feat(format): apply fill values to unallocated storage on read

HDF5 allocates lazily: a chunk nobody wrote doesn't exist in the file, and a
dataset nobody wrote has no data address. Such regions must read as the
dataset's fill value. There was no Fill Value message parser at all, so:

- a sparse chunked dataset read its holes as zeros — silently wrong whenever
  the fill value isn't zero (h5py `fillvalue=-1` came back as 0);
- a dataset that was created but never written failed with NoDataAllocated /
  "no address for chunked layout" where h5py returns a filled array.

New clawhdf5_format::fill_value: parses Fill Value messages v1-v3 and the old
0x0004 message (validated against HDF5 2.0 output under default and latest
libver), builds a fully filled dataset when there is no storage, and writes the
fill value into exactly the chunk-grid cells absent from the chunk index —
never mistaking a stored zero for a hole, clipping edge chunks, any rank. It is
skipped entirely for the default (zero) fill value. The chunk index dispatch is
extracted from read_chunked_data into a reusable list_chunks.

The reader, lazy and mmap facades apply it on full reads; selection reads go
through a fill-aware full read when the fill value matters. h5py interop test
compares against h5py's own readback, including a sparse 2-D dataset and a
hyperslab straddling allocated and unallocated chunks.

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

crates/clawhdf5-format/src/chunked_read.rs

@@ -362,15 +362,17 @@ pub fn generate_implicit_chunks(
 }
 
 /// Read a chunked dataset, decompressing chunks as needed.
-pub fn read_chunked_data(
+/// Every allocated chunk of a chunked dataset, for any supported chunk index,
+/// plus the spatial chunk dimensions. Chunks the file never allocated (sparse
+/// datasets) are simply absent from the list.
+pub fn list_chunks(
     file_data: &[u8],
     layout: &DataLayout,
     dataspace: &Dataspace,
-    datatype: &Datatype,
-    pipeline: Option<&FilterPipeline>,
+    elem_size: usize,
     offset_size: u8,
     length_size: u8,
-) -> Result<Vec<u8>, FormatError> {
+) -> Result<(Vec<ChunkInfo>, Vec<usize>), FormatError> {
     let (
         chunk_dimensions,
         version,
@@ -404,8 +406,6 @@ pub fn read_chunked_data(
     let addr = addr_opt
         .ok_or_else(|| FormatError::ChunkedReadError("no address for chunked layout".into()))?;
 
-    let elem_size = datatype.type_size() as usize;
-
     // Both v3 and v4 include element size as last dim (rank+1)
     let ndims = chunk_dimensions.len();
     let rank = ndims
@@ -494,6 +494,30 @@ pub fn read_chunked_data(
         }
     };
 
+    Ok((chunks, chunk_dims))
+}
+
+pub fn read_chunked_data(
+    file_data: &[u8],
+    layout: &DataLayout,
+    dataspace: &Dataspace,
+    datatype: &Datatype,
+    pipeline: Option<&FilterPipeline>,
+    offset_size: u8,
+    length_size: u8,
+) -> Result<Vec<u8>, FormatError> {
+    let elem_size = datatype.type_size() as usize;
+    let (chunks, chunk_dims) = list_chunks(
+        file_data,
+        layout,
+        dataspace,
+        elem_size,
+        offset_size,
+        length_size,
+    )?;
+    let rank = chunk_dims.len();
+    let ds_dims: Vec<usize> = dataspace.dimensions.iter().map(|&d| d as usize).collect();
+
     // Assemble output
     let total_bytes = checked_byte_len(dataspace.checked_num_elements()?, elem_size)?;
     if total_bytes == 0 {

crates/clawhdf5-format/src/data_read.rs

@@ -600,7 +600,7 @@ fn read_named_dataset_raw(
 }
 
 /// Extract selected elements from a full dataset buffer.
-fn extract_selection_from_buffer(
+pub fn extract_selection_from_buffer(
     full_data: &[u8],
     dims: &[u64],
     elem_size: usize,

crates/clawhdf5-format/src/fill_value.rs

@@ -0,0 +1,398 @@
+//! Fill Value messages (0x0005, and the old 0x0004) and applying them on read.
+//!
+//! HDF5 allocates storage lazily: a chunk nobody wrote to does not exist in the
+//! file, and a contiguous dataset nobody wrote to has no data address at all.
+//! Reading such a region must yield the dataset's *fill value* (zeros unless
+//! the creator chose otherwise). The readers in [`crate::chunked_read`] leave
+//! those regions zeroed; [`apply_to_unallocated_chunks`] then overwrites exactly
+//! the chunk-grid cells that are absent from the chunk index — so it can never
+//! mistake a stored zero for a hole — and is skipped entirely in the common
+//! case of a zero fill value.
+
+#[cfg(not(feature = "std"))]
+use alloc::{format, vec, vec::Vec};
+
+use crate::chunked_read::{alloc_output, checked_byte_len, list_chunks};
+use crate::data_layout::DataLayout;
+use crate::dataspace::Dataspace;
+use crate::error::FormatError;
+use crate::message_type::MessageType;
+use crate::object_header::HeaderMessage;
+
+/// Largest fill value accepted. A fill value is one element of the dataset's
+/// datatype; this only bounds the allocation driven by the message's size field.
+const MAX_FILL_VALUE_SIZE: usize = 1 << 20;
+
+/// Parse a Fill Value message, returning the user-defined fill value bytes, or
+/// `None` when the dataset uses the default (all zeros) or has the fill value
+/// explicitly undefined.
+pub fn parse_fill_value(msg: &HeaderMessage) -> Result<Option<Vec<u8>>, FormatError> {
+    let data = msg.data.as_slice();
+    let value_at = |pos: usize| -> Result<Option<Vec<u8>>, FormatError> {
+        let size_bytes = data.get(pos..pos + 4).ok_or(FormatError::UnexpectedEof {
+            expected: pos + 4,
+            available: data.len(),
+        })?;
+        let size = u32::from_le_bytes([size_bytes[0], size_bytes[1], size_bytes[2], size_bytes[3]])
+            as usize;
+        if size == 0 {
+            return Ok(None);
+        }
+        if size > MAX_FILL_VALUE_SIZE {
+            return Err(FormatError::Overflow(format!(
+                "fill value of {size} bytes exceeds the {MAX_FILL_VALUE_SIZE}-byte limit"
+            )));
+        }
+        let start = pos + 4;
+        let value =
+            data.get(start..start.saturating_add(size))
+                .ok_or(FormatError::UnexpectedEof {
+                    expected: start.saturating_add(size),
+                    available: data.len(),
+                })?;
+        Ok(Some(value.to_vec()))
+    };
+
+    match msg.msg_type {
+        // Old fill value message: size(4), value.
+        MessageType::FillValueOld => value_at(0),
+        MessageType::FillValue => {
+            let version = *data.first().ok_or(FormatError::UnexpectedEof {
+                expected: 1,
+                available: 0,
+            })?;
+            match version {
+                // version, alloc time, write time, defined, [size, value]
+                1 | 2 => {
+                    let defined = *data.get(3).ok_or(FormatError::UnexpectedEof {
+                        expected: 4,
+                        available: data.len(),
+                    })?;
+                    if version == 2 && defined == 0 {
+                        Ok(None)
+                    } else if data.len() < 8 && version == 1 {
+                        // v1 always carries a size, but tolerate its absence.
+                        Ok(None)
+                    } else {
+                        value_at(4)
+                    }
+                }
+                // version, flags (bit 4 = undefined, bit 5 = defined), [size, value]
+                3 => {
+                    let flags = *data.get(1).ok_or(FormatError::UnexpectedEof {
+                        expected: 2,
+                        available: data.len(),
+                    })?;
+                    if flags & 0x10 != 0 || flags & 0x20 == 0 {
+                        Ok(None)
+                    } else {
+                        value_at(2)
+                    }
+                }
+                v => Err(FormatError::UnsupportedVersion(v)),
+            }
+        }
+        _ => Ok(None),
+    }
+}
+
+/// The fill value that applies to a dataset given its header messages. The new
+/// message wins over the old one when both are present.
+pub fn dataset_fill_value(messages: &[HeaderMessage]) -> Result<Option<Vec<u8>>, FormatError> {
+    for wanted in [MessageType::FillValue, MessageType::FillValueOld] {
+        if let Some(msg) = messages.iter().find(|m| m.msg_type == wanted) {
+            if crate::shared_message::is_shared(msg.flags) {
+                // A shared fill value is legal but vanishingly rare; treat it
+                // as the default rather than misparsing the reference.
+                return Ok(None);
+            }
+            if let Some(value) = parse_fill_value(msg)? {
+                return Ok(Some(value));
+            }
+        }
+    }
+    Ok(None)
+}
+
+/// `true` when a fill value is absent or all zeros, i.e. identical to what the
+/// readers already produce for unallocated storage.
+pub fn is_default(fill: Option<&[u8]>) -> bool {
+    fill.is_none_or(|f| f.iter().all(|&b| b == 0))
+}
+
+/// A whole dataset's worth of fill value: what reading a dataset with no
+/// allocated storage at all must return.
+pub fn filled_dataset(
+    dataspace: &Dataspace,
+    elem_size: usize,
+    fill: Option<&[u8]>,
+) -> Result<Vec<u8>, FormatError> {
+    let total = checked_byte_len(dataspace.checked_num_elements()?, elem_size)?;
+    let mut out = alloc_output(total)?;
+    if let Some(fill) = fill.filter(|f| f.len() == elem_size && !is_default(Some(f))) {
+        for element in out.chunks_exact_mut(elem_size) {
+            element.copy_from_slice(fill);
+        }
+    }
+    Ok(out)
+}
+
+/// Whether the layout has any storage in the file at all. A dataset that was
+/// created but never written to has none.
+pub fn has_storage(layout: &DataLayout) -> bool {
+    !matches!(
+        layout,
+        DataLayout::Contiguous { address: None, .. }
+            | DataLayout::Chunked {
+                btree_address: None,
+                ..
+            }
+    )
+}
+
+/// Run a full-dataset `read`, giving unallocated storage its fill value: a
+/// dataset with no storage at all reads as entirely fill value (instead of
+/// failing), and a chunked dataset has the fill value written into every
+/// chunk the file never allocated.
+#[allow(clippy::too_many_arguments)]
+pub fn read_full_with_fill<E: From<FormatError>>(
+    messages: &[HeaderMessage],
+    file_data: &[u8],
+    layout: &DataLayout,
+    dataspace: &Dataspace,
+    elem_size: usize,
+    offset_size: u8,
+    length_size: u8,
+    read: impl FnOnce() -> Result<Vec<u8>, E>,
+) -> Result<Vec<u8>, E> {
+    let fill = dataset_fill_value(messages)?;
+    if !has_storage(layout) {
+        return Ok(filled_dataset(dataspace, elem_size, fill.as_deref())?);
+    }
+    let mut output = read()?;
+    apply_to_unallocated_chunks(
+        &mut output,
+        file_data,
+        layout,
+        dataspace,
+        elem_size,
+        fill.as_deref(),
+        offset_size,
+        length_size,
+    )?;
+    Ok(output)
+}
+
+/// Overwrite, in a fully read chunked dataset `output`, every region whose
+/// chunk was never allocated with `fill`. No-op for non-chunked layouts, a
+/// default fill value, or a fill value whose size doesn't match the element.
+#[allow(clippy::too_many_arguments)]
+pub fn apply_to_unallocated_chunks(
+    output: &mut [u8],
+    file_data: &[u8],
+    layout: &DataLayout,
+    dataspace: &Dataspace,
+    elem_size: usize,
+    fill: Option<&[u8]>,
+    offset_size: u8,
+    length_size: u8,
+) -> Result<(), FormatError> {
+    let Some(fill) = fill.filter(|f| f.len() == elem_size && !is_default(Some(f))) else {
+        return Ok(());
+    };
+    if !matches!(layout, DataLayout::Chunked { .. }) || elem_size == 0 {
+        return Ok(());
+    }
+    let (chunks, chunk_dims) = list_chunks(
+        file_data,
+        layout,
+        dataspace,
+        elem_size,
+        offset_size,
+        length_size,
+    )?;
+    let rank = chunk_dims.len();
+    let ds_dims: Vec<usize> = dataspace.dimensions.iter().map(|&d| d as usize).collect();
+    if rank == 0 || ds_dims.len() != rank || chunk_dims.contains(&0) {
+        return Ok(());
+    }
+
+    // Row-major strides over the dataset and over the chunk grid.
+    let mut ds_strides = vec![1usize; rank];
+    for i in (0..rank - 1).rev() {
+        ds_strides[i] = ds_strides[i + 1].saturating_mul(ds_dims[i + 1]);
+    }
+    let grid: Vec<usize> = ds_dims
+        .iter()
+        .zip(&chunk_dims)
+        .map(|(&d, &c)| d.div_ceil(c))
+        .collect();
+    let cells = grid
+        .iter()
+        .try_fold(1usize, |acc, &g| acc.checked_mul(g))
+        .ok_or_else(|| FormatError::Overflow("chunk grid size overflows".into()))?;
+    if cells == 0 {
+        return Ok(());
+    }
+
+    let mut allocated = vec![false; cells];
+    for chunk in &chunks {
+        // Undefined address: the index has a slot for the chunk but no storage.
+        if chunk.address == u64::MAX || chunk.offsets.len() < rank {
+            continue;
+        }
+        let mut cell = 0usize;
+        let mut in_range = true;
+        for d in 0..rank {
+            let coord = chunk.offsets[d] as usize / chunk_dims[d];
+            if coord >= grid[d] {
+                in_range = false;
+                break;
+            }
+            cell = cell * grid[d] + coord;
+        }
+        if in_range {
+            allocated[cell] = true;
+        }
+    }
+
+    let mut coord = vec![0usize; rank];
+    for (cell, is_allocated) in allocated.iter().enumerate() {
+        if *is_allocated {
+            continue;
+        }
+        // Decode the cell index into grid coordinates.
+        let mut rem = cell;
+        for d in (0..rank).rev() {
+            coord[d] = rem % grid[d];
+            rem /= grid[d];
+        }
+        fill_cell(
+            output,
+            &coord,
+            &chunk_dims,
+            &ds_dims,
+            &ds_strides,
+            elem_size,
+            fill,
+        );
+    }
+    Ok(())
+}
+
+/// Fill the part of chunk-grid cell `coord` that lies inside the dataset.
+fn fill_cell(
+    output: &mut [u8],
+    coord: &[usize],
+    chunk_dims: &[usize],
+    ds_dims: &[usize],
+    ds_strides: &[usize],
+    elem_size: usize,
+    fill: &[u8],
+) {
+    let rank = coord.len();
+    let start: Vec<usize> = (0..rank).map(|d| coord[d] * chunk_dims[d]).collect();
+    let end: Vec<usize> = (0..rank)
+        .map(|d| (start[d] + chunk_dims[d]).min(ds_dims[d]))
+        .collect();
+    if (0..rank).any(|d| start[d] >= end[d]) {
+        return;
+    }
+    // Walk every row (all dims but the last) and fill the run along the last.
+    let run = end[rank - 1] - start[rank - 1];
+    let mut idx = start.clone();
+    loop {
+        let first: usize = (0..rank).map(|d| idx[d] * ds_strides[d]).sum();
+        let from = first * elem_size;
+        let to = from + run * elem_size;
+        if let Some(region) = output.get_mut(from..to) {
+            for element in region.chunks_exact_mut(elem_size) {
+                element.copy_from_slice(fill);
+            }
+        }
+        // Advance the odometer over dims 0..rank-1.
+        let mut d = rank - 1;
+        loop {
+            if d == 0 {
+                return;
+            }
+            d -= 1;
+            idx[d] += 1;
+            if idx[d] < end[d] {
+                break;
+            }
+            idx[d] = start[d];
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn msg(msg_type: MessageType, data: &[u8]) -> HeaderMessage {
+        HeaderMessage {
+            msg_type,
+            size: data.len(),
+            flags: 0,
+            creation_order: None,
+            data: data.to_vec(),
+        }
+    }
+
+    #[test]
+    fn parses_v3_defined_undefined_and_default() {
+        // Real message for h5py `fillvalue=-1` on an i4 dataset (HDF5 2.0).
+        let defined = msg(
+            MessageType::FillValue,
+            &[3, 0x2b, 4, 0, 0, 0, 0xff, 0xff, 0xff, 0xff],
+        );
+        assert_eq!(parse_fill_value(&defined).unwrap(), Some(vec![0xff; 4]));
+        let default = msg(MessageType::FillValue, &[3, 0x0a]);
+        assert_eq!(parse_fill_value(&default).unwrap(), None);
+        let undefined = msg(MessageType::FillValue, &[3, 0x19]);
+        assert_eq!(parse_fill_value(&undefined).unwrap(), None);
+    }
+
+    #[test]
+    fn parses_v2_and_old_messages() {
+        let v2 = msg(MessageType::FillValue, &[2, 2, 2, 1, 2, 0, 0, 0, 7, 0]);
+        assert_eq!(parse_fill_value(&v2).unwrap(), Some(vec![7, 0]));
+        let v2_undefined = msg(MessageType::FillValue, &[2, 2, 2, 0]);
+        assert_eq!(parse_fill_value(&v2_undefined).unwrap(), None);
+        let old = msg(MessageType::FillValueOld, &[2, 0, 0, 0, 9, 9]);
+        assert_eq!(parse_fill_value(&old).unwrap(), Some(vec![9, 9]));
+    }
+
+    #[test]
+    fn truncated_or_oversized_fill_is_an_error() {
+        let short = msg(MessageType::FillValue, &[3, 0x29, 4, 0, 0, 0, 0xff]);
+        assert!(parse_fill_value(&short).is_err());
+        let huge = msg(MessageType::FillValue, &[3, 0x29, 0xff, 0xff, 0xff, 0x7f]);
+        assert!(matches!(
+            parse_fill_value(&huge),
+            Err(FormatError::Overflow(_))
+        ));
+    }
+
+    #[test]
+    fn fill_cell_clips_edge_chunks_in_2d() {
+        // 3x5 dataset, 2x2 chunks; fill grid cell (1, 2): rows 2..3, cols 4..5.
+        let mut out = vec![0u8; 15];
+        fill_cell(&mut out, &[1, 2], &[2, 2], &[3, 5], &[5, 1], 1, &[9]);
+        let mut expected = vec![0u8; 15];
+        expected[2 * 5 + 4] = 9;
+        assert_eq!(out, expected);
+
+        // Interior cell (0, 1): rows 0..2, cols 2..4.
+        let mut out = vec![0u8; 15];
+        fill_cell(&mut out, &[0, 1], &[2, 2], &[3, 5], &[5, 1], 1, &[7]);
+        let filled: Vec<usize> = out
+            .iter()
+            .enumerate()
+            .filter(|(_, b)| **b == 7)
+            .map(|(i, _)| i)
+            .collect();
+        assert_eq!(filled, [2, 3, 7, 8]);
+    }
+}

crates/clawhdf5-format/src/lib.rs

@@ -67,6 +67,7 @@ pub mod ea_writer;
 pub mod error;
 pub mod extensible_array;
 pub mod file_writer;
+pub mod fill_value;
 pub mod filter_pipeline;
 pub mod filters;
 mod filters_szip;

crates/clawhdf5/src/lazy.rs

@@ -480,15 +480,27 @@ impl<'f, R: HDF5Read> LazyDataset<'f, R> {
         let dl = self.data_layout()?;
         let pipeline = self.filter_pipeline()?;
         let data = self.file.reader.as_bytes();
-        Ok(data_read::read_raw_data_full(
+        // Unallocated storage reads as the dataset's fill value.
+        clawhdf5_format::fill_value::read_full_with_fill(
+            &self.header.messages,
             data,
             &dl,
             &ds,
-            &dt,
-            pipeline.as_ref(),
+            dt.type_size() as usize,
             self.file.offset_size(),
             self.file.length_size(),
-        )?)
+            || {
+                Ok(data_read::read_raw_data_full(
+                    data,
+                    &dl,
+                    &ds,
+                    &dt,
+                    pipeline.as_ref(),
+                    self.file.offset_size(),
+                    self.file.length_size(),
+                )?)
+            },
+        )
     }
 }
 

crates/clawhdf5/src/mmap_file.rs

@@ -420,15 +420,27 @@ impl<'f> MmapDataset<'f> {
         let ds = self.dataspace()?;
         let dl = self.data_layout()?;
         let pipeline = self.filter_pipeline()?;
-        Ok(data_read::read_raw_data_full(
+        // Unallocated storage reads as the dataset's fill value.
+        clawhdf5_format::fill_value::read_full_with_fill(
+            &self.header.messages,
             self.file.reader.as_bytes(),
             &dl,
             &ds,
-            &dt,
-            pipeline.as_ref(),
+            dt.type_size() as usize,
             self.file.offset_size(),
             self.file.length_size(),
-        )?)
+            || {
+                Ok(data_read::read_raw_data_full(
+                    self.file.reader.as_bytes(),
+                    &dl,
+                    &ds,
+                    &dt,
+                    pipeline.as_ref(),
+                    self.file.offset_size(),
+                    self.file.length_size(),
+                )?)
+            },
+        )
     }
 }
 

crates/clawhdf5/src/reader.rs

@@ -448,6 +448,24 @@ impl<'f> Dataset<'f> {
         let ds = self.dataspace()?;
         let dl = self.data_layout()?;
         let pipeline = self.filter_pipeline()?;
+        // The selection reader knows nothing about fill values. When they
+        // matter — no storage at all, or a non-zero fill on a chunked (possibly
+        // sparse) dataset — select from a fill-aware full read instead. (The
+        // selection reader currently decodes the full dataset too, so this
+        // costs nothing extra.)
+        let fill = clawhdf5_format::fill_value::dataset_fill_value(&self.header.messages)?;
+        let fill_matters = !clawhdf5_format::fill_value::has_storage(&dl)
+            || (matches!(dl, DataLayout::Chunked { .. })
+                && !clawhdf5_format::fill_value::is_default(fill.as_deref()));
+        if fill_matters {
+            let full = self.read_raw()?;
+            return Ok(data_read::extract_selection_from_buffer(
+                &full,
+                &ds.dimensions,
+                dt.type_size() as usize,
+                selection,
+            )?);
+        }
         Ok(data_read::read_raw_data_selection(
             self.file.data.as_bytes(),
             &dl,
@@ -808,16 +826,28 @@ impl<'f> Dataset<'f> {
             )?);
         }
 
-        Ok(data_read::read_raw_data_cached(
+        // Unallocated storage reads as the dataset's fill value.
+        clawhdf5_format::fill_value::read_full_with_fill(
+            &self.header.messages,
             self.file.data.as_bytes(),
             &dl,
             &ds,
-            &dt,
-            pipeline.as_ref(),
+            dt.type_size() as usize,
             self.file.offset_size(),
             self.file.length_size(),
-            &self.file.chunk_cache,
-        )?)
+            || {
+                Ok(data_read::read_raw_data_cached(
+                    self.file.data.as_bytes(),
+                    &dl,
+                    &ds,
+                    &dt,
+                    pipeline.as_ref(),
+                    self.file.offset_size(),
+                    self.file.length_size(),
+                    &self.file.chunk_cache,
+                )?)
+            },
+        )
     }
 }
 

crates/clawhdf5/tests/h5py_interop_tests.rs

@@ -614,3 +614,88 @@ with h5py.File("{path_str}", "w"{kwargs}) as f:
         );
     }
 }
+
+// ---------------------------------------------------------------------------
+// h5py writes sparse / never-written datasets -> clawhdf5 applies fill values
+// ---------------------------------------------------------------------------
+
+/// Parse h5py's `print(arr.ravel().tolist())` output for integer data.
+fn parse_int_list(s: &str) -> Vec<i32> {
+    s.trim()
+        .trim_matches(|c| c == '[' || c == ']')
+        .split(',')
+        .filter(|t| !t.trim().is_empty())
+        .map(|t| t.trim().parse().unwrap())
+        .collect()
+}
+
+/// Storage HDF5 never allocated must read as the dataset's fill value. These
+/// used to read as zeros (silently wrong for a non-zero fill value) or fail
+/// outright (`NoDataAllocated`) for a dataset that was never written.
+#[test]
+fn h5py_fill_values_clawhdf5_reads() {
+    skip_if_no_python!();
+    let dir = tempfile::tempdir().unwrap();
+    for (tag, kwargs) in [("default", ""), ("latest", ", libver='latest'")] {
+        let path = dir.path().join(format!("fill_{tag}.h5"));
+        let path_str = path.display().to_string();
+        let script = format!(
+            r#"
+import h5py, numpy as np
+with h5py.File("{path_str}", "w"{kwargs}) as f:
+    d = f.create_dataset("partial", shape=(20,), dtype="<i4", chunks=(5,), fillvalue=-1)
+    d[0:5] = np.arange(5)
+    f.create_dataset("never", shape=(4,), dtype="<i4", fillvalue=25)
+    f.create_dataset("never_chunked", shape=(6,), dtype="<i4", chunks=(3,), fillvalue=9)
+    f.create_dataset("default_fill", shape=(3,), dtype="<i4")
+    g = f.create_dataset("gz", shape=(20,), dtype="<i4", chunks=(5,), fillvalue=7, compression="gzip")
+    g[10:15] = 1
+    s = f.create_dataset("sparse2d", shape=(5, 7), dtype="<i4", chunks=(2, 3), fillvalue=-3)
+    s[2:4, 3:6] = 8
+    s[4, 6] = 5
+with h5py.File("{path_str}", "r") as f:
+    for name in ["partial", "never", "never_chunked", "default_fill", "gz", "sparse2d"]:
+        print(name, f[name][...].ravel().tolist())
+    print("slab", f["sparse2d"][1:5, 2:7].ravel().tolist())
+"#
+        );
+        let expected: std::collections::HashMap<String, Vec<i32>> = run_python_output(&script)
+            .lines()
+            .map(|line| {
+                let (name, list) = line.split_once(' ').unwrap();
+                (name.to_string(), parse_int_list(list))
+            })
+            .collect();
+
+        let file = File::open(&path).unwrap();
+        for name in [
+            "partial",
+            "never",
+            "never_chunked",
+            "default_fill",
+            "gz",
+            "sparse2d",
+        ] {
+            assert_eq!(
+                file.dataset(name).unwrap().read_i32().unwrap(),
+                expected[name],
+                "{tag}/{name}"
+            );
+        }
+        // A hyperslab straddling allocated and unallocated chunks.
+        let slab = clawhdf5_format::selection::Selection::Hyperslab {
+            start: vec![1, 2],
+            stride: vec![1, 1],
+            count: vec![4, 5],
+            block: vec![1, 1],
+        };
+        assert_eq!(
+            file.dataset("sparse2d")
+                .unwrap()
+                .read_i32_selection(&slab)
+                .unwrap(),
+            expected["slab"],
+            "{tag}/sparse2d hyperslab"
+        );
+    }
+}