Merge branch 'ds/commit-graph-fsck'

"git fsck" learns to make sure the optional commit-graph file is in
a sane state.

* ds/commit-graph-fsck: (23 commits)
  coccinelle: update commit.cocci
  commit-graph: update design document
  gc: automatically write commit-graph files
  commit-graph: add '--reachable' option
  commit-graph: use string-list API for input
  fsck: verify commit-graph
  commit-graph: verify contents match checksum
  commit-graph: test for corrupted octopus edge
  commit-graph: verify commit date
  commit-graph: verify generation number
  commit-graph: verify parent list
  commit-graph: verify root tree OIDs
  commit-graph: verify objects exist
  commit-graph: verify corrupt OID fanout and lookup
  commit-graph: verify required chunks are present
  commit-graph: verify catches corrupt signature
  commit-graph: add 'verify' subcommand
  commit-graph: load a root tree from specific graph
  commit: force commit to parse from object database
  commit-graph: parse commit from chosen graph
  ...

1 files changed, 203 insertions, 2 deletions

diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh
index 77d85aefe7..5947de3d24 100755
--- a/t/t5318-commit-graph.sh
+++ b/t/t5318-commit-graph.sh
@@ -11,6 +11,11 @@ test_expect_success 'setup full repo' '
 	objdir=".git/objects"
 '
 
+test_expect_success 'verify graph with no graph file' '
+	cd "$TRASH_DIRECTORY/full" &&
+	git commit-graph verify
+'
+
 test_expect_success 'write graph with no packs' '
 	cd "$TRASH_DIRECTORY/full" &&
 	git commit-graph write --object-dir . &&
@@ -28,8 +33,8 @@ test_expect_success 'create commits and repack' '
 '
 
 graph_git_two_modes() {
-	git -c core.graph=true $1 >output
-	git -c core.graph=false $1 >expect
+	git -c core.commitGraph=true $1 >output
+	git -c core.commitGraph=false $1 >expect
 	test_cmp output expect
 }
 
@@ -200,6 +205,16 @@ test_expect_success 'build graph from commits with append' '
 graph_git_behavior 'append graph, commit 8 vs merge 1' full commits/8 merge/1
 graph_git_behavior 'append graph, commit 8 vs merge 2' full commits/8 merge/2
 
+test_expect_success 'build graph using --reachable' '
+	cd "$TRASH_DIRECTORY/full" &&
+	git commit-graph write --reachable &&
+	test_path_is_file $objdir/info/commit-graph &&
+	graph_read_expect "11" "large_edges"
+'
+
+graph_git_behavior 'append graph, commit 8 vs merge 1' full commits/8 merge/1
+graph_git_behavior 'append graph, commit 8 vs merge 2' full commits/8 merge/2
+
 test_expect_success 'setup bare repo' '
 	cd "$TRASH_DIRECTORY" &&
 	git clone --bare --no-local full bare &&
@@ -230,4 +245,190 @@ test_expect_success 'perform fast-forward merge in full repo' '
 	test_cmp expect output
 '
 
+test_expect_success 'check that gc computes commit-graph' '
+	cd "$TRASH_DIRECTORY/full" &&
+	git commit --allow-empty -m "blank" &&
+	git commit-graph write --reachable &&
+	cp $objdir/info/commit-graph commit-graph-before-gc &&
+	git reset --hard HEAD~1 &&
+	git config gc.writeCommitGraph true &&
+	git gc &&
+	cp $objdir/info/commit-graph commit-graph-after-gc &&
+	! test_cmp commit-graph-before-gc commit-graph-after-gc &&
+	git commit-graph write --reachable &&
+	test_cmp commit-graph-after-gc $objdir/info/commit-graph
+'
+
+# the verify tests below expect the commit-graph to contain
+# exactly the commits reachable from the commits/8 branch.
+# If the file changes the set of commits in the list, then the
+# offsets into the binary file will result in different edits
+# and the tests will likely break.
+
+test_expect_success 'git commit-graph verify' '
+	cd "$TRASH_DIRECTORY/full" &&
+	git rev-parse commits/8 | git commit-graph write --stdin-commits &&
+	git commit-graph verify >output
+'
+
+NUM_COMMITS=9
+NUM_OCTOPUS_EDGES=2
+HASH_LEN=20
+GRAPH_BYTE_VERSION=4
+GRAPH_BYTE_HASH=5
+GRAPH_BYTE_CHUNK_COUNT=6
+GRAPH_CHUNK_LOOKUP_OFFSET=8
+GRAPH_CHUNK_LOOKUP_WIDTH=12
+GRAPH_CHUNK_LOOKUP_ROWS=5
+GRAPH_BYTE_OID_FANOUT_ID=$GRAPH_CHUNK_LOOKUP_OFFSET
+GRAPH_BYTE_OID_LOOKUP_ID=$(($GRAPH_CHUNK_LOOKUP_OFFSET + \
+			    1 * $GRAPH_CHUNK_LOOKUP_WIDTH))
+GRAPH_BYTE_COMMIT_DATA_ID=$(($GRAPH_CHUNK_LOOKUP_OFFSET + \
+			     2 * $GRAPH_CHUNK_LOOKUP_WIDTH))
+GRAPH_FANOUT_OFFSET=$(($GRAPH_CHUNK_LOOKUP_OFFSET + \
+		       $GRAPH_CHUNK_LOOKUP_WIDTH * $GRAPH_CHUNK_LOOKUP_ROWS))
+GRAPH_BYTE_FANOUT1=$(($GRAPH_FANOUT_OFFSET + 4 * 4))
+GRAPH_BYTE_FANOUT2=$(($GRAPH_FANOUT_OFFSET + 4 * 255))
+GRAPH_OID_LOOKUP_OFFSET=$(($GRAPH_FANOUT_OFFSET + 4 * 256))
+GRAPH_BYTE_OID_LOOKUP_ORDER=$(($GRAPH_OID_LOOKUP_OFFSET + $HASH_LEN * 8))
+GRAPH_BYTE_OID_LOOKUP_MISSING=$(($GRAPH_OID_LOOKUP_OFFSET + $HASH_LEN * 4 + 10))
+GRAPH_COMMIT_DATA_OFFSET=$(($GRAPH_OID_LOOKUP_OFFSET + $HASH_LEN * $NUM_COMMITS))
+GRAPH_BYTE_COMMIT_TREE=$GRAPH_COMMIT_DATA_OFFSET
+GRAPH_BYTE_COMMIT_PARENT=$(($GRAPH_COMMIT_DATA_OFFSET + $HASH_LEN))
+GRAPH_BYTE_COMMIT_EXTRA_PARENT=$(($GRAPH_COMMIT_DATA_OFFSET + $HASH_LEN + 4))
+GRAPH_BYTE_COMMIT_WRONG_PARENT=$(($GRAPH_COMMIT_DATA_OFFSET + $HASH_LEN + 3))
+GRAPH_BYTE_COMMIT_GENERATION=$(($GRAPH_COMMIT_DATA_OFFSET + $HASH_LEN + 11))
+GRAPH_BYTE_COMMIT_DATE=$(($GRAPH_COMMIT_DATA_OFFSET + $HASH_LEN + 12))
+GRAPH_COMMIT_DATA_WIDTH=$(($HASH_LEN + 16))
+GRAPH_OCTOPUS_DATA_OFFSET=$(($GRAPH_COMMIT_DATA_OFFSET + \
+			     $GRAPH_COMMIT_DATA_WIDTH * $NUM_COMMITS))
+GRAPH_BYTE_OCTOPUS=$(($GRAPH_OCTOPUS_DATA_OFFSET + 4))
+GRAPH_BYTE_FOOTER=$(($GRAPH_OCTOPUS_DATA_OFFSET + 4 * $NUM_OCTOPUS_EDGES))
+
+# usage: corrupt_graph_and_verify <position> <data> <string>
+# Manipulates the commit-graph file at the position
+# by inserting the data, then runs 'git commit-graph verify'
+# and places the output in the file 'err'. Test 'err' for
+# the given string.
+corrupt_graph_and_verify() {
+	pos=$1
+	data="${2:-\0}"
+	grepstr=$3
+	cd "$TRASH_DIRECTORY/full" &&
+	test_when_finished mv commit-graph-backup $objdir/info/commit-graph &&
+	cp $objdir/info/commit-graph commit-graph-backup &&
+	printf "$data" | dd of="$objdir/info/commit-graph" bs=1 seek="$pos" conv=notrunc &&
+	test_must_fail git commit-graph verify 2>test_err &&
+	grep -v "^+" test_err >err
+	test_i18ngrep "$grepstr" err
+}
+
+test_expect_success 'detect bad signature' '
+	corrupt_graph_and_verify 0 "\0" \
+		"graph signature"
+'
+
+test_expect_success 'detect bad version' '
+	corrupt_graph_and_verify $GRAPH_BYTE_VERSION "\02" \
+		"graph version"
+'
+
+test_expect_success 'detect bad hash version' '
+	corrupt_graph_and_verify $GRAPH_BYTE_HASH "\02" \
+		"hash version"
+'
+
+test_expect_success 'detect low chunk count' '
+	corrupt_graph_and_verify $GRAPH_BYTE_CHUNK_COUNT "\02" \
+		"missing the .* chunk"
+'
+
+test_expect_success 'detect missing OID fanout chunk' '
+	corrupt_graph_and_verify $GRAPH_BYTE_OID_FANOUT_ID "\0" \
+		"missing the OID Fanout chunk"
+'
+
+test_expect_success 'detect missing OID lookup chunk' '
+	corrupt_graph_and_verify $GRAPH_BYTE_OID_LOOKUP_ID "\0" \
+		"missing the OID Lookup chunk"
+'
+
+test_expect_success 'detect missing commit data chunk' '
+	corrupt_graph_and_verify $GRAPH_BYTE_COMMIT_DATA_ID "\0" \
+		"missing the Commit Data chunk"
+'
+
+test_expect_success 'detect incorrect fanout' '
+	corrupt_graph_and_verify $GRAPH_BYTE_FANOUT1 "\01" \
+		"fanout value"
+'
+
+test_expect_success 'detect incorrect fanout final value' '
+	corrupt_graph_and_verify $GRAPH_BYTE_FANOUT2 "\01" \
+		"fanout value"
+'
+
+test_expect_success 'detect incorrect OID order' '
+	corrupt_graph_and_verify $GRAPH_BYTE_OID_LOOKUP_ORDER "\01" \
+		"incorrect OID order"
+'
+
+test_expect_success 'detect OID not in object database' '
+	corrupt_graph_and_verify $GRAPH_BYTE_OID_LOOKUP_MISSING "\01" \
+		"from object database"
+'
+
+test_expect_success 'detect incorrect tree OID' '
+	corrupt_graph_and_verify $GRAPH_BYTE_COMMIT_TREE "\01" \
+		"root tree OID for commit"
+'
+
+test_expect_success 'detect incorrect parent int-id' '
+	corrupt_graph_and_verify $GRAPH_BYTE_COMMIT_PARENT "\01" \
+		"invalid parent"
+'
+
+test_expect_success 'detect extra parent int-id' '
+	corrupt_graph_and_verify $GRAPH_BYTE_COMMIT_EXTRA_PARENT "\00" \
+		"is too long"
+'
+
+test_expect_success 'detect wrong parent' '
+	corrupt_graph_and_verify $GRAPH_BYTE_COMMIT_WRONG_PARENT "\01" \
+		"commit-graph parent for"
+'
+
+test_expect_success 'detect incorrect generation number' '
+	corrupt_graph_and_verify $GRAPH_BYTE_COMMIT_GENERATION "\070" \
+		"generation for commit"
+'
+
+test_expect_success 'detect incorrect generation number' '
+	corrupt_graph_and_verify $GRAPH_BYTE_COMMIT_GENERATION "\01" \
+		"non-zero generation number"
+'
+
+test_expect_success 'detect incorrect commit date' '
+	corrupt_graph_and_verify $GRAPH_BYTE_COMMIT_DATE "\01" \
+		"commit date"
+'
+
+test_expect_success 'detect incorrect parent for octopus merge' '
+	corrupt_graph_and_verify $GRAPH_BYTE_OCTOPUS "\01" \
+		"invalid parent"
+'
+
+test_expect_success 'detect invalid checksum hash' '
+	corrupt_graph_and_verify $GRAPH_BYTE_FOOTER "\00" \
+		"incorrect checksum"
+'
+
+test_expect_success 'git fsck (checks commit-graph)' '
+	cd "$TRASH_DIRECTORY/full" &&
+	git fsck &&
+	corrupt_graph_and_verify $GRAPH_BYTE_FOOTER "\00" \
+		"incorrect checksum" &&
+	test_must_fail git fsck
+'
+
 test_done