attoparsec parsers for all new-format uuid-based logs

There should be some speed gains here, especially for chunk and remote
state logs, which are queried once per key.

Now only old-format uuid-based logs still need to be converted to attoparsec.
This commit is contained in:
Joey Hess 2019-01-10 13:23:42 -04:00
parent 7e54c215b4
commit 66603d6f75
No known key found for this signature in database
GPG key ID: DB12DB0FF05F8F38
10 changed files with 88 additions and 56 deletions

View file

@ -19,6 +19,9 @@ import Logs.MapLog
import Data.Int
import qualified Data.ByteString as S
import qualified Data.ByteString.Lazy as L
import qualified Data.Attoparsec.ByteString.Lazy as A
import qualified Data.Attoparsec.ByteString.Char8 as A8
import Data.ByteString.Builder
-- Currently chunks are all fixed size, but other chunking methods
@ -33,20 +36,13 @@ type ChunkCount = Integer
type ChunkLog = MapLog (UUID, ChunkMethod) ChunkCount
parseChunkMethod :: String -> ChunkMethod
parseChunkMethod s = maybe (UnknownChunks $ encodeBS s) FixedSizeChunks (readish s)
buildChunkMethod :: ChunkMethod -> Builder
buildChunkMethod (FixedSizeChunks sz) = int64Dec sz
buildChunkMethod (UnknownChunks s) = byteString s
parseLog :: String -> ChunkLog
parseLog = parseMapLog fieldparser valueparser
where
fieldparser s =
let (u,m) = separate (== ':') s
in Just (toUUID u, parseChunkMethod m)
valueparser = readish
chunkMethodParser :: A.Parser ChunkMethod
chunkMethodParser =
(FixedSizeChunks <$> A8.decimal) <|> (UnknownChunks <$> A.takeByteString)
buildLog :: ChunkLog -> Builder
buildLog = buildMapLog fieldbuilder valuebuilder
@ -54,3 +50,13 @@ buildLog = buildMapLog fieldbuilder valuebuilder
fieldbuilder (u, m) = buildUUID u <> sep <> buildChunkMethod m
valuebuilder = integerDec
sep = charUtf8 ':'
parseLog :: L.ByteString -> ChunkLog
parseLog = parseMapLog fieldparser valueparser
where
fieldparser = (,)
<$> (toUUID <$> A8.takeTill (== ':'))
<* A8.char ':'
<*> chunkMethodParser
<* A.endOfInput
valueparser = A8.decimal