8c4fc9d9a4
Add a dedicated length-prefixing method to `Hasher` This accomplishes two main goals: - Make it clear who is responsible for prefix-freedom, including how they should do it - Make it feasible for a `Hasher` that *doesn't* care about Hash-DoS resistance to get better performance by not hashing lengths This does not change rustc-hash, since that's in an external crate, but that could potentially use it in future. Fixes #94026 r? rust-lang/libs --- The core of this change is the following two new methods on `Hasher`: ```rust pub trait Hasher { /// Writes a length prefix into this hasher, as part of being prefix-free. /// /// If you're implementing [`Hash`] for a custom collection, call this before /// writing its contents to this `Hasher`. That way /// `(collection![1, 2, 3], collection![4, 5])` and /// `(collection![1, 2], collection![3, 4, 5])` will provide different /// sequences of values to the `Hasher` /// /// The `impl<T> Hash for [T]` includes a call to this method, so if you're /// hashing a slice (or array or vector) via its `Hash::hash` method, /// you should **not** call this yourself. /// /// This method is only for providing domain separation. If you want to /// hash a `usize` that represents part of the *data*, then it's important /// that you pass it to [`Hasher::write_usize`] instead of to this method. /// /// # Examples /// /// ``` /// #![feature(hasher_prefixfree_extras)] /// # // Stubs to make the `impl` below pass the compiler /// # struct MyCollection<T>(Option<T>); /// # impl<T> MyCollection<T> { /// # fn len(&self) -> usize { todo!() } /// # } /// # impl<'a, T> IntoIterator for &'a MyCollection<T> { /// # type Item = T; /// # type IntoIter = std::iter::Empty<T>; /// # fn into_iter(self) -> Self::IntoIter { todo!() } /// # } /// /// use std:#️⃣:{Hash, Hasher}; /// impl<T: Hash> Hash for MyCollection<T> { /// fn hash<H: Hasher>(&self, state: &mut H) { /// state.write_length_prefix(self.len()); /// for elt in self { /// elt.hash(state); /// } /// } /// } /// ``` /// /// # Note to Implementers /// /// If you've decided that your `Hasher` is willing to be susceptible to /// Hash-DoS attacks, then you might consider skipping hashing some or all /// of the `len` provided in the name of increased performance. #[inline] #[unstable(feature = "hasher_prefixfree_extras", issue = "88888888")] fn write_length_prefix(&mut self, len: usize) { self.write_usize(len); } /// Writes a single `str` into this hasher. /// /// If you're implementing [`Hash`], you generally do not need to call this, /// as the `impl Hash for str` does, so you can just use that. /// /// This includes the domain separator for prefix-freedom, so you should /// **not** call `Self::write_length_prefix` before calling this. /// /// # Note to Implementers /// /// The default implementation of this method includes a call to /// [`Self::write_length_prefix`], so if your implementation of `Hasher` /// doesn't care about prefix-freedom and you've thus overridden /// that method to do nothing, there's no need to override this one. /// /// This method is available to be overridden separately from the others /// as `str` being UTF-8 means that it never contains `0xFF` bytes, which /// can be used to provide prefix-freedom cheaper than hashing a length. /// /// For example, if your `Hasher` works byte-by-byte (perhaps by accumulating /// them into a buffer), then you can hash the bytes of the `str` followed /// by a single `0xFF` byte. /// /// If your `Hasher` works in chunks, you can also do this by being careful /// about how you pad partial chunks. If the chunks are padded with `0x00` /// bytes then just hashing an extra `0xFF` byte doesn't necessarily /// provide prefix-freedom, as `"ab"` and `"ab\u{0}"` would likely hash /// the same sequence of chunks. But if you pad with `0xFF` bytes instead, /// ensuring at least one padding byte, then it can often provide /// prefix-freedom cheaper than hashing the length would. #[inline] #[unstable(feature = "hasher_prefixfree_extras", issue = "88888888")] fn write_str(&mut self, s: &str) { self.write_length_prefix(s.len()); self.write(s.as_bytes()); } } ``` With updates to the `Hash` implementations for slices and containers to call `write_length_prefix` instead of `write_usize`. `write_str` defaults to using `write_length_prefix` since, as was pointed out in the issue, the `write_u8(0xFF)` approach is insufficient for hashers that work in chunks, as those would hash `"a\u{0}"` and `"a"` to the same thing. But since `SipHash` works byte-wise (there's an internal buffer to accumulate bytes until a full chunk is available) it overrides `write_str` to continue to use the add-non-UTF-8-byte approach. --- Compatibility: Because the default implementation of `write_length_prefix` calls `write_usize`, the changed hash implementation for slices will do the same thing the old one did on existing `Hasher`s.
142 lines
3.3 KiB
Rust
142 lines
3.3 KiB
Rust
#![feature(alloc_layout_extra)]
|
|
#![feature(array_chunks)]
|
|
#![feature(array_methods)]
|
|
#![feature(array_windows)]
|
|
#![feature(bench_black_box)]
|
|
#![feature(box_syntax)]
|
|
#![feature(cell_update)]
|
|
#![feature(const_assume)]
|
|
#![feature(const_black_box)]
|
|
#![feature(const_bool_to_option)]
|
|
#![feature(const_cell_into_inner)]
|
|
#![feature(const_convert)]
|
|
#![feature(const_heap)]
|
|
#![feature(const_maybe_uninit_as_mut_ptr)]
|
|
#![feature(const_maybe_uninit_assume_init_read)]
|
|
#![feature(const_nonnull_new)]
|
|
#![feature(const_num_from_num)]
|
|
#![feature(const_ptr_as_ref)]
|
|
#![feature(const_ptr_read)]
|
|
#![feature(const_ptr_write)]
|
|
#![feature(const_trait_impl)]
|
|
#![feature(const_likely)]
|
|
#![feature(core_ffi_c)]
|
|
#![feature(core_intrinsics)]
|
|
#![feature(core_private_bignum)]
|
|
#![feature(core_private_diy_float)]
|
|
#![feature(dec2flt)]
|
|
#![feature(div_duration)]
|
|
#![feature(duration_consts_float)]
|
|
#![feature(duration_constants)]
|
|
#![feature(exact_size_is_empty)]
|
|
#![feature(extern_types)]
|
|
#![feature(flt2dec)]
|
|
#![feature(fmt_internals)]
|
|
#![feature(float_minimum_maximum)]
|
|
#![feature(future_join)]
|
|
#![feature(future_poll_fn)]
|
|
#![feature(array_from_fn)]
|
|
#![feature(hasher_prefixfree_extras)]
|
|
#![feature(hashmap_internals)]
|
|
#![feature(try_find)]
|
|
#![feature(inline_const)]
|
|
#![feature(is_sorted)]
|
|
#![feature(pattern)]
|
|
#![feature(pin_macro)]
|
|
#![feature(sort_internals)]
|
|
#![feature(slice_take)]
|
|
#![feature(slice_from_ptr_range)]
|
|
#![feature(split_as_slice)]
|
|
#![feature(maybe_uninit_uninit_array)]
|
|
#![feature(maybe_uninit_array_assume_init)]
|
|
#![feature(maybe_uninit_write_slice)]
|
|
#![feature(min_specialization)]
|
|
#![feature(numfmt)]
|
|
#![feature(step_trait)]
|
|
#![feature(str_internals)]
|
|
#![feature(std_internals)]
|
|
#![feature(test)]
|
|
#![feature(trusted_len)]
|
|
#![feature(try_blocks)]
|
|
#![feature(try_trait_v2)]
|
|
#![feature(slice_internals)]
|
|
#![feature(slice_partition_dedup)]
|
|
#![feature(int_log)]
|
|
#![feature(iter_advance_by)]
|
|
#![feature(iter_collect_into)]
|
|
#![feature(iter_partition_in_place)]
|
|
#![feature(iter_intersperse)]
|
|
#![feature(iter_is_partitioned)]
|
|
#![feature(iter_order_by)]
|
|
#![feature(iterator_try_collect)]
|
|
#![feature(iterator_try_reduce)]
|
|
#![feature(const_mut_refs)]
|
|
#![feature(const_pin)]
|
|
#![feature(const_slice_from_raw_parts)]
|
|
#![feature(never_type)]
|
|
#![feature(unwrap_infallible)]
|
|
#![feature(result_into_ok_or_err)]
|
|
#![feature(portable_simd)]
|
|
#![feature(ptr_metadata)]
|
|
#![feature(once_cell)]
|
|
#![feature(option_result_contains)]
|
|
#![feature(unsized_tuple_coercion)]
|
|
#![feature(const_option)]
|
|
#![feature(const_option_ext)]
|
|
#![feature(const_result)]
|
|
#![feature(integer_atomics)]
|
|
#![feature(int_roundings)]
|
|
#![feature(slice_group_by)]
|
|
#![feature(split_array)]
|
|
#![feature(strict_provenance)]
|
|
#![feature(trusted_random_access)]
|
|
#![feature(unsize)]
|
|
#![feature(unzip_option)]
|
|
#![feature(const_array_from_ref)]
|
|
#![feature(const_slice_from_ref)]
|
|
#![feature(waker_getters)]
|
|
#![feature(slice_flatten)]
|
|
#![deny(unsafe_op_in_unsafe_fn)]
|
|
|
|
extern crate test;
|
|
|
|
mod alloc;
|
|
mod any;
|
|
mod array;
|
|
mod ascii;
|
|
mod atomic;
|
|
mod bool;
|
|
mod cell;
|
|
mod char;
|
|
mod clone;
|
|
mod cmp;
|
|
mod const_ptr;
|
|
mod convert;
|
|
mod fmt;
|
|
mod future;
|
|
mod hash;
|
|
mod intrinsics;
|
|
mod iter;
|
|
mod lazy;
|
|
mod macros;
|
|
mod manually_drop;
|
|
mod mem;
|
|
mod nonzero;
|
|
mod num;
|
|
mod ops;
|
|
mod option;
|
|
mod pattern;
|
|
mod pin;
|
|
mod pin_macro;
|
|
mod ptr;
|
|
mod result;
|
|
mod simd;
|
|
mod slice;
|
|
mod str;
|
|
mod str_lossy;
|
|
mod task;
|
|
mod time;
|
|
mod tuple;
|
|
mod unicode;
|
|
mod waker;
|