HDU - 6629 string matching

string matching

Time Limit: 2000/1000 MS (Java/Others)
Memory Limit: 262144/262144 K (Java/Others)

Problem Description

String matching is a common type of problem in computer science. One string matching problem is as following:

Given a string $s[0\dots len-1]$, please calculate the length of the longest common prefix of $s[i\dots len-1]$ and $s[0\dots len-1]$ for each $i>0$.

I believe everyone can do it by brute force.
The pseudo code of the brute force approach is as the following:

We are wondering, for any given string, what is the number of compare operations invoked if we use the above algorithm. Please tell us the answer before we attempt to run this algorithm.

Input

The first line contains an integer $T$, denoting the number of test cases.
Each test case contains one string in a line consisting of printable ASCII characters except space.

• $1\le T\le 30$

• string length $\le 10^6$ for every string

Output

For each test, print an integer in one line indicating the number of compare operations invoked if we run the algorithm in the statement against the input string.

Sample Input

3
_Happy_New_Year_
ywwyww
zjczzzjczjczzzjc

Sample Output

17
7
32

Tips

题意

若使用 $\text{BF}$ 算法求给定字符串 $s[0..len-1]$ 的每一个后缀与其自身的最长前缀，问比较次数的总和。

题解

拓展 $\text{KMP}$ 的裸题，最终的答案为 ${\sum }_{i=1}^{len-1}\left[\text{extend}[i]+(i+\text{extend}[i]<len)\right]$ 。

#include <bits/stdc++.h>
using std::max;
typedef long long ll;
const int MAXN=1e6+10;
void pre_EKMP(char x[],int m,int next[]){
    next[0]=m;
    int j=0;
    for (;j+1<m&&x[j]==x[j+1];++j);
    next[1]=j;
    int k=1;
    for (int i=2;i<m;++i){
        int p=next[k]+k-1;
        int L=next[i-k];
        if (i+L<p+1) next[i]=L;
        else{
            for (j=max(0,p-i+1);i+j<m&&x[i+j]==x[j];++j);
            next[i]=j;
            k=i;
        }
    }
}
void EKMP(char x[],int m,char y[],int n,int next[],int extend[]){
    pre_EKMP(x,m,next);
    int j=0;
    for (;j<n&&j<m&&x[j]==y[j];++j);
    extend[0]=j;
    int k=0;
    for (int i=1;i<n;++i){
        int p=extend[k]+k-1;
        int L=next[i-k];
        if (i+L<p+1) extend[i]=L;
        else{
            for (j=max(0,p-i+1);i+j<n&&j<m&&y[i+j]==x[j];++j);
            extend[i]=j;
            k=i;
        }
    }
}
int T;
char str[MAXN];
int next[MAXN],extend[MAXN];
int main(){
    scanf("%d",&T);
    while (T--){
        scanf("%s",str);
        int len=strlen(str);
        EKMP(str,len,str,len,next,extend);
        ll res=0;
        for (int i=1;i<len;++i){
            res+=extend[i];
            if (i+extend[i]<len) ++res;
        }
        printf("%lld\n",res);
    }
    return 0;
}