def test_init(self):
hash_map = HashMap()
self.assertEqual(len(hash_map._bucket_array), 10)
hash_map = HashMap(('key', 'value'))
self.assertEqual(len(hash_map._bucket_array), 10)
hash_map = HashMap([
(self.key_1, self.value_1),
(self.key_2, self.value_2)
])
self.assertEqual(len(hash_map._bucket_array), 10)
self.assertRaises(TypeError, HashMap, 'string')
def test_insert(self):
d = HashMap()
d.insert(lower_to_upper.items())
self.assertEqual(len(d), len(lowercase))
for ll, ul in zip(lowercase, uppercase):
self.assertEqual(d[ll], ul)
def main():
m = HashMap()
ops = [
('insert', (5, 6), (True, )),
('lookup', (5, ), (6, )),
('insert', (7, 3), (True, )),
('lookup', (7, ), (3, )),
('lookup', (5, ), (6, )),
('insert', (5, 2), (False, )),
('lookup', (5, ), (2, )),
('erase', (5, ), (True, )),
('lookup', (5, ), (None, )),
('erase', (3, ), (False, )),
]
for op, input, expected_output in ops:
if op == 'insert':
output = (m.insert(*input), )
elif op == 'lookup':
output = (m.lookup(*input), )
else:
output = (m.erase(*input), )
assert output == expected_output, 'Expected {} == {}'.format(
output, expected_output)
print('Succeed')
def test_update(self):
d = HashMap()
d.update(lower_to_upper)
self.assertEqual(len(d), len(lowercase))
for ll, ul in lower_to_upper.items():
self.assertEqual(d[ll], ul)
def test_rehashing(self):
keys = [
"first", "second", "third", "fourth", "fifth", "sixth", "seventh",
"eighth", "ninth", "tenth"
]
values = list(range(1, 11))
hm = HashMap()
self.assertEqual(hm.size(), 0)
self.assertEqual(hm.capacity(), 8)
for i in range(0, 5):
hm.set(keys[i], values[i])
self.assertEqual(hm.size(), 5)
self.assertEqual(hm.capacity(), 8)
output = hm.keys()
self.assertEqual(len(output), 5)
for key in output:
self.assertIn(key, keys)
for i in range(5, 10):
hm.set(keys[i], values[i])
self.assertEqual(hm.size(), 10)
self.assertEqual(hm.capacity(), 16)
output = hm.keys()
for key in output:
self.assertIn(key, keys)
for key in keys:
self.assertIn(key, output)
def download(client, container, object, path):
res = client.retrieve_object_hashmap(container, object)
blocksize = int(res['block_size'])
blockhash = res['block_hash']
bytes = res['bytes']
map = res['hashes']
if os.path.exists(path):
h = HashMap(blocksize, blockhash)
h.load(open(path))
hashes = [hexlify(x) for x in h]
else:
open(path, 'w').close() # Create an empty file
hashes = []
with open(path, 'a+') as fp:
if bytes != 0:
for i, h in enumerate(map):
if i < len(hashes) and h == hashes[i]:
continue
start = i * blocksize
end = '' if i == len(map) - 1 else ((i + 1) * blocksize) - 1
data = client.retrieve_object(
container, object, range='bytes=%s-%s' % (start, end))
if i != len(map) - 1:
data += (blocksize - len(data)) * '\x00'
fp.seek(start)
fp.write(data)
fp.truncate(bytes)
def test_getitem_magic_method_raises_value_error_when_target_key_not_extant(
self):
hashmap = HashMap()
hashmap['key'] = 'val'
self.assertEqual(hashmap['key'], 'val')
with self.assertRaises(ValueError):
hashmap['not_key']
def test_multiprocessing_update(self):
d = HashMap(key_type=ctypes.c_int,
value_type=ctypes.c_int,
lock=mp.Lock())
def update_1():
d.update({1: 1, 11: 11, 111: 111})
def update_2():
d.update({2: 2, 22: 22, 222: 222})
p1 = mp.Process(target=update_1)
p2 = mp.Process(target=update_2)
p1.start()
p2.start()
p1.join()
p2.join()
for n in [1, 11, 111]:
self.assertTrue(n in d)
for n in [2, 22, 222]:
self.assertTrue(n in d)
self.assertEqual(len(d), 6)
def test_can_set_and_get_basic_case(self):
hashmap = HashMap()
self.assertEqual(hashmap._number_of_elements, 0)
hashmap.set('key', 'val')
self.assertEqual(hashmap._number_of_elements, 1)
self.assertEqual(hashmap.get('key'), 'val')
self.assertIsNone(hashmap.get('otherval'))
def test_has(self):
# New HashMap object
HM = HashMap()
# For Normal Inputs
# Putting Value
self.assertTrue(HM.put(1, "one"))
self.assertTrue(HM.put(2, "two"))
# Testing has()
self.assertTrue(HM.has(1))
self.assertTrue(HM.has(2))
# For Inputs with colliding hash values
self.assertTrue(HM.put(3, "three"))
self.assertTrue(HM.put(25, "twenty-five"))
self.assertTrue(HM.put(36, "thirty-six"))
self.assertTrue(HM.put(47, "forty-seven"))
self.assertTrue(HM.has(3))
self.assertTrue(HM.has(25))
self.assertTrue(HM.has(36))
self.assertTrue(HM.has(47))
self.assertTrue(HM.has(1))
self.assertTrue(HM.has(2))
self.assertFalse(HM.has(4))
def main():
"""Runs the main program"""
hash_map = HashMap()
def count(key):
"""Function to return the value attached to the key given"""
number = hash_map.get(key, 0)
return number
with open("AliceInWonderland.txt", 'r') as alice:
for line in alice:
words = clean_line(line)
for i in words:
hash_map.set(i, count(i) + 1)
ranking = []
position = 0
while hash_map.lyst[position] is not None:
ranking.append(hash_map.lyst[position])
position += 1
ranking.sort(key=lambda x: x[1], reverse=True)
top_15 = []
for i in range(15):
top_15.append(ranking[i])
print("The most common words are:")
for i in top_15:
if len(i[0]) >= 3:
print(i[0], '\t', '\t', '\t', '\t', i[1])
else:
print(i[0], '\t', '\t', '\t', '\t', '\t', i[1])
def test_rehashing():
keys = [(r, r) for r in (range(10))]
values = list(range(1, 11))
hm = HashMap()
for k, v in zip(keys, values):
hm.set(k, v)
assert hm.size() == 10
assert hm.capacity() == 13
def test_init(self):
hash_map = HashMap()
assert hash_map.capacity == 17
assert len(hash_map.array) == 17
assert len(hash_map) == 0
for item in hash_map.array:
assert item is None
def test_key_present(self):
hm = HashMap()
self.assertEqual(hm.get("asdf"), None)
self.assertEqual(hm.get("asdf", 0), 0)
hm.set("qwerty", 12345)
self.assertEqual(hm.get("qwerty"), 12345)
self.assertEqual(hm.size(), 1)
self.assertEqual(hm.capacity(), 8)
def test_hash_map_updates_with_other_hashmap(self):
self.hashmap["FirstKey"] = "FirstValue"
other_hashmap = HashMap()
other_hashmap["FirstKey"] = "OtherFirstValue"
other_hashmap["SeondKey"] = "SecondValue"
self.hashmap.update(other_hashmap)
self.assertEqual("OtherFirstValue", self.hashmap["FirstKey"])
def main():
'''Driver function for hashmap.py.'''
hm = HashMap()
with open('AliceInWonderland.txt', 'r') as file:
for line in file:
for word in clean_line(line):
hm.set(word, 1)
print('The most common words are:')
get_most_used_words(hm)
def test_clear():
hm = HashMap()
keys = [(r, r) for r in (range(10))]
values = list(range(1, 11))
for k, v in zip(keys, values):
hm.set(k, v)
hm.clear()
assert hm.capacity() == 7
assert hm.size() == 0
def test_memory_error(self):
d = HashMap(capacity=4)
d[b'a'] = b"a"
d[b'b'] = b"tester"
d[b'c'] = b"something new"
d[b'd'] = b"DEE"
with self.assertRaises(MemoryError):
d[b'oh no'] = b'too many!'
def __init__(self, hash_function, initial_size=10, max_load_factor=0.7):
"""
This function is used to initialize the hashtable based on the hashfunction provided with a certain load factor
which is used to increase the size of the hash table
:param hash_function: a particular hash value calculating function
:param initial_size: initial size of the table
:param max_load_factor: loac factor for a table
"""
self.hash_table = HashMap(initsz=initial_size, hash_func=hash_function, maxload=max_load_factor)
def test_keys():
hm = HashMap()
keys = [(r, r) for r in (range(10))]
values = list(range(1, 11))
for k, v in zip(keys, values):
hm.set(k, v)
keys2 = hm.keys()
keys2.sort()
assert keys == keys2
def test_can_set_and_get_many_values(self):
hashmap = HashMap()
for number in range(0, 20):
key, val = str(number), number
hashmap.set(key, val)
self.assertEqual(hashmap._number_of_elements, 20)
for number in range(0, 20):
key, expected_val = str(number), number
self.assertEqual(hashmap.get(key), expected_val)
def build_data(dat):
for restaurant in dat:
resto = resto_styles.retrieve(restaurant[0])
resto.insert_beginning(HashMap(4))
node = resto.get_head_node().get_value()
node.assign('Name', restaurant[1])
node.assign('Price', restaurant[2])
node.assign('Rating', restaurant[3])
node.assign('Address', restaurant[4])
return resto_styles
def test_clear(self):
d = HashMap(upper_to_i.items(),
key_type=ctypes.c_char_p,
value_type=ctypes.c_int)
d.clear()
self.assertEqual(len(d), 0)
d.update(upper_to_i)
self.assertEqual(len(d), len(upper_to_i))
def test_setting(self):
d = HashMap(capacity=4)
d[b'a'] = b'A'
d[b'b'] = b'B'
self.assertEqual(d[b'a'], b'A', "Failed to insert A")
self.assertEqual(d[b'b'], b'B', "Failed to insert B")
d[b'a'] = b'H'
self.assertEqual(d[b'a'], b'H', "Failed to change a")
self.assertEqual(d[b'b'], b'B', "Changing a changed b")
def test_contains(self):
d = HashMap(capacity=4)
d[b'a'] = b'hi'
d[b'b'] = b'Bee'
self.assertTrue(b'a' in d)
self.assertTrue(b'b' in d)
self.assertTrue(b'nope' not in d)
d = HashMap(key_type=ctypes.c_char_p, value_type=ctypes.c_int)
for i, letter in enumerate(uppercase):
d[letter] = i
for i, letter in enumerate(uppercase):
self.assertTrue(letter in d, "Didn't contain letter: %s" % letter)
for i, letter in enumerate(lowercase):
self.assertTrue(letter not in d,
"Somehow contains letter: %s" % letter)
def test_can_set_and_get_multiple_values(self):
hashmap = HashMap()
self.assertEqual(hashmap._number_of_elements, 0)
hashmap.set('key', 'val')
self.assertEqual(hashmap._number_of_elements, 1)
self.assertEqual(hashmap.get('key'), 'val')
hashmap.set('otherkey', 'otherval')
self.assertEqual(hashmap._number_of_elements, 2)
self.assertEqual(hashmap.get('otherkey'), 'otherval')
self.assertEqual(hashmap.get('key'), 'val')
self.assertIsNone(hashmap.get('blah'))
def setUpClass(cls):
# class variable run before the test suite.
# We'll be making changes to this with each
# test.
cls.hashmap = HashMap()
cls.key_list = [
''.join(random.choice(string.lowercase) for i in xrange(100))
for j in xrange(26)
] # 26 random keys
cls.value_list = random.sample(range(1000), 26) # 26 random values
def test_remove():
hm = HashMap()
keys = [(r, r) for r in (range(10))]
values = list(range(1, 11))
for k, v in zip(keys, values):
hm.set(k, v)
hm.remove((3, 3))
print(hm)
with pytest.raises(KeyError):
hm.get((3, 3))
assert hm.get((5, 5)) == 6
def performance_test():
import time
import dbm
from itertools import permutations
def test_dict(d):
for p in [''.join(p) for p in permutations('1234567')]:
d[p.encode()] = p.encode()
def test_lookup(d):
for p in [''.join(p) for p in permutations('1234567')]:
if p.encode() in d:
pass
d = {}
t = time.time()
test_dict(d)
print("dict insert: %s" % (time.time() - t))
t = time.time()
test_lookup(d)
print("dict lookup: %s" % (time.time() - t))
d = HashMap(key_type=ctypes.c_char_p,
value_type=ctypes.c_char_p,
capacity=1000000)
t = time.time()
test_dict(d)
print("Shared-Memory HashMap insert: %s" % (time.time() - t))
t = time.time()
test_lookup(d)
print("Shared-Memory HashMap lookup: %s" % (time.time() - t))
d = mp.Manager().dict()
t = time.time()
test_dict(d)
print("Manager().dict insert: %s" % (time.time() - t))
t = time.time()
test_lookup(d)
print("Manager().dict lookup: %s" % (time.time() - t))
db = dbm.open('cache', 'c')
t = time.time()
test_dict(db)
print("dbm insert time: %s" % (time.time() - t))
t = time.time()
test_lookup(db)
print("dbm lookup time: %s" % (time.time() - t))
db.close()
def test_add_collision(self):
key1 = "hysh"
key2 = "vwtuyy"
hash_map = HashMap()
hash_map[key1] = True
hash_map[key2] = False
assert len(hash_map) == 2
assert hash_map[key1] == True
assert hash_map[key2] == False
