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/chunked_write.rs
+12 -11
View File
@@ -3,6 +3,7 @@
#[cfg(not(feature = "std"))]
extern crate alloc;
use crate::addr::saturating_usize;
#[cfg(not(feature = "std"))]
use alloc::{format, vec, vec::Vec};
@@ -414,18 +415,18 @@ pub fn split_into_chunks(
// Dataset strides (row-major)
let mut ds_strides = vec![1usize; rank];
for i in (0..rank.saturating_sub(1)).rev() {
ds_strides[i] = ds_strides[i + 1] * shape[i + 1] as usize;
ds_strides[i] = ds_strides[i + 1] * saturating_usize(shape[i + 1]);
}
// Chunk strides
let mut chunk_strides = vec![1usize; rank];
for i in (0..rank.saturating_sub(1)).rev() {
chunk_strides[i] = chunk_strides[i + 1] * chunk_dims[i + 1] as usize;
chunk_strides[i] = chunk_strides[i + 1] * saturating_usize(chunk_dims[i + 1]);
}
let chunk_total_elements: usize = chunk_dims.iter().map(|&d| d as usize).product();
let chunk_total_elements: usize = chunk_dims.iter().map(|&d| saturating_usize(d)).product();
let mut result = Vec::with_capacity(total_chunks as usize);
let mut result = Vec::with_capacity(saturating_usize(total_chunks));
for linear_idx in 0..total_chunks {
// Convert linear index to chunk grid coordinates
@@ -453,8 +454,8 @@ pub fn split_into_chunks(
let coord_in_chunk = remaining_idx / chunk_strides[d];
remaining_idx %= chunk_strides[d];
let global_coord = offsets[d] as usize + coord_in_chunk;
if global_coord >= shape[d] as usize {
let global_coord = saturating_usize(offsets[d]) + coord_in_chunk;
if global_coord >= saturating_usize(shape[d]) {
out_of_bounds = true;
break;
}
@@ -1036,7 +1037,7 @@ impl ChunkIndexPlan {
Ok(Self::SingleChunk)
} else {
let grid = ChunkGrid::fixed_array(shape, Some(max), chunk_dims)?;
Ok(Self::FixedArray(grid, nslots as usize))
Ok(Self::FixedArray(grid, saturating_usize(nslots)))
}
}
1 => Ok(Self::ExtensibleArray(ChunkGrid::extensible_array(
@@ -1251,7 +1252,7 @@ pub fn write_selection_to_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] * saturating_usize(dims[i + 1]);
}
let mut src_offset = 0usize;
@@ -1301,7 +1302,7 @@ pub fn write_selection_to_buffer(
buffer,
new_data,
src_offset,
current_ds_offset + coord as usize * ds_strides[d],
current_ds_offset + saturating_usize(coord) * ds_strides[d],
);
}
}
@@ -1328,14 +1329,14 @@ pub fn write_selection_to_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] * saturating_usize(dims[i + 1]);
}
for (pi, pt) in pts.iter().enumerate() {
let flat: usize = pt
.iter()
.zip(ds_strides.iter())
.map(|(&p, &s)| p as usize * s)
.map(|(&p, &s)| saturating_usize(p) * s)
.sum();
let dst = flat * elem_size;
let src = pi * elem_size;