记录几个经典的字符串hash算法

记录几个经典的字符串hash算法，方便以后查看：

推荐一篇文章：

http://www.partow.net/programming/hashfunctions/#

（1）暴雪字符串hash

#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <stdint.h>
#include <stdbool.h>

#define MAXTABLELEN 102400000

typedef struct  _HASHTABLE
{  
    long nHashA;  
    long nHashB;  
    bool bExists;  
}HASHTABLE, *PHASHTABLE;

const unsigned long nTableLength = MAXTABLELEN;
unsigned long m_tablelength;    // 哈希索引表长度  
HASHTABLE *m_HashIndexTable;
unsigned long cryptTable[0x500];

int collc = 0;
int errstr = 0;

void InitCryptTable()  
{   
    unsigned long seed = 0x00100001, index1 = 0, index2 = 0, i;  
 
    for( index1 = 0; index1 < 0x100; 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 );   
        }   
    }   
}  
 
/************************************************************************/
/*函数名：HashString
 *功  能：求取哈希值   
 *返回值：返回hash值
 ************************************************************************/
unsigned long HashString(char *lpszString, unsigned long dwHashType)
{
    unsigned char *key = (unsigned char *)lpszString;
    unsigned long seed1 = 0x7FED7FED, seed2 = 0xEEEEEEEE;
    int ch; 

    while(*key != 0)
    {   
        ch = toupper(*key++);

        seed1 = cryptTable[(dwHashType << 8) + ch] ^ (seed1 + seed2);
        seed2 = ch + seed1 + seed2 + (seed2 << 5) + 3;
    }   
    return seed1;
}
/************************************************************************/
/*函数名：Hashed
 *功  能：检测一个字符串是否被hash过
 *返回值：如果存在，返回位置；否则，返回-1
 ************************************************************************/
unsigned long Hashed(char * lpszString)  
 
{   
    const unsigned long HASH_OFFSET = 0, HASH_A = 1, HASH_B = 2;  
    //不同的字符串三次hash还会碰撞的率无限接近于不可能
    unsigned long nHash = HashString(lpszString, HASH_OFFSET);  
    unsigned long nHashA = HashString(lpszString, HASH_A);  
    unsigned long nHashB = HashString(lpszString, HASH_B);  
    unsigned long nHashStart = nHash % m_tablelength;  
    unsigned long nHashPos = nHashStart;  
 
    while (m_HashIndexTable[nHashPos].bExists)  
    {   
        if (m_HashIndexTable[nHashPos].nHashA == nHashA && m_HashIndexTable[nHashPos].nHashB == nHashB)   
            return nHashPos;   
        else  
            nHashPos = (nHashPos + 1) % m_tablelength;  
 
        if (nHashPos == nHashStart)   
            break;   
    }  
    errstr++;
 
    return -1; //没有找到  
}  
 
/************************************************************************/
/*函数名：Hash
 *功  能：hash一个字符串 
 *返回值：成功，返回true；失败，返回false
 ************************************************************************/
bool Hash(char * lpszString)
{  
    const unsigned long HASH_OFFSET = 0, HASH_A = 1, HASH_B = 2;  
    unsigned long nHash = HashString(lpszString, HASH_OFFSET);  
    unsigned long nHashA = HashString(lpszString, HASH_A);  
    unsigned long nHashB = HashString(lpszString, HASH_B);  
    unsigned long nHashStart = nHash % m_tablelength, 
    nHashPos = nHashStart;  
 
    while (m_HashIndexTable[nHashPos].bExists)  
    {    
        nHashPos = (nHashPos + 1) % m_tablelength;  
        if (nHashPos == nHashStart) //一个轮回  
        { 
            collc ++; 
            //hash表中没有空余的位置了,无法完成hash
            return false;   
        }  
    }  
    m_HashIndexTable[nHashPos].bExists = true;  
    m_HashIndexTable[nHashPos].nHashA = nHashA;  
    m_HashIndexTable[nHashPos].nHashB = nHashB;  
 
    return true;  
}

int InitHashTable()
{
    int i;
    
    InitCryptTable();  
    m_tablelength = nTableLength;
    
    m_HashIndexTable = (HASHTABLE *)malloc(nTableLength * sizeof(HASHTABLE));
    if (NULL == m_HashIndexTable) {
        printf("Init HashTable failure!!
");
        return -1;
    }

    for (i = 0; i < nTableLength; i++ )  
    {  
        m_HashIndexTable[i].nHashA = 0;  
        m_HashIndexTable[i].nHashB = 0;  
        m_HashIndexTable[i].bExists = false;  
    }
    
    return 0;    
}

void do_test()
{
    int count = 0;
    FILE *fp;
    char url[2048] = {0};
    
    fp = fopen("urllist", "rb+");
    if (NULL == fp) {
        return;
    }

    if (InitHashTable()) {
        return;
    }

    while (!feof(fp)) {
        fgets(url, 2048, fp);
        Hash(url);
        count++;
    }

    printf("count: %d
", count);

    fclose(fp);
}

/*test main*/
int main()
{
    do_test();

    printf("conflict: %d
", collc);
    printf("not find: %d
", errstr);

    return 0;
}

 （2）字符串hash算法 ELFhash 

#include <stdio.h>
#include <string.h>
#include <stdlib.h>

#define MOD 10

int ELFhash(char*key)
{
    unsigned long h=0;
    while(*key)
    {   
        h = (h << 4) + *key++;
        unsigned long g = h & 0xF0000000L;
        if(g)
            h ^= g >> 24; 
        h &= ~g; 
    }   
    return h % MOD;
}

int main(int argc, char **argv)
{
    if (argc < 2) {
        printf("using %s <string>
", argv[0]);
        return -1; 
    }   

    int num = 0;
    num = ELFhash(argv[1]);

    printf("num is %d
", num);
}