def test_no_false_negatives():
bf = BloomFilter(size=100, hash_funcs=2)
for ii in range(0, 1000, 20):
bf.add(ii)
for ii in range(0, 1000, 20):
assert ii in bf
def test_bloom_pickle():
bf = BloomFilter(size=100, hash_funcs=2)
for ii in range(0, 1000, 20):
bf.add(ii)
data = pickle.dumps(bf)
bf2 = pickle.loads(data)
for ii in range(0, 1000, 20):
assert ii in bf2
def test_contains():
bf = BloomFilter()
assert 23 not in bf
bf.add(23)
assert 23 in bf
bf.add(5)
bf.add(42)
bf.add(1002)
assert 5 in bf
assert 42 in bf
assert 1002 in bf
def test_to_from_bytes():
bf = BloomFilter(size=100, hash_funcs=2)
for ii in range(0, 1000, 20):
bf.add(ii)
data = bf.to_bytes()
bf2 = BloomFilter()
for ii in range(0, 1000, 20):
assert ii not in bf2
bf2.from_bytes(data)
for ii in range(0, 1000, 20):
assert ii in bf2
assert bf2.to_bytes() == data
def test_from_error():
bf = BloomFilter.from_error_rate(1000)
for ii in range(0, 1000, 20):
bf.add(ii)
for ii in range(0, 1000, 20):
assert ii in bf
def from_bytes(self, bytes_data: bytes) -> "Table":
"""Load a table from a bytestring.
bytes_data (bytes): The data to load.
RETURNS (Table): The loaded table.
DOCS: https://spacy.io/api/lookups#table.from_bytes
"""
loaded = srsly.msgpack_loads(bytes_data)
data = loaded.get("dict", {})
self.name = loaded["name"]
self.bloom = BloomFilter().from_bytes(loaded["bloom"])
self.clear()
self.update(data)
return self
def __init__(self, name: Optional[str] = None, data: Optional[dict] = None) -> None:
"""Initialize a new table.
name (str): Optional table name for reference.
data (dict): Initial data, used to hint Bloom Filter.
DOCS: https://spacy.io/api/lookups#table.init
"""
OrderedDict.__init__(self)
self.name = name
# Assume a default size of 1M items
self.default_size = 1e6
size = max(len(data), 1) if data is not None else self.default_size
self.bloom = BloomFilter.from_error_rate(size)
if data:
self.update(data)
def __init__(self, name=None, data=None):
"""Initialize a new table.
name (unicode): Optional table name for reference.
data (dict): Initial data, used to hint Bloom Filter.
RETURNS (Table): The newly created object.
DOCS: https://spacy.io/api/lookups#table.init
"""
OrderedDict.__init__(self)
self.name = name
# Assume a default size of 1M items
self.default_size = 1e6
size = len(data) if data and len(data) > 0 else self.default_size
self.bloom = BloomFilter.from_error_rate(size)
if data:
self.update(data)
