d8fb97806c
Under ghc 7.4, this seems to be able to handle all filename encodings again. Including filename encodings that do not match the LANG setting. I think this will not work with earlier versions of ghc, it uses some ghc internals. Turns out that ghc 7.4 has a special filesystem encoding that it uses when reading/writing filenames (as FilePaths). This encoding is documented to allow "arbitrary undecodable bytes to be round-tripped through it". So, to get FilePaths from eg, git ls-files, set the Handle that is reading from git to use this encoding. Then things basically just work. However, I have not found a way to make Text read using this encoding. Text really does assume unicode. So I had to switch back to using String when reading/writing data to git. Which is a pity, because it's some percent slower, but at least it works. Note that stdout and stderr also have to be set to this encoding, or printing out filenames that contain undecodable bytes causes a crash. IMHO this is a misfeature in ghc, that the user can pass you a filename, which you can readFile, etc, but that default, putStr of filename may cause a crash! Git.CheckAttr gave me special trouble, because the filenames I got back from git, after feeding them in, had further encoding breakage. Rather than try to deal with that, I just zip up the input filenames with the attributes. Which must be returned in the same order queried for this to work. Also of note is an apparent GHC bug I worked around in Git.CheckAttr. It used to forkProcess and feed git from the child process. Unfortunatly, after this forkProcess, accessing the `files` variable from the parent returns []. Not the value that was passed into the function. This screams of a bad bug, that's clobbering a variable, but for now I just avoid forkProcess there to work around it. That forkProcess was itself only added because of a ghc bug, #624389. I've confirmed that the test case for that bug doesn't reproduce it with ghc 7.4. So that's ok, except for the new ghc bug I have not isolated and reported. Why does this simple bit of code magnet the ghc bugs? :) Also, the symlink touching code is currently broken, when used on utf-8 filenames in a non-utf-8 locale, or probably on any filename containing undecodable bytes, and I temporarily commented it out.
95 lines
2.7 KiB
Haskell
95 lines
2.7 KiB
Haskell
{- git-annex command
|
|
-
|
|
- Copyright 2010 Joey Hess <joey@kitenet.net>
|
|
-
|
|
- Licensed under the GNU GPL version 3 or higher.
|
|
-}
|
|
|
|
module Command.Add where
|
|
|
|
import Common.Annex
|
|
import Annex.Exception
|
|
import Command
|
|
import qualified Annex
|
|
import qualified Annex.Queue
|
|
import qualified Backend
|
|
import Logs.Location
|
|
import Annex.Content
|
|
import Utility.Touch
|
|
import Backend
|
|
|
|
def :: [Command]
|
|
def = [command "add" paramPaths seek "add files to annex"]
|
|
|
|
{- Add acts on both files not checked into git yet, and unlocked files. -}
|
|
seek :: [CommandSeek]
|
|
seek = [withFilesNotInGit start, withFilesUnlocked start]
|
|
|
|
{- The add subcommand annexes a file, storing it in a backend, and then
|
|
- moving it into the annex directory and setting up the symlink pointing
|
|
- to its content. -}
|
|
start :: BackendFile -> CommandStart
|
|
start p@(_, file) = notBareRepo $ ifAnnexed file fixup add
|
|
where
|
|
add = do
|
|
s <- liftIO $ getSymbolicLinkStatus file
|
|
if isSymbolicLink s || not (isRegularFile s)
|
|
then stop
|
|
else do
|
|
showStart "add" file
|
|
next $ perform p
|
|
fixup (key, _) = do
|
|
-- fixup from an interrupted add; the symlink
|
|
-- is present but not yet added to git
|
|
showStart "add" file
|
|
liftIO $ removeFile file
|
|
next $ next $ cleanup file key =<< inAnnex key
|
|
|
|
perform :: BackendFile -> CommandPerform
|
|
perform (backend, file) = Backend.genKey file backend >>= go
|
|
where
|
|
go Nothing = stop
|
|
go (Just (key, _)) = do
|
|
handle (undo file key) $ moveAnnex key file
|
|
next $ cleanup file key True
|
|
|
|
{- On error, put the file back so it doesn't seem to have vanished.
|
|
- This can be called before or after the symlink is in place. -}
|
|
undo :: FilePath -> Key -> IOException -> Annex a
|
|
undo file key e = do
|
|
unlessM (inAnnex key) rethrow -- no cleanup to do
|
|
liftIO $ whenM (doesFileExist file) $ removeFile file
|
|
handle tryharder $ fromAnnex key file
|
|
logStatus key InfoMissing
|
|
rethrow
|
|
where
|
|
rethrow = throw e
|
|
|
|
-- fromAnnex could fail if the file ownership is weird
|
|
tryharder :: IOException -> Annex ()
|
|
tryharder _ = do
|
|
src <- inRepo $ gitAnnexLocation key
|
|
liftIO $ moveFile src file
|
|
|
|
cleanup :: FilePath -> Key -> Bool -> CommandCleanup
|
|
cleanup file key hascontent = do
|
|
handle (undo file key) $ do
|
|
link <- calcGitLink file key
|
|
liftIO $ createSymbolicLink link file
|
|
|
|
when hascontent $ do
|
|
logStatus key InfoPresent
|
|
|
|
-- touch the symlink to have the same mtime as the
|
|
-- file it points to
|
|
-- XXX Currently broken on non-utf8 locales when
|
|
-- dealing with utf-8 filenames.
|
|
--liftIO $ do
|
|
--mtime <- modificationTime <$> getFileStatus file
|
|
--touch file (TimeSpec mtime) False
|
|
|
|
force <- Annex.getState Annex.force
|
|
if force
|
|
then Annex.Queue.add "add" [Param "-f", Param "--"] [file]
|
|
else Annex.Queue.add "add" [Param "--"] [file]
|
|
return True
|