Codeforces 427D Match & Catch 后缀自动机 或 后缀数组

题目大意：

就是对于两个字符串S1和S2, 求出他们最短的一个公共字串P, 满足P在S1中只出现1次, P在S2中也只出现一次, 输出P最小的长度, 如果这样的P不存在, 输出-1

大致思路：

很明显的一个做法是将S1和S2连接起来中间用未出现的字符隔开, 然后建立后缀自动机, 记录每一个状态中表示的字符串的来源(可以状压记录), 然后所有状态中, 满足Right集合为2, 且状压表示出现在了2个字符串中即可, 在这样一个状态中取最短可行长度, 遍历所有状态点即可, 复杂度O(|S1| + |S2|)

当然还可以用后缀数组来做, 考虑到P要满足的条件如果这样的P存在, 必定是sa数组中相邻的存在, 所以扫描一遍height数组, 当sa[i - 1]与sa[i]不属于同一字符串时, 考虑P不能再其他位置出现那么只能height[i - 1] < height[i], height[i + 1] < height[i]是存在这样的P, 最小长度为 max(height[i - 1], height[i + 1]) + 1, 扫描一遍height数组找出满足条件的最小的那一个P即可

后缀自动机代码如下：

Result  :  Accepted     Memory  :  2648 KB     Time  :  31 ms

/*
 * Author: Gatevin
 * Created Time:  2015/4/16 19:29:08
 * 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 maxm 10010
#define maxn 20010

struct Suffix_Automation
{
    struct State
    {
        State *par;
        State *go[27];
        int right, val, mi, appear;
        void init(int _val = 0)
        {
            par = 0, val = _val, right = mi = appear = 0;
            memset(go, 0, sizeof(go));
        }
    };
    State *root, *last, *cur;
    State nodePool[maxn];
    State* newState(int val = 0)
    {
        cur->init(val);
        return cur++;
    }
    void initSAM()
    {
        cur = nodePool;
        root = newState();
        last = root;
    }
    void extend(int w, int belong)
    {
        State *p = last;
        State *np = newState(p->val + 1);
        np->right = 1;
        np->appear = (1 << belong);
        while(p && p->go[w] == 0)
        {
            p->go[w] = np;
            p = p->par;
        }
        if(p == 0)
        {
            np->par = root;
        }
        else
        {
            State *q = p->go[w];
            if(q->val == p->val + 1)
                np->par = q;
            else
            {
                State *nq = newState(p->val + 1);
                memcpy(nq->go, q->go, sizeof(q->go));
                nq->par = q->par;
                q->par = nq;
                np->par = nq;
                while(p && p->go[w] == q)
                {
                    p->go[w] = nq;
                    p = p->par;
                }
            }
        }
        last = np;
    }
    int d[maxm];
    State *b[maxn];
    void topo()
    {
        int cnt = cur - nodePool;
        int maxVal = 0;
        memset(d, 0, sizeof(d));
        for(int i = 1; i < cnt; i++)
            maxVal = max(maxVal, nodePool[i].val), d[nodePool[i].val]++;
        for(int i = 1; i <= maxVal; i++) d[i] += d[i - 1];
        for(int i = 1; i < cnt; i++) b[d[nodePool[i].val]--] = &nodePool[i];
        b[0] = root;
    }
    void SAMInfo()
    {
        State *p;
        int cnt = cur - nodePool;
        for(int i = cnt - 1; i > 0; i--)
        {
            p = b[i];
            p->par->right += p->right;
            p->par->appear |= p->appear;
            p->mi = p->par->val + 1;
        }
    }
};

Suffix_Automation sam;
char s[maxm];

int main()
{
    scanf("%s", s);
    int len = strlen(s);
    sam.initSAM();
    for(int i = 0; i < len; i++)
        sam.extend(s[i] - 'a', 0);
    sam.extend(26, 2);
    scanf("%s", s);
    len = strlen(s);
    for(int i = 0; i < len; i++)
        sam.extend(s[i] - 'a', 1);
    sam.topo();
    sam.SAMInfo();
    int ans = 1e9;
    int cnt = sam.cur - sam.nodePool;
    for(int i = cnt - 1; i > 0; i--)
        if(sam.b[i]->appear == (1 << 2) - 1 && sam.b[i]->right == 2)//这个串只出现两次且属于不同串
            ans = min(ans, sam.b[i]->mi);//取长度最小的即可
    if(ans == 1e9) ans = -1;
    printf("%d\n", ans);
    return 0;
}

后缀数组做法如下：

Result  :  Accepted     Memory  :  400  KB     Time  :  31 ms

/*
 * Author: Gatevin
 * Created Time:  2015/4/16 20:11:25
 * 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 10010

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], belong[maxn];
int N;

int main()
{
    scanf("%s", in);
    int len = strlen(in);
    N = 0;
    for(int i = 0; i < len; i++)
        s[N] = in[i] - 'a' + 1, belong[N++] = 1;
    belong[N] = 0;
    s[N++] = 27;//刚开始逗比地写的26就WA了...
    scanf("%s", in);
    len = strlen(in);
    for(int i = 0; i < len; i++)
        s[N] = in[i] - 'a' + 1, belong[N++] = 2;
    s[N] = 0;
    da(s, sa, N + 1, 30);
    calheight(s, sa, N);
    int ans = 1e9;
    for(int i = 1; i <= N; i++) if(height[i] > 0)//s[sa[0]] = 0, s[sa[N]] = 26不考虑
        if(belong[sa[i - 1]] != belong[sa[i]])//说明这两个不属于同一个串, 接下来保证P在各个串中只出现一次
        {
            if(i == N && height[i - 1] < height[i])
                ans = min(ans, height[i - 1] + 1);
            if(i == 1 && height[i + 1] < height[i])
                ans = min(ans, height[i + 1] + 1);
            if(i > 1 && i < N && height[i - 1] < height[i] && height[i + 1] < height[i])
                ans = min(ans, max(height[i - 1], height[i + 1]) + 1);
        }
    if(ans == 1e9) ans = -1;
    printf("%d\n", ans);
    return 0;
}