver='latest')
f = h5py.File('{}', 'w'{})
f.create_dataset('particles', data=data)
f.close()
"#,
path.display()
path.display(),
libver_kw
);
h5py_read(&path, &gen_script);
@@ -363,17 +377,31 @@ else:
#[test]
#[ignore = "requires Python h5py module"]
fn read_h5py_generated_enum() {
let path = std::env::temp_dir().join("clawhdf5_h5py_enum.h5");
check_h5py_generated_enum("latest", ", libver='latest'");
}
/// Same file written with h5py's default format bounds. HDF5 2.0 raised the
/// default low bound to 1.8, so "default" files exercise different on-disk
/// structures than both `libver='latest'` and pre-2.0 defaults.
#[test]
#[ignore = "requires Python h5py module"]
fn read_h5py_generated_enum_default_libver() {
check_h5py_generated_enum("default", "");
}
fn check_h5py_generated_enum(tag: &str, libver_kw: &str) {
let path = std::env::temp_dir().join(format!("clawhdf5_h5py_enum_{tag}.h5"));
let gen_script = format!(
r#"
import h5py, numpy as np
dt = h5py.enum_dtype({{"RED": 0, "GREEN": 1, "BLUE": 2}}, basetype=np.int32)
data = np.array([1, 0, 2, 1], dtype=np.int32)
f = h5py.File('{}', 'w', libver='latest')
f = h5py.File('{}', 'w'{})
f.create_dataset('colors', data=data, dtype=dt)
f.close()
"#,
path.display()
path.display(),
libver_kw
);
h5py_read(&path, &gen_script);