Last active
July 23, 2017 14:17
-
-
Save giuscri/321a51a140fab4435f36db7a29cc7061 to your computer and use it in GitHub Desktop.
A collection of string matching algorithms taken from chapter 32 of CSLR.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from functools import reduce | |
from string import ascii_lowercase | |
def naive_string_matching(T, P): | |
"""Computes all the occurrences of P in T. | |
Cost of this procedure is O(n-m+1 * m) | |
where n, m are the length of T and of P | |
respectively. | |
Args: | |
T: text into which find occurrences. | |
P: substring to search in T. | |
Returns: | |
A list containing the indexes at which | |
the occurrences of P in T start. The actual | |
substrings can be derived via mapping | |
each element x of the returned list to T[x:x+len(P)]. | |
""" | |
shifts = [] | |
s, n, m = 0, len(T), len(P) | |
assert m <= n, 'substring is longer than string' | |
while s < n-m+1: | |
if T[s] != P[0]: s += 1; continue | |
j = 1 | |
while j < m: | |
if T[s+j] != P[j]: break | |
j += 1 | |
if j == m: shifts.append(s) | |
s += 1 | |
return shifts | |
def rabin_karp_matching(T, P, q=997): | |
"""Computes all the occurrences of P in T. | |
Cost of this procedure is O(n-m+1 * m) | |
where n, m are the length of T and of P | |
respectively. | |
The idea behind Rabin-Karp is to leverage | |
comparisons between computer WORD's that | |
are supposed to happen in constant time. | |
Thus a numeric fingerprint is computed | |
for the pattern P and for each substring | |
of T of length m. In case fingerprints | |
match, the original pattern and the substring | |
of T that generated one of the fingerprints | |
are compared byte by byte. | |
Assuming comparison of two strings happen in O(m), | |
the worst case running time is computed assuming | |
that for each substring of T of length m (i.e. | |
n-m+1 substrings) a match of fingerprints will | |
happen, forcing a O(m) comparison n-m+1 times. | |
""" | |
T, P = T.encode('ASCII'), P.encode('ASCII') | |
n, m = len(T), len(P) | |
valid_shifts = [] | |
p = reduce(lambda ac, x, q=q: (ac*128 + x) % q, P) | |
t_list = [reduce(lambda ac, x, q=q: (ac*128 + x) % q, T[:m])] | |
for s in range(n-m): | |
t = (t_list[-1]*128 + T[m+s] - pow(128, m, q) * T[s]) % q | |
t_list.append(t) | |
for s, t in enumerate(t_list): | |
if t == p and T[s:s+m] == P: | |
valid_shifts.append(s) | |
return valid_shifts | |
def is_suffix(a, b): | |
"""Computes whethere a is suffix of b""" | |
n = len(b) | |
return a == b[n-len(a):] | |
def build_delta(P, sigma=ascii_lowercase): | |
"""Build the transition function 𝛿 for the DFA of P. | |
𝛿(q, a) tells you the maximum number of characters | |
that can act as a suffix for P[:q]+a. | |
""" | |
delta, m = {}, len(P) | |
for q in range(m+1): | |
for a in sigma: | |
k = min(m, q+1) | |
while not is_suffix(P[:k], P[:q]+a): | |
k = k - 1 | |
delta[(q, a)] = k | |
return lambda q, a, delta=delta: delta[(q, a)] | |
def dfa_matching(T, P): | |
"""Computes all the occurrences of P in T.""" | |
delta = build_delta(P) | |
valid_shifts, q, m = [], 0, len(P) | |
for i, c in enumerate(T): | |
q = delta(q, c) | |
if q == m: valid_shifts.append(i-m+1) | |
return valid_shifts | |
def build_pi(P): | |
"""Build the prefix function π, as described in CSLR. | |
π(q) tells you the maximum number of characters | |
that can act as a *proper* suffix for P[:q]. | |
""" | |
pi, m = [None], len(P) | |
for q in range(1, m+1): | |
k = q-1 | |
while not is_suffix(P[:k], P[:q]): | |
k -= 1 | |
pi.append(k) | |
return lambda q, pi=pi: pi[q] | |
def kmp_matching(T, P): | |
"""Computes all the occurrences of P in T.""" | |
pi, n, m, q = build_pi(P), len(T), len(P), 0 | |
valid_shifts = [] | |
for i in range(n): | |
while q > 0 and P[q] != T[i]: | |
q = pi(q) | |
if P[q] == T[i]: | |
q += 1 | |
if q == m: | |
valid_shifts.append(i+1-m) | |
q = pi(m) | |
return valid_shifts |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment