Merge branch 'jh/partial-clone'

The machinery to clone & fetch, which in turn involves packing and
unpacking objects, have been told how to omit certain objects using
the filtering mechanism introduced by the jh/object-filtering
topic, and also mark the resulting pack as a promisor pack to
tolerate missing objects, taking advantage of the mechanism
introduced by the jh/fsck-promisors topic.

* jh/partial-clone:
  t5616: test bulk prefetch after partial fetch
  fetch: inherit filter-spec from partial clone
  t5616: end-to-end tests for partial clone
  fetch-pack: restore save_commit_buffer after use
  unpack-trees: batch fetching of missing blobs
  clone: partial clone
  partial-clone: define partial clone settings in config
  fetch: support filters
  fetch: refactor calculation of remote list
  fetch-pack: test support excluding large blobs
  fetch-pack: add --no-filter
  fetch-pack, index-pack, transport: partial clone
  upload-pack: add object filtering for partial clone

3 files changed, 310 insertions, 0 deletions

diff --git a/t/t5500-fetch-pack.sh b/t/t5500-fetch-pack.sh
index 80a1a3239a..ec9ba9bf6e 100755
--- a/t/t5500-fetch-pack.sh
+++ b/t/t5500-fetch-pack.sh
@@ -755,4 +755,67 @@ test_expect_success 'fetching deepen' '
 	)
 '
 
+test_expect_success 'filtering by size' '
+	rm -rf server client &&
+	test_create_repo server &&
+	test_commit -C server one &&
+	test_config -C server uploadpack.allowfilter 1 &&
+
+	test_create_repo client &&
+	git -C client fetch-pack --filter=blob:limit=0 ../server HEAD &&
+
+	# Ensure that object is not inadvertently fetched
+	test_must_fail git -C client cat-file -e $(git hash-object server/one.t)
+'
+
+test_expect_success 'filtering by size has no effect if support for it is not advertised' '
+	rm -rf server client &&
+	test_create_repo server &&
+	test_commit -C server one &&
+
+	test_create_repo client &&
+	git -C client fetch-pack --filter=blob:limit=0 ../server HEAD 2> err &&
+
+	# Ensure that object is fetched
+	git -C client cat-file -e $(git hash-object server/one.t) &&
+
+	test_i18ngrep "filtering not recognized by server" err
+'
+
+fetch_filter_blob_limit_zero () {
+	SERVER="$1"
+	URL="$2"
+
+	rm -rf "$SERVER" client &&
+	test_create_repo "$SERVER" &&
+	test_commit -C "$SERVER" one &&
+	test_config -C "$SERVER" uploadpack.allowfilter 1 &&
+
+	git clone "$URL" client &&
+	test_config -C client extensions.partialclone origin &&
+
+	test_commit -C "$SERVER" two &&
+
+	git -C client fetch --filter=blob:limit=0 origin HEAD:somewhere &&
+
+	# Ensure that commit is fetched, but blob is not
+	test_config -C client extensions.partialclone "arbitrary string" &&
+	git -C client cat-file -e $(git -C "$SERVER" rev-parse two) &&
+	test_must_fail git -C client cat-file -e $(git hash-object "$SERVER/two.t")
+}
+
+test_expect_success 'fetch with --filter=blob:limit=0' '
+	fetch_filter_blob_limit_zero server server
+'
+
+. "$TEST_DIRECTORY"/lib-httpd.sh
+start_httpd
+
+test_expect_success 'fetch with --filter=blob:limit=0 and HTTP' '
+	fetch_filter_blob_limit_zero "$HTTPD_DOCUMENT_ROOT_PATH/server" "$HTTPD_URL/smart/server"
+'
+
+stop_httpd
+
+
 test_done
diff --git a/t/t5601-clone.sh b/t/t5601-clone.sh
index 8c437bf872..0b62037744 100755
--- a/t/t5601-clone.sh
+++ b/t/t5601-clone.sh
@@ -628,4 +628,105 @@ test_expect_success 'clone on case-insensitive fs' '
 	)
 '
 
+partial_clone () {
+	       SERVER="$1" &&
+	       URL="$2" &&
+
+	rm -rf "$SERVER" client &&
+	test_create_repo "$SERVER" &&
+	test_commit -C "$SERVER" one &&
+	HASH1=$(git hash-object "$SERVER/one.t") &&
+	git -C "$SERVER" revert HEAD &&
+	test_commit -C "$SERVER" two &&
+	HASH2=$(git hash-object "$SERVER/two.t") &&
+	test_config -C "$SERVER" uploadpack.allowfilter 1 &&
+	test_config -C "$SERVER" uploadpack.allowanysha1inwant 1 &&
+
+	git clone --filter=blob:limit=0 "$URL" client &&
+
+	git -C client fsck &&
+
+	# Ensure that unneeded blobs are not inadvertently fetched.
+	test_config -C client extensions.partialclone "not a remote" &&
+	test_must_fail git -C client cat-file -e "$HASH1" &&
+
+	# But this blob was fetched, because clone performs an initial checkout
+	git -C client cat-file -e "$HASH2"
+}
+
+test_expect_success 'partial clone' '
+	partial_clone server "file://$(pwd)/server"
+'
+
+test_expect_success 'partial clone: warn if server does not support object filtering' '
+	rm -rf server client &&
+	test_create_repo server &&
+	test_commit -C server one &&
+
+	git clone --filter=blob:limit=0 "file://$(pwd)/server" client 2> err &&
+
+	test_i18ngrep "filtering not recognized by server" err
+'
+
+test_expect_success 'batch missing blob request during checkout' '
+	rm -rf server client &&
+
+	test_create_repo server &&
+	echo a >server/a &&
+	echo b >server/b &&
+	git -C server add a b &&
+
+	git -C server commit -m x &&
+	echo aa >server/a &&
+	echo bb >server/b &&
+	git -C server add a b &&
+	git -C server commit -m x &&
+
+	test_config -C server uploadpack.allowfilter 1 &&
+	test_config -C server uploadpack.allowanysha1inwant 1 &&
+
+	git clone --filter=blob:limit=0 "file://$(pwd)/server" client &&
+
+	# Ensure that there is only one negotiation by checking that there is
+	# only "done" line sent. ("done" marks the end of negotiation.)
+	GIT_TRACE_PACKET="$(pwd)/trace" git -C client checkout HEAD^ &&
+	grep "git> done" trace >done_lines &&
+	test_line_count = 1 done_lines
+'
+
+test_expect_success 'batch missing blob request does not inadvertently try to fetch gitlinks' '
+	rm -rf server client &&
+
+	test_create_repo repo_for_submodule &&
+	test_commit -C repo_for_submodule x &&
+
+	test_create_repo server &&
+	echo a >server/a &&
+	echo b >server/b &&
+	git -C server add a b &&
+	git -C server commit -m x &&
+
+	echo aa >server/a &&
+	echo bb >server/b &&
+	# Also add a gitlink pointing to an arbitrary repository
+	git -C server submodule add "$(pwd)/repo_for_submodule" c &&
+	git -C server add a b c &&
+	git -C server commit -m x &&
+
+	test_config -C server uploadpack.allowfilter 1 &&
+	test_config -C server uploadpack.allowanysha1inwant 1 &&
+
+	# Make sure that it succeeds
+	git clone --filter=blob:limit=0 "file://$(pwd)/server" client
+'
+
+. "$TEST_DIRECTORY"/lib-httpd.sh
+start_httpd
+
+test_expect_success 'partial clone using HTTP' '
+	partial_clone "$HTTPD_DOCUMENT_ROOT_PATH/server" "$HTTPD_URL/smart/server"
+'
+
+stop_httpd
+
 test_done
diff --git a/t/t5616-partial-clone.sh b/t/t5616-partial-clone.sh
new file mode 100755
index 0000000000..29d8631184
--- /dev/null
+++ b/t/t5616-partial-clone.sh
@@ -0,0 +1,146 @@
+#!/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_done