From 6ddd4ab70fb7826f4ec2ec03667f24a43792e990 Mon Sep 17 00:00:00 2001 From: Jan Sucan Date: Sat, 8 Nov 2025 19:02:25 +0100 Subject: 26_a_1: Add solution --- README.md | 2 +- ch26/26_a_1/26_a_1.hs | 86 ++++ ch26/26_a_1/BloomFilter.hs | 42 ++ ch26/26_a_1/BloomFilter/Easy.hs | 55 ++ ch26/26_a_1/BloomFilter/Hash.hs | 138 +++++ ch26/26_a_1/BloomFilter/Internal.hs | 24 + ch26/26_a_1/BloomFilter/Mutable.hs | 59 +++ ch26/26_a_1/License.txt | 1 + ch26/26_a_1/Setup.lhs | 3 + ch26/26_a_1/cbits/lookup3.c | 978 ++++++++++++++++++++++++++++++++++++ ch26/26_a_1/cbits/lookup3.h | 23 + ch26/26_a_1/rwh-bloomfilter.cabal | 61 +++ 12 files changed, 1471 insertions(+), 1 deletion(-) create mode 100644 ch26/26_a_1/26_a_1.hs create mode 100644 ch26/26_a_1/BloomFilter.hs create mode 100644 ch26/26_a_1/BloomFilter/Easy.hs create mode 100644 ch26/26_a_1/BloomFilter/Hash.hs create mode 100644 ch26/26_a_1/BloomFilter/Internal.hs create mode 100644 ch26/26_a_1/BloomFilter/Mutable.hs create mode 100644 ch26/26_a_1/License.txt create mode 100644 ch26/26_a_1/Setup.lhs create mode 100644 ch26/26_a_1/cbits/lookup3.c create mode 100644 ch26/26_a_1/cbits/lookup3.h create mode 100644 ch26/26_a_1/rwh-bloomfilter.cabal diff --git a/README.md b/README.md index 4444c05..771dcd5 100644 --- a/README.md +++ b/README.md @@ -191,7 +191,7 @@ are prefixed with 'Module_'. | 24_a_2 | yes | | | | **_24_b_1_** | yes | 551 | | | 24_b_2 | yes, in 24_b_1 | | | -| **_26_a_1_** | | 610 | 26. Advanced library design: building a Bloom filter | +| **_26_a_1_** | yes | 610 | 26. Advanced library design: building a Bloom filter | | 26_a_2 | | | | ## Bug reports diff --git a/ch26/26_a_1/26_a_1.hs b/ch26/26_a_1/26_a_1.hs new file mode 100644 index 0000000..3b497a2 --- /dev/null +++ b/ch26/26_a_1/26_a_1.hs @@ -0,0 +1,86 @@ +-- Our use of genericLength in easyList will cause our function to loop +-- infinitely if we supply an infinite list. Fix this. + + +-- It is not possible to decide whether a list has been defined as infinite. For +-- this, there would have to be some reflection capabilities in the +-- language. Only a finite limit on the list max. length can be set and checked. + + +-- I was compiling the code of this chapter by 'cabal build'. There were some +-- warnings and errors. I have fixed only the errors. +-- +-- - in BloomFilter/Hash.hs, a part of the import statement for CSize had to +-- be changed from '(CSize)' to '(CSize(..))' to import the data +-- constructor, not only the type constructor. +-- +-- - in BloomFilter.hs in the fromList function, the 'B hash . runSTUArray $' +-- had to be changed to 'B hash $ runSTUArray $' for the code to compile. + + +-- For testing, I was loading the code into ghci. For it to be able to find +-- symbols from the lookup3.o file, I needed to convert it to a shared library +-- +-- gcc ./dist-newstyle/build/x86_64-linux/ghc-9.6.7/rwh-bloomfilter-0.1/build/cbits/lookup3.o -shared -o liblookup3.so +-- +-- and load the shared library on start of ghci +-- +-- stack ghci --ghci-options "-L$(pwd) -llookup3" + + +import BloomFilter.Easy +import BloomFilter.Hash (Hashable, doubleHash) +import Data.List (genericLength) +import qualified BloomFilter as B + +-- Helper function for forcing evaluation of the easyList and fixedEasyList +-- return value +easyListLength l = + case l of + Left err -> error err + Right b -> BloomFilter.Easy.length b + +-- Short length for more illustrative testing +maxLength = 10 + +fixedEasyList errRate values = + if isLongerThan values maxLength + then + Left $ "List longer than " ++ (show maxLength) ++ " elements" + else + case suggestSizing (genericLength values) errRate of + Left err -> Left err + Right (bits,hashes) -> Right filt + where filt = B.fromList (doubleHash hashes) bits values + +isLongerThan values max = isLongerThan' values 0 max + where + isLongerThan' [] l max = False + isLongerThan' (v:vs) l max + | (l + 1) > max = True + | otherwise = isLongerThan' vs (l + 1) max + + +-- ghci> :l 26_a_1.hs +-- [1 of 7] Compiling BloomFilter.Hash ( BloomFilter/Hash.hs, interpreted ) +-- ... +-- [2 of 7] Compiling BloomFilter.Internal ( BloomFilter/Internal.hs, interpreted ) +-- [3 of 7] Compiling BloomFilter.Mutable ( BloomFilter/Mutable.hs, interpreted ) +-- [4 of 7] Compiling BloomFilter ( BloomFilter.hs, interpreted ) +-- [5 of 7] Compiling BloomFilter.Easy ( BloomFilter/Easy.hs, interpreted ) +-- [6 of 7] Compiling Main ( 26_a_1.hs, interpreted ) +-- Ok, six modules loaded. + +-- ghci> l = easyList 0.2 [1..] +-- ghci> easyListLength l +-- *** Exception: stack overflow + +-- ghci> l = fixedEasyList 0.2 [1..] +-- ghci> easyListLength l +-- *** Exception: List longer than 10 elements +-- CallStack (from HasCallStack): +-- error, called at 26_a_1.hs:40:17 in main:Main + +-- ghci> l = fixedEasyList 0.2 [1..10] +-- ghci> easyListLength l +-- 34 diff --git a/ch26/26_a_1/BloomFilter.hs b/ch26/26_a_1/BloomFilter.hs new file mode 100644 index 0000000..c8b8f8d --- /dev/null +++ b/ch26/26_a_1/BloomFilter.hs @@ -0,0 +1,42 @@ +{-- snippet module --} +module BloomFilter + ( + Bloom + , length + , elem + , notElem + , fromList + ) where + +import BloomFilter.Internal +import BloomFilter.Mutable (insert, new) +import Data.Array.ST (runSTUArray) +import Data.Array.IArray ((!), bounds) +import Data.Word (Word32) +import Prelude hiding (elem, length, notElem) + +length :: Bloom a -> Int +length = fromIntegral . len + +len :: Bloom a -> Word32 +len = succ . snd . bounds . blmArray + +elem :: a -> Bloom a -> Bool +elt `elem` filt = all test (blmHash filt elt) + where test hash = blmArray filt ! (hash `mod` len filt) + +notElem :: a -> Bloom a -> Bool +elt `notElem` filt = not (elt `elem` filt) +{-- /snippet module --} + +{-- snippet fromList --} +fromList :: (a -> [Word32]) -- family of hash functions to use + -> Word32 -- number of bits in filter + -> [a] -- values to populate with + -> Bloom a +fromList hash numBits values = + B hash $ runSTUArray $ + do mb <- new hash numBits + mapM_ (insert mb) values + return (mutArray mb) +{-- /snippet fromList --} diff --git a/ch26/26_a_1/BloomFilter/Easy.hs b/ch26/26_a_1/BloomFilter/Easy.hs new file mode 100644 index 0000000..4a032ce --- /dev/null +++ b/ch26/26_a_1/BloomFilter/Easy.hs @@ -0,0 +1,55 @@ +{-- snippet easyList --} +module BloomFilter.Easy + ( + suggestSizing + , sizings + , easyList + + -- re-export useful names from BloomFilter + , B.Bloom + , B.length + , B.elem + , B.notElem + ) where + +import BloomFilter.Hash (Hashable, doubleHash) +import Data.List (genericLength) +import Data.Maybe (catMaybes) +import Data.Word (Word32) +import qualified BloomFilter as B + +easyList errRate values = + case suggestSizing (genericLength values) errRate of + Left err -> Left err + Right (bits,hashes) -> Right filt + where filt = B.fromList (doubleHash hashes) bits values +{-- /snippet easyList --} + +{-- snippet suggestSizing --} +suggestSizing + :: Integer -- expected maximum capacity + -> Double -- desired false positive rate + -> Either String (Word32,Int) -- (filter size, number of hashes) +suggestSizing capacity errRate + | capacity <= 0 = Left "capacity too small" + | errRate <= 0 || errRate >= 1 = Left "invalid error rate" + | null saneSizes = Left "capacity too large" + | otherwise = Right (minimum saneSizes) + where saneSizes = catMaybes . map sanitize $ sizings capacity errRate + sanitize (bits,hashes) + | bits > maxWord32 - 1 = Nothing + | otherwise = Just (ceiling bits, truncate hashes) + where maxWord32 = fromIntegral (maxBound :: Word32) + +sizings :: Integer -> Double -> [(Double, Double)] +sizings capacity errRate = + [(((-k) * cap / log (1 - (errRate ** (1 / k)))), k) | k <- [1..50]] + where cap = fromIntegral capacity +{-- /snippet suggestSizing --} + +{-- snippet easyList.type --} +easyList :: (Hashable a) + => Double -- false positive rate (between 0 and 1) + -> [a] -- values to populate the filter with + -> Either String (B.Bloom a) +{-- /snippet easyList.type --} diff --git a/ch26/26_a_1/BloomFilter/Hash.hs b/ch26/26_a_1/BloomFilter/Hash.hs new file mode 100644 index 0000000..0399b0e --- /dev/null +++ b/ch26/26_a_1/BloomFilter/Hash.hs @@ -0,0 +1,138 @@ +{-- snippet jenkins --} +{-# LANGUAGE BangPatterns, ForeignFunctionInterface #-} +module BloomFilter.Hash + ( + Hashable(..) + , hash + , doubleHash + ) where + +import Data.Bits ((.&.), shiftR) +import Foreign.Marshal.Array (withArrayLen) +import Control.Monad (foldM) +import Data.Word (Word32, Word64) +import Foreign.C.Types (CSize(..)) +import Foreign.Marshal.Utils (with) +import Foreign.Ptr (Ptr, castPtr, plusPtr) +import Foreign.Storable (Storable, peek, sizeOf) +import qualified Data.ByteString as Strict +import qualified Data.ByteString.Lazy as Lazy +import System.IO.Unsafe (unsafePerformIO) + +foreign import ccall unsafe "lookup3.h hashword2" hashWord2 + :: Ptr Word32 -> CSize -> Ptr Word32 -> Ptr Word32 -> IO () + +foreign import ccall unsafe "lookup3.h hashlittle2" hashLittle2 + :: Ptr a -> CSize -> Ptr Word32 -> Ptr Word32 -> IO () +{-- /snippet jenkins --} + +{-- snippet Hashable --} +class Hashable a where + hashSalt :: Word64 -- ^ salt + -> a -- ^ value to hash + -> Word64 + +hash :: Hashable a => a -> Word64 +hash = hashSalt 0x106fc397cf62f64d3 +{-- /snippet Hashable --} + +{-- snippet hashIO --} +hashIO :: Ptr a -- value to hash + -> CSize -- number of bytes + -> Word64 -- salt + -> IO Word64 +hashIO ptr bytes salt = + with (fromIntegral salt) $ \sp -> do + let p1 = castPtr sp + p2 = castPtr sp `plusPtr` 4 + go p1 p2 + peek sp + where go p1 p2 + | bytes .&. 3 == 0 = hashWord2 (castPtr ptr) words p1 p2 + | otherwise = hashLittle2 ptr bytes p1 p2 + words = bytes `div` 4 +{-- /snippet hashIO --} + +{-- snippet hashStorable --} +hashStorable :: Storable a => Word64 -> a -> Word64 +hashStorable salt k = unsafePerformIO . with k $ \ptr -> + hashIO ptr (fromIntegral (sizeOf k)) salt + +instance Hashable Char where hashSalt = hashStorable +instance Hashable Int where hashSalt = hashStorable +instance Hashable Double where hashSalt = hashStorable +{-- /snippet hashStorable --} + +{- +{-- snippet Storable --} +instance Storable a => Hashable a where + hashSalt = hashStorable +{-- /snippet Storable --} +-} + +{-- snippet hashList --} +hashList :: (Storable a) => Word64 -> [a] -> IO Word64 +hashList salt xs = + withArrayLen xs $ \len ptr -> + hashIO ptr (fromIntegral (len * sizeOf x)) salt + where x = head xs + +instance (Storable a) => Hashable [a] where + hashSalt salt xs = unsafePerformIO $ hashList salt xs +{-- /snippet hashList --} + +{-- snippet hash2 --} +hash2 :: (Hashable a) => a -> Word64 -> Word64 +hash2 k salt = hashSalt salt k + +instance (Hashable a, Hashable b) => Hashable (a,b) where + hashSalt salt (a,b) = hash2 b . hash2 a $ salt + +instance (Hashable a, Hashable b, Hashable c) => Hashable (a,b,c) where + hashSalt salt (a,b,c) = hash2 c . hash2 b . hash2 a $ salt +{-- /snippet hash2 --} + +{-- snippet hashSB --} +hashByteString :: Word64 -> Strict.ByteString -> IO Word64 +hashByteString salt bs = Strict.useAsCStringLen bs $ \(ptr, len) -> + hashIO ptr (fromIntegral len) salt + +instance Hashable Strict.ByteString where + hashSalt salt bs = unsafePerformIO $ hashByteString salt bs + +rechunk :: Lazy.ByteString -> [Strict.ByteString] +rechunk s + | Lazy.null s = [] + | otherwise = let (pre,suf) = Lazy.splitAt chunkSize s + in repack pre : rechunk suf + where repack = Strict.concat . Lazy.toChunks + chunkSize = 64 * 1024 + +instance Hashable Lazy.ByteString where + hashSalt salt bs = unsafePerformIO $ + foldM hashByteString salt (rechunk bs) +{-- /snippet hashSB --} + +{- +{-- snippet doubleHash --} +doubleHash :: Hashable a => Int -> a -> [Word32] +doubleHash numHashes value = [h1 + h2 * i | i <- [0..num]] + where h = hashSalt 0x9150a946c4a8966e value + h1 = fromIntegral (h `shiftR` 32) .&. maxBound + h2 = fromIntegral h + num = fromIntegral numHashes +{-- /snippet doubleHash --} +-} + +{-- snippet doubleHash_new --} +doubleHash :: Hashable a => Int -> a -> [Word32] +doubleHash numHashes value = go 0 + where go n | n == num = [] + | otherwise = h1 + h2 * n : go (n + 1) + + !h1 = fromIntegral (h `shiftR` 32) .&. maxBound + !h2 = fromIntegral h + + h = hashSalt 0x9150a946c4a8966e value + num = fromIntegral numHashes +{-- /snippet doubleHash_new --} diff --git a/ch26/26_a_1/BloomFilter/Internal.hs b/ch26/26_a_1/BloomFilter/Internal.hs new file mode 100644 index 0000000..5631ae9 --- /dev/null +++ b/ch26/26_a_1/BloomFilter/Internal.hs @@ -0,0 +1,24 @@ +{-- snippet Bloom --} +module BloomFilter.Internal + ( + Bloom(..) + , MutBloom(..) + ) where + +import Data.Array.ST (STUArray) +import Data.Array.Unboxed (UArray) +import Data.Word (Word32) + +data Bloom a = B { + blmHash :: (a -> [Word32]) + , blmArray :: UArray Word32 Bool + } +{-- /snippet Bloom --} + +{-- snippet MutBloom --} +data MutBloom s a = MB { + mutHash :: (a -> [Word32]) + , mutArray :: STUArray s Word32 Bool + } +{-- /snippet MutBloom --} + diff --git a/ch26/26_a_1/BloomFilter/Mutable.hs b/ch26/26_a_1/BloomFilter/Mutable.hs new file mode 100644 index 0000000..c284013 --- /dev/null +++ b/ch26/26_a_1/BloomFilter/Mutable.hs @@ -0,0 +1,59 @@ +{-- snippet Mutable --} +module BloomFilter.Mutable + ( + MutBloom + , elem + , notElem + , insert + , length + , new + ) where + +import Control.Monad (liftM) +import Control.Monad.ST (ST) +import Data.Array.MArray (getBounds, newArray, readArray, writeArray) +import Data.Word (Word32) +import Prelude hiding (elem, length, notElem) + +import BloomFilter.Internal (MutBloom(..)) +{-- /snippet Mutable --} + +{-- snippet new --} +new :: (a -> [Word32]) -> Word32 -> ST s (MutBloom s a) +new hash numBits = MB hash `liftM` newArray (0,numBits-1) False +{-- /snippet new --} + +{-- snippet length --} +length :: MutBloom s a -> ST s Word32 +length filt = (succ . snd) `liftM` getBounds (mutArray filt) +{-- /snippet length --} + +{-- snippet insert --} +insert :: MutBloom s a -> a -> ST s () +insert filt elt = indices filt elt >>= + mapM_ (\bit -> writeArray (mutArray filt) bit True) + +indices :: MutBloom s a -> a -> ST s [Word32] +indices filt elt = do + modulus <- length filt + return $ map (`mod` modulus) (mutHash filt elt) +{-- /snippet insert --} + +{-- snippet elem --} +elem, notElem :: a -> MutBloom s a -> ST s Bool + +elem elt filt = indices filt elt >>= + allM (readArray (mutArray filt)) + +notElem elt filt = not `liftM` elem elt filt +{-- /snippet elem --} + +{-- snippet allM --} +allM :: Monad m => (a -> m Bool) -> [a] -> m Bool +allM p (x:xs) = do + ok <- p x + if ok + then allM p xs + else return False +allM _ [] = return True +{-- /snippet allM --} diff --git a/ch26/26_a_1/License.txt b/ch26/26_a_1/License.txt new file mode 100644 index 0000000..965cd63 --- /dev/null +++ b/ch26/26_a_1/License.txt @@ -0,0 +1 @@ +Foo. diff --git a/ch26/26_a_1/Setup.lhs b/ch26/26_a_1/Setup.lhs new file mode 100644 index 0000000..4c55f9b --- /dev/null +++ b/ch26/26_a_1/Setup.lhs @@ -0,0 +1,3 @@ +#!/usr/bin/env runhaskell +> import Distribution.Simple +> main = defaultMain diff --git a/ch26/26_a_1/cbits/lookup3.c b/ch26/26_a_1/cbits/lookup3.c new file mode 100644 index 0000000..4db9582 --- /dev/null +++ b/ch26/26_a_1/cbits/lookup3.c @@ -0,0 +1,978 @@ +/* +------------------------------------------------------------------------------- +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. +------------------------------------------------------------------------------- +*/ + +#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 */ + + 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>(8-j)); + c[0] = hashlittle(a, hlen, m); + 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; lz) 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 +#include + +/* only accepts uint32_t aligned arrays of uint32_t */ +void hashword2(const uint32_t *key, /* array of uint32_t */ + size_t length, /* number of uint32_t values */ + uint32_t *pc, /* in: seed1, out: hash1 */ + uint32_t *pb); /* in: seed2, out: hash2 */ + +/* handles arbitrarily aligned arrays of bytes */ +void hashlittle2(const void *key, /* array of bytes */ + size_t length, /* number of bytes */ + uint32_t *pc, /* in: seed1, out: hash1 */ + uint32_t *pb); /* in: seed2, out: hash2 */ + +#endif /* _lookup3_h */ +/** /snippet header */ diff --git a/ch26/26_a_1/rwh-bloomfilter.cabal b/ch26/26_a_1/rwh-bloomfilter.cabal new file mode 100644 index 0000000..14ccb09 --- /dev/null +++ b/ch26/26_a_1/rwh-bloomfilter.cabal @@ -0,0 +1,61 @@ +-- snippet header +Name: rwh-bloomfilter +Version: 0.1 +License: BSD3 +License-File: License.txt +Category: Data +Stability: experimental +Build-Type: Simple +-- /snippet header + +-- snippet extraSourceFiles +Extra-Source-Files: cbits/lookup3.c cbits/lookup3.h +-- /snippet extraSourceFiles + +-- snippet splitBase +Cabal-Version: >= 1.2 + +Flag split-base + Description: Has the base package been split up? + Default: True + +Flag bytestring-in-base + Description: Is ByteString in the base or bytestring package? + Default: False +-- /snippet splitBase + +-- snippet library +Library + if flag(bytestring-in-base) + -- bytestring was in base-2.0 and 2.1.1 + Build-Depends: base >= 2.0 && < 2.2 + else + -- in base 1.0 and 3.0, bytestring is a separate package + Build-Depends: base < 2.0 || >= 3, bytestring >= 0.9 + + if flag(split-base) + Build-Depends: base >= 3.0, array + else + Build-Depends: base < 3.0 +-- /snippet library + +-- snippet modules + Exposed-Modules: BloomFilter + BloomFilter.Easy + BloomFilter.Hash + BloomFilter.Mutable + Other-Modules: BloomFilter.Internal + GHC-Options: -O2 -Wall -fvia-C -optc-O2 +-- /snippet modules + +-- snippet modules + GHC-Prof-Options: -auto-all +-- /snippet modules + +-- snippet cbits + C-Sources: cbits/lookup3.c + CC-Options: -O3 + Include-Dirs: cbits + Includes: lookup3.h + Install-Includes: lookup3.h +-- /snippet cbits -- cgit v1.2.3