/*-------------------------------------------------------------------------------lookup3.c, by Bob Jenkins, May 2006, Public Domain.These are functions for producing 32-bit hashes for hash table lookup.hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() are externally useful functions.  Routines to test the hash are included if SELF_TEST is defined.  You can use this free for any purpose.  It's inthe public domain.  It has no warranty.You probably want to use hashlittle().  hashlittle() and hashbig()hash byte arrays.  hashlittle() is is faster than hashbig() onlittle-endian machines.  Intel and AMD are little-endian machines.On second thought, you probably want hashlittle2(), which is identical tohashlittle() except it returns two 32-bit hashes for the price of one.  You could implement hashbig2() if you wanted but I haven't bothered here.If you want to find a hash of, say, exactly 7 integers, do  a = i1;  b = i2;  c = i3;  mix(a,b,c);  a += i4; b += i5; c += i6;  mix(a,b,c);  a += i7;  final(a,b,c);then use c as the hash value.  If you have a variable length array of4-byte integers to hash, use hashword().  If you have a byte array (likea character string), use hashlittle().  If you have several byte arrays, ora mix of things, see the comments above hashlittle().  Why is this so big?  I read 12 bytes at a time into 3 4-byte integers, then mix those integers.  This is fast (you can do a lot more thoroughmixing with 12*3 instructions on 3 integers than you can with 3 instructionson 1 byte), but shoehorning those bytes into integers efficiently is messy.-------------------------------------------------------------------------------*/#define SELF_TEST 1#include <stdio.h>      /* defines printf for tests */#include <time.h>       /* defines time_t for timings in the test */#include <stdint.h>     /* defines uint32_t etc */#include <sys/param.h>  /* attempt to define endianness */#ifdef linux# include <endian.h>    /* attempt to define endianness */#endif/* * My best guess at if you are big-endian or little-endian.  This may * need adjustment. */#if (defined(__BYTE_ORDER) && defined(__LITTLE_ENDIAN) && \     __BYTE_ORDER == __LITTLE_ENDIAN) || \    (defined(i386) || defined(__i386__) || defined(__i486__) || \     defined(__i586__) || defined(__i686__) || defined(vax) || defined(MIPSEL))# define HASH_LITTLE_ENDIAN 1# define HASH_BIG_ENDIAN 0#elif (defined(__BYTE_ORDER) && defined(__BIG_ENDIAN) && \       __BYTE_ORDER == __BIG_ENDIAN) || \      (defined(sparc) || defined(POWERPC) || defined(mc68000) || defined(sel))# define HASH_LITTLE_ENDIAN 0# define HASH_BIG_ENDIAN 1#else# define HASH_LITTLE_ENDIAN 0# define HASH_BIG_ENDIAN 0#endif#define hashsize(n) ((uint32_t)1<<(n))#define hashmask(n) (hashsize(n)-1)#define rot(x,k) (((x)<<(k)) | ((x)>>(32-(k))))/*-------------------------------------------------------------------------------mix -- mix 3 32-bit values reversibly.This is reversible, so any information in (a,b,c) before mix() isstill in (a,b,c) after mix().If four pairs of (a,b,c) inputs are run through mix(), or throughmix() in reverse, there are at least 32 bits of the output thatare sometimes the same for one pair and different for another pair.This was tested for:* pairs that differed by one bit, by two bits, in any combination  of top bits of (a,b,c), or in any combination of bottom bits of  (a,b,c).* "differ" is defined as +, -, ^, or ~^.  For + and -, I transformed  the output delta to a Gray code (a^(a>>1)) so a string of 1's (as  is commonly produced by subtraction) look like a single 1-bit  difference.* the base values were pseudorandom, all zero but one bit set, or   all zero plus a counter that starts at zero.Some k values for my "a-=c; a^=rot(c,k); c+=b;" arrangement thatsatisfy this are    4  6  8 16 19  4    9 15  3 18 27 15   14  9  3  7 17  3Well, "9 15 3 18 27 15" didn't quite get 32 bits diffingfor "differ" defined as + with a one-bit base and a two-bit delta.  Iused http://burtleburtle.net/bob/hash/avalanche.html to choose the operations, constants, and arrangements of the variables.This does not achieve avalanche.  There are input bits of (a,b,c)that fail to affect some output bits of (a,b,c), especially of a.  Themost thoroughly mixed value is c, but it doesn't really even achieveavalanche in c.This allows some parallelism.  Read-after-writes are good at doublingthe number of bits affected, so the goal of mixing pulls in the oppositedirection as the goal of parallelism.  I did what I could.  Rotatesseem to cost as much as shifts on every machine I could lay my handson, and rotates are much kinder to the top and bottom bits, so I usedrotates.-------------------------------------------------------------------------------*/#define mix(a,b,c) \{ \  a -= c;  a ^= rot(c, 4);  c += b; \  b -= a;  b ^= rot(a, 6);  a += c; \  c -= b;  c ^= rot(b, 8);  b += a; \  a -= c;  a ^= rot(c,16);  c += b; \  b -= a;  b ^= rot(a,19);  a += c; \  c -= b;  c ^= rot(b, 4);  b += a; \}/*-------------------------------------------------------------------------------final -- final mixing of 3 32-bit values (a,b,c) into cPairs of (a,b,c) values differing in only a few bits will usuallyproduce values of c that look totally different.  This was tested for* pairs that differed by one bit, by two bits, in any combination  of top bits of (a,b,c), or in any combination of bottom bits of  (a,b,c).* "differ" is defined as +, -, ^, or ~^.  For + and -, I transformed  the output delta to a Gray code (a^(a>>1)) so a string of 1's (as  is commonly produced by subtraction) look like a single 1-bit  difference.* the base values were pseudorandom, all zero but one bit set, or   all zero plus a counter that starts at zero.These constants passed: 14 11 25 16 4 14 24 12 14 25 16 4 14 24and these came close:  4  8 15 26 3 22 24 10  8 15 26 3 22 24 11  8 15 26 3 22 24-------------------------------------------------------------------------------*/#define final(a,b,c) \{ \  c ^= b; c -= rot(b,14); \  a ^= c; a -= rot(c,11); \  b ^= a; b -= rot(a,25); \  c ^= b; c -= rot(b,16); \  a ^= c; a -= rot(c,4);  \  b ^= a; b -= rot(a,14); \  c ^= b; c -= rot(b,24); \}/*-------------------------------------------------------------------- This works on all machines.  To be useful, it requires -- that the key be an array of uint32_t's, and -- that the length be the number of uint32_t's in the key The function hashword() is identical to hashlittle() on little-endian machines, and identical to hashbig() on big-endian machines, except that the length has to be measured in uint32_ts rather than in bytes.  hashlittle() is more complicated than hashword() only because hashlittle() has to dance around fitting the key bytes into registers.--------------------------------------------------------------------*/uint32_t hashword(const uint32_t *k,                   /* the key, an array of uint32_t values */size_t          length,               /* the length of the key, in uint32_ts */uint32_t        initval)         /* the previous hash, or an arbitrary value */{  uint32_t a,b,c;  /* Set up the internal state */  a = b = c = 0xdeadbeef + (((uint32_t)length)<<2) + initval;  /*------------------------------------------------- handle most of the key */  while (length > 3)  {    a += k[0];    b += k[1];    c += k[2];    mix(a,b,c);    length -= 3;    k += 3;  }  /*------------------------------------------- handle the last 3 uint32_t's */  switch(length)                     /* all the case statements fall through */  {   case 3 : c+=k[2];  case 2 : b+=k[1];  case 1 : a+=k[0];    final(a,b,c);  case 0:     /* case 0: nothing left to add */    break;  }  /*------------------------------------------------------ report the result */  return c;}/*--------------------------------------------------------------------hashword2() -- same as hashword(), but take two seeds and return two32-bit values.  pc and pb must both be nonnull, and *pc and *pb mustboth be initialized with seeds.  If you pass in (*pb)==0, the output (*pc) will be the same as the return value from hashword().--------------------------------------------------------------------*/void hashword2 (const uint32_t *k,                   /* the key, an array of uint32_t values */size_t          length,               /* the length of the key, in uint32_ts */uint32_t       *pc,                      /* IN: seed OUT: primary hash value */uint32_t       *pb)               /* IN: more seed OUT: secondary hash value */{  uint32_t a,b,c;  /* Set up the internal state */  a = b = c = 0xdeadbeef + ((uint32_t)(length<<2)) + *pc;  c += *pb;  /*------------------------------------------------- handle most of the key */  while (length > 3)  {    a += k[0];    b += k[1];    c += k[2];    mix(a,b,c);    length -= 3;    k += 3;  }  /*------------------------------------------- handle the last 3 uint32_t's */  switch(length)                     /* all the case statements fall through */  {   case 3 : c+=k[2];  case 2 : b+=k[1];  case 1 : a+=k[0];    final(a,b,c);  case 0:     /* case 0: nothing left to add */    break;  }  /*------------------------------------------------------ report the result */  *pc=c; *pb=b;}/*-------------------------------------------------------------------------------hashlittle() -- hash a variable-length key into a 32-bit value  k       : the key (the unaligned variable-length array of bytes)  length  : the length of the key, counting by bytes  initval : can be any 4-byte valueReturns a 32-bit value.  Every bit of the key affects every bit ofthe return value.  Two keys differing by one or two bits will havetotally different hash values.The best hash table sizes are powers of 2.  There is no need to domod a prime (mod is sooo slow!).  If you need less than 32 bits,use a bitmask.  For example, if you need only 10 bits, do  h = (h & hashmask(10));In which case, the hash table should have hashsize(10) elements.If you are hashing n strings (uint8_t **)k, do it like this:  for (i=0, h=0; i<n; ++i) h = hashlittle( k[i], len[i], h);By Bob Jenkins, 2006.  bob_jenkins@burtleburtle.net.  You may use thiscode any way you wish, private, educational, or commercial.  It's free.Use for hash table lookup, or anything where one collision in 2^^32 isacceptable.  Do NOT use for cryptographic purposes.-------------------------------------------------------------------------------*/uint32_t hashlittle( const void *key, size_t length, uint32_t initval){  uint32_t a,b,c;                                          /* internal state */  union { const void *ptr; size_t i; } u;     /* needed for Mac Powerbook G4 */  /* Set up the internal state */  a = b = c = 0xdeadbeef + ((uint32_t)length) + initval;  u.ptr = key;  if (HASH_LITTLE_ENDIAN && ((u.i & 0x3) == 0)) {    const uint32_t *k = (const uint32_t *)key;         /* read 32-bit chunks */    const uint8_t  *k8;    /*------ all but last block: aligned reads and affect 32 bits of (a,b,c) */    while (length > 12)    {      a += k[0];      b += k[1];      c += k[2];      mix(a,b,c);      length -= 12;      k += 3;    }    /*----------------------------- handle the last (probably partial) block */    /*      * "k[2]&0xffffff" actually reads beyond the end of the string, but     * then masks off the part it's not allowed to read.  Because the     * string is aligned, the masked-off tail is in the same word as the     * rest of the string.  Every machine with memory protection I've seen     * does it on word boundaries, so is OK with this.  But VALGRIND will     * still catch it and complain.  The masking trick does make the hash     * noticably faster for short strings (like English words).     */#ifndef VALGRIND    switch(length)    {    case 12: c+=k[2]; b+=k[1]; a+=k[0]; break;    case 11: c+=k[2]&0xffffff; b+=k[1]; a+=k[0]; break;    case 10: c+=k[2]&0xffff; b+=k[1]; a+=k[0]; break;    case 9 : c+=k[2]&0xff; b+=k[1]; a+=k[0]; break;    case 8 : b+=k[1]; a+=k[0]; break;    case 7 : b+=k[1]&0xffffff; a+=k[0]; break;    case 6 : b+=k[1]&0xffff; a+=k[0]; break;    case 5 : b+=k[1]&0xff; a+=k[0]; break;    case 4 : a+=k[0]; break;    case 3 : a+=k[0]&0xffffff; break;    case 2 : a+=k[0]&0xffff; break;    case 1 : a+=k[0]&0xff; break;    case 0 : return c;              /* zero length strings require no mixing */    }#else /* make valgrind happy */