quantumclaw/clawhdf5
3
1
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases 1 Wiki Activity

format: no truncating u64 -> usize casts

Browse Source 
Every `u64 as usize` cast in clawhdf5-format (115 on wasm32) now goes
through addr::to_usize for values read from the file — addresses, lengths,
counts, dimensions: FormatError::Overflow where the value does not fit
instead of wrapping onto another part of the file on a 32-bit target — or
addr::saturating_usize for counts bounded by something in memory (codec
progress counters, writer sizes), which fail a bounds check or allocation
rather than wrap. A chunk whose offset does not fit lies outside the
dataset and is skipped; partial reads treat such an offset as out of the
buffers. On 64-bit targets nothing changes.

scripts/check-32bit-casts.sh (run by ci-test.sh) lints the wasm32 build
with clippy's cast_possible_truncation and fails on any u64 -> usize
finding; before this commit it listed 115.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
This commit is contained in:
osobh
2026-09-26 13:33:24 -05:00
co-authored by Claude Opus 5.5
parent 02e89c1d2d
commit b41583113a
27 changed files with 236 additions and 99 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/clawhdf5-format/src/data_read.rs
+9 -8
View File
@@ -6,6 +6,7 @@ use alloc::{collections::BTreeMap, format, string::String, vec, vec::Vec};
#[cfg(feature = "std")]
use std::collections::BTreeMap;
use crate::addr::to_usize;
#[cfg(feature = "std")]
use crate::chunk_cache::ChunkCache;
use crate::chunked_read::read_chunked_data;
@@ -117,7 +118,7 @@ pub fn read_raw_data_zerocopy<'a>(
dataspace: &Dataspace,
datatype: &Datatype,
) -> Result<Option<&'a [u8]>, FormatError> {
let num_elements = dataspace.num_elements() as usize;
let num_elements = to_usize(dataspace.num_elements())?;
let elem_size = datatype.type_size() as usize;
let expected_size = num_elements.checked_mul(elem_size).ok_or_else(|| {
FormatError::Overflow(format!(
@@ -128,7 +129,7 @@ pub fn read_raw_data_zerocopy<'a>(
match layout {
DataLayout::Contiguous { address, size } => {
let addr = address.ok_or(FormatError::NoDataAllocated)?;
let addr = addr as usize;
let addr = to_usize(addr)?;
let sz = contiguous_read_len(*size, expected_size)?;
ensure_len(file_data, addr, sz)?;
Ok(Some(&file_data[addr..addr + sz]))
@@ -219,7 +220,7 @@ fn read_raw_data_full_impl(
length_size: u8,
resolver: Option<&VdsSourceResolver>,
) -> Result<Vec<u8>, FormatError> {
let num_elements = dataspace.num_elements() as usize;
let num_elements = to_usize(dataspace.num_elements())?;
let elem_size = datatype.type_size() as usize;
let expected_size = num_elements.checked_mul(elem_size).ok_or_else(|| {
FormatError::Overflow(format!(
@@ -239,7 +240,7 @@ fn read_raw_data_full_impl(
}
DataLayout::Contiguous { address, size } => {
let addr = address.ok_or(FormatError::NoDataAllocated)?;
let addr = addr as usize;
let addr = to_usize(addr)?;
let sz = contiguous_read_len(*size, expected_size)?;
ensure_len(file_data, addr, sz)?;
let mut out = crate::bulk_alloc::vec_for_bulk(sz);
@@ -582,7 +583,7 @@ pub fn extract_selection_from_buffer(
let rank = dims.len();
let mut ds_strides = vec![1usize; rank];
for i in (0..rank.saturating_sub(1)).rev() {
ds_strides[i] = ds_strides[i + 1] * dims[i + 1] as usize;
ds_strides[i] = ds_strides[i + 1] * to_usize(dims[i + 1])?;
}
let mut output = Vec::with_capacity(pts.len() * elem_size);
@@ -590,8 +591,8 @@ pub fn extract_selection_from_buffer(
let flat: usize = pt
.iter()
.zip(ds_strides.iter())
.map(|(&p, &s)| p as usize * s)
.sum();
.map(|(&p, &s)| Ok(to_usize(p)? * s))
.sum::<Result<usize, FormatError>>()?;
let src = flat * elem_size;
if src + elem_size <= full_data.len() {
output.extend_from_slice(&full_data[src..src + elem_size]);
@@ -1341,7 +1342,7 @@ pub fn read_compound_fields(
let mut fields = Vec::with_capacity(members.len());
for m in members {
let field_size = m.datatype.type_size() as usize;
let offset = m.byte_offset as usize;
let offset = to_usize(m.byte_offset)?;
if offset
.checked_add(field_size)
.is_none_or(|end| end > elem_size)