字符串

字符串hash进阶

1，给出N个只有小写字母的字符串，求其中不同的字符串的个数

#include<iostream>
#include<string>
#include<vector>
#include<algorithm>
using namespace std;
const int MOD = 1000000007;
const int P = 10000017;
vector<int> ans;
long long hashFunc(string str){
	long long H = 0;//使用long long避免溢出 
	for(int i = 1;i <str.length();i++){
		H = (H * P + str[i] - 'a') % MOD;
	}
	return H;
} 
int main(){
	string str;
	while(getline(cin,str),str!="#"){//输入str直到#时停止 
		long long id = hashFunc(str); //将字符串str转换为整数 
		ans.push_back(id);
	}
	sort(ans.begin(),ans.end());  //排序 
	int count = 0;
	for(int i =0;i < ans.size();i++){
		if(i == 0 || ans[i] != ans[i - 1]){
			count++;//统计不同的数的个数 
		}
	}
	cout<<count<<endl;
	return 0;
}

2，输入两个长度均不超过1000的字符串，求它们的最长公共子串的长度

#include<iostream>
#include<cstdio>
#include<string>
#include<vector>
#include<map>
#include<algorithm>
using namespace std;
typedef long long LL;
const LL MOD = 1000000007;
const LL P = 10000019;
const LL MAXN = 1010;
LL powP[MAXN],H1[MAXN] = {0},H2[MAXN] = {0};
vector<pair<int ,int> >pr1,pr2;
void init(int len){
	powP[0] = 1;
	for(int i = 1; i <= len;i++){
		powP[i] = (powP[i-1]*P)%MOD;
	}
}
//计算字符串的hash值 
void calH(LL H[],string &str){
	H[0] = str[0];
	for(int i = 0 ;i < str.length();i++){
		H[i] = (H[i-1] * P + str[i]) % MOD;
	}
}
//calSingleSubH计算H[i...j]
int calSingleSubH(LL H[],int i,int j){
	if(i == 0) return H[j];
	return ((H[j] - H[i-1] * powP[j - i + 1]) % MOD + MOD) % MOD;
} 
//calSubH计算所有的子串的hash值，并将子串hash值，子串长度存入pr
void calSubH(LL H[],int len ,vector<pair<int ,int> >&pr){
	for(int i = 0;i < len;i++){
		for(int j = i;j < len;j++){
			int hashValue = calSingleSubH(H,i,j);
			pr.push_back(make_pair(hashValue,j - i + 1));
		}
	}
} 
//计算pr1和pr2中相同的hash值，维护最大长度
int getMax(){
	int ans = 0;
	for(int i = 0;i < pr1.size();i++){
		for(int j = 0;j < pr2.size();j++){
			if(pr1[i].first == pr2[j].first){
				ans = max(ans , pr1[i].second);
			}
		}
	}
	return ans;
}
int main(){
	string str1,str2;
	getline(cin , str1);
	getline(cin , str2);
	init(max(str1.length(),str2.length()));
	calH(H1,str1);
	calH(H2,str2);
	calSubH(H1,str1.length(),pr1);
	calSubH(H2,str2.length(),pr2);
	printf("ans = %d\n",getMax());
	return 0;
} 

3，最长回文子串

#include<iostream>
#include<cstdio>
#include<string>
#include<vector>
#include<algorithm>
using namespace std;
typedef long long LL;
const LL P = 10000019;
const LL MOD = 1000000007;
const LL MAXN = 200010;
LL powP[MAXN],H1[MAXN],H2[MAXN];
void init(){
	powP[0] = 1;
	for(int i = 1;i < MAXN;i++){
		powP[i] = (powP[i -1] * P) % MOD;
	}
}
//calH函数计算字符串str的hash值
void calH(LL H[],string &str){
	H[0] = str[0];//H[0]单独处理
	for(int i = 1;i < str.length();i++){
		H[i] = (H[i - 1] * P + str[i]) % MOD;
	} 
} 
//calSingleSubH计算H[i...j]
int calSingleSubH(LL H[],int i,int j){
	if(i == 0) return H[j];
	return ((H[j] - H[i - 1] * powP[j - i + 1] )% MOD + MOD) % MOD;
} 
int binarySearch(int l,int r,int len,int i,int isEven){
	 while(l < r){
	 	int mid = (l + r)/2;
	 	int H1L = i - mid + isEven,H1R = i;
	 	int H2L = len - 1 -(i + mid),H2R =  len - 1 - (i + isEven);
	 	int hashL = calSingleSubH(H1,H1L,H1R);
	 	int hashR = calSingleSubH(H2,H2L,H2R);
	 	if(hashL != hashR)  r = mid;
	 	else {
	 		 l = mid + 1;
		 } 
	 }
	  return l -1;//返回最大回文半径
}
int main(){
	init();
	string str;
	getline(cin,str);
	calH(H1,str);
	reverse(str.begin(),str.end());
	calH(H2,str);
	int ans = 0;
	//奇回文
	for(int i = 0;i < str.length();i++){
		int maxLen = min(i , (int) str.length()-1-i) + 1;
		int k = binarySearch(0,maxLen,str.length(),i,0);
		ans = max(ans,k * 2 + 1);
	} 
	//偶回文
	for(int i = 0; i < str.length();i++){
		int maxLen = min(i + 1,(int)str.length() - 1 - i) +1;
		int k = binarySearch(0, maxLen,str.length(),i,1);
		ans = max(ans,k * 2);
	} 
	printf("%d\n",ans);
	return 0;
}

KMP算法

next数组

void getNext(char s[],int len){
	int j = -1;
	next[0] = -1;
	for(int i = 1;i < len;i++){
		while(j != -1&&s[i] != s[j + 1]){
			j = next[j];
		}
		if(s[i] == s[ i + 1]){
			j++;
		}
		next[i] = j;//令next[i]  = j
	}
}

KMP算法

bool KMP(char text[],char pattern[]){
	int n = strlen(text),m = strlen(pattern);
	getNext(pattern,m);//计算pattern的next数组
	int j = -1；
	for(int i = 0;i < n;i++){
		while(j != -1&&text[i] != pattern[j + 1]){
			j = next[j];
		}
		if(text[i] == pattern[j + 1]){
			j++;
		}
		if( j == m-1){
			return true;//执行完text还没匹配成功，说明pattern不是text的子串 
		}
	} 
	return false;
}

统计模式串出现次数

bool KMP(char text[],char pattern[]){
	int n = strlen(text),m = strlen(pattern);
	getNext(pattern,m);//计算pattern的next数组
	int j = -1；
	for(int i = 0;i < n;i++){
		while(j != -1&&text[i] != pattern[j + 1]){
			j = next[j];
		}
		if(text[i] == pattern[j + 1]){
			j++;
		}
		if( j == m-1){
			return true;//执行完text还没匹配成功，说明pattern不是text的子串 
		}
	} 
	return false;
}

求解nextval数组

//求解nextval数组
void getNextval(char s[],int len){
	int j = -1;
	nextval[0] = -1;
	for(int i =1;i < len;i++){
		while(j != -1&&s[i] != s[j + 1]){
			j = nextval[j];
		}
		if(s[i] == s[j+1]){
			j++;
		}
		if(j == -1||s[i+1]!=s[j + 1]){
			nextval[i] = j;
		}else{
			nextval[i] = nextval[j];
		}
	}
}