PAT T1005 Programming Pattern

建立后缀数组,遍历height数组找到连续大于len的最长子序列~

#include<bits/stdc++.h>
using namespace std;
const int maxn=1e7+14;
char s[maxn];
int n;
int rk[maxn];
int sa[maxn];
int height[maxn];
int tmp[maxn];
int c[maxn];
int t1[maxn];
int t2[maxn];
void build_sa (char s[],int n,int m) {
    int i,j,p;
    int *x=t1;
    int *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 (j=1;j<=n;j<<=1) {
        p=0;
        for (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<m;i++) c[i]=0;
        for (i=0;i<n;i++) c[x[y[i]]]++;
        for (i=1;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]+j]==y[sa[i]+j]?p-1:p++;
        if (p>=n) break;
        m=p; 
    }
} 
void getHeight (char s[],int n) {
    int i,j,k=0;
    for (i=0;i<=n;i++) rk[sa[i]]=i;
    for (i=0;i<n;i++) {
        if (k) k--;
        j=sa[rk[i]-1];
        while (s[i+k]==s[j+k]) k++;
        height[rk[i]]=k;
    }
}
int main () {
    int len;
    scanf ("%d",&len);
    getchar ();
    cin.getline (s,maxn);
    n=strlen(s);
    build_sa (s,n+1,128);
    getHeight (s,n);
    int cnt=0;
    int res=0;
    int ans=1;
    for (int i=0;i<=n;i++) {
        if (height[i]>=len) ans++;
        else ans=1;
        if (sa[i]+len<=n&&cnt<ans) {
            cnt=ans;
            res=sa[i];
        }
    }
    for (int i=0;i<len;i++)
    printf ("%c",s[res+i]);
    printf (" %d",cnt);
    return 0;
}

 

posted @ 2020-02-13 11:24  zlc0405  阅读(180)  评论(0编辑  收藏  举报