fix(format): read a v1 chunk B-tree where libhdf5's lookup finds chunks

libhdf5 does not walk the chunk B-tree to read a dataset: it looks each
chunk up (H5B_find with H5D__btree_cmp3 and H5D__btree_found), asking for
the element-size coordinate as 0. collect_chunk_info_checked now parses
the tree with its keys and returns each stored chunk only when that
lookup, replayed over the scaled keys, finds it.

A key with a non-zero element-size coordinate is therefore found in a
1-D dataset (cmp3 compares only the first coordinate there, and found
compares with <=) and missed in a dataset of rank 2 or more, which reads
fill values. The previous commit refused every such key, which refused
1-D files libhdf5 reads correctly; before that, the rank-2 case read the
chunk's data where h5py reads fill values (cve-2025-44905
/Shuffle_float_data_le, now identical to h5py, so it leaves the
conformance report's list of libhdf5 bugs).

Test: chunk_keys_with_an_element_offset_read_as_libhdf5_reads_them
compares 1-D and 2-D files against h5py's values. It fails on the
previous commit (the 1-D file is refused) and with the refusal removed
(the 2-D file reads 0..23 where h5py reads fill values).

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

CHANGELOG.md

@@ -40,8 +40,15 @@ ZFP filters; the 2 mismatches are the known h5py big-endian VL bug.
   - shuffle uses its own parameter as the element size, as libhdf5 does
     (`cve-2025-44905`);
   - an unfiltered chunk the index records at other than the chunk's size is
-    refused (it read with zeros for the missing bytes; `cve-2025-44904`),
+    refused (it read with zeros for the missing bytes; `cve-2025-44904`);
-    as is a chunk B-tree key with a non-zero element offset.
+  - a v1 B-tree chunk index is read as libhdf5 reads it: each chunk is
+    looked up the way `H5B_find` / `H5D__btree_cmp3` / `H5D__btree_found`
+    look it up, and a chunk that lookup does not find reads as fill values.
+    A key with a non-zero element-size coordinate is found in a 1-D dataset
+    and not in one of rank 2 or more (`cve-2025-44905`
+    `/Shuffle_float_data_le`, which read the chunk's data where h5py reads
+    fill values); an interim fix refused every such key, including 1-D
+    files libhdf5 reads correctly.
 - **Refused as libhdf5 refuses them:** a v1 group with an empty link name
   fails its listing (`FormatError::InvalidLinkName`; lookups still work,
   `cve-2021-46244`); dataspaces with more than 32 dimensions, a rank on a

conformance/report.py

@@ -100,8 +100,8 @@ def is_h5py_be_vlen(i):
 
 # Objects the reference (h5py 3.16 / HDF5 2.0) reads only because of an
 # HDF5 2.0 bug, and that clawhdf5 refuses: each one reads past a buffer or
-# returns bytes the file does not hold, and libhdf5's develop branch refuses the
+# returns bytes the file does not hold, and libhdf5's develop branch refuses all
-# first three. (file, object) -> why. Checked 2026-09-26 against HDF5 2.0.0
+# three. (file, object) -> why. Checked 2026-09-26 against HDF5 2.0.0
 # and HDFGroup/hdf5 develop sources; see docs/known-issues.md.
 LIBHDF5_BUGS = {
     ("cve_hdf5/cvefiles/cve-2025-2308.h5", "/Scale_offset_long_long_data_le"):
@@ -114,9 +114,6 @@ LIBHDF5_BUGS = {
     ("hdf5/test/testfiles/bad_nbit_parms_walk.h5", "/Nbit_int_data_le"):
         "an N-Bit parameter list one value short: HDF5 2.0 reads past the list; libhdf5's own "
         "test (`test_filter_bad_params`, test/dsets.c) now requires the read to fail",
-    ("cve_hdf5/cvefiles/cve-2025-44905.h5", "/Shuffle_float_data_le"):
-        "a chunk B-tree key with element offset 4096: libhdf5's lookup misses the chunk and "
-        "returns fill values for data the file holds; clawhdf5 refuses the key",
 }
 
 

crates/clawhdf5-format/src/chunked_read.rs

@@ -316,26 +316,41 @@ pub fn collect_chunk_info(
     offset_size: u8,
     length_size: u8,
 ) -> Result<Vec<ChunkInfo>, FormatError> {
-    collect_chunk_info_inner(
+    let _ = length_size;
+    let mut chunks = Vec::new();
+    parse_chunk_node(
         file_data,
         btree_address,
         ndims,
         None,
         offset_size,
-        length_size,
         0,
-    )
+        &mut chunks,
+    )?;
+    Ok(chunks)
 }
 
-/// [`collect_chunk_info`] for a layout with these `chunk_dimensions` (the
+/// The chunks of a v1 B-tree chunk index as libhdf5 reads them, for a
-/// layout message's list, element size last), checking every key of the
+/// layout with these `chunk_dimensions` (the layout message's list, element
-/// B-tree as libhdf5 does (`H5D__btree_decode_key`): each coordinate offset
+/// size last).
-/// must be a multiple of its chunk dimension. That includes the keys that
+///
-/// only bound a node (internal-node keys and each node's final key), which
+/// Every key of the B-tree is checked as libhdf5 checks it
-/// is where a corrupt chunk dimension shows when the chunks themselves all
+/// (`H5D__btree_decode_key`): each coordinate offset must be a multiple of
-/// start at offset 0 in that dimension (`cve-2018-11205`). A key that fails
+/// its chunk dimension. That includes the keys that only bound a node
-/// ("bad coordinate offset") means a corrupt index or chunk dimension; the
+/// (internal-node keys and each node's final key), which is where a
-/// chunks were read at the wrong place, or the dataset read as fill values.
+/// corrupt chunk dimension shows when the chunks themselves all start at
+/// offset 0 in that dimension (`cve-2018-11205`). A key that fails ("bad
+/// coordinate offset") means a corrupt index or chunk dimension.
+///
+/// libhdf5 does not read a chunk by walking the tree: it looks each chunk
+/// up (`H5B_find` with `H5D__btree_cmp3` and `H5D__btree_found`), comparing
+/// the element-size coordinate too, which it asks for as 0. So a chunk is
+/// returned only where that lookup finds it: a key whose element-size
+/// coordinate is not 0 is found in a 1-D dataset (the comparison looks at
+/// that coordinate only against the next key) but not in a dataset of rank
+/// 2 or more (`cve-2025-44905` `/Shuffle_float_data_le`), which then reads
+/// as fill values, and a tree whose keys are out of order loses the chunks
+/// libhdf5's binary search misses.
 pub fn collect_chunk_info_checked(
     file_data: &[u8],
     btree_address: u64,
@@ -343,15 +358,141 @@ pub fn collect_chunk_info_checked(
     offset_size: u8,
     length_size: u8,
 ) -> Result<Vec<ChunkInfo>, FormatError> {
-    collect_chunk_info_inner(
+    let _ = length_size;
+    let ndims = chunk_dimensions.len();
+    if ndims == 0 {
+        return Err(FormatError::ChunkedReadError(
+            "chunk layout has no dimensions".into(),
+        ));
+    }
+    let mut stored = Vec::new();
+    let mut root = parse_chunk_node(
         file_data,
         btree_address,
-        chunk_dimensions.len(),
+        ndims,
         Some(chunk_dimensions),
         offset_size,
-        length_size,
         0,
-    )
+        &mut stored,
+    )?;
+    // Keys were checked to be multiples of non-zero dimensions.
+    root.scale_keys(chunk_dimensions);
+    // Look every stored chunk's position up. A lookup finds a chunk only at
+    // that chunk's own position, so each is returned at most once.
+    let mut returned = vec![false; stored.len()];
+    let mut wanted = vec![0u64; ndims];
+    for chunk in &stored {
+        for (w, (&o, &d)) in wanted
+            .iter_mut()
+            .zip(chunk.offsets.iter().zip(chunk_dimensions))
+        {
+            *w = o / u64::from(d);
+        }
+        wanted[ndims - 1] = 0;
+        if let Some(i) = root.find(&wanted) {
+            returned[i] = true;
+        }
+    }
+    Ok(stored
+        .into_iter()
+        .zip(returned)
+        .filter_map(|(c, r)| r.then_some(c))
+        .collect())
+}
+
+/// A node of a v1 B-tree chunk index: its `n + 1` keys (`ndims`
+/// coordinates each, flattened; byte offsets as stored, or scaled by the
+/// chunk dimensions after [`ChunkNode::scale_keys`]) and its `n` children,
+/// a leaf's as indices into the list of stored chunks.
+struct ChunkNode {
+    ndims: usize,
+    keys: Vec<u64>,
+    children: ChunkChildren,
+}
+
+enum ChunkChildren {
+    Nodes(Vec<ChunkNode>),
+    Chunks(Vec<usize>),
+}
+
+impl ChunkNode {
+    fn key(&self, i: usize) -> &[u64] {
+        &self.keys[i * self.ndims..(i + 1) * self.ndims]
+    }
+
+    fn len(&self) -> usize {
+        match &self.children {
+            ChunkChildren::Nodes(n) => n.len(),
+            ChunkChildren::Chunks(c) => c.len(),
+        }
+    }
+
+    fn scale_keys(&mut self, dims: &[u32]) {
+        for (k, &d) in self.keys.iter_mut().zip(dims.iter().cycle()) {
+            *k /= u64::from(d);
+        }
+        if let ChunkChildren::Nodes(nodes) = &mut self.children {
+            for n in nodes {
+                n.scale_keys(dims);
+            }
+        }
+    }
+
+    /// `H5B_find_helper` over scaled keys: binary search for the child
+    /// whose keys bracket `scaled`, then `H5D__btree_found` at the leaf.
+    /// Returns the index of the chunk found.
+    fn find(&self, scaled: &[u64]) -> Option<usize> {
+        let (mut lt, mut rt) = (0, self.len());
+        let mut idx = 0;
+        let mut cmp = core::cmp::Ordering::Greater;
+        while lt < rt && cmp != core::cmp::Ordering::Equal {
+            idx = (lt + rt) / 2;
+            cmp = btree_cmp3(self.key(idx), scaled, self.key(idx + 1));
+            if cmp == core::cmp::Ordering::Less {
+                rt = idx;
+            } else {
+                lt = idx + 1;
+            }
+        }
+        if cmp != core::cmp::Ordering::Equal {
+            return None;
+        }
+        match &self.children {
+            ChunkChildren::Nodes(nodes) => nodes[idx].find(scaled),
+            ChunkChildren::Chunks(chunks) => {
+                // "Is this *really* the requested chunk?"
+                let lt_key = self.key(idx);
+                let found = scaled
+                    .iter()
+                    .zip(lt_key)
+                    .all(|(&s, &k)| s < k.wrapping_add(1));
+                found.then_some(chunks[idx])
+            }
+        }
+    }
+}
+
+/// `H5D__btree_cmp3`: where `scaled` falls against a child's left and
+/// right keys. `Less` is left of the child, `Greater` right of it. With a
+/// rank-1 dataset (two coordinates, element size last) libhdf5 compares
+/// only the first coordinate, and the second against the right key.
+fn btree_cmp3(lt: &[u64], scaled: &[u64], rt: &[u64]) -> core::cmp::Ordering {
+    use core::cmp::Ordering;
+    if scaled.len() == 2 {
+        if scaled[0] > rt[0] || (scaled[0] == rt[0] && scaled[1] >= rt[1]) {
+            Ordering::Greater
+        } else if scaled[0] < lt[0] {
+            Ordering::Less
+        } else {
+            Ordering::Equal
+        }
+    } else if scaled >= rt {
+        Ordering::Greater
+    } else if scaled < lt {
+        Ordering::Less
+    } else {
+        Ordering::Equal
+    }
 }
 
 /// Check one v1 B-tree chunk key's offsets (see
@@ -368,24 +509,25 @@ fn check_key_offsets(offsets: &[u64], chunk_dimensions: &[u32]) -> Result<(), Fo
 }
 
 /// Read the `ndims` 8-byte offsets of the chunk key at `pos` (after its
-/// chunk size and filter mask) and check them when `chunk_dimensions` is
+/// chunk size and filter mask) into `out`, checking them when
-/// given.
+/// `chunk_dimensions` is given.
 fn read_key_offsets(
     file_data: &[u8],
     pos: usize,
     ndims: usize,
     chunk_dimensions: Option<&[u32]>,
-) -> Result<Vec<u64>, FormatError> {
+    out: &mut Vec<u64>,
-    let mut offsets = Vec::with_capacity(ndims);
+) -> Result<(), FormatError> {
+    let start = out.len();
     let mut kp = pos + 8;
     for _ in 0..ndims {
-        offsets.push(read_offset(file_data, kp, CHUNK_KEY_OFFSET_SIZE)?);
+        out.push(read_offset(file_data, kp, CHUNK_KEY_OFFSET_SIZE)?);
         kp += CHUNK_KEY_OFFSET_SIZE as usize;
     }
     if let Some(dims) = chunk_dimensions {
-        check_key_offsets(&offsets, dims)?;
+        check_key_offsets(&out[start..], dims)?;
     }
-    Ok(offsets)
+    Ok(())
 }
 
 /// Width of each chunk offset in a v1 chunk B-tree key, independent of the
@@ -396,15 +538,17 @@ const CHUNK_KEY_OFFSET_SIZE: u8 = 8;
 /// protection), matching `btree_v1.rs`'s `MAX_BTREE_DEPTH`.
 const MAX_CHUNK_BTREE_DEPTH: usize = 64;
 
-fn collect_chunk_info_inner(
+/// Parse the v1 B-tree chunk index node at `btree_address` and its
+/// subtree, appending its chunks to `stored` in tree order.
+fn parse_chunk_node(
     file_data: &[u8],
     btree_address: u64,
     ndims: usize,
     chunk_dimensions: Option<&[u32]>,
     offset_size: u8,
-    _length_size: u8,
     depth: usize,
-) -> Result<Vec<ChunkInfo>, FormatError> {
+    stored: &mut Vec<ChunkInfo>,
+) -> Result<ChunkNode, FormatError> {
     if depth > MAX_CHUNK_BTREE_DEPTH {
         return Err(FormatError::NestingDepthExceeded);
     }
@@ -439,15 +583,14 @@ fn collect_chunk_info_inner(
         .and_then(|n| n.checked_add(8))
         .ok_or_else(|| FormatError::ChunkedReadError("chunk key too large".into()))?;
 
-    if node_level == 0 {
-        // Leaf node: keys and children interleaved
     // key[0], child[0], key[1], child[1], ..., key[N-1], child[N-1], key[N]
     let needed = entries_used * (key_size + os) + key_size;
     ensure_len(file_data, pos, needed)?;
 
-        let mut chunks = Vec::with_capacity(entries_used);
+    let mut keys = Vec::with_capacity((entries_used + 1) * ndims);
+    let mut chunks = Vec::new();
+    let mut child_addrs = Vec::new();
     for _ in 0..entries_used {
-            // Parse key
         let chunk_size = u32::from_le_bytes([
             file_data[pos],
             file_data[pos + 1],
@@ -460,64 +603,48 @@ fn collect_chunk_info_inner(
             file_data[pos + 6],
             file_data[pos + 7],
         ]);
-            let offsets = read_key_offsets(file_data, pos, ndims, chunk_dimensions)?;
+        let k = keys.len();
-            // A chunk's key carries 0 in the element-size dimension. libhdf5
+        read_key_offsets(file_data, pos, ndims, chunk_dimensions, &mut keys)?;
-            // compares that coordinate too when it looks a chunk up
-            // (`H5D__btree_found`), so whether it finds a chunk keyed
-            // otherwise depends on where the key falls; in `cve-2025-44905`
-            // `/Shuffle_float_data_le` (offset 4096) it does not, and h5py
-            // reads fill values there. Such a key is refused here.
-            if chunk_dimensions.is_some() && offsets.last().is_some_and(|&o| o != 0) {
-                return Err(FormatError::ChunkedReadError(format!(
-                    "chunk key {offsets:?} has a non-zero element offset"
-                )));
-            }
         pos += key_size;
-
-            // Parse child address
         let address = read_offset(file_data, pos, offset_size)?;
         pos += os;
-
+        if node_level == 0 {
-            chunks.push(ChunkInfo {
+            chunks.push(stored.len());
+            stored.push(ChunkInfo {
                 chunk_size,
                 filter_mask,
-                offsets,
+                offsets: keys[k..].to_vec(),
                 address,
             });
+        } else {
+            child_addrs.push(address);
+        }
     }
     // The final key only bounds the node; libhdf5 still checks it.
-        read_key_offsets(file_data, pos, ndims, chunk_dimensions)?;
+    read_key_offsets(file_data, pos, ndims, chunk_dimensions, &mut keys)?;
-        Ok(chunks)
+
+    let children = if node_level == 0 {
+        ChunkChildren::Chunks(chunks)
     } else {
-        // Internal node: recurse into children
+        let mut nodes = Vec::with_capacity(child_addrs.len());
-        let needed = entries_used * (key_size + os) + key_size;
-        ensure_len(file_data, pos, needed)?;
-
-        let mut child_addrs = Vec::with_capacity(entries_used);
-        for _ in 0..entries_used {
-            read_key_offsets(file_data, pos, ndims, chunk_dimensions)?;
-            pos += key_size;
-            let child_addr = read_offset(file_data, pos, offset_size)?;
-            child_addrs.push(child_addr);
-            pos += os;
-        }
-        read_key_offsets(file_data, pos, ndims, chunk_dimensions)?;
-
-        let mut all_chunks = Vec::new();
         for child_addr in child_addrs {
-            let child_chunks = collect_chunk_info_inner(
+            nodes.push(parse_chunk_node(
                 file_data,
                 child_addr,
                 ndims,
                 chunk_dimensions,
                 offset_size,
-                _length_size,
                 depth + 1,
-            )?;
+                stored,
-            all_chunks.extend(child_chunks);
+            )?);
-        }
-        Ok(all_chunks)
         }
+        ChunkChildren::Nodes(nodes)
+    };
+    Ok(ChunkNode {
+        ndims,
+        keys,
+        children,
+    })
 }
 
 /// Generate ChunkInfo entries for an implicit index (v4 index type 2).
@@ -1754,6 +1881,25 @@ mod tests {
 
     /// Build a B-tree v1 type 1 leaf node with given chunk infos.
     fn build_chunk_btree_leaf(chunks: &[ChunkInfo], ndims: usize, offset_size: u8) -> Vec<u8> {
+        build_chunk_btree_leaf_to(chunks, &vec![0; ndims], offset_size)
+    }
+
+    /// A leaf whose final key is the one libhdf5 writes past the last chunk:
+    /// each coordinate of the last chunk plus its chunk dimension (the
+    /// element size last).
+    fn build_chunk_btree_leaf_dims(chunks: &[ChunkInfo], dims: &[u32], offset_size: u8) -> Vec<u8> {
+        let last = &chunks.last().expect("a chunk").offsets;
+        let end: Vec<u64> = dims
+            .iter()
+            .enumerate()
+            .map(|(d, &c)| last.get(d).copied().unwrap_or(0) + u64::from(c))
+            .collect();
+        build_chunk_btree_leaf_to(chunks, &end, offset_size)
+    }
+
+    /// A leaf holding `chunks`, with final key `end`.
+    fn build_chunk_btree_leaf_to(chunks: &[ChunkInfo], end: &[u64], offset_size: u8) -> Vec<u8> {
+        let ndims = end.len();
         let _os = offset_size as usize;
         let entries_used = chunks.len() as u16;
         let mut buf = Vec::new();
@@ -1795,8 +1941,8 @@ mod tests {
         // checks; 0 always is)
         buf.extend_from_slice(&0u32.to_le_bytes()); // chunk_size
         buf.extend_from_slice(&0u32.to_le_bytes()); // filter_mask
-        for _ in 0..ndims {
+        for &e in end {
-            write_offset(&mut buf, 0, 8);
+            write_offset(&mut buf, e, 8);
         }
 
         buf
@@ -1812,8 +1958,11 @@ mod tests {
             offsets,
             address,
         };
-        let good =
+        let good = build_chunk_btree_leaf_dims(
-            build_chunk_btree_leaf(&[chunk(vec![0, 0], 0x100), chunk(vec![10, 0], 0x200)], 2, 8);
+            &[chunk(vec![0, 0], 0x100), chunk(vec![10, 0], 0x200)],
+            &[10, 8],
+            8,
+        );
         assert_eq!(
             collect_chunk_info_checked(&good, 0, &[10, 8], 8, 8)
                 .unwrap()
@@ -2044,7 +2193,6 @@ mod tests {
     ) -> (Vec<u8>, DataLayout, Dataspace) {
         let os: u8 = 8;
         let elem_size = 8usize;
-        let ndims = 2; // rank(1) + 1
         let total = values.len();
 
         // Place chunk data starting at offset 0x2000
@@ -2075,12 +2223,13 @@ mod tests {
         }
 
         // Build B-tree at offset 0x100
-        let btree = build_chunk_btree_leaf(&chunk_infos, ndims, os);
+        let dims = [chunk_size_elems as u32, elem_size as u32];
+        let btree = build_chunk_btree_leaf_dims(&chunk_infos, &dims, os);
         let btree_addr = 0x100usize;
         file_data[btree_addr..btree_addr + btree.len()].copy_from_slice(&btree);
 
         let layout = DataLayout::Chunked {
-            chunk_dimensions: vec![chunk_size_elems as u32, elem_size as u32],
+            chunk_dimensions: dims.to_vec(),
             btree_address: Some(btree_addr as u64),
             version: 3,
             chunk_index_type: None,
@@ -2218,7 +2367,6 @@ mod tests {
 
         let os: u8 = 8;
         let elem_size = 8usize;
-        let ndims = 2;
         let chunk_elems = 10usize;
         let total = 20usize;
 
@@ -2257,12 +2405,13 @@ mod tests {
             data_offset += compressed.len() + 16; // some padding
         }
 
-        let btree = build_chunk_btree_leaf(&chunk_infos, ndims, os);
+        let dims = [chunk_elems as u32, elem_size as u32];
+        let btree = build_chunk_btree_leaf_dims(&chunk_infos, &dims, os);
         let btree_addr = 0x100usize;
         file_data[btree_addr..btree_addr + btree.len()].copy_from_slice(&btree);
 
         let layout = DataLayout::Chunked {
-            chunk_dimensions: vec![chunk_elems as u32, elem_size as u32],
+            chunk_dimensions: dims.to_vec(),
             btree_address: Some(btree_addr as u64),
             version: 3,
             chunk_index_type: None,
@@ -2300,7 +2449,6 @@ mod tests {
         // 4x6 dataset with chunk size 2x3 => 4 chunks
         let os: u8 = 8;
         let elem_size = 4usize; // f32
-        let ndims = 3; // rank(2) + 1
         let ds_dims = [4usize, 6];
         let chunk_dims = [2usize, 3];
 
@@ -2340,12 +2488,13 @@ mod tests {
             }
         }
 
-        let btree = build_chunk_btree_leaf(&chunk_infos, ndims, os);
+        let dims = [chunk_dims[0] as u32, chunk_dims[1] as u32, elem_size as u32];
+        let btree = build_chunk_btree_leaf_dims(&chunk_infos, &dims, os);
         let btree_addr = 0x100usize;
         file_data[btree_addr..btree_addr + btree.len()].copy_from_slice(&btree);
 
         let layout = DataLayout::Chunked {
-            chunk_dimensions: vec![chunk_dims[0] as u32, chunk_dims[1] as u32, elem_size as u32],
+            chunk_dimensions: dims.to_vec(),
             btree_address: Some(btree_addr as u64),
             version: 3,
             chunk_index_type: None,

crates/clawhdf5/tests/header_validation_interop.rs

@@ -629,17 +629,13 @@ save("mdc_past_eof", bad)
     );
 }
 
-/// Chunk index entries HDF5 2.0 mis-reads, refused here. An unfiltered
+/// An unfiltered chunk the index records at less than the chunk's size
-/// chunk the index records at less than the chunk's size (`cve-2025-44904`):
+/// (`cve-2025-44904`): HDF5 2.0 fills the rest of the chunk with whatever
-/// HDF5 2.0 fills the rest of the chunk with whatever its buffer held, and
+/// its buffer held, and later libhdf5 releases refuse it ("incorrect chunk
-/// later libhdf5 releases refuse it ("incorrect chunk size returned from
+/// size returned from index for unfiltered chunk"); we used to read the
-/// index for unfiltered chunk"); we read the rest as zeros. A chunk keyed
+/// rest as zeros, and now refuse it.
-/// with a non-zero element offset (`cve-2025-44905`): libhdf5's lookup
-/// compares that coordinate too, so whether it finds the chunk depends on
-/// where the key falls (in `cve-2025-44905` it does not, and h5py reads
-/// fill values; in this file it does); we read the chunk.
 #[test]
-fn chunk_index_entries_libhdf5_misreads_are_refused() {
+fn unfiltered_chunk_of_the_wrong_size_is_refused() {
     skip_if_no_python!();
     let dir = tempfile::tempdir().unwrap();
     run_python(
@@ -658,8 +654,6 @@ second = key + 24 + 8  # a key (4 + 4 + 2 x 8 bytes), then a child address
 assert struct.unpack_from("<IIQQ", data, second) == (148, 0, 37, 0)
 bad = bytearray(data); struct.pack_into("<I", bad, second, 100)
 open(os.path.join(d, "short_chunk.h5"), "wb").write(bad)
-bad = bytearray(data); struct.pack_into("<Q", bad, second + 16, 4096)
-open(os.path.join(d, "element_offset.h5"), "wb").write(bad)
 "#,
     );
     assert_eq!(
@@ -667,8 +661,58 @@ open(os.path.join(d, "element_offset.h5"), "wb").write(bad)
         Ok(()),
         "good"
     );
-    for name in ["short_chunk", "element_offset"] {
+    let err = clawhdf5_reads(&dir.path().join("short_chunk.h5"), "d").unwrap_err();
-        let err = clawhdf5_reads(&dir.path().join(format!("{name}.h5")), "d").unwrap_err();
+    assert!(err.starts_with("read:"), "short_chunk: {err}");
-        assert!(err.starts_with("read:"), "{name}: {err}");
+}
+
+/// A v1 B-tree chunk key whose element-size coordinate is not 0. libhdf5
+/// looks each chunk up with that coordinate set to 0 (`H5B_find`,
+/// `H5D__btree_cmp3`, `H5D__btree_found`): in a 1-D dataset it still finds
+/// the chunk, in a 2-D one it does not and reads fill values
+/// (`cve-2025-44905` `/Shuffle_float_data_le`). Both must read exactly what
+/// h5py reads: the 1-D file was refused, and before that the 2-D chunk was
+/// read as if its key were well formed.
+#[test]
+fn chunk_keys_with_an_element_offset_read_as_libhdf5_reads_them() {
+    skip_if_no_python!();
+    let dir = tempfile::tempdir().unwrap();
+    run_python(
+        dir.path(),
+        r#"
+def corrupt(name, shape, chunks, which, element_offset):
+    path = os.path.join(d, name + ".h5")
+    with h5py.File(path, "w", libver="earliest") as f:
+        f.create_dataset("d", data=np.arange(np.prod(shape), dtype="<i4").reshape(shape),
+                         chunks=chunks, fillvalue=-1)
+    data = bytearray(open(path, "rb").read())
+    tree = data.find(b"TREE")
+    while data[tree + 4] != 1:  # the chunk index, not the root group's B-tree
+        tree = data.find(b"TREE", tree + 1)
+    assert tree > 0 and data[tree + 5] == 0
+    ndims = len(shape) + 1
+    key_size = 8 + 8 * ndims
+    key = tree + 8 + 16 + which * (key_size + 8)
+    last = key + 8 + 8 * (ndims - 1)
+    assert struct.unpack_from("<Q", data, last) == (0,)
+    struct.pack_into("<Q", data, last, element_offset)
+    open(path, "wb").write(data)
+    with h5py.File(path, "r") as f:
+        open(path + ".txt", "w").write(" ".join(map(str, f["d"][()].ravel())))
+
+corrupt("one_d", (100,), (37,), 1, 4096)
+corrupt("two_d", (4, 6), (2, 3), 1, 4)
+corrupt("two_d_first", (4, 6), (2, 3), 0, 8)
+"#,
+    );
+    for name in ["one_d", "two_d", "two_d_first"] {
+        let path = dir.path().join(format!("{name}.h5"));
+        let expected: Vec<i32> = std::fs::read_to_string(dir.path().join(format!("{name}.h5.txt")))
+            .unwrap()
+            .split_whitespace()
+            .map(|v| v.parse().unwrap())
+            .collect();
+        let file = File::open(&path).unwrap();
+        let got = file.dataset("d").unwrap().read_i32();
+        assert_eq!(got.as_deref().ok(), Some(&expected[..]), "{name}: {got:?}");
     }
 }