git-annex/Remote/Web.hs
Joey Hess 9a2c8757f3
add thirdPartyPopulated interface
This is to support, eg a borg repo as a special remote, which is
populated not by running git-annex commands, but by using borg. Then
git-annex sync lists the content of the remote, learns which files are
annex objects, and treats those as present in the remote.

So, most of the import machinery is reused, to a new purpose. While
normally importtree maintains a remote tracking branch, this does not,
because the files stored in the remote are annex object files, not
user-visible filenames. But, internally, a git tree is still generated,
of the files on the remote that are annex objects. This tree is used
by retrieveExportWithContentIdentifier, etc. As with other import/export
remotes, that  the tree is recorded in the export log, and gets grafted
into the git-annex branch.

importKey changed to be able to return Nothing, to indicate when an
ImportLocation is not an annex object and so should be skipped from
being included in the tree.

It did not seem to make sense to have git-annex import do this, since
from the user's perspective, it's not like other imports. So only
git-annex sync does it.

Note that, git-annex sync does not yet download objects from such
remotes that are preferred content. importKeys is run with
content downloading disabled, to avoid getting the content of all
objects. Perhaps what's needed is for seekSyncContent to be run with these
remotes, but I don't know if it will just work (in particular, it needs
to avoid trying to transfer objects to them), so I skipped that for now.

(Untested and unused as of yet.)

This commit was sponsored by Jochen Bartl on Patreon.
2020-12-18 15:23:58 -04:00

131 lines
3.6 KiB
Haskell

{- Web remote.
-
- Copyright 2011 Joey Hess <id@joeyh.name>
-
- Licensed under the GNU AGPL version 3 or higher.
-}
module Remote.Web (remote, getWebUrls) where
import Annex.Common
import Types.Remote
import Remote.Helper.Messages
import Remote.Helper.ExportImport
import qualified Git
import qualified Git.Construct
import Annex.Content
import Config.Cost
import Config
import Logs.Web
import Annex.UUID
import Utility.Metered
import qualified Annex.Url as Url
import Annex.YoutubeDl
import Annex.SpecialRemote.Config
remote :: RemoteType
remote = RemoteType
{ typename = "web"
, enumerate = list
, generate = gen
, configParser = mkRemoteConfigParser []
, setup = error "not supported"
, exportSupported = exportUnsupported
, importSupported = importUnsupported
, thirdPartyPopulated = False
}
-- There is only one web remote, and it always exists.
-- (If the web should cease to exist, remove this module and redistribute
-- a new release to the survivors by carrier pigeon.)
list :: Bool -> Annex [Git.Repo]
list _autoinit = do
r <- liftIO $ Git.Construct.remoteNamed "web" (pure Git.Construct.fromUnknown)
return [r]
gen :: Git.Repo -> UUID -> RemoteConfig -> RemoteGitConfig -> RemoteStateHandle -> Annex (Maybe Remote)
gen r _ rc gc rs = do
c <- parsedRemoteConfig remote rc
cst <- remoteCost gc expensiveRemoteCost
return $ Just Remote
{ uuid = webUUID
, cost = cst
, name = Git.repoDescribe r
, storeKey = uploadKey
, retrieveKeyFile = downloadKey
, retrieveKeyFileCheap = Nothing
-- HttpManagerRestricted is used here, so this is
-- secure.
, retrievalSecurityPolicy = RetrievalAllKeysSecure
, removeKey = dropKey
, lockContent = Nothing
, checkPresent = checkKey
, checkPresentCheap = False
, exportActions = exportUnsupported
, importActions = importUnsupported
, whereisKey = Nothing
, remoteFsck = Nothing
, repairRepo = Nothing
, config = c
, gitconfig = gc
, localpath = Nothing
, getRepo = return r
, readonly = True
, appendonly = False
, availability = GloballyAvailable
, remotetype = remote
, mkUnavailable = return Nothing
, getInfo = return []
, claimUrl = Nothing -- implicitly claims all urls
, checkUrl = Nothing
, remoteStateHandle = rs
}
downloadKey :: Key -> AssociatedFile -> FilePath -> MeterUpdate -> Annex Verification
downloadKey key _af dest p = do
get =<< getWebUrls key
return UnVerified
where
get [] = giveup "no known url"
get urls = do
r <- untilTrue urls $ \u -> do
let (u', downloader) = getDownloader u
case downloader of
YoutubeDownloader -> youtubeDlTo key u' dest p
_ -> Url.withUrlOptions $ downloadUrl key p [u'] dest
unless r $
giveup "download failed"
uploadKey :: Key -> AssociatedFile -> MeterUpdate -> Annex ()
uploadKey _ _ _ = giveup "upload to web not supported"
dropKey :: Key -> Annex ()
dropKey k = mapM_ (setUrlMissing k) =<< getWebUrls k
checkKey :: Key -> Annex Bool
checkKey key = do
us <- getWebUrls key
if null us
then return False
else either giveup return =<< checkKey' key us
checkKey' :: Key -> [URLString] -> Annex (Either String Bool)
checkKey' key us = firsthit us (Right False) $ \u -> do
let (u', downloader) = getDownloader u
showChecking u'
case downloader of
YoutubeDownloader -> youtubeDlCheck u'
_ -> catchMsgIO $
Url.withUrlOptions $ Url.checkBoth u' (fromKey keySize key)
where
firsthit [] miss _ = return miss
firsthit (u:rest) _ a = do
r <- a u
case r of
Right True -> return r
_ -> firsthit rest r a
getWebUrls :: Key -> Annex [URLString]
getWebUrls key = filter supported <$> getUrls key
where
supported u = snd (getDownloader u)
`elem` [WebDownloader, YoutubeDownloader]