HDU 3336 Count the string 后缀数组 或 (KMP + DP)

题目大意：

就是现在给出一个长度不超过20W的字符串S, 对于这个字符串求其所有前缀在串中出现次数的和, 结果对10007取模

大致思路：

很容易想到后缀数组, 找到sa[i] = 0的那个就是串S, 那么找出这个位置向两边能扩展到的长度即可, 就是利用一下height数组就行了, 没什么难度= =

还是不清楚的话看代码细节吧

另外也可以用KMP + DP来做

首先next[i]表示在第i个字符处适配了应该匹配第几个字符, 那么用dp[i]表示以第i个字符作为结尾的匹配的前缀的个数, 就可以有

dp[i] = dp[next[i]] + 1, 所有的dp的和就是最终的结果了

代码如下：

后缀数组的做法:

Result  :  Accepted     Memory  :  9608 KB     Time  :  452 ms

/*
 * Author: Gatevin
 * Created Time:  2015/5/4 16:03:18
 * File Name: Rin_Tohsaka.cpp
 */
#include<iostream>
#include<sstream>
#include<fstream>
#include<vector>
#include<list>
#include<deque>
#include<queue>
#include<stack>
#include<map>
#include<set>
#include<bitset>
#include<algorithm>
#include<cstdio>
#include<cstdlib>
#include<cstring>
#include<cctype>
#include<cmath>
#include<ctime>
#include<iomanip>
using namespace std;
const double eps(1e-8);
typedef long long lint;
#define foreach(e, x) for(__typeof(x.begin()) e = x.begin(); e != x.end(); ++e)
#define SHOW_MEMORY(x) cout<<sizeof(x)/(1024*1024.)<<"MB"<<endl

#define maxn 200010

#define rank rankrankrank

int wa[maxn], wb[maxn], wv[maxn], Ws[maxn];

int cmp(int *r, int a, int b, int l)
{
    return r[a] == r[b] && r[a + l] == r[b + l];
}
void da(int *r, int *sa, int n, int m)
{
    int *x = wa, *y = wb, *t, i, j, p;
    for(i = 0; i < m; i++) Ws[i] = 0;
    for(i = 0; i < n; i++) Ws[x[i] = r[i]]++;
    for(i = 1; i < m; i++) Ws[i] += Ws[i - 1];
    for(i = n - 1; i >= 0; i--) sa[--Ws[x[i]]] = i;
    for(j = 1, p = 1; p < n; j <<= 1, m = p)
    {
        for(p = 0, i = n - j; i < n; i++) y[p++] = i;
        for(i = 0; i < n; i++) if(sa[i] >= j) y[p++] = sa[i] - j;
        for(i = 0; i < n; i++) wv[i] = x[y[i]];
        for(i = 0; i < m; i++) Ws[i] = 0;
        for(i = 0; i < n; i++) Ws[wv[i]]++;
        for(i = 1; i < m; i++) Ws[i] += Ws[i - 1];
        for(i = n - 1; i >= 0; i--) sa[--Ws[wv[i]]] = y[i];
        for(t = x, x = y, y = t, p = 1, x[sa[0]] = 0, i = 1; i < n; i++)
            x[sa[i]] = cmp(y, sa[i - 1], sa[i], j) ? p - 1 : p++;
    }
    return;
}

int rank[maxn], height[maxn];
void calheight(int *r, int *sa, int n)
{
    int i, j, k = 0;
    for(i = 1; i <= n; i++) rank[sa[i]] = i;
    for(i = 0; i < n; height[rank[i++]] = k)
        for(k ? k-- : 0, j = sa[rank[i] - 1]; r[i + k] == r[j + k]; k++);
    return;
}

char in[maxn];
int s[maxn], sa[maxn];
const int mod = 10007;
int L[maxn], R[maxn];
int main()
{
    int T;
    scanf("%d", &T);
    while(T--)
    {
        int len;
        scanf("%d", &len);
        scanf("%s", in);
        for(int i = 0; i < len; i++)
            s[i] = in[i] - 'a' + 1;
        s[len] = 0;
        da(s, sa, len + 1, 28);
        calheight(s, sa, len);
        int pos = -1;
        for(int i = 0; i <= len; i++)
            if(sa[i] == 0)
            {
                pos = i;//找到pos的位置
                break;
            }
        int now = len;
        //[L[i], R[i]]是和sa[pos]公共前缀 >= i的连续一段
        for(int i = pos + 1; i <= len; i++)
        {
            if(height[i] < now)
            {
                for(int j = height[i] + 1; j <= now; j++)
                    R[j] = i - 1;
                now = height[i];
            }
        }
        now = len;
        for(int i = pos; i >= 0; i--)
        {
            if(height[i] < now)
            {
                for(int j = height[i] + 1; j <= now; j++)
                    L[j] = i;
                now = height[i];
            }
        }
        int ans = 0;
        for(int i = 1; i <= len; i++)
            ans = (ans + R[i] - L[i] + 1) % mod;
        printf("%d\n", ans);
    }
    return 0;
}

KMP + DP的做法：

Result  :  Accepted     Memory  :  3332 KB     Time  :  46 ms

/*
 * Author: Gatevin
 * Created Time:  2015/5/4 18:31:56
 * File Name: Rin_Tohsaka.cpp
 */
#include<iostream>
#include<sstream>
#include<fstream>
#include<vector>
#include<list>
#include<deque>
#include<queue>
#include<stack>
#include<map>
#include<set>
#include<bitset>
#include<algorithm>
#include<cstdio>
#include<cstdlib>
#include<cstring>
#include<cctype>
#include<cmath>
#include<ctime>
#include<iomanip>
using namespace std;
const double eps(1e-8);
typedef long long lint;
#define foreach(e, x) for(__typeof(x.begin()) e = x.begin(); e != x.end(); ++e)
#define SHOW_MEMORY(x) cout<<sizeof(x)/(1024*1024.)<<"MB"<<endl

#define maxn 200010
#define next nextnext
int next[maxn];

void KMP(char *s, int n)
{
    memset(next, 0, sizeof(next));
    for(int i = 1; i < n; i++)
    {
        int j = i;
        while(j > 0)
        {
            j = next[j];
            if(s[i] == s[j])
            {
                next[i + 1] = j + 1;
                break;
            }
        }
    }
    //next[i]表示在第i个字符处失配时应该转到第几个字符
}

char s[maxn];
int n;
int dp[maxn];//用dp[i]表示以第i个字符结尾的匹配前缀有多少个
const int mod = 10007;
int main()
{
    int T;
    scanf("%d", &T);
    while(T--)
    {
        scanf("%d", &n);
        scanf("%s", s);
        KMP(s, n);
        dp[0] = 0;
        int ans = 0;
        for(int i = 1; i <= n; i++)
        {
            dp[i] = dp[next[i]] + 1;
            if(dp[i] >= mod) dp[i] -= mod;
            ans += dp[i];
            if(ans >= mod) ans -= mod;
        }
        printf("%d\n", ans);
    }
    return 0;
}