fix(format): parse HDF5 2.0 native complex datatypes (class 11)

Class 11 (datatype version 5) properties are a single base floating-point
datatype message, not a compound-style member list. The old parser read the
base type's bytes as member names, yielding a garbage datatype, and failed
with UnexpectedEof when a complex type was nested in a compound.

Parse the base type and surface the type as the equivalent {r, i} compound
(the shape h5py writes for numpy complex dtypes), with a size check against
the base type. Covered by byte-level tests taken from HDF5 2.0 output and an
h5py end-to-end test (writer_h5py_tests is now 27/27 against HDF5 2.0.0).

Found while validating a user report of InvalidDatatypeVersion
{ class: 6, version: 5 } against v2.1.0 (already fixed on main in a13ff51,
never released). Add docs/known-issues.md recording that report, this bug,
the open reference-v4 gap and a gpu_tests parallel-run hang; credit the
reporter in the changelog.

Co-Authored-By: Claude Fable 5.1 <[email protected]>
This commit is contained in:
osobh
2026-09-18 20:58:29 -07:00
co-authored by Claude Fable 5.1
parent 48c745a960
commit b55b7dbac5
4 changed files with 260 additions and 19 deletions
@@ -292,6 +292,74 @@ f.close()
assert_eq!(x_vals, vec![1.0, 3.0]);
}
#[test]
#[ignore = "requires Python h5py module"]
fn read_h5py_generated_native_complex() {
// HDF5 2.0 native complex (datatype class 11, version 5), written through
// h5py's low-level API. Skips when the linked HDF5 predates 2.0.
let path = std::env::temp_dir().join("clawhdf5_h5py_native_complex.h5");
let gen_script = format!(
r#"
import h5py, numpy as np
from h5py import h5t, h5s, h5d, h5f, h5p
if not getattr(h5py.get_config(), 'has_native_complex', False):
print('SKIP')
else:
fapl = h5p.create(h5p.FILE_ACCESS)
fapl.set_libver_bounds(h5f.LIBVER_LATEST, h5f.LIBVER_LATEST)
fid = h5f.create(b'{}', h5f.ACC_TRUNC, fapl=fapl)
t = h5t.COMPLEX_IEEE_F64LE
d = h5d.create(fid, b'z', t, h5s.create_simple((2,)))
d.write(h5s.ALL, h5s.ALL, np.array([1+2j, 3+4j], dtype=np.complex128), mtype=t)
fid.close()
"#,
path.display()
);
if h5py_read(&path, &gen_script) == "SKIP" {
eprintln!("HDF5 < 2.0: no native complex support, skipping");
return;
}
let bytes = std::fs::read(&path).unwrap();
let sig = clawhdf5_format::signature::find_signature(&bytes).unwrap();
let sb = clawhdf5_format::superblock::Superblock::parse(&bytes, sig).unwrap();
let addr = clawhdf5_format::group_v2::resolve_path_any(&bytes, &sb, "z").unwrap();
let hdr = clawhdf5_format::object_header::ObjectHeader::parse(
&bytes,
addr as usize,
sb.offset_size,
sb.length_size,
)
.unwrap();
let msg = |t: clawhdf5_format::message_type::MessageType| {
&hdr.messages.iter().find(|m| m.msg_type == t).unwrap().data
};
let (dt, _) = clawhdf5_format::datatype::Datatype::parse(msg(
clawhdf5_format::message_type::MessageType::Datatype,
))
.unwrap();
let ds = clawhdf5_format::dataspace::Dataspace::parse(
msg(clawhdf5_format::message_type::MessageType::Dataspace),
sb.length_size,
)
.unwrap();
let dl = clawhdf5_format::data_layout::DataLayout::parse(
msg(clawhdf5_format::message_type::MessageType::DataLayout),
sb.offset_size,
sb.length_size,
)
.unwrap();
let raw = clawhdf5_format::data_read::read_raw_data(&bytes, &dl, &ds, &dt).unwrap();
let fields = clawhdf5_format::data_read::read_compound_fields(&raw, &dt).unwrap();
assert_eq!(fields.len(), 2);
let re =
clawhdf5_format::data_read::read_as_f64(&fields[0].raw_data, &fields[0].datatype).unwrap();
let im =
clawhdf5_format::data_read::read_as_f64(&fields[1].raw_data, &fields[1].datatype).unwrap();
assert_eq!((fields[0].name.as_str(), re), ("r", vec![1.0, 3.0]));
assert_eq!((fields[1].name.as_str(), im), ("i", vec![2.0, 4.0]));
}
#[test]
#[ignore = "requires Python h5py module"]
fn read_h5py_generated_enum() {