repack: modify behavior of -A option to leave unreferenced objects unpacked

The previous behavior of the -A option was to retain any previously
packed objects which had become unreferenced, and place them into the newly
created pack file.  Since git-gc, when run automatically with the --auto
option, calls repack with the -A option, this had the effect of retaining
unreferenced packed objects indefinitely. To avoid this scenario, the
user was required to run git-gc with the little known --prune option or
to manually run repack with the -a option.

This patch changes the behavior of the -A option so that unreferenced
objects that exist in any pack file being replaced, will be unpacked into
the repository. The unreferenced loose objects can then be garbage collected
by git-gc (i.e. git-prune) based on the gc.pruneExpire setting.

Also add new tests for checking whether unreferenced objects which were
previously packed are properly left in the repository unpacked after
repacking.

Signed-off-by: Brandon Casey <drafnel@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

2 files changed, 60 insertions, 5 deletions

diff --git a/git-repack.sh b/git-repack.sh
index e18eb3f5dc..a0e06ed076 100755
--- a/git-repack.sh
+++ b/git-repack.sh
@@ -30,7 +30,7 @@ do
 	-n)	no_update_info=t ;;
 	-a)	all_into_one=t ;;
 	-A)	all_into_one=t
-		keep_unreachable=--keep-unreachable ;;
+		keep_unreachable=t ;;
 	-d)	remove_redundant=t ;;
 	-q)	quiet=-q ;;
 	-f)	no_reuse=--no-reuse-object ;;
@@ -78,9 +78,6 @@ case ",$all_into_one," in
 	if test -z "$args"
 	then
 		args='--unpacked --incremental'
-	elif test -n "$keep_unreachable"
-	then
-		args="$args $keep_unreachable"
 	fi
 	;;
 esac
@@ -130,7 +127,18 @@ then
 		  do
 			case " $fullbases " in
 			*" $e "*) ;;
-			*)	rm -f "$e.pack" "$e.idx" "$e.keep" ;;
+			*)
+				rm -f "$e.idx" "$e.keep"
+				if test -n "$keep_unreachable" &&
+				   test -f "$e.pack"
+				then
+					git unpack-objects < "$e.pack" || {
+						echo >&2 "Failed unpacking unreachable objects from redundant pack file $e.pack"
+						exit 1
+					}
+				fi
+				rm -f "$e.pack"
+			;;
 			esac
 		  done
 		)
diff --git a/t/t7701-repack-unpack-unreachable.sh b/t/t7701-repack-unpack-unreachable.sh
new file mode 100755
index 0000000000..6a5211f187
--- /dev/null
+++ b/t/t7701-repack-unpack-unreachable.sh
@@ -0,0 +1,47 @@
+#!/bin/sh
+
+test_description='git-repack works correctly'
+
+. ./test-lib.sh
+
+test_expect_success '-A option leaves unreachable objects unpacked' '
+	echo content > file1 &&
+	git add . &&
+	git commit -m initial_commit &&
+	# create a transient branch with unique content
+	git checkout -b transient_branch &&
+	echo more content >> file1 &&
+	# record the objects created in the database for file, commit, tree
+	fsha1=$(git hash-object file1) &&
+	git commit -a -m more_content &&
+	csha1=$(git rev-parse HEAD^{commit}) &&
+	tsha1=$(git rev-parse HEAD^{tree}) &&
+	git checkout master &&
+	echo even more content >> file1 &&
+	git commit -a -m even_more_content &&
+	# delete the transient branch
+	git branch -D transient_branch &&
+	# pack the repo
+	git repack -A -d -l &&
+	# verify objects are packed in repository
+	test 3 = $(git verify-pack -v -- .git/objects/pack/*.idx |
+		   grep -e "^$fsha1 " -e "^$csha1 " -e "^$tsha1 " |
+		   sort | uniq | wc -l) &&
+	git show $fsha1 &&
+	git show $csha1 &&
+	git show $tsha1 &&
+	# now expire the reflog
+	sleep 1 &&
+	git reflog expire --expire-unreachable=now --all &&
+	# and repack
+	git repack -A -d -l &&
+	# verify objects are retained unpacked
+	test 0 = $(git verify-pack -v -- .git/objects/pack/*.idx |
+		   grep -e "^$fsha1 " -e "^$csha1 " -e "^$tsha1 " |
+		   sort | uniq | wc -l) &&
+	git show $fsha1 &&
+	git show $csha1 &&
+	git show $tsha1
+'
+
+test_done