How to use the mmh3.hash function in mmh3

To help you get started, we’ve selected a few mmh3 examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github hajimes / mmh3 / test_mmh3.py View on Github external
def test_hash_unsigned():
    assert mmh3.hash('foo', signed = False) == 4138058784

    # Several test vectors devised by Ian Boyd
    # https://stackoverflow.com/a/31929528
    assert mmh3.hash(b'', seed=0, signed = False) == 0
    assert mmh3.hash(b'', seed=1, signed = False) == 0x514E28B7
    assert mmh3.hash(b'', seed=0xffffffff, signed = False) == 0x81F16F39
    assert mmh3.hash(b'\x21\x43\x65\x87', 0, signed = False) == 0xF55B516B
    assert mmh3.hash(b'\x21\x43\x65\x87',
        0x5082EDEE, signed = False) == 0x2362F9DE
    assert mmh3.hash(b'\x21\x43\x65', 0, signed = False) == 0x7E4A8634
    assert mmh3.hash(b'\x21\x43', 0, signed = False) == 0xA0F7B07A
    assert mmh3.hash(b'\x21', 0, signed = False) == 0x72661CF4
    assert mmh3.hash(b'\xff\xff\xff\xff', 0, signed = False) == 0x76293B50
    assert mmh3.hash(b'\x00\x00\x00\x00', 0, signed = False) == 0x2362F9DE
    assert mmh3.hash(b'\x00\x00\x00', 0, signed = False) == 0x85F0B427
    assert mmh3.hash(b'\x00\x00', 0, signed = False) == 0x30F4C306
    assert mmh3.hash(b'\x00', 0, signed = False) == 0x514E28B7
    
    assert mmh3.hash('aaaa', 0x9747b28c, signed = False) == 0x5A97808A
    assert mmh3.hash('aaa', 0x9747b28c, signed = False) == 0x283E0130
    assert mmh3.hash('aa', 0x9747b28c, signed = False) == 0x5D211726
    assert mmh3.hash('a', 0x9747b28c, signed = False) == 0x7FA09EA6

    assert mmh3.hash('abcd', 0x9747b28c, signed = False) == 0xF0478627
    assert mmh3.hash('abc', 0x9747b28c, signed = False) == 0xC84A62DD
    assert mmh3.hash('ab', 0x9747b28c, signed = False) == 0x74875592
github hajimes / mmh3 / test_mmh3.py View on Github external
assert mmh3.hash(b'', seed=0, signed = False) == 0
    assert mmh3.hash(b'', seed=1, signed = False) == 0x514E28B7
    assert mmh3.hash(b'', seed=0xffffffff, signed = False) == 0x81F16F39
    assert mmh3.hash(b'\x21\x43\x65\x87', 0, signed = False) == 0xF55B516B
    assert mmh3.hash(b'\x21\x43\x65\x87',
        0x5082EDEE, signed = False) == 0x2362F9DE
    assert mmh3.hash(b'\x21\x43\x65', 0, signed = False) == 0x7E4A8634
    assert mmh3.hash(b'\x21\x43', 0, signed = False) == 0xA0F7B07A
    assert mmh3.hash(b'\x21', 0, signed = False) == 0x72661CF4
    assert mmh3.hash(b'\xff\xff\xff\xff', 0, signed = False) == 0x76293B50
    assert mmh3.hash(b'\x00\x00\x00\x00', 0, signed = False) == 0x2362F9DE
    assert mmh3.hash(b'\x00\x00\x00', 0, signed = False) == 0x85F0B427
    assert mmh3.hash(b'\x00\x00', 0, signed = False) == 0x30F4C306
    assert mmh3.hash(b'\x00', 0, signed = False) == 0x514E28B7
    
    assert mmh3.hash('aaaa', 0x9747b28c, signed = False) == 0x5A97808A
    assert mmh3.hash('aaa', 0x9747b28c, signed = False) == 0x283E0130
    assert mmh3.hash('aa', 0x9747b28c, signed = False) == 0x5D211726
    assert mmh3.hash('a', 0x9747b28c, signed = False) == 0x7FA09EA6

    assert mmh3.hash('abcd', 0x9747b28c, signed = False) == 0xF0478627
    assert mmh3.hash('abc', 0x9747b28c, signed = False) == 0xC84A62DD
    assert mmh3.hash('ab', 0x9747b28c, signed = False) == 0x74875592
    assert mmh3.hash('a', 0x9747b28c, signed = False) == 0x7FA09EA6

    assert mmh3.hash('Hello, world!',
        0x9747b28c, signed = False) == 0x24884CBA
    
    assert mmh3.hash(u'ππππππππ'.encode('utf-8'),
        0x9747b28c, signed = False) == 0xD58063C1
        
    assert mmh3.hash('a'*256, 0x9747b28c, signed = False) == 0x37405BDC
github hajimes / mmh3 / test_mmh3.py View on Github external
assert mmh3.hash(b'\x21\x43', 0) == u32_to_s32(0xA0F7B07A)
    assert mmh3.hash(b'\x21', 0) == u32_to_s32(0x72661CF4)
    assert mmh3.hash(b'\xff\xff\xff\xff', 0) == u32_to_s32(0x76293B50)
    assert mmh3.hash(b'\x00\x00\x00\x00', 0) == u32_to_s32(0x2362F9DE)
    assert mmh3.hash(b'\x00\x00\x00', 0) == u32_to_s32(0x85F0B427)
    assert mmh3.hash(b'\x00\x00', 0) == u32_to_s32(0x30F4C306)
    assert mmh3.hash(b'\x00', 0) == u32_to_s32(0x514E28B7)
    
    assert mmh3.hash('aaaa', 0x9747b28c) == u32_to_s32(0x5A97808A)
    assert mmh3.hash('aaa', 0x9747b28c) == u32_to_s32(0x283E0130)
    assert mmh3.hash('aa', 0x9747b28c) == u32_to_s32(0x5D211726)
    assert mmh3.hash('a', 0x9747b28c) == u32_to_s32(0x7FA09EA6)

    assert mmh3.hash('abcd', 0x9747b28c) == u32_to_s32(0xF0478627)
    assert mmh3.hash('abc', 0x9747b28c) == u32_to_s32(0xC84A62DD)
    assert mmh3.hash('ab', 0x9747b28c) == u32_to_s32(0x74875592)
    assert mmh3.hash('a', 0x9747b28c) == u32_to_s32(0x7FA09EA6)

    assert mmh3.hash('Hello, world!', 0x9747b28c) == u32_to_s32(0x24884CBA)
    
    assert mmh3.hash(u'ππππππππ'.encode('utf-8'),
        0x9747b28c) == u32_to_s32(0xD58063C1)
        
    assert mmh3.hash('a'*256, 0x9747b28c) == u32_to_s32(0x37405BDC)

    assert mmh3.hash('abc', 0) == u32_to_s32(0xB3DD93FA)
    assert mmh3.hash('abcdbcdecdefdefgefghfghighijhijkijkljklmklmnlmnomnopnopq',
        0) == u32_to_s32(0xEE925B90)

    assert mmh3.hash('The quick brown fox jumps over the lazy dog',
        0x9747b28c) == u32_to_s32(0x2FA826CD)
github Silv3rHorn / evtx2json / evtx2json.py View on Github external
def _isdup(parsed_output, channel):
    record_hash = hex(mmh3.hash(parsed_output))
    if record_hash in PARSED_RECORDS[channel]:
        return True
    else:
        PARSED_RECORDS[channel].add(record_hash)
        return False
github cpselvis / zhihu-crawler / bloom_filter.py View on Github external
def get_postions(self, url):
        # Get points positions in bit vector.
        point1 = mmh3.hash(url, 41) % BIT_SIZE
        point2 = mmh3.hash(url, 42) % BIT_SIZE
        point3 = mmh3.hash(url, 43) % BIT_SIZE
        point4 = mmh3.hash(url, 44) % BIT_SIZE
        point5 = mmh3.hash(url, 45) % BIT_SIZE
        point6 = mmh3.hash(url, 46) % BIT_SIZE
        point7 = mmh3.hash(url, 47) % BIT_SIZE


        return [point1, point2, point3, point4, point5, point6, point7]
github mbinary / algorithm / search / bloomFilter.py View on Github external
def add(self,item):
        for i in range(self.hash_count):
            idx = mmh3.hash(item,i) % self.size
            self.bits[idx]=1
        return self
    def __contains__(self,item):
github cpselvis / zhihu-crawler / bloom_filter.py View on Github external
def get_postions(self, url):
        # Get points positions in bit vector.
        point1 = mmh3.hash(url, 41) % BIT_SIZE
        point2 = mmh3.hash(url, 42) % BIT_SIZE
        point3 = mmh3.hash(url, 43) % BIT_SIZE
        point4 = mmh3.hash(url, 44) % BIT_SIZE
        point5 = mmh3.hash(url, 45) % BIT_SIZE
        point6 = mmh3.hash(url, 46) % BIT_SIZE
        point7 = mmh3.hash(url, 47) % BIT_SIZE


        return [point1, point2, point3, point4, point5, point6, point7]
github wikimedia / revscoring / revscoring / datasources / meta / hashing.py View on Github external
def mmh3_item(item, n):
    return (2**32 + mmh3.hash(json.dumps(item))) % n
github allenai / spv2 / dataprep2.py View on Github external
        fn = np.vectorize(lambda t: mmh3.hash(normalize(t)), otypes=[np.uint32])
        text_features[:,1] = fn(lab_token_text_features[:,1]) % model_settings.font_hash_size
github s0lst1c3 / sentrygun / sentrygun.py View on Github external
essid=None,
                tx=None,
                intent=None):

    # all arguments are required
    assert not any([
                location is None,
                bssid is None,
                channel is None,
                essid is None,
                tx is None,
                intent is None,
            ])

    # return dict from arguments
    _id = str(mmh3.hash(''.join([ bssid, str(channel), intent])))

    return {
        
        'id' : _id,
        'location' : location,
        'bssid' : bssid,
        'channel' : channel,
        'tx' : tx,
        'essid' : essid,
        'intent' : intent,
        'timestamp' : time.time(),
    }

mmh3

Python extension for MurmurHash (MurmurHash3), a set of fast and robust hash functions.

MIT
Latest version published 2 months ago

Package Health Score

88 / 100
Full package analysis