（13）字符串哈希

最新推荐文章于 2013-09-03 18:42:45 发布

leileicaocao

最新推荐文章于 2013-09-03 18:42:45 发布

阅读量463

点赞数

分类专栏：算法文章标签： C++ 算法

本文链接：https://blog.csdn.net/leileicaocao/article/details/8961093

版权

算法专栏收录该内容

29 篇文章 0 订阅

订阅专栏

#include <iostream>
#include <string>

using namespace std;

void TestReverseIndex();

const unsigned HASH_SIZE = 1024;
const unsigned CRYPT_SIZE = 0x100;

// 索引节点
struct KeyNode
{
	string strKey;
	int count;
	int pos;
	struct KeyNode *pNext;
};

KeyNode *hash_table[HASH_SIZE];

struct DocNode
{
	string docID;
	int classOne;
	string classTwo;
	string time;
	string MD5;
	int weight;
	struct DocNode * pNext;
};

unsigned long cryptTable[CRYPT_SIZE];
// 构造cryptTable
void PrepareCryptTable();
// 返回字符串的hash值
unsigned long HashString(const char *lpszkeyName, unsigned long dwHashType);
// 在hash表中寻找关键字，如何找到，则返回hash节点
KeyNode * SearchByString(const char * lpszkeyName);

#include "13_ReverseIndex.h"



void TestReverseIndex()
{
}

void PrepareCryptTable()
{
	unsigned long seed = 0x00100001;
	unsigned long index1, index2, i;

	for (index1 = 0; index1 < 0x001; ++index1)
	{
		for (index2 = index1, i = 0; i < 5; i++, index2 += 0x100)
		{
			unsigned long temp1, temp2;
			seed = (seed * 125 + 3) % 0x2AAAAB;
			temp1 = (seed & 0xFFFF) << 0x10;
			seed = (seed * 125 + 3) % 0x2AAAAB;
			temp2 = (seed % 0xFFFF);
			cryptTable[index2] = (temp1 | temp2);
		}
	}
}

unsigned long HashString(const char *lpszkeyName, unsigned long dwHashType)
{
	unsigned char *key = (unsigned char *)lpszkeyName;
	unsigned long seed1 = 0x7FED7FED;
	unsigned long seed2 = 0xEEEEEEEE;

	int ch;
	while (*key != 0)
	{
		ch = *key++;
		seed1 = cryptTable[(dwHashType << 8) + ch] ^ (seed1 + seed2);
		seed2 = ch + seed1 + seed2 + (seed2 << 5) + 3;
	}
	return seed1;
}

KeyNode * SearchByString(const char * lpszkeyName)
{
	const int HASH_OFFSET = 0, HASH_C = 1, HASH_D = 2;
	unsigned int nHash = HashString(lpszkeyName, HASH_OFFSET);
	unsigned int nHashC = HashString(lpszkeyName, HASH_C);
	unsigned int nHashD = HashString(lpszkeyName, HASH_D);
	unsigned int nHashStart = nHash % HASH_SIZE;
	unsigned int nHashPos = nHashStart;

}