zoukankan      html  css  js  c++  java
  • HDU2222 Keywords Search ac自动机第一题

     指针我一般都会出错,所以还是自己写数组版本。

    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. 

    InputFirst 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. 
    OutputPrint how many keywords are contained in the description.Sample Input

    1
    5
    she
    he
    say
    shr
    her
    yasherhs

    Sample Output

    3

     第一版:

    #include <cstdio>
    #include <cstdlib>
    #include <iostream>
    #include <queue>
    #include <cstring>
    using namespace std;
    const int maxn=1000010;
    int Next[maxn][26],End[maxn],fail[maxn];
    int cnt,root=1,ans;//root不能为0 
    void _init()
    {
         memset(Next,0,sizeof(Next));
         memset(End,0,sizeof(End));
         memset(fail,0,sizeof(fail));
         ans=0;cnt=1;
    }
    void _insert(char s[])
    {
        int L=strlen(s);
        int now=root;
        for(int i=0;i<L;i++){
            if(!Next[now][s[i]-'a']) Next[now][s[i]-'a']=++cnt;
            now=Next[now][s[i]-'a'];
        }
        End[now]++;
    }
    void _build()//bfs 
    {
        queue<int>q;
        q.push(root);
        while(!q.empty()){
            int Now=q.front();q.pop();
            for(int i=0;i<26;i++){
                if(Next[Now][i]){
                    if(Now==root) fail[Next[Now][i]]=root;
                    else{
                        int p=fail[Now];
                        while(p){//给儿子们找对象 
                            if(Next[p][i]){
                                fail[Next[Now][i]]=Next[p][i];
                                break;//找到了就停止 
                            }
                            p=fail[p];
                        }
                        if(!p) fail[Next[Now][i]]=root;//不晓得? 
                    }
                    q.push(Next[Now][i]);
                }
            }    
        }
    }
    void _query(char s[])
    {
        int L=strlen(s);
        int Now=root;
        for(int i=0;i<L;i++){
              int x=s[i]-'a';
              while(Now!=root&&!Next[Now][x]) Now=fail[Now];
              Now=Next[Now][x];
              if(!Now) Now=root;//不晓得? 
              int tmp=Now;
              while(tmp!=root){
                    if(End[tmp]>=0){
                       ans+=End[tmp];
                       End[tmp]=-1;//避免重复 
                    }
                    else break;
                    tmp=fail[tmp];
              }
        }
    }
    int main()
    {
        char s[55];
        char c[maxn] ;
        int n,j,i,T;
        scanf("%d",&T);
        while(T--){
            
            _init();
            scanf("%d",&n);
            for(i=1;i<=n;i++){
               scanf("%s",s);
               _insert(s);//单词 
            }
            scanf("%s",c);
            
            _build();
            _query(c);//文章 
        
            printf("%d
    ",ans);
       
        } 
        return 0;
    }
    View Code

    稍微改进版:

    #include <cstdio>
    #include <cstdlib>
    #include <iostream>
    #include <queue>
    #include <cstring>
    using namespace std;
    const int maxn=1000010;
    int Next[maxn][26],End[maxn],fail[maxn];
    int cnt,root=0,ans;
    int q[10000000],tail,head;
    void _init()
    {
        //不要memset只要200ms 
         ans=0;cnt=0;fail[root]=-1;//root的fail不能等于本身,不然不能重新开始。 
         head=tail=0;End[root]=0;
         for(int i=0;i<26;i++) Next[root][i]=0;
    }
    void _insert(char s[])
    {
        int now=root;
        for(int i=0;s[i];i++){
            if(!Next[now][s[i]-'a']) { 
               Next[now][s[i]-'a']=++cnt;
               fail[cnt]=0;
               End[cnt]=0;
               for(int i=0;i<26;i++) Next[cnt][i]=0;
            }
            now=Next[now][s[i]-'a'];
        }
        End[now]++;
    }
    void _build()//bfs 
    {
        q[++head]=root;
        while(tail<head){
            int Now=q[++tail];
            for(int i=0;i<26;i++){
                if(Next[Now][i]){
                    if(Now==root) fail[Next[Now][i]]=root;
                    else{
                        int p=fail[Now];
                        while(p!=-1){//给儿子们找对象 
                            if(Next[p][i]){
                                fail[Next[Now][i]]=Next[p][i];
                                break;//找到了就停止 
                            }
                            p=fail[p];//配对 
                        }
                        if(p==-1) {
                           fail[Next[Now][i]]=root;//重新开始 
                        }
                    }
                    q[++head]=Next[Now][i];
                }
            }    
        }
    }
    void _query(char s[])
    {
        int L=strlen(s);
        int Now=root;
        for(int i=0;i<L;i++){
              int x=s[i]-'a';
              while(Now!=root&&!Next[Now][x]) Now=fail[Now];
              Now=Next[Now][x];
              if(Now==-1)  Now=root;//即使失败,也不气馁,一切从零开始 
              int tmp=Now;
              while(tmp!=root){
                    if(End[tmp]>0){
                       ans+=End[tmp];
                       End[tmp]=-1;//避免重复 
                    }
                    else break;
                    tmp=fail[tmp];
              }
        }
    }
    int main()
    {
        char s[55];
        char c[maxn] ;
        int n,j,i,T;
        scanf("%d",&T);
        while(T--){
            
            _init();
            scanf("%d",&n);
            for(i=1;i<=n;i++){
               scanf("%s",s);
               _insert(s);//单词 
            }
            scanf("%s",c);
            
            _build();
            _query(c);//文章 
        
            printf("%d
    ",ans);
       
        } 
        return 0;
    }
    View Code
  • 相关阅读:
    VirtualPathUtility.IsAppRelative的bug?
    textoverflow: ellipsis 在IE8、9下显示问题
    Windows Server 2012 不支持SharePoint Server 2010(KB2724471)
    本地测试网址推荐
    神奇的img
    json三层解析(数组解析)
    json两层解析
    把json数据转化成对象
    Centos7 修改yum源为阿里源
    使用Webdriver刷博客文章评论
  • 原文地址:https://www.cnblogs.com/hua-dong/p/7726311.html
Copyright © 2011-2022 走看看