git-annex/Logs/Web.hs

140 lines
4.1 KiB
Haskell
Raw Normal View History

{- Web url logs.
-
- Copyright 2011-2023 Joey Hess <id@joeyh.name>
-
- Licensed under the GNU AGPL version 3 or higher.
-}
{-# LANGUAGE BangPatterns #-}
module Logs.Web (
URLString,
URLByteString,
2012-11-29 21:01:07 +00:00
getUrls,
getUrls',
getUrlsWithPrefix,
setUrlPresent,
2012-11-29 21:01:07 +00:00
setUrlMissing,
Downloader(..),
getDownloader,
setDownloader,
2016-01-19 19:55:32 +00:00
setDownloader',
setTempUrl,
removeTempUrl,
2021-04-23 15:44:10 +00:00
parseUrlLog,
) where
import qualified Data.Map as M
import qualified Data.ByteString as S
2021-04-23 15:44:10 +00:00
import qualified Data.ByteString.Lazy as L
import Annex.Common
import qualified Annex
import Logs
import Logs.Presence
import Logs.Location
2014-12-08 17:40:15 +00:00
import Utility.Url
2016-01-19 19:55:32 +00:00
import Annex.UUID
2021-04-23 17:26:10 +00:00
import qualified Annex.Branch
2016-01-19 19:55:32 +00:00
import qualified Types.Remote as Remote
type URLByteString = S.ByteString
{- Gets all urls that a key might be available from. -}
getUrls :: Key -> Annex [URLString]
getUrls key = do
l <- map decodeBS <$> getUrls' key
tmpl <- Annex.getState (maybeToList . M.lookup key . Annex.tempurls)
return (tmpl ++ l)
{- Note that this does not include temporary urls set with setTempUrl. -}
getUrls' :: Key -> Annex [URLByteString]
getUrls' key = do
config <- Annex.getGitConfig
go $ urlLogFile config key : oldurlLogs config key
2012-11-11 04:51:07 +00:00
where
go [] = return []
go (l:ls) = do
us <- currentLogInfo l
2012-11-11 04:51:07 +00:00
if null us
then go ls
else return $ map fromLogInfo us
getUrlsWithPrefix :: Key -> String -> Annex [URLString]
getUrlsWithPrefix key prefix = filter (prefix `isPrefixOf`)
. map (fst . getDownloader)
<$> getUrls key
setUrlPresent :: Key -> URLString -> Annex ()
setUrlPresent key url = do
-- Avoid reading the url log when not compacting, for speed.
us <- ifM (annexAlwaysCompact <$> Annex.getGitConfig)
( getUrls key
, pure mempty
)
unless (url `elem` us) $ do
config <- Annex.getGitConfig
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 Changes that are regarding a UUID that is private will get written to this journal, and so will not be published into the git-annex branch.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
addLog (Annex.Branch.RegardingUUID []) (urlLogFile config key)
deal better with clock skew situations, using vector clocks * Deal with clock skew, both forwards and backwards, when logging information to the git-annex branch. * GIT_ANNEX_VECTOR_CLOCK can now be set to a fixed value (eg 1) rather than needing to be advanced each time a new change is made. * Misuse of GIT_ANNEX_VECTOR_CLOCK will no longer confuse git-annex. When changing a file in the git-annex branch, the vector clock to use is now determined by first looking at the current time (or GIT_ANNEX_VECTOR_CLOCK when set), and comparing it to the newest vector clock already in use in that file. If a newer time stamp was already in use, advance it forward by a second instead. When the clock is set to a time in the past, this avoids logging with an old timestamp, which would risk that log line later being ignored in favor of "newer" line that is really not newer. When a log entry has been made with a clock that was set far ahead in the future, this avoids newer information being logged with an older timestamp and so being ignored in favor of that future-timestamped information. Once all clocks get fixed, this will result in the vector clocks being incremented, until finally enough time has passed that time gets back ahead of the vector clock value, and then it will return to usual operation. (This latter situation is not ideal, but it seems the best that can be done. The issue with it is, since all writers will be incrementing the last vector clock they saw, there's no way to tell when one writer made a write significantly later in time than another, so the earlier write might arbitrarily be picked when merging. This problem is why git-annex uses timestamps in the first place, rather than pure vector clocks.) Advancing forward by 1 second is somewhat arbitrary. setDead advances a timestamp by just 1 picosecond, and the vector clock could too. But then it would interfere with setDead, which wants to be overrulled by any change. So it could use 2 picoseconds or something, but that seems weird. It could just as well advance it forward by a minute or whatever, but then it would be harder for real time to catch up with the vector clock when forward clock slew had happened. A complication is that many log files contain several different peices of information, and it may be best to only use vector clocks for the same peice of information. For example, a key's location log file contains InfoPresent/InfoMissing for each UUID, and it only looks at the vector clocks for the UUID that is being changed, and not other UUIDs. Although exactly where the dividing line is can be hard to determine. Consider metadata logs, where a field "tag" can have multiple values set at different times. Should it advance forward past the last tag? Probably. What about when a different field is set, should it look at the clocks of other fields? Perhaps not, but currently it does, and this does not seems like it will cause any problems. Another one I'm not entirely sure about is the export log, which is keyed by (fromuuid, touuid). So if multiple repos are exporting to the same remote, different vector clocks can be used for that remote. It looks like that's probably ok, because it does not try to determine what order things occurred when there was an export conflict. Sponsored-by: Jochen Bartl on Patreon
2021-08-03 20:45:20 +00:00
InfoPresent (LogInfo (encodeBS url))
-- If the url does not have an OtherDownloader, it must be present
-- in the web.
case snd (getDownloader url) of
OtherDownloader -> return ()
_ -> logChange key webUUID InfoPresent
setUrlMissing :: Key -> URLString -> Annex ()
setUrlMissing key url = do
-- Avoid making any changes if the url was not registered.
us <- getUrls key
when (url `elem` us) $ do
config <- Annex.getGitConfig
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
addLog (Annex.Branch.RegardingUUID []) (urlLogFile config key)
deal better with clock skew situations, using vector clocks * Deal with clock skew, both forwards and backwards, when logging information to the git-annex branch. * GIT_ANNEX_VECTOR_CLOCK can now be set to a fixed value (eg 1) rather than needing to be advanced each time a new change is made. * Misuse of GIT_ANNEX_VECTOR_CLOCK will no longer confuse git-annex. When changing a file in the git-annex branch, the vector clock to use is now determined by first looking at the current time (or GIT_ANNEX_VECTOR_CLOCK when set), and comparing it to the newest vector clock already in use in that file. If a newer time stamp was already in use, advance it forward by a second instead. When the clock is set to a time in the past, this avoids logging with an old timestamp, which would risk that log line later being ignored in favor of "newer" line that is really not newer. When a log entry has been made with a clock that was set far ahead in the future, this avoids newer information being logged with an older timestamp and so being ignored in favor of that future-timestamped information. Once all clocks get fixed, this will result in the vector clocks being incremented, until finally enough time has passed that time gets back ahead of the vector clock value, and then it will return to usual operation. (This latter situation is not ideal, but it seems the best that can be done. The issue with it is, since all writers will be incrementing the last vector clock they saw, there's no way to tell when one writer made a write significantly later in time than another, so the earlier write might arbitrarily be picked when merging. This problem is why git-annex uses timestamps in the first place, rather than pure vector clocks.) Advancing forward by 1 second is somewhat arbitrary. setDead advances a timestamp by just 1 picosecond, and the vector clock could too. But then it would interfere with setDead, which wants to be overrulled by any change. So it could use 2 picoseconds or something, but that seems weird. It could just as well advance it forward by a minute or whatever, but then it would be harder for real time to catch up with the vector clock when forward clock slew had happened. A complication is that many log files contain several different peices of information, and it may be best to only use vector clocks for the same peice of information. For example, a key's location log file contains InfoPresent/InfoMissing for each UUID, and it only looks at the vector clocks for the UUID that is being changed, and not other UUIDs. Although exactly where the dividing line is can be hard to determine. Consider metadata logs, where a field "tag" can have multiple values set at different times. Should it advance forward past the last tag? Probably. What about when a different field is set, should it look at the clocks of other fields? Perhaps not, but currently it does, and this does not seems like it will cause any problems. Another one I'm not entirely sure about is the export log, which is keyed by (fromuuid, touuid). So if multiple repos are exporting to the same remote, different vector clocks can be used for that remote. It looks like that's probably ok, because it does not try to determine what order things occurred when there was an export conflict. Sponsored-by: Jochen Bartl on Patreon
2021-08-03 20:45:20 +00:00
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
-- in the web.
when (isweb url && null (filter isweb $ filter (/= url) us)) $
logChange key webUUID InfoMissing
where
isweb u = case snd (getDownloader u) of
OtherDownloader -> False
_ -> True
setTempUrl :: Key -> URLString -> Annex ()
setTempUrl key url = Annex.changeState $ \s ->
s { Annex.tempurls = M.insert key url (Annex.tempurls s) }
removeTempUrl :: Key -> Annex ()
removeTempUrl key = Annex.changeState $ \s ->
s { Annex.tempurls = M.delete key (Annex.tempurls s) }
2017-11-28 21:17:40 +00:00
data Downloader = WebDownloader | YoutubeDownloader | QuviDownloader | OtherDownloader
deriving (Eq, Show, Enum, Bounded)
{- To keep track of how an url is downloaded, it's mangled slightly in
2017-11-28 21:17:40 +00:00
- the log, with a prefix indicating when a Downloader is used. -}
setDownloader :: URLString -> Downloader -> String
setDownloader u WebDownloader = u
setDownloader u QuviDownloader = "quvi:" ++ u
2017-11-28 21:17:40 +00:00
setDownloader u YoutubeDownloader = "yt:" ++ u
setDownloader u OtherDownloader = ":" ++ u
2016-01-19 19:55:32 +00:00
setDownloader' :: URLString -> Remote -> String
setDownloader' u r
| Remote.uuid r == webUUID = setDownloader u WebDownloader
| otherwise = setDownloader u OtherDownloader
getDownloader :: URLString -> (URLString, Downloader)
getDownloader u = case separate (== ':') u of
2017-11-28 21:17:40 +00:00
("yt", u') -> (u', YoutubeDownloader)
-- quvi is not used any longer; youtube-dl should be able to handle
-- all urls it did.
("quvi", u') -> (u', YoutubeDownloader)
("", u') -> (u', OtherDownloader)
_ -> (u, WebDownloader)
2021-04-23 15:44:10 +00:00
{- Parses the content of an url log file, returning the urls that are
- currently recorded. -}
parseUrlLog :: L.ByteString -> [URLByteString]
parseUrlLog = map fromLogInfo . getLog