ee251b2e2e
untested This won't be super slow, but it does need to diff two likely large trees, and since the git-annex branch rarely sits still, it will most likely be run at the beginning of every import. A possible speed improvement would be to only run this when the database did not contain a ContentIdentifier. But that would only speed up imports when there is no new version of a file on the special remote, at most renames of existing files being imported. A better speed improvement would be to record something in the git-annex branch that indicates when an import has been run, and only do the diff if the git-annex branch has record of a newer import than we've seen before. Then, it would only run when there is in fact new ContentIdentifier information available from a remote. Certianly doable, but didn't want to complicate things yet.
47 lines
1.4 KiB
Haskell
47 lines
1.4 KiB
Haskell
{- 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,
|
|
recordContentIdentifier,
|
|
getContentIdentifiers,
|
|
) where
|
|
|
|
import Annex.Common
|
|
import Logs
|
|
import Logs.MapLog
|
|
import Types.Import
|
|
import qualified Annex.Branch
|
|
import Logs.ContentIdentifier.Pure as X
|
|
import qualified Annex
|
|
|
|
import qualified Data.Map as M
|
|
import Data.List.NonEmpty (NonEmpty(..))
|
|
import qualified Data.List.NonEmpty as NonEmpty
|
|
|
|
-- | 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 :: UUID -> ContentIdentifier -> Key -> Annex ()
|
|
recordContentIdentifier u cid k = do
|
|
c <- liftIO currentVectorClock
|
|
config <- Annex.getGitConfig
|
|
Annex.Branch.change (remoteContentIdentifierLogFile config k) $
|
|
buildLog . addcid c . parseLog
|
|
where
|
|
addcid c l = changeMapLog c u (cid :| contentIdentifierList (M.lookup u m)) l
|
|
where
|
|
m = simpleMap l
|
|
|
|
-- | Get all known content identifiers for a key.
|
|
getContentIdentifiers :: Key -> Annex [(UUID, [ContentIdentifier])]
|
|
getContentIdentifiers k = do
|
|
config <- Annex.getGitConfig
|
|
map (\(u, l) -> (u, NonEmpty.toList l) )
|
|
. M.toList . simpleMap . parseLog
|
|
<$> Annex.Branch.get (remoteContentIdentifierLogFile config k)
|