fix(format): encode Time, BitField, Opaque and Reference datatypes

Datatype::serialize returned an empty message for these four classes, so
any dataset or attribute of them (including a Raw attribute copied from
another file) was unreadable by libhdf5 ("ran off end of input buffer
while decoding"). They now encode exactly as libhdf5 does: legacy object
and region references as datatype version 1, H5T_STD_REF kinds as version
4 with their encoding version, opaque tags NUL-padded to 8 bytes.

Parsing an opaque tag now stops at its first NUL, so libhdf5's padding
no longer becomes part of the tag. Datatype::check_encodable rejects
what has no encoding (an opaque tag over 248 bytes); FileWriter::finish
calls it for every dataset and attribute type.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
This commit is contained in:
osobh
2026-09-25 21:06:51 -05:00
co-authored by Claude Opus 5.5
parent b36998ef01
commit be88e3fec7
3 changed files with 377 additions and 3 deletions
+11
View File
@@ -1125,6 +1125,17 @@ impl FileWriter {
root_attrs.push(build_attr_message(n, v));
}
// Every datatype must have an on-disk encoding before anything is laid
// out: `Datatype::serialize` itself cannot report a failure.
let group_attrs = groups.iter().flat_map(|g| &g.attrs);
let ds_attrs = all_ds.iter().flat_map(|d| &d.attrs);
for a in root_attrs.iter().chain(group_attrs).chain(ds_attrs) {
a.datatype.check_encodable()?;
}
for d in &all_ds {
d.dt.check_encodable()?;
}
let is_vds: Vec<bool> = all_ds.iter().map(|d| d.virtual_sources.is_some()).collect();
let is_chunked: Vec<bool> = all_ds
.iter()