git/builtin/mktag.c
Ævar Arnfjörð Bjarmason 96e41f58fe fsck: report invalid object type-path combinations
Improve the error that's emitted in cases where we find a loose object
we parse, but which isn't at the location we expect it to be.

Before this change we'd prefix the error with a not-a-OID derived from
the path at which the object was found, due to an emergent behavior in
how we'd end up with an "OID" in these codepaths.

Now we'll instead say what object we hashed, and what path it was
found at. Before this patch series e.g.:

    $ git hash-object --stdin -w -t blob </dev/null
    e69de29bb2
    $ mv objects/e6/ objects/e7

Would emit ("[...]" used to abbreviate the OIDs):

    git fsck
    error: hash mismatch for ./objects/e7/9d[...] (expected e79d[...])
    error: e79d[...]: object corrupt or missing: ./objects/e7/9d[...]

Now we'll instead emit:

    error: e69d[...]: hash-path mismatch, found at: ./objects/e7/9d[...]

Furthermore, we'll do the right thing when the object type and its
location are bad. I.e. this case:

    $ git hash-object --stdin -w -t garbage --literally </dev/null
    8315a83d2acc4c174aed59430f9a9c4ed926440f
    $ mv objects/83 objects/84

As noted in an earlier commits we'd simply die early in those cases,
until preceding commits fixed the hard die on invalid object type:

    $ git fsck
    fatal: invalid object type

Now we'll instead emit sensible error messages:

    $ git fsck
    error: 8315[...]: hash-path mismatch, found at: ./objects/84/15[...]
    error: 8315[...]: object is of unknown type 'garbage': ./objects/84/15[...]

In both fsck.c and object-file.c we're using null_oid as a sentinel
value for checking whether we got far enough to be certain that the
issue was indeed this OID mismatch.

We need to add the "object corrupt or missing" special-case to deal
with cases where read_loose_object() will return an error before
completing check_object_signature(), e.g. if we have an error in
unpack_loose_rest() because we find garbage after the valid gzip
content:

    $ git hash-object --stdin -w -t blob </dev/null
    e69de29bb2
    $ chmod 755 objects/e6/9de29bb2d1d6434b8b29ae775ad8c2e48c5391
    $ echo garbage >>objects/e6/9de29bb2d1d6434b8b29ae775ad8c2e48c5391
    $ git fsck
    error: garbage at end of loose object 'e69d[...]'
    error: unable to unpack contents of ./objects/e6/9d[...]
    error: e69d[...]: object corrupt or missing: ./objects/e6/9d[...]

There is currently some weird messaging in the edge case when the two
are combined, i.e. because we're not explicitly passing along an error
state about this specific scenario from check_stream_oid() via
read_loose_object() we'll end up printing the null OID if an object is
of an unknown type *and* it can't be unpacked by zlib, e.g.:

    $ git hash-object --stdin -w -t garbage --literally </dev/null
    8315a83d2acc4c174aed59430f9a9c4ed926440f
    $ chmod 755 objects/83/15a83d2acc4c174aed59430f9a9c4ed926440f
    $ echo garbage >>objects/83/15a83d2acc4c174aed59430f9a9c4ed926440f
    $ /usr/bin/git fsck
    fatal: invalid object type
    $ ~/g/git/git fsck
    error: garbage at end of loose object '8315a83d2acc4c174aed59430f9a9c4ed926440f'
    error: unable to unpack contents of ./objects/83/15a83d2acc4c174aed59430f9a9c4ed926440f
    error: 8315a83d2acc4c174aed59430f9a9c4ed926440f: object corrupt or missing: ./objects/83/15a83d2acc4c174aed59430f9a9c4ed926440f
    error: 0000000000000000000000000000000000000000: object is of unknown type 'garbage': ./objects/83/15a83d2acc4c174aed59430f9a9c4ed926440f
    [...]

I think it's OK to leave that for future improvements, which would
involve enum-ifying more error state as we've done with "enum
unpack_loose_header_result" in preceding commits. In these
increasingly more obscure cases the worst that can happen is that
we'll get slightly nonsensical or inapplicable error messages.

There's other such potential edge cases, all of which might produce
some confusing messaging, but still be handled correctly as far as
passing along errors goes. E.g. if check_object_signature() returns
and oideq(real_oid, null_oid()) is true, which could happen if it
returns -1 due to the read_istream() call having failed.

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-10-01 15:06:01 -07:00

109 lines
2.9 KiB
C

#include "builtin.h"
#include "parse-options.h"
#include "tag.h"
#include "replace-object.h"
#include "object-store.h"
#include "fsck.h"
#include "config.h"
static char const * const builtin_mktag_usage[] = {
N_("git mktag"),
NULL
};
static int option_strict = 1;
static struct fsck_options fsck_options = FSCK_OPTIONS_STRICT;
static int mktag_fsck_error_func(struct fsck_options *o,
const struct object_id *oid,
enum object_type object_type,
enum fsck_msg_type msg_type,
enum fsck_msg_id msg_id,
const char *message)
{
switch (msg_type) {
case FSCK_WARN:
if (!option_strict) {
fprintf_ln(stderr, _("warning: tag input does not pass fsck: %s"), message);
return 0;
}
/* fallthrough */
case FSCK_ERROR:
/*
* We treat both warnings and errors as errors, things
* like missing "tagger" lines are "only" warnings
* under fsck, we've always considered them an error.
*/
fprintf_ln(stderr, _("error: tag input does not pass fsck: %s"), message);
return 1;
default:
BUG(_("%d (FSCK_IGNORE?) should never trigger this callback"),
msg_type);
}
}
static int verify_object_in_tag(struct object_id *tagged_oid, int *tagged_type)
{
int ret;
enum object_type type;
unsigned long size;
void *buffer;
const struct object_id *repl;
buffer = read_object_file(tagged_oid, &type, &size);
if (!buffer)
die(_("could not read tagged object '%s'"),
oid_to_hex(tagged_oid));
if (type != *tagged_type)
die(_("object '%s' tagged as '%s', but is a '%s' type"),
oid_to_hex(tagged_oid),
type_name(*tagged_type), type_name(type));
repl = lookup_replace_object(the_repository, tagged_oid);
ret = check_object_signature(the_repository, repl,
buffer, size, type_name(*tagged_type),
NULL);
free(buffer);
return ret;
}
int cmd_mktag(int argc, const char **argv, const char *prefix)
{
static struct option builtin_mktag_options[] = {
OPT_BOOL(0, "strict", &option_strict,
N_("enable more strict checking")),
OPT_END(),
};
struct strbuf buf = STRBUF_INIT;
struct object_id tagged_oid;
int tagged_type;
struct object_id result;
argc = parse_options(argc, argv, NULL,
builtin_mktag_options,
builtin_mktag_usage, 0);
if (strbuf_read(&buf, 0, 0) < 0)
die_errno(_("could not read from stdin"));
fsck_options.error_func = mktag_fsck_error_func;
fsck_set_msg_type_from_ids(&fsck_options, FSCK_MSG_EXTRA_HEADER_ENTRY,
FSCK_WARN);
/* config might set fsck.extraHeaderEntry=* again */
git_config(git_fsck_config, &fsck_options);
if (fsck_tag_standalone(NULL, buf.buf, buf.len, &fsck_options,
&tagged_oid, &tagged_type))
die(_("tag on stdin did not pass our strict fsck check"));
if (verify_object_in_tag(&tagged_oid, &tagged_type))
die(_("tag on stdin did not refer to a valid object"));
if (write_object_file(buf.buf, buf.len, tag_type, &result) < 0)
die(_("unable to write tag file"));
strbuf_release(&buf);
puts(oid_to_hex(&result));
return 0;
}