2013-10-07 20:06:34 +00:00
|
|
|
{- git-annex scheduled activities log
|
|
|
|
-
|
2015-01-21 16:50:09 +00:00
|
|
|
- Copyright 2013 Joey Hess <id@joeyh.name>
|
2013-10-07 20:06:34 +00:00
|
|
|
-
|
2019-03-13 19:48:14 +00:00
|
|
|
- Licensed under the GNU AGPL version 3 or higher.
|
2013-10-07 20:06:34 +00:00
|
|
|
-}
|
|
|
|
|
|
|
|
module Logs.Schedule (
|
|
|
|
scheduleLog,
|
|
|
|
scheduleSet,
|
2013-10-11 06:57:36 +00:00
|
|
|
scheduleAdd,
|
|
|
|
scheduleRemove,
|
|
|
|
scheduleChange,
|
2013-10-07 20:06:34 +00:00
|
|
|
scheduleGet,
|
2013-10-07 21:11:13 +00:00
|
|
|
scheduleMap,
|
2013-10-08 15:48:28 +00:00
|
|
|
getLastRunTimes,
|
|
|
|
setLastRunTime,
|
2013-10-07 20:06:34 +00:00
|
|
|
) where
|
|
|
|
|
|
|
|
import qualified Data.Map as M
|
2013-10-08 15:48:28 +00:00
|
|
|
import qualified Data.Set as S
|
|
|
|
import Data.Time.LocalTime
|
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 18:39:36 +00:00
|
|
|
import qualified Data.Attoparsec.ByteString.Lazy as A
|
2019-01-09 18:00:35 +00:00
|
|
|
import Data.ByteString.Builder
|
2013-10-07 20:06:34 +00:00
|
|
|
|
2016-01-20 20:36:33 +00:00
|
|
|
import Annex.Common
|
2013-10-07 20:06:34 +00:00
|
|
|
import Types.ScheduledActivity
|
|
|
|
import qualified Annex.Branch
|
|
|
|
import Logs
|
|
|
|
import Logs.UUIDBased
|
2018-01-02 21:17:10 +00:00
|
|
|
import Logs.File
|
2013-10-07 20:06:34 +00:00
|
|
|
|
|
|
|
scheduleSet :: UUID -> [ScheduledActivity] -> Annex ()
|
|
|
|
scheduleSet uuid@(UUID _) activities = do
|
2020-12-23 19:21:33 +00:00
|
|
|
c <- currentVectorClock
|
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.change (Annex.Branch.RegardingUUID [uuid]) scheduleLog $
|
2019-02-21 17:43:21 +00:00
|
|
|
buildLogOld byteString
|
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 18:39:36 +00:00
|
|
|
. changeLog c uuid (encodeBS val)
|
2019-02-21 17:43:21 +00:00
|
|
|
. parseLogOld A.takeByteString
|
2013-10-07 20:06:34 +00:00
|
|
|
where
|
2014-10-09 18:53:13 +00:00
|
|
|
val = fromScheduledActivities activities
|
2013-10-07 20:06:34 +00:00
|
|
|
scheduleSet NoUUID _ = error "unknown UUID; cannot modify"
|
|
|
|
|
|
|
|
scheduleMap :: Annex (M.Map UUID [ScheduledActivity])
|
2019-02-21 17:43:21 +00:00
|
|
|
scheduleMap = simpleMap . parseLogOld parser <$> Annex.Branch.get scheduleLog
|
2013-10-07 20:06:34 +00:00
|
|
|
where
|
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 18:39:36 +00:00
|
|
|
parser = either fail pure . parseScheduledActivities . decodeBS
|
|
|
|
=<< A.takeByteString
|
2013-10-07 20:06:34 +00:00
|
|
|
|
2013-10-08 15:48:28 +00:00
|
|
|
scheduleGet :: UUID -> Annex (S.Set ScheduledActivity)
|
2013-10-07 20:06:34 +00:00
|
|
|
scheduleGet u = do
|
|
|
|
m <- scheduleMap
|
2013-10-08 15:48:28 +00:00
|
|
|
return $ maybe S.empty S.fromList (M.lookup u m)
|
|
|
|
|
2013-10-11 06:57:36 +00:00
|
|
|
scheduleRemove :: UUID -> ScheduledActivity -> Annex ()
|
|
|
|
scheduleRemove u activity = scheduleChange u $ S.delete activity
|
|
|
|
|
|
|
|
scheduleAdd :: UUID -> ScheduledActivity -> Annex ()
|
|
|
|
scheduleAdd u activity = scheduleChange u $ S.insert activity
|
|
|
|
|
|
|
|
scheduleChange :: UUID -> (S.Set ScheduledActivity -> S.Set ScheduledActivity) -> Annex ()
|
|
|
|
scheduleChange u a = scheduleSet u . S.toList . a =<< scheduleGet u
|
|
|
|
|
2013-10-08 15:48:28 +00:00
|
|
|
getLastRunTimes :: Annex (M.Map ScheduledActivity LocalTime)
|
|
|
|
getLastRunTimes = do
|
2020-10-29 18:20:57 +00:00
|
|
|
f <- fromRawFilePath <$> fromRepo gitAnnexScheduleState
|
2013-10-08 15:48:28 +00:00
|
|
|
liftIO $ fromMaybe M.empty
|
|
|
|
<$> catchDefaultIO Nothing (readish <$> readFile f)
|
|
|
|
|
|
|
|
setLastRunTime :: ScheduledActivity -> LocalTime -> Annex ()
|
|
|
|
setLastRunTime activity lastrun = do
|
|
|
|
f <- fromRepo gitAnnexScheduleState
|
2018-01-02 21:17:10 +00:00
|
|
|
writeLogFile f . show . M.insert activity lastrun
|
2013-10-08 15:48:28 +00:00
|
|
|
=<< getLastRunTimes
|