String Matching -- Brute Force + Rabin-Karp + KMP

String Matching

暴力解法：

"""
Programmer  :   EOF
Date        :   2015.02.28
Code file   :   nsm.py

"""

def naive_string_matcher(T, P) :
if (T or P) is None :
return

n = len(T)
m = len(P)

for s in range(0, n-m+1) :
match = True
for i in range(0, m) :
if P[i] is not T[s+i] :
match = False
break

if match is True :
print "Pattern occurs with shift", s

#------------ for testing --------------------

string1 = "hello goodbye and hello"
string2 = "hello"
naive_string_matcher(string1, string2)

Rabin-Krap :

"""
Programmer  :   EOF
Code date   :   2015.02.28
Code file   :   rkm.py
e-mail      :   jasonleaster@gmail.com

"""
def rabin_karp_matcher(T, P, d, q) :
n = len(T)
m = len(P)

h = d**(m-1) % q
p = 0
t_0 = 0

t = [0 for i in range(0, n - m + 1)]

# preprosecessing
for i in range(0, m) :
p = ( d*p + ord(P[i]) ) % q
t[0] = (d*t[0] + ord(T[i])) % q

# matching
for s in range(0, n-m+1) :
match = True
if p is t[s] :
for i in range(0, m) :
if P[i] is not T[s+i] :
match = False
break

if match is True :
print "Pattern occurs with shift", s

if s < n-m :
t[s+1] = (d * ( t[s] - ord(T[s]) * h ) + ord(T[s+m]) ) % q

#------------ for testing --------------------

string1 = "hello goodbye and hello"
string2 = "hello"
rabin_karp_matcher(string1, string2, 10, 13)

KMP:

"""
Programmer  :   EOF
Code date   :   2015.02.28
Code file   :   kmp.py
e-mail      :   jasonleaster@gmail.com

Code description    :
Here is a implementation of KMP which is a useful
algorithm for string matching.

"""

def kmp_matcher(T, P) :
n = len(T)
m = len(P)

pi = compute_prefix_function(P)
q = -1 # number of characters matched
for i in range(0, n) : # scan the text from left to right
while q > 0 and P[q+1] != T[i] :
q = pi[q]       # next character doesn't match

if P[q+1] == T[i] :
q += 1          # next character matches
if (q+1) == m :         # Is all of P matched ?
print "Pattern occurs with shift ", i-m
q = pi[q]       # look for the next match

def compute_prefix_function(P) :
m = len(P)
pi = [-1 for i in range(0, m)]

k = -1 # Attention !
for q in range(1, m) :
while k > 0 and P[k+1] != P[q] :
k = pi[k]
if P[k+1] == P[q] :
k += 1

pi[q] = k

return pi

#-------------for testing----------------------
#string_1 = "hello goodbye and hello"
#string_2 = "hello"
string_1 = "abcabaabcabac"
string_2 = "abaa"
kmp_matcher(string_1, string_2)