fix(format): read VL values in files with 4-byte offsets

In a file with sizeof_addr = 4, a VL string attribute came back as
AttrValue::Raw, a compound's VL member failed with
GlobalHeapObjectNotFound and VL datasets failed with a size mismatch.

Two bugs: Datatype::type_size() said 16 for every VL type, while the
element is 4 + offset size + 4 bytes (12 here); and the global heap was
parsed without the padding libhdf5 puts after its collection and object
headers (both round up to 8), so with 4-byte lengths every object was
looked up 4 bytes early. Datatype::VariableLength now carries the size
its datatype message stores, and writes it back.

Checked against h5py in tests/vl_offset4_interop.rs (fails with either
fix reverted). Conformance unchanged at 575 of 697; in cve-2024-32608 a
VL attribute whose datatype claims 524304-byte elements is now an error
(h5py cannot iterate those attributes at all).

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

CHANGELOG.md

@@ -2,6 +2,21 @@
 
 ## Unreleased
 
+### Variable-length data (2026-09-26)
+- **VL values in files with 4-byte offsets** (`sizeof_addr = 4`). A VL
+  string attribute came back as `AttrValue::Raw`, a VL member of a compound
+  failed with `GlobalHeapObjectNotFound`, and VL datasets failed with a
+  size mismatch. Two causes: `Datatype::type_size()` reported 16 for every
+  VL type (the element is 4 + offset size + 4 bytes: 12 here), and the
+  global heap was parsed without the padding libhdf5 puts after its
+  collection and object headers (`H5HG_SIZEOF_HDR`/`H5HG_SIZEOF_OBJHDR`
+  round up to 8), so with 4-byte lengths every object was looked up 4
+  bytes early. `Datatype::VariableLength` now carries the element `size`
+  stored in the datatype message (**breaking** for code that builds or
+  exhaustively destructures that variant; patterns with `..` are
+  unaffected), and it is written back as stored. Tested against h5py
+  (`crates/clawhdf5/tests/vl_offset4_interop.rs`).
+
 ### Plugin filters (2026-09-26)
 - **LZF, bitshuffle, bzip2 and Blosc read and write, in pure Rust.** Files
   written by h5py with `compression="lzf"`, or with hdf5plugin's

crates/clawhdf5-format/src/datatype.rs

@@ -125,6 +125,11 @@ pub enum Datatype {
     },
     /// Class 9: Variable-length type.
     VariableLength {
+        /// Size of one element as stored in the file: a sequence length (4
+        /// bytes), a global heap collection address (the file's
+        /// `offset_size`) and an object index (4 bytes) — 16 in a file with
+        /// 8-byte offsets, 12 with 4-byte offsets.
+        size: u32,
         is_string: bool,
         padding: Option<StringPadding>,
         charset: Option<CharacterSet>,
@@ -771,6 +776,7 @@ impl Datatype {
                 pos += consumed;
                 Ok((
                     Datatype::VariableLength {
+                        size,
                         is_string,
                         padding,
                         charset,
@@ -1017,6 +1023,7 @@ impl Datatype {
                 Self::build_header(3, 1, [bf0, 0, 0], *size)
             }
             Datatype::VariableLength {
+                size,
                 is_string,
                 padding,
                 charset,
@@ -1039,7 +1046,7 @@ impl Datatype {
                 } else {
                     0
                 };
-                let mut buf = Self::build_header(9, 1, [bf0, bf1, 0], 16);
+                let mut buf = Self::build_header(9, 1, [bf0, bf1, 0], *size);
                 buf.extend_from_slice(&base_type.serialize());
                 buf
             }
@@ -1208,7 +1215,7 @@ impl Datatype {
             Datatype::Compound { size, .. } => *size,
             Datatype::Reference { size, .. } => *size,
             Datatype::Enumeration { size, .. } => *size,
-            Datatype::VariableLength { .. } => 16, // typically pointer + length
+            Datatype::VariableLength { size, .. } => *size,
             Datatype::Array {
                 base_type,
                 dimensions,
@@ -1889,11 +1896,13 @@ mod tests {
         let (dt, _) = Datatype::parse(&buf).unwrap();
         match dt {
             Datatype::VariableLength {
+                size,
                 is_string,
                 padding,
                 charset,
                 base_type,
             } => {
+                assert_eq!(size, 16);
                 assert!(is_string);
                 assert_eq!(padding, Some(StringPadding::NullTerminate));
                 assert_eq!(charset, Some(CharacterSet::Utf8));
@@ -1914,11 +1923,13 @@ mod tests {
         let (dt, _) = Datatype::parse(&buf).unwrap();
         match dt {
             Datatype::VariableLength {
+                size,
                 is_string,
                 padding,
                 charset,
                 base_type,
             } => {
+                assert_eq!(size, 16);
                 assert!(!is_string);
                 assert_eq!(padding, None);
                 assert_eq!(charset, None);
@@ -1928,6 +1939,19 @@ mod tests {
         }
     }
 
+    #[test]
+    fn variable_length_size_is_the_stored_size() {
+        // A file with 4-byte offsets stores 12-byte VL elements (length 4 +
+        // address 4 + index 4); the type used to report 16 regardless, so
+        // every read laid the elements out 16 bytes apart.
+        let mut buf = build_dt_header(9, 1, [0x01, 0x00, 0], 12);
+        buf.extend_from_slice(&build_fixed_point(1, false, false, 0, 8));
+        let (dt, _) = Datatype::parse(&buf).unwrap();
+        assert_eq!(dt.type_size(), 12);
+        // And it is written back as stored.
+        assert_eq!(dt.serialize()[4..8], 12u32.to_le_bytes());
+    }
+
     #[test]
     fn test_array_2d() {
         // Array [3][4] of i32 LE, version 3

crates/clawhdf5-format/src/global_heap.rs

@@ -64,8 +64,11 @@ impl GlobalHeapCollection {
         offset: usize,
         length_size: u8,
     ) -> Result<GlobalHeapCollection, FormatError> {
-        // signature(4) + version(1) + reserved(3) + collection_size(length_size)
+        // signature(4) + version(1) + reserved(3) + collection_size(length_size),
-        let header_size = 8 + length_size as usize;
+        // padded to a multiple of 8 as libhdf5 lays it out (`H5HG_SIZEOF_HDR`).
+        // With 8-byte lengths the padding is 0; with 4-byte lengths it is 4,
+        // and reading without it put every object 4 bytes early.
+        let header_size = pad8(8 + length_size as usize);
         ensure_len(file_data, offset, header_size)?;
 
         if file_data[offset..offset + 4] != GCOL_SIGNATURE {
@@ -104,8 +107,9 @@ impl GlobalHeapCollection {
                 break;
             }
 
-            // object_index(2) + reference_count(2) + reserved(4) + object_size(length_size)
+            // object_index(2) + reference_count(2) + reserved(4) +
-            let obj_header_size = 8 + length_size as usize;
+            // object_size(length_size), padded to 8 (`H5HG_SIZEOF_OBJHDR`).
+            let obj_header_size = pad8(8 + length_size as usize);
             ensure_len(file_data, pos, obj_header_size)?;
 
             let reference_count = u16::from_le_bytes([file_data[pos + 2], file_data[pos + 3]]);
@@ -149,10 +153,11 @@ mod tests {
         let ls = length_size as usize;
 
         // Calculate total size
-        let header_size = 8 + ls;
+        // libhdf5 pads both headers to a multiple of 8.
+        let header_size = pad8(8 + ls);
         let mut obj_size_total = 0usize;
         for (_, _, data) in objects {
-            let obj_header = 8 + ls;
+            let obj_header = pad8(8 + ls);
             obj_size_total += obj_header + pad8(data.len());
         }
         // Free space marker (2 bytes for index 0)
@@ -170,6 +175,7 @@ mod tests {
             8 => buf.extend_from_slice(&(collection_size as u64).to_le_bytes()),
             _ => panic!("unsupported length_size"),
         }
+        buf.resize(header_size, 0);
 
         // Objects
         for (index, ref_count, data) in objects {
@@ -181,6 +187,7 @@ mod tests {
                 8 => buf.extend_from_slice(&(data.len() as u64).to_le_bytes()),
                 _ => panic!("unsupported"),
             }
+            buf.resize(buf.len() + (pad8(8 + ls) - (8 + ls)), 0);
             buf.extend_from_slice(data);
             // Pad to 8 bytes
             let padded = pad8(data.len());

crates/clawhdf5/tests/vl_offset4_interop.rs

@@ -0,0 +1,126 @@
+//! Variable-length values in files with 4-byte offsets and lengths
+//! (`sizeof_addr = 4`), checked against h5py/libhdf5 through the
+//! `clawhdf5_format` decoders.
+//!
+//! These failed with `GlobalHeapObjectNotFound` or came back as
+//! `AttrValue::Raw`: the VL datatype claimed 16-byte elements whatever the
+//! file's offset size, and the global heap was read without the padding
+//! libhdf5 puts after its collection and object headers. Skipped when
+//! python3 with h5py is unavailable, unless `CLAWHDF5_REQUIRE_INTEROP=1`.
+
+use std::process::Command;
+
+use clawhdf5::{AttrValue, File, Selection};
+use clawhdf5_format::data_read::{read_as_i64, read_compound_fields};
+use clawhdf5_format::vl_data::{read_vl_bytes, read_vl_strings};
+
+fn python() -> String {
+    std::env::var("CLAWHDF5_PYTHON").unwrap_or_else(|_| "python3".to_string())
+}
+
+fn interop_required() -> bool {
+    std::env::var("CLAWHDF5_REQUIRE_INTEROP").is_ok_and(|v| v == "1")
+}
+
+fn python_available() -> bool {
+    Command::new(python())
+        .args(["-c", "import h5py, numpy"])
+        .output()
+        .map(|o| o.status.success())
+        .unwrap_or(false)
+}
+
+#[test]
+fn vl_values_in_a_file_with_4_byte_offsets_read_like_h5py() {
+    if !python_available() {
+        assert!(
+            !interop_required(),
+            "CLAWHDF5_REQUIRE_INTEROP=1 but python3 with h5py is not available"
+        );
+        eprintln!("SKIP: python3 with h5py not available");
+        return;
+    }
+    let dir = tempfile::tempdir().unwrap();
+    let path = dir.path().join("offset4.h5");
+    let script = format!(
+        r#"
+import h5py, numpy as np
+S = h5py.string_dtype()
+fcpl = h5py.h5p.create(h5py.h5p.FILE_CREATE); fcpl.set_sizes(4, 4)
+with h5py.File(h5py.h5f.create({path:?}.encode(), h5py.h5f.ACC_TRUNC, fcpl=fcpl)) as f:
+    f.attrs['vlattr'] = 'attr-value'
+    f.attrs.create('vlattr_arr', np.array(['p', 'qq', ''], dtype=object), dtype=S)
+    ct = np.dtype([('id', '<i4'), ('name', S), ('v', '<f8')])
+    arr = np.zeros(3, dtype=ct); arr['id'] = [1, 2, 3]; arr['name'] = ['one', '', 'three']
+    f.create_dataset('compound', data=arr)
+    f.attrs.create('vlen_attr', np.array([np.array([1, 2], dtype='<i8'), np.array([3], dtype='<i8')],
+                   dtype=object), dtype=h5py.vlen_dtype(np.dtype('<i8')))
+with h5py.File({path:?}, 'r') as f:
+    assert f.id.get_create_plist().get_sizes() == (4, 4)
+    print(f.attrs['vlattr'])
+    print(','.join(f.attrs['vlattr_arr']))
+    print(','.join(s.decode() for s in f['compound']['name']))
+    print(';'.join(' '.join(str(x) for x in s) for s in f.attrs['vlen_attr']))
+"#,
+        path = path.display().to_string()
+    );
+    let output = Command::new(python())
+        .args(["-c", &script])
+        .output()
+        .expect("failed to run python");
+    assert!(
+        output.status.success(),
+        "python failed:\n{}",
+        String::from_utf8_lossy(&output.stderr)
+    );
+    let stdout = String::from_utf8(output.stdout).unwrap();
+    let lines: Vec<&str> = stdout.lines().collect();
+    let (vlattr, vlattr_arr, names, seqs) = (lines[0], lines[1], lines[2], lines[3]);
+
+    let file = File::open(&path).unwrap();
+    let sb = file.superblock();
+    assert_eq!((sb.offset_size, sb.length_size), (4, 4));
+
+    let attrs = file.root().attrs().unwrap();
+    match &attrs["vlattr"] {
+        AttrValue::String(s) => assert_eq!(s, vlattr),
+        other => panic!("vlattr: {other:?}"),
+    }
+    match &attrs["vlattr_arr"] {
+        AttrValue::StringArray(s) => assert_eq!(s.join(","), vlattr_arr),
+        other => panic!("vlattr_arr: {other:?}"),
+    }
+
+    // The compound's VL string member.
+    let ds = file.dataset("compound").unwrap();
+    let dt = ds.raw_datatype().unwrap();
+    assert_eq!(dt.type_size(), 24, "4 + 12-byte VL element + 8");
+    let raw = ds.read_selection(&Selection::All).unwrap();
+    let fields = read_compound_fields(&raw, &dt).unwrap();
+    let name = fields.iter().find(|f| f.name == "name").unwrap();
+    assert_eq!(name.datatype.type_size(), 12);
+    let got = read_vl_strings(file.as_bytes(), &name.raw_data, 3, 4, 4).unwrap();
+    assert_eq!(got.join(","), names);
+    let id = fields.iter().find(|f| f.name == "id").unwrap();
+    assert_eq!(
+        read_as_i64(&id.raw_data, &id.datatype).unwrap(),
+        vec![1, 2, 3]
+    );
+
+    // A VL sequence attribute.
+    let AttrValue::Raw { datatype, data, .. } = &attrs["vlen_attr"] else {
+        panic!("vlen_attr is Raw");
+    };
+    let clawhdf5_format::datatype::Datatype::VariableLength { base_type, .. } = datatype else {
+        panic!("vlen_attr is VL");
+    };
+    let got: Vec<String> = read_vl_bytes(file.as_bytes(), data, 2, 4, 4)
+        .unwrap()
+        .iter()
+        .map(|b| {
+            let v = read_as_i64(b, base_type).unwrap();
+            v.iter().map(i64::to_string).collect::<Vec<_>>().join(" ")
+        })
+        .collect();
+    assert_eq!(got.join(";"), seqs);
+}

docs/known-issues.md

@@ -146,7 +146,10 @@ fill-value item that did is fixed).
     `GlobalHeapObjectNotFound` or come back as `Raw`: these paths assume
     the 16-byte element of an 8-byte-offset file. The datatype itself reads
     (it was refused as "member overlaps with previous member" until
-    2026-09-26).
+    2026-09-26). **Fixed 2026-09-26:** a VL type's element size is the one
+    its datatype message stores (12 with 4-byte offsets), and the global
+    heap is read with libhdf5's header padding
+    (`crates/clawhdf5/tests/vl_offset4_interop.rs`).
   - Metadata cache images are not supported.
   - x87 long double and binary128 are refused.
   - N-Bit on 64-bit scale-offset data and some N-Bit parameter layouts fail.