From 4ec0f822a7c87da9eb95b6fd354d6d486e103a6e Mon Sep 17 00:00:00 2001 From: Isaac Turner Date: Tue, 19 Nov 2013 14:11:01 +0000 Subject: [PATCH] Added get_wordn, set_wordn functions; Merged lookup3.c; Exported BIT_MASK Added: uint8_t bit_array_get_wordn (const BIT_ARRAY* bitarr, bit_index_t start, int n) void bit_array_set_wordn (BIT_ARRAY* bitarr, bit_index_t start, uint64_t word, int n) Merged lookup3.c into bit_array.c Exported macros: word_t BIT_MASK(int nbits) word_t BIT_MASK_MERGE(word_t a, word_t b, int abits) --- Makefile | 4 +- README.md | 27 +- bit_array.c | 197 +++++++++----- bit_array.h | 15 ++ lookup3.c | 761 ---------------------------------------------------- lookup3.h | 95 ------- 6 files changed, 166 insertions(+), 933 deletions(-) delete mode 100644 lookup3.c delete mode 100644 lookup3.h diff --git a/Makefile b/Makefile index 084d9b9..0e765d7 100644 --- a/Makefile +++ b/Makefile @@ -12,8 +12,8 @@ CFLAGS = -Wall -Wextra -Wc++-compat -I. all: libbitarr.a dev examples -libbitarr.a: lookup3.o bit_array.o - ar -csru libbitarr.a bit_array.o lookup3.o +libbitarr.a: bit_array.o + ar -csru libbitarr.a bit_array.o %.o: %.c $(CC) $(OPT) $(CFLAGS) -c $< -o $@ diff --git a/README.md b/README.md index e49c322..50994fe 100644 --- a/README.md +++ b/README.md @@ -106,6 +106,14 @@ checking: bit_array_toggle(BIT_ARRAY *arr, bit_index_t i) bit_array_assign(BIT_ARRAY *arr, bit_index_t i, char c) +Get a word_t with the bottom `nbits` set to 1, the rest to 0: + + word_t BIT_MASK(int nbits) + +Combine two words with a mask `((a & abits) | (b & ~abits))`: + + word_t BIT_MASK_MERGE(word_t a, word_t b, int abits) + Set, clear and toggle several bits ---------------------------------- @@ -168,17 +176,22 @@ Set all 1 bits to 0, and all 0 bits to 1 (i.e. flip all the bits) Get / set a word ---------------- -Get a word of a given size. First bit is in the least significant bit position -start index must be within the range of the bit array (0 <= x < length) +Get a word of a given size. First bit is in the least significant bit position. +Index `start` must be within the range of the bit array (0 <= x < length) uint64_t bit_array_get_word64(const BIT_ARRAY* bitarr, bit_index_t start) uint32_t bit_array_get_word32(const BIT_ARRAY* bitarr, bit_index_t start) uint16_t bit_array_get_word16(const BIT_ARRAY* bitarr, bit_index_t start) uint8_t bit_array_get_word8 (const BIT_ARRAY* bitarr, bit_index_t start) + uint8_t bit_array_get_wordn (const BIT_ARRAY* bitarr, bit_index_t start, int n) Set 64 bits at once from a particular start position void bit_array_set_word64(BIT_ARRAY* bitarr, bit_index_t start, uint64_t word) + void bit_array_set_word32(BIT_ARRAY* bitarr, bit_index_t start, uint32_t word) + void bit_array_set_word16(BIT_ARRAY* bitarr, bit_index_t start, uint16_t word) + void bit_array_set_word8 (BIT_ARRAY* bitarr, bit_index_t start, uint8_t word) + void bit_array_set_wordn (BIT_ARRAY* bitarr, bit_index_t start, uint64_t word, int n) Count bits set -------------- @@ -581,12 +594,12 @@ Contributing Please feel free to submit issues and pull requests. I appreciate bug reports. Methods are named: - _name() - indicates only used internally - _bit_array_name() - exported and wrapped in a #define in the header - bit_array_name - exported as is +* `_name()` indicates only used internally +* `_bit_array_name()` exported and wrapped in a #define in the header +* `bit_array_name()` exported as is -_bit_array_name() functions are wrapped in a #define to allow reporting of file -and line number of offending call in the case of an out of bounds error etc. +`_bit_array_name()` functions are wrapped in a `#define` to allow reporting of +file and line number of offending call in the case of an out of bounds error etc. Testing on different platforms is especially appreciated. I only have access to Mac OS X and Linux. diff --git a/bit_array.c b/bit_array.c index c2b2098..32d626e 100644 --- a/bit_array.c +++ b/bit_array.c @@ -47,7 +47,6 @@ #endif #include "bit_array.h" -#include "lookup3.h" // // Tables of constants @@ -238,10 +237,6 @@ static word_t __inline windows_parity(word_t w) // if w == 0 return WORD_SIZE, otherwise index of top bit set #define TOP_BIT_SET(w) (w == 0 ? WORD_SIZE : WORD_SIZE - LEADING_ZEROS(w) - 1) -// WORD_MAX >> (WORD_SIZE-(length)) gives WORD_MAX instead of 0 if length is 0 -// need to check for length == 0 -#define BIT_MASK(length) (length == 0 ? (word_t)0 : WORD_MAX >> (WORD_SIZE-(length))) - // Index of word #define bindex(b) ((b) / WORD_SIZE) @@ -252,10 +247,6 @@ static word_t __inline windows_parity(word_t w) #define CLEAR_REGION(arr,start,len) _set_region((arr),(start),(len),ZERO_REGION) #define TOGGLE_REGION(arr,start,len) _set_region((arr),(start),(len),SWAP_REGION) -// A possibly faster way to combine two words with a mask -//#define MASK_MERGE(a,b,abits) ((a & abits) | (b & ~abits)) -#define MASK_MERGE(a,b,abits) (b ^ ((a ^ b) & abits)) - // Have we initialised with srand() ? static char rand_initiated = 0; @@ -315,6 +306,24 @@ static inline char* _word_to_str(word_t word, char str[WORD_SIZE+1]) return str; } +// Error reporting code +void call_die(const char *file, int line, const char *fmt, ...) +__attribute__((format(printf, 3, 4))) +__attribute__((noreturn)); + +void call_die(const char *file, int line, const char *fmt, ...) +{ + va_list argptr; + fflush(stdout); + fprintf(stderr, "[%s:%i] Error: ", file, line); + va_start(argptr, fmt); + vfprintf(stderr, fmt, argptr); + va_end(argptr); + if(*(fmt + strlen(fmt) - 1) != '\n') fputc('\n', stderr); + kill(getpid(), SIGABRT); + exit(EXIT_FAILURE); +} + // Used in debugging #define VALIDATE_BIT_ARRAY(a) validate_bitarr((a), __FILE__, __LINE__) @@ -326,28 +335,20 @@ void validate_bitarr(BIT_ARRAY *arr, char *file, int lineno) if(arr->words[tw] > BIT_MASK(top_bits)) { - fprintf(stderr, "%s:%i:VALIDATE_BIT_ARRAY(): Fail -- " - "expected %i bits in top word[%i]:\n", - file, lineno, (int)top_bits, (int)tw); - _print_word(arr->words[tw], stderr); fprintf(stderr, "\n"); - - kill(getpid(), SIGABRT); - // exit(EXIT_FAILURE); + call_die(file, lineno, "VALIDATE_BIT_ARRAY(): Fail -- " + "expected %i bits in top word[%i]:\n", + (int)top_bits, (int)tw); } // Check num of words is correct word_addr_t num_words = nwords(arr->num_of_bits); if(num_words != arr->num_of_words) { - fprintf(stderr, "%s:%i:VALIDATE_BIT_ARRAY(): Fail -- num of words wrong " - "[bits: %i, word: %i, actual words: %i]\n", - file, lineno, - (int)arr->num_of_bits, (int)num_words, (int)arr->num_of_words); - - kill(getpid(), SIGABRT); - // exit(EXIT_FAILURE); + call_die(file, lineno, "VALIDATE_BIT_ARRAY(): Fail -- num of words wrong " + "[bits: %i, word: %i, actual words: %i]\n", + (int)arr->num_of_bits, (int)num_words, (int)arr->num_of_words); } } @@ -384,30 +385,8 @@ static inline void _bounds_check_start(const BIT_ARRAY* bitarr, { if(start >= bitarr->num_of_bits) { - fprintf(stderr, "%s:%i:%s() - out of bounds error " - "(index: %lu, num_of_bits: %lu)\n", - file, line, func, - (unsigned long)start, (unsigned long)bitarr->num_of_bits); - kill(getpid(), SIGABRT); - // errno = EDOM; - // exit(EXIT_FAILURE); - } -} - -static inline void _bounds_check_length(const BIT_ARRAY* bitarr, - bit_index_t length, - const char* file, int line, - const char* func) -{ - if(length > bitarr->num_of_bits) - { - fprintf(stderr, "%s:%i:%s() - out of bounds error " - "(length: %lu, num_of_bits: %lu)\n", - file, line, func, - (unsigned long)length, (unsigned long)bitarr->num_of_bits); - kill(getpid(), SIGABRT); - // errno = EDOM; - // exit(EXIT_FAILURE); + call_die(file, line, "%s() - out of bounds error (index: %zu, num_of_bits: %zu)", + func, (size_t)start, (size_t)bitarr->num_of_bits); } } @@ -418,14 +397,10 @@ static inline void _bounds_check_offset(const BIT_ARRAY* bitarr, { if(start + len > bitarr->num_of_bits) { - fprintf(stderr, "%s:%i:%s() - out of bounds error " - "(start: %lu; length: %lu; num_of_bits: %lu)\n", - file, line, func, - (unsigned long)start, (unsigned long)len, - (unsigned long)bitarr->num_of_bits); - kill(getpid(), SIGABRT); - // errno = EDOM; - // exit(EXIT_FAILURE); + call_die(file, line, "%s() - out of bounds error " + "(start: %zu; length: %zu; num_of_bits: %zu)\n", + func, (size_t)start, (size_t)len, + (size_t)bitarr->num_of_bits); } } @@ -537,7 +512,7 @@ static inline void _set_word_cyclic(BIT_ARRAY* bitarr, word_offset_t bits_remaining = MIN(WORD_SIZE - bits_set, start); word_t mask = BIT_MASK(bits_remaining); - bitarr->words[0] = MASK_MERGE(word, bitarr->words[0], mask); + bitarr->words[0] = BIT_MASK_MERGE(word, bitarr->words[0], mask); } } @@ -1016,7 +991,6 @@ uint64_t _bit_array_get_word64(const char *file, int line, { // Bounds checking _bounds_check_start(bitarr, start, file, line, "bit_array_word64"); - return (uint64_t)_get_word(bitarr, start); } @@ -1026,7 +1000,6 @@ uint32_t _bit_array_get_word32(const char *file, int line, { // Bounds checking _bounds_check_start(bitarr, start, file, line, "bit_array_word32"); - return (uint32_t)_get_word(bitarr, start); } @@ -1036,7 +1009,6 @@ uint16_t _bit_array_get_word16(const char *file, int line, { // Bounds checking _bounds_check_start(bitarr, start, file, line, "bit_array_word16"); - return (uint16_t)_get_word(bitarr, start); } @@ -1046,10 +1018,19 @@ uint8_t _bit_array_get_word8(const char *file, int line, { // Bounds checking _bounds_check_start(bitarr, start, file, line, "bit_array_word8"); - return (uint8_t)_get_word(bitarr, start); } +uint64_t _bit_array_get_wordn(const char *file, int line, + const BIT_ARRAY* bitarr, + bit_index_t start, int n) +{ + // Bounds checking + _bounds_check_start(bitarr, start, file, line, "bit_array_wordn"); + if(n > 64) call_die(file, line, "_bit_array_get_wordn(): n > 64"); + return (uint64_t)(_get_word(bitarr, start) & BIT_MASK(n)); +} + // // Set a word at a time // @@ -1060,7 +1041,6 @@ void _bit_array_set_word64(const char *file, int line, { // Bounds checking _bounds_check_start(bitarr, start, file, line, "bit_array_set_word64"); - _set_word(bitarr, start, (word_t)word); } @@ -1070,7 +1050,6 @@ void _bit_array_set_word32(const char *file, int line, { // Bounds checking _bounds_check_start(bitarr, start, file, line, "bit_array_set_word32"); - word_t w = _get_word(bitarr, start); _set_word(bitarr, start, (w & ~(word_t)0xffffffff) | word); } @@ -1081,7 +1060,6 @@ void _bit_array_set_word16(const char *file, int line, { // Bounds checking _bounds_check_start(bitarr, start, file, line, "bit_array_set_word16"); - word_t w = _get_word(bitarr, start); _set_word(bitarr, start, (w & ~(word_t)0xffff) | word); } @@ -1092,10 +1070,19 @@ void _bit_array_set_word8(const char *file, int line, { // Bounds checking _bounds_check_start(bitarr, start, file, line, "bit_array_set_word8"); - _set_byte(bitarr, start, byte); } +void _bit_array_set_wordn(const char *file, int line, + BIT_ARRAY* bitarr, + bit_index_t start, uint64_t word, int n) +{ + // Bounds checking + _bounds_check_start(bitarr, start, file, line, "bit_array_set_wordn"); + word_t w = _get_word(bitarr, start), m = BIT_MASK(n); + _set_word(bitarr, start, BIT_MASK_MERGE(word,w,m)); +} + // // Number/position of bits set // @@ -1610,7 +1597,7 @@ static void _array_copy(BIT_ARRAY* dst, bit_index_t dstindx, word_t dst_word = _get_word(dst, dstindx+i*WORD_SIZE); word_t mask = BIT_MASK(bits_in_last_word); - word_t word = MASK_MERGE(src_word, dst_word, mask); + word_t word = BIT_MASK_MERGE(src_word, dst_word, mask); _set_word(dst, dstindx+num_of_full_words*WORD_SIZE, word); } @@ -1639,7 +1626,7 @@ static void _array_copy(BIT_ARRAY* dst, bit_index_t dstindx, word_t dst_word = _get_word(dst, dstindx); word_t mask = BIT_MASK(bits_in_last_word); - word_t word = MASK_MERGE(src_word, dst_word, mask); + word_t word = BIT_MASK_MERGE(src_word, dst_word, mask); _set_word(dst, dstindx, word); } } @@ -2030,7 +2017,7 @@ static void _reverse_region(BIT_ARRAY* bitarr, rev >>= WORD_SIZE - length; word_t mask = BIT_MASK(length); - word = MASK_MERGE(rev, word, mask); + word = BIT_MASK_MERGE(rev, word, mask); _set_word_cyclic(bitarr, left, word); } @@ -2041,7 +2028,7 @@ void _bit_array_reverse_region(const char *file, int line, { // Bounds checking _bounds_check_start(bitarr, start, file, line, "bit_array_reverse_region"); - _bounds_check_length(bitarr, length, file, line, "bit_array_reverse_region"); + _bounds_check_offset(bitarr, start, length, file, line, "bit_array_reverse_region"); if(length > 0) { @@ -3382,6 +3369,80 @@ char bit_array_load(BIT_ARRAY* bitarr, FILE* f) // Hash function // +/* From: lookup3.c, by Bob Jenkins, May 2006, Public Domain. */ +#define hashsize(n) ((uint32_t)1<<(n)) +#define hashmask(n) (hashsize(n)-1) +#define rot(x,k) (((x)<<(k)) | ((x)>>(32-(k)))) + +/* From: lookup3.c, by Bob Jenkins, May 2006, Public Domain. */ +#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; \ +} + +/* From: lookup3.c, by Bob Jenkins, May 2006, Public Domain. */ +#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); \ +} + +/* +From: lookup3.c, by Bob Jenkins, May 2006, Public Domain. +-------------------------------------------------------------------- +hashword2() -- same as hashword(), but take two seeds and return two +32-bit values. pc and pb must both be nonnull, and *pc and *pb must +both be initialized with seeds. If you pass in (*pb)==0, the output +(*pc) will be the same as the return value from hashword(). +-------------------------------------------------------------------- +*/ +static 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; +} + // Pass seed as 0 on first call, pass previous hash value if rehashing due // to a collision // Using bob jenkins hash lookup3 diff --git a/bit_array.h b/bit_array.h index b3a5c73..7a00686 100644 --- a/bit_array.h +++ b/bit_array.h @@ -87,6 +87,14 @@ char bit_array_ensure_size(BIT_ARRAY* bitarr, bit_index_t ensure_num_of_bits); // Macros // +// WORD_MAX >> (WORD_SIZE-(length)) gives WORD_MAX instead of 0 if length is 0 +// need to check for length == 0 +#define BIT_MASK(nbits) (nbits ? ~(word_t)0 >> (sizeof(word_t)*8-(nbits)) : (word_t)0) + +// A possibly faster way to combine two words with a mask +//#define BIT_MASK_MERGE(a,b,abits) ((a & abits) | (b & ~abits)) +#define BIT_MASK_MERGE(a,b,abits) (b ^ ((a ^ b) & abits)) + // Macros for fast access -- beware: no bounds checking #define bit_array_get(arr,i) (((arr)->words[(i)/64] >> ((i) % 64)) & 0x1) #define bit_array_set(arr,i) ((arr)->words[(i)/64] |= ((word_t)1 << ((i) % 64))) @@ -113,11 +121,13 @@ char bit_array_ensure_size(BIT_ARRAY* bitarr, bit_index_t ensure_num_of_bits); #define bit_array_get_word32(bitarr,start) _bit_array_get_word32(__FILE__,__LINE__,bitarr,start) #define bit_array_get_word16(bitarr,start) _bit_array_get_word16(__FILE__,__LINE__,bitarr,start) #define bit_array_get_word8(bitarr,start) _bit_array_get_word8(__FILE__,__LINE__,bitarr,start) +#define bit_array_get_wordn(bitarr,start,n) _bit_array_get_wordn(__FILE__,__LINE__,bitarr,start,n) #define bit_array_set_word64(bitarr,start,word) _bit_array_set_word64(__FILE__,__LINE__,bitarr,start,word) #define bit_array_set_word32(bitarr,start,word) _bit_array_set_word32(__FILE__,__LINE__,bitarr,start,word) #define bit_array_set_word16(bitarr,start,word) _bit_array_set_word16(__FILE__,__LINE__,bitarr,start,word) #define bit_array_set_word8(bitarr,start,word) _bit_array_set_word8(__FILE__,__LINE__,bitarr,start,word) +#define bit_array_set_wordn(bitarr,start,word,n) _bit_array_set_wordn(__FILE__,__LINE__,bitarr,start,word,n) #define bit_array_reverse_region(arr,start,len) \ _bit_array_reverse_region(__FILE__,__LINE__,arr,start,len) @@ -244,6 +254,8 @@ uint16_t _bit_array_get_word16(const char *file, int line, const BIT_ARRAY* bitarr, bit_index_t start); uint8_t _bit_array_get_word8(const char *file, int line, const BIT_ARRAY* bitarr, bit_index_t start); +uint64_t _bit_array_get_wordn(const char *file, int line, + const BIT_ARRAY* bitarr, bit_index_t start, int n); // Set 64 bits at once from a particular start position void _bit_array_set_word64(const char *file, int line, @@ -254,6 +266,9 @@ void _bit_array_set_word16(const char *file, int line, BIT_ARRAY* bitarr, bit_index_t start, uint16_t word); void _bit_array_set_word8(const char *file, int line, BIT_ARRAY* bitarr, bit_index_t start, uint8_t byte); +void _bit_array_set_wordn(const char *file, int line, + BIT_ARRAY* bitarr, bit_index_t start, + uint64_t word, int n); // // Number of bits set diff --git a/lookup3.c b/lookup3.c deleted file mode 100644 index 16bb5b4..0000000 --- a/lookup3.c +++ /dev/null @@ -1,761 +0,0 @@ -/* -------------------------------------------------------------------------------- -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 in -the public domain. It has no warranty. - -You probably want to use hashlittle(). hashlittle() and hashbig() -hash byte arrays. hashlittle() is is faster than hashbig() on -little-endian machines. Intel and AMD are little-endian machines. -On second thought, you probably want hashlittle2(), which is identical to -hashlittle() 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 of -4-byte integers to hash, use hashword(). If you have a byte array (like -a character string), use hashlittle(). If you have several byte arrays, or -a 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 thorough -mixing with 12*3 instructions on 3 integers than you can with 3 instructions -on 1 byte), but shoehorning those bytes into integers efficiently is messy. -------------------------------------------------------------------------------- -*/ -#define SELF_TEST 1 - -#include /* defines printf for tests */ -#include /* defines time_t for timings in the test */ -#include /* defines uint32_t etc */ -#include /* attempt to define endianness */ -#ifdef linux -# include /* 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() is -still in (a,b,c) after mix(). - -If four pairs of (a,b,c) inputs are run through mix(), or through -mix() in reverse, there are at least 32 bits of the output that -are 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 that -satisfy this are - 4 6 8 16 19 4 - 9 15 3 18 27 15 - 14 9 3 7 17 3 -Well, "9 15 3 18 27 15" didn't quite get 32 bits diffing -for "differ" defined as + with a one-bit base and a two-bit delta. I -used 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. The -most thoroughly mixed value is c, but it doesn't really even achieve -avalanche in c. - -This allows some parallelism. Read-after-writes are good at doubling -the number of bits affected, so the goal of mixing pulls in the opposite -direction as the goal of parallelism. I did what I could. Rotates -seem to cost as much as shifts on every machine I could lay my hands -on, and rotates are much kinder to the top and bottom bits, so I used -rotates. -------------------------------------------------------------------------------- -*/ -#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 c - -Pairs of (a,b,c) values differing in only a few bits will usually -produce 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 24 -and 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 two -32-bit values. pc and pb must both be nonnull, and *pc and *pb must -both 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 value -Returns a 32-bit value. Every bit of the key affects every bit of -the return value. Two keys differing by one or two bits will have -totally different hash values. - -The best hash table sizes are powers of 2. There is no need to do -mod 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 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 */ - - const uint8_t k8 = (const uint8_t *)k; - switch(length) - { - case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; - case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ - case 10: c+=((uint32_t)k8[9])<<8; /* fall through */ - case 9 : c+=k8[8]; /* fall through */ - case 8 : b+=k[1]; a+=k[0]; break; - case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ - case 6 : b+=((uint32_t)k8[5])<<8; /* fall through */ - case 5 : b+=k8[4]; /* fall through */ - case 4 : a+=k[0]; break; - case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ - case 2 : a+=((uint32_t)k8[1])<<8; /* fall through */ - case 1 : a+=k8[0]; break; - case 0 : return c; - } - -#endif /* !valgrind */ - - } else if (HASH_LITTLE_ENDIAN && ((u.i & 0x1) == 0)) { - const uint16_t *k = (const uint16_t *)key; /* read 16-bit chunks */ - const uint8_t *k8; - - /*--------------- all but last block: aligned reads and different mixing */ - while (length > 12) - { - a += k[0] + (((uint32_t)k[1])<<16); - b += k[2] + (((uint32_t)k[3])<<16); - c += k[4] + (((uint32_t)k[5])<<16); - mix(a,b,c); - length -= 12; - k += 6; - } - - /*----------------------------- handle the last (probably partial) block */ - k8 = (const uint8_t *)k; - switch(length) - { - case 12: c+=k[4]+(((uint32_t)k[5])<<16); - b+=k[2]+(((uint32_t)k[3])<<16); - a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ - case 10: c+=k[4]; - b+=k[2]+(((uint32_t)k[3])<<16); - a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 9 : c+=k8[8]; /* fall through */ - case 8 : b+=k[2]+(((uint32_t)k[3])<<16); - a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ - case 6 : b+=k[2]; - a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 5 : b+=k8[4]; /* fall through */ - case 4 : a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ - case 2 : a+=k[0]; - break; - case 1 : a+=k8[0]; - break; - case 0 : return c; /* zero length requires no mixing */ - } - - } else { /* need to read the key one byte at a time */ - const uint8_t *k = (const uint8_t *)key; - - /*--------------- all but the last block: affect some 32 bits of (a,b,c) */ - while (length > 12) - { - a += k[0]; - a += ((uint32_t)k[1])<<8; - a += ((uint32_t)k[2])<<16; - a += ((uint32_t)k[3])<<24; - b += k[4]; - b += ((uint32_t)k[5])<<8; - b += ((uint32_t)k[6])<<16; - b += ((uint32_t)k[7])<<24; - c += k[8]; - c += ((uint32_t)k[9])<<8; - c += ((uint32_t)k[10])<<16; - c += ((uint32_t)k[11])<<24; - mix(a,b,c); - length -= 12; - k += 12; - } - - /*-------------------------------- last block: affect all 32 bits of (c) */ - switch(length) /* all the case statements fall through */ - { - case 12: c+=((uint32_t)k[11])<<24; - case 11: c+=((uint32_t)k[10])<<16; - case 10: c+=((uint32_t)k[9])<<8; - case 9 : c+=k[8]; - case 8 : b+=((uint32_t)k[7])<<24; - case 7 : b+=((uint32_t)k[6])<<16; - case 6 : b+=((uint32_t)k[5])<<8; - case 5 : b+=k[4]; - case 4 : a+=((uint32_t)k[3])<<24; - case 3 : a+=((uint32_t)k[2])<<16; - case 2 : a+=((uint32_t)k[1])<<8; - case 1 : a+=k[0]; - break; - case 0 : return c; - } - } - - final(a,b,c); - return c; -} - - -/* - * hashlittle2: return 2 32-bit hash values - * - * This is identical to hashlittle(), except it returns two 32-bit hash - * values instead of just one. This is good enough for hash table - * lookup with 2^^64 buckets, or if you want a second hash if you're not - * happy with the first, or if you want a probably-unique 64-bit ID for - * the key. *pc is better mixed than *pb, so use *pc first. If you want - * a 64-bit value do something like "*pc + (((uint64_t)*pb)<<32)". - */ -void hashlittle2( - const void *key, /* the key to hash */ - size_t length, /* length of the key */ - uint32_t *pc, /* IN: primary initval, OUT: primary hash */ - uint32_t *pb) /* IN: secondary initval, OUT: secondary hash */ -{ - 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) + *pc; - c += *pb; - - u.ptr = key; - if (HASH_LITTLE_ENDIAN && ((u.i & 0x3) == 0)) { - const uint32_t *k = (const uint32_t *)key; /* read 32-bit chunks */ - - /*------ 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 : *pc=c; *pb=b; return; /* zero length strings require no mixing */ - } - -#else /* make valgrind happy */ - - const uint8_t *k8 = (const uint8_t *)k; - switch(length) - { - case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; - case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ - case 10: c+=((uint32_t)k8[9])<<8; /* fall through */ - case 9 : c+=k8[8]; /* fall through */ - case 8 : b+=k[1]; a+=k[0]; break; - case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ - case 6 : b+=((uint32_t)k8[5])<<8; /* fall through */ - case 5 : b+=k8[4]; /* fall through */ - case 4 : a+=k[0]; break; - case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ - case 2 : a+=((uint32_t)k8[1])<<8; /* fall through */ - case 1 : a+=k8[0]; break; - case 0 : *pc=c; *pb=b; return; /* zero length strings require no mixing */ - } - -#endif /* !valgrind */ - - } else if (HASH_LITTLE_ENDIAN && ((u.i & 0x1) == 0)) { - const uint16_t *k = (const uint16_t *)key; /* read 16-bit chunks */ - const uint8_t *k8; - - /*--------------- all but last block: aligned reads and different mixing */ - while (length > 12) - { - a += k[0] + (((uint32_t)k[1])<<16); - b += k[2] + (((uint32_t)k[3])<<16); - c += k[4] + (((uint32_t)k[5])<<16); - mix(a,b,c); - length -= 12; - k += 6; - } - - /*----------------------------- handle the last (probably partial) block */ - k8 = (const uint8_t *)k; - switch(length) - { - case 12: c+=k[4]+(((uint32_t)k[5])<<16); - b+=k[2]+(((uint32_t)k[3])<<16); - a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ - case 10: c+=k[4]; - b+=k[2]+(((uint32_t)k[3])<<16); - a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 9 : c+=k8[8]; /* fall through */ - case 8 : b+=k[2]+(((uint32_t)k[3])<<16); - a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ - case 6 : b+=k[2]; - a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 5 : b+=k8[4]; /* fall through */ - case 4 : a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ - case 2 : a+=k[0]; - break; - case 1 : a+=k8[0]; - break; - case 0 : *pc=c; *pb=b; return; /* zero length strings require no mixing */ - } - - } else { /* need to read the key one byte at a time */ - const uint8_t *k = (const uint8_t *)key; - - /*--------------- all but the last block: affect some 32 bits of (a,b,c) */ - while (length > 12) - { - a += k[0]; - a += ((uint32_t)k[1])<<8; - a += ((uint32_t)k[2])<<16; - a += ((uint32_t)k[3])<<24; - b += k[4]; - b += ((uint32_t)k[5])<<8; - b += ((uint32_t)k[6])<<16; - b += ((uint32_t)k[7])<<24; - c += k[8]; - c += ((uint32_t)k[9])<<8; - c += ((uint32_t)k[10])<<16; - c += ((uint32_t)k[11])<<24; - mix(a,b,c); - length -= 12; - k += 12; - } - - /*-------------------------------- last block: affect all 32 bits of (c) */ - switch(length) /* all the case statements fall through */ - { - case 12: c+=((uint32_t)k[11])<<24; - case 11: c+=((uint32_t)k[10])<<16; - case 10: c+=((uint32_t)k[9])<<8; - case 9 : c+=k[8]; - case 8 : b+=((uint32_t)k[7])<<24; - case 7 : b+=((uint32_t)k[6])<<16; - case 6 : b+=((uint32_t)k[5])<<8; - case 5 : b+=k[4]; - case 4 : a+=((uint32_t)k[3])<<24; - case 3 : a+=((uint32_t)k[2])<<16; - case 2 : a+=((uint32_t)k[1])<<8; - case 1 : a+=k[0]; - break; - case 0 : *pc=c; *pb=b; return; /* zero length strings require no mixing */ - } - } - - final(a,b,c); - *pc=c; *pb=b; -} - - - -/* - * hashbig(): - * This is the same as hashword() on big-endian machines. It is different - * from hashlittle() on all machines. hashbig() takes advantage of - * big-endian byte ordering. - */ -uint32_t hashbig( const void *key, size_t length, uint32_t initval) -{ - uint32_t a,b,c; - union { const void *ptr; size_t i; } u; /* to cast key to (size_t) happily */ - - /* Set up the internal state */ - a = b = c = 0xdeadbeef + ((uint32_t)length) + initval; - - u.ptr = key; - if (HASH_BIG_ENDIAN && ((u.i & 0x3) == 0)) { - const uint32_t *k = (const uint32_t *)key; /* read 32-bit chunks */ - - /*------ 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]<<8" actually reads beyond the end of the string, but - * then shifts out the part it's not allowed to read. Because the - * string is aligned, the illegal read 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]&0xffffff00; b+=k[1]; a+=k[0]; break; - case 10: c+=k[2]&0xffff0000; b+=k[1]; a+=k[0]; break; - case 9 : c+=k[2]&0xff000000; b+=k[1]; a+=k[0]; break; - case 8 : b+=k[1]; a+=k[0]; break; - case 7 : b+=k[1]&0xffffff00; a+=k[0]; break; - case 6 : b+=k[1]&0xffff0000; a+=k[0]; break; - case 5 : b+=k[1]&0xff000000; a+=k[0]; break; - case 4 : a+=k[0]; break; - case 3 : a+=k[0]&0xffffff00; break; - case 2 : a+=k[0]&0xffff0000; break; - case 1 : a+=k[0]&0xff000000; break; - case 0 : return c; /* zero length strings require no mixing */ - } - -#else /* make valgrind happy */ - - const uint8_t *k8 = (const uint8_t *)k; - switch(length) /* all the case statements fall through */ - { - case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; - case 11: c+=((uint32_t)k8[10])<<8; /* fall through */ - case 10: c+=((uint32_t)k8[9])<<16; /* fall through */ - case 9 : c+=((uint32_t)k8[8])<<24; /* fall through */ - case 8 : b+=k[1]; a+=k[0]; break; - case 7 : b+=((uint32_t)k8[6])<<8; /* fall through */ - case 6 : b+=((uint32_t)k8[5])<<16; /* fall through */ - case 5 : b+=((uint32_t)k8[4])<<24; /* fall through */ - case 4 : a+=k[0]; break; - case 3 : a+=((uint32_t)k8[2])<<8; /* fall through */ - case 2 : a+=((uint32_t)k8[1])<<16; /* fall through */ - case 1 : a+=((uint32_t)k8[0])<<24; break; - case 0 : return c; - } - -#endif /* !VALGRIND */ - - } else { /* need to read the key one byte at a time */ - const uint8_t *k = (const uint8_t *)key; - - /*--------------- all but the last block: affect some 32 bits of (a,b,c) */ - while (length > 12) - { - a += ((uint32_t)k[0])<<24; - a += ((uint32_t)k[1])<<16; - a += ((uint32_t)k[2])<<8; - a += ((uint32_t)k[3]); - b += ((uint32_t)k[4])<<24; - b += ((uint32_t)k[5])<<16; - b += ((uint32_t)k[6])<<8; - b += ((uint32_t)k[7]); - c += ((uint32_t)k[8])<<24; - c += ((uint32_t)k[9])<<16; - c += ((uint32_t)k[10])<<8; - c += ((uint32_t)k[11]); - mix(a,b,c); - length -= 12; - k += 12; - } - - /*-------------------------------- last block: affect all 32 bits of (c) */ - switch(length) /* all the case statements fall through */ - { - case 12: c+=k[11]; - case 11: c+=((uint32_t)k[10])<<8; - case 10: c+=((uint32_t)k[9])<<16; - case 9 : c+=((uint32_t)k[8])<<24; - case 8 : b+=k[7]; - case 7 : b+=((uint32_t)k[6])<<8; - case 6 : b+=((uint32_t)k[5])<<16; - case 5 : b+=((uint32_t)k[4])<<24; - case 4 : a+=k[3]; - case 3 : a+=((uint32_t)k[2])<<8; - case 2 : a+=((uint32_t)k[1])<<16; - case 1 : a+=((uint32_t)k[0])<<24; - break; - case 0 : return c; - } - } - - final(a,b,c); - return c; -} diff --git a/lookup3.h b/lookup3.h deleted file mode 100644 index f7483b8..0000000 --- a/lookup3.h +++ /dev/null @@ -1,95 +0,0 @@ -/* -------------------------------------------------------------------------------- -Header file for lookup3.c -lookup3.c, by Bob Jenkins, May 2006, Public Domain. -http://burtleburtle.net/bob/c/lookup3.c -------------------------------------------------------------------------------- -*/ - -#include /* defines uint32_t etc */ - -/* --------------------------------------------------------------------- - 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 */ - -/* --------------------------------------------------------------------- -hashword2() -- same as hashword(), but take two seeds and return two -32-bit values. pc and pb must both be nonnull, and *pc and *pb must -both 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 */ - -/* -------------------------------------------------------------------------------- -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 value -Returns a 32-bit value. Every bit of the key affects every bit of -the return value. Two keys differing by one or two bits will have -totally different hash values. - -The best hash table sizes are powers of 2. There is no need to do -mod 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