From 75acf5f440bba2e366c5cf66b544f63cf796e57f Mon Sep 17 00:00:00 2001
From: Joey Hess <joeyh@joeyh.name>
Date: Mon, 14 Dec 2020 13:17:43 -0400
Subject: [PATCH] improve some edge cases around partial initialization

* Guard against running in a repo where annex.uuid is set but
  annex.version is set, or vice-versa.
* Avoid autoinit when a repo does not have annex.version or annex.uuid
  set, but has a git-annex objects directory, suggesting it was used
  by git-annex before.
---
 Annex/Init.hs                                 | 45 +++++++++++++++++--
 CHANGELOG                                     |  5 +++
 ..._when_git-annex_branch_already_exists.mdwn |  2 +
 3 files changed, 49 insertions(+), 3 deletions(-)

diff --git a/Annex/Init.hs b/Annex/Init.hs
index c05263c7df..3078a6213f 100644
--- a/Annex/Init.hs
+++ b/Annex/Init.hs
@@ -159,6 +159,29 @@ uninitialize = do
 	removeRepoUUID
 	removeVersion
 
+{- Gets the version that the repo is initialized with.
+ -
+ - To make sure the repo is fully initialized, also checks that it has a
+ - uuid configured. In the unusual case where one is set and the other is
+ - not, errors out to avoid running in an inconsistent state.
+ -}
+getInitializedVersion :: Annex (Maybe RepoVersion)
+getInitializedVersion = do
+	um <- (\u -> if u == NoUUID then Nothing else Just u) <$> getUUID
+	vm <- getVersion
+	case (um, vm) of
+		(Just _, Just v) -> return (Just v)
+		(Nothing, Nothing) -> return Nothing
+		(Just _, Nothing) -> onemissing "annex.version" "annex.uuid"
+		(Nothing, Just _) -> onemissing "annex.uuid" "annex.version"
+  where
+	onemissing missing have = giveup $ unwords
+		[ "This repository has " ++ have ++ " set,"
+		, "but " ++ missing ++ " is not set. Perhaps that"
+		, "git config was lost. Cannot use the repository"
+		, "in this state; set back " ++ missing ++ " to fix this."
+		]
+
 {- Will automatically initialize if there is already a git-annex
  - branch from somewhere. Otherwise, require a manual init
  - to avoid git-annex accidentally being run in git
@@ -167,7 +190,7 @@ uninitialize = do
  - Checks repository version and handles upgrades too.
  -}
 ensureInitialized :: Annex ()
-ensureInitialized = getVersion >>= maybe needsinit checkUpgrade
+ensureInitialized = getInitializedVersion >>= maybe needsinit checkUpgrade
   where
 	needsinit = ifM autoInitializeAllowed
 		( do
@@ -178,14 +201,30 @@ ensureInitialized = getVersion >>= maybe needsinit checkUpgrade
 
 {- Check if auto-initialize is allowed. -}
 autoInitializeAllowed :: Annex Bool
-autoInitializeAllowed = Annex.Branch.hasSibling
+autoInitializeAllowed = Annex.Branch.hasSibling <&&> objectDirNotPresent
+
+objectDirNotPresent :: Annex Bool
+objectDirNotPresent = do
+	d <- fromRawFilePath <$> fromRepo gitAnnexObjectDir
+	exists <- liftIO $ doesDirectoryExist d
+	when exists $
+		giveup $ unwords $ 
+			[ "This repository is not initialized for use"
+			, "by git-annex, but " ++ d ++ " exists,"
+			, "which indicates this repository was used by"
+			, "git-annex before, and may have lost its"
+			, "annex.uuid and annex.version configs. Either"
+			, "set back missing configs, or run git-annex init"
+			, "to initialize with a new uuid."
+			]
+	return (not exists)
 
 {- Initialize if it can do so automatically. Avoids failing if it cannot.
  -
  - Checks repository version and handles upgrades too.
  -}
 autoInitialize :: Annex ()
-autoInitialize = getVersion >>= maybe needsinit checkUpgrade
+autoInitialize = getInitializedVersion >>= maybe needsinit checkUpgrade
   where
 	needsinit =
 		whenM (initializeAllowed <&&> autoInitializeAllowed) $ do
diff --git a/CHANGELOG b/CHANGELOG
index ef42edcb33..af80578008 100644
--- a/CHANGELOG
+++ b/CHANGELOG
@@ -12,6 +12,11 @@ git-annex (8.20201128) UNRELEASED; urgency=medium
     having a copy of the content.
   * Support special remotes that are configured with importtree=yes but
     without exporttree=yes.
+  * Guard against running in a repo where annex.uuid is set but
+    annex.version is set, or vice-versa.
+  * Avoid autoinit when a repo does not have annex.version or annex.uuid
+    set, but has a git-annex objects directory, suggesting it was used
+    by git-annex before.
 
  -- Joey Hess <id@joeyh.name>  Mon, 30 Nov 2020 12:55:49 -0400
 
diff --git a/doc/todo/avoid_autoinit_when_git-annex_branch_already_exists.mdwn b/doc/todo/avoid_autoinit_when_git-annex_branch_already_exists.mdwn
index 914a74ecc6..f94a128bf1 100644
--- a/doc/todo/avoid_autoinit_when_git-annex_branch_already_exists.mdwn
+++ b/doc/todo/avoid_autoinit_when_git-annex_branch_already_exists.mdwn
@@ -24,3 +24,5 @@ A bare repo that was just cloned will have a git-annex branch
 before it gets initialized. So for bare repos, would need to not consider
 that, but looking if annex/index exists would still do. Or may be better
 not to special case it, and only look for the annex/index file? --[[Joey]]
+
+> [[done]] --[[Joey]]
-- 
2.39.5