fix(format): write paged files libhdf5 can open

FileWriter::with_page_size wrote a "version 4" superblock with an extra
page-size field. HDF5 has no superblock version 4, so libhdf5 refused
every such file ("bad superblock version number").

A paged file is now what libhdf5 itself writes for fs_strategy="page":
a v3 superblock whose extension object header holds a File Space Info
message (strategy PAGE, the page size, free space not persisted; same
bytes and flags as HDF5 2.0), with the file padded to a whole page.
h5py opens it, reports the strategy and page size, and can modify it in
r+ mode. Page sizes outside libhdf5's 512 B..1 GiB are an error.

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

crates/clawhdf5-format/src/file_writer.rs

@@ -4,7 +4,7 @@
 //! link messages, contiguous datasets, inline and dense attributes.
 
 #[cfg(not(feature = "std"))]
-use alloc::{string::String, string::ToString, vec, vec::Vec};
+use alloc::{format, string::String, string::ToString, vec, vec::Vec};
 
 use crate::attribute::AttributeMessage;
 use crate::chunked_write::{
@@ -38,6 +38,31 @@ const SUPERBLOCK_SIZE: usize = 48;
 /// field is 2 bytes. Bigger "compact" requests fall back to contiguous storage.
 const MAX_COMPACT_DATA_SIZE: usize = crate::object_header_writer::MAX_MESSAGE_SIZE - 4;
 
+/// libhdf5's bounds on a file space page size (`H5F_FILE_SPACE_PAGE_SIZE_MIN`
+/// and `_MAX`).
+const MIN_FILE_SPACE_PAGE_SIZE: u32 = 512;
+const MAX_FILE_SPACE_PAGE_SIZE: u32 = 1024 * 1024 * 1024;
+
+/// Superblock extension object header for a file using the paged file-space
+/// strategy: a single File Space Info message (0x0017), as libhdf5 writes it
+/// for `fs_strategy="page"` without persisted free space.
+fn build_paged_superblock_extension(page_size: u32) -> Result<Vec<u8>, FormatError> {
+    let mut fsinfo = Vec::new();
+    fsinfo.push(1); // version
+    fsinfo.push(1); // strategy: H5F_FSPACE_STRATEGY_PAGE
+    fsinfo.push(0); // persisting free space: no
+    write_length(&mut fsinfo, 1, LENGTH_SIZE); // free-space section threshold
+    write_length(&mut fsinfo, u64::from(page_size), LENGTH_SIZE);
+    fsinfo.extend_from_slice(&0u16.to_le_bytes()); // page end metadata threshold
+    write_undef_offset(&mut fsinfo, OFFSET_SIZE); // EOA before free-space info
+    let mut w = ObjectHeaderWriter::new();
+    // Flags as libhdf5 sets them: bit 2 (never share) and bit 4 (mark if
+    // unknown). Not constant: libhdf5 rewrites the message when it closes a
+    // file it opened for writing.
+    w.add_message_with_flags(MessageType::Unknown(0x0017), fsinfo, 0x14);
+    w.serialize()
+}
+
 /// Threshold for switching from compact (inline) to dense attribute storage.
 const DENSE_ATTR_THRESHOLD: usize = 8;
 
@@ -961,7 +986,9 @@ pub struct FileWriter {
     alignment_threshold: usize,
     /// Global alignment boundary in bytes (0 = disabled).
     alignment_bytes: usize,
-    /// Page size for page-buffer mode. When set, a v4 superblock is written.
+    /// File space page size. When set, the file uses libhdf5's paged
+    /// file-space strategy (a File Space Info message in the superblock
+    /// extension).
     page_size: Option<u32>,
 }
 
@@ -993,9 +1020,16 @@ impl FileWriter {
         self
     }
 
-    /// Enable page-buffer mode with the given page size. Writing this causes
-    /// the file to be written with a v4 superblock (page_size field) instead
-    /// of the default v3.
+    /// Write the file with libhdf5's *paged* file-space strategy and the given
+    /// page size, as `H5Pset_file_space_strategy(H5F_FSPACE_STRATEGY_PAGE)` +
+    /// `H5Pset_file_space_page_size` (h5py: `fs_strategy="page"`,
+    /// `fs_page_size=...`) do: a v3 superblock with an extension holding a
+    /// File Space Info message, and the file padded to a whole number of
+    /// pages. Readers with a page buffer can then fetch metadata page by page.
+    ///
+    /// `page_size` must be between 512 bytes and 1 GiB (libhdf5's limits);
+    /// [`Self::finish`] fails otherwise. This used to write a "version 4"
+    /// superblock, which does not exist and no HDF5 library can open.
     pub fn with_page_size(&mut self, page_size: u32) -> &mut Self {
         self.page_size = Some(page_size);
         self
@@ -1020,6 +1054,14 @@ impl FileWriter {
 
     pub fn finish(self) -> Result<Vec<u8>, FormatError> {
         let page_size = self.page_size;
+        if let Some(ps) = page_size
+            && !(MIN_FILE_SPACE_PAGE_SIZE..=MAX_FILE_SPACE_PAGE_SIZE).contains(&ps)
+        {
+            return Err(FormatError::SerializationError(format!(
+                "file space page size {ps} is outside libhdf5's \
+                 {MIN_FILE_SPACE_PAGE_SIZE}..={MAX_FILE_SPACE_PAGE_SIZE} bytes"
+            )));
+        }
         struct DsFlat {
             name: String,
             dt: Datatype,
@@ -1328,12 +1370,12 @@ impl FileWriter {
         let actual_ds_oh_sizes: Vec<usize> = dummy_blobs.iter().map(|b| b.oh_bytes.len()).collect();
 
         // Pass 2: compute real addresses
-        // v4 superblocks add a 4-byte page_size field before the checksum.
-        let superblock_size = if page_size.is_some() {
-            SUPERBLOCK_SIZE + 4
-        } else {
-            SUPERBLOCK_SIZE
-        };
+        // A paged file carries its File Space Info in a superblock extension
+        // object header, placed right after the superblock.
+        let sb_ext = page_size
+            .map(build_paged_superblock_extension)
+            .transpose()?;
+        let superblock_size = SUPERBLOCK_SIZE + sb_ext.as_ref().map_or(0, Vec::len);
         let root_group_addr = superblock_size as u64;
         let mut cursor2 = superblock_size + root_oh_size;
 
@@ -1507,11 +1549,16 @@ impl FileWriter {
         let actual_ds_oh_sizes2: Vec<usize> = ds_blobs2.iter().map(|b| b.oh_bytes.len()).collect();
         debug_assert_eq!(actual_ds_oh_sizes, actual_ds_oh_sizes2);
 
+        // libhdf5 ends a paged file on a page boundary.
+        let data_end = cursor2;
+        if let Some(ps) = page_size {
+            cursor2 = cursor2.next_multiple_of(ps as usize);
+        }
         let eof_addr2 = cursor2 as u64;
         let mut buf = Vec::with_capacity(cursor2);
 
         let sb = Superblock {
-            version: if page_size.is_some() { 4 } else { 3 },
+            version: 3,
             offset_size: OFFSET_SIZE,
             length_size: LENGTH_SIZE,
             base_address: 0,
@@ -1523,11 +1570,18 @@ impl FileWriter {
             free_space_address: None,
             driver_info_address: None,
             consistency_flags: 0,
-            superblock_extension_address: Some(u64::MAX),
+            superblock_extension_address: Some(if sb_ext.is_some() {
+                SUPERBLOCK_SIZE as u64
+            } else {
+                u64::MAX
+            }),
             checksum: None,
-            page_size,
+            page_size: None,
         };
         buf.extend_from_slice(&sb.serialize());
+        if let Some(ref ext) = sb_ext {
+            buf.extend_from_slice(ext);
+        }
 
         // Root group OH
         let mut root_links: Vec<LinkMessage> = Vec::new();
@@ -1595,7 +1649,8 @@ impl FileWriter {
             buf.extend_from_slice(&blob.data);
         }
 
-        debug_assert_eq!(buf.len(), cursor2);
+        debug_assert_eq!(buf.len(), data_end);
+        buf.resize(cursor2, 0);
         Ok(buf)
     }
 }
@@ -2169,7 +2224,8 @@ mod tests {
     }
 
     #[test]
-    fn file_writer_v4_superblock() {
+    fn file_writer_paged_file_uses_v3_superblock_and_fsinfo_extension() {
+        // This used to write superblock "version 4", which does not exist.
         let mut fw = FileWriter::new();
         fw.with_page_size(4096);
         fw.create_dataset("data").with_f64_data(&[1.0, 2.0]);
@@ -2177,8 +2233,31 @@ mod tests {
 
         let sig = signature::find_signature(&bytes).unwrap();
         let sb = Superblock::parse(&bytes, sig).unwrap();
-        assert_eq!(sb.version, 4, "expected superblock v4");
-        assert_eq!(sb.page_size, Some(4096));
+        assert_eq!(sb.version, 3);
+        assert_eq!(sb.superblock_extension_address, Some(48));
+        assert_eq!(bytes.len() % 4096, 0);
+        assert_eq!(sb.eof_address, bytes.len() as u64);
+        let ext = ObjectHeader::parse(&bytes, 48, 8, 8).unwrap();
+        let fsinfo = &ext.messages[0];
+        assert_eq!(fsinfo.msg_type, MessageType::Unknown(0x0017));
+        // Byte-for-byte what HDF5 2.0 writes for fs_strategy="page",
+        // fs_page_size=4096.
+        let mut expected = vec![1u8, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0];
+        expected.extend_from_slice(&4096u64.to_le_bytes());
+        expected.extend_from_slice(&[0, 0]);
+        expected.extend_from_slice(&[0xff; 8]);
+        assert_eq!(fsinfo.data, expected);
+        assert_eq!(fsinfo.flags, 0x14);
+        assert_eq!(read_dataset_f64(&bytes, "data"), vec![1.0, 2.0]);
+    }
+
+    #[test]
+    fn file_writer_rejects_page_sizes_libhdf5_would() {
+        for ps in [0u32, 511, MAX_FILE_SPACE_PAGE_SIZE + 1] {
+            let mut fw = FileWriter::new();
+            fw.with_page_size(ps);
+            assert!(fw.finish().is_err(), "page size {ps}");
+        }
     }
 
     #[test]

crates/clawhdf5-format/src/superblock.rs

@@ -39,7 +39,13 @@ pub struct Superblock {
     pub superblock_extension_address: Option<u64>,
     /// CRC32C checksum (v2/v3 only).
     pub checksum: Option<u32>,
-    /// Page size for page-buffer mode (v4 only). `None` for v0–v3.
+    /// Page size of the non-standard "version 4" superblock layout (v4 only).
+    /// `None` for v0–v3.
+    ///
+    /// HDF5 has no superblock version 4 — libhdf5 refuses it. A real paged
+    /// file is a v2/v3 superblock whose extension holds a File Space Info
+    /// message (what `FileWriter::with_page_size` writes). This field is kept
+    /// only so such files written by older clawhdf5 versions still parse.
     pub page_size: Option<u32>,
 }
 
@@ -127,8 +133,9 @@ impl Superblock {
 
     /// Serialize this superblock to bytes.
     ///
-    /// Writes v2/v3 format, or v4 (with `page_size`) when `self.version == 4`.
-    /// Computes and appends Jenkins lookup3 checksum.
+    /// Writes v2/v3 format, or the non-standard v4 (with `page_size`) when
+    /// `self.version == 4` — which no HDF5 library opens; see
+    /// [`Self::page_size`]. Computes and appends Jenkins lookup3 checksum.
     pub fn serialize(&self) -> Vec<u8> {
         let mut buf = Vec::with_capacity(48);
         buf.extend_from_slice(&HDF5_SIGNATURE);

crates/clawhdf5-format/tests/writer_meta_tests.rs

@@ -317,3 +317,59 @@ fn raw_attributes_copied_from_h5py_survive_a_rewrite() {
     assert_eq!(out, r#"[["/", "/"], "abcdefgh", 1, [258, 772]]"#);
     h5dump_ok(&path);
 }
+
+// ---- 3. paged file-space strategy ----
+
+fn paged_file(page_size: u32) -> Vec<u8> {
+    let mut fw = FileWriter::new();
+    fw.with_page_size(page_size);
+    fw.create_dataset("d").with_f64_data(&[1.0, 2.0, 3.0]);
+    fw.create_dataset("c")
+        .with_i32_data(&(0..100).collect::<Vec<_>>())
+        .with_chunks(&[10]);
+    fw.set_root_attr("a", AttrValue::I64(7));
+    let mut g = fw.create_group("g");
+    g.create_dataset("e").with_u8_data(&[9; 5000]);
+    fw.add_group(g.finish());
+    fw.finish().unwrap()
+}
+
+#[test]
+fn paged_file_has_a_real_superblock() {
+    // Measured: `with_page_size` wrote superblock version 4, which does not
+    // exist ("bad superblock version number" in libhdf5).
+    for ps in [512u32, 4096, 65536] {
+        let bytes = paged_file(ps);
+        let (sb, _) = header_at(&bytes, "/");
+        assert_eq!(sb.version, 3);
+        assert_eq!(bytes.len() % ps as usize, 0);
+        let (_, e) = header_at(&bytes, "g/e");
+        assert!(
+            e.messages
+                .iter()
+                .any(|m| m.msg_type == MessageType::Dataspace)
+        );
+    }
+}
+
+#[test]
+#[ignore = "requires Python h5py module and h5dump"]
+fn h5py_opens_paged_files() {
+    for ps in [512u32, 4096, 65536] {
+        let path = write_tmp(&format!("paged_{ps}"), &paged_file(ps));
+        let out = h5py(
+            &path,
+            "f = h5py.File(path, 'r')\n\
+             p = f.id.get_create_plist()\n\
+             print(json.dumps([p.get_file_space_strategy()[0], p.get_file_space_page_size(),\n\
+             \x20   f['d'][()].tolist(), int(f['c'][()].sum()), int(f.attrs['a']),\n\
+             \x20   int(f['g/e'][()].sum())]))",
+        );
+        assert_eq!(
+            out,
+            format!("[1, {ps}, [1.0, 2.0, 3.0], 4950, 7, 45000]"),
+            "page size {ps}"
+        );
+        h5dump_ok(&path);
+    }
+}