FractalHeapHeader::parse_in reads the header as one window (a second, longer one when it holds an I/O filter pipeline); read_managed_object_in reads direct blocks, indirect blocks (one window up to the last child entry) and huge objects with bounded reads. The &[u8] methods are wrappers. A huge object indexed by the huge-object v2 B-tree, which is not converted yet, is a clean ContiguousStorageRequired error on a backend without the whole file in memory (after the "no index" check, so the error order is unchanged). storage::Window (crate-internal) reads a window of a structure and reports bounds failures exactly as the whole-file ensure_len did, and a short read inside the file is now a Storage error rather than an EOF. New tests: headers (with and without a filter pipeline) cut at every length, and managed objects in a direct root and through an indirect root, huge objects with direct IDs and tiny objects, give identical results through a read_at-only CountingStorage. Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
401 lines
13 KiB
Rust
401 lines
13 KiB
Rust
//! Where the parsers read the file from: the [`Storage`] trait.
|
|
//!
|
|
//! Every parser used to take the whole file as one `&[u8]`. [`Storage`] is
|
|
//! the abstraction that replaces it (see `docs/design/range-reads.md`,
|
|
//! option (a)): a parser asks for the bytes it needs, `[offset, offset +
|
|
//! len)`, with 64-bit offsets, and gets them back as a [`Cow`] — borrowed
|
|
//! when the backend holds the file in memory (a `Vec`, an mmap), owned when
|
|
//! it had to fetch them (a range request, a block cache).
|
|
//!
|
|
//! `impl Storage for [u8]` serves the in-memory case with no copy, and
|
|
//! [`Storage::as_contiguous`] lets a hot loop borrow the whole file at once
|
|
//! when the backend has it. Modules are converted one at a time: a converted
|
|
//! parser has an `*_in(file: &dyn Storage, ..)` core and keeps its old
|
|
//! `&[u8]` signature as a thin wrapper, so callers do not change.
|
|
//!
|
|
//! The trait is synchronous and `no_std`: parsing is CPU work, and a remote
|
|
//! backend bridges to its own I/O.
|
|
|
|
#[cfg(not(feature = "std"))]
|
|
use alloc::{borrow::Cow, boxed::Box, vec::Vec};
|
|
#[cfg(feature = "std")]
|
|
use std::{borrow::Cow, boxed::Box, vec::Vec};
|
|
|
|
use core::ops::Range;
|
|
|
|
use crate::error::FormatError;
|
|
|
|
/// A random-access source of file bytes.
|
|
///
|
|
/// Offsets are relative to the start of the HDF5 data (the superblock), like
|
|
/// every address in the file.
|
|
pub trait Storage {
|
|
/// Bytes `[offset, offset + len)`.
|
|
///
|
|
/// The result is shorter than `len` only when the range runs past the
|
|
/// end of the storage (and empty when `offset` is at or past the end);
|
|
/// a backend that cannot serve a range returns an error instead of a
|
|
/// short read.
|
|
fn read_at(&self, offset: u64, len: usize) -> Result<Cow<'_, [u8]>, FormatError>;
|
|
|
|
/// Current length of the storage in bytes.
|
|
fn len(&self) -> u64;
|
|
|
|
/// Whether the storage holds no bytes.
|
|
fn is_empty(&self) -> bool {
|
|
self.len() == 0
|
|
}
|
|
|
|
/// Several reads at once, in the order given. Backends that talk to a
|
|
/// remote store coalesce and parallelise these; the default reads them
|
|
/// one by one with [`Storage::read_at`].
|
|
fn read_ranges(&self, ranges: &[Range<u64>]) -> Result<Vec<Cow<'_, [u8]>>, FormatError> {
|
|
ranges
|
|
.iter()
|
|
.map(|r| {
|
|
let len = usize::try_from(r.end.saturating_sub(r.start)).map_err(|_| {
|
|
FormatError::Overflow("read range longer than the address space".into())
|
|
})?;
|
|
self.read_at(r.start, len)
|
|
})
|
|
.collect()
|
|
}
|
|
|
|
/// The whole storage as one slice, when the backend has it in memory
|
|
/// (a `Vec`, an mmap). Hot loops use this to keep their zero-copy path;
|
|
/// `None` means every byte has to go through [`Storage::read_at`].
|
|
fn as_contiguous(&self) -> Option<&[u8]> {
|
|
None
|
|
}
|
|
}
|
|
|
|
impl Storage for [u8] {
|
|
#[inline]
|
|
fn read_at(&self, offset: u64, len: usize) -> Result<Cow<'_, [u8]>, FormatError> {
|
|
let n = self.len();
|
|
let start = usize::try_from(offset).map_or(n, |o| o.min(n));
|
|
let end = start.saturating_add(len).min(n);
|
|
Ok(Cow::Borrowed(&self[start..end]))
|
|
}
|
|
|
|
#[inline]
|
|
fn len(&self) -> u64 {
|
|
<[u8]>::len(self) as u64
|
|
}
|
|
|
|
#[inline]
|
|
fn as_contiguous(&self) -> Option<&[u8]> {
|
|
Some(self)
|
|
}
|
|
}
|
|
|
|
impl Storage for Vec<u8> {
|
|
#[inline]
|
|
fn read_at(&self, offset: u64, len: usize) -> Result<Cow<'_, [u8]>, FormatError> {
|
|
self.as_slice().read_at(offset, len)
|
|
}
|
|
|
|
#[inline]
|
|
fn len(&self) -> u64 {
|
|
Vec::len(self) as u64
|
|
}
|
|
|
|
#[inline]
|
|
fn as_contiguous(&self) -> Option<&[u8]> {
|
|
Some(self.as_slice())
|
|
}
|
|
}
|
|
|
|
impl<T: Storage + ?Sized> Storage for &T {
|
|
#[inline]
|
|
fn read_at(&self, offset: u64, len: usize) -> Result<Cow<'_, [u8]>, FormatError> {
|
|
(**self).read_at(offset, len)
|
|
}
|
|
|
|
#[inline]
|
|
fn len(&self) -> u64 {
|
|
(**self).len()
|
|
}
|
|
|
|
#[inline]
|
|
fn read_ranges(&self, ranges: &[Range<u64>]) -> Result<Vec<Cow<'_, [u8]>>, FormatError> {
|
|
(**self).read_ranges(ranges)
|
|
}
|
|
|
|
#[inline]
|
|
fn as_contiguous(&self) -> Option<&[u8]> {
|
|
(**self).as_contiguous()
|
|
}
|
|
}
|
|
|
|
impl<T: Storage + ?Sized> Storage for Box<T> {
|
|
#[inline]
|
|
fn read_at(&self, offset: u64, len: usize) -> Result<Cow<'_, [u8]>, FormatError> {
|
|
(**self).read_at(offset, len)
|
|
}
|
|
|
|
#[inline]
|
|
fn len(&self) -> u64 {
|
|
(**self).len()
|
|
}
|
|
|
|
#[inline]
|
|
fn read_ranges(&self, ranges: &[Range<u64>]) -> Result<Vec<Cow<'_, [u8]>>, FormatError> {
|
|
(**self).read_ranges(ranges)
|
|
}
|
|
|
|
#[inline]
|
|
fn as_contiguous(&self) -> Option<&[u8]> {
|
|
(**self).as_contiguous()
|
|
}
|
|
}
|
|
|
|
#[cfg(feature = "std")]
|
|
impl<T: Storage + ?Sized> Storage for std::sync::Arc<T> {
|
|
#[inline]
|
|
fn read_at(&self, offset: u64, len: usize) -> Result<Cow<'_, [u8]>, FormatError> {
|
|
(**self).read_at(offset, len)
|
|
}
|
|
|
|
#[inline]
|
|
fn len(&self) -> u64 {
|
|
(**self).len()
|
|
}
|
|
|
|
#[inline]
|
|
fn read_ranges(&self, ranges: &[Range<u64>]) -> Result<Vec<Cow<'_, [u8]>>, FormatError> {
|
|
(**self).read_ranges(ranges)
|
|
}
|
|
|
|
#[inline]
|
|
fn as_contiguous(&self) -> Option<&[u8]> {
|
|
(**self).as_contiguous()
|
|
}
|
|
}
|
|
|
|
/// `storage.len()` as the `usize` the parsers' end-of-file errors report
|
|
/// (saturating on targets where the file is larger than the address space).
|
|
#[inline]
|
|
pub(crate) fn len_usize(file: &dyn Storage) -> usize {
|
|
usize::try_from(file.len()).unwrap_or(usize::MAX)
|
|
}
|
|
|
|
/// Bytes `[offset, offset + len)`, all of them.
|
|
///
|
|
/// A range that runs past the end of the storage is
|
|
/// [`FormatError::UnexpectedEof`] with `expected = offset + len` and
|
|
/// `available = storage length` — the error the `&[u8]` parsers give for
|
|
/// the same bounds check (`offset + len > file_data.len()`).
|
|
#[inline]
|
|
pub fn read_exact_at(
|
|
file: &dyn Storage,
|
|
offset: u64,
|
|
len: usize,
|
|
) -> Result<Cow<'_, [u8]>, FormatError> {
|
|
let eof = || FormatError::UnexpectedEof {
|
|
expected: usize::try_from(offset)
|
|
.unwrap_or(usize::MAX)
|
|
.saturating_add(len),
|
|
available: len_usize(file),
|
|
};
|
|
match offset.checked_add(len as u64) {
|
|
Some(end) if end <= file.len() => {}
|
|
_ => return Err(eof()),
|
|
}
|
|
let bytes = file.read_at(offset, len)?;
|
|
if bytes.len() < len {
|
|
// The storage shrank or the backend served a short read inside the
|
|
// file: never parse a partial structure.
|
|
return Err(short_read());
|
|
}
|
|
Ok(bytes)
|
|
}
|
|
|
|
fn short_read() -> FormatError {
|
|
FormatError::Storage(
|
|
"short read inside the file (the storage shrank or the backend failed)".into(),
|
|
)
|
|
}
|
|
|
|
/// A window of the file: up to `max` bytes read at `base`, fewer only at
|
|
/// the end of the file. Its [`Window::ensure`] reports a bounds failure
|
|
/// exactly as the whole-file check `ensure_len(file_data, base + rel, n)`
|
|
/// did — with the absolute position and the file's length — as long as
|
|
/// every position checked lies within the `max` bytes the window was asked
|
|
/// for: then a position past the window is past the end of the file.
|
|
pub(crate) struct Window<'a> {
|
|
/// The bytes, from `base` on.
|
|
pub bytes: Cow<'a, [u8]>,
|
|
base: usize,
|
|
file_len: usize,
|
|
}
|
|
|
|
impl<'a> Window<'a> {
|
|
/// Read up to `max` bytes at `base`.
|
|
pub fn read(file: &'a dyn Storage, base: u64, max: usize) -> Result<Self, FormatError> {
|
|
Ok(Window {
|
|
bytes: read_upto(file, base, max)?,
|
|
base: usize::try_from(base).unwrap_or(usize::MAX),
|
|
file_len: len_usize(file),
|
|
})
|
|
}
|
|
|
|
/// Check that `[rel, rel + needed)` (relative to `base`) is in the file.
|
|
pub fn ensure(&self, rel: usize, needed: usize) -> Result<(), FormatError> {
|
|
match rel.checked_add(needed) {
|
|
Some(end) if end <= self.bytes.len() => Ok(()),
|
|
_ => Err(FormatError::UnexpectedEof {
|
|
expected: self.base.saturating_add(rel).saturating_add(needed),
|
|
available: self.file_len,
|
|
}),
|
|
}
|
|
}
|
|
}
|
|
|
|
/// Up to `max` bytes from `offset` on: fewer only at the end of the
|
|
/// storage. For structures whose size is only known once their prefix has
|
|
/// been parsed and whose parsers bound-check what they are given.
|
|
#[inline]
|
|
pub fn read_upto(
|
|
file: &dyn Storage,
|
|
offset: u64,
|
|
max: usize,
|
|
) -> Result<Cow<'_, [u8]>, FormatError> {
|
|
let avail = file.len().saturating_sub(offset);
|
|
let len = usize::try_from(avail).map_or(max, |a| a.min(max));
|
|
let bytes = file.read_at(offset, len)?;
|
|
if bytes.len() < len {
|
|
return Err(short_read());
|
|
}
|
|
Ok(bytes)
|
|
}
|
|
|
|
/// Borrow the whole file for a code path that has not been converted to
|
|
/// [`Storage`] yet. On a backend without a contiguous view this is the
|
|
/// clean [`FormatError::ContiguousStorageRequired`] error, never a guess.
|
|
#[inline]
|
|
pub fn require_contiguous<'a>(
|
|
file: &'a dyn Storage,
|
|
what: &'static str,
|
|
) -> Result<&'a [u8], FormatError> {
|
|
file.as_contiguous()
|
|
.ok_or(FormatError::ContiguousStorageRequired(what))
|
|
}
|
|
|
|
/// A [`Storage`] over an in-memory buffer that serves every byte through
|
|
/// [`Storage::read_at`] (its [`Storage::as_contiguous`] is `None`, so no
|
|
/// parser can take the whole-slice shortcut), copies what it serves (as a
|
|
/// remote backend would), and counts the reads and bytes.
|
|
///
|
|
/// It is the equivalence harness of the range-read migration: parsing a
|
|
/// file through it must give exactly what parsing the `&[u8]` gives, and
|
|
/// the counters are the request counts a cacheless range reader would make.
|
|
#[derive(Debug)]
|
|
pub struct CountingStorage {
|
|
data: Vec<u8>,
|
|
reads: portable_atomic::AtomicU64,
|
|
bytes: portable_atomic::AtomicU64,
|
|
}
|
|
|
|
impl CountingStorage {
|
|
/// Serve `data` (the file from the superblock on).
|
|
pub fn new(data: Vec<u8>) -> Self {
|
|
CountingStorage {
|
|
data,
|
|
reads: portable_atomic::AtomicU64::new(0),
|
|
bytes: portable_atomic::AtomicU64::new(0),
|
|
}
|
|
}
|
|
|
|
/// Number of `read_at` calls served so far.
|
|
pub fn reads(&self) -> u64 {
|
|
self.reads.load(portable_atomic::Ordering::Relaxed)
|
|
}
|
|
|
|
/// Number of bytes served so far.
|
|
pub fn bytes_read(&self) -> u64 {
|
|
self.bytes.load(portable_atomic::Ordering::Relaxed)
|
|
}
|
|
|
|
/// Reset both counters.
|
|
pub fn reset(&self) {
|
|
self.reads.store(0, portable_atomic::Ordering::Relaxed);
|
|
self.bytes.store(0, portable_atomic::Ordering::Relaxed);
|
|
}
|
|
}
|
|
|
|
impl Storage for CountingStorage {
|
|
fn read_at(&self, offset: u64, len: usize) -> Result<Cow<'_, [u8]>, FormatError> {
|
|
let got = self.data.as_slice().read_at(offset, len)?;
|
|
self.reads.fetch_add(1, portable_atomic::Ordering::Relaxed);
|
|
self.bytes
|
|
.fetch_add(got.len() as u64, portable_atomic::Ordering::Relaxed);
|
|
Ok(Cow::Owned(got.into_owned()))
|
|
}
|
|
|
|
fn len(&self) -> u64 {
|
|
self.data.len() as u64
|
|
}
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod tests {
|
|
use super::*;
|
|
|
|
#[test]
|
|
fn slice_reads_are_borrowed_and_clamped() {
|
|
let data: Vec<u8> = (0u8..10).collect();
|
|
let s: &[u8] = &data;
|
|
let dynamic: &dyn Storage = &s;
|
|
assert_eq!(dynamic.len(), 10);
|
|
let r = dynamic.read_at(2, 3).unwrap();
|
|
assert!(matches!(r, Cow::Borrowed(_)));
|
|
assert_eq!(&*r, &[2, 3, 4]);
|
|
assert_eq!(&*dynamic.read_at(8, 5).unwrap(), &[8, 9]);
|
|
assert!(dynamic.read_at(10, 5).unwrap().is_empty());
|
|
assert!(dynamic.read_at(u64::MAX, 5).unwrap().is_empty());
|
|
assert_eq!(dynamic.as_contiguous(), Some(&data[..]));
|
|
let v: &dyn Storage = &data;
|
|
assert_eq!(v.as_contiguous(), Some(&data[..]));
|
|
}
|
|
|
|
#[test]
|
|
fn read_exact_matches_slice_bounds_errors() {
|
|
let data = [0u8; 10];
|
|
let s: &[u8] = &data;
|
|
assert_eq!(&*read_exact_at(&s, 4, 6).unwrap(), &[0; 6]);
|
|
assert_eq!(
|
|
read_exact_at(&s, 4, 7).unwrap_err(),
|
|
FormatError::UnexpectedEof {
|
|
expected: 11,
|
|
available: 10
|
|
}
|
|
);
|
|
assert!(read_exact_at(&s, u64::MAX, 1).is_err());
|
|
assert_eq!(read_upto(&s, 7, 100).unwrap().len(), 3);
|
|
assert_eq!(read_upto(&s, 70, 100).unwrap().len(), 0);
|
|
}
|
|
|
|
#[test]
|
|
fn counting_storage_counts_and_hides_the_slice() {
|
|
let c = CountingStorage::new((0u8..10).collect());
|
|
assert!(c.as_contiguous().is_none());
|
|
let r = c.read_at(3, 4).unwrap();
|
|
assert!(matches!(r, Cow::Owned(_)));
|
|
assert_eq!(&*r, &[3, 4, 5, 6]);
|
|
c.read_at(8, 4).unwrap();
|
|
assert_eq!((c.reads(), c.bytes_read()), (2, 6));
|
|
c.reset();
|
|
assert_eq!((c.reads(), c.bytes_read()), (0, 0));
|
|
}
|
|
|
|
#[test]
|
|
fn read_ranges_default_loops() {
|
|
let data: Vec<u8> = (0u8..10).collect();
|
|
let s: &[u8] = &data;
|
|
let got = s.read_ranges(&[1..3, 5..9]).unwrap();
|
|
assert_eq!(&*got[0], &[1, 2]);
|
|
assert_eq!(&*got[1], &[5, 6, 7, 8]);
|
|
}
|
|
}
|