Range reads M0/M1 (indexed lookups, Storage trait), ZFP, in-place editing #17

Merged
osobh merged 52 commits from feat/p3-range-zfp-edit into main 2026-09-26 20:42:22 +00:00
Showing only changes of commit 6a9bb02f37 - Show all commits
+78 -30
View File
@@ -4,6 +4,7 @@
use alloc::string::String; use alloc::string::String;
use crate::error::FormatError; use crate::error::FormatError;
use crate::storage::{Storage, len_usize, read_exact_at};
/// Parsed HDF5 Local Heap header. /// Parsed HDF5 Local Heap header.
#[derive(Debug, Clone)] #[derive(Debug, Clone)]
@@ -16,21 +17,6 @@ pub struct LocalHeap {
pub data_segment_address: u64, pub data_segment_address: u64,
} }
/// Checks that `[offset, offset + needed)` fits within `data`, guarding the
/// addition against `usize` overflow from a crafted near-`usize::MAX` offset.
fn ensure_len(data: &[u8], offset: usize, needed: usize) -> Result<(), FormatError> {
if offset
.checked_add(needed)
.is_none_or(|end| end > data.len())
{
return Err(FormatError::UnexpectedEof {
expected: offset.saturating_add(needed),
available: data.len(),
});
}
Ok(())
}
fn read_offset(data: &[u8], pos: usize, size: u8) -> Result<u64, FormatError> { fn read_offset(data: &[u8], pos: usize, size: u8) -> Result<u64, FormatError> {
let s = size as usize; let s = size as usize;
if pos.checked_add(s).is_none_or(|end| end > data.len()) { if pos.checked_add(s).is_none_or(|end| end > data.len()) {
@@ -57,12 +43,24 @@ impl LocalHeap {
offset: usize, offset: usize,
offset_size: u8, offset_size: u8,
length_size: u8, length_size: u8,
) -> Result<LocalHeap, FormatError> {
Self::parse_in(&file_data, offset as u64, offset_size, length_size)
}
/// [`Self::parse`] over any [`Storage`]: one read of the header.
pub fn parse_in(
file: &dyn Storage,
offset: u64,
offset_size: u8,
length_size: u8,
) -> Result<LocalHeap, FormatError> { ) -> Result<LocalHeap, FormatError> {
// signature(4) + version(1) + reserved(3) = 8, then length_size*2 + offset_size // signature(4) + version(1) + reserved(3) = 8, then length_size*2 + offset_size
let ls = length_size as usize; let ls = length_size as usize;
let os = offset_size as usize; let os = offset_size as usize;
let total = 8 + ls * 2 + os; let total = 8 + ls * 2 + os;
ensure_len(file_data, offset, total)?; let header = read_exact_at(file, offset, total)?;
let file_data: &[u8] = &header;
let offset = 0usize;
if &file_data[offset..offset + 4] != b"HEAP" { if &file_data[offset..offset + 4] != b"HEAP" {
return Err(FormatError::InvalidLocalHeapSignature); return Err(FormatError::InvalidLocalHeapSignature);
@@ -99,6 +97,16 @@ impl LocalHeap {
/// The end of the list is `H5HL_FREE_NULL` (1); an all-ones value (the /// The end of the list is `H5HL_FREE_NULL` (1); an all-ones value (the
/// undefined address) is accepted as "no free list" too. /// undefined address) is accepted as "no free list" too.
pub fn validate_free_list(&self, file_data: &[u8], length_size: u8) -> Result<(), FormatError> { pub fn validate_free_list(&self, file_data: &[u8], length_size: u8) -> Result<(), FormatError> {
self.validate_free_list_in(&file_data, length_size)
}
/// [`Self::validate_free_list`] over any [`Storage`]: two small reads
/// per free block.
pub fn validate_free_list_in(
&self,
file: &dyn Storage,
length_size: u8,
) -> Result<(), FormatError> {
const FREE_NULL: u64 = 1; const FREE_NULL: u64 = 1;
let ls = length_size as usize; let ls = length_size as usize;
let undefined = if ls >= 8 { let undefined = if ls >= 8 {
@@ -123,11 +131,12 @@ impl LocalHeap {
.and_then(|a| usize::try_from(a).ok()) .and_then(|a| usize::try_from(a).ok())
.ok_or(FormatError::InvalidLocalHeapFreeList)?; .ok_or(FormatError::InvalidLocalHeapFreeList)?;
let block_offset = next; let block_offset = next;
next = read_offset(file_data, at, length_size)?; next = read_offset(&read_exact_at(file, at as u64, ls)?, 0, length_size)?;
if next == 0 { if next == 0 {
return Err(FormatError::InvalidLocalHeapFreeList); return Err(FormatError::InvalidLocalHeapFreeList);
} }
let block_size = read_offset(file_data, at + ls, length_size)?; let block_size =
read_offset(&read_exact_at(file, (at + ls) as u64, ls)?, 0, length_size)?;
if block_offset if block_offset
.checked_add(block_size) .checked_add(block_size)
.is_none_or(|end| end > size) .is_none_or(|end| end > size)
@@ -140,6 +149,17 @@ impl LocalHeap {
/// Read a null-terminated string from the heap's data segment at the given byte offset. /// Read a null-terminated string from the heap's data segment at the given byte offset.
pub fn read_string(&self, file_data: &[u8], string_offset: u64) -> Result<String, FormatError> { pub fn read_string(&self, file_data: &[u8], string_offset: u64) -> Result<String, FormatError> {
self.read_string_in(&file_data, string_offset)
}
/// [`Self::read_string`] over any [`Storage`]: one read, from the
/// string to the end of the data segment.
pub fn read_string_in(
&self,
file: &dyn Storage,
string_offset: u64,
) -> Result<String, FormatError> {
let file_len = len_usize(file);
let seg_addr = self.data_segment_address as usize; let seg_addr = self.data_segment_address as usize;
let str_start = let str_start =
seg_addr seg_addr
@@ -153,28 +173,24 @@ impl LocalHeap {
"local heap seg_addr + data_segment_size overflow".into(), "local heap seg_addr + data_segment_size overflow".into(),
))?; ))?;
if str_start >= file_data.len() || str_start >= seg_end { if str_start >= file_len || str_start >= seg_end {
return Err(FormatError::UnexpectedEof { return Err(FormatError::UnexpectedEof {
expected: str_start + 1, expected: str_start + 1,
available: file_data.len(), available: file_len,
}); });
} }
// Find null terminator // Find null terminator
let search_end = seg_end.min(file_data.len()); let search_end = seg_end.min(file_len);
let mut end = str_start; let rest = read_exact_at(file, str_start as u64, search_end - str_start)?;
while end < search_end && file_data[end] != 0 { let Some(len) = rest.iter().position(|&b| b == 0) else {
end += 1;
}
if end >= search_end {
return Err(FormatError::UnexpectedEof { return Err(FormatError::UnexpectedEof {
expected: end + 1, expected: search_end + 1,
available: search_end, available: search_end,
}); });
} };
let s = core::str::from_utf8(&file_data[str_start..end]) let s = core::str::from_utf8(&rest[..len])
.map_err(|_| FormatError::InvalidLocalHeapSignature)?; .map_err(|_| FormatError::InvalidLocalHeapSignature)?;
Ok(String::from(s)) Ok(String::from(s))
} }
@@ -345,4 +361,36 @@ mod tests {
let err = LocalHeap::parse(&file, 0, 8, 8).unwrap_err(); let err = LocalHeap::parse(&file, 0, 8, 8).unwrap_err();
assert_eq!(err, FormatError::InvalidLocalHeapVersion(1)); assert_eq!(err, FormatError::InvalidLocalHeapVersion(1));
} }
/// Header, free list and strings read identically through a
/// `read_at`-only storage, for every truncation of the file.
#[test]
fn storage_reads_match_slice_reads() {
use crate::storage::CountingStorage;
let plain = build_heap_file(0, 64, &["", "alpha", "beta"], 8, 8);
// A free block of 16 bytes at segment offset 12, ending the list.
let mut free = build_heap_file(0, 64, &["", "alpha", "beta", &"x".repeat(20)], 8, 8);
free[16..24].copy_from_slice(&12u64.to_le_bytes());
free[64 + 12..64 + 20].copy_from_slice(&1u64.to_le_bytes());
free[64 + 20..64 + 28].copy_from_slice(&16u64.to_le_bytes());
let mut bad_free = free.clone();
bad_free[64 + 20..64 + 28].copy_from_slice(&99u64.to_le_bytes());
for full in [plain, free, bad_free] {
for cut in 0..=full.len() {
let f = &full[..cut];
let storage = CountingStorage::new(f.to_vec());
let want = LocalHeap::parse(f, 0, 8, 8);
let got = LocalHeap::parse_in(&storage, 0, 8, 8);
assert_eq!(format!("{got:?}"), format!("{want:?}"));
let Ok(heap) = want else { continue };
assert_eq!(
heap.validate_free_list_in(&storage, 8),
heap.validate_free_list(f, 8)
);
for off in [0u64, 1, 2, 6, 7, 11, 100] {
assert_eq!(heap.read_string_in(&storage, off), heap.read_string(f, off));
}
}
}
}
} }