git-annex config annex.largefiles

annex.largefiles can be configured by git-annex config, to more easily set
a default that will also be used by clones, without needing to shoehorn the
expression into the gitattributes file. The git config and gitattributes
override that.

Whenever something is added to git-annex config, we have to consider what
happens if a user puts a purposfully bad value in there. Or, if a new
git-annex adds some new value that an old git-annex can't parse.
In this case, a global annex.largefiles that can't be parsed currently
makes an error be thrown. That might not be ideal, but the gitattribute
behaves the same, and is almost equally repo-global.

Performance notes:

git-annex add and addurl construct a matcher once
and uses it for every file, so the added time penalty for reading the global
config log is minor. If the gitattributes annex.largefiles were deprecated,
git-annex add would get around 2% faster (excluding hashing), because
looking that up for each file is not fast. So this new way of setting
it is progress toward speeding up add.

git-annex smudge does need to load the log every time. As well as checking
the git attribute. Not ideal. Setting annex.gitaddtoannex=false avoids
both overheads.
This commit is contained in:
Joey Hess 2019-12-20 12:12:31 -04:00
parent ce3fb0b2e5
commit 4acbb40112
No known key found for this signature in database
GPG key ID: DB12DB0FF05F8F38
9 changed files with 119 additions and 63 deletions

View file

@ -9,6 +9,7 @@
module Types.GitConfig (
Configurable(..),
ConfigSource(..),
GitConfig(..),
extractGitConfig,
mergeGitConfig,
@ -46,13 +47,17 @@ import qualified Data.Set as S
-- | A configurable value, that may not be fully determined yet because
-- the global git config has not yet been loaded.
data Configurable a
= HasConfig a
-- ^ Value is fully determined.
= HasGitConfig a
-- ^ The git config has a value.
| HasGlobalConfig a
-- ^ The global config has a value (and the git config does not).
| DefaultConfig a
-- ^ A default value is known, but not all config sources
-- have been read yet.
deriving (Show)
data ConfigSource = FromGitConfig | FromGlobalConfig
{- Main git-annex settings. Each setting corresponds to a git-config key
- such as annex.foo -}
data GitConfig = GitConfig
@ -80,7 +85,7 @@ data GitConfig = GitConfig
, annexYoutubeDlOptions :: [String]
, annexAriaTorrentOptions :: [String]
, annexCrippledFileSystem :: Bool
, annexLargeFiles :: Maybe String
, annexLargeFiles :: Configurable (Maybe String)
, annexGitAddToAnnex :: Bool
, annexAddSmallFiles :: Bool
, annexFsckNudge :: Bool
@ -116,8 +121,8 @@ data GitConfig = GitConfig
, gpgCmd :: GpgCmd
}
extractGitConfig :: Git.Repo -> GitConfig
extractGitConfig r = GitConfig
extractGitConfig :: ConfigSource -> Git.Repo -> GitConfig
extractGitConfig configsource r = GitConfig
{ annexVersion = RepoVersion <$> getmayberead (annex "version")
, annexUUID = maybe NoUUID toUUID $ getmaybe (annex "uuid")
, annexNumCopies = NumCopies <$> getmayberead (annex "numcopies")
@ -151,7 +156,8 @@ extractGitConfig r = GitConfig
, annexYoutubeDlOptions = getwords (annex "youtube-dl-options")
, annexAriaTorrentOptions = getwords (annex "aria-torrent-options")
, annexCrippledFileSystem = getbool (annex "crippledfilesystem") False
, annexLargeFiles = getmaybe (annex "largefiles")
, annexLargeFiles = configurable Nothing $
fmap Just $ getmaybe (annex "largefiles")
, annexGitAddToAnnex = getbool (annex "gitaddtoannex") True
, annexAddSmallFiles = getbool (annex "addsmallfiles") True
, annexFsckNudge = getbool (annex "fscknudge") True
@ -209,7 +215,9 @@ extractGitConfig r = GitConfig
getwords k = fromMaybe [] $ words <$> getmaybe k
configurable d Nothing = DefaultConfig d
configurable _ (Just v) = HasConfig v
configurable _ (Just v) = case configsource of
FromGitConfig -> HasGitConfig v
FromGlobalConfig -> HasGlobalConfig v
annex k = ConfigKey $ "annex." <> k
@ -222,13 +230,15 @@ mergeGitConfig gitconfig repoglobals = gitconfig
{ annexAutoCommit = merge annexAutoCommit
, annexSyncContent = merge annexSyncContent
, annexResolveMerge = merge annexResolveMerge
, annexLargeFiles = merge annexLargeFiles
}
where
merge f = case f gitconfig of
HasConfig v -> HasConfig v
HasGitConfig v -> HasGitConfig v
DefaultConfig d -> case f repoglobals of
HasConfig v -> HasConfig v
DefaultConfig _ -> HasConfig d
HasGlobalConfig v -> HasGlobalConfig v
_ -> HasGitConfig d
HasGlobalConfig v -> HasGlobalConfig v
{- Per-remote git-annex settings. Each setting corresponds to a git-config
- key such as <remote>.annex-foo, or if that is not set, a default from