hash_set实现

最新推荐文章于 2019-10-17 10:42:00 发布

xw_njust_ecjtu

最新推荐文章于 2019-10-17 10:42:00 发布

阅读量617

点赞数

分类专栏：数据结构

本文链接：https://blog.csdn.net/njust_ecjtu/article/details/23297499

版权

数据结构专栏收录该内容

12 篇文章 0 订阅

订阅专栏

hash_set的实现是由hash表，再加冲突处理机制实现。本文的冲突处理方法为链地址法。除了这种方法还有再hash法，开放定址法等。

对于hash的实现推荐地址：http://blog.csdn.net/eaglex/article/details/6310727

本文用的方法DJB 。

推荐参考：

http://blog.csdn.net/morewindows/article/details/7330323（此文章写的相当不错，不足：析构函数资源会泄露，

不知是否更改。浏览时需注意。）

数据结构严蔚敏版本，编程珠玑-15章字符串。

以下为代码：

#ifndef _HASH_MY_
#define _HASH_MY_

#include <string>
using namespace std;
struct node
{
	string str_val;
	node *next;
};

class hash_my
{
	public:
		hash_my(int size = 1000);//分配资源
		hash_my::~hash_my();//释放资源
		unsigned int hash(string str);//hash函数
		void insert(string str);//插入元素
		bool find(string str);
		void print();

	private:
		unsigned int table_size;
		node **m_pnode;
};

#endif

#include "hash_my.h"
#include <iostream>

hash_my::hash_my(int size )//分配资源
{	
	table_size = size;
	m_pnode = new node *[size];
	if(m_pnode == NULL)return;

	memset(m_pnode,NULL,sizeof(node*)*size);//初始化
	 
}

hash_my::~hash_my()//释放资源
{
	node * p_node,*temp_node;
	for (int i = 0; i < table_size;i++)	
	{
		for (p_node = m_pnode[i];p_node != NULL;)
		{
			temp_node = p_node;//暂存
			p_node = p_node->next;
			delete temp_node;
		}

	}
	
	delete []m_pnode;//最后析构
}

unsigned int hash_my::hash(string str)//hash函数
{
	const int MULT = 33;
	int h = 5381;//记得初始化或者0
	for (int i =0 ; i < str.size();i++)
	{
		h = (h*MULT + str[i])%table_size;
	}
	return h;
}

void hash_my::insert(string str)//插入元素
{
	 int h = hash(str);
	 node * p_node;
	
	 for (p_node = m_pnode[h];p_node != NULL;p_node = p_node->next)
	 {
		 if (p_node->str_val == str)
		 {
			 return ;//已经存在，或者可在此增加计数功能
		 }
	 }
	 //未找到则插入
	 node *new_node = new node;
	 if(new_node == NULL)return;
	
	 new_node->str_val = str;

	 new_node->next = m_pnode[h];
	 m_pnode[h] = new_node;
}

bool hash_my::find(string str)
{
	int h = hash(str);
	node * p_node;

	for (p_node = m_pnode[h];p_node != NULL;p_node = p_node->next)
	{
		if (p_node->str_val == str)
		{
			return true; 
		}
	} 

	return false;

}
void hash_my::print()
{
	node * p_node;
	for (int i = 0; i < table_size;i++)	
	{
		for (p_node = m_pnode[i];p_node != NULL;p_node = p_node->next)
		{
			cout<<p_node->str_val<<"  ";
		}

	}
	cout<<endl;
}

#include "vld.h"
#include <iostream>
#include <hash_set>
#include "hash_my.h"
#include <string>
#include <cstdlib>
#include <ctime>
#include <sstream>


using namespace std;
using namespace stdext;

const unsigned int max_num = 1000000;
int main()
{
	hash_my hash_obj;
	hash_set<string> hash_cmp;
	clock_t start,end;
 
	stringstream str_sream;
	string *str_store = new string[max_num];
	srand((unsigned int)time(NULL));	
	
	for (int i = 0;i < max_num;i++)
	{
		str_sream.clear();
		str_sream<<rand();//int范围内
		str_sream>>str_store[i];
		str_sream.str("");//清空
		//cout<<str_store[i]<<" ";
		
	}
 
	start = clock();
	
	for (int j = 0;j < max_num;j++)
	{
		hash_obj.insert(str_store[j]);
	 
	}
	
	for (int k = 0;k < max_num;k++)
	hash_obj.find(str_store[k]);
 
	end = clock();

	cout<<"hash_my 用时："<<end-start<<endl;
	
	start = clock();

	for (int j = 0;j < max_num;j++)
	   hash_cmp.insert(str_store[j]);

	for (int k = 0;k < max_num;k++)
		hash_cmp.find(str_store[k]);

	end = clock();
	cout<<"hash_set 用时："<<end-start<<endl;

	//hash_obj.print();
	delete []str_store;
	return 1;
}

sy_njust_ecjtu