Added filename extension preserving variant backends SHA1E, SHA256E, etc.

Backend/SHA.hs

@@ -14,6 +14,7 @@ import System.IO
 import System.Directory
 import Data.Maybe
 import System.Posix.Files
+import System.FilePath
 
 import qualified Backend.File
 import BackendClass
@@ -27,11 +28,14 @@ import qualified SysConfig
 import Key
 
 type SHASize = Int
- 
+
+sizes :: [Int]
+sizes = [1, 256, 512, 224, 384]
+
 backends :: [Backend Annex]
 -- order is slightly significant; want sha1 first ,and more general
 -- sizes earlier
-backends = catMaybes $ map genBackend [1, 256, 512, 224, 384]
+backends = catMaybes $ map genBackend sizes ++ map genBackendE sizes
 
 genBackend :: SHASize -> Maybe (Backend Annex)
 genBackend size
@@ -44,6 +48,15 @@ genBackend size
 			, fsckKey = Backend.File.checkKey $ checkKeyChecksum size
 			}
 
+genBackendE :: SHASize -> Maybe (Backend Annex)
+genBackendE size =
+	case genBackend size of
+		Nothing -> Nothing
+		Just b -> Just $ b
+			{ name = shaNameE size
+			, getKey = keyValueE size
+			}
+
 shaCommand :: SHASize -> Maybe String
 shaCommand 1 = SysConfig.sha1
 shaCommand 256 = SysConfig.sha256
@@ -55,6 +68,9 @@ shaCommand _ = Nothing
 shaName :: SHASize -> String
 shaName size = "SHA" ++ show size
 
+shaNameE :: SHASize -> String
+shaNameE size = shaName size ++ "E"
+
 shaN :: SHASize -> FilePath -> Annex String
 shaN size file = do
 	showNote "checksum..."
@@ -72,11 +88,25 @@ keyValue :: SHASize -> FilePath -> Annex (Maybe Key)
 keyValue size file = do
 	s <- shaN size file	
 	stat <- liftIO $ getFileStatus file
-	return $ Just $ stubKey {
-		keyName = s,
-		keyBackendName = shaName size,
-		keySize = Just $ fromIntegral $ fileSize stat
-	}
+	return $ Just $ stubKey
+		{ keyName = s
+		, keyBackendName = shaName size
+		, keySize = Just $ fromIntegral $ fileSize stat
+		}
+
+{- Extension preserving keys. -}
+keyValueE :: SHASize -> FilePath -> Annex (Maybe Key)
+keyValueE size file = keyValue size file >>= maybe (return Nothing) addE
+	where
+		addE k = return $ Just $ k
+			{ keyName = keyName k ++ extension
+			, keyBackendName = shaNameE size
+			}
+		naiveextension = takeExtension file
+		extension = 
+			if length naiveextension > 6
+				then "" -- probably not really an extension
+				else naiveextension
 
 -- A key's checksum is checked during fsck.
 checkKeyChecksum :: SHASize -> Key -> Annex Bool

debian/changelog

@@ -6,6 +6,7 @@ git-annex (0.20110504) UNRELEASED; urgency=low
     limits, disable encryption, support their nonstandard way of creating
     buckets, and allow x-amz-* headers to be specified in initremote to set
     item metadata.
+  * Added filename extension preserving variant backends SHA1E, SHA256E, etc.
 
  -- Joey Hess <joeyh@debian.org>  Fri, 06 May 2011 15:20:38 -0400
 

doc/backends.mdwn

@@ -23,6 +23,9 @@ these backends.
 * `SHA512`, `SHA384`, `SHA256`, `SHA224` -- Like SHA1, but larger
   checksums. Mostly useful for the very paranoid, or anyone who is
   researching checksum collisions and wants to annex their colliding data. ;)
+* `SHA1E`, `SHA512E`, etc -- Variants that preserve filename extension as
+  part of the key. Useful for archival tasks where the filename extension
+  contains metadata that should be preserved.
 
 These backends store file contents in other key/value stores.
 

doc/walkthrough/Internet_Archive_via_S3.mdwn

@@ -32,20 +32,18 @@ specify `x-archive-meta*` headers to add metadata as explained in their
 
 Then you can annex files and copy them to the remote as usual:
 
-	# git annex add photo1.jpeg
-	add photo1.jpeg ok
+	# git annex add photo1.jpeg --backend=SHA1E
+	add photo1.jpeg (checksum...) ok
 	# git annex copy photo1.jpeg --fast --to archive-panama
 	copy (to archive-panama...) ok
 
------
+Note the use of the SHA1E [[backend|backends]]. It makes most sense 
+to use the WORM or SHA1E backend for files that will be stored in
+the Internet Archive, since the key name will be exposed as the filename
+there, and since the Archive does special processing of files based on
+their extension.
 
-Note that it probably makes the most sense to use the WORM backend
-for files, since that exposes the original filename in the key stored
-in the Archive, which allows its special processing for sound files,
-movies, etc to be done. 
-
-Also, the Internet Archive has restrictions on what is allowed in a
-filename; particularly no spaces are allowed. 
+----
 
 There seems to be a bug in either hS3 or the archive that breaks
 authentication when the bucket name contains spaces or upper-case letters..