2020秋数据结构实验第五题：哈希查找 C++实现

实验描述：

实验分析：

所谓哈希查找也就是根据输入的数据找到我们想要查找的信息，而且要做到O(1)的时间复杂度，即并不随着数据量的变大而查找次数变得很大，基础哈希表的创建过程如下：

1. 根据输入计算Hash值，如果不冲突直接放入对应的槽中；
2. 如果冲突可以采用几种冲突解决的方法进行解决，开放地址法和链式存储法，现在本助教给出开放地址法中的再Hash的方法进行解决冲突；
3. 通过1和2已经创建了Hash表，我们再创建的时候记录冲突最大的次数，也将是我们在查找时的最大查找次数，进行查找，计算平均查找次数。

实验代码

#include<stdio.h>
#include<iostream>
#include<iomanip>
#include<fstream>
#include<string>
#include<vector>
using namespace std;

#define MAXNUM 1000
#define HASHSPACE 2
string com = "";
struct student {
	string name;
	string sex;
	string age;
	string mail;
	string phone;
	struct student() {
		name = "";
		sex = "";
		age = "";
		mail = "";
		phone = "";
	}
};
const int Sum_Space = int(HASHSPACE*MAXNUM);
student stus[MAXNUM], stus_hash[Sum_Space - 1];
int Hash(string name, int confict_num) {
	unsigned int index = 0,sum = 0;
	for (int i = 0; i < name.size(); i++) {
		sum += int(name[i])*(i*i+1);
	}
	index = sum % (Sum_Space - 1);
	if (confict_num == 0) return index;
	int Gk = (sum + 1) % (Sum_Space - 3);
	return ((index + (confict_num*Gk) % (Sum_Space - 1)))%(Sum_Space-1);
}
int CreatHashTable(student *stus, student *stus_hash) {
	int max_confict_num = 0;
	int index = 0;
	for (int i = 0; i < MAXNUM; i++) {
		bool flag = false;
		int confict_num = 0;
		string name = stus[i].name;
		while (1) {
			index = Hash(name,confict_num);
			if (stus_hash[index].name._Equal(com))
			{
				memcpy(stus_hash + index, stus + i, sizeof(student) * 1);
				break;
			}
			confict_num++;
			if (max_confict_num < confict_num)
				max_confict_num = confict_num;
		}
	}
	return max_confict_num;
}
int find_hash(string name, int max_confict_num,student *stus_hash,int &find_error_time) {
	int find_time = 0;
	while (find_time <= max_confict_num) {
		int index = Hash(name, find_time);
		if (stus_hash[index].name == name)
		{
			//cout << "Find Success!" << "  Index:" << index << endl;
			return find_time+1;
		}
		else
		{
			//cout << "Find Confict With " << index << endl;
			find_time++;
		}
	}
	cout << "Error Can't Find The " << name << endl;
	find_error_time = find_time;
	return -1;
}

int main() {
	/**********************************Read Student Info**********************************************/
	
	fstream name("name.txt"),sex("sex.txt"),age("age.txt"),mail("mail.txt"),phone("phone.txt");
	//fstream name("name_100000.txt"), sex("sex_100000.txt"), age("age_100000.txt"), mail("mail_100000.txt"), phone("phone_100000.txt");
	string tmp_name,tmp_sex,tmp_age,tmp_mail,tmp_phone;
	int num = 0,max_confict_num = 0;
	while (getline(name, tmp_name)&&getline(sex, tmp_sex) && getline(age, tmp_age) && getline(mail, tmp_mail) && getline(phone, tmp_phone)) {
		if (num == MAXNUM) break;
		stus[num].name = tmp_name;
		stus[num].age = tmp_age;
		stus[num].mail = tmp_mail;
		stus[num].phone = tmp_phone;
		stus[num].sex = tmp_sex;
		//cout << "num:" <<tmp_name <<tmp_name.size() << endl;
		num++;
	}
	/**********************************Creat Hash Table************************************************/
	cout << "/**********************************Hash Search************************************************/" << endl;
	max_confict_num = CreatHashTable(stus, stus_hash);
	cout << "Used_Num:Data_Num=" << Sum_Space  << ":" << MAXNUM << "="<<float(Sum_Space) / float(MAXNUM) << endl;
	cout << "max_confict_num:" << max_confict_num << endl;
	int val = 0;
	for (int i = 0; i < Sum_Space - 1; i++) {
		if (stus_hash[i].name._Equal(com))
			val++;
		//cout << "index:"<<setw(3)<<i<<"  name:" << setw(8) << stus_hash[i].name << "  sex:" << setw(2) << stus_hash[i].sex << "  age:" << setw(3) << stus_hash[i].age << "  mail:" << setw(14) << stus_hash[i].mail << "  phone:" << setw(12) << stus_hash[i].phone << endl;
	}
	cout << "None Val Num:" << val << endl;
	/*********************************Compute Average Find Time*****************************************/
	int find_sum_time = 0,find_error_time=0;
	for (int i = 0; i < MAXNUM; i++) {
		int find_time = find_hash(stus[i].name, max_confict_num, stus_hash,find_error_time);
		if (find_time == -1) {
			cout << "Error Find!" << endl;
			getchar();
		}
		else
			find_sum_time += find_time;
	}
	cout << "Average Find Time :" << find_sum_time / float(MAXNUM) << endl;
	/***********************************Test The Case of Can't Find*************************************/
	int find_time = find_hash("Jerry", max_confict_num, stus_hash,find_error_time);
	if (find_time == -1) cout << "Find Error Time :" << find_error_time << endl;
	getchar();
}

实验结果：

从以上结果我们能看出，随着槽数的增加，最大冲突次数变小，平均查找次数也变小，但随之带来的没用到的空间也变多了，时间空间需要做一个权衡了，当然同学们日后还会学习更加高级的查找结构红黑树，能带来更好的查找性能 。