Merge branch 'duplicate'

Conflicts:
	debian/changelog

4 files changed, 70 insertions, 9 deletions

diff --git a/Command/Import.hs b/Command/Import.hs
index 518666af9..56fe9c7ab 100644
--- a/Command/Import.hs
+++ b/Command/Import.hs
@@ -1,6 +1,6 @@
 {- git-annex command
  -
- - Copyright 2012 Joey Hess <joey@kitenet.net>
+ - Copyright 2012-2013 Joey Hess <joey@kitenet.net>
  -
  - Licensed under the GNU GPL version 3 or higher.
  -}
@@ -13,30 +13,66 @@ import Common.Annex
 import Command
 import qualified Annex
 import qualified Command.Add
+import qualified Option
+import Utility.CopyFile
 
 def :: [Command]
-def = [notBareRepo $ command "import" paramPaths seek
+def = [withOptions opts $ notBareRepo $ command "import" paramPaths seek
 	SectionCommon "move and add files from outside git working copy"]
 
+opts :: [Option]
+opts =
+	[ duplicateOption
+	, deduplicateOption
+	, cleanDuplicatesOption
+	]
+
+duplicateOption :: Option
+duplicateOption = Option.flag [] "duplicate" "do not delete outside files"
+
+deduplicateOption :: Option
+deduplicateOption = Option.flag [] "deduplicate" "do not add files whose content has been seen"
+
+cleanDuplicatesOption :: Option
+cleanDuplicatesOption = Option.flag [] "clean-duplicates" "delete outside duplicate files (import nothing)"
+
+data DuplicateMode = Default | Duplicate | DeDuplicate | CleanDuplicates
+	deriving (Eq)
+
+getDuplicateMode :: Annex DuplicateMode
+getDuplicateMode = gen
+	<$> getflag duplicateOption
+	<*> getflag deduplicateOption
+	<*> getflag cleanDuplicatesOption
+  where
+  	getflag = Annex.getFlag . Option.name
+  	gen False False False = Default
+	gen True False False = Duplicate
+	gen False True False = DeDuplicate
+	gen False False True = CleanDuplicates
+	gen _ _ _ = error "bad combination of --duplicate, --deduplicate, --clean-duplicates"
+
 seek :: [CommandSeek]
-seek = [withPathContents start]
+seek = [withValue getDuplicateMode $ \mode -> withPathContents $ start mode]
 
-start :: (FilePath, FilePath) -> CommandStart
-start (srcfile, destfile) =
+start :: DuplicateMode -> (FilePath, FilePath) -> CommandStart
+start mode (srcfile, destfile) =
 	ifM (liftIO $ isRegularFile <$> getSymbolicLinkStatus srcfile)
 		( do
 			showStart "import" destfile
-			next $ perform srcfile destfile
+			next $ perform mode srcfile destfile
 		, stop
 		)
 
-perform :: FilePath -> FilePath -> CommandPerform
-perform srcfile destfile = do
+perform :: DuplicateMode -> FilePath -> FilePath -> CommandPerform
+perform mode srcfile destfile = do
 	whenM (liftIO $ doesFileExist destfile) $
 		unlessM (Annex.getState Annex.force) $
 			error $ "not overwriting existing " ++ destfile ++
 				" (use --force to override)"
 
 	liftIO $ createDirectoryIfMissing True (parentDir destfile)
-	liftIO $ moveFile srcfile destfile
+	liftIO $ if mode == Duplicate
+		then void $ copyFileExternal srcfile destfile
+		else moveFile srcfile destfile
 	Command.Add.perform destfile
diff --git a/debian/changelog b/debian/changelog
index 150307c22..7d1abbf67 100644
--- a/debian/changelog
+++ b/debian/changelog
@@ -4,6 +4,8 @@ git-annex (4.20130816) UNRELEASED; urgency=low
   * Debian: Recommend ssh-askpass, which ssh will use when the assistant
     is run w/o a tty. Closes: #719832
   * sync, merge: Bug fix: Don't try to merge into master when in a bare repo.
+  * import: Add options to control handling of duplicate files:
+    --duplicate, --deduplicate, and --clean-duplicates
 
  -- Joey Hess <joeyh@debian.org>  Thu, 15 Aug 2013 15:47:52 +0200
 
diff --git a/doc/git-annex.mdwn b/doc/git-annex.mdwn
index 60736d579..44abd6943 100644
--- a/doc/git-annex.mdwn
+++ b/doc/git-annex.mdwn
@@ -190,6 +190,28 @@ subdirectories).
 
 	git annex import /media/camera/DCIM/
 
+  By default, importing two files with the same contents from two different
+  locations will result in both files being added to the repository.
+  (With all checksumming backends, including the default SHA256E,
+  only one copy of the data will be stored.)
+
+  To not delete files from the import location, use the
+  --duplicate option. This could allow importing the same files repeatedly
+  to different locations in a repository. More likely, it could be used to
+  import the same files to a number of different branches or separate git
+  repositories.
+
+  To only import files whose content has not been seen before by git-annex,
+  use the --deduplicate option. Duplicate files will be deleted from the
+  import location.
+  
+  The --clean-duplicates option does not import any new files, but any files
+  found in the import location that are duplicates of content in the annex
+  are deleted.
+  
+  (Note that using --deduplicate or --clean-duplicates with the WORM
+  backend does not look at file content, but filename and mtime.)
+
 * importfeed [url ...]
 
   Imports the contents of podcast feeds. Only downloads files whose
diff --git a/doc/related_software.mdwn b/doc/related_software.mdwn
index 4a8bc78ac..024a155e3 100644
--- a/doc/related_software.mdwn
+++ b/doc/related_software.mdwn
@@ -9,3 +9,4 @@ designed to interoperate with it.
   is git-annex aware.
 * [sizes](http://hackage.haskell.org/package/sizes) is another du-like
   utility, with a `-A` switch that enables git-annex support.
+* Emacs Org mode can auto-commit attached files to git-annex.