传统的暴力模式匹配算法是不断地查找、回溯,但回溯的过程浪费时间,但在弄清楚匹配的子串结构时并不需要回溯,而是不断地向前匹配,降低时间复杂度。但KMP算法提出的时候并不是最快速的,后来还有人将它优化。
KMP算法的关键在于构建匹配串当中元素之间联系的next数组。
传统的KMP算法:
#include <iostream>
#include <cstring>
using namespace std;
const int maxn = 100000+5;
char s[maxn], p[maxn];
int next[maxn];
void get_next(int pn){
int i = 0, k = -1;
next[0] = -1;
while(i < pn){
if(k == -1 || p[i] == p[k]){
i++; k++;
next[i] = k;
}
else k = next[k];
}
}
int kmp(int sn, int pn){
int i = 0, k = 0;
while(i <= sn){
if(k == -1 || s[i] == p[k]) { i++; k++; }
else k = next[k];
if(k == pn) break;
}
if(i <= sn) return i-k;
else return maxn;
}
int main(){
int sn, pn;
cin >> s >> p;
sn = strlen(s); pn = strlen(p);
get_next(pn);
for(int i = 0; i < pn; i++) cout << next[i] << " " ;
cout << kmp(sn, pn) << endl;
}
改良的KMP算法:
#include <iostream>
#include <cstring>
using namespace std;
const int maxn = 100000+5;
char s[maxn], p[maxn];
int next[maxn];
void get_next(int pn){
int i = 0, k = -1;
next[0] = -1;
while(i < pn){
if(k == -1 || p[i] == p[k]){
i++; k++;
if(p[i] == p[k]) next[i] = next[k];
else next[i] = k;
}
else k = next[k];
}
}
int kmp(int sn, int pn){
int i = 0, k = 0;
while(i <= sn){
if(k == -1 || s[i] == p[k]) { i++; k++; }
else k = next[k];
if(k == pn) break;
}
if(i <= sn) return i-k;
else return maxn;
}
int main(){
int sn, pn;
cin >> s >> p;
sn = strlen(s); pn = strlen(p);
get_next(pn);
for(int i = 0; i < pn; i++) cout << next[i] << " ";
cout << endl << kmp(sn, pn) << endl;
}