feat(format): follow soft links; explicit errors for external links and external raw data

- Path resolution follows soft links in both old-style (symbol table, cache
  type 2) and new-style (compact and dense Link message) groups: absolute and
  relative targets, links to groups, links through links, with a depth limit
  so a link cycle is NestingDepthExceeded rather than a hang. A dangling link
  reports the target it could not find. Previously every soft link was
  PathNotFound.
- An external link is FormatError::ExternalLinkUnsupported { filename,
  object_path } instead of a misleading PathNotFound.
- Message 0x0007 (External Data Files) is now a known MessageType, and a
  dataset carrying it is FormatError::ExternalDataFilesUnsupported. Such a
  dataset has no data address in this file, so it would otherwise be read as
  "never written" and answered with fill values — wrong data, no error.
- Dense link iteration is shared between hard-link listing and the new
  symbolic-link lookup; entry listing behaviour is unchanged.
- h5py interop test for both libver settings.

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

crates/clawhdf5-format/src/error.rs

@@ -117,6 +117,17 @@ pub enum FormatError {
     /// A message is marked shared but was parsed without access to the file,
     /// so the reference to the real message could not be followed.
     UnresolvedSharedMessage,
+    /// The dataset's raw data is stored in external files (External Data
+    /// Files message), which this reader does not follow.
+    ExternalDataFilesUnsupported,
+    /// The path goes through an external link (a link into another file),
+    /// which this reader does not follow.
+    ExternalLinkUnsupported {
+        /// The file the link points into.
+        filename: String,
+        /// The object path within that file.
+        object_path: String,
+    },
     /// Invalid SOHM table version.
     InvalidSohmTableVersion(u8),
     /// Invalid SOHM table signature (expected "SMTB").
@@ -310,6 +321,18 @@ impl fmt::Display for FormatError {
             FormatError::InvalidSharedMessageVersion(v) => {
                 write!(f, "invalid shared message version: {v}")
             }
+            FormatError::ExternalLinkUnsupported {
+                filename,
+                object_path,
+            } => write!(
+                f,
+                "path goes through an external link to {object_path} in {filename}, which is \
+                 not supported"
+            ),
+            FormatError::ExternalDataFilesUnsupported => write!(
+                f,
+                "dataset raw data is stored in external file(s), which is not supported"
+            ),
             FormatError::UnresolvedSharedMessage => write!(
                 f,
                 "message is shared but no file data was available to resolve it"

crates/clawhdf5-format/src/fill_value.rs

@@ -165,6 +165,15 @@ pub fn read_full_with_fill<E: From<FormatError>>(
     length_size: u8,
     read: impl FnOnce() -> Result<Vec<u8>, E>,
 ) -> Result<Vec<u8>, E> {
+    // A dataset with external raw data also has no data address in this
+    // file. It is NOT unallocated — its values live elsewhere — so it must
+    // never be answered with the fill value.
+    if messages
+        .iter()
+        .any(|m| m.msg_type == MessageType::ExternalDataFiles)
+    {
+        return Err(FormatError::ExternalDataFilesUnsupported.into());
+    }
     let fill = dataset_fill_value(messages)?;
     if !has_storage(layout) {
         return Ok(filled_dataset(dataspace, elem_size, fill.as_deref())?);

crates/clawhdf5-format/src/group_v1.rs

@@ -60,6 +60,54 @@ pub fn resolve_v1_group_entries(
     Ok(entries)
 }
 
+/// Symbol table cache type for a soft link: the scratch pad's first four bytes
+/// are the local-heap offset of the link's target path, and the entry's object
+/// header address is undefined.
+const CACHE_TYPE_SOFT_LINK: u32 = 2;
+
+/// The target path of the soft link called `name` in a v1 group, if any.
+pub fn find_v1_soft_link(
+    file_data: &[u8],
+    sym_table_msg: &SymbolTableMessage,
+    name: &str,
+    offset_size: u8,
+    length_size: u8,
+) -> Result<Option<String>, FormatError> {
+    let heap = LocalHeap::parse(
+        file_data,
+        sym_table_msg.local_heap_address as usize,
+        offset_size,
+        length_size,
+    )?;
+    let snod_addrs = collect_symbol_table_nodes(
+        file_data,
+        sym_table_msg.btree_address,
+        offset_size,
+        length_size,
+    )?;
+    for snod_addr in snod_addrs {
+        let snod = SymbolTableNode::parse(file_data, snod_addr as usize, offset_size)?;
+        for entry in &snod.entries {
+            if entry.cache_type != CACHE_TYPE_SOFT_LINK {
+                continue;
+            }
+            if heap.read_string(file_data, entry.link_name_offset)? != name {
+                continue;
+            }
+            let value_offset = u32::from_le_bytes([
+                entry.scratch_pad[0],
+                entry.scratch_pad[1],
+                entry.scratch_pad[2],
+                entry.scratch_pad[3],
+            ]);
+            return heap
+                .read_string(file_data, u64::from(value_offset))
+                .map(Some);
+        }
+    }
+    Ok(None)
+}
+
 /// Extract the SymbolTableMessage from an object header's messages.
 fn find_symbol_table_message(
     obj_header: &ObjectHeader,

crates/clawhdf5-format/src/group_v2.rs

@@ -63,14 +63,15 @@ fn resolve_compact_entries(
     Ok(entries)
 }
 
-/// Resolve entries from dense storage (fractal heap + B-tree v2).
+/// Visit every link in dense storage (fractal heap + B-tree v2 name index).
-fn resolve_dense_entries(
+fn for_each_dense_link(
     file_data: &[u8],
     link_info: &LinkInfoMessage,
     fh_addr: u64,
     offset_size: u8,
     length_size: u8,
-) -> Result<Vec<GroupEntry>, FormatError> {
+    mut visit: impl FnMut(LinkMessage),
+) -> Result<(), FormatError> {
     // Parse fractal heap
     let fh = FractalHeapHeader::parse(file_data, fh_addr as usize, offset_size, length_size)?;
 
@@ -81,7 +82,6 @@ fn resolve_dense_entries(
     let btree_hdr = BTreeV2Header::parse(file_data, btree_addr as usize, offset_size, length_size)?;
     let records = collect_btree_v2_records(file_data, &btree_hdr, offset_size, length_size)?;
 
-    let mut entries = Vec::new();
     for record in &records {
         // For type 5 (name index): hash(4) + heap_id(heap_id_length)
         // For type 6 (creation order): creation_order(8) + heap_id(heap_id_length)
@@ -98,22 +98,94 @@ fn resolve_dense_entries(
 
         // Read managed object from fractal heap
         let link_data = fh.read_managed_object(file_data, id_bytes, offset_size)?;
+        visit(LinkMessage::parse(&link_data, offset_size)?);
+    }
+    Ok(())
+}
 
-        // Parse as Link message
+/// Resolve entries from dense storage (fractal heap + B-tree v2).
-        let link = LinkMessage::parse(&link_data, offset_size)?;
+fn resolve_dense_entries(
-        if let LinkTarget::Hard {
+    file_data: &[u8],
-            object_header_address,
+    link_info: &LinkInfoMessage,
-        } = link.link_target
+    fh_addr: u64,
-        {
+    offset_size: u8,
-            entries.push(GroupEntry {
+    length_size: u8,
-                name: link.name,
+) -> Result<Vec<GroupEntry>, FormatError> {
+    let mut entries = Vec::new();
+    for_each_dense_link(
+        file_data,
+        link_info,
+        fh_addr,
+        offset_size,
+        length_size,
+        |link| {
+            if let LinkTarget::Hard {
                 object_header_address,
-                cache_type: 0,
+            } = link.link_target
-            });
+            {
+                entries.push(GroupEntry {
+                    name: link.name,
+                    object_header_address,
+                    cache_type: 0,
+                });
+            }
+        },
+    )?;
+    Ok(entries)
+}
+
+/// The soft or external link called `name` in this group, if there is one.
+/// Hard links are what `resolve_group_entries` returns; this is consulted only
+/// when a path component isn't among them.
+fn find_symbolic_link(
+    file_data: &[u8],
+    object_header: &ObjectHeader,
+    name: &str,
+    offset_size: u8,
+    length_size: u8,
+) -> Result<Option<LinkTarget>, FormatError> {
+    if is_v1_group(object_header) {
+        let Some(sym_msg) = object_header
+            .messages
+            .iter()
+            .find(|m| m.msg_type == MessageType::SymbolTable)
+        else {
+            return Ok(None);
+        };
+        let stm = SymbolTableMessage::parse(&sym_msg.data, offset_size)?;
+        return group_v1::find_v1_soft_link(file_data, &stm, name, offset_size, length_size)
+            .map(|target| target.map(|target_path| LinkTarget::Soft { target_path }));
+    }
+    if !is_v2_group(object_header) {
+        return Ok(None);
+    }
+    let is_symbolic = |t: &LinkTarget| !matches!(t, LinkTarget::Hard { .. });
+    let link_info = find_link_info(object_header, offset_size)?;
+    let mut found = None;
+    if let Some(fh_addr) = link_info.fractal_heap_address {
+        for_each_dense_link(
+            file_data,
+            &link_info,
+            fh_addr,
+            offset_size,
+            length_size,
+            |link| {
+                if link.name == name && is_symbolic(&link.link_target) {
+                    found = Some(link.link_target);
+                }
+            },
+        )?;
+    } else {
+        for msg in &object_header.messages {
+            if msg.msg_type == MessageType::Link {
+                let link = LinkMessage::parse(&msg.data, offset_size)?;
+                if link.name == name && is_symbolic(&link.link_target) {
+                    found = Some(link.link_target);
+                }
+            }
         }
     }
-
+    Ok(found)
-    Ok(entries)
 }
 
 /// Find and parse the Link Info message from an object header.
@@ -158,6 +230,19 @@ pub fn resolve_path_any(
     file_data: &[u8],
     superblock: &Superblock,
     path: &str,
+) -> Result<u64, FormatError> {
+    resolve_path_following_links(file_data, superblock, path, 0)
+}
+
+/// Soft links followed while resolving one path. Guards against link cycles
+/// (`a -> b -> a`), which are legal to create.
+const MAX_SOFT_LINK_DEPTH: u8 = 16;
+
+fn resolve_path_following_links(
+    file_data: &[u8],
+    superblock: &Superblock,
+    path: &str,
+    depth: u8,
 ) -> Result<u64, FormatError> {
     let components: Vec<&str> = path.split('/').filter(|s| !s.is_empty()).collect();
     if components.is_empty() {
@@ -176,7 +261,9 @@ pub fn resolve_path_any(
     for (i, component) in components.iter().enumerate() {
         let entries = resolve_group_entries(file_data, &current_header, os, ls)?;
 
-        let found = entries.iter().find(|e| e.name == *component);
+        let found = entries
+            .iter()
+            .find(|e| e.name == *component && e.object_header_address != u64::MAX);
         match found {
             Some(entry) => {
                 if i == components.len() - 1 {
@@ -186,7 +273,37 @@ pub fn resolve_path_any(
                 current_header = ObjectHeader::parse(file_data, current_addr as usize, os, ls)?;
             }
             None => {
-                return Err(FormatError::PathNotFound(String::from(*component)));
+                return match find_symbolic_link(file_data, &current_header, component, os, ls)? {
+                    Some(LinkTarget::Soft { target_path }) => {
+                        if depth >= MAX_SOFT_LINK_DEPTH {
+                            return Err(FormatError::NestingDepthExceeded);
+                        }
+                        // A relative target is relative to the group holding
+                        // the link; then the rest of the original path.
+                        let mut full = String::new();
+                        if !target_path.starts_with('/') {
+                            for parent in &components[..i] {
+                                full.push('/');
+                                full.push_str(parent);
+                            }
+                        }
+                        full.push('/');
+                        full.push_str(&target_path);
+                        for rest in &components[i + 1..] {
+                            full.push('/');
+                            full.push_str(rest);
+                        }
+                        resolve_path_following_links(file_data, superblock, &full, depth + 1)
+                    }
+                    Some(LinkTarget::External {
+                        filename,
+                        object_path,
+                    }) => Err(FormatError::ExternalLinkUnsupported {
+                        filename,
+                        object_path,
+                    }),
+                    _ => Err(FormatError::PathNotFound(String::from(*component))),
+                };
             }
         }
     }

crates/clawhdf5-format/src/message_type.rs

@@ -9,6 +9,9 @@ pub enum MessageType {
     Datatype,
     FillValueOld,
     FillValue,
+    /// External Data Files (0x0007): the dataset's raw data lives in other
+    /// files, listed by this message.
+    ExternalDataFiles,
     Link,
     DataLayout,
     GroupInfo,
@@ -36,6 +39,7 @@ impl MessageType {
             0x0004 => MessageType::FillValueOld,
             0x0005 => MessageType::FillValue,
             0x0006 => MessageType::Link,
+            0x0007 => MessageType::ExternalDataFiles,
             0x0008 => MessageType::DataLayout,
             0x000A => MessageType::GroupInfo,
             0x000B => MessageType::FilterPipeline,
@@ -60,6 +64,7 @@ impl MessageType {
             MessageType::Datatype => 0x0003,
             MessageType::FillValueOld => 0x0004,
             MessageType::FillValue => 0x0005,
+            MessageType::ExternalDataFiles => 0x0007,
             MessageType::Link => 0x0006,
             MessageType::DataLayout => 0x0008,
             MessageType::GroupInfo => 0x000A,
@@ -90,6 +95,7 @@ mod tests {
             (0x0003, MessageType::Datatype),
             (0x0004, MessageType::FillValueOld),
             (0x0005, MessageType::FillValue),
+            (0x0007, MessageType::ExternalDataFiles),
             (0x0006, MessageType::Link),
             (0x0008, MessageType::DataLayout),
             (0x000A, MessageType::GroupInfo),
@@ -119,8 +125,13 @@ mod tests {
 
     #[test]
     fn unknown_type_zero_gap() {
-        // 0x0007 is not a defined type
+        // 0x0009 is reserved for the library's own testing; no file uses it.
-        let mt = MessageType::from_u16(0x0007);
+        let mt = MessageType::from_u16(0x0009);
-        assert_eq!(mt, MessageType::Unknown(0x0007));
+        assert_eq!(mt, MessageType::Unknown(0x0009));
+        // 0x0007 used to be treated as unknown: it is External Data Files.
+        assert_eq!(
+            MessageType::from_u16(0x0007),
+            MessageType::ExternalDataFiles
+        );
     }
 }

crates/clawhdf5/tests/h5py_interop_tests.rs

@@ -699,3 +699,88 @@ with h5py.File("{path_str}", "r") as f:
         );
     }
 }
+
+// ---------------------------------------------------------------------------
+// h5py writes soft / external links and external raw data -> clawhdf5
+// ---------------------------------------------------------------------------
+
+/// Soft links are followed (absolute, relative, through groups, with a cycle
+/// guard). Things this reader does not follow — external links, and datasets
+/// whose raw data lives in another file — are explicit errors. They used to
+/// surface as a misleading `PathNotFound`, and external raw data could read
+/// back as fill values.
+#[test]
+fn h5py_links_clawhdf5_resolves_or_refuses() {
+    use clawhdf5::Error;
+    use clawhdf5_format::error::FormatError;
+
+    skip_if_no_python!();
+    let dir = tempfile::tempdir().unwrap();
+    let dir_str = dir.path().display().to_string();
+    for (tag, kwargs) in [("default", ""), ("latest", ", libver='latest'")] {
+        let script = format!(
+            r#"
+import h5py, numpy as np, os
+os.chdir("{dir_str}")
+with h5py.File("other_{tag}.h5", "w"{kwargs}) as o:
+    o.create_dataset("remote", data=np.arange(3, dtype="<i4"))
+with h5py.File("links_{tag}.h5", "w"{kwargs}) as f:
+    f.create_dataset("real", data=np.arange(4, dtype="<i4"))
+    g = f.create_group("grp")
+    g.create_dataset("inner", data=np.arange(2, dtype="<i4"))
+    g["rel"] = h5py.SoftLink("inner")
+    f["soft"] = h5py.SoftLink("/real")
+    f["soft_grp"] = h5py.SoftLink("/grp")
+    f["dangling"] = h5py.SoftLink("/nope")
+    f["loop_a"] = h5py.SoftLink("/loop_b")
+    f["loop_b"] = h5py.SoftLink("/loop_a")
+    f["ext"] = h5py.ExternalLink("other_{tag}.h5", "/remote")
+    f.create_dataset("extdata", shape=(4,), dtype="<i4", external=[("raw_{tag}.bin", 0, 16)])
+    f["extdata"][...] = np.array([11, 22, 33, 44], dtype="<i4")
+"#
+        );
+        run_python(&script);
+
+        let file = File::open(dir.path().join(format!("links_{tag}.h5"))).unwrap();
+        let read = |path: &str| file.dataset(path).and_then(|d| d.read_i32());
+        assert_eq!(read("soft").unwrap(), vec![0, 1, 2, 3], "{tag}");
+        assert_eq!(read("soft_grp/inner").unwrap(), vec![0, 1], "{tag}");
+        assert_eq!(
+            read("grp/rel").unwrap(),
+            vec![0, 1],
+            "{tag}: relative target"
+        );
+        assert_eq!(
+            read("soft_grp/rel").unwrap(),
+            vec![0, 1],
+            "{tag}: link via link"
+        );
+
+        assert!(
+            matches!(read("dangling"), Err(Error::Format(FormatError::PathNotFound(p))) if p == "nope"),
+            "{tag}: dangling link names its missing target"
+        );
+        assert!(
+            matches!(
+                read("loop_a"),
+                Err(Error::Format(FormatError::NestingDepthExceeded))
+            ),
+            "{tag}: link cycle"
+        );
+        assert!(
+            matches!(
+                read("ext"),
+                Err(Error::Format(FormatError::ExternalLinkUnsupported { ref object_path, .. }))
+                    if object_path == "/remote"
+            ),
+            "{tag}: external link"
+        );
+        assert!(
+            matches!(
+                read("extdata"),
+                Err(Error::Format(FormatError::ExternalDataFilesUnsupported))
+            ),
+            "{tag}: external raw data must not read as fill values"
+        );
+    }
+}