[thirdparty/git.git] / t / t5616-partial-clone.sh

#!/bin/sh

test_description='git partial clone'

. ./test-lib.sh

# create a normal "src" repo where we can later create new commits.
# expect_1.oids will contain a list of the OIDs of all blobs.
test_expect_success 'setup normal src repo' '
	echo "{print \$1}" >print_1.awk &&
	echo "{print \$2}" >print_2.awk &&

	git init src &&
	for n in 1 2 3 4
	do
		echo "This is file: $n" > src/file.$n.txt
		git -C src add file.$n.txt
		git -C src commit -m "file $n"
		git -C src ls-files -s file.$n.txt >>temp
	done &&
	awk -f print_2.awk <temp | sort >expect_1.oids &&
	test_line_count = 4 expect_1.oids
'

# bare clone "src" giving "srv.bare" for use as our server.
test_expect_success 'setup bare clone for server' '
	git clone --bare "file://$(pwd)/src" srv.bare &&
	git -C srv.bare config --local uploadpack.allowfilter 1 &&
	git -C srv.bare config --local uploadpack.allowanysha1inwant 1
'

# do basic partial clone from "srv.bare"
# confirm we are missing all of the known blobs.
# confirm partial clone was registered in the local config.
test_expect_success 'do partial clone 1' '
	git clone --no-checkout --filter=blob:none "file://$(pwd)/srv.bare" pc1 &&

	git -C pc1 rev-list HEAD --quiet --objects --missing=print |
	awk -f print_1.awk |
	sed "s/?//" |
	sort >observed.oids &&

	test_cmp expect_1.oids observed.oids &&
	test "$(git -C pc1 config --local core.repositoryformatversion)" = "1" &&
	test "$(git -C pc1 config --local extensions.partialclone)" = "origin" &&
	test "$(git -C pc1 config --local core.partialclonefilter)" = "blob:none"
'

# checkout master to force dynamic object fetch of blobs at HEAD.
test_expect_success 'verify checkout with dynamic object fetch' '
	git -C pc1 rev-list HEAD --quiet --objects --missing=print >observed &&
	test_line_count = 4 observed &&
	git -C pc1 checkout master &&
	git -C pc1 rev-list HEAD --quiet --objects --missing=print >observed &&
	test_line_count = 0 observed
'

# create new commits in "src" repo to establish a blame history on file.1.txt
# and push to "srv.bare".
test_expect_success 'push new commits to server' '
	git -C src remote add srv "file://$(pwd)/srv.bare" &&
	for x in a b c d e
	do
		echo "Mod file.1.txt $x" >>src/file.1.txt
		git -C src add file.1.txt
		git -C src commit -m "mod $x"
	done &&
	git -C src blame master -- file.1.txt >expect.blame &&
	git -C src push -u srv master
'

# (partial) fetch in the partial clone repo from the promisor remote.
# verify that fetch inherited the filter-spec from the config and DOES NOT
# have the new blobs.
test_expect_success 'partial fetch inherits filter settings' '
	git -C pc1 fetch origin &&
	git -C pc1 rev-list master..origin/master --quiet --objects --missing=print >observed &&
	test_line_count = 5 observed
'

# force dynamic object fetch using diff.
# we should only get 1 new blob (for the file in origin/master).
test_expect_success 'verify diff causes dynamic object fetch' '
	git -C pc1 diff master..origin/master -- file.1.txt &&
	git -C pc1 rev-list master..origin/master --quiet --objects --missing=print >observed &&
	test_line_count = 4 observed
'

# force full dynamic object fetch of the file's history using blame.
# we should get the intermediate blobs for the file.
test_expect_success 'verify blame causes dynamic object fetch' '
	git -C pc1 blame origin/master -- file.1.txt >observed.blame &&
	test_cmp expect.blame observed.blame &&
	git -C pc1 rev-list master..origin/master --quiet --objects --missing=print >observed &&
	test_line_count = 0 observed
'

# create new commits in "src" repo to establish a history on file.2.txt
# and push to "srv.bare".
test_expect_success 'push new commits to server for file.2.txt' '
	for x in a b c d e f
	do
		echo "Mod file.2.txt $x" >>src/file.2.txt
		git -C src add file.2.txt
		git -C src commit -m "mod $x"
	done &&
	git -C src push -u srv master
'

# Do FULL fetch by disabling inherited filter-spec using --no-filter.
# Verify we have all the new blobs.
test_expect_success 'override inherited filter-spec using --no-filter' '
	git -C pc1 fetch --no-filter origin &&
	git -C pc1 rev-list master..origin/master --quiet --objects --missing=print >observed &&
	test_line_count = 0 observed
'

# create new commits in "src" repo to establish a history on file.3.txt
# and push to "srv.bare".
test_expect_success 'push new commits to server for file.3.txt' '
	for x in a b c d e f
	do
		echo "Mod file.3.txt $x" >>src/file.3.txt
		git -C src add file.3.txt
		git -C src commit -m "mod $x"
	done &&
	git -C src push -u srv master
'

# Do a partial fetch and then try to manually fetch the missing objects.
# This can be used as the basis of a pre-command hook to bulk fetch objects
# perhaps combined with a command in dry-run mode.
test_expect_success 'manual prefetch of missing objects' '
	git -C pc1 fetch --filter=blob:none origin &&

	git -C pc1 rev-list master..origin/master --quiet --objects --missing=print |
	awk -f print_1.awk |
	sed "s/?//" |
	sort >observed.oids &&

	test_line_count = 6 observed.oids &&
	git -C pc1 fetch-pack --stdin "file://$(pwd)/srv.bare" <observed.oids &&

	git -C pc1 rev-list master..origin/master --quiet --objects --missing=print |
	awk -f print_1.awk |
	sed "s/?//" |
	sort >observed.oids &&

	test_line_count = 0 observed.oids
'

test_expect_success 'partial clone with transfer.fsckobjects=1 uses index-pack --fsck-objects' '
	git init src &&
	test_commit -C src x &&
	test_config -C src uploadpack.allowfilter 1 &&
	test_config -C src uploadpack.allowanysha1inwant 1 &&

	GIT_TRACE="$(pwd)/trace" git -c transfer.fsckobjects=1 \
		clone --filter="blob:none" "file://$(pwd)/src" dst &&
	grep "git index-pack.*--fsck-objects" trace
'

test_expect_success 'partial clone fetches blobs pointed to by refs even if normally filtered out' '
	rm -rf src dst &&
	git init src &&
	test_commit -C src x &&
	test_config -C src uploadpack.allowfilter 1 &&
	test_config -C src uploadpack.allowanysha1inwant 1 &&

	# Create a tag pointing to a blob.
	BLOB=$(echo blob-contents | git -C src hash-object --stdin -w) &&
	git -C src tag myblob "$BLOB" &&

	git clone --filter="blob:none" "file://$(pwd)/src" dst 2>err &&
	! grep "does not point to a valid object" err &&
	git -C dst fsck
'

. "$TEST_DIRECTORY"/lib-httpd.sh
start_httpd

# Converts bytes into a form suitable for inclusion in a sed command. For
# example, "printf 'ab\r\n' | hex_unpack" results in '\x61\x62\x0d\x0a'.
sed_escape () {
	perl -e '$/ = undef; $input = <>; print unpack("H2" x length($input), $input)' |
		sed 's/\(..\)/\\x\1/g'
}

test_expect_success 'upon cloning, check that all refs point to objects' '
	SERVER="$HTTPD_DOCUMENT_ROOT_PATH/server" &&
	rm -rf "$SERVER" repo &&
	test_create_repo "$SERVER" &&
	test_commit -C "$SERVER" foo &&
	test_config -C "$SERVER" uploadpack.allowfilter 1 &&
	test_config -C "$SERVER" uploadpack.allowanysha1inwant 1 &&

	# Create a tag pointing to a blob.
	BLOB=$(echo blob-contents | git -C "$SERVER" hash-object --stdin -w) &&
	git -C "$SERVER" tag myblob "$BLOB" &&

	# Craft a packfile not including that blob.
	git -C "$SERVER" rev-parse HEAD |
	git -C "$SERVER" pack-objects --stdout >incomplete.pack &&

	# Replace the existing packfile with the crafted one. The protocol
	# requires that the packfile be sent in sideband 1, hence the extra
	# \x01 byte at the beginning.
	printf "1,/packfile/!c %04x\\\\x01%s0000" \
		"$(($(wc -c <incomplete.pack) + 5))" \
		"$(sed_escape <incomplete.pack)" \
		>"$HTTPD_ROOT_PATH/one-time-sed" &&

	# Use protocol v2 because the sed command looks for the "packfile"
	# section header.
	test_config -C "$SERVER" protocol.version 2 &&
	test_must_fail git -c protocol.version=2 clone \
		--filter=blob:none $HTTPD_URL/one_time_sed/server repo 2>err &&

	grep "did not send all necessary objects" err &&

	# Ensure that the one-time-sed script was used.
	! test -e "$HTTPD_ROOT_PATH/one-time-sed"
'

test_expect_success 'when partial cloning, tolerate server not sending target of tag' '
	SERVER="$HTTPD_DOCUMENT_ROOT_PATH/server" &&
	rm -rf "$SERVER" repo &&
	test_create_repo "$SERVER" &&
	test_commit -C "$SERVER" foo &&
	test_config -C "$SERVER" uploadpack.allowfilter 1 &&
	test_config -C "$SERVER" uploadpack.allowanysha1inwant 1 &&

	# Create an annotated tag pointing to a blob.
	BLOB=$(echo blob-contents | git -C "$SERVER" hash-object --stdin -w) &&
	git -C "$SERVER" tag -m message -a myblob "$BLOB" &&

	# Craft a packfile including the tag, but not the blob it points to.
	# Also, omit objects referenced from HEAD in order to force a second
	# fetch (to fetch missing objects) upon the automatic checkout that
	# happens after a clone.
	printf "%s\n%s\n--not\n%s\n%s\n" \
		$(git -C "$SERVER" rev-parse HEAD) \
		$(git -C "$SERVER" rev-parse myblob) \
		$(git -C "$SERVER" rev-parse HEAD^{tree}) \
		$(git -C "$SERVER" rev-parse myblob^{blob}) |
		git -C "$SERVER" pack-objects --thin --stdout >incomplete.pack &&

	# Replace the existing packfile with the crafted one. The protocol
	# requires that the packfile be sent in sideband 1, hence the extra
	# \x01 byte at the beginning.
	printf "1,/packfile/!c %04x\\\\x01%s0000" \
		"$(($(wc -c <incomplete.pack) + 5))" \
		"$(sed_escape <incomplete.pack)" \
		>"$HTTPD_ROOT_PATH/one-time-sed" &&

	# Use protocol v2 because the sed command looks for the "packfile"
	# section header.
	test_config -C "$SERVER" protocol.version 2 &&

	# Exercise to make sure it works.
	git -c protocol.version=2 clone \
		--filter=blob:none $HTTPD_URL/one_time_sed/server repo 2> err &&
	! grep "missing object referenced by" err &&

	# Ensure that the one-time-sed script was used.
	! test -e "$HTTPD_ROOT_PATH/one-time-sed"
'

stop_httpd

test_done
Commit	Line	Data
35a7ae95 JH	1	#!/bin/sh
	2
	3	test_description='git partial clone'
	4
	5	. ./test-lib.sh
	6
	7	# create a normal "src" repo where we can later create new commits.
	8	# expect_1.oids will contain a list of the OIDs of all blobs.
	9	test_expect_success 'setup normal src repo' '
	10	echo "{print \$1}" >print_1.awk &&
	11	echo "{print \$2}" >print_2.awk &&
	12
	13	git init src &&
	14	for n in 1 2 3 4
	15	do
	16	echo "This is file: $n" > src/file.$n.txt
	17	git -C src add file.$n.txt
	18	git -C src commit -m "file $n"
	19	git -C src ls-files -s file.$n.txt >>temp
	20	done &&
	21	awk -f print_2.awk <temp \| sort >expect_1.oids &&
	22	test_line_count = 4 expect_1.oids
	23	'
	24
	25	# bare clone "src" giving "srv.bare" for use as our server.
	26	test_expect_success 'setup bare clone for server' '
	27	git clone --bare "file://$(pwd)/src" srv.bare &&
	28	git -C srv.bare config --local uploadpack.allowfilter 1 &&
	29	git -C srv.bare config --local uploadpack.allowanysha1inwant 1
	30	'
	31
	32	# do basic partial clone from "srv.bare"
	33	# confirm we are missing all of the known blobs.
	34	# confirm partial clone was registered in the local config.
	35	test_expect_success 'do partial clone 1' '
	36	git clone --no-checkout --filter=blob:none "file://$(pwd)/srv.bare" pc1 &&
bdbc17e8 MD	37
	38	git -C pc1 rev-list HEAD --quiet --objects --missing=print \|
	39	awk -f print_1.awk \|
	40	sed "s/?//" \|
	41	sort >observed.oids &&
	42
35a7ae95 JH	43	test_cmp expect_1.oids observed.oids &&
	44	test "$(git -C pc1 config --local core.repositoryformatversion)" = "1" &&
	45	test "$(git -C pc1 config --local extensions.partialclone)" = "origin" &&
	46	test "$(git -C pc1 config --local core.partialclonefilter)" = "blob:none"
	47	'
	48
	49	# checkout master to force dynamic object fetch of blobs at HEAD.
	50	test_expect_success 'verify checkout with dynamic object fetch' '
	51	git -C pc1 rev-list HEAD --quiet --objects --missing=print >observed &&
	52	test_line_count = 4 observed &&
	53	git -C pc1 checkout master &&
	54	git -C pc1 rev-list HEAD --quiet --objects --missing=print >observed &&
	55	test_line_count = 0 observed
	56	'
	57
	58	# create new commits in "src" repo to establish a blame history on file.1.txt
	59	# and push to "srv.bare".
	60	test_expect_success 'push new commits to server' '
	61	git -C src remote add srv "file://$(pwd)/srv.bare" &&
	62	for x in a b c d e
	63	do
aa57b871	64	echo "Mod file.1.txt $x" >>src/file.1.txt
35a7ae95 JH	65	git -C src add file.1.txt
	66	git -C src commit -m "mod $x"
	67	done &&
	68	git -C src blame master -- file.1.txt >expect.blame &&
	69	git -C src push -u srv master
	70	'
	71
	72	# (partial) fetch in the partial clone repo from the promisor remote.
	73	# verify that fetch inherited the filter-spec from the config and DOES NOT
	74	# have the new blobs.
	75	test_expect_success 'partial fetch inherits filter settings' '
	76	git -C pc1 fetch origin &&
	77	git -C pc1 rev-list master..origin/master --quiet --objects --missing=print >observed &&
	78	test_line_count = 5 observed
	79	'
	80
	81	# force dynamic object fetch using diff.
	82	# we should only get 1 new blob (for the file in origin/master).
	83	test_expect_success 'verify diff causes dynamic object fetch' '
	84	git -C pc1 diff master..origin/master -- file.1.txt &&
	85	git -C pc1 rev-list master..origin/master --quiet --objects --missing=print >observed &&
	86	test_line_count = 4 observed
	87	'
	88
	89	# force full dynamic object fetch of the file's history using blame.
	90	# we should get the intermediate blobs for the file.
	91	test_expect_success 'verify blame causes dynamic object fetch' '
	92	git -C pc1 blame origin/master -- file.1.txt >observed.blame &&
	93	test_cmp expect.blame observed.blame &&
	94	git -C pc1 rev-list master..origin/master --quiet --objects --missing=print >observed &&
	95	test_line_count = 0 observed
	96	'
	97
aa57b871 JH	98	# create new commits in "src" repo to establish a history on file.2.txt
	99	# and push to "srv.bare".
	100	test_expect_success 'push new commits to server for file.2.txt' '
	101	for x in a b c d e f
	102	do
	103	echo "Mod file.2.txt $x" >>src/file.2.txt
	104	git -C src add file.2.txt
	105	git -C src commit -m "mod $x"
	106	done &&
	107	git -C src push -u srv master
	108	'
	109
3aa6694f	110	# Do FULL fetch by disabling inherited filter-spec using --no-filter.
aa57b871 JH	111	# Verify we have all the new blobs.
	112	test_expect_success 'override inherited filter-spec using --no-filter' '
	113	git -C pc1 fetch --no-filter origin &&
	114	git -C pc1 rev-list master..origin/master --quiet --objects --missing=print >observed &&
	115	test_line_count = 0 observed
	116	'
	117
3aa6694f JH	118	# create new commits in "src" repo to establish a history on file.3.txt
	119	# and push to "srv.bare".
	120	test_expect_success 'push new commits to server for file.3.txt' '
	121	for x in a b c d e f
	122	do
	123	echo "Mod file.3.txt $x" >>src/file.3.txt
	124	git -C src add file.3.txt
	125	git -C src commit -m "mod $x"
	126	done &&
	127	git -C src push -u srv master
	128	'
	129
	130	# Do a partial fetch and then try to manually fetch the missing objects.
	131	# This can be used as the basis of a pre-command hook to bulk fetch objects
	132	# perhaps combined with a command in dry-run mode.
	133	test_expect_success 'manual prefetch of missing objects' '
	134	git -C pc1 fetch --filter=blob:none origin &&
bdbc17e8 MD	135
	136	git -C pc1 rev-list master..origin/master --quiet --objects --missing=print \|
	137	awk -f print_1.awk \|
	138	sed "s/?//" \|
	139	sort >observed.oids &&
	140
3aa6694f JH	141	test_line_count = 6 observed.oids &&
3aa6694f JH	142	git -C pc1 fetch-pack --stdin "file://$(pwd)/srv.bare" <observed.oids &&
bdbc17e8 MD	143
	144	git -C pc1 rev-list master..origin/master --quiet --objects --missing=print \|
	145	awk -f print_1.awk \|
	146	sed "s/?//" \|
	147	sort >observed.oids &&
	148
3aa6694f JH	149	test_line_count = 0 observed.oids
	150	'
	151
98a2ea46 JT	152	test_expect_success 'partial clone with transfer.fsckobjects=1 uses index-pack --fsck-objects' '
	153	git init src &&
	154	test_commit -C src x &&
	155	test_config -C src uploadpack.allowfilter 1 &&
	156	test_config -C src uploadpack.allowanysha1inwant 1 &&
	157
	158	GIT_TRACE="$(pwd)/trace" git -c transfer.fsckobjects=1 \
	159	clone --filter="blob:none" "file://$(pwd)/src" dst &&
	160	grep "git index-pack.*--fsck-objects" trace
	161	'
	162
a0c9016a JT	163	test_expect_success 'partial clone fetches blobs pointed to by refs even if normally filtered out' '
	164	rm -rf src dst &&
	165	git init src &&
	166	test_commit -C src x &&
	167	test_config -C src uploadpack.allowfilter 1 &&
	168	test_config -C src uploadpack.allowanysha1inwant 1 &&
	169
	170	# Create a tag pointing to a blob.
	171	BLOB=$(echo blob-contents \| git -C src hash-object --stdin -w) &&
	172	git -C src tag myblob "$BLOB" &&
	173
	174	git clone --filter="blob:none" "file://$(pwd)/src" dst 2>err &&
	175	! grep "does not point to a valid object" err &&
	176	git -C dst fsck
	177	'
	178
a7e67c11 JT	179	. "$TEST_DIRECTORY"/lib-httpd.sh
	180	start_httpd
	181
	182	# Converts bytes into a form suitable for inclusion in a sed command. For
	183	# example, "printf 'ab\r\n' \| hex_unpack" results in '\x61\x62\x0d\x0a'.
	184	sed_escape () {
	185	perl -e '$/ = undef; $input = <>; print unpack("H2" x length($input), $input)' \|
	186	sed 's/\(..\)/\\x\1/g'
	187	}
	188
	189	test_expect_success 'upon cloning, check that all refs point to objects' '
	190	SERVER="$HTTPD_DOCUMENT_ROOT_PATH/server" &&
	191	rm -rf "$SERVER" repo &&
	192	test_create_repo "$SERVER" &&
	193	test_commit -C "$SERVER" foo &&
	194	test_config -C "$SERVER" uploadpack.allowfilter 1 &&
	195	test_config -C "$SERVER" uploadpack.allowanysha1inwant 1 &&
	196
	197	# Create a tag pointing to a blob.
	198	BLOB=$(echo blob-contents \| git -C "$SERVER" hash-object --stdin -w) &&
	199	git -C "$SERVER" tag myblob "$BLOB" &&
	200
	201	# Craft a packfile not including that blob.
	202	git -C "$SERVER" rev-parse HEAD \|
bdbc17e8	203	git -C "$SERVER" pack-objects --stdout >incomplete.pack &&
a7e67c11 JT	204
	205	# Replace the existing packfile with the crafted one. The protocol
	206	# requires that the packfile be sent in sideband 1, hence the extra
	207	# \x01 byte at the beginning.
	208	printf "1,/packfile/!c %04x\\\\x01%s0000" \
	209	"$(($(wc -c <incomplete.pack) + 5))" \
	210	"$(sed_escape <incomplete.pack)" \
	211	>"$HTTPD_ROOT_PATH/one-time-sed" &&
	212
	213	# Use protocol v2 because the sed command looks for the "packfile"
	214	# section header.
	215	test_config -C "$SERVER" protocol.version 2 &&
	216	test_must_fail git -c protocol.version=2 clone \
	217	--filter=blob:none $HTTPD_URL/one_time_sed/server repo 2>err &&
	218
	219	grep "did not send all necessary objects" err &&
	220
	221	# Ensure that the one-time-sed script was used.
	222	! test -e "$HTTPD_ROOT_PATH/one-time-sed"
	223	'
	224
dc0a13f6 JT	225	test_expect_success 'when partial cloning, tolerate server not sending target of tag' '
	226	SERVER="$HTTPD_DOCUMENT_ROOT_PATH/server" &&
	227	rm -rf "$SERVER" repo &&
	228	test_create_repo "$SERVER" &&
	229	test_commit -C "$SERVER" foo &&
	230	test_config -C "$SERVER" uploadpack.allowfilter 1 &&
	231	test_config -C "$SERVER" uploadpack.allowanysha1inwant 1 &&
	232
	233	# Create an annotated tag pointing to a blob.
	234	BLOB=$(echo blob-contents \| git -C "$SERVER" hash-object --stdin -w) &&
	235	git -C "$SERVER" tag -m message -a myblob "$BLOB" &&
	236
	237	# Craft a packfile including the tag, but not the blob it points to.
8c4cc326 JT	238	# Also, omit objects referenced from HEAD in order to force a second
	239	# fetch (to fetch missing objects) upon the automatic checkout that
	240	# happens after a clone.
	241	printf "%s\n%s\n--not\n%s\n%s\n" \
dc0a13f6 JT	242	$(git -C "$SERVER" rev-parse HEAD) \
dc0a13f6 JT	243	$(git -C "$SERVER" rev-parse myblob) \
8c4cc326	244	$(git -C "$SERVER" rev-parse HEAD^{tree}) \
dc0a13f6 JT	245	$(git -C "$SERVER" rev-parse myblob^{blob}) \|
	246	git -C "$SERVER" pack-objects --thin --stdout >incomplete.pack &&
	247
	248	# Replace the existing packfile with the crafted one. The protocol
	249	# requires that the packfile be sent in sideband 1, hence the extra
	250	# \x01 byte at the beginning.
	251	printf "1,/packfile/!c %04x\\\\x01%s0000" \
	252	"$(($(wc -c <incomplete.pack) + 5))" \
	253	"$(sed_escape <incomplete.pack)" \
	254	>"$HTTPD_ROOT_PATH/one-time-sed" &&
	255
	256	# Use protocol v2 because the sed command looks for the "packfile"
	257	# section header.
	258	test_config -C "$SERVER" protocol.version 2 &&
	259
	260	# Exercise to make sure it works.
	261	git -c protocol.version=2 clone \
8c4cc326 JT	262	--filter=blob:none $HTTPD_URL/one_time_sed/server repo 2> err &&
8c4cc326 JT	263	! grep "missing object referenced by" err &&
dc0a13f6 JT	264
	265	# Ensure that the one-time-sed script was used.
	266	! test -e "$HTTPD_ROOT_PATH/one-time-sed"
	267	'
	268
a7e67c11 JT	269	stop_httpd
a7e67c11 JT	270
35a7ae95	271	test_done