PHP内核——hash算法

php的hash算法是采用典型的DJBX33A算法

原理：
hash(i) = hash(i-1)*33 + str[i]
hash(0) = 5381
php内部实现：

static inline ulong zend_inline_hash_func(char *arKey, uint nKeyLength)
{
register ulong hash = 5381;

/* variant with the hash unrolled eight times */
for (; nKeyLength >= 8; nKeyLength -= 8) {
hash = ((hash << 5) + hash) + *arKey++;
hash = ((hash << 5) + hash) + *arKey++;
hash = ((hash << 5) + hash) + *arKey++;
hash = ((hash << 5) + hash) + *arKey++;
hash = ((hash << 5) + hash) + *arKey++;
hash = ((hash << 5) + hash) + *arKey++;
hash = ((hash << 5) + hash) + *arKey++;
hash = ((hash << 5) + hash) + *arKey++;
}
switch (nKeyLength) {
case 7: hash = ((hash << 5) + hash) + *arKey++; /* fallthrough... */
case 6: hash = ((hash << 5) + hash) + *arKey++; /* fallthrough... */
case 5: hash = ((hash << 5) + hash) + *arKey++; /* fallthrough... */
case 4: hash = ((hash << 5) + hash) + *arKey++; /* fallthrough... */
case 3: hash = ((hash << 5) + hash) + *arKey++; /* fallthrough... */
case 2: hash = ((hash << 5) + hash) + *arKey++; /* fallthrough... */
case 1: hash = ((hash << 5) + hash) + *arKey++; break;
case 0: break;
EMPTY_SWITCH_DEFAULT_CASE()
}
return hash;
}

Apache和Perl中采用的是Times33算法
算法思想跟DJBX33A基本一致

sub perlhash{
$hash = 0;
foreach(split){
$hash = $hash*33 + ord($_);
}
return hash;
}

对比两个算法发现不同之处主要有两点：1、初始值2、移位与乘。显然DJB33A的效率要更高一点。对于php初始值为什么选择5381，可能是使用经验值吧~