From 5e1221ad530fbc9bb63cc4f5997485fc5494c6fe Mon Sep 17 00:00:00 2001
From: Joey Hess <joeyh@joeyh.name>
Date: Tue, 21 May 2019 11:32:54 -0400
Subject: [PATCH] Improve shape of commit tree when importing from unversioned
 special remotes

Make the import have the previous import as a parent, so eg `git log --stat`
displays a useful diff.

Also a minor optimisation, only calculate the depth of the imported history
once.
---
 Annex/Import.hs                               | 38 ++++++++++++-------
 CHANGELOG                                     |  2 +
 ...ort_from_special_remote_large_git_log.mdwn |  2 +
 3 files changed, 29 insertions(+), 13 deletions(-)

diff --git a/Annex/Import.hs b/Annex/Import.hs
index 006bd02999..2e152a0f7a 100644
--- a/Annex/Import.hs
+++ b/Annex/Import.hs
@@ -163,40 +163,44 @@ buildImportCommit remote importtreeconfig importcommitconfig importable =
 buildImportCommit' :: ImportCommitConfig -> Maybe Sha -> History Sha -> Annex (Maybe Sha)
 buildImportCommit' importcommitconfig mtrackingcommit imported@(History ti _) =
 	case mtrackingcommit of
-		Nothing -> Just <$> mkcommits imported
+		Nothing -> Just <$> mkcommitsunconnected imported
 		Just trackingcommit -> do
 			-- Get history of tracking branch to at most
 			-- one more level deep than what was imported,
 			-- so we'll have enough history to compare,
 			-- but not spend too much time getting it.
-			let maxdepth = succ (historyDepth imported)
+			let maxdepth = succ importeddepth
 			inRepo (getHistoryToDepth maxdepth trackingcommit)
 				>>= go trackingcommit
   where
-	go _ Nothing = Just <$> mkcommits imported
+	go _ Nothing = Just <$> mkcommitsunconnected imported
 	go trackingcommit (Just h)
 		-- If the tracking branch head is a merge commit
 		-- with a tree that matches the head of the history,
 		-- and one side of the merge matches the history,
 		-- nothing new needs to be committed.
-		| t == ti && any (sametodepth imported) (S.toList s) = return Nothing
+		| t == ti && any sametodepth (S.toList s) = return Nothing
 		-- If the tracking branch matches the history,
 		-- nothing new needs to be committed.
 		-- (This is unlikely to happen.)
-		| sametodepth imported h' = return Nothing
+		| sametodepth h' = return Nothing
 		| otherwise = do
 			importedcommit <- case getRemoteTrackingBranchImportHistory h of
-				Nothing ->
-					mkcommits imported
-				Just oldimported@(History oldhc _) -> do
-					let oldimportedtrees = mapHistory historyCommitTree oldimported
-					mknewcommits oldhc oldimportedtrees imported
+				Nothing -> mkcommitsunconnected imported
+				Just oldimported@(History oldhc _)
+					| importeddepth == 1 ->
+						mkcommitconnected imported oldimported
+					| otherwise -> do
+						let oldimportedtrees = mapHistory historyCommitTree oldimported
+						mknewcommits oldhc oldimportedtrees imported
 			Just <$> makeRemoteTrackingBranchMergeCommit'
 				trackingcommit importedcommit ti
 	  where
 		h'@(History t s) = mapHistory historyCommitTree h
 
-	sametodepth a b = a == truncateHistoryToDepth (historyDepth a) b
+	importeddepth = historyDepth imported
+
+	sametodepth b = imported == truncateHistoryToDepth importeddepth b
 
 	mkcommit parents tree = inRepo $ Git.Branch.commitTree
 		(importCommitMode importcommitconfig)
@@ -204,8 +208,16 @@ buildImportCommit' importcommitconfig mtrackingcommit imported@(History ti _) =
 		parents
 		tree
 
-	mkcommits (History importedtree hs) = do
-		parents <- mapM mkcommits (S.toList hs)
+	-- Start a new history of import commits, not connected to any
+	-- prior import commits.
+	mkcommitsunconnected (History importedtree hs) = do
+		parents <- mapM mkcommitsunconnected (S.toList hs)
+		mkcommit parents importedtree
+
+	-- Commit the new history connected with the old history.
+	-- Used when the import is not versioned, so the history depth is 1.
+	mkcommitconnected (History importedtree _) (History oldhc _) = do
+		let parents = [historyCommit oldhc]
 		mkcommit parents importedtree
 
 	-- Reuse the commits from the old imported History when possible.
diff --git a/CHANGELOG b/CHANGELOG
index dbcab637ee..bb47c69098 100644
--- a/CHANGELOG
+++ b/CHANGELOG
@@ -5,6 +5,8 @@ git-annex (7.20190508) UNRELEASED; urgency=medium
   * Makefile: Added install-completions to install target.
   * Added the ability to run one job per CPU (core), by setting
     annex.jobs=cpus, or using option --jobs=cpus or -Jcpus.
+  * Improve shape of commit tree when importing from unversioned special
+    remotes.
 
  -- Joey Hess <id@joeyh.name>  Mon, 06 May 2019 13:52:02 -0400
 
diff --git a/doc/todo/import_from_special_remote_large_git_log.mdwn b/doc/todo/import_from_special_remote_large_git_log.mdwn
index f1b43221fa..5949367156 100644
--- a/doc/todo/import_from_special_remote_large_git_log.mdwn
+++ b/doc/todo/import_from_special_remote_large_git_log.mdwn
@@ -18,3 +18,5 @@ and adds more commits on top of those, so this is mostly not a problem
 there. If the old and new imported histories are disjoint, a commit or
 commits will be made with no parent, but that seems acceptable; it's an
 edge case and it's replicating the information from the remote.
+
+> [[done]] --[[Joey]]