POJ 2217 Secretary (后缀数组)

原题链接

Problem Description

The basic condition of success of a political party, it is the good Election Programme. PSOS know about it, so they entrust the top secretary Juliet with this task. Because she wanted to make her work easier, she used her charm to talk round her friend Romeo to help her. Romeo is assistent of another political party and he was writing the programme some time ago. While writing the Programme for Juliet, he used some parts of his previous programme. When he gave the finished Programme to Juliet, they recognized that both programmes are too similar and that someone could notice it. They need to determine the longest part of text which is common to both programmes.

Input

At the first line there is a positive integer N stating the number of assignments to follow. Each assignment consists of exactly two lines of text, each of them contains at most 10000 characters. The end-of-line character is not considered to be a part of the text.

Output

Print a single line of text for each assignment. The line should contain the sentence “Nejdelsi spolecny retezec ma delku X.” (The longest common part of text has X characters). Replace X with the length of the longest common substring of both texts.

Sample Input

2
Tady nejsou zadni mimozemstani.
Lide tady take nejsou.
Ja do lesa nepojedu.
V sobotu pojedeme na vylet.

Sample Output

Nejdelsi spolecny retezec ma delku 7.
Nejdelsi spolecny retezec ma delku 5.

题目大意

给出两个字符串，要求出两个字符串的最长公共子串。

解题思路

将两个字符串相连，中间用一个特殊字符隔开。直接使用后缀数组，构建height数组，在比较的时候需要保证两个子串来自两个不同的字符串。

AC代码

#include<iostream>
#include<cstdio>
#include<cstdlib>
#include<cstring>
#include<cctype>
#include<algorithm>
#include<cmath>
#include<vector>
#include<string>
#include<queue>
#include<list>
#include<stack>
#include<set>
#include<map>
#define ll long long
#define ull unsigned long long
#define rep(i,n) for(int i = 0;i < n; i++)
#define fil(a,b) memset((a),(b),sizeof(a))
#define cl(a) fil(a,0)
#define pb push_back
#define mp make_pair
#define PI 3.1415927
#define inf 0x3f3f3f3f
#define fi first
#define se second
#define eps 1e-7
#define mod 1000000007ll
using namespace std;
const int size  = 200005,INF = 1<<30;
int rk[size],sa[size],height[size],w[size],wa[size],res[size];
void getSa (int len,int up) {
    int *k = rk,*id = height,*r = res, *cnt = wa;
    rep(i,up) cnt[i] = 0;
    rep(i,len) cnt[k[i] = w[i]]++;
    rep(i,up) cnt[i+1] += cnt[i];
    for(int i = len - 1; i >= 0; i--) {
        sa[--cnt[k[i]]] = i;
    }
    int d = 1,p = 0;
    while(p < len){
        for(int i = len - d; i < len; i++) id[p++] = i;
        rep(i,len)  if(sa[i] >= d) id[p++] = sa[i] - d;
        rep(i,len) r[i] = k[id[i]];
        rep(i,up) cnt[i] = 0;
        rep(i,len) cnt[r[i]]++;
        rep(i,up) cnt[i+1] += cnt[i];
        for(int i = len - 1; i >= 0; i--) {
            sa[--cnt[r[i]]] = id[i];
        } 
        swap(k,r);
        p = 0;
        k[sa[0]] = p++;
        rep(i,len-1) {
            if(sa[i]+d < len && sa[i+1]+d <len &&r[sa[i]] == r[sa[i+1]]&& r[sa[i]+d] == r[sa[i+1]+d])
                k[sa[i+1]] = p - 1;
            else k[sa[i+1]] = p++;
        }
        if(p >= len) return ;
        d *= 2,up = p, p = 0;
    }
}
void getHeight(int len) {
    rep(i,len) rk[sa[i]] = i;
    height[0] =  0;
    for(int i = 0,p = 0; i < len - 1; i++) {
        int j = sa[rk[i]-1];
        while(i+p < len&& j+p < len&& w[i+p] == w[j+p]) {
            p++;
        }
        height[rk[i]] = p;
        p = max(0,p - 1);
    }
}
int getSuffix(char s[]) {
    int len = strlen(s),up = 0; 
    for(int i = 0; i < len; i++) {
        w[i] = s[i];
        up = max(up,w[i]);
    }
    w[len++] = 0;
    getSa(len,up+1);
    getHeight(len);
    return len;
}
char a[30005];
char b[30005];
char tmp[2];
int main(void)
{
    tmp[0]='$';
    tmp[1]='\0';
    int k;
    cin>>k;
    getchar();
    while(k--)
    {
        cin.getline(a,inf);
        cin.getline(b,inf);
        int la=strlen(a);
        int lb=strlen(b);
        strcat(a,tmp);
        strcat(a,b);
        int useless=getSuffix(a);
        int maxa=0;
        for(int i=2;i<=strlen(a);++i)
        {
            if(height[i]>maxa)
            {
                int len1=strlen(a)-sa[i];
                int len2=strlen(a)-sa[i-1];
                if((len1>lb&&len2<=lb)||(len2>lb&&len1<=lb)) //保证来自两个不同的字符串
                {
                    maxa=height[i];
                }
            }
        }
        printf("Nejdelsi spolecny retezec ma delku %d.\n",maxa);
    }
    return 0;
}