unused: Bug fix when a new file was added to the annex, and then removed (but not git rmed). git still has the add staged in this case, so the content should not be unused and was wrongly treated as such.

So, we need to look at both the file on disk to see if it's a annex link,
and the file in the index too. lookupFile doesn't look in the index if the file
is not present on disk.

3 files changed, 17 insertions, 10 deletions

diff --git a/Command/Unused.hs b/Command/Unused.hs
index 4353bd075..a643cf8e0 100644
--- a/Command/Unused.hs
+++ b/Command/Unused.hs
@@ -26,6 +26,7 @@ import qualified Git.LsFiles as LsFiles
 import qualified Git.DiffTree as DiffTree
 import qualified Remote
 import qualified Annex.Branch
+import Annex.Link
 import Annex.CatFile
 import Types.Key
 import Types.RefSpec
@@ -214,8 +215,12 @@ withKeysReferenced' mdir initial a = do
 		Just dir -> inRepo $ LsFiles.inRepo [dir]
 	go v [] = return v
 	go v (f:fs) = do
-		x <- lookupFile f
-		case x of
+		mk <- getM id
+			[ isAnnexLink f
+			, liftIO (isPointerFile f)
+			, catKeyFile f
+			]
+		case mk of
 			Nothing -> go v fs
 			Just k -> do
 				!v' <- a k f v
diff --git a/Test.hs b/Test.hs
index 7918ff0c1..ba491f3d8 100644
--- a/Test.hs
+++ b/Test.hs
@@ -705,8 +705,8 @@ test_fsck_basic = intmpclonerepo $ do
 		git_annex "get" [f] @? "get of file failed"
 		Utility.FileMode.allowWrite f
 		writeFile f (changedcontent f)
-		ifM (annexeval Config.isDirect)
-			( git_annex "fsck" [] @? "fsck failed in direct mode with changed file content"
+		ifM (annexeval Config.isDirect <||> unlockedFiles <$> getTestMode)
+			( git_annex "fsck" [] @? "fsck failed on unlocked file with changed file content"
 			, not <$> git_annex "fsck" [] @? "fsck failed to fail with corrupted file content"
 			)
 		git_annex "fsck" [] @? "fsck unexpectedly failed again; previous one did not fix problem with " ++ f
@@ -828,7 +828,7 @@ test_unused = intmpclonerepoInDirect $ do
 	checkunused [unusedfilekey] "with renamed link deleted"
 
 	-- unused used to miss symlinks that were deleted or modified
-	-- manually, but commited as such.
+	-- manually
 	writeFile "unusedfile" "unusedcontent"
 	git_annex "add" ["unusedfile"] @? "add of unusedfile failed"
 	boolSystem "git" [Param "add", File "unusedfile"] @? "git add failed"
@@ -837,15 +837,14 @@ test_unused = intmpclonerepoInDirect $ do
 	boolSystem "git" [Param "rm", Param "-qf", File "unusedfile"] @? "git rm failed"
 	checkunused [unusedfilekey'] "with staged link deleted"
 
-	-- unused used to miss symlinks that were deleted or modified
-	-- manually, but not staged as such.
+	-- unused used to false positive on symlinks that were
+	-- deleted or modified manually, but not staged as such
 	writeFile "unusedfile" "unusedcontent"
 	git_annex "add" ["unusedfile"] @? "add of unusedfile failed"
 	boolSystem "git" [Param "add", File "unusedfile"] @? "git add failed"
-	unusedfilekey'' <- annexeval $ findkey "unusedfile"
-	checkunused [] "with unstaged deleted link"
+	checkunused [] "with staged file"
 	removeFile "unusedfile"
-	checkunused [unusedfilekey''] "with unstaged link deleted"
+	checkunused [] "with staged deleted file"
 
   where
 	checkunused expectedkeys desc = do
diff --git a/debian/changelog b/debian/changelog
index cab3bc8d4..e5d968d9b 100644
--- a/debian/changelog
+++ b/debian/changelog
@@ -40,6 +40,9 @@ git-annex (6.20151219) UNRELEASED; urgency=medium
     This may break existing parsers of this json output, if there were any.
   * whereis --json: Make url list be included in machine-parseable form.
   * test: Added --keep-failures option.
+  * unused: Bug fix when a new file was added to the annex, and then
+    removed (but not git rmed). git still has the add staged in this case,
+    so the content should not be unused and was wrongly treated as such.
 
  -- Joey Hess <id@joeyh.name>  Sat, 19 Dec 2015 13:31:17 -0400