LA4513 后缀数组/字符串hash

对于height的维护还是不太理解。

后缀数组裸题：

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

#define maxn 80000

int s[maxn];
int sa[maxn];
int n, m;

int t[maxn], t2[maxn], c[maxn];
int Rank[maxn],height[maxn];

void build_sa(int n,int m)
{
    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;
    }
}

void getheight()
{
    int k = 0;
    for (int i=0;i<=n;i++) Rank[sa[i]]=i;
    for (int 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;
    }
}

bool valid(int ans,bool flag)
{
    int cnt=0 ,pre=0, suf=0 ;
    for (int i=1; i<=n; i++) {
        if (height[i]>=ans) {
            if (!cnt) {
                cnt=1;
                pre=max(pre,sa[i-1]);
            }
            cnt++;
            pre=max(sa[i],pre);
        }
        else {
            if (cnt>=m)
                if (!flag) return true;
                else suf=max(pre,suf);
            cnt = pre = 0;
        }
    }
    if (cnt>=m)
        if (!flag) return true;
        else suf=max(pre,suf);

    if(!flag) return false;
    else printf("%d %d\n",ans,suf);
    return 0;
}

int main()
{
    freopen("1.in","r",stdin);
    char str[maxn];
    while (scanf("%d",&m)!=EOF && m) {
        scanf("%s",str);
        if (m==1) {
            printf("%d 0\n",strlen(str));
            continue;
        }
        for (n=0;str[n];n++)
            s[n]=str[n]-'a'+1;
        s[n]=0;
        build_sa(n+1,27);
        getheight();

        if (!valid(1,false)) {
            printf("none\n");
            continue;
        }

        int p=0, q=n+1, mid, ans=1;
        while (p<=q) {
            mid = (p+q)>>1;
            if (valid(mid,false)) {
                ans = mid;
                p = mid+1;
            }
            else q = mid-1;
        }
        valid(ans,true);
    }
    return 0;
}

字符串hash：

hash[i]=s[i]+s[i+1]*x+...+s[n-1]*x^n-1-i;

hash[i]=hash[i+1]*x+s[i];

hash[i,L]=hash[i]-hash[i+L]*x^L;

#include <iostream>
#include <fstream>
#include <algorithm>
#include <cstring>
using namespace std;

#define maxn 40005
#define 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);
    //frome latge to small
}

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()
{
    freopen("1.in","r",stdin);

    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;
}