git-annex/Utility/Hash.hs

136 lines
4.4 KiB
Haskell
Raw Normal View History

{- Convenience wrapper around cryptohash/cryptonite.
-
- SHA3 hashes are currently only enabled when using cryptonite,
- because of https://github.com/vincenthz/hs-cryptohash/issues/36
-}
{-# LANGUAGE CPP #-}
module Utility.Hash (
sha1,
sha2_224,
sha2_256,
sha2_384,
sha2_512,
#ifdef WITH_CRYPTONITE
sha3_224,
sha3_256,
sha3_384,
sha3_512,
#endif
skein256,
skein512,
2015-02-04 17:47:54 +00:00
md5,
2015-04-19 14:57:14 +00:00
prop_hashes_stable,
Mac(..),
calcMac,
prop_mac_stable,
) where
Use cryptohash rather than SHA for hashing. This is a massive win on OSX, which doesn't have a sha256sum normally. Only use external hash commands when the file is > 1 mb, since cryptohash is quite close to them in speed. SHA is still used to calculate HMACs. I don't quite understand cryptohash's API for those. Used the following benchmark to arrive at the 1 mb number. 1 mb file: benchmarking sha256/internal mean: 13.86696 ms, lb 13.83010 ms, ub 13.93453 ms, ci 0.950 std dev: 249.3235 us, lb 162.0448 us, ub 458.1744 us, ci 0.950 found 5 outliers among 100 samples (5.0%) 4 (4.0%) high mild 1 (1.0%) high severe variance introduced by outliers: 10.415% variance is moderately inflated by outliers benchmarking sha256/external mean: 14.20670 ms, lb 14.17237 ms, ub 14.27004 ms, ci 0.950 std dev: 230.5448 us, lb 150.7310 us, ub 427.6068 us, ci 0.950 found 3 outliers among 100 samples (3.0%) 2 (2.0%) high mild 1 (1.0%) high severe 2 mb file: benchmarking sha256/internal mean: 26.44270 ms, lb 26.23701 ms, ub 26.63414 ms, ci 0.950 std dev: 1.012303 ms, lb 925.8921 us, ub 1.122267 ms, ci 0.950 variance introduced by outliers: 35.540% variance is moderately inflated by outliers benchmarking sha256/external mean: 26.84521 ms, lb 26.77644 ms, ub 26.91433 ms, ci 0.950 std dev: 347.7867 us, lb 210.6283 us, ub 571.3351 us, ci 0.950 found 6 outliers among 100 samples (6.0%) import Crypto.Hash import Data.ByteString.Lazy as L import Criterion.Main import Common testfile :: FilePath testfile = "/run/shm/data" -- on ram disk main = defaultMain [ bgroup "sha256" [ bench "internal" $ whnfIO internal , bench "external" $ whnfIO external ] ] sha256 :: L.ByteString -> Digest SHA256 sha256 = hashlazy internal :: IO String internal = show . sha256 <$> L.readFile testfile external :: IO String external = do s <- readProcess "sha256sum" [testfile] return $ fst $ separate (== ' ') s
2013-09-22 23:45:08 +00:00
import qualified Data.ByteString.Lazy as L
import qualified Data.Text as T
import qualified Data.Text.Encoding as T
2015-04-19 14:57:14 +00:00
import qualified Data.ByteString as S
#ifdef WITH_CRYPTONITE
import "cryptonite" Crypto.MAC.HMAC
import "cryptonite" Crypto.Hash
#else
import "cryptohash" Crypto.Hash
#endif
Use cryptohash rather than SHA for hashing. This is a massive win on OSX, which doesn't have a sha256sum normally. Only use external hash commands when the file is > 1 mb, since cryptohash is quite close to them in speed. SHA is still used to calculate HMACs. I don't quite understand cryptohash's API for those. Used the following benchmark to arrive at the 1 mb number. 1 mb file: benchmarking sha256/internal mean: 13.86696 ms, lb 13.83010 ms, ub 13.93453 ms, ci 0.950 std dev: 249.3235 us, lb 162.0448 us, ub 458.1744 us, ci 0.950 found 5 outliers among 100 samples (5.0%) 4 (4.0%) high mild 1 (1.0%) high severe variance introduced by outliers: 10.415% variance is moderately inflated by outliers benchmarking sha256/external mean: 14.20670 ms, lb 14.17237 ms, ub 14.27004 ms, ci 0.950 std dev: 230.5448 us, lb 150.7310 us, ub 427.6068 us, ci 0.950 found 3 outliers among 100 samples (3.0%) 2 (2.0%) high mild 1 (1.0%) high severe 2 mb file: benchmarking sha256/internal mean: 26.44270 ms, lb 26.23701 ms, ub 26.63414 ms, ci 0.950 std dev: 1.012303 ms, lb 925.8921 us, ub 1.122267 ms, ci 0.950 variance introduced by outliers: 35.540% variance is moderately inflated by outliers benchmarking sha256/external mean: 26.84521 ms, lb 26.77644 ms, ub 26.91433 ms, ci 0.950 std dev: 347.7867 us, lb 210.6283 us, ub 571.3351 us, ci 0.950 found 6 outliers among 100 samples (6.0%) import Crypto.Hash import Data.ByteString.Lazy as L import Criterion.Main import Common testfile :: FilePath testfile = "/run/shm/data" -- on ram disk main = defaultMain [ bgroup "sha256" [ bench "internal" $ whnfIO internal , bench "external" $ whnfIO external ] ] sha256 :: L.ByteString -> Digest SHA256 sha256 = hashlazy internal :: IO String internal = show . sha256 <$> L.readFile testfile external :: IO String external = do s <- readProcess "sha256sum" [testfile] return $ fst $ separate (== ' ') s
2013-09-22 23:45:08 +00:00
sha1 :: L.ByteString -> Digest SHA1
sha1 = hashlazy
sha2_224 :: L.ByteString -> Digest SHA224
sha2_224 = hashlazy
sha2_256 :: L.ByteString -> Digest SHA256
sha2_256 = hashlazy
Use cryptohash rather than SHA for hashing. This is a massive win on OSX, which doesn't have a sha256sum normally. Only use external hash commands when the file is > 1 mb, since cryptohash is quite close to them in speed. SHA is still used to calculate HMACs. I don't quite understand cryptohash's API for those. Used the following benchmark to arrive at the 1 mb number. 1 mb file: benchmarking sha256/internal mean: 13.86696 ms, lb 13.83010 ms, ub 13.93453 ms, ci 0.950 std dev: 249.3235 us, lb 162.0448 us, ub 458.1744 us, ci 0.950 found 5 outliers among 100 samples (5.0%) 4 (4.0%) high mild 1 (1.0%) high severe variance introduced by outliers: 10.415% variance is moderately inflated by outliers benchmarking sha256/external mean: 14.20670 ms, lb 14.17237 ms, ub 14.27004 ms, ci 0.950 std dev: 230.5448 us, lb 150.7310 us, ub 427.6068 us, ci 0.950 found 3 outliers among 100 samples (3.0%) 2 (2.0%) high mild 1 (1.0%) high severe 2 mb file: benchmarking sha256/internal mean: 26.44270 ms, lb 26.23701 ms, ub 26.63414 ms, ci 0.950 std dev: 1.012303 ms, lb 925.8921 us, ub 1.122267 ms, ci 0.950 variance introduced by outliers: 35.540% variance is moderately inflated by outliers benchmarking sha256/external mean: 26.84521 ms, lb 26.77644 ms, ub 26.91433 ms, ci 0.950 std dev: 347.7867 us, lb 210.6283 us, ub 571.3351 us, ci 0.950 found 6 outliers among 100 samples (6.0%) import Crypto.Hash import Data.ByteString.Lazy as L import Criterion.Main import Common testfile :: FilePath testfile = "/run/shm/data" -- on ram disk main = defaultMain [ bgroup "sha256" [ bench "internal" $ whnfIO internal , bench "external" $ whnfIO external ] ] sha256 :: L.ByteString -> Digest SHA256 sha256 = hashlazy internal :: IO String internal = show . sha256 <$> L.readFile testfile external :: IO String external = do s <- readProcess "sha256sum" [testfile] return $ fst $ separate (== ' ') s
2013-09-22 23:45:08 +00:00
sha2_384 :: L.ByteString -> Digest SHA384
sha2_384 = hashlazy
Use cryptohash rather than SHA for hashing. This is a massive win on OSX, which doesn't have a sha256sum normally. Only use external hash commands when the file is > 1 mb, since cryptohash is quite close to them in speed. SHA is still used to calculate HMACs. I don't quite understand cryptohash's API for those. Used the following benchmark to arrive at the 1 mb number. 1 mb file: benchmarking sha256/internal mean: 13.86696 ms, lb 13.83010 ms, ub 13.93453 ms, ci 0.950 std dev: 249.3235 us, lb 162.0448 us, ub 458.1744 us, ci 0.950 found 5 outliers among 100 samples (5.0%) 4 (4.0%) high mild 1 (1.0%) high severe variance introduced by outliers: 10.415% variance is moderately inflated by outliers benchmarking sha256/external mean: 14.20670 ms, lb 14.17237 ms, ub 14.27004 ms, ci 0.950 std dev: 230.5448 us, lb 150.7310 us, ub 427.6068 us, ci 0.950 found 3 outliers among 100 samples (3.0%) 2 (2.0%) high mild 1 (1.0%) high severe 2 mb file: benchmarking sha256/internal mean: 26.44270 ms, lb 26.23701 ms, ub 26.63414 ms, ci 0.950 std dev: 1.012303 ms, lb 925.8921 us, ub 1.122267 ms, ci 0.950 variance introduced by outliers: 35.540% variance is moderately inflated by outliers benchmarking sha256/external mean: 26.84521 ms, lb 26.77644 ms, ub 26.91433 ms, ci 0.950 std dev: 347.7867 us, lb 210.6283 us, ub 571.3351 us, ci 0.950 found 6 outliers among 100 samples (6.0%) import Crypto.Hash import Data.ByteString.Lazy as L import Criterion.Main import Common testfile :: FilePath testfile = "/run/shm/data" -- on ram disk main = defaultMain [ bgroup "sha256" [ bench "internal" $ whnfIO internal , bench "external" $ whnfIO external ] ] sha256 :: L.ByteString -> Digest SHA256 sha256 = hashlazy internal :: IO String internal = show . sha256 <$> L.readFile testfile external :: IO String external = do s <- readProcess "sha256sum" [testfile] return $ fst $ separate (== ' ') s
2013-09-22 23:45:08 +00:00
sha2_512 :: L.ByteString -> Digest SHA512
sha2_512 = hashlazy
Use cryptohash rather than SHA for hashing. This is a massive win on OSX, which doesn't have a sha256sum normally. Only use external hash commands when the file is > 1 mb, since cryptohash is quite close to them in speed. SHA is still used to calculate HMACs. I don't quite understand cryptohash's API for those. Used the following benchmark to arrive at the 1 mb number. 1 mb file: benchmarking sha256/internal mean: 13.86696 ms, lb 13.83010 ms, ub 13.93453 ms, ci 0.950 std dev: 249.3235 us, lb 162.0448 us, ub 458.1744 us, ci 0.950 found 5 outliers among 100 samples (5.0%) 4 (4.0%) high mild 1 (1.0%) high severe variance introduced by outliers: 10.415% variance is moderately inflated by outliers benchmarking sha256/external mean: 14.20670 ms, lb 14.17237 ms, ub 14.27004 ms, ci 0.950 std dev: 230.5448 us, lb 150.7310 us, ub 427.6068 us, ci 0.950 found 3 outliers among 100 samples (3.0%) 2 (2.0%) high mild 1 (1.0%) high severe 2 mb file: benchmarking sha256/internal mean: 26.44270 ms, lb 26.23701 ms, ub 26.63414 ms, ci 0.950 std dev: 1.012303 ms, lb 925.8921 us, ub 1.122267 ms, ci 0.950 variance introduced by outliers: 35.540% variance is moderately inflated by outliers benchmarking sha256/external mean: 26.84521 ms, lb 26.77644 ms, ub 26.91433 ms, ci 0.950 std dev: 347.7867 us, lb 210.6283 us, ub 571.3351 us, ci 0.950 found 6 outliers among 100 samples (6.0%) import Crypto.Hash import Data.ByteString.Lazy as L import Criterion.Main import Common testfile :: FilePath testfile = "/run/shm/data" -- on ram disk main = defaultMain [ bgroup "sha256" [ bench "internal" $ whnfIO internal , bench "external" $ whnfIO external ] ] sha256 :: L.ByteString -> Digest SHA256 sha256 = hashlazy internal :: IO String internal = show . sha256 <$> L.readFile testfile external :: IO String external = do s <- readProcess "sha256sum" [testfile] return $ fst $ separate (== ' ') s
2013-09-22 23:45:08 +00:00
#ifdef WITH_CRYPTONITE
sha3_224 :: L.ByteString -> Digest SHA3_224
sha3_224 = hashlazy
Use cryptohash rather than SHA for hashing. This is a massive win on OSX, which doesn't have a sha256sum normally. Only use external hash commands when the file is > 1 mb, since cryptohash is quite close to them in speed. SHA is still used to calculate HMACs. I don't quite understand cryptohash's API for those. Used the following benchmark to arrive at the 1 mb number. 1 mb file: benchmarking sha256/internal mean: 13.86696 ms, lb 13.83010 ms, ub 13.93453 ms, ci 0.950 std dev: 249.3235 us, lb 162.0448 us, ub 458.1744 us, ci 0.950 found 5 outliers among 100 samples (5.0%) 4 (4.0%) high mild 1 (1.0%) high severe variance introduced by outliers: 10.415% variance is moderately inflated by outliers benchmarking sha256/external mean: 14.20670 ms, lb 14.17237 ms, ub 14.27004 ms, ci 0.950 std dev: 230.5448 us, lb 150.7310 us, ub 427.6068 us, ci 0.950 found 3 outliers among 100 samples (3.0%) 2 (2.0%) high mild 1 (1.0%) high severe 2 mb file: benchmarking sha256/internal mean: 26.44270 ms, lb 26.23701 ms, ub 26.63414 ms, ci 0.950 std dev: 1.012303 ms, lb 925.8921 us, ub 1.122267 ms, ci 0.950 variance introduced by outliers: 35.540% variance is moderately inflated by outliers benchmarking sha256/external mean: 26.84521 ms, lb 26.77644 ms, ub 26.91433 ms, ci 0.950 std dev: 347.7867 us, lb 210.6283 us, ub 571.3351 us, ci 0.950 found 6 outliers among 100 samples (6.0%) import Crypto.Hash import Data.ByteString.Lazy as L import Criterion.Main import Common testfile :: FilePath testfile = "/run/shm/data" -- on ram disk main = defaultMain [ bgroup "sha256" [ bench "internal" $ whnfIO internal , bench "external" $ whnfIO external ] ] sha256 :: L.ByteString -> Digest SHA256 sha256 = hashlazy internal :: IO String internal = show . sha256 <$> L.readFile testfile external :: IO String external = do s <- readProcess "sha256sum" [testfile] return $ fst $ separate (== ' ') s
2013-09-22 23:45:08 +00:00
sha3_256 :: L.ByteString -> Digest SHA3_256
sha3_256 = hashlazy
sha3_384 :: L.ByteString -> Digest SHA3_384
sha3_384 = hashlazy
sha3_512 :: L.ByteString -> Digest SHA3_512
sha3_512 = hashlazy
#endif
Use cryptohash rather than SHA for hashing. This is a massive win on OSX, which doesn't have a sha256sum normally. Only use external hash commands when the file is > 1 mb, since cryptohash is quite close to them in speed. SHA is still used to calculate HMACs. I don't quite understand cryptohash's API for those. Used the following benchmark to arrive at the 1 mb number. 1 mb file: benchmarking sha256/internal mean: 13.86696 ms, lb 13.83010 ms, ub 13.93453 ms, ci 0.950 std dev: 249.3235 us, lb 162.0448 us, ub 458.1744 us, ci 0.950 found 5 outliers among 100 samples (5.0%) 4 (4.0%) high mild 1 (1.0%) high severe variance introduced by outliers: 10.415% variance is moderately inflated by outliers benchmarking sha256/external mean: 14.20670 ms, lb 14.17237 ms, ub 14.27004 ms, ci 0.950 std dev: 230.5448 us, lb 150.7310 us, ub 427.6068 us, ci 0.950 found 3 outliers among 100 samples (3.0%) 2 (2.0%) high mild 1 (1.0%) high severe 2 mb file: benchmarking sha256/internal mean: 26.44270 ms, lb 26.23701 ms, ub 26.63414 ms, ci 0.950 std dev: 1.012303 ms, lb 925.8921 us, ub 1.122267 ms, ci 0.950 variance introduced by outliers: 35.540% variance is moderately inflated by outliers benchmarking sha256/external mean: 26.84521 ms, lb 26.77644 ms, ub 26.91433 ms, ci 0.950 std dev: 347.7867 us, lb 210.6283 us, ub 571.3351 us, ci 0.950 found 6 outliers among 100 samples (6.0%) import Crypto.Hash import Data.ByteString.Lazy as L import Criterion.Main import Common testfile :: FilePath testfile = "/run/shm/data" -- on ram disk main = defaultMain [ bgroup "sha256" [ bench "internal" $ whnfIO internal , bench "external" $ whnfIO external ] ] sha256 :: L.ByteString -> Digest SHA256 sha256 = hashlazy internal :: IO String internal = show . sha256 <$> L.readFile testfile external :: IO String external = do s <- readProcess "sha256sum" [testfile] return $ fst $ separate (== ' ') s
2013-09-22 23:45:08 +00:00
skein256 :: L.ByteString -> Digest Skein256_256
skein256 = hashlazy
Use cryptohash rather than SHA for hashing. This is a massive win on OSX, which doesn't have a sha256sum normally. Only use external hash commands when the file is > 1 mb, since cryptohash is quite close to them in speed. SHA is still used to calculate HMACs. I don't quite understand cryptohash's API for those. Used the following benchmark to arrive at the 1 mb number. 1 mb file: benchmarking sha256/internal mean: 13.86696 ms, lb 13.83010 ms, ub 13.93453 ms, ci 0.950 std dev: 249.3235 us, lb 162.0448 us, ub 458.1744 us, ci 0.950 found 5 outliers among 100 samples (5.0%) 4 (4.0%) high mild 1 (1.0%) high severe variance introduced by outliers: 10.415% variance is moderately inflated by outliers benchmarking sha256/external mean: 14.20670 ms, lb 14.17237 ms, ub 14.27004 ms, ci 0.950 std dev: 230.5448 us, lb 150.7310 us, ub 427.6068 us, ci 0.950 found 3 outliers among 100 samples (3.0%) 2 (2.0%) high mild 1 (1.0%) high severe 2 mb file: benchmarking sha256/internal mean: 26.44270 ms, lb 26.23701 ms, ub 26.63414 ms, ci 0.950 std dev: 1.012303 ms, lb 925.8921 us, ub 1.122267 ms, ci 0.950 variance introduced by outliers: 35.540% variance is moderately inflated by outliers benchmarking sha256/external mean: 26.84521 ms, lb 26.77644 ms, ub 26.91433 ms, ci 0.950 std dev: 347.7867 us, lb 210.6283 us, ub 571.3351 us, ci 0.950 found 6 outliers among 100 samples (6.0%) import Crypto.Hash import Data.ByteString.Lazy as L import Criterion.Main import Common testfile :: FilePath testfile = "/run/shm/data" -- on ram disk main = defaultMain [ bgroup "sha256" [ bench "internal" $ whnfIO internal , bench "external" $ whnfIO external ] ] sha256 :: L.ByteString -> Digest SHA256 sha256 = hashlazy internal :: IO String internal = show . sha256 <$> L.readFile testfile external :: IO String external = do s <- readProcess "sha256sum" [testfile] return $ fst $ separate (== ' ') s
2013-09-22 23:45:08 +00:00
skein512 :: L.ByteString -> Digest Skein512_512
skein512 = hashlazy
2015-02-04 17:47:54 +00:00
md5 :: L.ByteString -> Digest MD5
md5 = hashlazy
{- Check that all the hashes continue to hash the same. -}
prop_hashes_stable :: Bool
prop_hashes_stable = all (\(hasher, result) -> hasher foo == result)
[ (show . sha1, "0beec7b5ea3f0fdbc95d0dd47f3c5bc275da8a33")
, (show . sha2_224, "0808f64e60d58979fcb676c96ec938270dea42445aeefcd3a4e6f8db")
, (show . sha2_256, "2c26b46b68ffc68ff99b453c1d30413413422d706483bfa0f98a5e886266e7ae")
, (show . sha2_384, "98c11ffdfdd540676b1a137cb1a22b2a70350c9a44171d6b1180c6be5cbb2ee3f79d532c8a1dd9ef2e8e08e752a3babb")
, (show . sha2_512, "f7fbba6e0636f890e56fbbf3283e524c6fa3204ae298382d624741d0dc6638326e282c41be5e4254d8820772c5518a2c5a8c0c7f7eda19594a7eb539453e1ed7")
, (show . skein256, "a04efd9a0aeed6ede40fe5ce0d9361ae7b7d88b524aa19917b9315f1ecf00d33")
, (show . skein512, "fd8956898113510180aa4658e6c0ac85bd74fb47f4a4ba264a6b705d7a8e8526756e75aecda12cff4f1aca1a4c2830fbf57f458012a66b2b15a3dd7d251690a7")
#ifdef WITH_CRYPTONITE
, (show . sha3_224, "f4f6779e153c391bbd29c95e72b0708e39d9166c7cea51d1f10ef58a")
, (show . sha3_256, "76d3bc41c9f588f7fcd0d5bf4718f8f84b1c41b20882703100b9eb9413807c01")
, (show . sha3_384, "665551928d13b7d84ee02734502b018d896a0fb87eed5adb4c87ba91bbd6489410e11b0fbcc06ed7d0ebad559e5d3bb5")
, (show . sha3_512, "4bca2b137edc580fe50a88983ef860ebaca36c857b1f492839d6d7392452a63c82cbebc68e3b70a2a1480b4bb5d437a7cba6ecf9d89f9ff3ccd14cd6146ea7e7")
#endif
2015-02-04 17:47:54 +00:00
, (show . md5, "acbd18db4cc2f85cedef654fccc4a4d8")
]
where
foo = L.fromChunks [T.encodeUtf8 $ T.pack "foo"]
2015-04-19 14:57:14 +00:00
{- File names are (client-side) MAC'ed on special remotes.
- The chosen MAC algorithm needs to be same for all files stored on the
- remote.
-}
data Mac = HmacSha1 | HmacSha224 | HmacSha256 | HmacSha384 | HmacSha512
deriving (Eq)
calcMac
:: Mac -- ^ MAC
-> S.ByteString -- ^ secret key
-> S.ByteString -- ^ message
-> String -- ^ MAC'ed message, in hexadecimal
calcMac mac = case mac of
HmacSha1 -> use SHA1
HmacSha224 -> use SHA224
HmacSha256 -> use SHA256
HmacSha384 -> use SHA384
HmacSha512 -> use SHA512
where
use alg k m = show (hmacGetDigest (hmacWitnessAlg alg k m))
hmacWitnessAlg :: HashAlgorithm a => a -> S.ByteString -> S.ByteString -> HMAC a
hmacWitnessAlg _ = hmac
2015-04-19 14:57:14 +00:00
-- Check that all the MACs continue to produce the same.
prop_mac_stable :: Bool
prop_mac_stable = all (\(mac, result) -> calcMac mac key msg == result)
[ (HmacSha1, "46b4ec586117154dacd49d664e5d63fdc88efb51")
, (HmacSha224, "4c1f774863acb63b7f6e9daa9b5c543fa0d5eccf61e3ffc3698eacdd")
, (HmacSha256, "f9320baf0249169e73850cd6156ded0106e2bb6ad8cab01b7bbbebe6d1065317")
, (HmacSha384, "3d10d391bee2364df2c55cf605759373e1b5a4ca9355d8f3fe42970471eca2e422a79271a0e857a69923839015877fc6")
, (HmacSha512, "114682914c5d017dfe59fdc804118b56a3a652a0b8870759cf9e792ed7426b08197076bf7d01640b1b0684df79e4b67e37485669e8ce98dbab60445f0db94fce")
]
where
key = T.encodeUtf8 $ T.pack "foo"
msg = T.encodeUtf8 $ T.pack "bar"