Skip to content

Reuse stored hashes for frozenset hashing and in-place set union #8859

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
youknowone merged 1 commit into from
Sep 27, 2026
Merged

Reuse stored hashes for frozenset hashing and in-place set union #8859

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 10 additions & 24 deletions crates/vm/src/builtins/set.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -491,20 +491,6 @@ impl PySetInner {
}
}

fn update(
&self,
others: impl core::iter::Iterator<Item = ArgIterable>,
vm: &VirtualMachine,
) -> PyResult<()> {
for iterable in others {
for item in iterable.iter(vm)? {
let item = item?;
self.add(&item, vm)?;
}
}
Ok(())
}

fn update_internal(&self, iterable: PyObjectRef, vm: &VirtualMachine) -> PyResult<()> {
// check AnySet
if let Ok(any_set) = AnySet::try_from_object(vm, iterable.to_owned()) {
Expand Down Expand Up @@ -592,15 +578,15 @@ impl PySetInner {
Ok(())
}

fn hash(&self, vm: &VirtualMachine) -> PyResult<PyHash> {
let hasher = self.content.try_fold_keys(
fn hash(&self) -> PyHash {
let hasher = self.content.fold_hashes(
hash::FrozenSetHash::new(self.len()),
|mut hasher, element| {
hasher.add(element.hash(vm)?);
Ok(hasher)
|mut hasher, element_hash| {
hasher.add(element_hash);
hasher
},
)?;
Ok(hasher.finish())
);
hasher.finish()
}

// Run operation, on failure, if item is a set/set subclass, convert it
Expand Down Expand Up @@ -887,7 +873,7 @@ impl PySet {
}

fn __ior__(zelf: PyRef<Self>, set: AnySet, vm: &VirtualMachine) -> PyResult<PyRef<Self>> {
zelf.inner.update(set.into_iterable_iter(vm)?, vm)?;
zelf.inner.merge_set(set, vm)?;
Ok(zelf)
}

Expand Down Expand Up @@ -1424,10 +1410,10 @@ impl AsSequence for PyFrozenSet {

impl Hashable for PyFrozenSet {
#[inline]
fn hash(zelf: &crate::Py<Self>, vm: &VirtualMachine) -> PyResult<PyHash> {
fn hash(zelf: &crate::Py<Self>, _vm: &VirtualMachine) -> PyResult<PyHash> {
let hash = match zelf.hash.load(Ordering::Relaxed) {
hash::SENTINEL => {
let hash = zelf.inner.hash(vm)?;
let hash = zelf.inner.hash();
match Radium::compare_exchange(
&zelf.hash,
hash::SENTINEL,
Expand Down
9 changes: 5 additions & 4 deletions crates/vm/src/dict_inner.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1105,15 +1105,16 @@ impl<T: Clone> Dict<T> {
.collect()
}

pub(crate) fn try_fold_keys<Acc, Fold>(&self, init: Acc, f: Fold) -> PyResult<Acc>
/// Fold stored hashes under the read lock; the callback must not run Python.
pub(crate) fn fold_hashes<Acc, Fold>(&self, init: Acc, f: Fold) -> Acc
where
Fold: FnMut(Acc, &PyObject) -> PyResult<Acc>,
Fold: FnMut(Acc, HashValue) -> Acc,
{
self.read()
.entries
.iter()
.filter_map(|v| v.as_ref().map(|v| v.key.as_object()))
.try_fold(init, f)
.filter_map(|v| v.as_ref().map(|v| v.hash))
.fold(init, f)
}

/// Lookup the index for the given key.
Expand Down
46 changes: 46 additions & 0 deletions extra_tests/snippets/builtin_set.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -566,3 +566,49 @@ def matched_then_error():
dictionary = {key: None}
key.hash_enabled = False
assert_raises(AssertionError, source.intersection, dictionary)


# Native operations reuse hashes stored when an element enters the collection.
class RemainingHashKey:
blocked = False

def __init__(self, value):
self.value = value

def __hash__(self):
assert not type(self).blocked, "stored key was hashed again"
return 7

def __eq__(self, other):
return isinstance(other, RemainingHashKey) and self.value == other.value


class NativeSetSource(set):
def __iter__(self):
raise AssertionError("native set operation called __iter__")


class NativeFrozenSetSource(frozenset):
def __iter__(self):
raise AssertionError("native set operation called __iter__")


stored_keys = [RemainingHashKey(1), RemainingHashKey(2)]
stored_frozen = frozenset(stored_keys)
stored_frozen_reversed = frozenset(reversed(stored_keys))
stored_sources = [
source_type(stored_keys)
for source_type in (set, frozenset, NativeSetSource, NativeFrozenSetSource)
]
RemainingHashKey.blocked = True
stored_hash = hash(stored_frozen)
assert stored_hash == hash(stored_frozen_reversed)
assert stored_hash == hash(stored_frozen)
for stored_source in stored_sources:
stored_target = set()
assert stored_target.__ior__(stored_source) is stored_target
assert len(stored_target) == 2
assert {item.value for item in stored_target} == {1, 2}
stored_target |= stored_target
assert len(stored_target) == 2
RemainingHashKey.blocked = False
Loading