feat(format): parse H5T_STD_REF references and decode object references

HDF5 1.12 revised the reference datatype (class 7) in datatype message version
4: reference types 2-4 are the new H5T_STD_REF object / dataset-region /
attribute references. Datatype::parse rejected them with
InvalidReferenceType, so any dataset of that type was unreadable.

h5py cannot write this type, which is why it had never been tested. A real
file was produced by calling the libhdf5 bundled in the h5py wheel through
ctypes (H5T_STD_REF_g, H5Rcreate_object, H5Dwrite); the 2 KB result is
committed as tests/fixtures/std_ref_hdf5_2_0.h5 with its generator,
gen_std_ref.py.

- ReferenceType gains Object2, DatasetRegion2 and Attribute, accepted only
  from datatype version 4.
- read_object_references decodes Object2 elements: type(1) flags(1)
  token_size(1) token, zero-padded to the element size; the token is the
  target's object header address. A null reference decodes to the undefined
  address; an external reference, a wrong type byte or a token that doesn't
  fit is an error.

The fixture test follows both references and checks they resolve to the
objects they were created from.

Co-Authored-By: Claude Fable 5.1 <[email protected]>

crates/clawhdf5-format/tests/reference_tests.rs

@@ -316,3 +316,97 @@ print('ok')
     // Clean up
     let _ = std::fs::remove_file(&path);
 }
+
+// ---------------------------------------------------------------------------
+// H5T_STD_REF (HDF5 1.12+ references, datatype message version 4)
+// ---------------------------------------------------------------------------
+
+/// `fixtures/std_ref_hdf5_2_0.h5` (see `gen_std_ref.py`) holds a dataset of
+/// `H5T_STD_REF` with two object references, written by HDF5 2.0 itself. The
+/// datatype used to be rejected with `InvalidReferenceType(2)`.
+#[test]
+fn std_ref_object_references_from_hdf5_2_0() {
+    use clawhdf5_format::data_layout::DataLayout;
+    use clawhdf5_format::dataspace::Dataspace;
+    use clawhdf5_format::group_v2::resolve_path_any;
+    use clawhdf5_format::message_type::MessageType;
+    use clawhdf5_format::object_header::ObjectHeader;
+    use clawhdf5_format::signature::find_signature;
+    use clawhdf5_format::superblock::Superblock;
+
+    let bytes: &[u8] = include_bytes!("fixtures/std_ref_hdf5_2_0.h5");
+    let sb = Superblock::parse(bytes, find_signature(bytes).unwrap()).unwrap();
+    let (os, ls) = (sb.offset_size, sb.length_size);
+
+    let refs_addr = resolve_path_any(bytes, &sb, "refs").unwrap();
+    let header = ObjectHeader::parse(bytes, refs_addr as usize, os, ls).unwrap();
+    let message = |t: MessageType| {
+        &header
+            .messages
+            .iter()
+            .find(|m| m.msg_type == t)
+            .unwrap()
+            .data
+    };
+
+    let (datatype, _) = Datatype::parse(message(MessageType::Datatype)).unwrap();
+    assert_eq!(
+        datatype,
+        Datatype::Reference {
+            size: 18,
+            ref_type: ReferenceType::Object2
+        }
+    );
+    let dataspace = Dataspace::parse(message(MessageType::Dataspace), ls).unwrap();
+    let layout = DataLayout::parse(message(MessageType::DataLayout), os, ls).unwrap();
+    let raw =
+        clawhdf5_format::data_read::read_raw_data(bytes, &layout, &dataspace, &datatype).unwrap();
+    assert_eq!(raw.len(), 2 * 18);
+
+    // The references point at the objects they were created from.
+    let refs = read_object_references(&raw, &datatype, os).unwrap();
+    let addresses: Vec<u64> = refs.iter().map(|r| r.address).collect();
+    assert_eq!(
+        addresses,
+        [
+            resolve_path_any(bytes, &sb, "target").unwrap(),
+            resolve_path_any(bytes, &sb, "grp").unwrap(),
+        ]
+    );
+    // And what they point at is a real object header.
+    for address in addresses {
+        ObjectHeader::parse(bytes, address as usize, os, ls).unwrap();
+    }
+}
+
+#[test]
+fn std_ref_decoding_rejects_malformed_elements() {
+    let dt = Datatype::Reference {
+        size: 18,
+        ref_type: ReferenceType::Object2,
+    };
+    let mut good = vec![0u8; 18];
+    good[..4].copy_from_slice(&[2, 0, 8, 0xb3]);
+    assert_eq!(
+        read_object_references(&good, &dt, 8).unwrap()[0].address,
+        0xb3
+    );
+
+    // Null reference.
+    assert_eq!(
+        read_object_references(&[0u8; 18], &dt, 8).unwrap()[0].address,
+        u64::MAX
+    );
+    for (what, patch) in [
+        ("wrong reference type", (0usize, 3u8)),
+        ("external flag", (1, 1)),
+        ("token longer than the element", (2, 200)),
+        ("zero-length token", (2, 0)),
+    ] {
+        let mut bad = good.clone();
+        bad[patch.0] = patch.1;
+        assert!(read_object_references(&bad, &dt, 8).is_err(), "{what}");
+    }
+    // Not a whole number of elements.
+    assert!(read_object_references(&good[..17], &dt, 8).is_err());
+}