Rollup merge of #127297 - the8472:path-new-hash, r=Nilstrieb

Improve std::Path's Hash quality by avoiding prefix collisions

This adds a bit rotation to the already existing state so that the same sequence of characters chunked at different offsets into separate path components results in different hashes.

The tests are from #127255

Closes #127254
This commit is contained in:
Matthias Krüger
2024-07-07 14:22:00 +02:00
committed by GitHub
2 changed files with 44 additions and 4 deletions

View File

@@ -3192,15 +3192,19 @@ impl Hash for Path {
let bytes = &bytes[prefix_len..];
let mut component_start = 0;
let mut bytes_hashed = 0;
// track some extra state to avoid prefix collisions.
// ["foo", "bar"] and ["foobar"], will have the same payload bytes
// but result in different chunk_bits
let mut chunk_bits: usize = 0;
for i in 0..bytes.len() {
let is_sep = if verbatim { is_verbatim_sep(bytes[i]) } else { is_sep_byte(bytes[i]) };
if is_sep {
if i > component_start {
let to_hash = &bytes[component_start..i];
chunk_bits = chunk_bits.wrapping_add(to_hash.len());
chunk_bits = chunk_bits.rotate_right(2);
h.write(to_hash);
bytes_hashed += to_hash.len();
}
// skip over separator and optionally a following CurDir item
@@ -3221,11 +3225,12 @@ impl Hash for Path {
if component_start < bytes.len() {
let to_hash = &bytes[component_start..];
chunk_bits = chunk_bits.wrapping_add(to_hash.len());
chunk_bits = chunk_bits.rotate_right(2);
h.write(to_hash);
bytes_hashed += to_hash.len();
}
h.write_usize(bytes_hashed);
h.write_usize(chunk_bits);
}
}