Preserve metadata when staging a new version of an annexed file.

Performance impact: When adding a large tree of new files, this needs
to do some git cat-file queries to check if any of the files already
existed and might need a metadata copy. I tried a benchmark in a copy
of my sound repository (so there was already a significant git tree
to check against.

Adding 10000 small files, with a cold cache:
  before: 1m48.539s
  after:  1m52.791s

So, impact is 0.0004 seconds per file added. Which seems acceptable, so did
not add some kind of configuration to enable/disable this.

This commit was sponsored by Lisa Feilen.
This commit is contained in:
Joey Hess 2014-02-24 14:41:33 -04:00
parent e7252cf192
commit 8d5158fa31
5 changed files with 41 additions and 14 deletions

View file

@ -11,6 +11,7 @@ import Common.Annex
import qualified Annex
import Types.MetaData
import Logs.MetaData
import Annex.CatFile
import qualified Data.Set as S
import qualified Data.Map as M
@ -27,18 +28,27 @@ yearMetaField = MetaField "year"
monthMetaField :: MetaField
monthMetaField = MetaField "month"
{- Generates metadata for a file that has just been ingested into the
- annex. Passed the FileStatus of the content file.
{- Adds metadata for a file that has just been ingested into the
- annex, but has not yet been committed to git.
-
- Does not overwrite any existing metadata values for the key.
- When the file has been modified, the metadata is copied over
- from the old key to the new key. Note that it looks at the old key as
- committed to HEAD -- the new key may or may not have already been staged
- in th annex.
-
- Also, can generate new metadata, if configured to do so.
-}
genMetaData :: Key -> FileStatus -> Annex ()
genMetaData key status = whenM (annexGenMetaData <$> Annex.getGitConfig) $ do
metadata <- getCurrentMetaData key
let metadata' = genMetaData' status metadata
unless (metadata' == emptyMetaData) $
addMetaData key metadata'
genMetaData :: Key -> FilePath -> FileStatus -> Annex ()
genMetaData key file status = do
maybe noop (flip copyMetaData key) =<< catKeyFileHEAD file
whenM (annexGenMetaData <$> Annex.getGitConfig) $ do
metadata <- getCurrentMetaData key
let metadata' = genMetaData' status metadata
unless (metadata' == emptyMetaData) $
addMetaData key metadata'
{- Generates metadata from the FileStatus.
- Does not overwrite any existing metadata values. -}
genMetaData' :: FileStatus -> MetaData -> MetaData
genMetaData' status old = MetaData $ M.fromList $ filter isnew
[ (yearMetaField, S.singleton $ toMetaValue $ show y)