Adjust built-in preferred content expressions to make most types of repositories want content that is only located on untrusted or dead repositories.

Types/StandardGroups.hs

@@ -16,6 +16,7 @@ data StandardGroup
 	| FullArchiveGroup
 	| SourceGroup
 	| ManualGroup
+	| UnwantedGroup
 	deriving (Eq, Ord, Enum, Bounded, Show)
 
 fromStandardGroup :: StandardGroup -> String
@@ -27,6 +28,7 @@ fromStandardGroup SmallArchiveGroup = "smallarchive"
 fromStandardGroup FullArchiveGroup = "archive"
 fromStandardGroup SourceGroup = "source"
 fromStandardGroup ManualGroup = "manual"
+fromStandardGroup UnwantedGroup = "unwanted"
 
 toStandardGroup :: String -> Maybe StandardGroup
 toStandardGroup "client" = Just ClientGroup
@@ -37,6 +39,7 @@ toStandardGroup "smallarchive" = Just SmallArchiveGroup
 toStandardGroup "archive" = Just FullArchiveGroup
 toStandardGroup "source" = Just SourceGroup
 toStandardGroup "manual" = Just ManualGroup
+toStandardGroup "unwanted" = Just UnwantedGroup
 toStandardGroup _ = Nothing
 
 descStandardGroup :: StandardGroup -> String
@@ -48,14 +51,26 @@ descStandardGroup SmallArchiveGroup = "small archive: archives files located in
 descStandardGroup FullArchiveGroup = "full archive: archives all files not archived elsewhere"
 descStandardGroup SourceGroup = "file source: moves files on to other repositories"
 descStandardGroup ManualGroup = "manual mode: only stores files you manually choose"
+descStandardGroup UnwantedGroup "unwanted: a repository in the process of being removed"
 
 {- See doc/preferred_content.mdwn for explanations of these expressions. -}
 preferredContent :: StandardGroup -> String
-preferredContent ClientGroup = "exclude=*/archive/* and exclude=archive/*"
-preferredContent TransferGroup = "not (inallgroup=client and copies=client:2) and " ++ preferredContent ClientGroup
+preferredContent ClientGroup = normal
+	"exclude=*/archive/* and exclude=archive/*"
+preferredContent TransferGroup = normal $
+	"not (inallgroup=client and copies=client:2) and " ++ preferredContent ClientGroup
 preferredContent BackupGroup = "include=*"
-preferredContent IncrementalBackupGroup = "include=* and (not copies=incrementalbackup:1)"
-preferredContent SmallArchiveGroup = "(include=*/archive/* or include=archive/*) and " ++ preferredContent FullArchiveGroup
-preferredContent FullArchiveGroup = "not (copies=archive:1 or copies=smallarchive:1)"
+preferredContent IncrementalBackupGroup = normal $
+	"include=* and (not copies=incrementalbackup:1)"
+preferredContent SmallArchiveGroup = normal $
+	"(include=*/archive/* or include=archive/*) and " ++ preferredContent FullArchiveGroup
+preferredContent FullArchiveGroup = normal $
+	"not (copies=archive:1 or copies=smallarchive:1)"
 preferredContent SourceGroup = "not (copies=1)"
-preferredContent ManualGroup = "present and exclude=*/archive/* and exclude=archive/*"
+preferredContent ManualGroup = normal $
+	"present and exclude=*/archive/* and exclude=archive/*"
+preferredContent UnwantedGroup = "exclude=*"
+  where
+  	{- Most repositories want any content that is only on untrusted
+	 - or dead repositories. -}
+	normal s = "(" ++ s ++ ") or (not copies=semitrusted:1)"

debian/changelog

@@ -19,6 +19,9 @@ git-annex (4.20130324) UNRELEASED; urgency=low
   * git-annex-shell: Passes rsync --bwlimit options on rsync.
     Thanks, guilhem for the patch.
   * webapp: Added UI to delete repositories. Closes: #689847
+  * Adjust built-in preferred content expressions to make most types
+    of repositories want content that is only located on untrusted or dead
+    repositories.
 
  -- Joey Hess <joeyh@debian.org>  Mon, 25 Mar 2013 10:21:46 -0400
 

doc/preferred_content.mdwn

@@ -77,13 +77,18 @@ drop content that is present! Don't go there..
 git-annex comes with some standard preferred content expressions, that can
 be used with repositories that are in some pre-defined groups. To make a
 repository use one of these, just set its preferred content expression
-to "standard", and put it in one of these groups:
+to "standard", and put it in one of these groups.
+
+(Note that most of these standard expressions also make the repository
+prefer any content that is only currently available on untrusted and
+dead repositories. So if an untrusted repository gets connected,
+any repository that can will back it up.)
 
 ### client
 
 All content is preferred, unless it's in a "archive" directory.
 
-`exclude=*/archive/* and exclude=archive/*`
+`(exclude=*/archive/* and exclude=archive/*) or (not copies=semitrusted:1)`
 
 ### transfer
 
@@ -95,7 +100,7 @@ USB drive used in a sneakernet.
 The preferred content expression for these causes them to get and retain
 data until all clients have a copy.
 
-`not (inallgroup=client and copies=client:2) and exclude=*/archive/* and exclude=archive/*`
+`(not (inallgroup=client and copies=client:2) and exclude=*/archive/* and exclude=archive/*) or (not copies=semitrusted:1)`
 
 The "copies=client:2" part of the above handles the case where
 there is only one client repository. It makes a transfer repository
@@ -114,20 +119,20 @@ All content is preferred.
 Only prefers content that's not already backed up to another backup
 or incremental backup repository.
 
-`include=* and (not copies=backup:1) and (not copies=incrementalbackup:1)`
+`(include=* and (not copies=backup:1) and (not copies=incrementalbackup:1)) or (not copies=semitrusted:1)`
 
 ### small archive
 
 Only prefers content that's located in an "archive" directory, and
 only if it's not already been archived somewhere else.
 
-`(include=*/archive/* or include=archive/*) and not (copies=archive:1 or copies=smallarchive:1)`
+`((include=*/archive/* or include=archive/*) and not (copies=archive:1 or copies=smallarchive:1)) or (not copies=semitrusted:1)`
 
 ### full archive
 
 All content is preferred, unless it's already been archived somewhere else.
 
-`not (copies=archive:1 or copies=smallarchive:1)`
+`(not (copies=archive:1 or copies=smallarchive:1)) or (not copies=semitrusted:1)`
 
 Note that if you want to archive multiple copies (not a bad idea!),
 you should instead configure all your archive repositories with a
@@ -155,4 +160,12 @@ local copy of every file. Instead, you can manually run `git annex get`,
 Only content that is present is preferred. Content in "archive"
 directories is never preferred.
 
-`present and exclude=*/archive/* and exclude=archive/*`
+`(present and exclude=*/archive/* and exclude=archive/*) or (not copies=semitrusted:1)`
+
+### unwanted
+
+Use for repositories that you don't want to exist. This will result
+in any content on them being moved away to other repositories. (Works
+best when the unwanted repository is also marked as untrusted or dead.)
+
+`exclude=*`