remove empty log files in transition

forget --drop-dead: Remove several classes of git-annex log files when they
become empty, further reducing the size of the git-annex branch.

Noticed while testing sameas uuid removal, but it could happen other times
too.

An empty log file is always treated by git-annex the same as no file
being present, and when the files are per-key, it can be a sizable space
saving to exclude them from the tree.

Annex/Branch.hs

@@ -583,22 +583,22 @@ performTransitionsLocked jl ts neednewlocalbranch transitionedrefs = do
 			content <- getStaged f
 			apply changers' f content
 	apply [] _ _ = return ()
-	apply (changer:rest) file content =
-		case changer file content of
-			RemoveFile -> do
-				Annex.Queue.addUpdateIndex
-					=<< inRepo (Git.UpdateIndex.unstageFile file)
-				-- File is deleted; can't run any other
-				-- transitions on it.
-				return ()
-			ChangeFile builder -> do
-				let content' = toLazyByteString builder
-				sha <- hashBlob content'
-				Annex.Queue.addUpdateIndex $ Git.UpdateIndex.pureStreamer $
-					Git.UpdateIndex.updateIndexLine sha TreeFile (asTopFilePath file)
-				apply rest file content'
-			PreserveFile ->
-				apply rest file content
+	apply (changer:rest) file content = case changer file content of
+		PreserveFile -> apply rest file content
+		ChangeFile builder -> do
+			let content' = toLazyByteString builder
+			if L.null content'
+				then do
+					Annex.Queue.addUpdateIndex
+						=<< inRepo (Git.UpdateIndex.unstageFile file)
+					-- File is deleted; can't run any other
+					-- transitions on it.
+					return ()
+				else do
+					sha <- hashBlob content'
+					Annex.Queue.addUpdateIndex $ Git.UpdateIndex.pureStreamer $
+						Git.UpdateIndex.updateIndexLine sha TreeFile (asTopFilePath file)
+					apply rest file content'
 
 checkBranchDifferences :: Git.Ref -> Annex ()
 checkBranchDifferences ref = do
@@ -666,3 +666,4 @@ rememberTreeish treeish graftpoint = lockJournal $ \jl -> do
 	-- and the index was updated to that above, so it's safe to
 	-- say that the index contains c'.
 	setIndexSha c'
+

Annex/Branch/Transitions.hs

@@ -24,14 +24,12 @@ import Types.Remote
 import Annex.SpecialRemote.Config
 
 import qualified Data.Map as M
-import qualified Data.Set as S
 import qualified Data.ByteString.Lazy as L
 import qualified Data.Attoparsec.ByteString.Lazy as A
 import Data.ByteString.Builder
 
 data FileTransition
 	= ChangeFile Builder
-	| RemoveFile
 	| PreserveFile
 
 type TransitionCalculator = TrustMap -> M.Map UUID RemoteConfig -> FilePath -> L.ByteString -> FileTransition
@@ -69,19 +67,15 @@ dropDead trustmap remoteconfigmap f content = case getLogVariety f of
 			dropDeadFromMapLog trustmap' id $
 				UUIDBased.parseLogNew A.takeByteString content
 	Just (ChunkLog _) -> ChangeFile $
-		Chunk.buildLog $ dropDeadFromMapLog trustmap' fst $ Chunk.parseLog content
-	Just (PresenceLog _) ->
-		let newlog = Presence.compactLog $
-			dropDeadFromPresenceLog trustmap' $ Presence.parseLog content
-		in if null newlog
-			then RemoveFile
-			else ChangeFile $ Presence.buildLog newlog
-	Just RemoteMetaDataLog ->
-		let newlog = dropDeadFromRemoteMetaDataLog trustmap' $
+		Chunk.buildLog $ dropDeadFromMapLog trustmap' fst $
+			Chunk.parseLog content
+	Just (PresenceLog _) -> ChangeFile $ Presence.buildLog $
+		Presence.compactLog $
+			dropDeadFromPresenceLog trustmap' $
+				Presence.parseLog content
+	Just RemoteMetaDataLog -> ChangeFile $ MetaData.buildLog $
+		dropDeadFromRemoteMetaDataLog trustmap' $
 			MetaData.simplifyLog $ MetaData.parseLog content
-		in if S.null newlog
-			then RemoveFile
-			else ChangeFile $ MetaData.buildLog newlog
 	Just OtherLog -> PreserveFile
 	Nothing -> PreserveFile
   where

CHANGELOG

@@ -7,6 +7,8 @@ git-annex (7.20191011) UNRELEASED; urgency=medium
     or EXPORTSUPPORTED will now get back an ERROR. That would be a very
     hackish thing for an external special remote to do, needing some kind
     of hard-coded key value to be used, so probably nothing will be affected.
+  * forget --drop-dead: Remove several classes of git-annex log files
+    when they become empty, further reducing the size of the git-annex branch.
 
  -- Joey Hess <id@joeyh.name>  Thu, 19 Sep 2019 11:11:19 -0400