[置顶] ACM and String
字符串理论, 多串匹配与AC自动机
例题
http://acm.hust.edu.cn/vjudge/contest/view.action?cid=21239#overview
A HDU 2222
木板题，统计包含个数
#include <iostream>
#include <stdio.h>
#include <string.h>
#include <vector>
#include <queue>
using namespace std;
const int CHAR = 26;
const int TOTLEN = 5e5 + 9;
const int MAXLEN = 1e6 + 9;
struct Node{
Node *fail , *next[CHAR];
int val;
void init(){
fail = NULL;
val = 0;
memset(next , 0 , sizeof(next));
}
};
class ACM{
public:
void init();
void insert(char * str);
void build();
int find(char * str);
private:
Node * newnode();
Node acm[TOTLEN];
Node * root;
int size;
};
Node * ACM::newnode(){
acm[size].init();
return &acm[size++];
}
void ACM::init(){
size = 0;
root = newnode();
}
void ACM::insert(char * str){
Node * p = root;
for ( ; *str ; ++str){
int ch = *str - 'a';
if (p -> next[ch] == NULL)
p -> next[ch] = newnode();
p = p -> next[ch];
}
p -> val ++;
}
void ACM::build(){
static queue<Node *> q;
q.push(root);
while(!q.empty()){
Node * tmp = q.front() ; q.pop();
Node * p;
for (int i = 0 ; i < CHAR ; ++i){
Node *& now = tmp -> next[i];
if (now != NULL){
q.push(now);
if (tmp == root){
now -> fail = root;
continue;
}
p = tmp -> fail;
while(p != NULL){
if (p -> next[i] != NULL){
now -> fail = p -> next[i];
break;
}
p = p -> fail;
}
if (p == NULL) now -> fail = root;
}
else{
if (tmp == root) now = root;
else now = tmp -> fail -> next[i];
}
}
}
}
int ACM::find(char * str){
Node *p = root;
int ans = 0;
for ( ; *str ; ++str){
int ch = *str - 'a';
p = p -> next[ch];
if (p == NULL) p = root;
Node * tmp = p;
while(tmp != root && tmp ->val != -1){
ans += tmp -> val;
tmp -> val = -1;
tmp = tmp -> fail;
}
}
return ans;
}
ACM ac;
char str[MAXLEN];
void solve(){
int n;
scanf("%d" , &n);
ac.init();
while(n--){
scanf("%s" , str);
ac.insert(str);
}
ac.build();
scanf("%s" , str);
printf("%d\n" , ac.find(str));
}
int main(){
// freopen("0" ,"r" ,stdin);
int _ = 0;
scanf("%d" , &_);
while(_--) solve();
}
B POJ 2778
建立自动机，搞出转移矩阵，快速幂。。
% 比 - 慢多了啊！！
#include <functional>
#include <algorithm>
#include <iostream>
#include <fstream>
#include <sstream>
#include <iomanip>
#include <numeric>
#include <cstring>
#include <cassert>
#include <cstdio>
#include <string>
#include <vector>
#include <bitset>
#include <queue>
#include <stack>
#include <cmath>
#include <ctime>
#include <list>
#include <set>
#include <map>
using namespace std;
#define Rush for(int ____T , scanf("%d" , &____T); ____T--;)
#define DO(n) for ( int ____n ## __line__ = n; ____n ## __line__ -- ; )
#define ALL(A) A.begin(), A.end()
#define BSC(A, x) (lower_bound(ALL(A), x) - A.begin())
#define CTN(T, x) (T.find(x) != T.end())
#define SZ(A) int(A.size())
#define PB push_back
#define MP(A, B) make_pair(A, B)
#define fi first
#define se second
typedef long long LL;
typedef vector<int> VI;
typedef map<int, int> MII;
typedef pair<int, int> PII;
typedef pair<LL, LL> PLL;
template<class T> inline void RST(T &A){memset(A, 0, sizeof(A));}
template<class T> inline void FLC(T &A, int x){memset(A, x, sizeof(A));}
template<class T> inline void CLR(T &A){A.clear();}
//}
/** Constant List .. **/ //{
const int dx4[] = {-1, 0, 1, 0};
const int dy4[] = {0, 1, 0, -1};
const int dx8[] = {-1, 0, 1, 0 , -1 , -1 , 1 , 1};
const int dy8[] = {0, 1, 0, -1 , -1 , 1 , -1 , 1};
const int dxhorse[] = {-2 , -2 , -1 , -1 , 1 , 1 , 2 , 2};
const int dyhorse[] = {1 , -1 , 2 , -2 , 2 ,-2 , 1 ,-1};
const int MOD = 1000000007;
//int MOD = 99990001;
const int INF = 0x3f3f3f3f;
const LL INFF = 1LL << 60;
const double EPS = 1e-9;
const double OO = 1e15;
const double PI = acos(-1.0); //M_PI;
#pragma comment(linker, "/STACK:36777216")
//}
template<class T> inline void checkMin(T &a,const T b){if (b<a) a=b;}
template<class T> inline void checkMax(T &a,const T b){if (a<b) a=b;}
//}
template<class T> inline T low_bit(T x) {return x & -x;}
/*****************************************************************/
const int CHAR = 4;
const int TOT = 129;
int next[TOT][CHAR] , fail[TOT];
bool virus[TOT];
int id[128];
const int Dic[] = {'A' , 'C' , 'G' ,'T'};
int L , root;
int newNode(){
for (int i = 0 ; i < CHAR; ++i)
next[L][i] = -1;
virus[L] = 0;
fail[L] = 0;
return L++;
}
void init(){
L = 0;
root = newNode();
}
void insert(char *s){
int now = root;
for (int i = 0 ; s[i] ; ++i){
int ch = id[s[i]];
if (next[now][ch] == -1)
next[now][ch] = newNode();
now = next[now][ch];
}
virus[now] = 1;
}
void build(){
queue<int> Q;
for (int i = 0 ; i < CHAR ; ++i)
if (next[root][i] == -1)
next[root][i] = root;
else{
fail[next[root][i]] = root;
Q.push(next[root][i]);
}
while(!Q.empty()){
int now = Q.front();
virus[now] |= virus[fail[now]];
Q.pop();
for (int i = 0 ; i < CHAR ; ++i)
if (next[now][i] == -1)
next[now][i] = next[fail[now]][i];
else{
fail[next[now][i]] = next[fail[now]][i];
Q.push(next[now][i]);
}
}
}
const int MATN = 129;
const int modo = 1e5;
struct Mat{
int Matn , Matm;
int a[MATN][MATN];
Mat(){
Matn = 0;
Matm = 0;
memset(a , 0 , sizeof(a));
}
void output(){
cout << "OUTPUT" << endl;
for (int i = 0 ; i < Matn ; ++i){
for (int j = 0 ; j < Matm ; ++j){
printf("%d ",a[i][j]);
}
printf("\n");
}
}
void init(){
Matn = 0;Matm = 0;
memset(a , 0 , sizeof(a));
}
Mat operator + (const Mat & A) const{
Mat ret = A;
for (int i = 0 ; i < Matn ; ++i){
for (int j = 0 ; j < Matm ; ++j)
ret.a[i][j] = (ret.a[i][j] + a[i][j]) % modo;
}
return ret;
}
Mat operator * (const Mat & A) const{
Mat c ;
c.Matn = Matn;
c.Matm = A.Matm;
for (int i = 0 ; i < Matn ; ++i)
for (int j = 0 ; j < A.Matm ; ++j)
for (int k = 0 ; k < Matm ; ++k){
c.a[i][j] = (c.a[i][j] + ((long long)a[i][k] * A.a[k][j])%modo);
if (c.a[i][j] >= modo) c.a[i][j] -= modo;
}
return c;
}
void initI(){
memset(a, 0 , sizeof(a));
for (int i = 0 ; i < Matn ; ++i)
a[i][i] = 1;
}
Mat power(int k){
Mat c = *this , b;
b.init();
b.Matn = Matn ; b.Matm = Matm;
b.initI();
while(k){
if (k & 1)
b = b * c;
c = c * c;
k >>= 1;
}
return b;
}
}P , Q;
char A[15];
int n , m;
void solve(){
init();
DO(m){
scanf("%s" , A);
insert(A);
}
build();
P.init();
P.Matn = P.Matm = L;
for (int i = 0 ; i < L ; ++i){
if (virus[i]) continue;
for (int j = 0 ; j < 4 ; ++j){
int ni = next[i][j];
if (ni == -1) ni = root;
// assert(ni != -1);
if (virus[ni]) continue;
P.a[i][ni]++;
}
}
// P.output();
P = P.power(n);
// P.output();
Q.init();
Q.Matn = 1 , Q.Matm = L;
Q.a[0][0] = 1;
// for(int i = 0 ; i < L ; ++i) Q.a[0][i] = 1;
Q = Q * P;
// Q.output();
int ans = 0;
for (int i = 0 ; i < L ; ++i) if (!virus[i]){
ans = (ans + Q.a[0][i]);
if (ans >= modo) ans -= modo;
}
printf("%d\n" , ans);
}
int main(){
id['A'] = 0;
id['C'] = 1;
id['G'] = 2;
id['T'] = 3;
while(~scanf("%d%d" , &m , &n))solve();
}
Manecher
资料
http://blog.csdn.net/ggggiqnypgjg/article/details/6645824例题
http://acm.hdu.edu.cn/showproblem.php?pid=3068
http://poj.org/problem?id=3974
http://acmpj.zstu.edu.cn/JudgeOnline/showproblem?problem_id=3780
http://acmpj.zstu.edu.cn/JudgeOnline/showproblem?problem_id=3769木板
#include <iostream>
#include <stdio.h>
#include <string.h>
using namespace std;
const int N = 120000;
namespace Manacher_String{
char Ma[N << 1];
int rad[N << 1] , ml;
void Manacher(char *s , int len){
int l = 0;
Ma[ l ++ ] = '.';
Ma[ l ++ ] = ',';
for (int i = 0 ; i < len ; ++i){
Ma[ l ++ ] = s[i];
Ma[ l ++ ] = ',';
}
Ma[l] = 0;
int pnow = 0 , pid = 0;
for (int i = 1 ; i < l ; ++i){
if (pnow > i)
rad[i] = min(rad[(pid << 1) - i] , pnow - i);
else
rad[i] = 1;
for ( ; Ma[i - rad[i]] == Ma[i + rad[i]] ; rad[i] ++);
if (i + rad[i] > pnow){
pnow = i + rad[i];
pid = i;
}
}
ml = l;
}
}using namespace Manacher_String;
char s[N];
int main(){
while(~scanf("%s" , s)){
int n = strlen(s);
Manacher(s , n);
int ans = 0;
for (int i = 1 ; i < ml ; ++i){
ans = max(ans , rad[i] - 1);
}
printf("%d\n" , ans);
}
}
http://acm.hdu.edu.cn/showproblem.php?pid=3948
hash 一下即可
http://acm.hust.edu.cn:8080/judge/contest/view.action?cid=12581#problem/A
http://acm.zju.edu.cn/onlinejudge/showProblem.do?problemCode=3661