Files
clawhdf5/crates/clawhdf5-format/src/storage.rs
T
osobhandClaude Opus 5.5 7d629f49e3 format: bound and batch every chunk fetch over Storage
Only the full read split its chunk fetches into 64 MiB batches. The
selection path, the indexed read and the parallel_read decoders fetched
every chunk's stored bytes in one read_ranges call, each extent bounded only
by the file length, so a crafted chunk index pointing many chunks at one
large extent made File::open_storage hold chunks x extent bytes (3.3 GB from
a 16.8 MB file) before the first decode error.

- storage::for_each_extent_batch is now the one way raw-data reads fetch
  chunk bytes: batches of at most RAW_BATCH_BYTES (now pub), each decoded
  before the next is fetched. Used by the full, cached, indexed, selection
  and parallel_read paths; the sweep read uses read_extent per chunk.
- ExtentReq carries each chunk's claimed extent (bounds-checked as before,
  same errors) and the prefix actually fetched:
  filters::stored_chunk_limit — the chunk size if unfiltered, else each
  applied filter's worst-case growth (n + n/4 + 4096 per codec; unbounded
  only for an application-registered codec). The in-memory path cuts the
  slice it decodes the same way, so both paths still agree.
- tests/raw_fetch_bounds.rs: a crafted chunked_large.h5 (ten chunks all
  claiming 20 MiB at one padding blob) read through every path over a
  storage that records the largest single fetch; and 160 MiB of legitimate
  unfiltered chunks fetched batch by batch. Before: one 80 MiB fetch
  (selection) and one 160 MiB fetch; after: within the budget.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
2026-09-26 18:30:30 -05:00

698 lines
24 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<S: Storage + ?Sized>(file: &S, ..)` core and keeps
//! its old `&[u8]` signature as a thin wrapper, so callers do not change.
//!
//! The cores are generic rather than taking `&dyn Storage` so that the
//! wrappers monomorphise for `[u8]`: the bounds check of each structure read
//! inlines to what the slice code did, with no indirect call and no copy,
//! which keeps local files as fast as before the migration. A `&dyn Storage`
//! still works (`S = dyn Storage`), and a remote backend pays one indirect
//! call per structure read.
//!
//! 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<S: Storage + ?Sized>(file: &S) -> 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<S: Storage + ?Sized>(
file: &S,
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),
};
// In-memory fast path: plain slicing (for `S = [u8]` this inlines to
// the slice code's bounds check).
if let Some(all) = file.as_contiguous() {
return usize::try_from(offset)
.ok()
.and_then(|start| all.get(start..start.checked_add(len)?))
.map(Cow::Borrowed)
.ok_or_else(eof);
}
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)
}
#[cold]
#[inline(never)]
fn short_read() -> FormatError {
FormatError::Storage(
"short read inside the file (the storage shrank or the backend failed)".into(),
)
}
/// Largest paged data block (fixed or extensible array) read in one piece.
/// A bigger one is read as its prefix and then page by page, only the pages
/// in use, so a block whose size fields claim more than the file holds
/// costs no more than the pages it really has.
pub(crate) const PAGED_BLOCK_ONE_READ_MAX: usize = 1 << 20;
/// 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<S: Storage + ?Sized>(
file: &'a S,
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),
})
}
/// A whole in-memory file as one window (base 0).
#[cfg(test)]
pub fn whole(bytes: &'a [u8]) -> Self {
Window {
bytes: Cow::Borrowed(bytes),
base: 0,
file_len: bytes.len(),
}
}
/// [`Window::ensure`] for a window at `base` that has not been read:
/// whether `[rel, rel + needed)` lies in the file, with the same error.
/// Lets a parser whose first step is to check a structure's whole extent
/// (a checksum at its end) fail before reading a structure that a
/// hostile size field has stretched past the end of the file.
pub fn check_extent<S: Storage + ?Sized>(
file: &S,
base: u64,
rel: usize,
needed: usize,
) -> Result<(), FormatError> {
let base = usize::try_from(base).unwrap_or(usize::MAX);
let file_len = len_usize(file);
match base.checked_add(rel).and_then(|p| p.checked_add(needed)) {
Some(end) if end <= file_len => Ok(()),
_ => Err(FormatError::UnexpectedEof {
expected: base.saturating_add(rel).saturating_add(needed),
available: file_len,
}),
}
}
/// Check that `[rel, rel + needed)` (relative to `base`) is in the file.
#[inline]
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<S: Storage + ?Sized>(
file: &S,
offset: u64,
max: usize,
) -> Result<Cow<'_, [u8]>, FormatError> {
if let Some(all) = file.as_contiguous() {
let start = usize::try_from(offset).map_or(all.len(), |o| o.min(all.len()));
let end = start.saturating_add(max).min(all.len());
return Ok(Cow::Borrowed(&all[start..end]));
}
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)
}
/// Most stored bytes fetched by one [`Storage::read_ranges`] call when a
/// read gathers many extents (a chunked dataset's chunks, a selection's
/// runs): a larger read is fetched and decoded batch by batch, so a backend
/// without the file in memory never holds more than this much undecoded
/// data per read (or one extent, when a single one is larger — and every
/// chunk's extent is bounded by what the chunk can need, see
/// [`crate::filters::stored_chunk_limit`]).
pub const RAW_BATCH_BYTES: usize = 64 << 20;
/// One extent of a raw-data read: `len` bytes stored at `addr`, whose
/// bounds are checked against the file, of which the first `fetch` bytes
/// are read (`None`: only checked, not read — its bytes are not needed).
///
/// `fetch` below `len` bounds what a crafted size field can make a read
/// fetch: a chunk never needs more of its stored bytes than its decoded
/// size allows, however large its index entry says it is.
#[derive(Debug, Clone, Copy)]
pub(crate) struct ExtentReq {
pub addr: u64,
pub len: usize,
pub fetch: Option<usize>,
}
impl ExtentReq {
/// How many bytes are read for this extent.
#[inline]
fn fetch_len(&self) -> usize {
self.fetch.map_or(0, |f| f.min(self.len))
}
}
/// One extent's bytes on their own (see [`ExtentReq`]): the whole extent's
/// bounds checked as [`read_exact_at`] checks them, and its first
/// `req.fetch` bytes read (none when `fetch` is `None`).
pub(crate) fn read_extent<'a, S: Storage + ?Sized>(
file: &'a S,
req: &ExtentReq,
) -> Result<Cow<'a, [u8]>, FormatError> {
let start = usize::try_from(req.addr).unwrap_or(usize::MAX);
match start.checked_add(req.len) {
Some(end) if end <= len_usize(file) => read_exact_at(file, req.addr, req.fetch_len()),
_ => Err(FormatError::UnexpectedEof {
expected: start.saturating_add(req.len),
available: len_usize(file),
}),
}
}
/// The stored bytes of one batch of extents (chunks, contiguous runs),
/// fetched together: [`Storage::read_ranges`] is called once for the batch,
/// so a remote backend can coalesce and parallelise the requests. See
/// [`for_each_extent_batch`], which is how every raw-data read gets them.
///
/// With the whole file in memory nothing is fetched: [`Self::get`] slices
/// it, as the slice readers did. Either way an extent that does not lie in
/// the file is the error the slice readers gave for it
/// ([`FormatError::UnexpectedEof`] with its end and the file length, or
/// [`FormatError::Overflow`] for an address past this platform's `usize`),
/// reported when that extent is asked for — so a read reports the first
/// failing extent in its own order, whatever fails after it.
pub(crate) enum ExtentBytes<'a> {
/// The whole file.
Contiguous(&'a [u8]),
/// Each extent's bytes, or its bounds error; the first is extent
/// `base` of the read.
Fetched {
base: usize,
extents: Vec<Extent<'a>>,
},
}
/// One extent of [`ExtentBytes::Fetched`].
pub(crate) enum Extent<'a> {
/// Its bytes.
Bytes(Cow<'a, [u8]>),
/// In the file, but not fetched (the caller did not want its bytes).
NotFetched,
/// The error reading it gives.
Err(FormatError),
}
impl<'a> ExtentBytes<'a> {
/// Fetch `reqs`, extents `base..base + reqs.len()` of the read: the
/// bytes of those wanted, and the bounds check of all of them.
fn fetch<S: Storage + ?Sized>(
file: &'a S,
reqs: &[ExtentReq],
base: usize,
) -> Result<Self, FormatError> {
if let Some(all) = file.as_contiguous() {
return Ok(ExtentBytes::Contiguous(all));
}
let file_len = len_usize(file);
let mut ranges = Vec::new();
let mut out = Vec::with_capacity(reqs.len());
// Positions in `out` of the extents being read, in `ranges` order.
let mut slots = Vec::new();
for req in reqs {
let checked = crate::addr::to_usize(req.addr).and_then(|start| {
match start.checked_add(req.len) {
Some(end) if end <= file_len => Ok(()),
_ => Err(FormatError::UnexpectedEof {
expected: start.saturating_add(req.len),
available: file_len,
}),
}
});
match checked {
Ok(()) if req.fetch.is_some() => {
slots.push(out.len());
ranges.push(req.addr..req.addr + req.fetch_len() as u64);
out.push(Extent::NotFetched);
}
Ok(()) => out.push(Extent::NotFetched),
Err(e) => out.push(Extent::Err(e)),
}
}
if !ranges.is_empty() {
let got = file.read_ranges(&ranges)?;
if got.len() != ranges.len() {
return Err(FormatError::Storage(
"read_ranges returned the wrong number of ranges".into(),
));
}
for ((slot, bytes), r) in slots.into_iter().zip(got).zip(&ranges) {
if (bytes.len() as u64) < r.end - r.start {
return Err(short_read());
}
out[slot] = Extent::Bytes(bytes);
}
}
Ok(ExtentBytes::Fetched { base, extents: out })
}
/// Whether extent `i` of the read (`req`) lies in the file: its bounds
/// error if not.
pub(crate) fn check(&self, i: usize, req: &ExtentReq) -> Result<(), FormatError> {
match self {
ExtentBytes::Contiguous(_) => self.get(i, req).map(|_| ()),
ExtentBytes::Fetched { base, extents } => {
match i.checked_sub(*base).and_then(|j| extents.get(j)) {
Some(Extent::Err(e)) => Err(e.clone()),
Some(_) => Ok(()),
None => Err(not_fetched()),
}
}
}
}
/// Extent `i` of the read (`req`): its first `req.fetch` bytes, the
/// same whether the file is in memory or not.
pub(crate) fn get(&self, i: usize, req: &ExtentReq) -> Result<&[u8], FormatError> {
match self {
ExtentBytes::Contiguous(all) => {
let start = crate::addr::to_usize(req.addr)?;
start
.checked_add(req.len)
.and_then(|end| all.get(start..end))
.map(|b| &b[..req.fetch_len()])
.ok_or(FormatError::UnexpectedEof {
expected: start.saturating_add(req.len),
available: <[u8]>::len(all),
})
}
ExtentBytes::Fetched { base, extents } => {
match i.checked_sub(*base).and_then(|j| extents.get(j)) {
Some(Extent::Bytes(b)) => Ok(b),
Some(Extent::Err(e)) => Err(e.clone()),
_ => Err(not_fetched()),
}
}
}
}
}
#[cold]
fn not_fetched() -> FormatError {
FormatError::Storage("an extent that was not fetched was asked for".into())
}
/// The one way raw-data reads fetch stored bytes: `reqs` are split into
/// consecutive batches of at most [`RAW_BATCH_BYTES`] of fetched bytes (at
/// least one extent each — and no extent fetches more than its
/// [`ExtentReq::fetch`]), and for each batch in turn its bytes are fetched
/// with one [`Storage::read_ranges`] call and `f(batch, &bytes)` is called,
/// with `bytes` indexed by the extent's position in `reqs`. A batch's bytes
/// are dropped before the next batch is fetched, and an error from `f`
/// stops the read before anything more is fetched.
///
/// With the whole file in memory there is nothing to fetch: one call, over
/// all of `reqs`, that slices the file.
pub(crate) fn for_each_extent_batch<'a, S: Storage + ?Sized>(
file: &'a S,
reqs: &[ExtentReq],
mut f: impl FnMut(Range<usize>, &ExtentBytes<'a>) -> Result<(), FormatError>,
) -> Result<(), FormatError> {
let contiguous = file.as_contiguous().is_some();
for batch in raw_batches(reqs.len(), contiguous, |i| reqs[i].fetch_len()) {
let bytes = ExtentBytes::fetch(file, &reqs[batch.clone()], batch.start)?;
f(batch, &bytes)?;
}
Ok(())
}
/// Split `n` extents, whose sizes `size(i)` gives, into consecutive batches
/// of at most [`RAW_BATCH_BYTES`] (at least one extent each): the ranges of
/// `0..n` to fetch together. With the whole file in memory (`contiguous`)
/// there is nothing to fetch, and one batch.
pub(crate) fn raw_batches(
n: usize,
contiguous: bool,
size: impl Fn(usize) -> usize,
) -> Vec<Range<usize>> {
if contiguous || n == 0 {
return core::iter::once(0..n).collect();
}
let mut out = Vec::new();
let (mut start, mut bytes) = (0, 0usize);
for i in 0..n {
let s = size(i);
if i > start && bytes.saturating_add(s) > RAW_BATCH_BYTES {
out.push(start..i);
start = i;
bytes = 0;
}
bytes = bytes.saturating_add(s);
}
out.push(start..n);
out
}
/// 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, S: Storage + ?Sized>(
file: &'a S,
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]);
}
}