常用字符串hash算法

来源：互联网发布：vb6.0连接mysql数据库编辑：程序博客网时间：2024/04/28 04:45

以前学习数据结构中有关hash部分的时候一带而过，现在真正在实践中用到的时候才感受到hash的魅力。HDOJ1800可作为练习

以下是常用字符串hash算法的简单对比分析：

Hash函数数据1数据2数据3数据4数据1分数数据2分数数据3分数数据4分数平均RSHash10486150510010051.5820.5175.96JSHash14476150610084.6296.8317.9581.94PJWHash302648785130043.89021.95ELFHash302648785130043.89021.95BKDRHash20477448196.5510090.9582.0592.64SDBMHash32484950493.192.3157.0123.0872.41DJBHash22497547496.5588.46010083.43APHash23475449396.5588.4610051.2886.28

注：

其中数据1为100000个字母和数字组成的随机串哈希冲突个数。数据2为100000个有意义的英文句子哈希冲突个数。数据3为数据1的哈希值与1000003(大素数)求模后存储到线性表中冲突的个数。数据4为数据1的哈希值与10000019(更大素数)求模后存储到线性表中冲突的个数。

// RS Hash Functionunsigned int RSHash(char* str){    unsigned int b = 378551;    unsigned int a = 63689;    unsigned int hash = 0;    while(*str){        hash = hash * a + (*str++);        a *= b;    }    return (hash & 0x7FFFFFFF);}// JS Hash Functionunsigned int JSHash(char* str){    unsigned int hash = 1315423911;    while(*str)        hash ^= ((hash << 5) + (*str++) + (hash >> 2));    return (hash & 0x7FFFFFFF);}// P. J. Weinberger Hash Functionunsigned int PJWHash(char* str){    unsigned int BitsInUnignedInt = (unsigned int )( sizeof (unsigned int)*8);    unsigned int ThreeQuarters = (unsigned int )((BitsInUnignedInt*3 ) / 4);    unsigned int OneEighth = (unsigned int )(BitsInUnignedInt / 8);    unsigned int HighBits = (unsigned int )( 0xFFFFFFFF ) << (BitsInUnignedInt - OneEighth);    unsigned int hash = 0;    unsigned int test = 0;    while(*str){        hash = (hash << OneEighth) + (*str++);        if((test = hash & HighBits) != 0)            hash = ((hash ^ (test >> ThreeQuarters)) & ( ~ HighBits));    }    return (hash & 0x7FFFFFFF);}// ELF Hash Functionunsigned int ELFHash(char* str){    unsigned int hash = 0;    unsigned int x = 0;        while(*str){        hash = (hash << 4 ) + (*str ++ );        if((x = hash & 0xF0000000L ) != 0 ){            hash ^= (x >> 24 );            hash &= ~ x;        }    }    return (hash & 0x7FFFFFFF);}// BKDR Hash Functionunsigned int BKDRHash(char* str){    unsigned int seed = 131; // 31 131 1313 13131 131313 etc..    unsigned int hash = 0;    while(*str)        hash = hash*seed + (*str ++ );    return (hash & 0x7FFFFFFF);}// SDBM Hash Functionunsigned int SDBMHash(char* str){    unsigned int hash = 0;    while(*str)        hash = (*str ++ ) + (hash << 6 ) + (hash << 16 ) - hash;    return (hash & 0x7FFFFFFF);}// DJB Hash Functionunsigned int DJBHash(char* str){    unsigned int hash = 5381;    while(*str)        hash += (hash << 5 ) + (*str ++ );    return (hash & 0x7FFFFFFF);}// AP Hash Functionunsigned int APHash(char* str){    unsigned int hash = 0;    int i;    for(i = 0 ;*str; i ++ ){        if((i & 1 ) == 0 )            hash ^= ((hash << 7 ) ^ (*str ++ ) ^ (hash >> 3 ));          else            hash ^= ( ~ ((hash << 11 ) ^ (*str ++ ) ^ (hash >> 5 )));    }    return (hash & 0x7FFFFFFF);}

0 0