CHANGELOG.md

@@ -323,7 +323,9 @@
     VAX byte order; libhdf5 ignores it before version 3, and so does this.
   - chunked layouts (`FormatError::InvalidChunkDimensions`): a zero chunk
     dimension, a chunk rank that does not match the dataspace, a chunk of
-    4 GiB or more (0x80000000-sized chunks hung the reader), and v1 B-tree
+    4 GiB or more indexed by a v1 B-tree (layout version 3 or earlier;
+    0x80000000-sized chunks hung the reader — layout versions 4 and 5 allow
+    larger chunks, and HDF5 2.0 writes them), and v1 B-tree
     chunk keys whose offsets are not multiples of the chunk dimensions,
     including the keys that only bound a node
     (`chunked_read::collect_chunk_info_checked`).

crates/clawhdf5-format/src/chunked_read.rs

@@ -152,12 +152,15 @@ pub(crate) fn checked_byte_len(elements: u64, elem_size: usize) -> Result<usize,
 /// the layout message's list: one per dataspace dimension, then the element
 /// size), after the checks libhdf5 makes when it opens a chunked dataset
 /// (`H5D__chunk_init` / `H5D__chunk_set_sizes`): the chunk rank must match
-/// the dataspace's, no chunk dimension may be 0, and a chunk may not be 4 GiB
+/// the dataspace's, no chunk dimension may be 0, and a chunk indexed by a
-/// or more (a v1 B-tree records chunk sizes in 32 bits; libhdf5 before
+/// version-1 B-tree (`layout_version` below 4) may not be 4 GiB or more (the
-/// layout version 5 refuses larger ones). A zero chunk dimension used to read
+/// B-tree records chunk sizes in 32 bits; libhdf5: "chunk size must be < 4GB
-/// as all fill values, and a huge one to hang the reader.
+/// with v1 b-tree index"). The other chunk indexes allow larger chunks:
+/// HDF5 2.0 writes them with layout version 5. A zero chunk dimension used
+/// to read as all fill values, and a huge one to hang the reader.
 pub(crate) fn chunk_geometry(
     chunk_dimensions: &[u32],
+    layout_version: u8,
     dataspace: &Dataspace,
     elem_size: usize,
 ) -> Result<(usize, Vec<usize>), FormatError> {
@@ -180,9 +183,9 @@ pub(crate) fn chunk_geometry(
     let bytes = spatial
         .iter()
         .fold(elem_size as u128, |acc, &c| acc * u128::from(c));
-    if bytes > u128::from(u32::MAX) {
+    if layout_version < 4 && bytes > u128::from(u32::MAX) {
         return Err(FormatError::InvalidChunkDimensions(format!(
-            "chunk size must be < 4GB (chunk {spatial:?} of {elem_size}-byte elements)"
+            "chunk size must be < 4GB with v1 b-tree index (chunk {spatial:?} of {elem_size}-byte elements)"
         )));
     }
     Ok((rank, spatial.iter().map(|&c| c as usize).collect()))
@@ -658,7 +661,7 @@ pub fn list_chunks(
         .ok_or_else(|| FormatError::ChunkedReadError("no address for chunked layout".into()))?;
 
     // Both v3 and v4 include element size as last dim (rank+1)
-    let (rank, chunk_dims) = chunk_geometry(chunk_dimensions, dataspace, elem_size)?;
+    let (rank, chunk_dims) = chunk_geometry(chunk_dimensions, version, dataspace, elem_size)?;
     let ds_dims: Vec<usize> = dataspace.dimensions.iter().map(|&d| d as usize).collect();
 
     // Collect chunks based on version and index type
@@ -894,12 +897,13 @@ pub fn read_chunked_data_cached(
     length_size: u8,
     cache: &ChunkCache,
 ) -> Result<Vec<u8>, FormatError> {
-    let (chunk_dimensions, addr_opt) = match layout {
+    let (chunk_dimensions, version, addr_opt) = match layout {
         DataLayout::Chunked {
             chunk_dimensions,
+            version,
             btree_address,
             ..
-        } => (chunk_dimensions, *btree_address),
+        } => (chunk_dimensions, *version, *btree_address),
         _ => {
             return Err(FormatError::ChunkedReadError(
                 "expected chunked layout".into(),
@@ -911,7 +915,7 @@ pub fn read_chunked_data_cached(
         .ok_or_else(|| FormatError::ChunkedReadError("no address for chunked layout".into()))?;
 
     let elem_size = datatype.type_size() as usize;
-    let (rank, chunk_dims) = chunk_geometry(chunk_dimensions, dataspace, elem_size)?;
+    let (rank, chunk_dims) = chunk_geometry(chunk_dimensions, version, dataspace, elem_size)?;
     let ds_dims: Vec<usize> = dataspace.dimensions.iter().map(|&d| d as usize).collect();
 
     // The per-file cache is shared across datasets (and threads); every
@@ -1199,12 +1203,13 @@ pub fn read_chunked_data_sweep(
     cache: &ChunkCache,
     sweep: &mut SweepContext,
 ) -> Result<Vec<u8>, FormatError> {
-    let (chunk_dimensions, addr_opt) = match layout {
+    let (chunk_dimensions, version, addr_opt) = match layout {
         DataLayout::Chunked {
             chunk_dimensions,
+            version,
             btree_address,
             ..
-        } => (chunk_dimensions, *btree_address),
+        } => (chunk_dimensions, *version, *btree_address),
         _ => {
             return Err(FormatError::ChunkedReadError(
                 "expected chunked layout".into(),
@@ -1216,7 +1221,7 @@ pub fn read_chunked_data_sweep(
         .ok_or_else(|| FormatError::ChunkedReadError("no address for chunked layout".into()))?;
 
     let elem_size = datatype.type_size() as usize;
-    let (rank, chunk_dims) = chunk_geometry(chunk_dimensions, dataspace, elem_size)?;
+    let (rank, chunk_dims) = chunk_geometry(chunk_dimensions, version, dataspace, elem_size)?;
     let ds_dims: Vec<usize> = dataspace.dimensions.iter().map(|&d| d as usize).collect();
 
     // The per-file cache is shared across datasets (and threads); every
@@ -1335,12 +1340,13 @@ pub fn read_chunked_data_indexed(
     length_size: u8,
     cache: &ChunkCache,
 ) -> Result<Vec<u8>, FormatError> {
-    let (chunk_dimensions, addr_opt) = match layout {
+    let (chunk_dimensions, version, addr_opt) = match layout {
         DataLayout::Chunked {
             chunk_dimensions,
+            version,
             btree_address,
             ..
-        } => (chunk_dimensions, *btree_address),
+        } => (chunk_dimensions, *version, *btree_address),
         _ => {
             return Err(FormatError::ChunkedReadError(
                 "expected chunked layout".into(),
@@ -1352,7 +1358,7 @@ pub fn read_chunked_data_indexed(
         .ok_or_else(|| FormatError::ChunkedReadError("no address for chunked layout".into()))?;
 
     let elem_size = datatype.type_size() as usize;
-    let (rank, chunk_dims) = chunk_geometry(chunk_dimensions, dataspace, elem_size)?;
+    let (rank, chunk_dims) = chunk_geometry(chunk_dimensions, version, dataspace, elem_size)?;
     let ds_dims: Vec<usize> = dataspace.dimensions.iter().map(|&d| d as usize).collect();
 
     // Chunk index and assembly plan for this dataset, built on first access
@@ -1845,31 +1851,41 @@ mod tests {
             dimensions: dims.to_vec(),
             max_dimensions: None,
         };
+        for v in [3, 4] {
+            assert_eq!(
+                chunk_geometry(&[4, 5, 8], v, &space(&[10, 10]), 8).unwrap(),
+                (2, vec![4, 5])
+            );
+            // Rank mismatch.
+            assert!(matches!(
+                chunk_geometry(&[4, 8], v, &space(&[10, 10]), 8),
+                Err(FormatError::InvalidChunkDimensions(m)) if m.contains("doesn't match")
+            ));
+            // Zero dimension (a layout built in memory, bypassing the parser).
+            assert!(matches!(
+                chunk_geometry(&[4, 0, 8], v, &space(&[10, 10]), 8),
+                Err(FormatError::InvalidChunkDimensions(m)) if m.contains("must be > 0")
+            ));
+            assert!(chunk_geometry(&[0xFFFF_FFFF, 1], v, &space(&[10]), 1).is_ok());
+        }
+        // With a v1 B-tree index (layout version 3) the largest chunk is
+        // 4 GiB - 1 bytes: 0x80000000 x 4-byte elements (8 GiB) is refused.
+        // These dims used to hang the reader.
+        assert!(matches!(
+            chunk_geometry(&[0x8000_0000, 4], 3, &space(&[10]), 4),
+            Err(FormatError::InvalidChunkDimensions(m)) if m.contains("4GB with v1 b-tree")
+        ));
+        assert!(matches!(
+            chunk_geometry(&[0xFFFF_FFFF, 0xFFFF_FFFF, 1], 3, &space(&[10, 10]), 1),
+            Err(FormatError::InvalidChunkDimensions(m)) if m.contains("4GB with v1 b-tree")
+        ));
+        // The other chunk indexes (layout version 4, and 5, which is read as
+        // 4) allow chunks of 4 GiB and more; HDF5 2.0 writes them.
         assert_eq!(
-            chunk_geometry(&[4, 5, 8], &space(&[10, 10]), 8).unwrap(),
+            chunk_geometry(&[0x2000_0001, 8], 4, &space(&[10]), 8).unwrap(),
-            (2, vec![4, 5])
+            (1, vec![0x2000_0001])
         );
-        // Rank mismatch.
+        assert!(chunk_geometry(&[0xFFFF_FFFF, 0xFFFF_FFFF, 1], 4, &space(&[10, 10]), 1).is_ok());
-        assert!(matches!(
-            chunk_geometry(&[4, 8], &space(&[10, 10]), 8),
-            Err(FormatError::InvalidChunkDimensions(m)) if m.contains("doesn't match")
-        ));
-        // Zero dimension (a layout built in memory, bypassing the parser).
-        assert!(matches!(
-            chunk_geometry(&[4, 0, 8], &space(&[10, 10]), 8),
-            Err(FormatError::InvalidChunkDimensions(m)) if m.contains("must be > 0")
-        ));
-        // 0x80000000 x 4-byte elements is 8 GiB; the largest allowed chunk
-        // is 4 GiB - 1 bytes. These dims used to hang the reader.
-        assert!(matches!(
-            chunk_geometry(&[0x8000_0000, 4], &space(&[10]), 4),
-            Err(FormatError::InvalidChunkDimensions(m)) if m.contains("4GB")
-        ));
-        assert!(matches!(
-            chunk_geometry(&[0xFFFF_FFFF, 0xFFFF_FFFF, 1], &space(&[10, 10]), 1),
-            Err(FormatError::InvalidChunkDimensions(m)) if m.contains("4GB")
-        ));
-        assert!(chunk_geometry(&[0xFFFF_FFFF, 1], &space(&[10]), 1).is_ok());
     }
 
     fn make_f64_type() -> Datatype {

crates/clawhdf5-format/src/data_read.rs

@@ -360,7 +360,7 @@ pub fn read_raw_data_selection(
             chunk_index_type,
             ..
         } => {
-            crate::chunked_read::chunk_geometry(chunk_dimensions, dataspace, elem_size)?;
+            crate::chunked_read::chunk_geometry(chunk_dimensions, *version, dataspace, elem_size)?;
             // For chunked data, only read chunks that intersect the selection
             let chunk_dims: Vec<u64> = chunk_dimensions.iter().map(|&d| d as u64).collect();
             let rank = dims.len();

crates/clawhdf5-format/src/error.rs

@@ -212,7 +212,7 @@ pub enum FormatError {
     InvalidDatatype(String),
     /// A chunked layout whose chunk dimensions libhdf5 refuses: a zero
     /// dimension, a rank that does not match the dataspace, or a chunk of
-    /// 4 GiB or more.
+    /// 4 GiB or more indexed by a version-1 B-tree.
     InvalidChunkDimensions(String),
     /// The superblock's end-of-file address lies past the end of the file:
     /// the file was truncated (libhdf5 refuses to open it).

crates/clawhdf5/tests/header_validation_interop.rs

@@ -269,3 +269,47 @@ save("float_overlap", bad)
         ],
     );
 }
+
+/// Runs a Python script (with `h5py`, `numpy as np` and `struct` imported,
+/// `d` the output directory) and fails the test if it fails.
+fn run_python(dir: &Path, body: &str) {
+    let script = format!(
+        "import h5py, numpy as np, struct, os\nd = \"{}\"\n{body}",
+        dir.display()
+    );
+    let out = Command::new(python())
+        .args(["-c", &script])
+        .output()
+        .expect("failed to run python");
+    assert!(
+        out.status.success(),
+        "python failed:\n{}",
+        String::from_utf8_lossy(&out.stderr)
+    );
+}
+
+/// libhdf5 limits a chunk to under 4 GiB only when a version-1 B-tree
+/// indexes it; HDF5 2.0 writes larger chunks with layout version 5 (libver
+/// v200), and h5py reads them. These were refused as "chunk size must be <
+/// 4GB". Ignored by default: h5py writes a 4 GiB chunk and both libraries
+/// hold it in memory (about 9 GiB in all).
+#[test]
+#[ignore = "writes and reads a 4 GiB chunk (about 9 GiB of memory)"]
+fn chunks_of_4_gib_and_more_read_with_layout_v5() {
+    skip_if_no_python!();
+    let dir = tempfile::tempdir().unwrap();
+    run_python(
+        dir.path(),
+        r#"
+with h5py.File(os.path.join(d, "big.h5"), "w", libver=("v200", "v200")) as f:
+    ds = f.create_dataset("d", shape=(10,), maxshape=(None,), chunks=(2**29 + 1,),
+                          dtype="<f8", compression="gzip", compression_opts=1)
+    ds[:] = np.arange(10.0)
+with h5py.File(os.path.join(d, "big.h5"), "r") as f:
+    assert list(f["d"][:]) == list(np.arange(10.0))
+"#,
+    );
+    let file = File::open(dir.path().join("big.h5")).unwrap();
+    let values = file.dataset("d").unwrap().read_f64().unwrap();
+    assert_eq!(values, (0..10).map(f64::from).collect::<Vec<_>>());
+}