def _get_bucket(self, key):
"""
Hashes a key string and returns the corresponding bucket.
:param key: a key string
:return: a bucket (list)
"""
return self.buckets[shash(key) % self.bucket_count]
def test_shash(self):
# How many buckets we will use.
bucket_count = 100
# The test fails if the population standard deviation of the buckets is bigger than the product of the tolerance
# and the mean of the buckets.
tolerance = 0.05
buckets = [0 for n in range(bucket_count)]
# Load a lot of words.
with open('../words.txt', 'r') as words:
for line in words.readlines():
buckets[shash(line) % bucket_count] += 1
self.failIf(pstdev(buckets) > tolerance * mean(buckets))
def find(text, substr):
"""
Attempts to find a substring in a string of text.
:param text: the string of text
:param substr: the substring
:return: the index of the first character of the first appearance of the substring in the string or -1
"""
text_size = len(text)
substr_size = len(substr)
if text_size < substr_size:
return -1
last_hash = shash(text[0:substr_size])
substr_hash = shash(substr)
if substr_hash == last_hash:
if text[0:substr_size] == substr:
return 0
for i in range(1, text_size - substr_size + 1):
last_hash = shash_roll(last_hash, substr_size, text[i - 1], text[substr_size + i - 1])
if substr_hash == last_hash:
if text[i:substr_size + i] == substr:
return i
return -1
