git-annex/Logs/Remote.hs
Joey Hess 591e4b145f
convert old uuid-based log parsers to attoparsec
This preserves the workaround for the old bug that caused NoUUID items
to be stored in the log, prefixing log lines with " ". It's now handled
implicitly, by using takeWhile1 (/= ' ') to get the uuid.

There is a behavior change from the old parser, which split the value
into words and then recombined it. That meant that "foo  bar" and "foo\tbar"
came out as "foo bar". That behavior was not documented, and seems
surprising; it meant that after a git-annex describe here "foo  bar",
you wouldn't get that same string back out when git-annex displayed repo
descriptions.

Otoh, some other parsers relied on the old behavior, and the attoparsec
rewrites had to deal with the issue themselves...

For group.log, there are some edge cases around the user providing a
group name with a leading or trailing space. The old parser would ignore
such excess whitespace. The new parser does too, because the alternative
is to refuse to parse something like " group1  group2 " due to excess
whitespace, which would be even more confusing behavior.

The only git-annex branch log file that is not converted to attoparsec
and bytestring-builder now is transitions.log.
2019-01-10 16:34:20 -04:00

100 lines
2.6 KiB
Haskell

{- git-annex remote log
-
- Copyright 2011 Joey Hess <id@joeyh.name>
-
- Licensed under the GNU GPL version 3 or higher.
-}
module Logs.Remote (
remoteLog,
readRemoteLog,
configSet,
keyValToConfig,
configToKeyVal,
showConfig,
prop_isomorphic_configEscape,
prop_parse_show_Config,
) where
import Annex.Common
import qualified Annex.Branch
import Types.Remote
import Logs
import Logs.UUIDBased
import qualified Data.Map as M
import Data.Char
import qualified Data.Attoparsec.ByteString.Lazy as A
import Data.ByteString.Builder
{- Adds or updates a remote's config in the log. -}
configSet :: UUID -> RemoteConfig -> Annex ()
configSet u cfg = do
c <- liftIO currentVectorClock
Annex.Branch.change remoteLog $
buildLog (byteString . encodeBS . showConfig)
. changeLog c u cfg
. parseLog remoteConfigParser
{- Map of remotes by uuid containing key/value config maps. -}
readRemoteLog :: Annex (M.Map UUID RemoteConfig)
readRemoteLog = simpleMap . parseLog remoteConfigParser
<$> Annex.Branch.get remoteLog
remoteConfigParser :: A.Parser RemoteConfig
remoteConfigParser = keyValToConfig . words . decodeBS <$> A.takeByteString
showConfig :: RemoteConfig -> String
showConfig = unwords . configToKeyVal
{- Given Strings like "key=value", generates a RemoteConfig. -}
keyValToConfig :: [String] -> RemoteConfig
keyValToConfig ws = M.fromList $ map (/=/) ws
where
(/=/) s = (k, v)
where
k = takeWhile (/= '=') s
v = configUnEscape $ drop (1 + length k) s
configToKeyVal :: M.Map String String -> [String]
configToKeyVal m = map toword $ sort $ M.toList m
where
toword (k, v) = k ++ "=" ++ configEscape v
configEscape :: String -> String
configEscape = concatMap escape
where
escape c
| isSpace c || c `elem` "&" = "&" ++ show (ord c) ++ ";"
| otherwise = [c]
configUnEscape :: String -> String
configUnEscape = unescape
where
unescape [] = []
unescape (c:rest)
| c == '&' = entity rest
| otherwise = c : unescape rest
entity s
| not (null num) && ";" `isPrefixOf` r =
chr (Prelude.read num) : unescape rest
| otherwise =
'&' : unescape s
where
num = takeWhile isNumber s
r = drop (length num) s
rest = drop 1 r
{- for quickcheck -}
prop_isomorphic_configEscape :: String -> Bool
prop_isomorphic_configEscape s = s == (configUnEscape . configEscape) s
prop_parse_show_Config :: RemoteConfig -> Bool
prop_parse_show_Config c
-- whitespace and '=' are not supported in keys
| any (\k -> any isSpace k || elem '=' k) (M.keys c) = True
| otherwise = A.parseOnly remoteConfigParser (encodeBS $ showConfig c) ~~ Right c
where
normalize v = sort . M.toList <$> v
a ~~ b = normalize a == normalize b