hash算法的大全

1150阅读　0评论2013-03-23　sbso_1988
分类：C/C++

1）几种的Hash算法的实现(源代码)   
URL：http://blog.minidx.com/2008/01/27/446.html

ByMinidxer| January 27, 2008

哈希算法将任意长度的二进制值映射为固定长度的较小二进制值，这个小的二进制值称为哈希值。哈希值是一段唯一且极其紧凑的数值表示形式。如果散列一段 明文而且哪怕只更改该段落的一个字母，随后的哈希都将产生不同的值。要找到散列为同一个值的两个不同的输入，在计算上是不可能的，所以数据的哈希值可以检 验数据的完整性。

链表查找的时间效率为O(N)，二分法为log2N，B+ Tree为log2N，但Hash链表查找的时间效率为O(1)。

设计高效算法往往需要使用Hash链表，常数级的查找速度是任何别的算法无法比拟的，Hash链表的构造和冲突的不同实现方法对效率当然有一定的影 响，然 而Hash函数是Hash链表最核心的部分，下面是几款经典软件中使用到的字符串Hash函数实现，通过阅读这些代码，我们可以在Hash算法的执行效 率、离散性、利用率等方面有比较深刻的了解。

下面分别介绍几个经典软件中出现的字符串Hash函数。

●PHP中出现的字符串Hash函数 


staticunsignedlonghashpjw(char*arKey, unsignedintnKeyLength)
{
unsignedlongh = 0, g;
char*arEnd=arKey+nKeyLength;

while(arKey < arEnd) {
h = (h << 4) + *arKey++;
if((g = (h & 0xF0000000))) {
h = h ^ (g >> 24);
h = h ^ g;
}
}
returnh;
}

.csharpcode, .csharpcode pre { font-size: small; color: black; font-family: consolas, "Courier New", courier, monospace; background-color: #ffffff; /*white-space: pre;*/ } .csharpcode pre { margin: 0em; } .csharpcode .rem { color: #008000; } .csharpcode .kwrd { color: #0000ff; } .csharpcode .str { color: #006080; } .csharpcode .op { color: #0000c0; } .csharpcode .preproc { color: #cc6633; } .csharpcode .asp { background-color: #ffff00; } .csharpcode .html { color: #800000; } .csharpcode .attr { color: #ff0000; } .csharpcode .alt { background-color: #f4f4f4; width: 100%; margin: 0em; } .csharpcode .lnum { color: #606060; }

●OpenSSL中出现的字符串Hash函数 


unsignedlonglh_strhash(char*str)
{
inti,l;
unsignedlongret=0;
unsignedshort*s;

if(str == NULL)return(0);
l=(strlen(str)+1)/2;
s=(unsignedshort*)str;

for(i=0; i
ret^=(s[i]<<(i&0×0f));
return(ret);
}

/* The following hash seems to work very well on normal text strings
* no collisions on /usr/dict/words and it distributes on %2^n quite
* well, not as good as MD5, but still good.
*/
unsignedlonglh_strhash(constchar*c)
{
unsignedlongret=0;
longn;
unsignedlongv;
intr;

if((c == NULL) || (*c ==‘/0′))
return(ret);
/*
unsigned char b[16];
MD5(c,strlen(c),b);
return(b[0]|(b[1]<<8)|(b[2]<<16)|(b[3]<<24));
*/

n=0×100;
while(*c)
{
v=n|(*c);
n+=0×100;
r= (int)((v>>2)^v)&0×0f;
ret=(ret(32-r));
ret&=0xFFFFFFFFL;
ret^=v*v;
c++;
}

return((ret>>16)^ret);
}

●中出现的字符串Hash函数 


#ifndef NEW_HASH_FUNCTION

/* Calc hashvalue for a key */
staticuintcalc_hashnr(constbyte*key,uintlength)
{
registeruintnr=1, nr2=4;

while(length–)
{
nr^= (((nr & 63)+nr2)*((uint) (uchar) *key++))+ (nr << 8);
nr2+=3;
}

return((uint) nr);
}

/* Calc hashvalue for a key, case indepenently */
staticuintcalc_hashnr_caseup(constbyte*key,uintlength)
{
registeruintnr=1, nr2=4;

while(length–)
{
nr^= (((nr & 63)+nr2)*((uint) (uchar) toupper(*key++)))+ (nr << 8);
nr2+=3;
}

return((uint) nr);
}
#else
/*
* Fowler/Noll/Vo hash
*
* The basis of the hash algorithm was taken from an idea sent by email to the
* IEEE Posix P1003.2 mailing list from Phong Vo (kpv@research.att.com) and
* Glenn Fowler (gsf@research.att.com). Landon Curt Noll (chongo@toad.com)
* later improved on their algorithm.
*
* The magic is in the interesting relationship between the special prime
* 16777619 (2^24 + 403) and 2^32 and 2^8.
*
* This hash produces the fewest collisions of any function that we’ve seen so
* far, and works well on both numbers and strings.
*/
uintcalc_hashnr(constbyte*key,uintlen)
{
constbyte*end=key+len;
uinthash;

for(hash = 0; key < end; key++)
{
hash *= 16777619;
hash ^= (uint) *(uchar*) key;
}

return(hash);
}

uintcalc_hashnr_caseup(constbyte*key,uintlen)
{
constbyte*end=key+len;
uinthash;

for(hash = 0; key < end; key++)
{
hash *= 16777619;
hash ^= (uint) (uchar) toupper(*key);
}

return(hash);
}
#endif

.csharpcode, .csharpcode pre { font-size: small; color: black; font-family: consolas, "Courier New", courier, monospace; background-color: #ffffff; /*white-space: pre;*/ } .csharpcode pre { margin: 0em; } .csharpcode .rem { color: #008000; } .csharpcode .kwrd { color: #0000ff; } .csharpcode .str { color: #006080; } .csharpcode .op { color: #0000c0; } .csharpcode .preproc { color: #cc6633; } .csharpcode .asp { background-color: #ffff00; } .csharpcode .html { color: #800000; } .csharpcode .attr { color: #ff0000; } .csharpcode .alt { background-color: #f4f4f4; width: 100%; margin: 0em; } .csharpcode .lnum { color: #606060; }

Mysql中对字符串Hash函数还区分了大小写

●另一个经典字符串Hash函数 


unsignedinthash(char*str)
{
register unsignedinth;
register unsignedchar*p;

for(h=0, p = (unsignedchar*)str; *p ; p++)
h = 31 * h + *p;

returnh;
}

2）大量HASH算法的实现 
URL：http://hi.baidu.com/algorithms/blog/item/79caabee879ece2a2cf53440.html

Hash算法有很多很多种类。具体的可以参考之前我写的Hash算法的一些分析。本处给大家提供一个集合了很多使用的Hash算法的类，应该可以满足不少人的需要的：

/** 
* Hash算法大全
 
* 推荐使用FNV1算法 
* @algorithm None 
* @author Goodzzp 2006-11-20 
* @lastEdit Goodzzp 2006-11-20 
* @editDetail Create 
*/ 
public class HashAlgorithms 
{ 
/** 
* 加法hash 
* @param key 字符串 
* @param prime 一个质数 
* @return hash结果 
*/ 
public static int additiveHash(String key, int prime) 
{ 
   int hash, i; 
   for (hash = key.length(), i = 0; i < key.length(); i++) 
    hash += key.charAt(i); 
   return (hash % prime); 
} 
/** 
* 旋转hash 
* @param key 输入字符串 
* @param prime 质数 
* @return hash值 
*/ 
public static int rotatingHash(String key, int prime) 
{ 
   int hash, i; 
   for (hash=key.length(), i=0; i      hash = (hash<<4)^(hash>>28)^key.charAt(i); 
   return (hash % prime); 
//   return (hash ^ (hash>>10) ^ (hash>>20)); 
}

// 替代： 
// 使用：hash = (hash ^ (hash>>10) ^ (hash>>20)) & mask; 
// 替代：hash %= prime; 
/** 
* MASK值，随便找一个值，最好是质数 
*/ 
static int M_MASK = 0x8765fed1; 
/** 
* 一次一个hash 
* @param key 输入字符串 
* @return 输出hash值 
*/ 
public static int oneByOneHash(String key) 
{ 
   int   hash, i; 
   for (hash=0, i=0; i    { 
     hash += key.charAt(i); 
     hash += (hash << 10); 
     hash ^= (hash >> 6); 
   } 
   hash += (hash << 3); 
   hash ^= (hash >> 11); 
   hash += (hash << 15); 
//   return (hash & M_MASK); 
   return hash; 
}

/** 
* Bernstein's hash 
* @param key 输入字节数组 
* @param level 初始hash常量 
* @return 结果hash 
*/ 
public static int bernstein(String key) 
{ 
   int hash = 0; 
   int i; 
   for (i=0; i    return hash; 
}

// 
//// Pearson's Hash 
// char pearson(char[]key, ub4 len, char tab[256]) 
// { 
//   char hash; 
//   ub4 i; 
//   for (hash=len, i=0; i //     hash=tab[hash^key[i]]; 
//   return (hash); 
// }

//// CRC Hashing，计算crc,具体代码见其他 
// ub4 crc(char *key, ub4 len, ub4 mask, ub4 tab[256]) 
// { 
//   ub4 hash, i; 
//   for (hash=len, i=0; i //     hash = (hash >> 8) ^ tab[(hash & 0xff) ^ key[i]]; 
//   return (hash & mask); 
// }

/** 
* Universal Hashing 
*/ 
public static int universal(char[]key, int mask, int[] tab) 
{ 
   int hash = key.length, i, len = key.length; 
   for (i=0; i<(len<<3); i+=8) 
   { 
     char k = key[i>>3]; 
     if ((k&0x01) == 0) hash ^= tab[i+0]; 
     if ((k&0x02) == 0) hash ^= tab[i+1]; 
     if ((k&0x04) == 0) hash ^= tab[i+2]; 
     if ((k&0x08) == 0) hash ^= tab[i+3]; 
     if ((k&0x10) == 0) hash ^= tab[i+4]; 
     if ((k&0x20) == 0) hash ^= tab[i+5]; 
     if ((k&0x40) == 0) hash ^= tab[i+6]; 
     if ((k&0x80) == 0) hash ^= tab[i+7]; 
   } 
   return (hash & mask); 
}

/** 
* Zobrist Hashing 
*/ 
public static int zobrist( char[] key,int mask, int[][] tab) 
{ 
   int hash, i; 
   for (hash=key.length, i=0; i      hash ^= tab[i][key[i]]; 
   return (hash & mask); 
}

// LOOKUP3 
// 见Bob Jenkins(3).c文件

// 32位FNV算法 
static int M_SHIFT = 0; 
/** 
* 32位的FNV算法 
* @param data 数组 
* @return int值 
*/ 
    public static int FNVHash(byte[] data) 
    { 
        int hash = (int)2166136261L; 
        for(byte b : data) 
            hash = (hash * 16777619) ^ b; 
        if (M_SHIFT == 0) 
            return hash; 
        return (hash ^ (hash >> M_SHIFT)) & M_MASK; 
    } 
    /** 
     * 改进的32位FNV算法1 
     * @param data 数组 
     * @return int值 
     */ 
    public static int FNVHash1(byte[] data) 
    { 
        final int p = 16777619; 
        int hash = (int)2166136261L; 
        for(byte b:data) 
            hash = (hash ^ b) * p; 
        hash += hash << 13; 
        hash ^= hash >> 7; 
        hash += hash << 3; 
        hash ^= hash >> 17; 
        hash += hash << 5; 
        return hash; 
    } 
    /** 
     * 改进的32位FNV算法1 
     * @param data 字符串 
     * @return int值 
     */ 
    public static int FNVHash1(String data) 
    { 
        final int p = 16777619; 
        int hash = (int)2166136261L; 
        for(int i=0;i             hash = (hash ^ data.charAt(i)) * p; 
        hash += hash << 13; 
        hash ^= hash >> 7; 
        hash += hash << 3; 
        hash ^= hash >> 17; 
        hash += hash << 5; 
        return hash; 
    }

    /** 
     * Thomas Wang的算法，整数hash 
     */ 
    public static int intHash(int key) 
    { 
      key += ~(key << 15); 
      key ^= (key >>> 10); 
      key += (key << 3); 
      key ^= (key >>> 6); 
      key += ~(key << 11); 
      key ^= (key >>> 16); 
      return key; 
    } 
    /** 
     * RS算法hash 
     * @param str 字符串 
     */ 
    public static int RSHash(String str) 
    { 
        int b    = 378551; 
        int a    = 63689; 
        int hash = 0;

       for(int i = 0; i < str.length(); i++) 
       { 
          hash = hash * a + str.charAt(i); 
          a    = a * b; 
       }

       return (hash & 0x7FFFFFFF); 
    } 
    /* End Of RS Hash Function */

    /** 
     * JS算法 
     */ 
    public static int JSHash(String str) 
    { 
       int hash = 1315423911;

       for(int i = 0; i < str.length(); i++) 
       { 
          hash ^= ((hash << 5) + str.charAt(i) + (hash >> 2)); 
       }

       return (hash & 0x7FFFFFFF); 
    } 
    /* End Of JS Hash Function */

    /** 
     * PJW算法 
     */ 
    public static int PJWHash(String str) 
    { 
        int BitsInUnsignedInt = 32; 
        int ThreeQuarters     = (BitsInUnsignedInt * 3) / 4; 
        int OneEighth         = BitsInUnsignedInt / 8; 
        int HighBits          = 0xFFFFFFFF << (BitsInUnsignedInt - OneEighth); 
        int hash              = 0; 
        int test              = 0;

       for(int i = 0; i < str.length();i++) 
       { 
          hash = (hash << OneEighth) + str.charAt(i);

          if((test = hash & HighBits) != 0) 
          { 
             hash = (( hash ^ (test >> ThreeQuarters)) & (~HighBits)); 
          } 
       }

       return (hash & 0x7FFFFFFF); 
    } 
    /* End Of P. J. Weinberger Hash Function */

    /** 
     * ELF算法 
     */ 
    public static int ELFHash(String str) 
    { 
        int hash = 0; 
        int x    = 0;

       for(int i = 0; i < str.length(); i++) 
       { 
          hash = (hash << 4) + str.charAt(i); 
          if((x = (int)(hash & 0xF0000000L)) != 0) 
          { 
             hash ^= (x >> 24); 
             hash &= ~x; 
          } 
       }

       return (hash & 0x7FFFFFFF); 
    } 
    /* End Of ELF Hash Function */

    /** 
     * BKDR算法 
     */ 
    public static int BKDRHash(String str) 
    { 
        int seed = 131; // 31 131 1313 13131 131313 etc.. 
        int hash = 0;

       for(int i = 0; i < str.length(); i++) 
       { 
          hash = (hash * seed) + str.charAt(i); 
       }

       return (hash & 0x7FFFFFFF); 
    } 
    /* End Of BKDR Hash Function */

    /** 
     * SDBM算法 
     */ 
    public static int SDBMHash(String str) 
    { 
        int hash = 0;

       for(int i = 0; i < str.length(); i++) 
       { 
          hash = str.charAt(i) + (hash << 6) + (hash << 16) - hash; 
       }

       return (hash & 0x7FFFFFFF); 
    } 
    /* End Of SDBM Hash Function */

    /** 
     * DJB算法 
     */ 
    public static int DJBHash(String str) 
    { 
       int hash = 5381;

       for(int i = 0; i < str.length(); i++) 
       { 
          hash = ((hash << 5) + hash) + str.charAt(i); 
       }

       return (hash & 0x7FFFFFFF); 
    } 
    /* End Of DJB Hash Function */

    /** 
     * DEK算法 
     */ 
    public static int DEKHash(String str) 
    { 
        int hash = str.length();

       for(int i = 0; i < str.length(); i++) 
       { 
          hash = ((hash << 5) ^ (hash >> 27)) ^ str.charAt(i); 
       }

       return (hash & 0x7FFFFFFF); 
    } 
    /* End Of DEK Hash Function */

    /** 
     * AP算法 
     */ 
    public static int APHash(String str) 
    { 
        int hash = 0;

       for(int i = 0; i < str.length(); i++) 
       { 
          hash ^= ((i & 1) == 0) ? ( (hash << 7) ^ str.charAt(i) ^ (hash >> 3)) : 
                                   (~((hash << 11) ^ str.charAt(i) ^ (hash >> 5))); 
       }

//       return (hash & 0x7FFFFFFF); 
       return hash; 
    } 
    /* End Of AP Hash Function */ 
    /** 
     * 自己带的算法 
     */ 
    public static int java(String str) 
{ 
   int h = 0; 
   int ff = 0; 
   int len = str.length(); 
   for (int i = 0; i < len; i++) 
   { 
    h = 31 * h + str.charAt(off++); 
   } 
   return h; 
} 
    /** 
     * 混合hash算法，输出64位的值 
     */ 
    public static long mixHash(String str) 
    { 
    long hash = str.hashCode(); 
    hash <<= 32; 
    hash |= FNVHash1(str); 
    return hash; 
    } 
}

3）WIKI 

4）BOOST 

上一篇：emacs 插件 elpa 介绍
下一篇：没有了