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]>
This commit is contained in:
co-authored by
Claude Fable 5.1
parent
12847c6c66
commit
e38c8133bc
@@ -63,14 +63,15 @@ fn resolve_compact_entries(
|
||||
Ok(entries)
|
||||
}
|
||||
|
||||
/// Resolve entries from dense storage (fractal heap + B-tree v2).
|
||||
fn resolve_dense_entries(
|
||||
/// Visit every link in dense storage (fractal heap + B-tree v2 name index).
|
||||
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
|
||||
let link = LinkMessage::parse(&link_data, offset_size)?;
|
||||
if let LinkTarget::Hard {
|
||||
object_header_address,
|
||||
} = link.link_target
|
||||
{
|
||||
entries.push(GroupEntry {
|
||||
name: link.name,
|
||||
/// Resolve entries from dense storage (fractal heap + B-tree v2).
|
||||
fn resolve_dense_entries(
|
||||
file_data: &[u8],
|
||||
link_info: &LinkInfoMessage,
|
||||
fh_addr: u64,
|
||||
offset_size: u8,
|
||||
length_size: u8,
|
||||
) -> 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(entries)
|
||||
Ok(found)
|
||||
}
|
||||
|
||||
/// 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, ¤t_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, ¤t_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))),
|
||||
};
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user