bundle: add new version for use with SHA-256

Currently we detect the hash algorithm in use by the length of the
object ID.  This is inelegant and prevents us from using a different
hash algorithm that is also 256 bits in length.

Since we cannot extend the v2 format in a backward-compatible way, let's
add a v3 format, which is identical, except for the addition of
capabilities, which are prefixed by an at sign.  We add "object-format"
as the only capability and reject unknown capabilities, since we do not
have a network connection and therefore cannot negotiate with the other
side.

For compatibility, default to the v2 format for SHA-1 and require v3
for SHA-256.

In t5510, always use format v3 so we can be sure we produce consistent
results across hash algorithms.  Since head -n N lists the top N lines
instead of the Nth line, let's run our output through sed to normalize
it and compare it against a fixed value, which will make sure we get
exactly what we're expecting.

Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
Reviewed-by: Eric Sunshine <sunshine@sunshineco.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
brian m. carlson 2020-07-29 23:14:20 +00:00 committed by Junio C Hamano
parent e74b606d47
commit c5aecfc866
7 changed files with 147 additions and 31 deletions

View File

@ -9,7 +9,8 @@ git-bundle - Move objects and refs by archive
SYNOPSIS
--------
[verse]
'git bundle' create [-q | --quiet | --progress | --all-progress] [--all-progress-implied] <file> <git-rev-list-args>
'git bundle' create [-q | --quiet | --progress | --all-progress] [--all-progress-implied]
[--version=<version>] <file> <git-rev-list-args>
'git bundle' verify [-q | --quiet] <file>
'git bundle' list-heads <file> [<refname>...]
'git bundle' unbundle <file> [<refname>...]
@ -102,6 +103,12 @@ unbundle <file>::
is activated. Unlike --all-progress this flag doesn't actually
force any progress display by itself.
--version=<version>::
Specify the bundle version. Version 2 is the older format and can only be
used with SHA-1 repositories; the newer version 3 contains capabilities that
permit extensions. The default is the oldest supported format, based on the
hash algorithm in use.
-q::
--quiet::
This flag makes the command not to report its progress

View File

@ -7,6 +7,8 @@ The Git bundle format is a format that represents both refs and Git objects.
We will use ABNF notation to define the Git bundle format. See
protocol-common.txt for the details.
A v2 bundle looks like this:
----
bundle = signature *prerequisite *reference LF pack
signature = "# v2 git bundle" LF
@ -18,9 +20,28 @@ reference = obj-id SP refname LF
pack = ... ; packfile
----
A v3 bundle looks like this:
----
bundle = signature *capability *prerequisite *reference LF pack
signature = "# v3 git bundle" LF
capability = "@" key ["=" value] LF
prerequisite = "-" obj-id SP comment LF
comment = *CHAR
reference = obj-id SP refname LF
key = 1*(ALPHA / DIGIT / "-")
value = *(%01-09 / %0b-FF)
pack = ... ; packfile
----
== Semantics
A Git bundle consists of three parts.
A Git bundle consists of several parts.
* "Capabilities", which are only in the v3 format, indicate functionality that
the bundle requires to be read properly.
* "Prerequisites" lists the objects that are NOT included in the bundle and the
reader of the bundle MUST already have, in order to use the data in the
@ -46,3 +67,10 @@ put any string here. The reader of the bundle MUST ignore the comment.
Note that the prerequisites does not represent a shallow-clone boundary. The
semantics of the prerequisites and the shallow-clone boundaries are different,
and the Git bundle v2 format cannot represent a shallow clone repository.
== Capabilities
Because there is no opportunity for negotiation, unknown capabilities cause 'git
bundle' to abort. The only known capability is `object-format`, which specifies
the hash algorithm in use, and can take the same values as the
`extensions.objectFormat` configuration value.

View File

@ -60,6 +60,7 @@ static int cmd_bundle_create(int argc, const char **argv, const char *prefix) {
int all_progress_implied = 0;
int progress = isatty(STDERR_FILENO);
struct argv_array pack_opts;
int version = -1;
struct option options[] = {
OPT_SET_INT('q', "quiet", &progress,
@ -71,6 +72,8 @@ static int cmd_bundle_create(int argc, const char **argv, const char *prefix) {
OPT_BOOL(0, "all-progress-implied",
&all_progress_implied,
N_("similar to --all-progress when progress meter is shown")),
OPT_INTEGER(0, "version", &version,
N_("specify bundle format version")),
OPT_END()
};
const char* bundle_file;
@ -91,7 +94,7 @@ static int cmd_bundle_create(int argc, const char **argv, const char *prefix) {
if (!startup_info->have_repository)
die(_("Need a repository to create a bundle."));
return !!create_bundle(the_repository, bundle_file, argc, argv, &pack_opts);
return !!create_bundle(the_repository, bundle_file, argc, argv, &pack_opts, version);
}
static int cmd_bundle_verify(int argc, const char **argv, const char *prefix) {

View File

@ -12,7 +12,16 @@
#include "refs.h"
#include "argv-array.h"
static const char bundle_signature[] = "# v2 git bundle\n";
static const char v2_bundle_signature[] = "# v2 git bundle\n";
static const char v3_bundle_signature[] = "# v3 git bundle\n";
static struct {
int version;
const char *signature;
} bundle_sigs[] = {
{ 2, v2_bundle_signature },
{ 3, v3_bundle_signature },
};
static void add_to_ref_list(const struct object_id *oid, const char *name,
struct ref_list *list)
@ -23,15 +32,30 @@ static void add_to_ref_list(const struct object_id *oid, const char *name,
list->nr++;
}
static const struct git_hash_algo *detect_hash_algo(struct strbuf *buf)
static int parse_capability(struct bundle_header *header, const char *capability)
{
size_t len = strcspn(buf->buf, " \n");
int algo;
const char *arg;
if (skip_prefix(capability, "object-format=", &arg)) {
int algo = hash_algo_by_name(arg);
if (algo == GIT_HASH_UNKNOWN)
return error(_("unrecognized bundle hash algorithm: %s"), arg);
header->hash_algo = &hash_algos[algo];
return 0;
}
return error(_("unknown capability '%s'"), capability);
}
algo = hash_algo_by_length(len / 2);
if (algo == GIT_HASH_UNKNOWN)
return NULL;
return &hash_algos[algo];
static int parse_bundle_signature(struct bundle_header *header, const char *line)
{
int i;
for (i = 0; i < ARRAY_SIZE(bundle_sigs); i++) {
if (!strcmp(line, bundle_sigs[i].signature)) {
header->version = bundle_sigs[i].version;
return 0;
}
}
return -1;
}
static int parse_bundle_header(int fd, struct bundle_header *header,
@ -42,14 +66,16 @@ static int parse_bundle_header(int fd, struct bundle_header *header,
/* The bundle header begins with the signature */
if (strbuf_getwholeline_fd(&buf, fd, '\n') ||
strcmp(buf.buf, bundle_signature)) {
parse_bundle_signature(header, buf.buf)) {
if (report_path)
error(_("'%s' does not look like a v2 bundle file"),
error(_("'%s' does not look like a v2 or v3 bundle file"),
report_path);
status = -1;
goto abort;
}
header->hash_algo = the_hash_algo;
/* The bundle header ends with an empty line */
while (!strbuf_getwholeline_fd(&buf, fd, '\n') &&
buf.len && buf.buf[0] != '\n') {
@ -57,19 +83,19 @@ static int parse_bundle_header(int fd, struct bundle_header *header,
int is_prereq = 0;
const char *p;
if (*buf.buf == '-') {
is_prereq = 1;
strbuf_remove(&buf, 0, 1);
}
strbuf_rtrim(&buf);
if (!header->hash_algo) {
header->hash_algo = detect_hash_algo(&buf);
if (!header->hash_algo) {
error(_("unknown hash algorithm length"));
if (header->version == 3 && *buf.buf == '@') {
if (parse_capability(header, buf.buf + 1)) {
status = -1;
break;
}
continue;
}
if (*buf.buf == '-') {
is_prereq = 1;
strbuf_remove(&buf, 0, 1);
}
/*
@ -449,13 +475,14 @@ static int write_bundle_refs(int bundle_fd, struct rev_info *revs)
}
int create_bundle(struct repository *r, const char *path,
int argc, const char **argv, struct argv_array *pack_options)
int argc, const char **argv, struct argv_array *pack_options, int version)
{
struct lock_file lock = LOCK_INIT;
int bundle_fd = -1;
int bundle_to_stdout;
int ref_count = 0;
struct rev_info revs;
int min_version = the_hash_algo == &hash_algos[GIT_HASH_SHA1] ? 2 : 3;
bundle_to_stdout = !strcmp(path, "-");
if (bundle_to_stdout)
@ -464,8 +491,22 @@ int create_bundle(struct repository *r, const char *path,
bundle_fd = hold_lock_file_for_update(&lock, path,
LOCK_DIE_ON_ERROR);
/* write signature */
write_or_die(bundle_fd, bundle_signature, strlen(bundle_signature));
if (version == -1)
version = min_version;
if (version < 2 || version > 3) {
die(_("unsupported bundle version %d"), version);
} else if (version < min_version) {
die(_("cannot write bundle version %d with algorithm %s"), version, the_hash_algo->name);
} else if (version == 2) {
write_or_die(bundle_fd, v2_bundle_signature, strlen(v2_bundle_signature));
} else {
const char *capability = "@object-format=";
write_or_die(bundle_fd, v3_bundle_signature, strlen(v3_bundle_signature));
write_or_die(bundle_fd, capability, strlen(capability));
write_or_die(bundle_fd, the_hash_algo->name, strlen(the_hash_algo->name));
write_or_die(bundle_fd, "\n", 1);
}
/* init revs to list objects for pack-objects later */
save_commit_buffer = 0;

View File

@ -13,6 +13,7 @@ struct ref_list {
};
struct bundle_header {
unsigned version;
struct ref_list prerequisites;
struct ref_list references;
const struct git_hash_algo *hash_algo;
@ -21,7 +22,8 @@ struct bundle_header {
int is_bundle(const char *path, int quiet);
int read_bundle_header(const char *path, struct bundle_header *header);
int create_bundle(struct repository *r, const char *path,
int argc, const char **argv, struct argv_array *pack_options);
int argc, const char **argv, struct argv_array *pack_options,
int version);
int verify_bundle(struct repository *r, struct bundle_header *header, int verbose);
#define BUNDLE_VERBOSE 1
int unbundle(struct repository *r, struct bundle_header *header,

View File

@ -281,15 +281,19 @@ test_expect_success 'create bundle 1' '
cd "$D" &&
echo >file updated again by origin &&
git commit -a -m "tip" &&
git bundle create bundle1 master^..master
git bundle create --version=3 bundle1 master^..master
'
test_expect_success 'header of bundle looks right' '
head -n 4 "$D"/bundle1 &&
head -n 1 "$D"/bundle1 | grep "^#" &&
head -n 2 "$D"/bundle1 | grep "^-$OID_REGEX " &&
head -n 3 "$D"/bundle1 | grep "^$OID_REGEX " &&
head -n 4 "$D"/bundle1 | grep "^$"
cat >expect <<-EOF &&
# v3 git bundle
@object-format=$(test_oid algo)
-OID updated by origin
OID refs/heads/master
EOF
sed -e "s/$OID_REGEX/OID/g" -e "5q" "$D"/bundle1 >actual &&
test_cmp expect actual
'
test_expect_success 'create bundle 2' '

View File

@ -4,6 +4,10 @@ test_description='some bundle related tests'
. ./test-lib.sh
test_expect_success 'setup' '
test_oid_cache <<-EOF &&
version sha1:2
version sha256:3
EOF
test_commit initial &&
test_tick &&
git tag -m tag tag &&
@ -94,4 +98,31 @@ test_expect_success 'fetch SHA-1 from bundle' '
git fetch --no-tags foo/tip.bundle "$(cat hash)"
'
test_expect_success 'git bundle uses expected default format' '
git bundle create bundle HEAD^.. &&
head -n1 bundle | grep "^# v$(test_oid version) git bundle$"
'
test_expect_success 'git bundle v3 has expected contents' '
git branch side HEAD &&
git bundle create --version=3 bundle HEAD^..side &&
head -n2 bundle >actual &&
cat >expect <<-EOF &&
# v3 git bundle
@object-format=$(test_oid algo)
EOF
test_cmp expect actual &&
git bundle verify bundle
'
test_expect_success 'git bundle v3 rejects unknown capabilities' '
cat >new <<-EOF &&
# v3 git bundle
@object-format=$(test_oid algo)
@unknown=silly
EOF
test_must_fail git bundle verify new 2>output &&
test_i18ngrep "unknown capability .unknown=silly." output
'
test_done