fix(format): dataspaces and contiguous storage as libhdf5 reads them

- A simple dataspace of rank 0 holds one element in libhdf5 (the product
  of no dimensions; h5py reads it as shape ()). num_elements() said 0, so
  cve-2020-18494's /dset1 failed with DataSizeMismatch { expected: 0 }.
- A contiguous dataset whose storage is larger than its elements reads:
  libhdf5 reads the elements from the start of the storage and ignores the
  rest (H5D__contig_check checks only that they fit in the file). We
  required the sizes to be equal, so the scalar /Dset1 of cve-2024-32623
  and cve-2025-2309 (240 bytes of storage for one int) failed. Storage too
  small for the elements is still an error. data_read::contiguous_read_len
  is the rule, used by every contiguous read path.
- Dataspace::parse refuses what H5O__sdspace_decode refuses: more than 32
  dimensions, a rank on a scalar or null dataspace, a dimension larger
  than its maximum (new FormatError::InvalidDataspace).

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

crates/clawhdf5-format/src/data_read.rs

@@ -32,6 +32,22 @@ fn ensure_len(data: &[u8], offset: usize, needed: usize) -> Result<(), FormatErr
     Ok(())
 }
 
+/// How many bytes to read from a contiguous dataset's storage of
+/// `storage_size` bytes (the layout message's size) holding `needed` bytes
+/// of elements. libhdf5 reads the elements' bytes from the start of the
+/// storage and ignores storage past them (`H5D__contig_check` checks only
+/// that the elements fit in the file), so a larger storage reads; one too
+/// small to hold the elements is an error.
+pub fn contiguous_read_len(storage_size: u64, needed: usize) -> Result<usize, FormatError> {
+    if storage_size < needed as u64 {
+        return Err(FormatError::DataSizeMismatch {
+            expected: needed,
+            actual: usize::try_from(storage_size).unwrap_or(usize::MAX),
+        });
+    }
+    Ok(needed)
+}
+
 /// Zero-copy read of contiguous raw data, returning a borrowed slice.
 ///
 /// For contiguous layouts, returns a direct `&[u8]` slice into `file_data`.
@@ -55,13 +71,7 @@ pub fn read_raw_data_zerocopy<'a>(
         DataLayout::Contiguous { address, size } => {
             let addr = address.ok_or(FormatError::NoDataAllocated)?;
             let addr = addr as usize;
-            let sz = *size as usize;
-            if sz != expected_size {
-                return Err(FormatError::DataSizeMismatch {
-                    expected: expected_size,
-                    actual: sz,
-                });
-            }
+            let sz = contiguous_read_len(*size, expected_size)?;
             ensure_len(file_data, addr, sz)?;
             Ok(Some(&file_data[addr..addr + sz]))
         }
@@ -172,13 +182,7 @@ fn read_raw_data_full_impl(
         DataLayout::Contiguous { address, size } => {
             let addr = address.ok_or(FormatError::NoDataAllocated)?;
             let addr = addr as usize;
-            let sz = *size as usize;
-            if sz != expected_size {
-                return Err(FormatError::DataSizeMismatch {
-                    expected: expected_size,
-                    actual: sz,
-                });
-            }
+            let sz = contiguous_read_len(*size, expected_size)?;
             ensure_len(file_data, addr, sz)?;
             let mut out = crate::bulk_alloc::vec_for_bulk(sz);
             out.extend_from_slice(&file_data[addr..addr + sz]);
@@ -2632,6 +2636,36 @@ mod tests {
         assert_eq!(result.unwrap(), &[1.5f32, 2.5, 3.5]);
     }
 
+    /// libhdf5 reads a contiguous dataset's elements from the start of its
+    /// storage and ignores storage past them (cve-2024-32623's scalar
+    /// `/Dset1` has 240 bytes of storage for one 4-byte element). Storage too
+    /// small for the elements is still an error.
+    #[test]
+    fn contiguous_storage_larger_than_the_elements_reads() {
+        let dt = make_f64_le_type();
+        let ds = make_simple_dataspace(&[2]);
+        let mut file_data = vec![0u8; 64];
+        file_data[..8].copy_from_slice(&1.5f64.to_le_bytes());
+        file_data[8..16].copy_from_slice(&2.5f64.to_le_bytes());
+        file_data[16..24].copy_from_slice(&9.0f64.to_le_bytes());
+        let layout = DataLayout::Contiguous {
+            address: Some(0),
+            size: 40,
+        };
+        let raw = read_raw_data(&file_data, &layout, &ds, &dt).unwrap();
+        assert_eq!(raw, file_data[..16]);
+        let zc = read_raw_data_zerocopy(&file_data, &layout, &ds, &dt).unwrap();
+        assert_eq!(zc, Some(&file_data[..16]));
+        let small = DataLayout::Contiguous {
+            address: Some(0),
+            size: 8,
+        };
+        assert!(matches!(
+            read_raw_data(&file_data, &small, &ds, &dt),
+            Err(FormatError::DataSizeMismatch { .. })
+        ));
+    }
+
     #[test]
     fn zerocopy_size_mismatch() {
         let dt = make_f64_le_type();