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
co-authored by
Claude Fable 5.1
Claude Fable 5.1
parent
48c745a960
commit
b55b7dbac5
@@ -546,27 +546,39 @@ impl Datatype {
|
||||
}
|
||||
}
|
||||
11 => {
|
||||
// Complex number — store as compound of two floats internally
|
||||
// Parse like compound with version 3 and 2 members
|
||||
// But actually class 11 has no special properties beyond class 6 compound.
|
||||
// It's just recognized as a separate class. For now parse the 2 members
|
||||
// as compound.
|
||||
let num_members = (bf0 as u16) | ((bf1 as u16) << 8);
|
||||
let mut members = Vec::with_capacity(num_members as usize);
|
||||
let ob = offset_bytes_for_size(size);
|
||||
for _ in 0..num_members {
|
||||
let (name, name_len) = read_null_terminated_string(data, pos)?;
|
||||
pos += name_len;
|
||||
let byte_offset = read_uint(data, pos, ob)?;
|
||||
pos += ob;
|
||||
let (member_dt, consumed) = Self::parse_with_depth(&data[pos..], depth + 1)?;
|
||||
pos += consumed;
|
||||
members.push(CompoundMember {
|
||||
name,
|
||||
byte_offset,
|
||||
datatype: member_dt,
|
||||
// Complex number (HDF5 2.0, datatype version 5). The properties
|
||||
// are a single base floating-point datatype message; an element
|
||||
// is two consecutive base-type values (real, imaginary). There
|
||||
// is no member list. Surface it as the equivalent two-member
|
||||
// compound `{r, i}` — the same shape h5py writes for numpy
|
||||
// complex dtypes — so downstream compound readers work as-is.
|
||||
if version != 5 {
|
||||
return Err(FormatError::InvalidDatatypeVersion {
|
||||
class: class_id,
|
||||
version,
|
||||
});
|
||||
}
|
||||
let (base_type, consumed) = Self::parse_with_depth(&data[pos..], depth + 1)?;
|
||||
pos += consumed;
|
||||
let base_size = base_type.type_size();
|
||||
if base_size.checked_mul(2) != Some(size) {
|
||||
return Err(FormatError::DataSizeMismatch {
|
||||
expected: (base_size as usize).saturating_mul(2),
|
||||
actual: size as usize,
|
||||
});
|
||||
}
|
||||
let members = vec![
|
||||
CompoundMember {
|
||||
name: String::from("r"),
|
||||
byte_offset: 0,
|
||||
datatype: base_type.clone(),
|
||||
},
|
||||
CompoundMember {
|
||||
name: String::from("i"),
|
||||
byte_offset: base_size as u64,
|
||||
datatype: base_type,
|
||||
},
|
||||
];
|
||||
Ok((Datatype::Compound { size, members }, pos))
|
||||
}
|
||||
_ => Err(FormatError::InvalidDatatypeClass(class_id)),
|
||||
@@ -1126,6 +1138,75 @@ mod tests {
|
||||
}
|
||||
}
|
||||
|
||||
/// Real datatype message bytes emitted by HDF5 2.0 for the native complex
|
||||
/// type `H5T_COMPLEX_IEEE_F64LE`: class 11, version 5, size 16, followed by
|
||||
/// the base IEEE f64 datatype message.
|
||||
const COMPLEX_F64_HDF5_2_0: [u8; 28] = [
|
||||
0x5b, 0x01, 0x00, 0x00, 0x10, 0x00, 0x00, 0x00, 0x11, 0x20, 0x3f, 0x00, 0x08, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x40, 0x00, 0x34, 0x0b, 0x00, 0x34, 0xff, 0x03, 0x00, 0x00,
|
||||
];
|
||||
|
||||
#[test]
|
||||
fn test_complex_v5_from_hdf5_2_0() {
|
||||
let (dt, consumed) = Datatype::parse(&COMPLEX_F64_HDF5_2_0).unwrap();
|
||||
assert_eq!(consumed, COMPLEX_F64_HDF5_2_0.len());
|
||||
match dt {
|
||||
Datatype::Compound { size, members } => {
|
||||
assert_eq!(size, 16);
|
||||
assert_eq!(members.len(), 2);
|
||||
assert_eq!((members[0].name.as_str(), members[0].byte_offset), ("r", 0));
|
||||
assert_eq!((members[1].name.as_str(), members[1].byte_offset), ("i", 8));
|
||||
for m in &members {
|
||||
assert!(matches!(
|
||||
m.datatype,
|
||||
Datatype::FloatingPoint { size: 8, .. }
|
||||
));
|
||||
}
|
||||
}
|
||||
other => panic!("expected Compound, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_compound_with_complex_member_from_hdf5_2_0() {
|
||||
// Compound { z: complex f64 @0, k: i64 @16 } as written by HDF5 2.0.
|
||||
// Regression guard: the complex member must consume exactly its own
|
||||
// bytes so the following member parses.
|
||||
let mut bytes = vec![0x56, 0x02, 0x00, 0x00, 0x18, 0x00, 0x00, 0x00, b'z', 0x00, 0x00];
|
||||
bytes.extend_from_slice(&COMPLEX_F64_HDF5_2_0);
|
||||
bytes.extend_from_slice(&[b'k', 0x00, 0x10]);
|
||||
bytes.extend_from_slice(&[
|
||||
0x10, 0x08, 0x00, 0x00, 0x08, 0x00, 0x00, 0x00, 0x00, 0x00, 0x40, 0x00,
|
||||
]);
|
||||
let (dt, consumed) = Datatype::parse(&bytes).unwrap();
|
||||
assert_eq!(consumed, bytes.len());
|
||||
match dt {
|
||||
Datatype::Compound { size, members } => {
|
||||
assert_eq!(size, 24);
|
||||
assert_eq!(members.len(), 2);
|
||||
assert!(matches!(
|
||||
&members[0].datatype,
|
||||
Datatype::Compound { size: 16, members } if members.len() == 2
|
||||
));
|
||||
assert_eq!((members[1].name.as_str(), members[1].byte_offset), ("k", 16));
|
||||
}
|
||||
other => panic!("expected Compound, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_complex_size_mismatch_rejected() {
|
||||
let mut bytes = COMPLEX_F64_HDF5_2_0;
|
||||
bytes[4] = 0x0c; // claims 12 bytes, base type is 8
|
||||
assert!(matches!(
|
||||
Datatype::parse(&bytes),
|
||||
Err(FormatError::DataSizeMismatch {
|
||||
expected: 16,
|
||||
actual: 12
|
||||
})
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_reference_object() {
|
||||
let buf = build_dt_header(7, 1, [0, 0, 0], 8);
|
||||
|
||||
@@ -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() {
|
||||
|
||||
Reference in New Issue
Block a user