git-annex/Logs/Group.hs
Joey Hess 2cecc8d2a3
Added GIT_ANNEX_VECTOR_CLOCK environment variable
Can be used to override the default timestamps used in log files in the
git-annex branch. This is a dangerous environment variable; use with
caution.

Note that this only affects writing to the logs on the git-annex branch.
It is not used for metadata in git commits (other env vars can be set for
that).

There are many other places where timestamps are still used, that don't
get committed to git, but do touch disk. Including regular timestamps
of files, and timestamps embedded in some files in .git/annex/, including
the last fsck timestamp and timestamps in transfer log files.

A good way to find such things in git-annex is to get for getPOSIXTime and
getCurrentTime, although some of the results are of course false positives
that never hit disk (unless git-annex gets swapped out..)

So this commit does NOT necessarily make git-annex comply with some HIPPA
privacy regulations; it's up to the user to determine if they can use it in
a way compliant with such regulations.

Benchmarking: It takes 0.00114 milliseconds to call getEnv
"GIT_ANNEX_VECTOR_CLOCK" when that env var is not set. So, 100 thousand log
files can be written with an added overhead of only 0.114 seconds. That
should be by far swamped by the actual overhead of writing the log files
and making the commit containing them.

This commit was supported by the NSF-funded DataLad project.
2017-08-14 14:19:58 -04:00

82 lines
2.3 KiB
Haskell

{- git-annex group log
-
- Copyright 2012 Joey Hess <id@joeyh.name>
-
- Licensed under the GNU GPL version 3 or higher.
-}
module Logs.Group (
groupLog,
groupChange,
groupSet,
lookupGroups,
groupMap,
groupMapLoad,
getStandardGroup,
inUnwantedGroup
) where
import qualified Data.Map as M
import qualified Data.Set as S
import Annex.Common
import Logs
import qualified Annex.Branch
import qualified Annex
import Logs.UUIDBased
import Types.Group
import Types.StandardGroups
{- Returns the groups of a given repo UUID. -}
lookupGroups :: UUID -> Annex (S.Set Group)
lookupGroups u = (fromMaybe S.empty . M.lookup u) . groupsByUUID <$> groupMap
{- Applies a set modifier to change the groups for a uuid in the groupLog. -}
groupChange :: UUID -> (S.Set Group -> S.Set Group) -> Annex ()
groupChange uuid@(UUID _) modifier = do
curr <- lookupGroups uuid
c <- liftIO currentVectorClock
Annex.Branch.change groupLog $
showLog (unwords . S.toList) .
changeLog c uuid (modifier curr) .
parseLog (Just . S.fromList . words)
-- The changed group invalidates the preferred content cache.
Annex.changeState $ \s -> s
{ Annex.groupmap = Nothing
, Annex.preferredcontentmap = Nothing
}
groupChange NoUUID _ = error "unknown UUID; cannot modify"
groupSet :: UUID -> S.Set Group -> Annex ()
groupSet u g = groupChange u (const g)
{- The map is cached for speed. -}
groupMap :: Annex GroupMap
groupMap = maybe groupMapLoad return =<< Annex.getState Annex.groupmap
{- Loads the map, updating the cache. -}
groupMapLoad :: Annex GroupMap
groupMapLoad = do
m <- makeGroupMap . simpleMap .
parseLog (Just . S.fromList . words) <$>
Annex.Branch.get groupLog
Annex.changeState $ \s -> s { Annex.groupmap = Just m }
return m
makeGroupMap :: M.Map UUID (S.Set Group) -> GroupMap
makeGroupMap byuuid = GroupMap byuuid bygroup
where
bygroup = M.fromListWith S.union $
concatMap explode $ M.toList byuuid
explode (u, s) = map (\g -> (g, S.singleton u)) (S.toList s)
{- If a repository is in exactly one standard group, returns it. -}
getStandardGroup :: S.Set Group -> Maybe StandardGroup
getStandardGroup s = case mapMaybe toStandardGroup $ S.toList s of
[g] -> Just g
_ -> Nothing
inUnwantedGroup :: UUID -> Annex Bool
inUnwantedGroup u = elem UnwantedGroup
. mapMaybe toStandardGroup . S.toList <$> lookupGroups u