git-annex/Git/Command.hs

107 lines
3.7 KiB
Haskell
Raw Normal View History

2011-12-14 19:56:11 +00:00
{- running git commands
-
Clean up handling of git directory and git worktree. Baked into the code was an assumption that a repository's git directory could be determined by adding ".git" to its work tree (or nothing for bare repos). That fails when core.worktree, or GIT_DIR and GIT_WORK_TREE are used to separate the two. This was attacked at the type level, by storing the gitdir and worktree separately, so Nothing for the worktree means a bare repo. A complication arose because we don't learn where a repository is bare until its configuration is read. So another Location type handles repositories that have not had their config read yet. I am not entirely happy with this being a Location type, rather than representing them entirely separate from the Git type. The new code is not worse than the old, but better types could enforce more safety. Added support for core.worktree. Overriding it with -c isn't supported because it's not really clear what to do if a git repo's config is read, is not bare, and is then overridden to bare. What is the right git directory in this case? I will worry about this if/when someone has a use case for overriding core.worktree with -c. (See Git.Config.updateLocation) Also removed and renamed some functions like gitDir and workTree that misused git's terminology. One minor regression is known: git annex add in a bare repository does not print a nice error message, but runs git ls-files in a way that fails earlier with a less nice error message. This is because before --work-tree was always passed to git commands, even in a bare repo, while now it's not.
2012-05-18 20:38:26 +00:00
- Copyright 2010-2012 Joey Hess <joey@kitenet.net>
2011-12-14 19:56:11 +00:00
-
- Licensed under the GNU GPL version 3 or higher.
-}
module Git.Command where
2012-10-04 23:41:58 +00:00
import System.Process (std_out, env)
2011-12-14 19:56:11 +00:00
import Common
import Git
import Git.Types
2012-09-15 21:25:05 +00:00
import qualified Utility.CoProcess as CoProcess
2011-12-14 19:56:11 +00:00
{- Constructs a git command line operating on the specified repo. -}
gitCommandLine :: [CommandParam] -> Repo -> [CommandParam]
Clean up handling of git directory and git worktree. Baked into the code was an assumption that a repository's git directory could be determined by adding ".git" to its work tree (or nothing for bare repos). That fails when core.worktree, or GIT_DIR and GIT_WORK_TREE are used to separate the two. This was attacked at the type level, by storing the gitdir and worktree separately, so Nothing for the worktree means a bare repo. A complication arose because we don't learn where a repository is bare until its configuration is read. So another Location type handles repositories that have not had their config read yet. I am not entirely happy with this being a Location type, rather than representing them entirely separate from the Git type. The new code is not worse than the old, but better types could enforce more safety. Added support for core.worktree. Overriding it with -c isn't supported because it's not really clear what to do if a git repo's config is read, is not bare, and is then overridden to bare. What is the right git directory in this case? I will worry about this if/when someone has a use case for overriding core.worktree with -c. (See Git.Config.updateLocation) Also removed and renamed some functions like gitDir and workTree that misused git's terminology. One minor regression is known: git annex add in a bare repository does not print a nice error message, but runs git ls-files in a way that fails earlier with a less nice error message. This is because before --work-tree was always passed to git commands, even in a bare repo, while now it's not.
2012-05-18 20:38:26 +00:00
gitCommandLine params Repo { location = l@(Local _ _ ) } = setdir : settree ++ params
where
setdir = Param $ "--git-dir=" ++ gitdir l
settree = case worktree l of
Nothing -> []
Just t -> [Param $ "--work-tree=" ++ t]
2011-12-14 19:56:11 +00:00
gitCommandLine _ repo = assertLocal repo $ error "internal"
{- Runs git in the specified repo. -}
runBool :: String -> [CommandParam] -> Repo -> IO Bool
runBool subcommand params repo = assertLocal repo $
2012-08-25 00:50:39 +00:00
boolSystemEnv "git"
(gitCommandLine (Param subcommand : params) repo)
(gitEnv repo)
2011-12-14 19:56:11 +00:00
{- Runs git in the specified repo, throwing an error if it fails. -}
run :: String -> [CommandParam] -> Repo -> IO ()
run subcommand params repo = assertLocal repo $
unlessM (runBool subcommand params repo) $
2012-01-26 00:43:01 +00:00
error $ "git " ++ subcommand ++ " " ++ show params ++ " failed"
2011-12-14 19:56:11 +00:00
{- Runs a git subcommand and returns its output, lazily.
2011-12-14 19:56:11 +00:00
-
- Also returns an action that should be used when the output is all
- read (or no more is needed), that will wait on the command, and
- return True if it succeeded. Failure to wait will result in zombies.
2011-12-14 19:56:11 +00:00
-}
pipeReadLazy :: [CommandParam] -> Repo -> IO (String, IO Bool)
pipeReadLazy params repo = assertLocal repo $ do
2012-10-04 23:41:58 +00:00
(_, Just h, _, pid) <- createProcess p { std_out = CreatePipe }
fileEncoding h
c <- hGetContents h
return (c, checkSuccessProcess pid)
where
p = gitCreateProcess params repo
{- Runs a git subcommand, and returns its output, strictly.
-
- Nonzero exit status is ignored.
-}
pipeReadStrict :: [CommandParam] -> Repo -> IO String
pipeReadStrict params repo = assertLocal repo $
withHandle StdoutHandle (createProcessChecked ignoreFailureProcess) p $ \h -> do
fileEncoding h
output <- hGetContentsStrict h
hClose h
return output
where
p = gitCreateProcess params repo
2011-12-14 19:56:11 +00:00
2012-07-17 18:40:05 +00:00
{- Runs a git subcommand, feeding it input, and returning its output,
- which is expected to be fairly small, since it's all read into memory
- strictly. -}
pipeWriteRead :: [CommandParam] -> String -> Repo -> IO String
pipeWriteRead params s repo = assertLocal repo $
2012-08-25 00:50:39 +00:00
writeReadProcessEnv "git" (toCommand $ gitCommandLine params repo)
(gitEnv repo) s (Just fileEncoding)
2012-08-25 00:50:39 +00:00
{- Runs a git subcommand, feeding it input on a handle with an action. -}
pipeWrite :: [CommandParam] -> Repo -> (Handle -> IO ()) -> IO ()
pipeWrite params repo = withHandle StdinHandle createProcessSuccess $
gitCreateProcess params repo
2011-12-14 19:56:11 +00:00
{- Reads null terminated output of a git command (as enabled by the -z
- parameter), and splits it. -}
pipeNullSplit :: [CommandParam] -> Repo -> IO ([String], IO Bool)
pipeNullSplit params repo = do
(s, cleanup) <- pipeReadLazy params repo
return (filter (not . null) $ split sep s, cleanup)
where
support all filename encodings with ghc 7.4 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.
2012-02-03 19:12:41 +00:00
sep = "\0"
2011-12-14 19:56:11 +00:00
pipeNullSplitZombie :: [CommandParam] -> Repo -> IO [String]
pipeNullSplitZombie params repo = leaveZombie <$> pipeNullSplit params repo
{- Doesn't run the cleanup action. A zombie results. -}
leaveZombie :: (a, IO Bool) -> a
leaveZombie = fst
2012-09-15 21:25:05 +00:00
{- Runs a git command as a coprocess. -}
gitCoProcessStart :: [CommandParam] -> Repo -> IO CoProcess.CoProcessHandle
gitCoProcessStart params repo = CoProcess.start "git" (toCommand $ gitCommandLine params repo) (gitEnv repo)
gitCreateProcess :: [CommandParam] -> Repo -> CreateProcess
gitCreateProcess params repo =
(proc "git" $ toCommand $ gitCommandLine params repo)
{ env = gitEnv repo }