zoukankan      html  css  js  c++  java
  • 字符串(后缀数组):POJ 3294 Life Forms

    Life Forms

    Description

    You may have wondered why most extraterrestrial life forms resemble humans, differing by superficial traits such as height, colour, wrinkles, ears, eyebrows and the like. A few bear no human resemblance; these typically have geometric or amorphous shapes like cubes, oil slicks or clouds of dust.

    The answer is given in the 146th episode of Star Trek - The Next Generation, titled The Chase. It turns out that in the vast majority of the quadrant's life forms ended up with a large fragment of common DNA.

    Given the DNA sequences of several life forms represented as strings of letters, you are to find the longest substring that is shared by more than half of them.

    Input

    Standard input contains several test cases. Each test case begins with 1 ≤ n ≤ 100, the number of life forms. n lines follow; each contains a string of lower case letters representing the DNA sequence of a life form. Each DNA sequence contains at least one and not more than 1000 letters. A line containing 0 follows the last test case.

    Output

    For each test case, output the longest string or strings shared by more than half of the life forms. If there are many, output all of them in alphabetical order. If there is no solution with at least one letter, output "?". Leave an empty line between test cases.

    Sample Input

    3
    abcdefg
    bcdefgh
    cdefghi
    3
    xxx
    yyy
    zzz
    0

    Sample Output

    bcdefg
    cdefgh
    
    ?
    

       注意一些细节就好。

      1 #include <iostream>
      2 #include <cstring>
      3 #include <cstdio>
      4 using namespace std;
      5 const int maxn=110110;
      6 char s[maxn];
      7 int r[maxn],Wa[maxn],Wb[maxn],Wv[maxn],Ws[maxn];
      8 int rank[maxn],lcp[maxn],belong[maxn],sa[maxn];
      9 bool cmp(int *p,int i,int j,int l){
     10     return p[i]==p[j]&&p[i+l]==p[j+l];
     11 }
     12 void DA(int n,int m){
     13     int i,j,p,*x=Wa,*y=Wb,*t;
     14     for(i=0;i<m;i++)Ws[i]=0;
     15     for(i=0;i<n;i++)++Ws[x[i]=r[i]];
     16     for(i=1;i<m;i++)Ws[i]+=Ws[i-1];
     17     for(i=n-1;i>=0;i--)sa[--Ws[x[i]]]=i;
     18     
     19     for(j=1,p=1;p<n;m=p,j<<=1){
     20         for(p=0,i=n-j;i<n;i++)y[p++]=i;
     21         for(i=0;i<n;i++)
     22             if(sa[i]>=j)    
     23                 y[p++]=sa[i]-j;
     24         for(i=0;i<m;i++)Ws[i]=0;
     25         for(i=0;i<n;i++)++Ws[Wv[i]=x[y[i]]];
     26         for(i=1;i<m;i++)Ws[i]+=Ws[i-1];
     27         for(i=n-1;i>=0;i--)
     28             sa[--Ws[Wv[i]]]=y[i];
     29         for(t=x,x=y,y=t,x[sa[0]]=0,i=1,p=1;i<n;i++)
     30             x[sa[i]]=cmp(y,sa[i],sa[i-1],j)?p-1:p++;    
     31     }    
     32 }
     33 
     34 void LCP(int n){
     35     int i,j,k=0;
     36     for(i=1;i<=n;i++)rank[sa[i]]=i;
     37     for(i=0;i<n;lcp[rank[i++]]=k)
     38         for(k?k--:k,j=sa[rank[i]-1];r[i+k]==r[j+k];k++);    
     39 }
     40 int tot,tim,vis[maxn];
     41 bool Judge(int n,int x,int g){
     42     int tmp=0;++tim;
     43     for(int i=2;i<=n;i++){
     44         if(lcp[i]<x)
     45             tmp=0,++tim;
     46         else{
     47             if(vis[belong[sa[i]]]!=tim)
     48                 tmp++,vis[belong[sa[i]]]=tim;
     49             if(vis[belong[sa[i-1]]]!=tim)
     50                 tmp++,vis[belong[sa[i-1]]]=tim;
     51             if(tmp>g)return true;
     52         }
     53     }
     54     return false;
     55 }
     56 
     57 void Solve(int n,int x,int g){
     58     int tmp=0,tag=0;++tim;
     59     for(int i=2;i<=n;i++){
     60         if(lcp[i]<x)
     61             tmp=0,++tim,tag=0;
     62         else{
     63             if(vis[belong[sa[i]]]!=tim)
     64                 tmp++,vis[belong[sa[i]]]=tim;
     65             if(vis[belong[sa[i-1]]]!=tim)
     66                 tmp++,vis[belong[sa[i-1]]]=tim;
     67             if(tmp>g&&!tag){
     68                 for(int j=0;j<x;j++)
     69                     printf("%c",r[sa[i-1]+j]);
     70                 printf("
    ");
     71                 tag=1;
     72             }
     73         }
     74     }
     75     return;
     76 }
     77 
     78 int main(){
     79     while(~scanf("%d",&tot)&&tot){
     80          
     81         int len=0,lo=1,hi=213333333;
     82         for(int i=1;i<=tot;i++){
     83             scanf("%s",s);
     84             for(int j=0;s[j];j++){
     85                 belong[len]=i;
     86                 r[len++]=s[j];
     87                 if(!s[j+1])hi=min(hi,j+1);
     88             }
     89             belong[len]=110+i;
     90             r[len++]='z'+i;    
     91         }
     92         r[len]=0; 
     93         DA(len+1,1024);
     94         LCP(len);
     95         
     96         while(lo<=hi){
     97             int mid=(lo+hi)>>1;
     98             if(Judge(len,mid,tot/2))lo=mid+1;
     99             else hi=mid-1;
    100         }
    101         if(hi>=1)
    102             Solve(len,hi,tot/2);
    103         else
    104             printf("?
    ");
    105         printf("
    ");
    106     }
    107     return 0;
    108 }
    尽最大的努力,做最好的自己!
  • 相关阅读:
    FSLIB.NETWORK 简易使用指南
    在CentOS上安装owncloud企业私有云过程
    用于ViEmu的重置为试用状态的Python脚本
    Microsoft.Office.Interop.Excel 报错
    FineUIMvc表格数据库分页,使用CYQ.Data组件
    如何在已有项目中引入FineUIMvc
    按键精灵-常用脚本命令汇集
    微信分享代码
    [教程] 【原创】媒体扫描耗电的彻底解决办法(申精)
    Less学习笔记
  • 原文地址:https://www.cnblogs.com/TenderRun/p/5370559.html
Copyright © 2011-2022 走看看