def test_iter():
key_sum = 0
val_sum = 0
h = PreshMap()
for i in range(56, 24, -3):
h[i] = i * 2
key_sum += i
val_sum += i * 2
for key, value in h.items():
key_sum -= key
val_sum -= value
assert key_sum == 0
assert val_sum == 0
def test_resize():
h = PreshMap(4)
h[4] = 12
for i in range(10, 100):
value = int(i * (random.random() + 1))
h[i] = value
assert h[4] == 12
def test():
logging.info("Starting")
a = {}
a = PreshMap()
#a = judy.JudyIntObjectMap()
#db = pickledb.load("pickledb.db", False)
dict_size = 100000000
keys = np.random.randint(0, 1000000000000, dict_size)
values = np.random.randint(0, 1000000000, dict_size).astype(np.float64)
logging.info("Creating")
a = IntFloatDict(keys, values)
logging.info("Done")
return
#a = dict(zip(np.random.randint(0, 100000000000, dict_size), np.random.randint(0, 100000000000, dict_size)))
for i in range(0, 10000):
if i % 1000000 == 0:
print(i)
number = randint(0, 10000000000000)
a[number] = randint(0, 3000000000)
#db.set(str(number), randint(0, 3000000000))
#db.dump()
logging.info("writing to file")
with open("testdict.pckl", "wb") as f:
pickle.dump(a, f, protocol=4)
logging.info("Wrote to file")
def test_one_and_empty():
# See Issue #21
table = PreshMap()
for i in range(100, 110):
table[i] = i
del table[i]
assert table[0] == None
def test_insert():
h = PreshMap()
assert h[1] is None
h[1] = 5
assert h[1] == 5
h[2] = 6
assert h[1] == 5
assert h[2] == 6
def test_zero_key():
h = PreshMap()
h[0] = 6
h[5] = 12
assert h[0] == 6
assert h[5] == 12
for i in range(500, 1000):
h[i] = i * random.random()
assert h[0] == 6
assert h[5] == 12
def main():
nlp = English(parser=False, tagger=False, entity=False)
gazetteer = [u'M.I.A.', 'Shiny Happy People', 'James E. Jones']
example_text = u'The artist M.I.A. did a cover of Shiny Happy People. People is not an entity.'
pattern_ids = PreshMap()
max_length = 0
for pattern_str in gazetteer:
pattern = nlp.tokenizer(pattern_str)
bilou_tags = get_bilou(len(pattern))
for word, tag in zip(pattern, bilou_tags):
lexeme = nlp.vocab[word.orth]
lexeme.set_flag(tag, True)
pattern_ids[hash_string(pattern.text)] = True
max_length = max(max_length, len(pattern))
matcher = make_matcher(nlp.vocab, max_length)
doc = nlp(example_text)
matches = get_matches(matcher, pattern_ids, doc)
merge_matches(doc, matches)
for token in doc:
print(token.text, token.ent_type_)
def test_zero_values():
table = PreshMap()
table[10] = 0
assert table[10] == 0
assert table[11] is None