clawhdf5: File::open_storage reads any Storage through the full API

File::open_storage(Arc<dyn Storage + Send + Sync>) opens a file served by
any backend: groups, datasets, attributes, read_*, selections, VL data
and virtual datasets (external sources through the new
File::set_vds_resolver) all read through Storage::read_at/read_ranges.
The file's view (user block skipped, bounded by the recorded end of
file) is itself a Storage; File::open and File::from_bytes keep their
mmap and in-memory paths, now as that view's as_contiguous() fast path.
A storage-backed file's metadata cache image is laid over each read it
covers (new CacheImage::entries), as libhdf5 loads it.

The typed readers keep their fast paths over any storage: a contiguous
dataset is read in one piece and converted (read_f64 and friends), and a
contiguous native selection reads only its runs
(data_read::read_selection_native_in). Zero-copy methods answer
ContiguousStorageRequired when the bytes are not in memory, and
File::as_bytes panics there (File::contiguous_bytes is the fallible
form).

Test: tests/storage_equivalence.rs reads every fixture, and with
CLAWHDF5_STORAGE_CORPUS every conformance-corpus file, through File::open
and through open_storage over a read_at-only CountingStorage — tree,
attributes, and every dataset's values several ways — and requires
identical transcripts; it prints the read_at calls and bytes a one-pass
read costs per file.

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

crates/clawhdf5-format/src/data_read.rs

@@ -956,6 +956,78 @@ pub fn read_selection_native<T: NativeElement>(
     crate::gather::gather::<T>(raw, dims, elem_size, selection).map(Some)
 }
 
+/// [`read_selection_native`] of a contiguous dataset in any [`Storage`],
+/// reading only the selected elements' runs (adjacent ones merged, one
+/// [`Storage::read_ranges`] call) instead of the whole dataset.
+///
+/// `Ok(None)` wherever the in-memory fast path does not apply and the
+/// caller converts through the byte readers instead: `datatype` is not
+/// `T`'s native representation, the layout is not contiguous, or the
+/// dataset's bytes cannot be located in the file (no address, storage too
+/// small, past the end of file: the cases [`read_raw_data_zerocopy`]
+/// fails). Otherwise the result and errors are [`read_selection_native`]'s
+/// over those bytes.
+pub fn read_selection_native_in<T: NativeElement, S: Storage + ?Sized>(
+    file_data: &S,
+    layout: &DataLayout,
+    dataspace: &Dataspace,
+    datatype: &Datatype,
+    selection: &crate::selection::Selection,
+) -> Result<Option<Vec<T>>, FormatError> {
+    if !T::is_native(datatype) {
+        return Ok(None);
+    }
+    let DataLayout::Contiguous {
+        address: Some(address),
+        size,
+    } = layout
+    else {
+        return Ok(None);
+    };
+    // Where the dataset's bytes are, as `read_raw_data_zerocopy` finds them.
+    let located = to_usize(dataspace.num_elements())
+        .ok()
+        .and_then(|n| n.checked_mul(datatype.type_size() as usize))
+        .filter(|&len| contiguous_read_len(*size, len).is_ok())
+        .filter(|&len| {
+            address
+                .checked_add(len as u64)
+                .is_some_and(|end| end <= file_data.len())
+        });
+    let Some(len) = located else {
+        return Ok(None);
+    };
+    if let Some(all) = file_data.as_contiguous() {
+        let start = to_usize(*address)?;
+        return read_selection_native(
+            &all[start..start + len],
+            &dataspace.dimensions,
+            datatype,
+            selection,
+        );
+    }
+    let dims = &dataspace.dimensions;
+    let elem_size = core::mem::size_of::<T>();
+    let total = dims
+        .iter()
+        .try_fold(1u64, |acc, &d| acc.checked_mul(d))
+        .ok_or_else(|| FormatError::Overflow("dataset shape overflows".into()))?;
+    let expected = crate::chunked_read::checked_byte_len(total, elem_size)?;
+    if len != expected {
+        return Err(FormatError::DataSizeMismatch {
+            expected,
+            actual: len,
+        });
+    }
+    let bytes = if let crate::selection::Selection::All = selection {
+        read_exact_at(file_data, *address, len)?.into_owned()
+    } else {
+        crate::partial_read::validate(selection, dims)?;
+        crate::gather::gather_storage(file_data, *address, len, dims, elem_size, selection)?
+    };
+    Ok(Some(native_to_vec(&bytes, bytes.len() / elem_size)))
+}
+
 /// The bytes of a slice of [`NativeElement`]s.
 #[cfg(feature = "std")]
 fn bytes_of_mut<T: NativeElement>(values: &mut [T]) -> &mut [u8] {

crates/clawhdf5-format/src/superblock_ext.rs

@@ -490,6 +490,23 @@ impl CacheImage {
         image_block_in(file, self.location)
     }
 
+    /// Every entry as `(file address, its bytes)`, taken from `block` (the
+    /// image block, see [`Self::block_in`]), in the order [`Self::apply`]
+    /// writes them: for a reader that cannot write the image over the
+    /// file's bytes and lays the entries over each read instead.
+    pub fn entries<'b>(&self, block: &'b [u8]) -> Result<Vec<(u64, &'b [u8])>, FormatError> {
+        let short = || FormatError::InvalidCacheImage("image applied to the wrong file");
+        self.entries
+            .iter()
+            .map(|e| {
+                let src = block
+                    .get(e.image_offset..e.image_offset + e.len)
+                    .ok_or_else(short)?;
+                Ok((e.address, src))
+            })
+            .collect()
+    }
+
     /// Write every entry over `dst`, the file's bytes from the superblock
     /// on (as long as the `data` the image was decoded from), taking the
     /// entries from `block` (the image block, see [`Self::block`]). `block`