git-annex/doc/bugs/blake3_hash_support.mdwn

164 lines
6.2 KiB
Markdown

This is a patch that seems to work for my personal use.
BLAKE3 does support variable lengths, but my code does not implement support for anything other than 256-bit (32-byte) digests.
I'm not familiar enough with the codebase to be sure whether adding variable length support later is a backwards compatibility hazard or not.
[[!format patch """
From efa115d94d1a5a52574d5760c6e951ed3c518667 Mon Sep 17 00:00:00 2001
From: edef <edef@edef.eu>
Date: Fri, 2 Dec 2022 12:16:44 +0000
Subject: [PATCH] support BLAKE3
This uses the blake3 package from Hackage, since cryptonite does not
have BLAKE3 support yet.
diff --git a/Backend/Hash.hs b/Backend/Hash.hs
index 550d8fc6c..809a82599 100644
--- a/Backend/Hash.hs
+++ b/Backend/Hash.hs
@@ -27,8 +27,11 @@ import qualified Data.ByteString as S
import qualified Data.ByteString.Short as S (toShort, fromShort)
import qualified Data.ByteString.Char8 as S8
import qualified Data.ByteString.Lazy as L
+import Data.IORef
+import Control.Arrow
import Control.DeepSeq
import Control.Exception (evaluate)
+import qualified BLAKE3
data Hash
= MD5Hash
@@ -40,6 +43,7 @@ data Hash
| Blake2bpHash HashSize
| Blake2sHash HashSize
| Blake2spHash HashSize
+ | Blake3Hash
cryptographicallySecure :: Hash -> Bool
cryptographicallySecure (SHA2Hash _) = True
@@ -49,6 +53,7 @@ cryptographicallySecure (Blake2bHash _) = True
cryptographicallySecure (Blake2bpHash _) = True
cryptographicallySecure (Blake2sHash _) = True
cryptographicallySecure (Blake2spHash _) = True
+cryptographicallySecure Blake3Hash = True
cryptographicallySecure SHA1Hash = False
cryptographicallySecure MD5Hash = False
@@ -63,6 +68,7 @@ hashes = concat
, map (Blake2bpHash . HashSize) [512]
, map (Blake2sHash . HashSize) [256, 160, 224]
, map (Blake2spHash . HashSize) [256, 224]
+ , [Blake3Hash]
, [SHA1Hash]
, [MD5Hash]
]
@@ -99,6 +105,7 @@ hashKeyVariety (Blake2bHash size) he = Blake2bKey size he
hashKeyVariety (Blake2bpHash size) he = Blake2bpKey size he
hashKeyVariety (Blake2sHash size) he = Blake2sKey size he
hashKeyVariety (Blake2spHash size) he = Blake2spKey size he
+hashKeyVariety Blake3Hash he = Blake3Key he
{- A key is a hash of its contents. -}
keyValue :: Hash -> KeySource -> MeterUpdate -> Annex Key
@@ -219,6 +226,7 @@ hasher (Blake2bHash hashsize) = blake2bHasher hashsize
hasher (Blake2bpHash hashsize) = blake2bpHasher hashsize
hasher (Blake2sHash hashsize) = blake2sHasher hashsize
hasher (Blake2spHash hashsize) = blake2spHasher hashsize
+hasher Blake3Hash = blake3Hasher
mkHasher :: HashAlgorithm h => (L.ByteString -> Digest h) -> Context h -> Hasher
mkHasher h c = (show . h, mkIncrementalVerifier c descChecksum . sameCheckSum)
@@ -272,6 +280,27 @@ blake2spHasher (HashSize hashsize)
| hashsize == 224 = mkHasher blake2sp_224 blake2sp_224_context
| otherwise = error $ "unsupported BLAKE2SP size " ++ show hashsize
+blake3Hasher :: Hasher
+blake3Hasher = (hash, incremental) where
+ finalize :: BLAKE3.Hasher -> BLAKE3.Digest BLAKE3.DEFAULT_DIGEST_LEN
+ finalize = BLAKE3.finalize
+
+ hash :: L.ByteString -> String
+ hash = show . finalize . L.foldlChunks ((. pure) . BLAKE3.update) BLAKE3.hasher
+
+ incremental :: Key -> IO IncrementalVerifier
+ incremental k = do
+ v <- newIORef (Just (BLAKE3.hasher, 0))
+ return $ IncrementalVerifier
+ { updateIncrementalVerifier = \b ->
+ modifyIORef' v . fmap $ flip BLAKE3.update [b] *** (fromIntegral (S.length b) +)
+ , finalizeIncrementalVerifier =
+ fmap (sameCheckSum k . show . finalize . fst) <$> readIORef v
+ , unableIncrementalVerifier = writeIORef v Nothing
+ , positionIncrementalVerifier = fmap snd <$> readIORef v
+ , descIncrementalVerifier = descChecksum
+ }
+
sha1Hasher :: Hasher
sha1Hasher = mkHasher sha1 sha1_context
diff --git a/Types/Key.hs b/Types/Key.hs
index 271723982..ea71f85ed 100644
--- a/Types/Key.hs
+++ b/Types/Key.hs
@@ -214,6 +214,7 @@ data KeyVariety
| Blake2bpKey HashSize HasExt
| Blake2sKey HashSize HasExt
| Blake2spKey HashSize HasExt
+ | Blake3Key HasExt
| SHA1Key HasExt
| MD5Key HasExt
| WORMKey
@@ -247,6 +248,7 @@ hasExt (Blake2bKey _ (HasExt b)) = b
hasExt (Blake2bpKey _ (HasExt b)) = b
hasExt (Blake2sKey _ (HasExt b)) = b
hasExt (Blake2spKey _ (HasExt b)) = b
+hasExt (Blake3Key (HasExt b)) = b
hasExt (SHA1Key (HasExt b)) = b
hasExt (MD5Key (HasExt b)) = b
hasExt WORMKey = False
@@ -262,6 +264,7 @@ sameExceptExt (Blake2bKey sz1 _) (Blake2bKey sz2 _) = sz1 == sz2
sameExceptExt (Blake2bpKey sz1 _) (Blake2bpKey sz2 _) = sz1 == sz2
sameExceptExt (Blake2sKey sz1 _) (Blake2sKey sz2 _) = sz1 == sz2
sameExceptExt (Blake2spKey sz1 _) (Blake2spKey sz2 _) = sz1 == sz2
+sameExceptExt (Blake3Key _) (Blake3Key _) = True
sameExceptExt (SHA1Key _) (SHA1Key _) = True
sameExceptExt (MD5Key _) (MD5Key _) = True
sameExceptExt _ _ = False
@@ -275,6 +278,7 @@ formatKeyVariety v = case v of
Blake2bpKey sz e -> adde e (addsz sz "BLAKE2BP")
Blake2sKey sz e -> adde e (addsz sz "BLAKE2S")
Blake2spKey sz e -> adde e (addsz sz "BLAKE2SP")
+ Blake3Key e -> adde e "BLAKE3"
SHA1Key e -> adde e "SHA1"
MD5Key e -> adde e "MD5"
WORMKey -> "WORM"
@@ -337,6 +341,8 @@ parseKeyVariety "BLAKE2SP224" = Blake2spKey (HashSize 224) (HasExt False)
parseKeyVariety "BLAKE2SP224E" = Blake2spKey (HashSize 224) (HasExt True)
parseKeyVariety "BLAKE2SP256" = Blake2spKey (HashSize 256) (HasExt False)
parseKeyVariety "BLAKE2SP256E" = Blake2spKey (HashSize 256) (HasExt True)
+parseKeyVariety "BLAKE3" = Blake3Key (HasExt False)
+parseKeyVariety "BLAKE3E" = Blake3Key (HasExt True)
parseKeyVariety "SHA1" = SHA1Key (HasExt False)
parseKeyVariety "SHA1E" = SHA1Key (HasExt True)
parseKeyVariety "MD5" = MD5Key (HasExt False)
diff --git a/git-annex.cabal b/git-annex.cabal
index cd58a4ca3..7c251e33b 100644
--- a/git-annex.cabal
+++ b/git-annex.cabal
@@ -362,6 +362,7 @@ Executable git-annex
securemem,
crypto-api,
cryptonite (>= 0.23),
+ blake3,
memory,
deepseq,
split,
diff --git a/stack.yaml b/stack.yaml
index 7dbfb657a..936ee841b 100644
--- a/stack.yaml
+++ b/stack.yaml
@@ -25,3 +25,4 @@ extra-deps:
- base64-bytestring-1.0.0.3
- bencode-0.6.1.1
- http-client-0.7.9
+- blake3-0.2@sha256:d1146b9a51ccfbb0532780778b6d016a614e3d44c05d8c1923dde9a8be869045,2448
"""]]