AC自动机
一种多模匹配算法(如:有N个字符串Si以及一个字符串T,计算每个字符串Si在T中出现的次数)
原理:KMP+Trie
模板
const int C = 26;
const int N = 1e5;
stack <int> st;
struct Node {
int son[C], next, end;
bool vis;
};
struct AC {
Node node[N];
int tol;
int newNode() // 新建节点
{
memset(node[tol].son, 0, sizeof(node[tol].son));
node[tol].next = 0;
node[tol].end = 0;
return tol++;
}
void init() { tol = 0; newNode(); }// 初始化
void insert(char s[]) // 插入字符串
{
int cur = 0;
for(int i = 0; s[i]; i++)
{
int &son = node[cur].son[s[i]-'a'];
if(!son) son = newNode();
cur = son;
}
node[cur].end++;
}
void bfs() //获取计算Next
{
queue<int> q;
for(int i = 0; i < C; i++) if(node[0].son[i]) q.push(node[0].son[i]);
while(!q.empty())
{
int fa = q.front();
q.pop();
int nex = node[fa].next;
for(int i = 0; i < C; i++)
{
int& son = node[fa].son[i];
if(!son) {
son = node[nex].son[i];
} else {
node[son].next = node[nex].son[i];
q.push(son);
st.push(son);}
}
}
}
int search(char *s) //字符串匹配
{
int l = strlen(s), cur = 0;
for(int i = 0; i < l; i++)
{
cur = node[cur].son[s[i] - 'a'];
node[cur].vis = true;
}
int ans = 0;
while(!st.empty())
{
int cur = st.top();
if(node[cur].vis)
node[node[cur].next].vis = true;
st.pop();
}
for(int i = 0; i < tol; i++)
if(node[i].vis) ans += node[i].end;
return ans;
}
} ;
例题(hdu2222)
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
AC:
#include <iostream>
#include <cstring>
#include <queue>
#include <stack>
using namespace std;
const int C = 26;
const int N = 1e5;
stack <int> st;
struct Node {
int son[C], next, end;
bool vis;
};
struct AC {
Node node[N];
int tol;
int newNode() // 新建节点
{
memset(node[tol].son, 0, sizeof(node[tol].son));
node[tol].next = 0;
node[tol].end = 0;
return tol++;
}
void init() { tol = 0; newNode(); }// 初始化
void insert(char s[]) // 插入字符串
{
int cur = 0;
for(int i = 0; s[i]; i++)
{
int &son = node[cur].son[s[i]-'a'];
if(!son) son = newNode();
cur = son;
}
node[cur].end++;
}
void bfs() //获取计算Next
{
queue<int> q;
for(int i = 0; i < C; i++) if(node[0].son[i]) q.push(node[0].son[i]);
while(!q.empty())
{
int fa = q.front();
q.pop();
int nex = node[fa].next;
for(int i = 0; i < C; i++)
{
int& son = node[fa].son[i];
if(!son) {
son = node[nex].son[i];
} else {
node[son].next = node[nex].son[i];
q.push(son);
st.push(son);}
}
}
}
int search(char s[]) //字符串匹配
{
int l = strlen(s), cur = 0;
for(int i = 0; i < l; i++)
{
cur = node[cur].son[s[i] - 'a'];
node[cur].vis = true;
}
int ans = 0;
while(!st.empty())
{
int cur = st.top();
if(node[cur].vis)
node[node[cur].next].vis = true;
st.pop();
}
for(int i = 0; i < tol; i++)
if(node[i].vis) ans += node[i].end;
return ans;
}
}ac;
int main()
{
int T,t;
char str[10];
cin>>T;
while(T--)
{
ac.init();
cin>>t;
while(t--)
{
cin>>str;
ac.insert(str);
}
ac.bfs();
cin>>str;
cout<<ac.search(str)<<endl;
}
return 0;
}