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this journal, and so will not be published into the git-annex branch.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.

Logs/Activity.hs

@@ -28,7 +28,7 @@ data Activity
 recordActivity :: Activity -> UUID -> Annex ()
 recordActivity act uuid = do
 	c <- currentVectorClock
-	Annex.Branch.change activityLog $
+	Annex.Branch.change (Annex.Branch.RegardingUUID [uuid]) activityLog $
 		buildLogOld buildActivity
 			. changeLog c uuid (Right act)
 			. parseLogOld parseActivity

Logs/Chunk.hs

@@ -37,8 +37,10 @@ chunksStored :: UUID -> Key -> ChunkMethod -> ChunkCount -> Annex ()
 chunksStored u k chunkmethod chunkcount = do
 	c <- currentVectorClock
 	config <- Annex.getGitConfig
-	Annex.Branch.change (chunkLogFile config k) $
-		buildLog . changeMapLog c (u, chunkmethod) chunkcount . parseLog
+	Annex.Branch.change
+		(Annex.Branch.RegardingUUID [u])
+		(chunkLogFile config k)
+		(buildLog . changeMapLog c (u, chunkmethod) chunkcount . parseLog)
 
 chunksRemoved :: UUID -> Key -> ChunkMethod -> Annex ()
 chunksRemoved u k chunkmethod = chunksStored u k chunkmethod 0

Logs/Config.hs

@@ -35,7 +35,7 @@ setGlobalConfig name new = do
 setGlobalConfig' :: ConfigKey -> ConfigValue -> Annex ()
 setGlobalConfig' name new = do
 	c <- currentVectorClock
-	Annex.Branch.change configLog $ 
+	Annex.Branch.change (Annex.Branch.RegardingUUID []) configLog $ 
 		buildGlobalConfig . changeMapLog c name new . parseGlobalConfig
 
 unsetGlobalConfig :: ConfigKey -> Annex ()

Logs/ContentIdentifier.hs

@@ -32,8 +32,10 @@ recordContentIdentifier :: RemoteStateHandle -> ContentIdentifier -> Key -> Anne
 recordContentIdentifier (RemoteStateHandle u) cid k = do
 	c <- currentVectorClock
 	config <- Annex.getGitConfig
-	Annex.Branch.maybeChange (remoteContentIdentifierLogFile config k) $
-		addcid c . parseLog
+	Annex.Branch.maybeChange
+		(Annex.Branch.RegardingUUID [u])
+		(remoteContentIdentifierLogFile config k)
+		(addcid c . parseLog)
   where
 	addcid c v
 		| cid `elem` l = Nothing -- no change needed

Logs/Difference.hs

@@ -26,7 +26,7 @@ import Logs.Difference.Pure
 recordDifferences :: Differences -> UUID -> Annex ()
 recordDifferences ds@(Differences {}) uuid = do
 	c <- currentVectorClock
-	Annex.Branch.change differenceLog $
+	Annex.Branch.change (Annex.Branch.RegardingUUID [uuid]) differenceLog $
 		buildLogOld byteString 
 			. changeLog c uuid (encodeBS $ showDifferences ds) 
 			. parseLogOld A.takeByteString

Logs/Export.hs

@@ -65,10 +65,10 @@ recordExportBeginning remoteuuid newtree = do
 		. parseExportLogMap
 		<$> Annex.Branch.get exportLog
 	let new = updateIncompleteExportedTreeish old (nub (newtree:incompleteExportedTreeishes [old]))
-	Annex.Branch.change exportLog $
-		buildExportLog 
-			. changeMapLog c ep new
-			. parseExportLog
+	Annex.Branch.change
+		(Annex.Branch.RegardingUUID [remoteuuid, u])
+		exportLog
+		(buildExportLog . changeMapLog c ep new . parseExportLog)
 	recordExportTreeish newtree
 
 -- Graft a tree ref into the git-annex branch. This is done
@@ -96,7 +96,9 @@ recordExportUnderway remoteuuid ec = do
 	hereuuid <- getUUID
 	let ep = ExportParticipants { exportFrom = hereuuid, exportTo = remoteuuid }
 	let exported = mkExported (newTreeish ec) []
-	Annex.Branch.change exportLog $
+	Annex.Branch.change
+		(Annex.Branch.RegardingUUID [remoteuuid, hereuuid]) 
+		exportLog $
 		buildExportLog
 			. changeMapLog c ep exported 
 			. M.mapWithKey (updateForExportChange remoteuuid ec c hereuuid)

Logs/Group.hs

@@ -39,7 +39,7 @@ groupChange :: UUID -> (S.Set Group -> S.Set Group) -> Annex ()
 groupChange uuid@(UUID _) modifier = do
 	curr <- lookupGroups uuid
 	c <- currentVectorClock
-	Annex.Branch.change groupLog $
+	Annex.Branch.change (Annex.Branch.RegardingUUID [uuid]) groupLog $
 		buildLogOld buildGroup . changeLog c uuid (modifier curr) . parseLogOld parseGroup
 	
 	-- The changed group invalidates the preferred content cache.

Logs/Location.hs

@@ -66,7 +66,8 @@ logChange = logChange' logNow
 logChange' :: (LogStatus -> LogInfo -> Annex LogLine) -> Key -> UUID -> LogStatus -> Annex ()
 logChange' mklog key u@(UUID _) s = do
 	config <- Annex.getGitConfig
-	maybeAddLog (locationLogFile config key) =<< mklog s (LogInfo (fromUUID u))
+	maybeAddLog (Annex.Branch.RegardingUUID [u]) (locationLogFile config key)
+		=<< mklog s (LogInfo (fromUUID u))
 logChange' _ _ NoUUID _ = noop
 
 {- Returns a list of repository UUIDs that, according to the log, have
@@ -114,7 +115,9 @@ setDead key = do
 	ls <- compactLog <$> readLog logfile
 	mapM_ (go logfile) (filter (\l -> status l == InfoMissing) ls)
   where
-	go logfile l = addLog logfile $ setDead' l
+	go logfile l = 
+		let u = toUUID (fromLogInfo (info l))
+		in addLog (Annex.Branch.RegardingUUID [u]) logfile (setDead' l)
 
 {- Note that the timestamp in the log is updated minimally, so that this
  - can be overruled by other location log changes. -}

Logs/MetaData.hs

@@ -99,25 +99,25 @@ getCurrentRemoteMetaData (RemoteStateHandle u) k = extractRemoteMetaData u <$>
 {- Adds in some metadata, which can override existing values, or unset
  - them, but otherwise leaves any existing metadata as-is. -}
 addMetaData :: Key -> MetaData -> Annex ()
-addMetaData = addMetaData' metaDataLogFile
+addMetaData = addMetaData' (Annex.Branch.RegardingUUID []) metaDataLogFile
 
-addMetaData' :: (GitConfig -> Key -> RawFilePath) -> Key -> MetaData -> Annex ()
-addMetaData' getlogfile k metadata = 
-	addMetaDataClocked' getlogfile k metadata =<< currentVectorClock
+addMetaData' :: Annex.Branch.RegardingUUID -> (GitConfig -> Key -> RawFilePath) -> Key -> MetaData -> Annex ()
+addMetaData' ru getlogfile k metadata = 
+	addMetaDataClocked' ru getlogfile k metadata =<< currentVectorClock
 
 {- Reusing the same VectorClock when making changes to the metadata
  - of multiple keys is a nice optimisation. The same metadata lines
  - will tend to be generated across the different log files, and so
  - git will be able to pack the data more efficiently. -}
 addMetaDataClocked :: Key -> MetaData -> VectorClock -> Annex ()
-addMetaDataClocked = addMetaDataClocked' metaDataLogFile
+addMetaDataClocked = addMetaDataClocked' (Annex.Branch.RegardingUUID []) metaDataLogFile
 
-addMetaDataClocked' :: (GitConfig -> Key -> RawFilePath) -> Key -> MetaData -> VectorClock -> Annex ()
-addMetaDataClocked' getlogfile k d@(MetaData m) c
+addMetaDataClocked' :: Annex.Branch.RegardingUUID -> (GitConfig -> Key -> RawFilePath) -> Key -> MetaData -> VectorClock -> Annex ()
+addMetaDataClocked' ru getlogfile k d@(MetaData m) c
 	| d == emptyMetaData = noop
 	| otherwise = do
 		config <- Annex.getGitConfig
-		Annex.Branch.change (getlogfile config k) $
+		Annex.Branch.change ru (getlogfile config k) $
 			buildLog . simplifyLog 
 				. S.insert (LogEntry c metadata)
 				. parseLog
@@ -126,7 +126,7 @@ addMetaDataClocked' getlogfile k d@(MetaData m) c
 
 addRemoteMetaData :: Key -> RemoteStateHandle -> MetaData -> Annex ()
 addRemoteMetaData k (RemoteStateHandle u) m = 
-	addMetaData' remoteMetaDataLogFile k $ fromRemoteMetaData $
+	addMetaData' (Annex.Branch.RegardingUUID [u]) remoteMetaDataLogFile k $ fromRemoteMetaData $
 		RemoteMetaData u m
 
 getMetaDataLog :: Key -> Annex (Log MetaData)
@@ -153,8 +153,10 @@ copyMetaData oldkey newkey
 			then return False
 			else do
 				config <- Annex.getGitConfig
-				Annex.Branch.change (metaDataLogFile config newkey) $
-					const $ buildLog l
+				Annex.Branch.change
+					(Annex.Branch.RegardingUUID [])
+					(metaDataLogFile config newkey)
+					(const $ buildLog l)
 				return True
 
 readLog :: RawFilePath -> Annex (Log MetaData)

Logs/Multicast.hs

@@ -26,7 +26,7 @@ newtype Fingerprint = Fingerprint String
 recordFingerprint :: Fingerprint -> UUID -> Annex ()
 recordFingerprint fp uuid = do
 	c <- currentVectorClock
-	Annex.Branch.change multicastLog $
+	Annex.Branch.change (Annex.Branch.RegardingUUID [uuid]) multicastLog $
 		buildLogOld buildFindgerPrint
 			. changeLog c uuid fp
 			. parseLogOld fingerprintParser

Logs/NumCopies.hs

@@ -18,6 +18,7 @@ module Logs.NumCopies (
 
 import Annex.Common
 import qualified Annex
+import qualified Annex.Branch
 import Types.NumCopies
 import Logs
 import Logs.SingleValue
@@ -34,13 +35,13 @@ setGlobalNumCopies :: NumCopies -> Annex ()
 setGlobalNumCopies new = do
 	curr <- getGlobalNumCopies
 	when (curr /= Just new) $
-		setLog numcopiesLog new
+		setLog (Annex.Branch.RegardingUUID []) numcopiesLog new
 
 setGlobalMinCopies :: MinCopies -> Annex ()
 setGlobalMinCopies new = do
 	curr <- getGlobalMinCopies
 	when (curr /= Just new) $
-		setLog mincopiesLog new
+		setLog (Annex.Branch.RegardingUUID []) mincopiesLog new
 
 {- Value configured in the numcopies log. Cached for speed. -}
 getGlobalNumCopies :: Annex (Maybe NumCopies)

Logs/PreferredContent/Raw.hs

@@ -31,7 +31,7 @@ requiredContentSet = setLog requiredContentLog
 setLog :: RawFilePath -> UUID -> PreferredContentExpression -> Annex ()
 setLog logfile uuid@(UUID _) val = do
 	c <- currentVectorClock
-	Annex.Branch.change logfile $
+	Annex.Branch.change (Annex.Branch.RegardingUUID [uuid]) logfile $
 		buildLogOld buildPreferredContentExpression
 		. changeLog c uuid val
 		. parseLogOld parsePreferredContentExpression
@@ -45,7 +45,9 @@ setLog _ NoUUID _ = error "unknown UUID; cannot modify"
 groupPreferredContentSet :: Group -> PreferredContentExpression -> Annex ()
 groupPreferredContentSet g val = do
 	c <- currentVectorClock
-	Annex.Branch.change groupPreferredContentLog $
+	Annex.Branch.change
+		(Annex.Branch.RegardingUUID [])
+		groupPreferredContentLog $
 		buildGroupPreferredContent
 		. changeMapLog c g val 
 		. parseGroupPreferredContent

Logs/Presence.hs

@@ -30,16 +30,16 @@ import Git.Types (RefDate)
 
 {- Adds a LogLine to the log, removing any LogLines that are obsoleted by
  - adding it. -}
-addLog :: RawFilePath -> LogLine -> Annex ()
-addLog file line = Annex.Branch.change file $ \b ->
+addLog :: Annex.Branch.RegardingUUID -> RawFilePath -> LogLine -> Annex ()
+addLog ru file line = Annex.Branch.change ru file $ \b ->
 	buildLog $ compactLog (line : parseLog b)
 
 {- When a LogLine already exists with the same status and info, but an
  - older timestamp, that LogLine is preserved, rather than updating the log
  - with a newer timestamp.
  -}
-maybeAddLog :: RawFilePath -> LogLine -> Annex ()
-maybeAddLog file line = Annex.Branch.maybeChange file $ \s -> do
+maybeAddLog :: Annex.Branch.RegardingUUID -> RawFilePath -> LogLine -> Annex ()
+maybeAddLog ru file line = Annex.Branch.maybeChange ru file $ \s -> do
 	m <- insertNewStatus line $ logMap $ parseLog s
 	return $ buildLog $ mapLog m
 

Logs/Remote.hs

@@ -33,7 +33,7 @@ import qualified Data.Map as M
 configSet :: UUID -> RemoteConfig -> Annex ()
 configSet u cfg = do
 	c <- currentVectorClock
-	Annex.Branch.change remoteLog $
+	Annex.Branch.change (Annex.Branch.RegardingUUID [u]) remoteLog $
 		buildRemoteConfigLog
 			. changeLog c u (removeSameasInherited cfg)
 			. parseRemoteConfigLog

Logs/RemoteState.hs

@@ -28,8 +28,10 @@ setRemoteState :: RemoteStateHandle -> Key -> RemoteState -> Annex ()
 setRemoteState (RemoteStateHandle u) k s = do
 	c <- currentVectorClock
 	config <- Annex.getGitConfig
-	Annex.Branch.change (remoteStateLogFile config k) $
-		buildRemoteState . changeLog c u s . parseRemoteState
+	Annex.Branch.change
+		(Annex.Branch.RegardingUUID [u])
+		(remoteStateLogFile config k)
+		(buildRemoteState . changeLog c u s . parseRemoteState)
 
 buildRemoteState :: Log RemoteState -> Builder
 buildRemoteState = buildLogNew (byteString . encodeBS)

Logs/Schedule.hs

@@ -33,7 +33,7 @@ import Logs.File
 scheduleSet :: UUID -> [ScheduledActivity] -> Annex ()
 scheduleSet uuid@(UUID _) activities = do
 	c <- currentVectorClock
-	Annex.Branch.change scheduleLog $
+	Annex.Branch.change (Annex.Branch.RegardingUUID [uuid]) scheduleLog $
 		buildLogOld byteString 
 			. changeLog c uuid (encodeBS val)
 			. parseLogOld A.takeByteString

Logs/SingleValue.hs

@@ -31,8 +31,8 @@ readLog = parseLog <$$> Annex.Branch.get
 getLog :: (Ord v, SingleValueSerializable v) => RawFilePath -> Annex (Maybe v)
 getLog = newestValue <$$> readLog
 
-setLog :: (SingleValueSerializable v) => RawFilePath -> v -> Annex ()
-setLog f v = do
+setLog :: (SingleValueSerializable v) => Annex.Branch.RegardingUUID -> RawFilePath -> v -> Annex ()
+setLog ru f v = do
 	c <- currentVectorClock
 	let ent = LogEntry c v
-	Annex.Branch.change f $ \_old -> buildLog (S.singleton ent)
+	Annex.Branch.change ru f $ \_old -> buildLog (S.singleton ent)

Logs/Trust/Basic.hs

@@ -23,7 +23,7 @@ import Logs.Trust.Pure as X
 trustSet :: UUID -> TrustLevel -> Annex ()
 trustSet uuid@(UUID _) level = do
 	c <- currentVectorClock
-	Annex.Branch.change trustLog $
+	Annex.Branch.change (Annex.Branch.RegardingUUID [uuid]) trustLog $
 		buildLogOld buildTrustLevel .
 			changeLog c uuid level .
 				parseLogOld trustLevelParser

Logs/UUID.hs

@@ -32,7 +32,7 @@ import qualified Data.Attoparsec.ByteString.Lazy as A
 describeUUID :: UUID -> UUIDDesc -> Annex ()
 describeUUID uuid desc = do
 	c <- currentVectorClock
-	Annex.Branch.change uuidLog $
+	Annex.Branch.change (Annex.Branch.RegardingUUID [uuid]) uuidLog $
 		buildLogOld buildUUIDDesc . changeLog c uuid desc . parseUUIDLog
 
 {- The map is cached for speed. -}

Logs/Web.hs

@@ -62,7 +62,7 @@ setUrlPresent key url = do
 	us <- getUrls key
 	unless (url `elem` us) $ do
 		config <- Annex.getGitConfig
-		addLog (urlLogFile config key)
+		addLog (Annex.Branch.RegardingUUID []) (urlLogFile config key)
 			=<< logNow InfoPresent (LogInfo (encodeBS url))
 	-- If the url does not have an OtherDownloader, it must be present
 	-- in the web.
@@ -76,7 +76,7 @@ setUrlMissing key url = do
 	us <- getUrls key
 	when (url `elem` us) $ do
 		config <- Annex.getGitConfig
-		addLog (urlLogFile config key)
+		addLog (Annex.Branch.RegardingUUID []) (urlLogFile config key)
 			=<< logNow InfoMissing (LogInfo (encodeBS url))
 		-- If the url was a web url and none of the remaining urls
 		-- for the key are web urls, the key must not be present