字符串匹配算法KMP

KMP算法的原理,这里我不写,建议参考:

http://www.ruanyifeng.com/blog/2013/05/Knuth%E2%80%93Morris%E2%80%93Pratt_algorithm.html

http://blog.csdn.net/v_JULY_v/article/details/6545192

http://blog.csdn.net/joylnwang/article/details/6778316

这篇博客写的非常好,以本人的能力只能写出更烂的解释 .....所以就不再多此一举了,下面仅仅给出两段代码,分别用C++和Python写的(都已经编译通过),

希望能对大家有所帮助:


C++代码:

#include <iostream>
#include <cstring>
using namespace std;


bool piFun(char *pattern, int *pi)									//pattern表示模式字符串,pi表示失配函数
{
	if (pattern == NULL || pi == NULL) return false ;
	int len = strlen(pattern) ;
	pi[ 0 ] = -1 ;
	int k = -1 ;
	for (int i = 1; i < len ; ++ i)
	{
		while ( k >= 0 && pattern[k + 1] != pattern[i])
			k = pi[k] ;															//寻找一个满足条件的前缀,使得该前缀是pattern[0 ~ i -1]的一个后缀
		if ( pattern[k + 1] == pattern[i])
			++ k;																//能够匹配的前缀和后缀的长度增加1
		pi[i] = k ;																//失配后开始查找的位置
	}
	return true ;
}

int matchStr(char *text, char*pattern)
{
	if (text == NULL || pattern == NULL) return -1 ;
	int lenT = strlen(text) ;
	int lenP = strlen(pattern) ;
	int *pi = new int[lenP] ;
	if (!piFun(pattern, pi)) return - 1;
	int k = -1 ;

	for (int i = 0; i < lenT; ++ i)
	{
		while(k >= 0 && pattern[k + 1] != text[i])
			k = pi[k] ;														//下一个字符不能匹配
		if (pattern[k + 1] == text[i])
			++ k ;															//匹配上下一个字符
		if (k == lenP - 1)												//已经找到可以匹配的pattern
		{
			delete[] pi ;
			return (i - lenP + 1) ;										//得到开始出现的第一个位置
		}
	}
	delete[] pi ;
	return - 1 ;
}


int main(int argc, char **argv)
{
	char p[] = "ababbacdefgacd" ;
	cout << matchStr(p, "aba") << endl;
	cout << matchStr(p, "ba") << endl;
	cout << matchStr(p, "efg") << endl;
	cout << matchStr(p, "addf") << endl;
	return 0 ;
}


Python代码:

#!/usr/bin/python
#Filename KMP.py

def piFun(pattern, pi):
	if len(pattern) == 0:
		return False
	del pi[:]
	pi.extend(-1 for i in range(0, len(pattern)))
	pi[0] = -1
	k = -1
	for i in range(1, len(pattern)) :
		while k >= 0 and pattern[k + 1] != pattern[i] :
			k = pi[k]
		if pattern[k + 1] == pattern[i] :
			k = k + 1
		pi[i] = k
	return True

def matchStr(text, pattern) :
	if len(text) == 0 or len(pattern) == 0 :
		return -1 
	pi = []
	if not piFun(pattern, pi) :
		return -1
	k = -1
	for i in range(0, len(text)) :
		while k >= 0 and pattern[k + 1] != text[i] :
			k = pi[k]
		if pattern[k + 1] == text[i] :
			k = k + 1
		if k == len(pattern) - 1 :
			return (i - len(pattern) + 1)
	return -1	



print(matchStr('abcefabdefcnfghiorpnpp', 'ce'))
print(matchStr('abcefabdefcnfghiorpnpp', 'ab'))
print(matchStr('abcefabdefcnfghiorpnpp', 'ef'))
print(matchStr('abcefabdefcnfghiorpnpp', 'npp'))
print(matchStr('abcefabdefcnfghiorpnpp', 'ok'))



posted @ 2013-07-03 15:22  dancingrain  阅读(186)  评论(0编辑  收藏  举报