后缀数组

Posted 2022-04-29 hanasaki

后缀数组用来解决无法事先知道查询时的多模板匹配问题
代码部分主要是要搞懂各种数组的意义
sa是后缀排名到位置的映射
x是第一关键字位置到排名的映射
y是第二关键字排名到位置的映射
明天再补图

char s[MAXN];
int sa[MAXN], t[MAXN], t2[MAXN], c[MAXN], n;
void build_sa(int m) 
    int i, *x = t, *y = t2;
    for(int i = 0; i < m; i++) c[i] = 0;
    for(int i = 0; i < n; i++) c[x[i] = s[i]]++;
    for(int i = 1; i < m; i++) c[i] += c[i-1];
    for(int i = n-1; i >= 0; i--) sa[--c[x[i]]] = i;
    for(int k = 1; k <= n; k <<= 1) 
        int p = 0;
        for(int i = n-k; i < n; i++) y[p++] = i;
        for(int i = 0; i < n; i++) if(sa[i] >= k) y[p++] = sa[i]-k;
        for(int i = 0; i < m; i++) c[i] = 0;
        for(int i = 0; i < n; i++) c[x[y[i]]]++;
        for(int i = 1; i < m; i++) c[i] += c[i-1];
        for(int i = n-1; i >= 0; i--) sa[--c[x[y[i]]]] = y[i];
        swap(x, y);
        p = 1; x[sa[0]] = 0;
        for(int 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;
     


 int m;
 int cmp_suffix(char* pattern, int p) 
     return strncmp(pattern, s+sa[p], m);
  
 
 int find(char* P) 
     m = strlen(P);
     if(cmp_suffix(P, 0) < 0) return -1;
     if(cmp_suffix(P, n-1) > 0) return -1;
     int L = 0, R = n-1;
     while(L <= R) 
         int M = (L + R) >> 1;
         int res = cmp_suffix(P, M);
         if(!res) return M;
         if(res < 0) R = M-1;
         else L = M+1;
      
     return -1;