def test_insert_then_test(self):
result = create_index(
'/tmp/fake.csv', # input filename
self.test_file, # file-like object
0.0001, # error rate
1, # skip lines
[1, 2], # fields
',', # delimiter
False) # recursive domain
self.assertEqual(
{'/tmp/fake.csv.2.bfindex': 6,
'/tmp/fake.csv.1.bfindex': 5},
result)
b1 = BloomFilter.fromfile(open('/tmp/fake.csv.1.bfindex', 'rb'))
b2 = BloomFilter.fromfile(open('/tmp/fake.csv.2.bfindex', 'rb'))
self.assertEqual(False, 'FieldA' in b1)
self.assertEqual(False, 'FieldB' in b2)
for word in ('apple', 'banana', 'orange', 'pear', 'pineapple'):
self.assertEqual(True, word in b1)
self.assertEqual(False, word in b2)
for word in ('carrot', 'potato', 'leek', 'cauliflower', 'bean'):
self.assertEqual(True, word in b2)
self.assertEqual(False, word in b1)
def test_insert_then_test(self):
result = create_index(
'/tmp/fake.csv', # input filename
self.test_file, # file-like object
0.0001, # error rate
1, # skip lines
[1, 2], # fields
',', # delimiter
False) # recursive domain
self.assertEqual(
{
'/tmp/fake.csv.2.bfindex': 6,
'/tmp/fake.csv.1.bfindex': 5
}, result)
b1 = BloomFilter.fromfile(open('/tmp/fake.csv.1.bfindex', 'rb'))
b2 = BloomFilter.fromfile(open('/tmp/fake.csv.2.bfindex', 'rb'))
self.assertEqual(False, 'FieldA' in b1)
self.assertEqual(False, 'FieldB' in b2)
for word in ('apple', 'banana', 'orange', 'pear', 'pineapple'):
self.assertEqual(True, word in b1)
self.assertEqual(False, word in b2)
for word in ('carrot', 'potato', 'leek', 'cauliflower', 'bean'):
self.assertEqual(True, word in b2)
self.assertEqual(False, word in b1)
def test_higher_field_than_column_count(self):
self.assertRaises(
InvalidArgument,
lambda: create_index(
'/tmp/fake.csv', # input filename
self.test_file, # file-like object
0.0001, # error rate
1, # skip lines
[4], # fields
',', # delimiter
False)) # recursive domain
def test_higher_field_than_column_count(self):
self.assertRaises(
InvalidArgument,
lambda: create_index(
'/tmp/fake.csv', # input filename
self.test_file, # file-like object
0.0001, # error rate
1, # skip lines
[4], # fields
',', # delimiter
False)) # recursive domain
def test_recursive_domains(self):
result = create_index(
'/tmp/fake.csv', # input filename
self.test_file, # file-like object
0.0001, # error rate
1, # skip lines
[3], # fields
',', # delimiter
True) # recursive domain
self.assertEqual({'/tmp/fake.csv.3.bfindex': 9}, result)
b = BloomFilter.fromfile(open('/tmp/fake.csv.3.bfindex', 'rb'))
for word in ('subdomain.yahoo.com', 'yahoo.com', 'com',
'example.domain.com', 'domain.com', 'www.google.co.uk',
'google.co.uk', 'co.uk', 'uk'):
self.assertEqual(True, word in b)
def test_recursive_domains(self):
result = create_index(
'/tmp/fake.csv', # input filename
self.test_file, # file-like object
0.0001, # error rate
1, # skip lines
[3], # fields
',', # delimiter
True) # recursive domain
self.assertEqual(
{'/tmp/fake.csv.3.bfindex': 9},
result)
b = BloomFilter.fromfile(open('/tmp/fake.csv.3.bfindex', 'rb'))
for word in ('subdomain.yahoo.com', 'yahoo.com', 'com',
'example.domain.com', 'domain.com', 'www.google.co.uk',
'google.co.uk', 'co.uk', 'uk'):
self.assertEqual(True, word in b)
