第二十四章：不重复Hash编码暴雪Hash算法

暴雪Hash算法：

#include <iostream>     
#include <ctype.h>  
using namespace std;    
  
#define nTableSize 99991  
#define nMaxStrLen 30  
  
//函数prepareCryptTable以下的函数生成一个长度为0x500（合10进制数：1280）的cryptTable[0x500]    
unsigned long cryptTable[0x500];  
void prepareCryptTable()    
{     
    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HashString以下函数计算lpszFileName 字符串的hash值，其中dwHashType 为hash的类型，    
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;    
}    
typedef struct    
{    
    int nHashA;    
    int nHashB;    
    char bExists;    
} MPQHASHTABLE;    
//一种可能的结构体定义？    
typedef struct{  
    char *pkey;  
    int weight;  
}KEYNODE, *key_list;  
  
//函数GetHashTablePos中，lpszString 为要在hash表中查找的字符串；lpTable 为存储字符串hash值的hash表；nTableSize 为hash表的长度：     
int GetHashTablePos(const char *lpszString, MPQHASHTABLE *lpTable )    
{    
    const int  HASH_OFFSET = 0, HASH_A = 1, HASH_B = 2;    
     
    int  nHash = HashString( lpszString, HASH_OFFSET );    
    int  nHashA = HashString( lpszString, HASH_A );    
    int  nHashB = HashString( lpszString, HASH_B );    
    int  nHashStart = nHash % nTableSize;    
    int  nHashPos = nHashStart;    
     
    while ( lpTable[nHashPos].bExists )    
   {    
//     如果仅仅是判断在该表中时候存在这个字符串，就比较这两个hash值就可以了，不用对结构体中的字符串进行比较。    
//         这样会加快运行的速度？减少hash表占用的空间？这种方法一般应用在什么场合？    
        if (lpTable[nHashPos].nHashA == nHashA    
        &&  lpTable[nHashPos].nHashB == nHashB )    
       {    
            return nHashPos;    
       }    
       else    
       {    
            nHashPos = (nHashPos + 1) % nTableSize;    
       }    
     
        if (nHashPos == nHashStart)    
              break;    
    }    
     return -1;    
}    
/    
//function: 哈希词典 编码    
//parameter:    
//author: lei.zhou    
//time: 2011-12-14    
/    
MPQHASHTABLE TestHashTable[nTableSize];    
int TestHashCTable[nTableSize];    
int TestHashDTable[nTableSize];    
key_list test_data[nTableSize];    
    
//按关键字查询，如果成功返回hash表中索引位置  
key_list SearchByString(const char *string_in)  
{  
    const int HASH_OFFSET = 0, HASH_C = 1, HASH_D = 2;  
    unsigned int nHash = HashString(string_in, HASH_OFFSET);  
    unsigned int nHashC = HashString(string_in, HASH_C);  
    unsigned int nHashD = HashString(string_in, HASH_D);  
    unsigned int nHashStart = nHash % nTableSize;  
    unsigned int nHashPos = nHashStart;  
  
    while (TestHashTable[nHashPos].bExists)   
    {  
        if (TestHashCTable[nHashPos] == (int) nHashC && TestHashDTable[nHashPos] == (int) nHashD)   
        {  
            break;  
            //查询与插入不同，此处不需修改  
        }   
        else   
        {  
            nHashPos = (nHashPos + 1) % nTableSize;  
        }  
  
        if (nHashPos == nHashStart)   
        {  
            break;  
        }  
    }  
  
    if( test_data[nHashPos] && strlen(test_data[nHashPos]->pkey))   
    {  
        return test_data[nHashPos];  
    }   
  
    return NULL;  
}  
  
//直接调用上面的hashstring，nHashPos就是对应的HASH值。    
int insert_string(const char *string_in)    
{    
    const int HASH_OFFSET = 0, HASH_C = 1, HASH_D = 2;    
    unsigned int nHash = HashString(string_in, HASH_OFFSET);    
    unsigned int nHashC = HashString(string_in, HASH_C);    
    unsigned int nHashD = HashString(string_in, HASH_D);    
    unsigned int nHashStart = nHash % nTableSize;    
    unsigned int nHashPos = nHashStart;    
    int ln, ires = 0;    
    
    while (TestHashTable[nHashPos].bExists)    
    {    
//      if (TestHashCTable[nHashPos]  == (int) nHashC && TestHashDTable[nHashPos] == (int) nHashD)    
//          break;    
//      //...    
//      else    
        //如之前所提示读者的那般，暴雪的Hash算法对于查询那样处理可以，但对插入就不能那么解决    
            nHashPos = (nHashPos + 1) % nTableSize;    
    
        if (nHashPos == nHashStart)    
            break;    
    }    
    
    ln = strlen(string_in);    
    if (!TestHashTable[nHashPos].bExists && (ln < nMaxStrLen))    
    {     
        TestHashCTable[nHashPos] = nHashC;    
        TestHashDTable[nHashPos] = nHashD;    
    
        test_data[nHashPos] = (KEYNODE *) malloc (sizeof(KEYNODE) * 1);    
        if(test_data[nHashPos] == NULL)    
        {    
            printf("10000 EMS ERROR !!!!\n");    
            return 0;    
        }    
    
        test_data[nHashPos]->pkey = (char *)malloc(ln+1);    
        if(test_data[nHashPos]->pkey == NULL)    
        {    
            printf("10000 EMS ERROR !!!!\n");    
            return 0;    
        }    
    
        memset(test_data[nHashPos]->pkey, 0, ln+1);    
        strncpy(test_data[nHashPos]->pkey, string_in, ln);    
        *((test_data[nHashPos]->pkey)+ln) = 0;    
        test_data[nHashPos]->weight = nHashPos;    
    
        TestHashTable[nHashPos].bExists = 1;   
        TestHashTable[nHashPos].nHashA=nHashC;  
        TestHashTable[nHashPos].nHashB=nHashD;  
    }    
    else    
    {    
        if(TestHashTable[nHashPos].bExists)    
            printf("30000 in the hash table %s !!!\n", string_in);    
        else    
            printf("90000 strkey error !!!\n");    
    }    
    return nHashPos;    
}    
int main()    
{    
    prepareCryptTable();  
    int i=insert_string("abcdefghijklmnopqrst");  
    int j=insert_string("abcdefghijklmnopqrt");  
    cout<<i<<"  "<<j<<endl;  
    cout<<test_data[i]->pkey<<endl;  
    cout<<GetHashTablePos("abcdefghijklmnopqrt",TestHashTable)<<endl;  
}