git-annex/Command/Add.hs
Joey Hess 436f107715
make CommandStart return a StartMessage
The goal is to be able to run CommandStart in the main thread when -J is
used, rather than unncessarily passing it off to a worker thread, which
incurs overhead that is signficant when the CommandStart is going to
quickly decide to stop.

To do that, the message it displays needs to be displayed in the worker
thread, after the CommandStart has run.

Also, the change will mean that CommandStart will no longer necessarily
run with the same Annex state as CommandPerform. While its docs already
said it should avoid modifying Annex state, I audited all the
CommandStart code as part of the conversion. (Note that CommandSeek
already sometimes runs with a different Annex state, and that has not been
a source of any problems, so I am not too worried that this change will
lead to breakage going forward.)

The only modification of Annex state I found was it calling
allowMessages in some Commands that default to noMessages. Dealt with
that by adding a startCustomOutput and a startingUsualMessages.
This lets a command start with noMessages and then select the output it
wants for each CommandStart.

One bit of breakage: onlyActionOn has been removed from commands that used it.
The plan is that, since a StartMessage contains an ActionItem,
when a Key can be extracted from that, the parallel job runner can
run onlyActionOn' automatically. Then commands won't need to worry about
this detail. Future work.

Otherwise, this was a fairly straightforward process of making each
CommandStart compile again. Hopefully other behavior changes were mostly
avoided.

In a few cases, a command had a CommandStart that called a CommandPerform
that then called showStart multiple times. I have collapsed those
down to a single start action. The main command to perhaps suffer from it
is Command.Direct, which used to show a start for each file, and no
longer does.

Another minor behavior change is that some commands used showStart
before, but had an associated file and a Key available, so were changed
to ShowStart with an ActionItemAssociatedFile. That will not change the
normal output or behavior, but --json output will now include the key.
This should not break it for anyone using a real json parser.
2019-06-06 17:13:54 -04:00

154 lines
4.1 KiB
Haskell

{- git-annex command
-
- Copyright 2010-2017 Joey Hess <id@joeyh.name>
-
- Licensed under the GNU AGPL version 3 or higher.
-}
module Command.Add where
import Command
import Annex.Ingest
import Logs.Location
import Annex.Content
import Annex.Content.Direct
import qualified Annex
import qualified Annex.Queue
import qualified Database.Keys
import Config
import Annex.FileMatcher
import Annex.Link
import Annex.Version
import Annex.Tmp
import Git.FilePath
cmd :: Command
cmd = notBareRepo $
withGlobalOptions [jobsOption, jsonOptions, fileMatchingOptions] $
command "add" SectionCommon "add files to annex"
paramPaths (seek <$$> optParser)
data AddOptions = AddOptions
{ addThese :: CmdParams
, includeDotFiles :: Bool
, batchOption :: BatchMode
, updateOnly :: Bool
}
optParser :: CmdParamsDesc -> Parser AddOptions
optParser desc = AddOptions
<$> cmdParams desc
<*> switch
( long "include-dotfiles"
<> help "don't skip dotfiles"
)
<*> parseBatchOption
<*> switch
( long "update"
<> short 'u'
<> help "only update tracked files"
)
seek :: AddOptions -> CommandSeek
seek o = allowConcurrentOutput $ do
matcher <- largeFilesMatcher
let gofile file = ifM (checkFileMatcher matcher file <||> Annex.getState Annex.force)
( start file
, ifM (annexAddSmallFiles <$> Annex.getGitConfig)
( startSmall file
, stop
)
)
case batchOption o of
Batch fmt
| updateOnly o ->
giveup "--update --batch is not supported"
| otherwise -> batchFilesMatching fmt gofile
NoBatch -> do
l <- workTreeItems (addThese o)
let go a = a (commandAction . gofile) l
unless (updateOnly o) $
go (withFilesNotInGit (not $ includeDotFiles o))
go withFilesMaybeModified
ifM versionSupportsUnlockedPointers
( go withUnmodifiedUnlockedPointers
, unlessM isDirect $
go withFilesOldUnlocked
)
{- Pass file off to git-add. -}
startSmall :: FilePath -> CommandStart
startSmall file = starting "add" (ActionItemWorkTreeFile file) $
next $ addSmall file
addSmall :: FilePath -> Annex Bool
addSmall file = do
showNote "non-large file; adding content to git repository"
addFile file
addFile :: FilePath -> Annex Bool
addFile file = do
ps <- forceParams
Annex.Queue.addCommand "add" (ps++[Param "--"]) [file]
return True
start :: FilePath -> CommandStart
start file = do
ifM versionSupportsUnlockedPointers
( do
mk <- liftIO $ isPointerFile file
maybe go fixuppointer mk
, go
)
where
go = ifAnnexed file addpresent add
add = liftIO (catchMaybeIO $ getSymbolicLinkStatus file) >>= \case
Nothing -> stop
Just s
| not (isRegularFile s) && not (isSymbolicLink s) -> stop
| otherwise ->
starting "add" (ActionItemWorkTreeFile file) $
if isSymbolicLink s
then next $ addFile file
else perform file
addpresent key = ifM versionSupportsUnlockedPointers
( liftIO (catchMaybeIO $ getSymbolicLinkStatus file) >>= \case
Just s | isSymbolicLink s -> fixuplink key
_ -> add
, ifM isDirect
( liftIO (catchMaybeIO $ getSymbolicLinkStatus file) >>= \case
Just s | isSymbolicLink s -> fixuplink key
_ -> ifM (goodContent key file)
( stop , add )
, fixuplink key
)
)
fixuplink key = starting "add" (ActionItemWorkTreeFile file) $ do
-- the annexed symlink is present but not yet added to git
liftIO $ removeFile file
addLink file key Nothing
next $
cleanup key =<< inAnnex key
fixuppointer key = starting "add" (ActionItemWorkTreeFile file) $ do
-- the pointer file is present, but not yet added to git
Database.Keys.addAssociatedFile key =<< inRepo (toTopFilePath file)
next $ addFile file
perform :: FilePath -> CommandPerform
perform file = withOtherTmp $ \tmpdir -> do
lockingfile <- not <$> addUnlocked
let cfg = LockDownConfig
{ lockingFile = lockingfile
, hardlinkFileTmpDir = Just tmpdir
}
lockDown cfg file >>= ingestAdd >>= finish
where
finish (Just key) = next $ cleanup key True
finish Nothing = stop
cleanup :: Key -> Bool -> CommandCleanup
cleanup key hascontent = do
maybeShowJSON $ JSONChunk [("key", serializeKey key)]
when hascontent $
logStatus key InfoPresent
return True