Permalink
Browse files

Basic implementation is done.

  • Loading branch information...
1 parent 5bf6dc9 commit 06da1cbd1b45b9d9a4a234f6c8791707b9b4a5a3 Andrei Zmievski committed Mar 16, 2009
Showing with 1,320 additions and 51 deletions.
  1. +80 −33 bloom.c
  2. +17 −2 bloom.h
  3. +1 −1 config.m4
  4. +1,001 −0 lookup3.c
  5. +220 −4 php_bloomy.c
  6. +1 −11 php_bloomy.h
View
113 bloom.c
@@ -19,30 +19,45 @@
#include <stdio.h>
#include <string.h>
#include <math.h>
+#include "php.h"
+
+#define BITS_PER_CHAR 8
+#define BITS_CHAR_SHIFT 3
+#define MAX_HASHES 50
+
+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 */
+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 */
+
+static void bloom_gen_salts(bloom_t *bloom)
+{
+ int i, num_salts = 2;
+ uint32_t salt;
+ uint32_t* salts[2] = { &bloom->salt1, &bloom->salt2 };
+
+ for (i = 0; i < num_salts; i++) {
+ salt = ((uint32_t)rand() ^ (uint32_t)rand());
+ if (salt == 0) continue;
+ *salts[i] = salt;
+ }
+}
-#define BITS_PER_CHAR 8
-#define MAX_HASHES 50
-
-struct _filter_spec_t {
- size_t filter_size;
- uint8_t num_hashes;
-};
-
-struct _bloom_t {
- uint8_t *filter;
- struct _filter_spec_t spec;
-
- double max_error_rate;
- size_t num_elements;
-
- uint32_t salt1;
- uint32_t salt2;
-};
-
-static void bloom_calc_salts(bloom_t *bloom)
+static void bloom_hash(bloom_t *bloom, const char *data, size_t data_len, uint32_t *hash1, uint32_t *hash2)
{
- if (!bloom) {
- return;
+ *hash1 = bloom->salt1;
+ *hash2 = bloom->salt2;
+
+ if ((data_len & 0x3) == 0) {
+ hashword2((uint32_t *)data, data_len / 4, hash1, hash2);
+ } else {
+ hashlittle2((void *)data, data_len, hash1, hash2);
}
}
@@ -70,28 +85,67 @@ bloom_return bloom_init(bloom_t *bloom, size_t num_elements, double max_error_ra
return status;
}
- bloom->filter = (uint8_t *)ecalloc(spec.filter_size / BITS_PER_CHAR, sizeof(uint8_t));
+ bloom->filter = (uint8_t *)safe_emalloc(spec.filter_size / BITS_PER_CHAR, sizeof(uint8_t), 0);
+ memset(bloom->filter, 0, spec.filter_size / BITS_PER_CHAR * sizeof(uint8_t));
bloom->spec = spec;
bloom->max_error_rate = max_error_rate;
+ bloom_gen_salts(bloom);
+
return BLOOM_SUCCESS;
}
void bloom_clean(bloom_t *bloom)
{
if (!bloom) {
- return BLOOM_BADARG;
+ return;
}
- efree(bloom->filter);
+ if (bloom->filter) {
+ efree(bloom->filter);
+ }
}
bloom_return bloom_add(bloom_t *bloom, const char *data, size_t data_len)
{
+ int i;
+ uint32_t hash1, hash2;
+ uint32_t index;
+
+ if (!bloom || !data || data_len == 0) {
+ return BLOOM_BADARG;
+ }
+
+ bloom_hash(bloom, data, data_len, &hash1, &hash2);
+ for (i = 0; i < bloom->spec.num_hashes; i++) {
+ index = (hash1 + i * hash2) % bloom->spec.filter_size;
+ bloom->filter[index >> BITS_CHAR_SHIFT] |= 1 << (index % BITS_PER_CHAR);
+ }
+
+ bloom->num_elements++;
+
+ return BLOOM_SUCCESS;
}
bloom_return bloom_contains(bloom_t *bloom, const char *data, size_t data_len)
{
+ int i;
+ uint32_t hash1, hash2;
+ uint32_t index;
+
+ if (!bloom || !data || data_len == 0) {
+ return BLOOM_BADARG;
+ }
+
+ bloom_hash(bloom, data, data_len, &hash1, &hash2);
+ for (i = 0; i < bloom->spec.num_hashes; i++) {
+ index = (hash1 + i * hash2) % bloom->spec.filter_size;
+ if ((bloom->filter[index >> BITS_CHAR_SHIFT] & (1 << (index % BITS_PER_CHAR))) == 0) {
+ return BLOOM_NOTFOUND;
+ }
+ }
+
+ return BLOOM_SUCCESS;
}
bloom_return bloom_calc_optimal(filter_spec_t *spec, size_t num_elements, double max_error_rate)
@@ -124,15 +178,8 @@ bloom_return bloom_calc_optimal(filter_spec_t *spec, size_t num_elements, double
spec->filter_size = filter_size;
spec->num_hashes = num_hashes;
+ spec->size_bytes = filter_size / BITS_PER_CHAR;
return BLOOM_SUCCESS;
}
-int main()
-{
- filter_spec_t spec;
-
- bloom_calc_optimal(&spec, 1000000, 0.01);
- printf("filter size = %d\nhashes = %d\n", spec.filter_size, spec.num_hashes);
- return 0;
-}
View
19 bloom.h
@@ -20,13 +20,28 @@
#include <stdlib.h>
#include <stdint.h>
-typedef struct _bloom_t bloom_t;
-typedef struct _filter_spec_t filter_spec_t;
+typedef struct _filter_spec_t {
+ size_t filter_size;
+ size_t size_bytes;
+ uint8_t num_hashes;
+} filter_spec_t;
+
+typedef struct _bloom_t {
+ uint8_t *filter;
+ struct _filter_spec_t spec;
+
+ double max_error_rate;
+ size_t num_elements;
+
+ uint32_t salt1;
+ uint32_t salt2;
+} bloom_t;
typedef enum {
BLOOM_SUCCESS,
BLOOM_FAILURE,
BLOOM_BADARG,
+ BLOOM_NOTFOUND,
BLOOM_BAD_FILTER_SIZE
} bloom_return;
View
2 config.m4
@@ -23,7 +23,7 @@ if test "$PHP_BLOOMY" != "no"; then
PHP_SUBST(BLOOMY_SHARED_LIBADD)
AC_DEFINE(HAVE_BLOOMY, 1, [ ])
- PHP_NEW_EXTENSION(bloomy, php_bloomy.c bloom.c, $ext_shared)
+ PHP_NEW_EXTENSION(bloomy, php_bloomy.c bloom.c lookup3.c, $ext_shared)
fi
View
1,001 lookup3.c
@@ -0,0 +1,1001 @@
+/*
+-------------------------------------------------------------------------------
+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 0
+
+#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() 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<n; ++i) h = hashlittle( k[i], len[i], h);
+
+By Bob Jenkins, 2006. bob_jenkins@burtleburtle.net. You may use this
+code any way you wish, private, educational, or commercial. It's free.
+
+Use for hash table lookup, or anything where one collision in 2^^32 is
+acceptable. 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 */
+
+ 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 */
+ 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 : *pc=c; *pb=b; return; /* zero length strings require no mixing */
+ }
+
+#else /* make valgrind happy */
+
+ 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 */
+ 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]<<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 */
+
+ 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;
+}
+
+
+#ifdef SELF_TEST
+
+/* used for timings */
+void driver1()
+{
+ uint8_t buf[256];
+ uint32_t i;
+ uint32_t h=0;
+ time_t a,z;
+
+ time(&a);
+ for (i=0; i<256; ++i) buf[i] = 'x';
+ for (i=0; i<1; ++i)
+ {
+ h = hashlittle(&buf[0],1,h);
+ }
+ time(&z);
+ if (z-a > 0) printf("time %d %.8x\n", z-a, h);
+}
+
+/* check that every input bit changes every output bit half the time */
+#define HASHSTATE 1
+#define HASHLEN 1
+#define MAXPAIR 60
+#define MAXLEN 70
+void driver2()
+{
+ uint8_t qa[MAXLEN+1], qb[MAXLEN+2], *a = &qa[0], *b = &qb[1];
+ uint32_t c[HASHSTATE], d[HASHSTATE], i=0, j=0, k, l, m=0, z;
+ uint32_t e[HASHSTATE],f[HASHSTATE],g[HASHSTATE],h[HASHSTATE];
+ uint32_t x[HASHSTATE],y[HASHSTATE];
+ uint32_t hlen;
+
+ printf("No more than %d trials should ever be needed \n",MAXPAIR/2);
+ for (hlen=0; hlen < MAXLEN; ++hlen)
+ {
+ z=0;
+ for (i=0; i<hlen; ++i) /*----------------------- for each input byte, */
+ {
+ for (j=0; j<8; ++j) /*------------------------ for each input bit, */
+ {
+ for (m=1; m<8; ++m) /*------------ for serveral possible initvals, */
+ {
+ for (l=0; l<HASHSTATE; ++l)
+ e[l]=f[l]=g[l]=h[l]=x[l]=y[l]=~((uint32_t)0);
+
+ /*---- check that every output bit is affected by that input bit */
+ for (k=0; k<MAXPAIR; k+=2)
+ {
+ uint32_t finished=1;
+ /* keys have one bit different */
+ for (l=0; l<hlen+1; ++l) {a[l] = b[l] = (uint8_t)0;}
+ /* have a and b be two keys differing in only one bit */
+ a[i] ^= (k<<j);
+ a[i] ^= (k>>(8-j));
+ c[0] = hashlittle(a, hlen, m);
+ b[i] ^= ((k+1)<<j);
+ b[i] ^= ((k+1)>>(8-j));
+ d[0] = hashlittle(b, hlen, m);
+ /* check every bit is 1, 0, set, and not set at least once */
+ for (l=0; l<HASHSTATE; ++l)
+ {
+ e[l] &= (c[l]^d[l]);
+ f[l] &= ~(c[l]^d[l]);
+ g[l] &= c[l];
+ h[l] &= ~c[l];
+ x[l] &= d[l];
+ y[l] &= ~d[l];
+ if (e[l]|f[l]|g[l]|h[l]|x[l]|y[l]) finished=0;
+ }
+ if (finished) break;
+ }
+ if (k>z) z=k;
+ if (k==MAXPAIR)
+ {
+ printf("Some bit didn't change: ");
+ printf("%.8x %.8x %.8x %.8x %.8x %.8x ",
+ e[0],f[0],g[0],h[0],x[0],y[0]);
+ printf("i %d j %d m %d len %d\n", i, j, m, hlen);
+ }
+ if (z==MAXPAIR) goto done;
+ }
+ }
+ }
+ done:
+ if (z < MAXPAIR)
+ {
+ printf("Mix success %2d bytes %2d initvals ",i,m);
+ printf("required %d trials\n", z/2);
+ }
+ }
+ printf("\n");
+}
+
+/* Check for reading beyond the end of the buffer and alignment problems */
+void driver3()
+{
+ uint8_t buf[MAXLEN+20], *b;
+ uint32_t len;
+ uint8_t q[] = "This is the time for all good men to come to the aid of their country...";
+ uint32_t h;
+ uint8_t qq[] = "xThis is the time for all good men to come to the aid of their country...";
+ uint32_t i;
+ uint8_t qqq[] = "xxThis is the time for all good men to come to the aid of their country...";
+ uint32_t j;
+ uint8_t qqqq[] = "xxxThis is the time for all good men to come to the aid of their country...";
+ uint32_t ref,x,y;
+ uint8_t *p;
+
+ printf("Endianness. These lines should all be the same (for values filled in):\n");
+ printf("%.8x %.8x %.8x\n",
+ hashword((const uint32_t *)q, (sizeof(q)-1)/4, 13),
+ hashword((const uint32_t *)q, (sizeof(q)-5)/4, 13),
+ hashword((const uint32_t *)q, (sizeof(q)-9)/4, 13));
+ p = q;
+ printf("%.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x\n",
+ hashlittle(p, sizeof(q)-1, 13), hashlittle(p, sizeof(q)-2, 13),
+ hashlittle(p, sizeof(q)-3, 13), hashlittle(p, sizeof(q)-4, 13),
+ hashlittle(p, sizeof(q)-5, 13), hashlittle(p, sizeof(q)-6, 13),
+ hashlittle(p, sizeof(q)-7, 13), hashlittle(p, sizeof(q)-8, 13),
+ hashlittle(p, sizeof(q)-9, 13), hashlittle(p, sizeof(q)-10, 13),
+ hashlittle(p, sizeof(q)-11, 13), hashlittle(p, sizeof(q)-12, 13));
+ p = &qq[1];
+ printf("%.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x\n",
+ hashlittle(p, sizeof(q)-1, 13), hashlittle(p, sizeof(q)-2, 13),
+ hashlittle(p, sizeof(q)-3, 13), hashlittle(p, sizeof(q)-4, 13),
+ hashlittle(p, sizeof(q)-5, 13), hashlittle(p, sizeof(q)-6, 13),
+ hashlittle(p, sizeof(q)-7, 13), hashlittle(p, sizeof(q)-8, 13),
+ hashlittle(p, sizeof(q)-9, 13), hashlittle(p, sizeof(q)-10, 13),
+ hashlittle(p, sizeof(q)-11, 13), hashlittle(p, sizeof(q)-12, 13));
+ p = &qqq[2];
+ printf("%.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x\n",
+ hashlittle(p, sizeof(q)-1, 13), hashlittle(p, sizeof(q)-2, 13),
+ hashlittle(p, sizeof(q)-3, 13), hashlittle(p, sizeof(q)-4, 13),
+ hashlittle(p, sizeof(q)-5, 13), hashlittle(p, sizeof(q)-6, 13),
+ hashlittle(p, sizeof(q)-7, 13), hashlittle(p, sizeof(q)-8, 13),
+ hashlittle(p, sizeof(q)-9, 13), hashlittle(p, sizeof(q)-10, 13),
+ hashlittle(p, sizeof(q)-11, 13), hashlittle(p, sizeof(q)-12, 13));
+ p = &qqqq[3];
+ printf("%.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x\n",
+ hashlittle(p, sizeof(q)-1, 13), hashlittle(p, sizeof(q)-2, 13),
+ hashlittle(p, sizeof(q)-3, 13), hashlittle(p, sizeof(q)-4, 13),
+ hashlittle(p, sizeof(q)-5, 13), hashlittle(p, sizeof(q)-6, 13),
+ hashlittle(p, sizeof(q)-7, 13), hashlittle(p, sizeof(q)-8, 13),
+ hashlittle(p, sizeof(q)-9, 13), hashlittle(p, sizeof(q)-10, 13),
+ hashlittle(p, sizeof(q)-11, 13), hashlittle(p, sizeof(q)-12, 13));
+ printf("\n");
+
+ /* check that hashlittle2 and hashlittle produce the same results */
+ i=47; j=0;
+ hashlittle2(q, sizeof(q), &i, &j);
+ if (hashlittle(q, sizeof(q), 47) != i)
+ printf("hashlittle2 and hashlittle mismatch\n");
+
+ /* check that hashword2 and hashword produce the same results */
+ len = 0xdeadbeef;
+ i=47, j=0;
+ hashword2(&len, 1, &i, &j);
+ if (hashword(&len, 1, 47) != i)
+ printf("hashword2 and hashword mismatch %x %x\n",
+ i, hashword(&len, 1, 47));
+
+ /* check hashlittle doesn't read before or after the ends of the string */
+ for (h=0, b=buf+1; h<8; ++h, ++b)
+ {
+ for (i=0; i<MAXLEN; ++i)
+ {
+ len = i;
+ for (j=0; j<i; ++j) *(b+j)=0;
+
+ /* these should all be equal */
+ ref = hashlittle(b, len, (uint32_t)1);
+ *(b+i)=(uint8_t)~0;
+ *(b-1)=(uint8_t)~0;
+ x = hashlittle(b, len, (uint32_t)1);
+ y = hashlittle(b, len, (uint32_t)1);
+ if ((ref != x) || (ref != y))
+ {
+ printf("alignment error: %.8x %.8x %.8x %d %d\n",ref,x,y,
+ h, i);
+ }
+ }
+ }
+}
+
+/* check for problems with nulls */
+ void driver4()
+{
+ uint8_t buf[1];
+ uint32_t h,i,state[HASHSTATE];
+
+
+ buf[0] = ~0;
+ for (i=0; i<HASHSTATE; ++i) state[i] = 1;
+ printf("These should all be different\n");
+ for (i=0, h=0; i<8; ++i)
+ {
+ h = hashlittle(buf, 0, h);
+ printf("%2ld 0-byte strings, hash is %.8x\n", i, h);
+ }
+}
+
+void driver5()
+{
+ uint32_t b,c;
+ b=0, c=0, hashlittle2("", 0, &c, &b);
+ printf("hash is %.8lx %.8lx\n", c, b); /* deadbeef deadbeef */
+ b=0xdeadbeef, c=0, hashlittle2("", 0, &c, &b);
+ printf("hash is %.8lx %.8lx\n", c, b); /* bd5b7dde deadbeef */
+ b=0xdeadbeef, c=0xdeadbeef, hashlittle2("", 0, &c, &b);
+ printf("hash is %.8lx %.8lx\n", c, b); /* 9c093ccd bd5b7dde */
+ b=0, c=0, hashlittle2("Four score and seven years ago", 30, &c, &b);
+ printf("hash is %.8lx %.8lx\n", c, b); /* 17770551 ce7226e6 */
+ b=1, c=0, hashlittle2("Four score and seven years ago", 30, &c, &b);
+ printf("hash is %.8lx %.8lx\n", c, b); /* e3607cae bd371de4 */
+ b=0, c=1, hashlittle2("Four score and seven years ago", 30, &c, &b);
+ printf("hash is %.8lx %.8lx\n", c, b); /* cd628161 6cbea4b3 */
+ c = hashlittle("Four score and seven years ago", 30, 0);
+ printf("hash is %.8lx\n", c); /* 17770551 */
+ c = hashlittle("Four score and seven years ago", 30, 1);
+ printf("hash is %.8lx\n", c); /* cd628161 */
+}
+
+
+int main()
+{
+ driver1(); /* test that the key is hashed: used for timings */
+ driver2(); /* test that whole key is hashed thoroughly */
+ driver3(); /* test that nothing but the key is hashed */
+ driver4(); /* test hashing multiple buffers (all buffers are null) */
+ driver5(); /* test the hash against known vectors */
+ return 1;
+}
+
+#endif /* SELF_TEST */
View
224 php_bloomy.c
@@ -17,14 +17,215 @@
/* $ Id: $ */
#include "php_bloomy.h"
+#include "bloom.h"
+
+#include "ext/standard/php_lcg.h"
+#include "ext/standard/php_rand.h"
+
+/****************************************
+ Helper macros
+****************************************/
+
+#define BLOOM_METHOD_INIT_VARS \
+ zval* object = getThis(); \
+ php_bloom_t* obj = NULL; \
+
+#define BLOOM_METHOD_FETCH_OBJECT \
+ obj = (php_bloom_t *) zend_object_store_get_object( object TSRMLS_CC ); \
+ if (!obj->bloom) { \
+ php_error_docref(NULL TSRMLS_CC, E_WARNING, "BloomFilter constructor was not called"); \
+ return; \
+ }
+
+
+/****************************************
+ Structures and definitions
+****************************************/
+
+typedef struct {
+ zend_object zo;
+
+ bloom_t *bloom;
+} php_bloom_t;
+
+static zend_class_entry *bloom_ce = NULL;
+static const double DEFAULT_ERROR_RATE = 0.01;
+
+
+/****************************************
+ Forward declarations
+****************************************/
+
+static void php_bloom_destroy(php_bloom_t *obj TSRMLS_DC);
+
+
+/****************************************
+ Method implementations
+****************************************/
+
+/* {{{ BloomFilter::__construct */
+static PHP_METHOD(BloomFilter, __construct)
+{
+ zval *object = getThis();
+ php_bloom_t *obj;
+ long capacity, seed = 0;
+ double error_rate = DEFAULT_ERROR_RATE;
+ bloom_return status;
+
+ if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "l|dl", &capacity, &error_rate, &seed) == FAILURE) {
+ ZVAL_NULL(object);
+ return;
+ }
+
+ if (capacity == 0 ||
+ capacity > SIZE_MAX ||
+ error_rate <= 0.0 ||
+ error_rate >= 1.0) {
+
+ ZVAL_NULL(object);
+ php_error_docref(NULL TSRMLS_CC, E_WARNING, "bad filter parameters");
+ return;
+ }
+
+ if (seed == 0) {
+ seed = GENERATE_SEED();
+ }
+ srand(seed);
+
+ obj = (php_bloom_t *) zend_object_store_get_object(object TSRMLS_CC);
+
+ obj->bloom = (bloom_t *) emalloc(sizeof(bloom_t));
+ status = bloom_init(obj->bloom, capacity, error_rate);
+ if (status != BLOOM_SUCCESS) {
+ ZVAL_NULL(object);
+ php_error_docref(NULL TSRMLS_CC, E_WARNING, "could not create filter");
+ return;
+ }
+
+ zend_update_property_double(bloom_ce, object, ZEND_STRL("errorRate"), error_rate TSRMLS_CC);
+ zend_update_property_long(bloom_ce, object, ZEND_STRL("sizeInBytes"), obj->bloom->spec.size_bytes TSRMLS_CC);
+}
+/* }}} */
+
+/* {{{ BloomFilter::add */
+static PHP_METHOD(BloomFilter, add)
+{
+ char *data = NULL;
+ int data_len;
+ BLOOM_METHOD_INIT_VARS;
+ bloom_return status;
+
+ if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "s", &data, &data_len) == FAILURE) {
+ return;
+ }
+
+ BLOOM_METHOD_FETCH_OBJECT;
+
+ status = bloom_add(obj->bloom, data, data_len);
+ if (status != BLOOM_SUCCESS) {
+ php_error_docref(NULL TSRMLS_CC, E_WARNING, "could not add data to filter");
+ RETURN_FALSE;
+ }
+
+ RETURN_TRUE;
+}
+/* }}} */
+
+/* {{{ BloomFilter::has */
+static PHP_METHOD(BloomFilter, has)
+{
+ char *data = NULL;
+ int data_len;
+ BLOOM_METHOD_INIT_VARS;
+ bloom_return status;
+
+ if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "s", &data, &data_len) == FAILURE) {
+ return;
+ }
+
+ BLOOM_METHOD_FETCH_OBJECT;
+
+ status = bloom_contains(obj->bloom, data, data_len);
+
+ if (status == BLOOM_NOTFOUND) {
+ RETURN_FALSE;
+ } else {
+ RETURN_TRUE;
+ }
+}
+/* }}} */
+
+
+/****************************************
+ Internal support code
+****************************************/
+
+/* {{{ constructor/destructor */
+static void php_bloom_destroy(php_bloom_t *obj TSRMLS_DC)
+{
+ if (obj->bloom) {
+ bloom_clean(obj->bloom);
+ efree(obj->bloom);
+ }
+}
+
+static void php_bloom_free_storage(php_bloom_t *obj TSRMLS_DC)
+{
+ zend_object_std_dtor(&obj->zo TSRMLS_CC);
+
+ php_bloom_destroy(obj TSRMLS_CC);
+ efree(obj);
+}
+
+zend_object_value php_bloom_new(zend_class_entry *ce TSRMLS_DC)
+{
+ zend_object_value retval;
+ php_bloom_t *obj;
+ zval *tmp;
+
+ obj = (php_bloom_t *) emalloc(sizeof(*obj));
+ memset(obj, 0, sizeof(*obj));
+ zend_object_std_init(&obj->zo, ce TSRMLS_CC);
+ zend_hash_copy(obj->zo.properties, &ce->default_properties, (copy_ctor_func_t) zval_add_ref, (void *) &tmp, sizeof(zval *));
+
+ retval.handle = zend_objects_store_put(obj, (zend_objects_store_dtor_t)zend_objects_destroy_object, (zend_objects_free_object_storage_t)php_bloom_free_storage, NULL TSRMLS_CC);
+ retval.handlers = zend_get_std_object_handlers();
+
+ return retval;
+}
+/* }}} */
+
+/* {{{ methods arginfo */
+ZEND_BEGIN_ARG_INFO_EX(arginfo___construct, 0, 0, 1)
+ ZEND_ARG_INFO(0, capacity)
+ ZEND_ARG_INFO(0, error_rate)
+ZEND_END_ARG_INFO()
+
+ZEND_BEGIN_ARG_INFO(arginfo_add, 0)
+ ZEND_ARG_INFO(0, data)
+ZEND_END_ARG_INFO()
+
+ZEND_BEGIN_ARG_INFO(arginfo_has, 0)
+ ZEND_ARG_INFO(0, data)
+ZEND_END_ARG_INFO()
+/* }}} */
+
+/* {{{ bloom_class_methods */
+static zend_function_entry bloom_class_methods[] = {
+ PHP_ME(BloomFilter, __construct, arginfo___construct, ZEND_ACC_PUBLIC)
+ PHP_ME(BloomFilter, add, arginfo_add, ZEND_ACC_PUBLIC)
+ PHP_ME(BloomFilter, has, arginfo_has, ZEND_ACC_PUBLIC)
+ { NULL, NULL, NULL }
+};
+/* }}} */
/* {{{ bloomy_module_entry
*/
zend_module_entry bloomy_module_entry = {
STANDARD_MODULE_HEADER,
"bloomy",
NULL,
- NULL,
+ PHP_MINIT(bloomy),
NULL,
NULL,
NULL,
@@ -34,10 +235,22 @@ zend_module_entry bloomy_module_entry = {
};
/* }}} */
-#ifdef COMPILE_DL_BLOOMY
-ZEND_GET_MODULE(bloomy)
-#endif
+/* {{{ PHP_MINIT_FUNCTION */
+PHP_MINIT_FUNCTION(bloomy)
+{
+ zend_class_entry ce;
+
+ INIT_CLASS_ENTRY(ce, "BloomFilter", bloom_class_methods);
+ bloom_ce = zend_register_internal_class(&ce TSRMLS_CC);
+ bloom_ce->create_object = php_bloom_new;
+ zend_declare_property_double(bloom_ce, "errorRate", sizeof("errorRate")-1, 0.0, ZEND_ACC_PUBLIC TSRMLS_CC);
+ zend_declare_property_long(bloom_ce, "sizeInBytes", sizeof("sizeInBytes")-1, 0, ZEND_ACC_PUBLIC TSRMLS_CC);
+ zend_declare_property_long(bloom_ce, "numElements", sizeof("numElements")-1, 0.0, ZEND_ACC_PUBLIC TSRMLS_CC);
+
+ return SUCCESS;
+}
+/* }}} */
/* {{{ PHP_MINFO_FUNCTION */
PHP_MINFO_FUNCTION(bloomy)
@@ -49,6 +262,9 @@ PHP_MINFO_FUNCTION(bloomy)
}
/* }}} */
+#ifdef COMPILE_DL_BLOOMY
+ZEND_GET_MODULE(bloomy)
+#endif
/*
* Local variables:
View
12 php_bloomy.h
@@ -39,19 +39,9 @@ extern zend_module_entry bloomy_module_entry;
#include "TSRM.h"
#endif
-#define PROP_GET_LONG(name) Z_LVAL_P(zend_read_property(_this_ce, _this_zval, #name, strlen(#name), 1 TSRMLS_CC))
-#define PROP_SET_LONG(name, l) zend_update_property_long(_this_ce, _this_zval, #name, strlen(#name), l TSRMLS_CC)
-
-#define PROP_GET_DOUBLE(name) Z_DVAL_P(zend_read_property(_this_ce, _this_zval, #name, strlen(#name), 1 TSRMLS_CC))
-#define PROP_SET_DOUBLE(name, d) zend_update_property_double(_this_ce, _this_zval, #name, strlen(#name), d TSRMLS_CC)
-
-#define PROP_GET_STRING(name) Z_STRVAL_P(zend_read_property(_this_ce, _this_zval, #name, strlen(#name), 1 TSRMLS_CC))
-#define PROP_GET_STRLEN(name) Z_STRLEN_P(zend_read_property(_this_ce, _this_zval, #name, strlen(#name), 1 TSRMLS_CC))
-#define PROP_SET_STRING(name, s) zend_update_property_string(_this_ce, _this_zval, #name, strlen(#name), s TSRMLS_CC)
-#define PROP_SET_STRINGL(name, s, l) zend_update_property_stringl(_this_ce, _this_zval, #name, strlen(#name), s, l TSRMLS_CC)
-
#define PHP_BLOOMY_VERSION "0.1.0"
+PHP_MINIT_FUNCTION(bloomy);
PHP_MINFO_FUNCTION(bloomy);
#endif /* PHP_BLOOMY_H */

0 comments on commit 06da1cb

Please sign in to comment.