019f8fd211
git-subtree-dir: users/wpcarro git-subtree-mainline:464bbcb15cgit-subtree-split:24f5a642afChange-Id: I6105b3762b79126b3488359c95978cadb3efa789
27 lines
1.1 KiB
Python
27 lines
1.1 KiB
Python
def substring_exists(corpus, pattern):
|
|
"""
|
|
Return True if `pattern` appears in `corpus`.
|
|
|
|
This function runs in O(m) time where n is equal to the length of
|
|
`corpus`. To improve the efficiency of this algorithm, use a hashing
|
|
function the reduces the number of collisions, which will consequently
|
|
reduce the number of string-to-string, linear comparisons.
|
|
"""
|
|
m, n = len(corpus), len(pattern)
|
|
a = sum(ord(c) for c in corpus[0:n])
|
|
b = sum(ord(c) for c in pattern)
|
|
|
|
# (clumsily) prevent an off-by-one error...
|
|
if a == b and corpus[0:n] == pattern:
|
|
return True
|
|
|
|
for i in range(1, m - n):
|
|
# Update the hash of corpus by subtracting the hash of the character
|
|
# that is sliding out of view and adding the hash of the character that
|
|
# is sliding into view.
|
|
a = a - ord(corpus[i - 1]) + ord(corpus[i + n - 1])
|
|
# Integer comparison in O(0) time followed by string comparison in O(m)
|
|
# time.
|
|
if a == b and corpus[i:i + n] == pattern:
|
|
return True
|
|
return False
|