zoukankan      html  css  js  c++  java
  • Keywords Search (ac 自己主动机)

    Keywords Search 

    Problem Description
    In the modern time, Search engine came into the life of everybody like Google, Baidu, etc.
    Wiskey also wants to bring this feature to his image retrieval system.
    Every image have a long description, when users type some keywords to find the image, the system will match the keywords with description of image and show the image which the most keywords be matched.
    To simplify the problem, giving you a description of image, and some keywords, you should tell me how many keywords will be match.
    Input
    First line will contain one integer means how many cases will follow by.
    Each case will contain two integers N means the number of keywords and N keywords follow. (N <= 10000)
    Each keyword will only contains characters 'a'-'z', and the length will be not longer than 50.
    The last line is the description, and the length will be not longer than 1000000. 
    Output
    Print how many keywords are contained in the description. 
    Sample Input
    1 5 she he say shr her yasherhs 
    Sample Output
    3
     #include <iostream>
     # include<cstring>
     # include<cstdio>
    # include<queue>
      using namespace std;
    
    
    struct node
      {
          node *fail;       //失败指针
          node *next[26]; //Tire每一个节点的26个子节点(最多26个字母)
         int count;        //是否为该单词的最后一个节点
         node(){           //构造函数初始化
             fail=NULL;
             count=0;
             memset(next,NULL,sizeof(next));
         }
     }*q[1<<6|5];
     char keyword[50+5];     //输入的单词
     char str[1<<6|5];    //模式串
    
    
     void insert(char *str, node *root)         //建立字典树
     {
           node *p=root;
        for(int i=0;str[i]!='';i++)
        {
           int  id=str[i]-'a';
            if(p->next[id]==NULL)
                  p->next[id]=new node();
            p=p->next[id];
         }
         p->count++;
     }
    
    void build_ac_automation(node *root)
    {
        queue<node *> Q;
         int i;
         root->fail=NULL;
         Q.push(root);
         while(!Q.empty())
            {
              node *temp=Q.front();
               Q.pop();
               node *p=NULL;
               for(i=0;i<26;i++)
              {
                 if(temp->next[i]!=NULL)       //temp 为父结点
                 {
                     if(temp==root) temp->next[i]->fail=root;
                     else
                     {
                         p=temp->fail;   //  思路的关键点,
                         while(p!=NULL)
                        {
                             if(p->next[i]!=NULL)
                             {
                                 temp->next[i]->fail=p->next[i];
                                 break;
                             }
                             p=p->fail;    //p=p->fail也就是p=NULL
                         }
                         if(p==NULL)    temp->next[i]->fail=root;
                     }
                     Q.push(temp->next[i]);
                 }
             }
         }
     }
     int query(node *root)
     {
         int i=0,cnt=0,len=strlen(str);
         node *p=root;
        for(int i=0;i<len;i++)
        {
             int id=str[i]-'a';
             while(p->next[id]==NULL && p!=root)   p=p->fail;
             p=p->next[id];
             p=(p==NULL)?root:p;  
             node *temp=p;
             while(temp!=root && temp->count!=-1)
            {
                 cnt+=temp->count;
                 temp->count=-1;    //表示该单词已经出现过了。防止反复计数
                 temp=temp->fail;     //temp指向e节点的失败指针所指向的节点继续查找
             }
         }
         return cnt;
     }
     int main()
     {
         int n,t;
         scanf("%d",&t);
         while(t--)
        {
             node *root=new node();
             scanf("%d",&n);
             getchar();
             while(n--)
              {
                 gets(keyword);
                 insert(keyword,root);
             }
             build_ac_automation(root);
             scanf("%s",str);
             printf("%d
    ",query(root));
         }
         return 0;
    }
    



  • 相关阅读:
    linux sort根据日期时间排序方法记录
    gitlab数据迁移与升级记录
    ubuntu加压7z分卷
    docker环境运行elasticsearch以及汉化运行kibana
    nginx 403错误 检查nginx.conf user有没有问题,最好是当前用户
    系统属性file.encoding在JVM启动后,再次设置无法对系统的默认编码造成影响 & sun.jnu.encoding
    IDEA快速选择提示代码的设置
    log4j2可以打印到控制台,但无法打印到文件
    IDEA快捷键
    Eclipse自定义快捷键
  • 原文地址:https://www.cnblogs.com/lcchuguo/p/5120620.html
Copyright © 2011-2022 走看看