git-annex/Logs/ContentIdentifier.hs

55 lines
1.6 KiB
Haskell
Raw Normal View History

2019-02-20 21:22:56 +00:00
{- Remote content identifier logs.
-
- Copyright 2019 Joey Hess <id@joeyh.name>
-
- Licensed under the GNU AGPL version 3 or higher.
-}
module Logs.ContentIdentifier (
module X,
2019-02-20 21:22:56 +00:00
recordContentIdentifier,
getContentIdentifiers,
) where
import Annex.Common
import Logs
import Logs.MapLog
import Types.Import
import Types.RemoteState
2019-02-20 21:22:56 +00:00
import qualified Annex.Branch
import Logs.ContentIdentifier.Pure as X
2019-02-20 21:22:56 +00:00
import qualified Annex
import qualified Data.Map as M
import Data.List.NonEmpty (NonEmpty(..))
import qualified Data.List.NonEmpty as NonEmpty
2019-02-20 21:22:56 +00:00
-- | Records a remote's content identifier and the key that it corresponds to.
--
-- A remote may use multiple content identifiers for the same key over time,
-- so ones that were recorded before are preserved.
recordContentIdentifier :: RemoteStateHandle -> ContentIdentifier -> Key -> Annex ()
recordContentIdentifier (RemoteStateHandle u) cid k = do
c <- currentVectorClock
2019-02-20 21:22:56 +00:00
config <- Annex.getGitConfig
void $ Annex.Branch.maybeChange
start implementing hidden git-annex repositories This adds a separate journal, which does not currently get committed to an index, but is planned to be committed to .git/annex/index-private. Changes that are regarding a UUID that is private will get written to this journal, and so will not be published into the git-annex branch. All log writing should have been made to indicate the UUID it's regarding, though I've not verified this yet. Currently, no UUIDs are treated as private yet, a way to configure that is needed. The implementation is careful to not add any additional IO work when privateUUIDsKnown is False. It will skip looking at the private journal at all. So this should be free, or nearly so, unless the feature is used. When it is used, all branch reads will be about twice as expensive. It is very lucky -- or very prudent design -- that Annex.Branch.change and maybeChange are the only ways to change a file on the branch, and Annex.Branch.set is only internal use. That let Annex.Branch.get always yield any private information that has been recorded, without the risk that Annex.Branch.set might be called, with a non-private UUID, and end up leaking the private information into the git-annex branch. And, this relies on the way git-annex union merges the git-annex branch. When reading a file, there can be a public and a private version, and they are just concacenated together. That will be handled the same as if there were two diverged git-annex branches that got union merged.
2021-04-20 18:32:41 +00:00
(Annex.Branch.RegardingUUID [u])
(remoteContentIdentifierLogFile config k)
(addcid c . parseLog)
2019-02-20 21:22:56 +00:00
where
addcid c v
| cid `elem` l = Nothing -- no change needed
| otherwise = Just $ buildLog $
changeMapLog c u (cid :| l) v
2019-02-20 21:22:56 +00:00
where
m = simpleMap v
l = contentIdentifierList (M.lookup u m)
2019-02-20 21:22:56 +00:00
-- | Get all known content identifiers for a key.
getContentIdentifiers :: Key -> Annex [(RemoteStateHandle, [ContentIdentifier])]
getContentIdentifiers k = do
2019-02-20 21:22:56 +00:00
config <- Annex.getGitConfig
map (\(u, l) -> (RemoteStateHandle u, NonEmpty.toList l) )
. M.toList . simpleMap . parseLog
2019-02-20 21:22:56 +00:00
<$> Annex.Branch.get (remoteContentIdentifierLogFile config k)