crates/clawhdf5-format/src/vl_data.rs

@@ -148,7 +148,12 @@ pub fn read_vl_strings(
     Ok(result)
 }
 
-/// Resolve VL byte sequences from raw data.
+/// Resolve VL sequences from raw data, returning each element's bytes.
+///
+/// Each element is the sequence's full encoding — element count × base type
+/// size bytes, in the base type's byte order — so a sequence of `i32` yields
+/// four bytes per value. Decode it with the base type (e.g.
+/// [`crate::data_read::read_as_i64`]).
 pub fn read_vl_bytes(
     file_data: &[u8],
     raw_data: &[u8],
@@ -177,8 +182,10 @@ pub fn read_vl_bytes(
             },
         )?;
 
-        let len = (vl.length as usize).min(obj.data.len());
+        // The heap object holds the whole sequence. `vl.length` counts
-        result.push(obj.data[..len].to_vec());
+        // elements, not bytes, so it is only the byte length when the base
+        // type is one byte wide.
+        result.push(obj.data.clone());
     }
 
     Ok(result)

crates/clawhdf5/tests/numeric_conversion_interop.rs

@@ -311,3 +311,64 @@ with h5py.File("{path}", "r") as f:
     assert_eq!(bools.read_u64().unwrap(), vec![1, 0, 1]);
     assert_eq!(bools.read_i32().unwrap(), vec![1, 0, 1]);
 }
+
+#[test]
+fn vl_sequences_of_wide_base_types_read_whole() {
+    // read_vl_bytes took the sequence's element count as its byte length, so
+    // [1, 2, 3] as VL int32 came back as 3 bytes instead of 12.
+    use clawhdf5::Selection;
+    use clawhdf5_format::datatype::{Datatype, DatatypeByteOrder};
+    use clawhdf5_format::vl_data::read_vl_bytes;
+
+    skip_if_no_python!();
+    let dir = tempfile::tempdir().unwrap();
+    let path = dir.path().join("vlen.h5");
+    let script = format!(
+        r#"{PRELUDE}
+data = {{
+    "i4": (h5py.vlen_dtype("<i4"), [[1, 2, 3], [], [-5], list(range(40))]),
+    "f8": (h5py.vlen_dtype("<f8"), [[1.5, -2.0], [0.25]]),
+    "u1": (h5py.vlen_dtype("u1"), [[1, 2, 255], []]),
+}}
+with h5py.File("{path}", "w") as f:
+    for name, (dt, seqs) in data.items():
+        ds = f.create_dataset(name, (len(seqs),), dtype=dt)
+        for i, s in enumerate(seqs):
+            ds[i] = s
+with h5py.File("{path}", "r") as f:
+    for name in data:
+        for i, s in enumerate(f[name][()]):
+            emit(f"{{name}}:{{i}}", np.frombuffer(np.asarray(s).tobytes(), "u1"))
+"#,
+        path = path.display()
+    );
+    let expected = run_python(&script);
+
+    let file = File::open(&path).unwrap();
+    let sb = file.superblock();
+    for (name, count) in [("i4", 4), ("f8", 2), ("u1", 2)] {
+        let raw = file
+            .dataset(name)
+            .unwrap()
+            .read_selection(&Selection::All)
+            .unwrap();
+        let got =
+            read_vl_bytes(file.as_bytes(), &raw, count, sb.offset_size, sb.length_size).unwrap();
+        let want: Vec<Vec<u8>> = (0..count)
+            .map(|i| parse(expected.get(&format!("{name}:{i}")).unwrap()))
+            .collect();
+        assert_eq!(got, want, "{name}");
+        if name == "i4" {
+            let i32_le = Datatype::FixedPoint {
+                size: 4,
+                byte_order: DatatypeByteOrder::LittleEndian,
+                signed: true,
+                bit_offset: 0,
+                bit_precision: 32,
+            };
+            let values = clawhdf5_format::data_read::read_as_i64(&got[0], &i32_le).unwrap();
+            assert_eq!(values, vec![1, 2, 3]);
+            assert_eq!(got[3].len(), 40 * 4);
+        }
+    }
+}