Merge branch 'jt/partial-clone-fsck-connectivity'

Partial clone support of "git clone" has been updated to correctly
validate the objects it receives from the other side.  The server
side has been corrected to send objects that are directly
requested, even if they may match the filtering criteria (e.g. when
doing a "lazy blob" partial clone).

* jt/partial-clone-fsck-connectivity:
  clone: check connectivity even if clone is partial
  upload-pack: send refs' objects despite "filter"

Author: gitster

Documentation/technical/pack-protocol.txt

@@ -284,7 +284,9 @@ information is sent back to the client in the next step.
 The client can optionally request that pack-objects omit various
 objects from the packfile using one of several filtering techniques.
 These are intended for use with partial clone and partial fetch
-operations.  See `rev-list` for possible "filter-spec" values.
+operations. An object that does not meet a filter-spec value is
+omitted unless explicitly requested in a 'want' line. See `rev-list`
+for possible filter-spec values.
 
 Once all the 'want's and 'shallow's (and optional 'deepen') are
 transferred, clients MUST send a flush-pkt, to tell the server side

builtin/clone.c

@@ -1202,7 +1202,7 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 
 	update_remote_refs(refs, mapped_refs, remote_head_points_at,
 			   branch_top.buf, reflog_msg.buf, transport,
-			   !is_local && !filter_options.choice);
+			   !is_local);
 
 	update_head(our_head_points_at, remote_head, reflog_msg.buf);
 

list-objects.c

@@ -48,7 +48,7 @@ static void process_blob(struct rev_info *revs,
 
 	pathlen = path->len;
 	strbuf_addstr(path, name);
-	if (filter_fn)
+	if (!(obj->flags & USER_GIVEN) && filter_fn)
 		r = filter_fn(LOFS_BLOB, obj,
 			      path->buf, &path->buf[pathlen],
 			      filter_data);
@@ -133,7 +133,7 @@ static void process_tree(struct rev_info *revs,
 	}
 
 	strbuf_addstr(base, name);
-	if (filter_fn)
+	if (!(obj->flags & USER_GIVEN) && filter_fn)
 		r = filter_fn(LOFS_BEGIN_TREE, obj,
 			      base->buf, &base->buf[baselen],
 			      filter_data);
@@ -172,7 +172,7 @@ static void process_tree(struct rev_info *revs,
 				     cb_data, filter_fn, filter_data);
 	}
 
-	if (filter_fn) {
+	if (!(obj->flags & USER_GIVEN) && filter_fn) {
 		r = filter_fn(LOFS_END_TREE, obj,
 			      base->buf, &base->buf[baselen],
 			      filter_data);

object.h

@@ -53,7 +53,7 @@ struct object_array {
 
 /*
  * object flag allocation:
- * revision.h:               0---------10                                26
+ * revision.h:               0---------10                              2526
  * fetch-pack.c:             0----5
  * walker.c:                 0-2
  * upload-pack.c:                4       11----------------19

revision.c

@@ -175,6 +175,7 @@ static void add_pending_object_with_path(struct rev_info *revs,
 		strbuf_release(&buf);
 		return; /* do not add the commit itself */
 	}
+	obj->flags |= USER_GIVEN;
 	add_object_array_with_path(obj, name, &revs->pending, mode, path);
 }
 

revision.h

@@ -20,8 +20,9 @@
 #define SYMMETRIC_LEFT	(1u<<8)
 #define PATCHSAME	(1u<<9)
 #define BOTTOM		(1u<<10)
+#define USER_GIVEN	(1u<<25) /* given directly by the user */
 #define TRACK_LINEAR	(1u<<26)
-#define ALL_REV_FLAGS	(((1u<<11)-1) | TRACK_LINEAR)
+#define ALL_REV_FLAGS	(((1u<<11)-1) | USER_GIVEN | TRACK_LINEAR)
 
 #define DECORATE_SHORT_REFS	1
 #define DECORATE_FULL_REFS	2

t/t5317-pack-objects-filter-objects.sh

@@ -160,6 +160,22 @@ test_expect_success 'verify blob:limit=1k' '
 	test_cmp observed expected
 '
 
+test_expect_success 'verify explicitly specifying oversized blob in input' '
+	git -C r2 ls-files -s large.1000 large.10000 \
+		| awk -f print_2.awk \
+		| sort >expected &&
+	git -C r2 pack-objects --rev --stdout --filter=blob:limit=1k >filter.pack <<-EOF &&
+	HEAD
+	$(git -C r2 rev-parse HEAD:large.10000)
+	EOF
+	git -C r2 index-pack ../filter.pack &&
+	git -C r2 verify-pack -v ../filter.pack \
+		| grep blob \
+		| awk -f print_1.awk \
+		| sort >observed &&
+	test_cmp observed expected
+'
+
 test_expect_success 'verify blob:limit=1m' '
 	git -C r2 ls-files -s large.1000 large.10000 \
 		| awk -f print_2.awk \

t/t5616-partial-clone.sh

@@ -154,4 +154,68 @@ test_expect_success 'partial clone with transfer.fsckobjects=1 uses index-pack -
 	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"
+'
+
+stop_httpd
+
 test_done