重复出现超过m次的最长的子串的最大下标 后缀数组或Hash+LCP UVA 12206 - Stammering Aliens

题目链接

题意：给定一个序列，求出出现次数大于m，长度最长的子串的最大下标

思路：hash大法或后缀数组，然后二分答案，每次利用hash值去找出最大下标即可。

代码：

#include <cstdio>  
#include <cstring>  
#include <algorithm>  
using namespace std;  
  
const int MAXLEN = 40005;  
  
struct Suffix {  
  
    int s[MAXLEN];  
    int sa[MAXLEN], t[MAXLEN], t2[MAXLEN], c[MAXLEN], n;  
    int rank[MAXLEN], height[MAXLEN];  
  
    void build_sa(int m) {  
    n++;  
    int i, *x = t, *y = t2;  
    for (i = 0; i < m; i++) c[i] = 0;  
    for (i = 0; i < n; i++) c[x[i] = s[i]]++;  
    for (i = 1; i < m; i++) c[i] += c[i - 1];  
    for (i = n - 1; i >= 0; i--) sa[--c[x[i]]] = i;  
    for (int k = 1; k <= n; k <<= 1) {  
        int p = 0;  
        for (i = n - k; i < n; i++) y[p++] = i;  
        for (i = 0; i < n; i++) if (sa[i] >= k) y[p++] = sa[i] - k;  
        for (i = 0; i < m; i++) c[i] = 0;  
        for (i = 0; i < n; i++) c[x[y[i]]]++;  
        for (i = 0; i < m; i++) c[i] += c[i - 1];  
        for (i = n - 1; i >= 0; i--) sa[--c[x[y[i]]]] = y[i];  
        swap(x, y);  
        p = 1; x[sa[0]] = 0;  
        for (i = 1; i < n; i++)  
        x[sa[i]] = (y[sa[i - 1]] == y[sa[i]] && y[sa[i - 1] + k] == y[sa[i] + k]) ? p - 1 : p++;  
        if (p >= n) break;  
        m = p;  
    }  
    n--;  
    }  
  
    void getHeight() {  
    int i, j, k = 0;  
    for (i = 1; i <= n; i++) rank[sa[i]] = i;  
    for (i = 0; i < n; i++) {  
        if (k) k--;  
        int j = sa[rank[i] - 1];  
        while (s[i + k] == s[j + k]) k++;  
        height[rank[i]] = k;  
    }  
    }  
} gao;  
  
const int N = 40005;  
  
int m;  
char str[N];  
  
int judge(int x) {  
    int ans = -1;  
    for (int i = 1; i <= gao.n; i++) {  
    if (gao.n - gao.sa[i] < x) continue;  
    int Max = gao.sa[i], cnt = 1;  
    while (gao.height[i + 1] >= x && i < gao.n) {  
        Max = max(Max, gao.sa[i + 1]);  
        cnt++;  
        i++;  
    }  
    if (cnt >= m)  
        ans = max(ans, Max);  
    }  
    return ans;  
}  
  
void solve() {  
    if (judge(1) == -1) {  
    printf("none\n");  
    return;  
    }  
    int l = 1, r = gao.n - m + 2;  
    while (l < r) {  
    int mid = (l + r) / 2;  
    if (judge(mid) != -1) l = mid + 1;  
    else r = mid;  
    }  
    l--;  
    printf("%d %d\n", l, judge(l));  
}  
  
int main() {  
    while (~scanf("%d", &m) && m) {  
    scanf("%s", str);  
    int len = strlen(str);  
    for (int i = 0; i < len; i++)  
        gao.s[i] = str[i] - 'a' + 1;  
    gao.s[len] = 0;  
    gao.n = len;  
    gao.build_sa(27);  
    gao.getHeight();  
    solve();  
    }  
    return 0;  
}  

#include<cstdio>
#include<cstring>
#include<algorithm>
using namespace std;

const int maxn = 40000 + 10;
const int x = 123;
int n, m, pos;
unsigned long long H[maxn], xp[maxn];

unsigned long long hash[maxn];
int rank[maxn];

int cmp(const int& a, const int& b) {
  return hash[a] < hash[b] || (hash[a] == hash[b] && a < b);
}

int possible(int L) {
  int c = 0;
  pos = -1;
  for(int i = 0; i < n-L+1; i++) {
    rank[i] = i;
    hash[i] = H[i] - H[i+L]*xp[L];
  }
  sort(rank, rank+n-L+1, cmp);
  for(int i = 0; i < n-L+1; i++) {
    if(i == 0 || hash[rank[i]] != hash[rank[i-1]]) c = 0;
    if(++c >= m) pos = max(pos, rank[i]);
  }
  return pos >= 0;
}

int main() {
  char s[maxn];
  while(scanf("%d", &m) == 1 && m) {
    scanf("%s", s);
    n = strlen(s);

    H[n] = 0;
    for(int i = n-1; i >= 0; i--) H[i] = H[i+1]*x + (s[i] - 'a');
    xp[0] = 1;
    for(int i = 1; i <= n; i++) xp[i] = xp[i-1]*x;

    if(!possible(1)) printf("none\n");
    else {
      int L = 1, R = n+1;
      while(R - L > 1) {
        int M = L + (R-L)/2;
        if(possible(M)) L = M; else R = M;
      }
      possible(L);
      printf("%d %d\n", L, pos);
    }
  }
  return 0;
}