[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 --quiet --objects --missing=print HEAD >revs &&
	awk -f print_1.awk revs |
	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 remote.origin.promisor)" = "true" &&
	test "$(git -C pc1 config --local remote.origin.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 --quiet --objects --missing=print HEAD >observed &&
	test_line_count = 4 observed &&
	git -C pc1 checkout master &&
	git -C pc1 rev-list --quiet --objects --missing=print HEAD >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 --quiet --objects --missing=print \
		master..origin/master >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 --quiet --objects --missing=print \
		 master..origin/master >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 --quiet --objects --missing=print \
		master..origin/master >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 --quiet --objects --missing=print \
		master..origin/master >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 --quiet --objects --missing=print \
		 master..origin/master >revs &&
	awk -f print_1.awk revs |
	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 --quiet --objects --missing=print \
		master..origin/master >revs &&
	awk -f print_1.awk revs |
	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 'use fsck before and after manually fetching a missing subtree' '
	# push new commit so server has a subtree
	mkdir src/dir &&
	echo "in dir" >src/dir/file.txt &&
	git -C src add dir/file.txt &&
	git -C src commit -m "file in dir" &&
	git -C src push -u srv master &&
	SUBTREE=$(git -C src rev-parse HEAD:dir) &&

	rm -rf dst &&
	git clone --no-checkout --filter=tree:0 "file://$(pwd)/srv.bare" dst &&
	git -C dst fsck &&

	# Make sure we only have commits, and all trees and blobs are missing.
	git -C dst rev-list --missing=allow-any --objects master \
		>fetched_objects &&
	awk -f print_1.awk fetched_objects |
	xargs -n1 git -C dst cat-file -t >fetched_types &&

	sort -u fetched_types >unique_types.observed &&
	echo commit >unique_types.expected &&
	test_cmp unique_types.expected unique_types.observed &&

	# Auto-fetch a tree with cat-file.
	git -C dst cat-file -p $SUBTREE >tree_contents &&
	grep file.txt tree_contents &&

	# fsck still works after an auto-fetch of a tree.
	git -C dst fsck &&

	# Auto-fetch all remaining trees and blobs with --missing=error
	git -C dst rev-list --missing=error --objects master >fetched_objects &&
	test_line_count = 70 fetched_objects &&

	awk -f print_1.awk fetched_objects |
	xargs -n1 git -C dst cat-file -t >fetched_types &&

	sort -u fetched_types >unique_types.observed &&
	test_write_lines blob commit tree >unique_types.expected &&
	test_cmp unique_types.expected unique_types.observed
'

test_expect_success 'implicitly construct combine: filter with repeated flags' '
	GIT_TRACE=$(pwd)/trace git clone --bare \
		--filter=blob:none --filter=tree:1 \
		"file://$(pwd)/srv.bare" pc2 &&
	grep "trace:.* git pack-objects .*--filter=combine:blob:none+tree:1" \
		trace &&
	git -C pc2 rev-list --objects --missing=allow-any HEAD >objects &&

	# We should have gotten some root trees.
	grep " $" objects &&
	# Should not have gotten any non-root trees or blobs.
	! grep " ." objects &&

	xargs -n 1 git -C pc2 cat-file -t <objects >types &&
	sort -u types >unique_types.actual &&
	test_write_lines commit tree >unique_types.expected &&
	test_cmp unique_types.expected unique_types.actual
'

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_expect_success 'fetch what is specified on CLI even if already promised' '
	rm -rf src dst.git &&
	git init src &&
	test_commit -C src foo &&
	test_config -C src uploadpack.allowfilter 1 &&
	test_config -C src uploadpack.allowanysha1inwant 1 &&

	git hash-object --stdin <src/foo.t >blob &&

	git clone --bare --filter=blob:none "file://$(pwd)/src" dst.git &&
	git -C dst.git rev-list --objects --quiet --missing=print HEAD >missing_before &&
	grep "?$(cat blob)" missing_before &&
	git -C dst.git fetch origin $(cat blob) &&
	git -C dst.git rev-list --objects --quiet --missing=print HEAD >missing_after &&
	! grep "?$(cat blob)" missing_after
'

test_expect_success 'setup src repo for sparse filter' '
	git init sparse-src &&
	git -C sparse-src config --local uploadpack.allowfilter 1 &&
	git -C sparse-src config --local uploadpack.allowanysha1inwant 1 &&
	test_commit -C sparse-src one &&
	test_commit -C sparse-src two &&
	echo /one.t >sparse-src/only-one &&
	git -C sparse-src add . &&
	git -C sparse-src commit -m "add sparse checkout files"
'

test_expect_success 'partial clone with sparse filter succeeds' '
	rm -rf dst.git &&
	git clone --no-local --bare \
		  --filter=sparse:oid=master:only-one \
		  sparse-src dst.git &&
	(
		cd dst.git &&
		git rev-list --objects --missing=print HEAD >out &&
		grep "^$(git rev-parse HEAD:one.t)" out &&
		grep "^?$(git rev-parse HEAD:two.t)" out
	)
'

test_expect_success 'partial clone with unresolvable sparse filter fails cleanly' '
	rm -rf dst.git &&
	test_must_fail git clone --no-local --bare \
				 --filter=sparse:oid=master:no-such-name \
				 sparse-src dst.git 2>err &&
	test_i18ngrep "unable to access sparse blob in .master:no-such-name" err &&
	test_must_fail git clone --no-local --bare \
				 --filter=sparse:oid=master \
				 sparse-src dst.git 2>err &&
	test_i18ngrep "unable to parse sparse filter data in" err
'

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

# Converts bytes into their hexadecimal representation. For example,
# "printf 'ab\r\n' | hex_unpack" results in '61620d0a'.
hex_unpack () {
	perl -e '$/ = undef; $input = <>; print unpack("H2" x length($input), $input)'
}

# Inserts $1 at the start of the string and every 2 characters thereafter.
intersperse () {
	sed 's/\(..\)/'$1'\1/g'
}

# Create a one-time-sed command to replace the existing packfile with $1.
replace_packfile () {
	# The protocol requires that the packfile be sent in sideband 1, hence
	# the extra \x01 byte at the beginning.
	printf "1,/packfile/!c %04x\\\\x01%s0000" \
		"$(($(wc -c <$1) + 5))" \
		"$(hex_unpack <$1 | intersperse '\\x')" \
		>"$HTTPD_ROOT_PATH/one-time-sed"
}

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.
	replace_packfile incomplete.pack &&

	# 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 &&

	test_i18ngrep "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.
	replace_packfile incomplete.pack &&

	# 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"
'

test_expect_success 'tolerate server sending REF_DELTA against missing promisor objects' '
	SERVER="$HTTPD_DOCUMENT_ROOT_PATH/server" &&
	rm -rf "$SERVER" repo &&
	test_create_repo "$SERVER" &&
	test_config -C "$SERVER" uploadpack.allowfilter 1 &&
	test_config -C "$SERVER" uploadpack.allowanysha1inwant 1 &&

	# Create a commit with 2 blobs to be used as delta bases.
	for i in $(test_seq 10)
	do
		echo "this is a line" >>"$SERVER/foo.txt" &&
		echo "this is another line" >>"$SERVER/have.txt"
	done &&
	git -C "$SERVER" add foo.txt have.txt &&
	git -C "$SERVER" commit -m bar &&
	git -C "$SERVER" rev-parse HEAD:foo.txt >deltabase_missing &&
	git -C "$SERVER" rev-parse HEAD:have.txt >deltabase_have &&

	# Clone. The client has deltabase_have but not deltabase_missing.
	git -c protocol.version=2 clone --no-checkout \
		--filter=blob:none $HTTPD_URL/one_time_sed/server repo &&
	git -C repo hash-object -w -- "$SERVER/have.txt" &&

	# Sanity check to ensure that the client does not have
	# deltabase_missing.
	git -C repo rev-list --objects --ignore-missing \
		-- $(cat deltabase_missing) >objlist &&
	test_line_count = 0 objlist &&

	# Another commit. This commit will be fetched by the client.
	echo "abcdefghijklmnopqrstuvwxyz" >>"$SERVER/foo.txt" &&
	echo "abcdefghijklmnopqrstuvwxyz" >>"$SERVER/have.txt" &&
	git -C "$SERVER" add foo.txt have.txt &&
	git -C "$SERVER" commit -m baz &&

	# Pack a thin pack containing, among other things, HEAD:foo.txt
	# delta-ed against HEAD^:foo.txt and HEAD:have.txt delta-ed against
	# HEAD^:have.txt.
	printf "%s\n--not\n%s\n" \
		$(git -C "$SERVER" rev-parse HEAD) \
		$(git -C "$SERVER" rev-parse HEAD^) |
		git -C "$SERVER" pack-objects --thin --stdout >thin.pack &&

	# Ensure that the pack contains one delta against HEAD^:foo.txt. Since
	# the delta contains at least 26 novel characters, the size cannot be
	# contained in 4 bits, so the object header will take up 2 bytes. The
	# most significant nybble of the first byte is 0b1111 (0b1 to indicate
	# that the header continues, and 0b111 to indicate REF_DELTA), followed
	# by any 3 nybbles, then the OID of the delta base.
	printf "f.,..%s" $(intersperse "," <deltabase_missing) >want &&
	hex_unpack <thin.pack | intersperse "," >have &&
	grep $(cat want) have &&

	# Ensure that the pack contains one delta against HEAD^:have.txt,
	# similar to the above.
	printf "f.,..%s" $(intersperse "," <deltabase_have) >want &&
	hex_unpack <thin.pack | intersperse "," >have &&
	grep $(cat want) have &&

	replace_packfile thin.pack &&

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

	# Fetch the thin pack and ensure that index-pack is able to handle the
	# REF_DELTA object with a missing promisor delta base.
	GIT_TRACE_PACKET="$(pwd)/trace" git -C repo -c protocol.version=2 fetch &&

	# Ensure that the missing delta base was directly fetched, but not the
	# one that the client has.
	grep "want $(cat deltabase_missing)" trace &&
	! grep "want $(cat deltabase_have)" trace &&

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

# DO NOT add non-httpd-specific tests here, because the last part of this
# test script is only executed when httpd is available and enabled.

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	37
8d6ba495	38	git -C pc1 rev-list --quiet --objects --missing=print HEAD >revs &&
61de0ff6	39	awk -f print_1.awk revs \|
bdbc17e8 MD	40	sed "s/?//" \|
	41	sort >observed.oids &&
	42
35a7ae95 JH	43	test_cmp expect_1.oids observed.oids &&
35a7ae95 JH	44	test "$(git -C pc1 config --local core.repositoryformatversion)" = "1" &&
b14ed5ad	45	test "$(git -C pc1 config --local remote.origin.promisor)" = "true" &&
fa3d1b63	46	test "$(git -C pc1 config --local remote.origin.partialclonefilter)" = "blob:none"
35a7ae95 JH	47	'
	48
	49	# checkout master to force dynamic object fetch of blobs at HEAD.
	50	test_expect_success 'verify checkout with dynamic object fetch' '
8d6ba495	51	git -C pc1 rev-list --quiet --objects --missing=print HEAD >observed &&
35a7ae95 JH	52	test_line_count = 4 observed &&
35a7ae95 JH	53	git -C pc1 checkout master &&
8d6ba495	54	git -C pc1 rev-list --quiet --objects --missing=print HEAD >observed &&
35a7ae95 JH	55	test_line_count = 0 observed
	56	'
	57
	58	# create new commits in "src" repo to establish a blame history on file.1.txt
	59	# and push to "srv.bare".
	60	test_expect_success 'push new commits to server' '
	61	git -C src remote add srv "file://$(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 &&
8d6ba495 MD	77	git -C pc1 rev-list --quiet --objects --missing=print \
8d6ba495 MD	78	master..origin/master >observed &&
35a7ae95 JH	79	test_line_count = 5 observed
	80	'
	81
	82	# force dynamic object fetch using diff.
	83	# we should only get 1 new blob (for the file in origin/master).
	84	test_expect_success 'verify diff causes dynamic object fetch' '
	85	git -C pc1 diff master..origin/master -- file.1.txt &&
8d6ba495 MD	86	git -C pc1 rev-list --quiet --objects --missing=print \
8d6ba495 MD	87	master..origin/master >observed &&
35a7ae95 JH	88	test_line_count = 4 observed
	89	'
	90
	91	# force full dynamic object fetch of the file's history using blame.
	92	# we should get the intermediate blobs for the file.
	93	test_expect_success 'verify blame causes dynamic object fetch' '
	94	git -C pc1 blame origin/master -- file.1.txt >observed.blame &&
	95	test_cmp expect.blame observed.blame &&
8d6ba495 MD	96	git -C pc1 rev-list --quiet --objects --missing=print \
8d6ba495 MD	97	master..origin/master >observed &&
35a7ae95 JH	98	test_line_count = 0 observed
	99	'
	100
aa57b871 JH	101	# create new commits in "src" repo to establish a history on file.2.txt
	102	# and push to "srv.bare".
	103	test_expect_success 'push new commits to server for file.2.txt' '
	104	for x in a b c d e f
	105	do
	106	echo "Mod file.2.txt $x" >>src/file.2.txt
	107	git -C src add file.2.txt
	108	git -C src commit -m "mod $x"
	109	done &&
	110	git -C src push -u srv master
	111	'
	112
3aa6694f	113	# Do FULL fetch by disabling inherited filter-spec using --no-filter.
aa57b871 JH	114	# Verify we have all the new blobs.
	115	test_expect_success 'override inherited filter-spec using --no-filter' '
	116	git -C pc1 fetch --no-filter origin &&
8d6ba495 MD	117	git -C pc1 rev-list --quiet --objects --missing=print \
8d6ba495 MD	118	master..origin/master >observed &&
aa57b871 JH	119	test_line_count = 0 observed
	120	'
	121
3aa6694f JH	122	# create new commits in "src" repo to establish a history on file.3.txt
	123	# and push to "srv.bare".
	124	test_expect_success 'push new commits to server for file.3.txt' '
	125	for x in a b c d e f
	126	do
	127	echo "Mod file.3.txt $x" >>src/file.3.txt
	128	git -C src add file.3.txt
	129	git -C src commit -m "mod $x"
	130	done &&
	131	git -C src push -u srv master
	132	'
	133
	134	# Do a partial fetch and then try to manually fetch the missing objects.
	135	# This can be used as the basis of a pre-command hook to bulk fetch objects
	136	# perhaps combined with a command in dry-run mode.
	137	test_expect_success 'manual prefetch of missing objects' '
	138	git -C pc1 fetch --filter=blob:none origin &&
bdbc17e8	139
8d6ba495 MD	140	git -C pc1 rev-list --quiet --objects --missing=print \
8d6ba495 MD	141	master..origin/master >revs &&
61de0ff6	142	awk -f print_1.awk revs \|
bdbc17e8 MD	143	sed "s/?//" \|
	144	sort >observed.oids &&
	145
3aa6694f JH	146	test_line_count = 6 observed.oids &&
3aa6694f JH	147	git -C pc1 fetch-pack --stdin "file://$(pwd)/srv.bare" <observed.oids &&
bdbc17e8	148
8d6ba495 MD	149	git -C pc1 rev-list --quiet --objects --missing=print \
8d6ba495 MD	150	master..origin/master >revs &&
61de0ff6	151	awk -f print_1.awk revs \|
bdbc17e8 MD	152	sed "s/?//" \|
	153	sort >observed.oids &&
	154
3aa6694f JH	155	test_line_count = 0 observed.oids
	156	'
	157
98a2ea46 JT	158	test_expect_success 'partial clone with transfer.fsckobjects=1 uses index-pack --fsck-objects' '
	159	git init src &&
	160	test_commit -C src x &&
	161	test_config -C src uploadpack.allowfilter 1 &&
	162	test_config -C src uploadpack.allowanysha1inwant 1 &&
	163
	164	GIT_TRACE="$(pwd)/trace" git -c transfer.fsckobjects=1 \
	165	clone --filter="blob:none" "file://$(pwd)/src" dst &&
	166	grep "git index-pack.*--fsck-objects" trace
	167	'
	168
bc5975d2 MD	169	test_expect_success 'use fsck before and after manually fetching a missing subtree' '
	170	# push new commit so server has a subtree
	171	mkdir src/dir &&
	172	echo "in dir" >src/dir/file.txt &&
	173	git -C src add dir/file.txt &&
	174	git -C src commit -m "file in dir" &&
	175	git -C src push -u srv master &&
	176	SUBTREE=$(git -C src rev-parse HEAD:dir) &&
	177
	178	rm -rf dst &&
	179	git clone --no-checkout --filter=tree:0 "file://$(pwd)/srv.bare" dst &&
	180	git -C dst fsck &&
	181
	182	# Make sure we only have commits, and all trees and blobs are missing.
	183	git -C dst rev-list --missing=allow-any --objects master \
	184	>fetched_objects &&
	185	awk -f print_1.awk fetched_objects \|
	186	xargs -n1 git -C dst cat-file -t >fetched_types &&
	187
	188	sort -u fetched_types >unique_types.observed &&
	189	echo commit >unique_types.expected &&
	190	test_cmp unique_types.expected unique_types.observed &&
	191
	192	# Auto-fetch a tree with cat-file.
	193	git -C dst cat-file -p $SUBTREE >tree_contents &&
	194	grep file.txt tree_contents &&
	195
	196	# fsck still works after an auto-fetch of a tree.
	197	git -C dst fsck &&
	198
	199	# Auto-fetch all remaining trees and blobs with --missing=error
	200	git -C dst rev-list --missing=error --objects master >fetched_objects &&
	201	test_line_count = 70 fetched_objects &&
	202
	203	awk -f print_1.awk fetched_objects \|
	204	xargs -n1 git -C dst cat-file -t >fetched_types &&
	205
	206	sort -u fetched_types >unique_types.observed &&
d9e6d094	207	test_write_lines blob commit tree >unique_types.expected &&
bc5975d2 MD	208	test_cmp unique_types.expected unique_types.observed
	209	'
	210
489fc9ee MD	211	test_expect_success 'implicitly construct combine: filter with repeated flags' '
	212	GIT_TRACE=$(pwd)/trace git clone --bare \
	213	--filter=blob:none --filter=tree:1 \
	214	"file://$(pwd)/srv.bare" pc2 &&
	215	grep "trace:.* git pack-objects .*--filter=combine:blob:none+tree:1" \
	216	trace &&
	217	git -C pc2 rev-list --objects --missing=allow-any HEAD >objects &&
	218
	219	# We should have gotten some root trees.
	220	grep " $" objects &&
	221	# Should not have gotten any non-root trees or blobs.
	222	! grep " ." objects &&
	223
	224	xargs -n 1 git -C pc2 cat-file -t <objects >types &&
	225	sort -u types >unique_types.actual &&
	226	test_write_lines commit tree >unique_types.expected &&
	227	test_cmp unique_types.expected unique_types.actual
	228	'
	229
a0c9016a JT	230	test_expect_success 'partial clone fetches blobs pointed to by refs even if normally filtered out' '
	231	rm -rf src dst &&
	232	git init src &&
	233	test_commit -C src x &&
	234	test_config -C src uploadpack.allowfilter 1 &&
	235	test_config -C src uploadpack.allowanysha1inwant 1 &&
	236
	237	# Create a tag pointing to a blob.
	238	BLOB=$(echo blob-contents \| git -C src hash-object --stdin -w) &&
	239	git -C src tag myblob "$BLOB" &&
	240
	241	git clone --filter="blob:none" "file://$(pwd)/src" dst 2>err &&
	242	! grep "does not point to a valid object" err &&
	243	git -C dst fsck
	244	'
	245
35f9e3e5 JT	246	test_expect_success 'fetch what is specified on CLI even if already promised' '
	247	rm -rf src dst.git &&
	248	git init src &&
	249	test_commit -C src foo &&
	250	test_config -C src uploadpack.allowfilter 1 &&
	251	test_config -C src uploadpack.allowanysha1inwant 1 &&
	252
	253	git hash-object --stdin <src/foo.t >blob &&
	254
	255	git clone --bare --filter=blob:none "file://$(pwd)/src" dst.git &&
	256	git -C dst.git rev-list --objects --quiet --missing=print HEAD >missing_before &&
	257	grep "?$(cat blob)" missing_before &&
	258	git -C dst.git fetch origin $(cat blob) &&
	259	git -C dst.git rev-list --objects --quiet --missing=print HEAD >missing_after &&
	260	! grep "?$(cat blob)" missing_after
	261	'
	262
72de5895 JS	263	test_expect_success 'setup src repo for sparse filter' '
	264	git init sparse-src &&
	265	git -C sparse-src config --local uploadpack.allowfilter 1 &&
	266	git -C sparse-src config --local uploadpack.allowanysha1inwant 1 &&
	267	test_commit -C sparse-src one &&
	268	test_commit -C sparse-src two &&
	269	echo /one.t >sparse-src/only-one &&
	270	git -C sparse-src add . &&
	271	git -C sparse-src commit -m "add sparse checkout files"
	272	'
	273
4c96a775	274	test_expect_success 'partial clone with sparse filter succeeds' '
72de5895 JS	275	rm -rf dst.git &&
	276	git clone --no-local --bare \
	277	--filter=sparse:oid=master:only-one \
	278	sparse-src dst.git &&
	279	(
	280	cd dst.git &&
	281	git rev-list --objects --missing=print HEAD >out &&
	282	grep "^$(git rev-parse HEAD:one.t)" out &&
	283	grep "^?$(git rev-parse HEAD:two.t)" out
	284	)
	285	'
	286
4c96a775	287	test_expect_success 'partial clone with unresolvable sparse filter fails cleanly' '
72de5895 JS	288	rm -rf dst.git &&
	289	test_must_fail git clone --no-local --bare \
	290	--filter=sparse:oid=master:no-such-name \
	291	sparse-src dst.git 2>err &&
	292	test_i18ngrep "unable to access sparse blob in .master:no-such-name" err &&
	293	test_must_fail git clone --no-local --bare \
	294	--filter=sparse:oid=master \
	295	sparse-src dst.git 2>err &&
cf34337f	296	test_i18ngrep "unable to parse sparse filter data in" err
72de5895 JS	297	'
72de5895 JS	298
a7e67c11 JT	299	. "$TEST_DIRECTORY"/lib-httpd.sh
	300	start_httpd
	301
385d1bfd JT	302	# Converts bytes into their hexadecimal representation. For example,
	303	# "printf 'ab\r\n' \| hex_unpack" results in '61620d0a'.
	304	hex_unpack () {
	305	perl -e '$/ = undef; $input = <>; print unpack("H2" x length($input), $input)'
	306	}
	307
	308	# Inserts $1 at the start of the string and every 2 characters thereafter.
	309	intersperse () {
	310	sed 's/\(..\)/'$1'\1/g'
	311	}
	312
	313	# Create a one-time-sed command to replace the existing packfile with $1.
	314	replace_packfile () {
	315	# The protocol requires that the packfile be sent in sideband 1, hence
	316	# the extra \x01 byte at the beginning.
	317	printf "1,/packfile/!c %04x\\\\x01%s0000" \
	318	"$(($(wc -c <$1) + 5))" \
	319	"$(hex_unpack <$1 \| intersperse '\\x')" \
	320	>"$HTTPD_ROOT_PATH/one-time-sed"
a7e67c11 JT	321	}
	322
	323	test_expect_success 'upon cloning, check that all refs point to objects' '
	324	SERVER="$HTTPD_DOCUMENT_ROOT_PATH/server" &&
	325	rm -rf "$SERVER" repo &&
	326	test_create_repo "$SERVER" &&
	327	test_commit -C "$SERVER" foo &&
	328	test_config -C "$SERVER" uploadpack.allowfilter 1 &&
	329	test_config -C "$SERVER" uploadpack.allowanysha1inwant 1 &&
	330
	331	# Create a tag pointing to a blob.
	332	BLOB=$(echo blob-contents \| git -C "$SERVER" hash-object --stdin -w) &&
	333	git -C "$SERVER" tag myblob "$BLOB" &&
	334
	335	# Craft a packfile not including that blob.
	336	git -C "$SERVER" rev-parse HEAD \|
bdbc17e8	337	git -C "$SERVER" pack-objects --stdout >incomplete.pack &&
a7e67c11 JT	338
	339	# Replace the existing packfile with the crafted one. The protocol
	340	# requires that the packfile be sent in sideband 1, hence the extra
	341	# \x01 byte at the beginning.
385d1bfd	342	replace_packfile incomplete.pack &&
a7e67c11 JT	343
	344	# Use protocol v2 because the sed command looks for the "packfile"
	345	# section header.
	346	test_config -C "$SERVER" protocol.version 2 &&
	347	test_must_fail git -c protocol.version=2 clone \
	348	--filter=blob:none $HTTPD_URL/one_time_sed/server repo 2>err &&
	349
3813a89f	350	test_i18ngrep "did not send all necessary objects" err &&
a7e67c11 JT	351
	352	# Ensure that the one-time-sed script was used.
	353	! test -e "$HTTPD_ROOT_PATH/one-time-sed"
	354	'
	355
dc0a13f6 JT	356	test_expect_success 'when partial cloning, tolerate server not sending target of tag' '
	357	SERVER="$HTTPD_DOCUMENT_ROOT_PATH/server" &&
	358	rm -rf "$SERVER" repo &&
	359	test_create_repo "$SERVER" &&
	360	test_commit -C "$SERVER" foo &&
	361	test_config -C "$SERVER" uploadpack.allowfilter 1 &&
	362	test_config -C "$SERVER" uploadpack.allowanysha1inwant 1 &&
	363
	364	# Create an annotated tag pointing to a blob.
	365	BLOB=$(echo blob-contents \| git -C "$SERVER" hash-object --stdin -w) &&
	366	git -C "$SERVER" tag -m message -a myblob "$BLOB" &&
	367
	368	# Craft a packfile including the tag, but not the blob it points to.
8c4cc326 JT	369	# Also, omit objects referenced from HEAD in order to force a second
	370	# fetch (to fetch missing objects) upon the automatic checkout that
	371	# happens after a clone.
	372	printf "%s\n%s\n--not\n%s\n%s\n" \
dc0a13f6 JT	373	$(git -C "$SERVER" rev-parse HEAD) \
dc0a13f6 JT	374	$(git -C "$SERVER" rev-parse myblob) \
8c4cc326	375	$(git -C "$SERVER" rev-parse HEAD^{tree}) \
dc0a13f6 JT	376	$(git -C "$SERVER" rev-parse myblob^{blob}) \|
	377	git -C "$SERVER" pack-objects --thin --stdout >incomplete.pack &&
	378
	379	# Replace the existing packfile with the crafted one. The protocol
	380	# requires that the packfile be sent in sideband 1, hence the extra
	381	# \x01 byte at the beginning.
385d1bfd	382	replace_packfile incomplete.pack &&
dc0a13f6 JT	383
	384	# Use protocol v2 because the sed command looks for the "packfile"
	385	# section header.
	386	test_config -C "$SERVER" protocol.version 2 &&
	387
	388	# Exercise to make sure it works.
	389	git -c protocol.version=2 clone \
8c4cc326 JT	390	--filter=blob:none $HTTPD_URL/one_time_sed/server repo 2> err &&
8c4cc326 JT	391	! grep "missing object referenced by" err &&
dc0a13f6 JT	392
	393	# Ensure that the one-time-sed script was used.
	394	! test -e "$HTTPD_ROOT_PATH/one-time-sed"
	395	'
	396
8a30a1ef JT	397	test_expect_success 'tolerate server sending REF_DELTA against missing promisor objects' '
	398	SERVER="$HTTPD_DOCUMENT_ROOT_PATH/server" &&
	399	rm -rf "$SERVER" repo &&
	400	test_create_repo "$SERVER" &&
	401	test_config -C "$SERVER" uploadpack.allowfilter 1 &&
	402	test_config -C "$SERVER" uploadpack.allowanysha1inwant 1 &&
	403
810e1932	404	# Create a commit with 2 blobs to be used as delta bases.
8a30a1ef JT	405	for i in $(test_seq 10)
8a30a1ef JT	406	do
810e1932 JT	407	echo "this is a line" >>"$SERVER/foo.txt" &&
810e1932 JT	408	echo "this is another line" >>"$SERVER/have.txt"
8a30a1ef	409	done &&
810e1932	410	git -C "$SERVER" add foo.txt have.txt &&
8a30a1ef	411	git -C "$SERVER" commit -m bar &&
810e1932 JT	412	git -C "$SERVER" rev-parse HEAD:foo.txt >deltabase_missing &&
810e1932 JT	413	git -C "$SERVER" rev-parse HEAD:have.txt >deltabase_have &&
8a30a1ef	414
810e1932	415	# Clone. The client has deltabase_have but not deltabase_missing.
8a30a1ef JT	416	git -c protocol.version=2 clone --no-checkout \
8a30a1ef JT	417	--filter=blob:none $HTTPD_URL/one_time_sed/server repo &&
810e1932	418	git -C repo hash-object -w -- "$SERVER/have.txt" &&
8a30a1ef	419
810e1932 JT	420	# Sanity check to ensure that the client does not have
810e1932 JT	421	# deltabase_missing.
5718c53d	422	git -C repo rev-list --objects --ignore-missing \
810e1932	423	-- $(cat deltabase_missing) >objlist &&
8a30a1ef JT	424	test_line_count = 0 objlist &&
	425
	426	# Another commit. This commit will be fetched by the client.
	427	echo "abcdefghijklmnopqrstuvwxyz" >>"$SERVER/foo.txt" &&
810e1932 JT	428	echo "abcdefghijklmnopqrstuvwxyz" >>"$SERVER/have.txt" &&
810e1932 JT	429	git -C "$SERVER" add foo.txt have.txt &&
8a30a1ef JT	430	git -C "$SERVER" commit -m baz &&
	431
	432	# Pack a thin pack containing, among other things, HEAD:foo.txt
810e1932 JT	433	# delta-ed against HEAD^:foo.txt and HEAD:have.txt delta-ed against
810e1932 JT	434	# HEAD^:have.txt.
8a30a1ef JT	435	printf "%s\n--not\n%s\n" \
	436	$(git -C "$SERVER" rev-parse HEAD) \
	437	$(git -C "$SERVER" rev-parse HEAD^) \|
	438	git -C "$SERVER" pack-objects --thin --stdout >thin.pack &&
	439
	440	# Ensure that the pack contains one delta against HEAD^:foo.txt. Since
	441	# the delta contains at least 26 novel characters, the size cannot be
	442	# contained in 4 bits, so the object header will take up 2 bytes. The
	443	# most significant nybble of the first byte is 0b1111 (0b1 to indicate
	444	# that the header continues, and 0b111 to indicate REF_DELTA), followed
	445	# by any 3 nybbles, then the OID of the delta base.
810e1932 JT	446	printf "f.,..%s" $(intersperse "," <deltabase_missing) >want &&
	447	hex_unpack <thin.pack \| intersperse "," >have &&
	448	grep $(cat want) have &&
	449
	450	# Ensure that the pack contains one delta against HEAD^:have.txt,
	451	# similar to the above.
	452	printf "f.,..%s" $(intersperse "," <deltabase_have) >want &&
8a30a1ef JT	453	hex_unpack <thin.pack \| intersperse "," >have &&
	454	grep $(cat want) have &&
	455
	456	replace_packfile thin.pack &&
	457
	458	# Use protocol v2 because the sed command looks for the "packfile"
	459	# section header.
	460	test_config -C "$SERVER" protocol.version 2 &&
	461
	462	# Fetch the thin pack and ensure that index-pack is able to handle the
	463	# REF_DELTA object with a missing promisor delta base.
810e1932 JT	464	GIT_TRACE_PACKET="$(pwd)/trace" git -C repo -c protocol.version=2 fetch &&
	465
	466	# Ensure that the missing delta base was directly fetched, but not the
	467	# one that the client has.
	468	grep "want $(cat deltabase_missing)" trace &&
	469	! grep "want $(cat deltabase_have)" trace &&
8a30a1ef JT	470
	471	# Ensure that the one-time-sed script was used.
	472	! test -e "$HTTPD_ROOT_PATH/one-time-sed"
	473	'
	474
decfe05b SG	475	# DO NOT add non-httpd-specific tests here, because the last part of this
	476	# test script is only executed when httpd is available and enabled.
	477
35a7ae95	478	test_done