Merge branch 'feat/p2b-blosc2' into feat/p2b-scale

# Conflicts:
#	CHANGELOG.md

crates/clawhdf5-format/Cargo.toml

@@ -76,8 +76,10 @@ bitshuffle = ["lz4_flex", "ruzstd"]
 bzip2 = ["dep:bzip2", "std"]
 # Blosc 1 (32001) with its BloscLZ, LZ4, Snappy, Zlib and Zstandard codecs.
 blosc = ["lz4_flex", "ruzstd", "snap", "deflate", "std"]
+# Blosc2 (32026), read-only: frames, B2ND arrays, and the Blosc codecs above.
+blosc2 = ["blosc"]
 # Every plugin filter above.
-plugin-filters = ["lzf", "bitshuffle", "bzip2", "blosc"]
+plugin-filters = ["lzf", "bitshuffle", "bzip2", "blosc", "blosc2"]
 
 [[bench]]
 name = "parallel_decompress_bench"

crates/clawhdf5-format/src/filter_registry.rs

@@ -5,7 +5,8 @@
 //! * **Built-in filters** — a static table of the filters compiled into this
 //!   build: the HDF5 standard filters (deflate, shuffle, Fletcher32, szip,
 //!   N-Bit, scale-offset) and the plugin filters whose cargo features are
-//!   enabled (LZ4, Zstandard, pcodec, LZF, bitshuffle, bzip2, blosc).
+//!   enabled (LZ4, Zstandard, pcodec, LZF, bitshuffle, bzip2, blosc,
+//!   blosc2).
 //!   [`builtin_filters`] lists them.
 //! * **Registered filters** (`std` only) — codecs the application supplies
 //!   for any other ID with [`register_filter`] (a [`FilterCodec`], or just a
@@ -166,7 +167,7 @@ pub fn known_filter(id: u16) -> Option<(&'static str, Option<&'static str>)> {
         32019 => ("JPEG", None),
         32022 => ("BitGroom", None),
         32023 => ("Granular BitRound", None),
-        32026 => ("Blosc2", None),
+        32026 => ("Blosc2", Some("blosc2")),
         _ => return None,
     })
 }
@@ -452,12 +453,12 @@ pub(crate) mod tests {
     #[test]
     fn unsupported_filter_error_names_the_filter() {
         let msg = FormatError::UnsupportedFilter(32026).to_string();
+        assert!(msg.contains("Blosc2") && msg.contains("`blosc2`"), "{msg}");
+        let msg = FormatError::UnsupportedFilter(32013).to_string();
         assert!(
-            msg.contains("Blosc2") && msg.contains("not implemented"),
+            msg.contains("ZFP") && msg.contains("not implemented"),
             "{msg}"
         );
-        let msg = FormatError::UnsupportedFilter(32013).to_string();
-        assert!(msg.contains("ZFP"), "{msg}");
         let msg = FormatError::UnsupportedFilter(32000).to_string();
         assert!(msg.contains("LZF") && msg.contains("`lzf`"), "{msg}");
         assert_eq!(

crates/clawhdf5-format/src/filters.rs

@@ -455,6 +455,13 @@ pub(crate) static BUILTIN_FILTERS: &[BuiltinFilter] = &[
         },
         encode: None,
     },
+    #[cfg(feature = "blosc2")]
+    BuiltinFilter {
+        id: crate::filter_pipeline::FILTER_BLOSC2,
+        name: "blosc2",
+        decode: crate::filters_blosc2::blosc2_decode,
+        encode: None,
+    },
 ];
 
 /// Decode the HDF5 scale-offset filter (id 6).

crates/clawhdf5-format/src/filters_bitshuffle.rs

@@ -218,12 +218,20 @@ pub(crate) fn bitshuffle_decode(
 }
 
 /// Decode Zstandard frames into exactly `dst`, failing if they hold more.
+///
+/// ruzstd reserves a frame's declared window (by default up to 100 MiB)
+/// before decoding it, so the window is capped at what the output could
+/// need: twice `dst` (window sizes are rounded up), and at least 128 KiB.
+/// The encoders behind these filters (c-blosc, c-blosc2, bitshuffle)
+/// compress each block in one call with its size known, so libzstd's
+/// window never exceeds the block.
 #[cfg(any(feature = "bitshuffle", feature = "blosc"))]
 pub(crate) fn zstd_decode_into(
     decoder: &mut ruzstd::decoding::FrameDecoder,
     frames: &[u8],
     dst: &mut [u8],
 ) -> Result<usize, FormatError> {
+    decoder.set_max_window_size((2 * dst.len()).max(1 << 17) as u64);
     decoder
         .decode_all(frames, dst)
         .map_err(|e| FormatError::DecompressionError(format!("zstd: {e}")))

crates/clawhdf5-format/src/filters_blosc.rs

@@ -49,7 +49,7 @@ fn le32(b: &[u8], at: usize) -> Result<usize, FormatError> {
 
 /// The codec inside a Blosc frame (flags bits 5-7).
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
-enum Codec {
+pub(crate) enum Codec {
     BloscLz,
     Lz4,
     Snappy,
@@ -58,7 +58,7 @@ enum Codec {
 }
 
 impl Codec {
-    fn from_flags(flags: u8) -> Result<Codec, FormatError> {
+    pub(crate) fn from_flags(flags: u8) -> Result<Codec, FormatError> {
         match flags >> 5 {
             0 => Ok(Codec::BloscLz),
             1 => Ok(Codec::Lz4),
@@ -71,7 +71,7 @@ impl Codec {
 }
 
 /// Decode one codec stream into exactly `dst`.
-fn decode_stream(
+pub(crate) fn decode_stream(
     codec: Codec,
     src: &[u8],
     dst: &mut [u8],

crates/clawhdf5-format/src/lib.rs

@@ -87,6 +87,8 @@ pub mod filters;
 mod filters_bitshuffle;
 #[cfg(feature = "blosc")]
 pub mod filters_blosc;
+#[cfg(feature = "blosc2")]
+pub mod filters_blosc2;
 #[cfg(feature = "bzip2")]
 mod filters_bzip2;
 #[cfg(feature = "lzf")]

crates/clawhdf5-format/tests/blosc2_alloc_bounds.rs

@@ -0,0 +1,641 @@
+//! Crafted Blosc2 frames and chunks cannot make the decoder allocate out of
+//! proportion to the HDF5 chunk it decodes.
+//!
+//! A frame's header, its offsets chunk and its chunk headers all declare
+//! sizes, and the decoder used to allocate what they declared: a 173-byte
+//! frame whose offsets chunk claimed 2 GiB was decoded in full before any
+//! check failed. Every allocation is now bounded by the output limit (the
+//! HDF5 chunk's size) and the input's length.
+//!
+//! Peak heap use is measured with a counting global allocator; the tests
+//! share it, so each holds `SERIAL` for its whole run.
+#![cfg(feature = "blosc2")]
+
+use std::alloc::{GlobalAlloc, Layout, System};
+use std::sync::Mutex;
+use std::sync::atomic::{AtomicUsize, Ordering};
+
+use clawhdf5_format::filters_blosc2::{blosc2_decompress, blosc2_decompress_chunk};
+
+struct Counting;
+
+static CURRENT: AtomicUsize = AtomicUsize::new(0);
+static PEAK: AtomicUsize = AtomicUsize::new(0);
+static SERIAL: Mutex<()> = Mutex::new(());
+
+unsafe impl GlobalAlloc for Counting {
+    unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
+        let p = unsafe { System.alloc(layout) };
+        if !p.is_null() {
+            let now = CURRENT.fetch_add(layout.size(), Ordering::Relaxed) + layout.size();
+            PEAK.fetch_max(now, Ordering::Relaxed);
+        }
+        p
+    }
+
+    unsafe fn alloc_zeroed(&self, layout: Layout) -> *mut u8 {
+        let p = unsafe { System.alloc_zeroed(layout) };
+        if !p.is_null() {
+            let now = CURRENT.fetch_add(layout.size(), Ordering::Relaxed) + layout.size();
+            PEAK.fetch_max(now, Ordering::Relaxed);
+        }
+        p
+    }
+
+    unsafe fn dealloc(&self, ptr: *mut u8, layout: Layout) {
+        unsafe { System.dealloc(ptr, layout) };
+        CURRENT.fetch_sub(layout.size(), Ordering::Relaxed);
+    }
+}
+
+#[global_allocator]
+static ALLOC: Counting = Counting;
+
+/// Bytes allocated at the peak of `f`, above what was live when it started.
+fn peak_during<T>(f: impl FnOnce() -> T) -> (T, usize) {
+    let base = CURRENT.load(Ordering::Relaxed);
+    PEAK.store(base, Ordering::Relaxed);
+    let out = f();
+    (out, PEAK.load(Ordering::Relaxed).saturating_sub(base))
+}
+
+/// What decoding one HDF5 chunk of `limit` bytes from `input` may hold at
+/// once: the output, a few blocks of scratch (each no larger than the
+/// output), the offsets table, and the Zstandard decoder's state, which has
+/// a fixed ceiling: a window of at most 128 KiB (or twice the stream) and a
+/// block's table of sequences (up to 98,303 of 12 bytes, 1.2 MB).
+fn bound(limit: usize, input: &[u8]) -> usize {
+    6 * limit + 2 * input.len() + (2 << 20)
+}
+
+fn lock() -> std::sync::MutexGuard<'static, ()> {
+    SERIAL.lock().unwrap_or_else(|e| e.into_inner())
+}
+
+/// A 32-byte (extended) Blosc2 chunk header.
+fn chunk_header(ts: u8, nbytes: i32, blocksize: i32, cbytes: i32, special: u8) -> Vec<u8> {
+    let mut c = vec![5u8, 1, 0x05, ts];
+    for v in [nbytes, blocksize, cbytes] {
+        c.extend_from_slice(&v.to_le_bytes());
+    }
+    c.resize(32, 0);
+    c[31] = special << 4;
+    c
+}
+
+/// A chunk of `nbytes` bytes that repeats one value (special type 3).
+fn repeated(value: &[u8], nbytes: i32, blocksize: i32) -> Vec<u8> {
+    let mut c = chunk_header(
+        value.len() as u8,
+        nbytes,
+        blocksize,
+        32 + value.len() as i32,
+        3,
+    );
+    c.extend_from_slice(value);
+    c
+}
+
+/// A frame offset recording a special chunk of `kind` (1 zeros, 2 NaN).
+fn special_offset(kind: u8) -> [u8; 8] {
+    (((0x80 | kind) as i64) << 56).to_le_bytes()
+}
+
+/// A B2ND metalayer.
+fn nd_meta(shape: &[i64], chunks: &[i32], blocks: &[i32]) -> Vec<u8> {
+    let n = shape.len() as u8;
+    let mut m = vec![0x95, 0, n, 0x90 | n];
+    for s in shape {
+        m.push(0xd3);
+        m.extend_from_slice(&s.to_be_bytes());
+    }
+    for dims in [chunks, blocks] {
+        m.push(0x90 | n);
+        for d in dims {
+            m.push(0xd2);
+            m.extend_from_slice(&d.to_be_bytes());
+        }
+    }
+    m
+}
+
+/// A contiguous frame: header (with a `b2nd` metalayer if given), the data
+/// chunks, then the offsets chunk.
+fn frame(
+    meta: Option<&[u8]>,
+    nbytes: i64,
+    typesize: i32,
+    chunksize: i32,
+    data: &[u8],
+    offsets: &[u8],
+) -> Vec<u8> {
+    let mut h = vec![0u8; 91];
+    h[0] = 0x9e;
+    h[1] = 0xa8;
+    h[2..10].copy_from_slice(b"b2frame\0");
+    h[25] = 2;
+    match meta {
+        Some(m) => {
+            h.extend_from_slice(&[0xde, 0, 1, 0xa4]);
+            h.extend_from_slice(b"b2nd");
+            let at = h.len() as i32 + 5;
+            h.push(0xd2);
+            h.extend_from_slice(&at.to_be_bytes());
+            h.push(0xc6);
+            h.extend_from_slice(&(m.len() as u32).to_be_bytes());
+            h.extend_from_slice(m);
+        }
+        None => h.extend_from_slice(&[0xde, 0, 0]),
+    }
+    let header_len = h.len() as i32;
+    h[11..15].copy_from_slice(&header_len.to_be_bytes());
+    h[30..38].copy_from_slice(&nbytes.to_be_bytes());
+    h[39..47].copy_from_slice(&(data.len() as i64).to_be_bytes());
+    h[48..52].copy_from_slice(&typesize.to_be_bytes());
+    h[58..62].copy_from_slice(&chunksize.to_be_bytes());
+    h.extend_from_slice(data);
+    h.extend_from_slice(offsets);
+    let len = h.len() as u64;
+    h[16..24].copy_from_slice(&len.to_be_bytes());
+    h
+}
+
+/// The frame header's own sizes must not size the offsets chunk: a frame
+/// declaring 32 Mi chunks of 4 bytes, whose offsets chunk (40 bytes) says
+/// "one repeated offset, 256 MiB of them", made the decoder build all
+/// 256 MiB of offsets for a 1 MiB HDF5 chunk and then return 4 bytes.
+#[test]
+fn offsets_chunk_is_bounded_by_the_output_limit() {
+    let _g = lock();
+    let limit = 1 << 20;
+    let offsets_len: i32 = 256 << 20;
+    let nchunks = offsets_len as i64 / 8;
+    let offsets = repeated(&special_offset(1), offsets_len, 64 << 20);
+    let f = frame(None, nchunks * 4, 4, 4, &[], &offsets);
+    let (r, peak) = peak_during(|| blosc2_decompress(&f, limit));
+    assert!(r.is_err(), "decoded {:?} bytes", r.map(|v| v.len()));
+    assert!(
+        peak <= bound(limit, &f),
+        "peak {peak} bytes for a {}-byte frame",
+        f.len()
+    );
+    // The same frame with a variable chunk size (0): the offsets chunk
+    // alone says how many chunks there are.
+    let f = frame(None, nchunks * 4, 4, 0, &[], &offsets);
+    let (r, peak) = peak_during(|| blosc2_decompress(&f, limit));
+    assert!(r.is_err());
+    assert!(peak <= bound(limit, &f), "chunksize 0: peak {peak} bytes");
+}
+
+/// A legitimate frame of this shape (one chunk, its offset special) still
+/// decodes.
+#[test]
+fn small_frames_still_decode() {
+    let _g = lock();
+    let offsets = repeated(&special_offset(1), 8, 8);
+    let f = frame(None, 64, 4, 64, &[], &offsets);
+    assert_eq!(blosc2_decompress(&f, 64).unwrap(), vec![0; 64]);
+    let _ = blosc2_decompress_chunk;
+}
+
+/// A chunk that decodes to nothing kept its declared block size (up to
+/// 512 MiB) and allocated two scratch blocks of it: about 1 GiB for a
+/// 20-byte chunk.
+#[test]
+fn empty_chunk_does_not_allocate_its_block_size() {
+    let _g = lock();
+    let mut c = vec![5u8, 1, 0x01, 1];
+    for v in [0i32, 0x1FFF_F000, 20] {
+        c.extend_from_slice(&v.to_le_bytes());
+    }
+    c.resize(20, 0);
+    let (r, peak) = peak_during(|| blosc2_decompress_chunk(&c, 1 << 20));
+    assert_eq!(r.map(|v| v.len()).unwrap_or(0), 0);
+    assert!(
+        peak <= bound(0, &c),
+        "peak {peak} bytes for a 20-byte chunk"
+    );
+    // Inside a frame for a non-empty HDF5 chunk it is an error, not data.
+    let offsets = repeated(&0i64.to_le_bytes(), 8, 8);
+    let f = frame(None, 64, 4, 64, &c, &offsets);
+    let (r, peak) = peak_during(|| blosc2_decompress(&f, 64));
+    assert!(r.is_err(), "decoded {:?}", r.map(|v| v.len()));
+    assert!(peak <= bound(64, &f), "in a frame: peak {peak} bytes");
+}
+
+/// B2ND chunks were decoded whole, padding included, with up to 16x the
+/// HDF5 chunk size as their limit. Blocks are now placed as they are
+/// decoded, so the padding is never held.
+///
+/// Ten dimensions: nine of 3 split into blocks of 2 (padded to 4) and one
+/// of 4, so each chunk is 13x the array. One chunk, stored three ways: as a
+/// NaN chunk in the frame's offsets, as a repeated-value chunk, and as a
+/// chunk of stored (uncompressed) blocks.
+#[test]
+fn b2nd_padding_is_never_held() {
+    let _g = lock();
+    let ts = 4usize;
+    let mut shape = vec![3i64; 9];
+    shape.push(4);
+    let chunks: Vec<i32> = shape.iter().map(|&s| s as i32).collect();
+    let mut blocks = vec![2i32; 9];
+    blocks.push(4);
+    let meta = nd_meta(&shape, &chunks, &blocks);
+    let items: usize = shape.iter().product::<i64>() as usize;
+    let limit = items * ts;
+    let block_bytes = ts * blocks.iter().product::<i32>() as usize;
+    let ext_bytes = ts * 4usize.pow(9) * 4;
+    assert!(ext_bytes > 13 * limit);
+    let offsets = |off: [u8; 8]| repeated(&off, 8, 8);
+
+    let value = 1.5f32.to_le_bytes();
+    let stored = {
+        // Every block stored raw: block k holds the value k.
+        let mut c = chunk_header(4, ext_bytes as i32, block_bytes as i32, 0, 0);
+        c[2] = 0x02 | 0x10; // memcpyed, not split
+        c.truncate(16);
+        for k in 0..ext_bytes / block_bytes {
+            c.extend((k as f32).to_le_bytes().repeat(block_bytes / 4));
+        }
+        let n = c.len() as i32;
+        c[12..16].copy_from_slice(&n.to_le_bytes());
+        c
+    };
+    let cases: Vec<(&str, Vec<u8>)> = vec![
+        (
+            "NaN offset",
+            frame(
+                Some(&meta),
+                ext_bytes as i64,
+                4,
+                ext_bytes as i32,
+                &[],
+                &offsets(special_offset(2)),
+            ),
+        ),
+        (
+            "repeated value",
+            frame(
+                Some(&meta),
+                ext_bytes as i64,
+                4,
+                ext_bytes as i32,
+                &repeated(&value, ext_bytes as i32, block_bytes as i32),
+                &offsets(0i64.to_le_bytes()),
+            ),
+        ),
+        (
+            "stored blocks",
+            frame(
+                Some(&meta),
+                ext_bytes as i64,
+                4,
+                ext_bytes as i32,
+                &stored,
+                &offsets(0i64.to_le_bytes()),
+            ),
+        ),
+    ];
+    for (name, f) in cases {
+        let (r, peak) = peak_during(|| blosc2_decompress(&f, limit));
+        let out = r.unwrap_or_else(|e| panic!("{name}: {e}"));
+        assert_eq!(out.len(), limit, "{name}");
+        match name {
+            "NaN offset" => assert!(
+                out.chunks(4)
+                    .all(|v| f32::from_le_bytes(v.try_into().unwrap()).is_nan())
+            ),
+            "repeated value" => assert!(out.chunks(4).all(|v| v == value)),
+            _ => {
+                // Element (i0..i9) lies in block (i0/2, .., i8/2), numbered
+                // in C order over a 2x..x2x1 grid of blocks.
+                let mut idx = [0usize; 10];
+                for (e, v) in out.chunks(4).enumerate() {
+                    let mut n = e;
+                    for d in (0..10).rev() {
+                        idx[d] = n % shape[d] as usize;
+                        n /= shape[d] as usize;
+                    }
+                    let k = idx[..9].iter().fold(0, |k, &i| k * 2 + i / 2);
+                    assert_eq!(
+                        f32::from_le_bytes(v.try_into().unwrap()),
+                        k as f32,
+                        "{name} {e}"
+                    );
+                }
+            }
+        }
+        assert!(
+            peak <= bound(limit, &f),
+            "{name}: peak {peak} bytes for a {limit}-byte chunk ({}-byte frame)",
+            f.len()
+        );
+    }
+}
+
+/// A B2ND chunk larger than the array (here 16x, the old cap) is refused,
+/// or at least never allocated.
+#[test]
+fn b2nd_chunk_larger_than_the_array_is_not_allocated() {
+    let _g = lock();
+    let limit = 1 << 20;
+    let c = 16 * limit as i32;
+    let meta = nd_meta(&[limit as i64], &[c], &[c]);
+    let offsets = repeated(&special_offset(1), 8, 8);
+    let f = frame(Some(&meta), c as i64, 1, c, &[], &offsets);
+    let (r, peak) = peak_during(|| blosc2_decompress(&f, limit));
+    assert!(
+        peak <= bound(limit, &f),
+        "peak {peak} bytes ({:?})",
+        r.map(|v| v.len())
+    );
+}
+
+/// ruzstd reserves a frame's declared window (up to 100 MiB) before it
+/// decodes a frame with a decoder it has used before: a Blosc2 chunk of
+/// two 16-byte Zstandard streams, each declaring a 96 MiB window,
+/// allocated 96 MiB. c-blosc2 compresses each block with its size known,
+/// so its windows never exceed the block.
+#[test]
+fn zstd_window_is_bounded_by_the_output() {
+    let _g = lock();
+    let mut z = 0xfd2f_b528u32.to_le_bytes().to_vec();
+    // No single segment, no checksum; window 2^26 + 4/8 of it = 96 MiB.
+    z.extend_from_slice(&[0x00, (16 << 3) | 4]);
+    // One raw block, last, of 16 bytes.
+    let h = 1 | (16 << 3);
+    z.extend_from_slice(&[h as u8, (h >> 8) as u8, 0]);
+    z.extend_from_slice(&[7; 16]);
+    // Two blocks of 16 bytes, one stream each (not split), Zstandard
+    // (codec 4).
+    let chunk = |z: &[u8]| {
+        let mut c = vec![5u8, 1, 0x10 | (4 << 5), 1];
+        for v in [32i32, 16, 0] {
+            c.extend_from_slice(&v.to_le_bytes());
+        }
+        let first = 24 + 4 + z.len();
+        c.extend_from_slice(&24i32.to_le_bytes());
+        c.extend_from_slice(&(first as i32).to_le_bytes());
+        for _ in 0..2 {
+            c.extend_from_slice(&(z.len() as i32).to_le_bytes());
+            c.extend_from_slice(z);
+        }
+        let n = c.len() as i32;
+        c[12..16].copy_from_slice(&n.to_le_bytes());
+        c
+    };
+    let c = chunk(&z);
+    let (r, peak) = peak_during(|| blosc2_decompress_chunk(&c, 32));
+    assert!(peak <= bound(32, &c), "peak {peak} bytes ({r:?})");
+    assert!(r.is_err(), "{r:?}");
+    // The same streams with a window they can use read.
+    z[5] = 0;
+    assert_eq!(
+        blosc2_decompress_chunk(&chunk(&z), 32).unwrap(),
+        vec![7; 32]
+    );
+}
+
+/// xorshift64*: deterministic, so a failure reproduces.
+struct Rng(u64);
+
+impl Rng {
+    fn next(&mut self) -> u64 {
+        let mut x = self.0;
+        x ^= x >> 12;
+        x ^= x << 25;
+        x ^= x >> 27;
+        self.0 = x;
+        x.wrapping_mul(0x2545_F491_4F6C_DD1D)
+    }
+
+    fn below(&mut self, n: usize) -> usize {
+        (self.next() % n.max(1) as u64) as usize
+    }
+
+    /// A size that tends to the edges: small, a power of two, huge.
+    fn size(&mut self) -> i64 {
+        match self.below(6) {
+            0 => self.below(64) as i64,
+            1 => 1 << self.below(31),
+            2 => i32::MAX as i64 - self.below(4096) as i64,
+            3 => (1i64 << self.below(62)) + self.below(8) as i64,
+            4 => MAX_BLOCK - self.below(3) as i64,
+            _ => self.next() as i32 as i64,
+        }
+    }
+}
+
+const MAX_BLOCK: i64 = 536_866_816;
+
+/// One to four edits: bytes, or a size field written little-endian (chunk
+/// headers) or big-endian (frame headers), most often at a header's size
+/// fields.
+fn mutate(rng: &mut Rng, seed: &[u8], data_at: usize) -> Vec<u8> {
+    let mut v = seed.to_vec();
+    for _ in 0..1 + rng.below(4) {
+        let len = v.len();
+        if len < 16 {
+            v.push(rng.next() as u8);
+            continue;
+        }
+        match rng.below(8) {
+            0 => {
+                let i = rng.below(len);
+                v[i] ^= 1 << rng.below(8);
+            }
+            1 => {
+                let i = rng.below(len);
+                v[i] = rng.next() as u8;
+            }
+            2 => {
+                // Frame header: nbytes, cbytes (i64), typesize, chunksize.
+                let x = rng.size();
+                match rng.below(4) {
+                    0 if len >= 38 => v[30..38].copy_from_slice(&x.to_be_bytes()),
+                    1 if len >= 47 => v[39..47].copy_from_slice(&x.to_be_bytes()),
+                    2 if len >= 52 => v[48..52].copy_from_slice(&(x as i32).to_be_bytes()),
+                    _ if len >= 62 => v[58..62].copy_from_slice(&(x as i32).to_be_bytes()),
+                    _ => {}
+                }
+            }
+            3 | 4 => {
+                // A chunk header's nbytes, blocksize or cbytes: in the first
+                // data chunk, or anywhere (the offsets chunk comes last).
+                let at = if rng.below(2) == 0 && data_at + 16 <= len {
+                    data_at + 4 * (1 + rng.below(3))
+                } else {
+                    rng.below(len - 3)
+                };
+                let x = rng.size() as i32;
+                v[at..at + 4].copy_from_slice(&x.to_le_bytes());
+            }
+            5 => v.truncate(rng.below(len)),
+            6 => {
+                let at = rng.below(len);
+                v[at] = [0x10, 0x20, 0x30, 0x40, 0x05, 0x07, 0x02][rng.below(7)];
+            }
+            _ => {
+                let i = rng.below(len - 3);
+                let x = rng.size() as i32;
+                v[i..i + 4].copy_from_slice(&x.to_be_bytes());
+            }
+        }
+    }
+    v
+}
+
+/// Every fixture frame that decodes, with its decoded size.
+fn seeds() -> Vec<(Vec<u8>, usize)> {
+    let dir = std::path::Path::new(env!("CARGO_MANIFEST_DIR")).join("tests/fixtures/blosc2");
+    let mut v = Vec::new();
+    for e in std::fs::read_dir(dir).unwrap() {
+        let p = e.unwrap().path();
+        if p.extension().is_some_and(|x| x == "b2f")
+            && let Ok(out) = std::fs::read(p.with_extension("out"))
+        {
+            v.push((std::fs::read(&p).unwrap(), out.len()));
+        }
+    }
+    v.sort();
+    assert!(v.len() >= 20, "fixtures missing");
+    v
+}
+
+fn header_len(frame: &[u8]) -> usize {
+    i32::from_be_bytes(frame[11..15].try_into().unwrap()) as usize
+}
+
+/// Mutated fixture frames, decoded with their HDF5 chunk size as the
+/// limit, and their first chunks on their own: whatever they declare, no
+/// decode holds more than a small multiple of the output and the input.
+#[test]
+fn fuzzed_frames_and_chunks_stay_within_the_allocation_bound() {
+    let _g = lock();
+    let seeds = seeds();
+    let mut rng = Rng(0xb2a1);
+    let mut worst = (0.0f64, String::new());
+    for i in 0..20_000 {
+        let (seed, limit) = &seeds[rng.below(seeds.len())];
+        let f = mutate(&mut rng, seed, header_len(seed));
+        let (r, peak) = peak_during(|| blosc2_decompress(&f, *limit));
+        if let Ok(out) = &r {
+            assert!(out.len() <= *limit, "iteration {i}: output past the limit");
+        }
+        assert!(
+            peak <= bound(*limit, &f),
+            "iteration {i}: peak {peak} bytes for a {limit}-byte chunk from {} bytes ({:?})",
+            f.len(),
+            r.map(|v| v.len())
+        );
+        let ratio = peak as f64 / bound(*limit, &f) as f64;
+        if ratio > worst.0 {
+            worst = (
+                ratio,
+                format!(
+                    "frame iteration {i}: peak {peak}, limit {limit}, input {}",
+                    f.len()
+                ),
+            );
+        }
+    }
+    for i in 0..20_000 {
+        let (seed, _) = &seeds[rng.below(seeds.len())];
+        let at = header_len(seed);
+        let chunk = &seed[at..];
+        let c = mutate(&mut rng, chunk, 0);
+        let limit = 1 << 16;
+        let (r, peak) = peak_during(|| blosc2_decompress_chunk(&c, limit));
+        assert!(
+            peak <= bound(limit, &c),
+            "chunk iteration {i}: peak {peak} bytes from {} bytes ({:?})",
+            c.len(),
+            r.map(|v| v.len())
+        );
+    }
+    eprintln!("worst peak / bound: {:.2} ({})", worst.0, worst.1);
+}
+
+/// Frames built from random header sizes, offsets chunks and B2ND shapes
+/// (chunk and block shapes that pad, special and repeated-value chunks).
+#[test]
+fn random_frames_stay_within_the_allocation_bound() {
+    let _g = lock();
+    let mut rng = Rng(0xb2a2);
+    for i in 0..5_000 {
+        let ts = [1usize, 2, 4, 8][rng.below(4)];
+        let ndim = 1 + rng.below(8);
+        let mut shape = Vec::new();
+        let mut chunks = Vec::new();
+        let mut blocks = Vec::new();
+        for _ in 0..ndim {
+            let s = 1 + rng.below(if ndim > 3 { 4 } else { 40 });
+            let c = if rng.below(8) == 0 {
+                s * (1 + rng.below(4))
+            } else {
+                1 + rng.below(s)
+            };
+            let b = 1 + rng.below(c);
+            shape.push(s as i64);
+            chunks.push(c as i32);
+            blocks.push(b as i32);
+        }
+        let items: usize = shape.iter().product::<i64>() as usize;
+        let limit = items * ts;
+        let meta = nd_meta(&shape, &chunks, &blocks);
+        let ext: usize = ts
+            * chunks
+                .iter()
+                .zip(&blocks)
+                .map(|(&c, &b)| (c as usize).div_ceil(b as usize) * b as usize)
+                .product::<usize>();
+        let nchunks: usize = shape
+            .iter()
+            .zip(&chunks)
+            .map(|(&s, &c)| (s as usize).div_ceil(c as usize))
+            .product();
+        let block_bytes = ts * blocks.iter().product::<i32>() as usize;
+        let chunksize = if rng.below(4) == 0 {
+            rng.size()
+        } else {
+            ext as i64
+        };
+        let nbytes = if rng.below(4) == 0 {
+            rng.size()
+        } else {
+            (nchunks * ext) as i64
+        };
+        let off_n = if rng.below(4) == 0 {
+            rng.size() as i32
+        } else {
+            8 * nchunks as i32
+        };
+        let (data, off) = match rng.below(3) {
+            0 => (Vec::new(), special_offset(1 + rng.below(2) as u8)),
+            _ => {
+                let bs = if rng.below(4) == 0 {
+                    rng.size() as i32
+                } else {
+                    block_bytes as i32
+                };
+                let value: Vec<u8> = (0..ts).map(|_| rng.next() as u8).collect();
+                let n = if rng.below(4) == 0 {
+                    rng.size() as i32
+                } else {
+                    ext as i32
+                };
+                (repeated(&value, n, bs), 0i64.to_le_bytes())
+            }
+        };
+        let offsets = repeated(&off, off_n, off_n.clamp(1, 8));
+        let meta = (rng.below(4) != 0).then_some(meta.as_slice());
+        let f = frame(meta, nbytes, ts as i32, chunksize as i32, &data, &offsets);
+        let (r, peak) = peak_during(|| blosc2_decompress(&f, limit));
+        assert!(
+            peak <= bound(limit, &f),
+            "iteration {i}: peak {peak} bytes for a {limit}-byte chunk ({:?}, shape {shape:?} \
+             chunks {chunks:?} blocks {blocks:?})",
+            r.map(|v| v.len())
+        );
+    }
+}

crates/clawhdf5-format/tests/fixtures/blosc2/bytedelta.err

@@ -0,0 +1 @@
+filter 35

crates/clawhdf5-format/tests/fixtures/blosc2/generate.py

@@ -0,0 +1,129 @@
+"""Generate the Blosc2 frames the `filters_blosc2` unit tests decode.
+
+Each case is `<name>.b2f` (a Blosc2 contiguous frame, what the HDF5 Blosc2
+filter stores per chunk) and `<name>.out` (what decoding it must give: the
+first chunk of a plain frame, or the whole array in C order for a B2ND
+frame), or `<name>.err` (a frame clawhdf5 must refuse; the file holds a word
+the error message must contain).
+
+These cover what files written by h5py + hdf5plugin never contain, but a
+Blosc2 frame may: special chunks (repeated value, NaN, uninitialised), the
+delta filter over many blocks and odd type sizes, bit shuffle of blocks that
+are not a multiple of 8 elements, shuffle with a byte-group size, forced
+stream splitting, multi-chunk B2ND arrays with padded edge chunks and a
+chunk of zeros, and features clawhdf5 refuses (dictionaries, registered
+filters).
+
+Written with python-blosc2 4.13.1 (c-blosc2 3.3.4) in a scratch venv
+(`pip install blosc2`). Re-run only to regenerate:
+
+    python generate.py <this directory>
+"""
+import os
+import sys
+
+import blosc2
+import numpy as np
+
+out = sys.argv[1]
+
+
+def save(name, frame, expected):
+    with open(os.path.join(out, name + ".b2f"), "wb") as f:
+        f.write(frame)
+    with open(os.path.join(out, name + ".out"), "wb") as f:
+        f.write(expected)
+
+
+def save_err(name, frame, word):
+    with open(os.path.join(out, name + ".b2f"), "wb") as f:
+        f.write(frame)
+    with open(os.path.join(out, name + ".err"), "w") as f:
+        f.write(word)
+
+
+def plain(data, **cparams):
+    """A one-chunk super-chunk frame of `data`, as hdf5-blosc2 writes."""
+    data = np.ascontiguousarray(data)
+    cp = blosc2.CParams(typesize=data.dtype.itemsize, **cparams)
+    sc = blosc2.SChunk(chunksize=data.nbytes, cparams=cp)
+    sc.append_data(data)
+    return sc.to_cframe(), data.tobytes()
+
+
+def special(nitems, dtype, kind, value=None):
+    dt = np.dtype(dtype)
+    sc = blosc2.SChunk(chunksize=nitems * dt.itemsize,
+                       cparams=blosc2.CParams(typesize=dt.itemsize))
+    sc.fill_special(nitems, kind, value)
+    return sc.to_cframe()
+
+
+# Special chunks. A repeated value stays in the frame as a 33+ byte chunk;
+# NaN and uninitialised chunks become special offsets.
+save("value_i4", special(300, "<i4", blosc2.SpecialValue.VALUE, 123456),
+     np.full(300, 123456, "<i4").tobytes())
+save("value_f8", special(250, "<f8", blosc2.SpecialValue.VALUE, -2.5),
+     np.full(250, -2.5, "<f8").tobytes())
+save("nan_f4", special(500, "<f4", blosc2.SpecialValue.NAN),
+     np.full(500, np.nan, "<f4").tobytes())
+save("nan_f8", special(300, "<f8", blosc2.SpecialValue.NAN),
+     np.full(300, np.nan, "<f8").tobytes())
+save("zero_u2", special(2000, "<u2", blosc2.SpecialValue.ZERO), bytes(4000))
+# Uninitialised values: libhdf5 would hand back whatever memory it had;
+# clawhdf5 returns zeros.
+save("uninit_i8", special(64, "<i8", blosc2.SpecialValue.UNINIT), bytes(512))
+
+rng = np.random.default_rng(11)
+ramp = lambda n, dt: ((np.arange(n) * 7) % 1000 + rng.integers(0, 3, n)).astype(dt)
+# Slowly varying: what the delta filter is for (noise would be stored raw).
+smooth = lambda n, dt: (np.arange(n) // 3 + 1000).astype(dt)
+
+# Delta over many blocks, for type sizes 1, 2, 4, 8, 3 (bytes) and 16 (u64
+# pairs).
+for dt, n, codec in [("<u1", 2000, blosc2.Codec.LZ4), ("<i2", 1000, blosc2.Codec.BLOSCLZ),
+                     ("<i4", 700, blosc2.Codec.LZ4), ("<u8", 400, blosc2.Codec.BLOSCLZ)]:
+    save(f"delta_{np.dtype(dt).name}_{codec.name.lower()}",
+         *plain(smooth(n, dt), codec=codec, blocksize=256,
+                filters=[blosc2.Filter.DELTA], filters_meta=[0]))
+rec3 = np.frombuffer(smooth(3 * 300, "<u1").tobytes(), dtype="V3")
+save("delta_v3", *plain(rec3, blocksize=300, filters=[blosc2.Filter.DELTA], filters_meta=[0]))
+rec16 = np.frombuffer(smooth(2 * 200, "<u8").tobytes(), dtype="V16")
+save("delta_shuffle_v16", *plain(rec16, blocksize=512,
+                                 filters=[blosc2.Filter.DELTA, blosc2.Filter.SHUFFLE],
+                                 filters_meta=[0, 0]))
+
+# Bit shuffle of blocks whose element count is not a multiple of 8 (44-byte
+# blocks of 4-byte elements: 8 transposed, 3 copied).
+save("bitshuffle_odd_blocks", *plain(ramp(500, "<i4"), codec=blosc2.Codec.ZSTD, blocksize=44,
+                                     filters=[blosc2.Filter.BITSHUFFLE], filters_meta=[0]))
+# Shuffle in groups of 2 bytes of an 8-byte type (filters_meta).
+save("shuffle_meta2", *plain(ramp(500, "<i8"), codec=blosc2.Codec.ZLIB,
+                             filters=[blosc2.Filter.SHUFFLE], filters_meta=[2]))
+# Streams split per byte, and never split.
+save("always_split", *plain(ramp(1000, "<f4"), codec=blosc2.Codec.LZ4HC,
+                            splitmode=blosc2.SplitMode.ALWAYS_SPLIT))
+save("never_split", *plain(ramp(1500, "<u2"), codec=blosc2.Codec.ZSTD,
+                           splitmode=blosc2.SplitMode.NEVER_SPLIT))
+
+# B2ND arrays of several chunks whose edge chunks and blocks are padded, and
+# one whose middle chunk is all zeros (a special offset).
+for name, shape, chunks, blocks, dt in [
+    ("b2nd_2d", (37, 29), (10, 16), (4, 6), "<i4"),
+    ("b2nd_3d", (9, 10, 7), (4, 5, 3), (3, 2, 2), "<f4"),
+    ("b2nd_4d", (5, 7, 5, 6), (3, 2, 5, 4), (2, 2, 3, 3), "<u2"),
+]:
+    a = ramp(int(np.prod(shape)), dt).reshape(shape)
+    arr = blosc2.asarray(a, chunks=chunks, blocks=blocks)
+    save(name, arr.to_cframe(), a.tobytes())
+a = ramp(60 * 20, "<i2").reshape(60, 20)
+a[20:40, :] = 0
+arr = blosc2.asarray(a, chunks=(20, 20), blocks=(8, 16))
+save("b2nd_zero_chunk", arr.to_cframe(), a.tobytes())
+
+# Refused: a dictionary, and a registered filter (bytedelta).
+frame, _ = plain(ramp(4000, "<i4"), codec=blosc2.Codec.ZSTD, use_dict=True, blocksize=2048)
+save_err("zstd_dict", frame, "dictionar")
+frame, _ = plain(ramp(500, "<i4"), filters=[blosc2.Filter.SHUFFLE, blosc2.Filter.BYTEDELTA],
+                 filters_meta=[0, 4])
+save_err("bytedelta", frame, "filter 35")

crates/clawhdf5-format/tests/fixtures/blosc2/zstd_dict.err

@@ -0,0 +1 @@
+dictionar

crates/clawhdf5/Cargo.toml

@@ -47,8 +47,9 @@ lzf = ["clawhdf5-format/lzf"]
 bitshuffle = ["clawhdf5-format/bitshuffle"]
 bzip2 = ["clawhdf5-format/bzip2"]
 blosc = ["clawhdf5-format/blosc"]
+blosc2 = ["clawhdf5-format/blosc2"]
 # Every plugin filter.
-plugin-filters = ["lzf", "bitshuffle", "bzip2", "blosc"]
+plugin-filters = ["lzf", "bitshuffle", "bzip2", "blosc", "blosc2"]
 # Dataset::verify_provenance() — recompute a dataset's SHA-256 and compare
 # against its stored _provenance_sha256 attribute. On by default, matching
 # clawhdf5-format's own default-on `provenance` feature.

crates/clawhdf5/tests/plugin_filters_interop.rs

@@ -77,7 +77,7 @@ except ImportError:
     hdf5plugin = None
 path = sys.argv[1]
 FILTERS = eval('(' + sys.argv[2] + ')')
-cases = [
+cases = eval('(' + sys.argv[3] + ')') if len(sys.argv) > 3 else [
     ('<u1', (1000,), (128,), 'ramp'),
     ('<i2', (37, 53), (10, 16), 'ramp'),
     ('<i4', (2000,), (300,), 'ramp'),
@@ -97,7 +97,10 @@ with h5py.File(path, 'w') as f:
     for label, kw in FILTERS:
         for dt, shape, chunks, kind in cases:
             n = int(np.prod(shape))
-            if kind == 'noise':
+            if kind in ('zeros', 'const', 'nan'):
+                fill = {'zeros': 0, 'const': 7, 'nan': np.nan}[kind]
+                data = np.full(n, fill, dtype=dt)
+            elif kind == 'noise':
                 raw = rng.integers(0, 256, n * np.dtype(dt).itemsize, dtype=np.uint8)
                 data = raw.view(dt)
                 if np.dtype(dt).kind == 'f':
@@ -117,11 +120,18 @@ print(i)
 /// `(label, create_dataset kwargs)`), then check that clawhdf5 reads each
 /// filtered dataset exactly as its unfiltered twin.
 fn check_h5py_written(tag: &str, filters: &str) {
+    check_h5py_written_cases(tag, filters, None);
+}
+
+/// [`check_h5py_written`] over `cases` (a Python list of `(dtype, shape,
+/// chunks, kind)`, kind one of ramp, noise, zeros, const, nan) instead of
+/// the default ones.
+fn check_h5py_written_cases(tag: &str, filters: &str, cases: Option<&str>) {
     let dir = tempfile::tempdir().unwrap();
     let path = dir.path().join(format!("{tag}.h5"));
-    let n: usize = run_python(GENERATE, &[path.to_str().unwrap(), filters])
-        .parse()
-        .unwrap();
+    let mut args = vec![path.to_str().unwrap(), filters];
+    args.extend(cases);
+    let n: usize = run_python(GENERATE, &args).parse().unwrap();
     assert!(n > 0);
     let file = File::open(&path).unwrap();
     for i in 0..n {
@@ -353,6 +363,110 @@ fn blosc_written_by_clawhdf5_reads_in_hdf5plugin() {
     }
 }
 
+#[cfg(feature = "blosc2")]
+#[test]
+fn blosc2_written_by_hdf5plugin_reads_exactly() {
+    if !have_python("h5py, hdf5plugin") {
+        return;
+    }
+    // Every codec hdf5plugin's Blosc2 offers, each lossless filter, and
+    // levels from "store" to maximum. Truncating precision is lossy, so it
+    // is checked separately against h5py's own reading.
+    check_h5py_written(
+        "blosc2",
+        r#"[(f'{c} {f} {l}', hdf5plugin.Blosc2(cname=c, clevel=l, filters=f))
+            for c in ['blosclz', 'lz4', 'lz4hc', 'zlib', 'zstd']
+            for f, l in [(hdf5plugin.Blosc2.NOFILTER, 5),
+                         (hdf5plugin.Blosc2.SHUFFLE, 9),
+                         (hdf5plugin.Blosc2.BITSHUFFLE, 1),
+                         (hdf5plugin.Blosc2.DELTA, 5)]]
+           + [('blosclz level 0', hdf5plugin.Blosc2(cname='blosclz', clevel=0)),
+              ('zstd level 0 bitshuffle',
+               hdf5plugin.Blosc2(cname='zstd', clevel=0, filters=hdf5plugin.Blosc2.BITSHUFFLE))]"#,
+    );
+}
+
+/// Blosc2 over more shapes and dtypes: every integer and float width,
+/// 1-D to 5-D chunks (B2ND arrays from 2-D on) with partial edge chunks and
+/// block shapes that pad the chunk, datasets of zeros, of one repeated value
+/// and of NaN (Blosc2's "special" chunks), and Fletcher32 before Blosc2
+/// (which makes hdf5-blosc2 fall back from B2ND to a plain frame).
+#[cfg(feature = "blosc2")]
+#[test]
+fn blosc2_shapes_and_special_chunks_read_exactly() {
+    if !have_python("h5py, hdf5plugin") {
+        return;
+    }
+    let cases = r#"[(dt, shape, chunks, kind)
+        for dt in ['<i1', '<u1', '<i2', '>u2', '<i4', '<u4', '<i8', '<u8', '<f4', '>f8']
+        for shape, chunks in [((777,), (100,)),
+                              ((37, 53), (10, 16)),
+                              ((9, 10, 11), (4, 5, 3)),
+                              ((6, 7, 5, 9), (3, 2, 5, 4))]
+        for kind in ['ramp', 'noise']]
+      + [('<f8', (300, 30), (64, 7), 'zeros'), ('<i4', (50, 40, 3), (7, 9, 3), 'zeros'),
+         ('<u2', (5000,), (1024,), 'const'), ('<i8', (40, 40), (16, 16), 'const'),
+         ('<f4', (100, 20), (32, 8), 'nan'), ('<f8', (3000,), (1000,), 'nan'),
+         ('<f4', (1000, 1000), (256, 512), 'ramp'),
+         ('<i2', (3, 3, 3, 3, 3), (2, 2, 2, 2, 2), 'ramp')]"#;
+    check_h5py_written_cases(
+        "blosc2_shapes",
+        r#"[('lz4 shuffle', hdf5plugin.Blosc2(cname='lz4')),
+            ('zstd bitshuffle',
+             hdf5plugin.Blosc2(cname='zstd', clevel=7, filters=hdf5plugin.Blosc2.BITSHUFFLE)),
+            ('blosclz delta', hdf5plugin.Blosc2(cname='blosclz', filters=hdf5plugin.Blosc2.DELTA)),
+            ('zlib + fletcher32', dict(**hdf5plugin.Blosc2(cname='zlib'), fletcher32=True))]"#,
+        Some(cases),
+    );
+}
+
+/// Truncating precision is lossy: clawhdf5 must read exactly what h5py
+/// (libhdf5 with hdf5plugin) reads.
+#[cfg(feature = "blosc2")]
+#[test]
+fn blosc2_truncated_precision_reads_as_h5py() {
+    if !have_python("h5py, hdf5plugin") {
+        return;
+    }
+    let dir = tempfile::tempdir().unwrap();
+    let path = dir.path().join("blosc2_trunc.h5");
+    let n: usize = run_python(
+        r#"
+import sys
+import numpy as np, h5py, hdf5plugin
+rng = np.random.default_rng(3)
+i = 0
+with h5py.File(sys.argv[1], 'w') as f:
+    for dt in ['<f4', '<f8']:
+        for shape, chunks in [((1000,), (300,)), ((37, 53), (10, 16))]:
+            d = (rng.standard_normal(shape) * 1000).astype(dt)
+            ds = f.create_dataset(f'f{i}', data=d, chunks=chunks,
+                                  **hdf5plugin.Blosc2(cname='lz4',
+                                                      filters=hdf5plugin.Blosc2.TRUNC_PREC))
+            f.create_dataset(f'r{i}', data=ds[()])
+            i += 1
+print(i)
+"#,
+        &[path.to_str().unwrap()],
+    )
+    .parse()
+    .unwrap();
+    let file = File::open(&path).unwrap();
+    for i in 0..n {
+        let got = file
+            .dataset(&format!("f{i}"))
+            .unwrap()
+            .read_selection(&Selection::All)
+            .unwrap();
+        let want = file
+            .dataset(&format!("r{i}"))
+            .unwrap()
+            .read_selection(&Selection::All)
+            .unwrap();
+        assert!(got == want, "trunc_prec f{i}: data differs from h5py");
+    }
+}
+
 #[cfg(feature = "lzf")]
 #[test]
 fn lzf_written_by_h5py_reads_exactly() {
@@ -381,8 +495,9 @@ fn lzf_written_by_clawhdf5_reads_in_h5py() {
     });
 }
 
-/// Blosc2 and ZFP are not implemented: reading them must be a clear error
-/// naming the filter, never data.
+/// ZFP is not implemented, and Blosc2 is not in a build without the
+/// `blosc2` feature: reading them must be a clear error naming the filter,
+/// never data.
 #[test]
 fn unimplemented_filters_are_a_clear_error() {
     if !have_python("h5py, hdf5plugin") {
@@ -402,7 +517,11 @@ with h5py.File(sys.argv[1], 'w') as f:
         &[path.to_str().unwrap()],
     );
     let file = File::open(&path).unwrap();
-    for (name, id, label) in [("blosc2", 32026u16, "Blosc2"), ("zfp", 32013, "ZFP")] {
+    let mut missing = vec![("zfp", 32013u16, "ZFP")];
+    if !cfg!(feature = "blosc2") {
+        missing.push(("blosc2", 32026, "Blosc2"));
+    }
+    for (name, id, label) in missing {
         let err = file
             .dataset(name)
             .unwrap()