Skip to content

Prevent small Bloom filters from matching every entry #330

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

Open
Harshil-1603 wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Prevent small Bloom filters from matching every entry #330

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
53e2f4d
Prevent newly constructed Bloom filters from matching every entry
Harshil-1603 Oct 14, 2026
8d1485c
Test small Bloom filters and quoted false-positive rates
Harshil-1603 Oct 14, 2026
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
5 changes: 3 additions & 2 deletions bitcoin/bloom.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,8 +107,9 @@ def __init__(self, nElements, nFPRate, nTweak, nFlags):
"""
LN2SQUARED = 0.4804530139182014246671025263266649717305529515945455
LN2 = 0.6931471805599453094172321214581765680755001343602552
self.vData = bytearray(int(min(-1 / LN2SQUARED * nElements * math.log(nFPRate), self.MAX_BLOOM_FILTER_SIZE * 8) / 8))
self.nHashFuncs = int(min(len(self.vData) * 8 / nElements * LN2, self.MAX_HASH_FUNCS))
# Rounding must not produce a filter that matches every element.
self.vData = bytearray(max(1, int(min(-1 / LN2SQUARED * nElements * math.log(nFPRate), self.MAX_BLOOM_FILTER_SIZE * 8) / 8)))
self.nHashFuncs = max(1, int(min(len(self.vData) * 8 / nElements * LN2, self.MAX_HASH_FUNCS)))
self.nTweak = nTweak
self.nFlags = nFlags

Expand Down
14 changes: 14 additions & 0 deletions bitcoin/tests/test_bloom.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,20 @@ def T(expected, seed, data):


class Test_CBloomFilter(unittest.TestCase):
def test_small_and_high_false_positive_rate_filters(self):
for elements in (1, 2, 10, 100):
for rate in (0.05, 0.1, 0.5, 0.9, 0.9999):
filter = CBloomFilter(elements, rate, 0, CBloomFilter.UPDATE_ALL)
# An empty filter must not match everything, even when its
# calculated storage size or hash count rounds down to zero.
self.assertFalse(filter.contains(b'not inserted'))
filter.insert(b'inserted')
self.assertTrue(filter.contains(b'inserted'))
self.assertTrue(filter.IsWithinSizeConstraints())
restored = CBloomFilter.deserialize(filter.serialize())
self.assertTrue(restored.contains(b'inserted'))
self.assertEqual(restored.serialize(), filter.serialize())

def test_create_insert_serialize(self):
filter = CBloomFilter(3, 0.01, 0, CBloomFilter.UPDATE_ALL)

Expand Down