从0写一个hash表？你懂字符串哈希吗？

1. 模拟哈希表

1.1 开放寻址法

开放寻址法- 线性探测法

#include<iostream>
#include<cstring>

using namespace std;

const int N = 2e5+10,null = 0x3f3f3f3f;
int p[N];


int find(int x){
    int index = (x%N+N)%N;
    while(p[index] != null&& p[index] != x){
        index = (index+1)%N;
    }
    return index;
}
int main(){
    int n;
    scanf("%d",&n);
    //int有四个字节，按字节初始化
    memset(p,0x3f,sizeof p);
    while(n--){
       char a[2];
       int b;
       scanf("%s%d",a,&b);
       if(*a =='I'){
           p[find(b)] = b;
       }else{
           if(p[find(b)] == null){
               puts("No");
           }else{
               puts("Yes");
           }
       }
        
    }
}

1.2 拉链法

#include<iostream>
#include<cstring>
using namespace std;

const int N = 200003;
int a[N],e[N],ne[N],h[N],idx,n;

void insert(int b){
    int a = (b%N+N)%N;
    e[idx] = b;
    ne[idx] = h[a];
    h[a] = idx++;
}
bool find(int x){
    int u  = (x%N+N)%N;
    for(int i = h[u]; i != -1; i = ne[i]){
        if(e[i] == x){
            return true; 	
        }
    }
    return false;
}
int main(){
    // char *类型 。它是一个指针，这个指针指向一个字符串。

    // char [] 类型。它是一个数组，他代表了这堆内存空间。
   memset(h,-1, sizeof h);
   scanf("%d",&n);
   while(n--){
       char x[2];
       int y;
        scanf("%s%d",x,&y);
        if(*x == 'I'){
           insert(y);
       }else{
           if(find(y)){
               puts("Yes");
           }else{
               puts("No");
           }
       }
   }
   
    
    
}

2. 字符串哈希

字符串前缀哈希法
设 str = “abcacbabc”
设h[0] = 0
h[1] 是a的hash值
h[2]是ab的hash值
那么如何对字符的hash值进行保存，可以利用p进制就是利用ASCII值进行计算

#include<bits/stdc++.h>
using namespace std;

typedef unsigned long long ULL;
const int N = 100010, P = 131;
int n,m;
char str[N];
ULL h[N],p[N];
ULL get(int l,int r){
    return h[r] - h[l-1]*p[r-l+1];
}
int main(){
    scanf("%d%d",&n,&m);
    scanf("%s",str+1);
    
    p[0] = 1;
    for(int i = 1; i <= n; i++){
        //计算并预处理进制
        p[i] = p[i-1]*P;
        //计算每一个前缀和的哈希值
        h[i] = h[i-1]*P+str[i];
    }
    while(m--){
        int l1,r1,l2,r2;
        scanf("%d%d%d%d",&l1,&r1,&l2,&r2);
        if(get(l1,r1) == get(l2,r2)){
            puts("Yes");
        }else{
            puts("No");
        }
    }
    return 0;
}

2.1 处理字符串经常用的还有KMP

#include<iostream>
#include<cstring>

const int N = 1e5+10, M = 1e6+10;
char p[N],s[M];
int ne[N];
int n,m;

int main(){
    scanf("%d%s",&n,p+1);
    scanf("%d%s",&m,s+1);

    //计算next数组
    for(int i = 2, j = 0; i <= n; i++){
        while(j && p[i] != p[j+1]){
            j = ne[j];
        }
        if(p[i] == p[j+1]){
            j++;
        }
        ne[i] = j;
    }

    for(int i = 1, j = 0; i <= m; i++){
        while(j && s[i] != p[j+1]){
            j = ne[j];
        }
        if(s[i] == p[j+1]){
            j++;
        }
        if(j==n){
            printf("%d ",i-n);
        }
    }
    return 0;
}

作者：acw_zzd
链接：https://www.acwing.com/activity/content/code/content/1600923/
来源：AcWing
著作权归作者所有。商业转载请联系作者获得授权，非商业转载请注明出处。

3. leetcode 习题 187

class Solution {
public:
    vector<string> findRepeatedDnaSequences(string s) {
        unordered_map<string,int> hash;
        vector<string> ans;
        for(int i = 0; i+10 <= s.length(); i++){
            hash[s.substr(i,10)]++;
        }
        for(auto &[k,v]:hash){
            if(v > 1){
                ans.push_back(k);
            }
        }
        return ans;
    }
};

class Solution {
    int N = (int)1e5+10, P = 13331;
    int[] h = new int[N], p = new int[N];
    public List<String> findRepeatedDnaSequences(String s) {
        int n = s.length();
        List<String> ans = new ArrayList<>();
        p[0] = 1;
        for (int i = 1; i <= n; i++) {
            h[i] = h[i - 1] * P + s.charAt(i - 1);
            p[i] = p[i - 1] * P;
        }
        Map<Integer, Integer> map = new HashMap<>();
        for (int i = 1; i + 10 - 1 <= n; i++) {
            int j = i + 10 - 1;
            int hash = h[j] - h[i - 1] * p[j - i + 1];
            int cnt = map.getOrDefault(hash, 0);
            if (cnt == 1) ans.add(s.substring(i - 1, i + 10 - 1));
            map.put(hash, cnt + 1);
        }
        return ans;
    }
}

字符串哈希加二分解决最长回文子串（好题）

解析描述

#include<bits/stdc++.h>
using namespace std;

typedef unsigned long long ULL;
const int N = 2e6+10,P = 131;
ULL sl[N],sr[N],p[N];
char ss[N];
ULL get(ULL s[],int l,int r){
	return s[r] - s[l-1] * p[r-l+1];
}
int main(){
	int T = 1;
	while(scanf("%s",ss+1),strcmp(ss+1,"END")){
		int n = strlen(ss+1);
		//初始化字符串 
		for(int i = n*2; i ; i-=2){
			ss[i] = ss[i/2];
			ss[i-1] = 'z'+1;
		}
		n*=2;
		p[0] = 1;
		for(int i = 1, j = n; i <= n; i++,j--){
			p[i] = p[i-1] *P;
			sl[i] = P * sl[i-1]+ss[i];
			sr[i] = P * sr[i-1]+ss[j];
		}
		int res = 0;
		for(int i = 1; i <= n; i++){
			//半径的最大长度 
			int l = 0, r = min(i-1,n-i);
			while(l < r){
				int mid = (l+r+1)>>1;
				if(get(sl,i-mid,i-1) == get(sr,n-(i+mid)+1,n-(i+1)+1)){
					l = mid;
				}else{
					r = mid - 1;
				}
			}
			if(ss[i-l] <='z'){
				res = max(res,l+1);
			}else{
				res = max(res,l);
			}
		}
		printf("Case %d: %d\n",T++,res);
	}
	
	
}