2008-02-26 00:46:04 +03:00
|
|
|
#include "cache.h"
|
|
|
|
#include "object.h"
|
|
|
|
#include "blob.h"
|
|
|
|
#include "tree.h"
|
|
|
|
#include "tree-walk.h"
|
|
|
|
#include "commit.h"
|
|
|
|
#include "tag.h"
|
|
|
|
#include "fsck.h"
|
2014-09-11 18:26:38 +04:00
|
|
|
#include "refs.h"
|
fsck: complain about HFS+ ".git" aliases in trees
Now that the index can block pathnames that case-fold to
".git" on HFS+, it would be helpful for fsck to notice such
problematic paths. This lets servers which use
receive.fsckObjects block them before the damage spreads.
Note that the fsck check is always on, even for systems
without core.protectHFS set. This is technically more
restrictive than we need to be, as a set of users on ext4
could happily use these odd filenames without caring about
HFS+.
However, on balance, it's helpful for all servers to block
these (because the paths can be used for mischief, and
servers which bother to fsck would want to stop the spread
whether they are on HFS+ themselves or not), and hardly
anybody will be affected (because the blocked names are
variants of .git with invisible Unicode code-points mixed
in, meaning mischief is almost certainly what the tree
author had in mind).
Ideally these would be controlled by a separate
"fsck.protectHFS" flag. However, it would be much nicer to
be able to enable/disable _any_ fsck flag individually, and
any scheme we choose should match such a system. Given the
likelihood of anybody using such a path in practice, it is
not unreasonable to wait until such a system materializes.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-12-16 02:21:57 +03:00
|
|
|
#include "utf8.h"
|
2015-06-22 18:27:18 +03:00
|
|
|
#include "sha1-array.h"
|
2016-07-17 13:59:49 +03:00
|
|
|
#include "decorate.h"
|
2008-02-26 00:46:04 +03:00
|
|
|
|
2015-06-22 18:26:42 +03:00
|
|
|
#define FSCK_FATAL -1
|
2015-06-22 18:26:54 +03:00
|
|
|
#define FSCK_INFO -2
|
2015-06-22 18:26:42 +03:00
|
|
|
|
2015-06-22 18:25:09 +03:00
|
|
|
#define FOREACH_MSG_ID(FUNC) \
|
2015-06-22 18:26:42 +03:00
|
|
|
/* fatal errors */ \
|
|
|
|
FUNC(NUL_IN_HEADER, FATAL) \
|
|
|
|
FUNC(UNTERMINATED_HEADER, FATAL) \
|
2015-06-22 18:25:09 +03:00
|
|
|
/* errors */ \
|
|
|
|
FUNC(BAD_DATE, ERROR) \
|
|
|
|
FUNC(BAD_DATE_OVERFLOW, ERROR) \
|
|
|
|
FUNC(BAD_EMAIL, ERROR) \
|
|
|
|
FUNC(BAD_NAME, ERROR) \
|
|
|
|
FUNC(BAD_OBJECT_SHA1, ERROR) \
|
|
|
|
FUNC(BAD_PARENT_SHA1, ERROR) \
|
|
|
|
FUNC(BAD_TAG_OBJECT, ERROR) \
|
|
|
|
FUNC(BAD_TIMEZONE, ERROR) \
|
|
|
|
FUNC(BAD_TREE, ERROR) \
|
|
|
|
FUNC(BAD_TREE_SHA1, ERROR) \
|
|
|
|
FUNC(BAD_TYPE, ERROR) \
|
|
|
|
FUNC(DUPLICATE_ENTRIES, ERROR) \
|
|
|
|
FUNC(MISSING_AUTHOR, ERROR) \
|
|
|
|
FUNC(MISSING_COMMITTER, ERROR) \
|
|
|
|
FUNC(MISSING_EMAIL, ERROR) \
|
|
|
|
FUNC(MISSING_GRAFT, ERROR) \
|
|
|
|
FUNC(MISSING_NAME_BEFORE_EMAIL, ERROR) \
|
|
|
|
FUNC(MISSING_OBJECT, ERROR) \
|
|
|
|
FUNC(MISSING_PARENT, ERROR) \
|
|
|
|
FUNC(MISSING_SPACE_BEFORE_DATE, ERROR) \
|
|
|
|
FUNC(MISSING_SPACE_BEFORE_EMAIL, ERROR) \
|
|
|
|
FUNC(MISSING_TAG, ERROR) \
|
|
|
|
FUNC(MISSING_TAG_ENTRY, ERROR) \
|
|
|
|
FUNC(MISSING_TAG_OBJECT, ERROR) \
|
|
|
|
FUNC(MISSING_TREE, ERROR) \
|
|
|
|
FUNC(MISSING_TYPE, ERROR) \
|
|
|
|
FUNC(MISSING_TYPE_ENTRY, ERROR) \
|
2015-06-22 18:26:23 +03:00
|
|
|
FUNC(MULTIPLE_AUTHORS, ERROR) \
|
2015-06-22 18:25:09 +03:00
|
|
|
FUNC(TAG_OBJECT_NOT_TAG, ERROR) \
|
|
|
|
FUNC(TREE_NOT_SORTED, ERROR) \
|
|
|
|
FUNC(UNKNOWN_TYPE, ERROR) \
|
|
|
|
FUNC(ZERO_PADDED_DATE, ERROR) \
|
|
|
|
/* warnings */ \
|
|
|
|
FUNC(BAD_FILEMODE, WARN) \
|
|
|
|
FUNC(EMPTY_NAME, WARN) \
|
|
|
|
FUNC(FULL_PATHNAME, WARN) \
|
|
|
|
FUNC(HAS_DOT, WARN) \
|
|
|
|
FUNC(HAS_DOTDOT, WARN) \
|
|
|
|
FUNC(HAS_DOTGIT, WARN) \
|
|
|
|
FUNC(NULL_SHA1, WARN) \
|
2015-06-22 18:26:54 +03:00
|
|
|
FUNC(ZERO_PADDED_FILEMODE, WARN) \
|
2016-04-14 20:58:22 +03:00
|
|
|
FUNC(NUL_IN_COMMIT, WARN) \
|
2015-06-22 18:26:54 +03:00
|
|
|
/* infos (reported as warnings, but ignored by default) */ \
|
|
|
|
FUNC(BAD_TAG_NAME, INFO) \
|
|
|
|
FUNC(MISSING_TAGGER_ENTRY, INFO)
|
2015-06-22 18:25:09 +03:00
|
|
|
|
|
|
|
#define MSG_ID(id, msg_type) FSCK_MSG_##id,
|
|
|
|
enum fsck_msg_id {
|
|
|
|
FOREACH_MSG_ID(MSG_ID)
|
|
|
|
FSCK_MSG_MAX
|
|
|
|
};
|
|
|
|
#undef MSG_ID
|
|
|
|
|
2015-06-22 18:25:14 +03:00
|
|
|
#define STR(x) #x
|
|
|
|
#define MSG_ID(id, msg_type) { STR(id), NULL, FSCK_##msg_type },
|
2015-06-22 18:25:09 +03:00
|
|
|
static struct {
|
2015-06-22 18:25:14 +03:00
|
|
|
const char *id_string;
|
|
|
|
const char *downcased;
|
2015-06-22 18:25:09 +03:00
|
|
|
int msg_type;
|
|
|
|
} msg_id_info[FSCK_MSG_MAX + 1] = {
|
|
|
|
FOREACH_MSG_ID(MSG_ID)
|
2015-06-22 18:25:14 +03:00
|
|
|
{ NULL, NULL, -1 }
|
2015-06-22 18:25:09 +03:00
|
|
|
};
|
|
|
|
#undef MSG_ID
|
|
|
|
|
2015-06-22 18:25:14 +03:00
|
|
|
static int parse_msg_id(const char *text)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
if (!msg_id_info[0].downcased) {
|
|
|
|
/* convert id_string to lower case, without underscores. */
|
|
|
|
for (i = 0; i < FSCK_MSG_MAX; i++) {
|
|
|
|
const char *p = msg_id_info[i].id_string;
|
|
|
|
int len = strlen(p);
|
|
|
|
char *q = xmalloc(len);
|
|
|
|
|
|
|
|
msg_id_info[i].downcased = q;
|
|
|
|
while (*p)
|
|
|
|
if (*p == '_')
|
|
|
|
p++;
|
|
|
|
else
|
|
|
|
*(q)++ = tolower(*(p)++);
|
|
|
|
*q = '\0';
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
for (i = 0; i < FSCK_MSG_MAX; i++)
|
|
|
|
if (!strcmp(text, msg_id_info[i].downcased))
|
|
|
|
return i;
|
|
|
|
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
2015-06-22 18:25:09 +03:00
|
|
|
static int fsck_msg_type(enum fsck_msg_id msg_id,
|
|
|
|
struct fsck_options *options)
|
|
|
|
{
|
|
|
|
int msg_type;
|
|
|
|
|
2015-06-22 18:25:25 +03:00
|
|
|
assert(msg_id >= 0 && msg_id < FSCK_MSG_MAX);
|
|
|
|
|
|
|
|
if (options->msg_type)
|
|
|
|
msg_type = options->msg_type[msg_id];
|
|
|
|
else {
|
|
|
|
msg_type = msg_id_info[msg_id].msg_type;
|
|
|
|
if (options->strict && msg_type == FSCK_WARN)
|
|
|
|
msg_type = FSCK_ERROR;
|
|
|
|
}
|
2015-06-22 18:25:09 +03:00
|
|
|
|
|
|
|
return msg_type;
|
|
|
|
}
|
|
|
|
|
2015-06-22 18:27:18 +03:00
|
|
|
static void init_skiplist(struct fsck_options *options, const char *path)
|
|
|
|
{
|
2017-03-31 04:40:00 +03:00
|
|
|
static struct oid_array skiplist = OID_ARRAY_INIT;
|
2015-06-22 18:27:18 +03:00
|
|
|
int sorted, fd;
|
2017-03-26 19:01:30 +03:00
|
|
|
char buffer[GIT_MAX_HEXSZ + 1];
|
|
|
|
struct object_id oid;
|
2015-06-22 18:27:18 +03:00
|
|
|
|
|
|
|
if (options->skiplist)
|
|
|
|
sorted = options->skiplist->sorted;
|
|
|
|
else {
|
|
|
|
sorted = 1;
|
|
|
|
options->skiplist = &skiplist;
|
|
|
|
}
|
|
|
|
|
|
|
|
fd = open(path, O_RDONLY);
|
|
|
|
if (fd < 0)
|
|
|
|
die("Could not open skip list: %s", path);
|
|
|
|
for (;;) {
|
2017-03-26 19:01:30 +03:00
|
|
|
const char *p;
|
2015-06-22 18:27:18 +03:00
|
|
|
int result = read_in_full(fd, buffer, sizeof(buffer));
|
|
|
|
if (result < 0)
|
|
|
|
die_errno("Could not read '%s'", path);
|
|
|
|
if (!result)
|
|
|
|
break;
|
2017-03-26 19:01:30 +03:00
|
|
|
if (parse_oid_hex(buffer, &oid, &p) || *p != '\n')
|
2015-06-22 18:27:18 +03:00
|
|
|
die("Invalid SHA-1: %s", buffer);
|
2017-03-31 04:40:00 +03:00
|
|
|
oid_array_append(&skiplist, &oid);
|
2015-06-22 18:27:18 +03:00
|
|
|
if (sorted && skiplist.nr > 1 &&
|
2017-03-26 19:01:37 +03:00
|
|
|
oidcmp(&skiplist.oid[skiplist.nr - 2],
|
|
|
|
&oid) > 0)
|
2015-06-22 18:27:18 +03:00
|
|
|
sorted = 0;
|
|
|
|
}
|
|
|
|
close(fd);
|
|
|
|
|
|
|
|
if (sorted)
|
|
|
|
skiplist.sorted = 1;
|
|
|
|
}
|
|
|
|
|
2015-06-22 18:25:25 +03:00
|
|
|
static int parse_msg_type(const char *str)
|
|
|
|
{
|
|
|
|
if (!strcmp(str, "error"))
|
|
|
|
return FSCK_ERROR;
|
|
|
|
else if (!strcmp(str, "warn"))
|
|
|
|
return FSCK_WARN;
|
2015-06-22 18:26:48 +03:00
|
|
|
else if (!strcmp(str, "ignore"))
|
|
|
|
return FSCK_IGNORE;
|
2015-06-22 18:25:25 +03:00
|
|
|
else
|
|
|
|
die("Unknown fsck message type: '%s'", str);
|
|
|
|
}
|
|
|
|
|
2015-06-22 18:25:31 +03:00
|
|
|
int is_valid_msg_type(const char *msg_id, const char *msg_type)
|
|
|
|
{
|
|
|
|
if (parse_msg_id(msg_id) < 0)
|
|
|
|
return 0;
|
|
|
|
parse_msg_type(msg_type);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2015-06-22 18:25:25 +03:00
|
|
|
void fsck_set_msg_type(struct fsck_options *options,
|
|
|
|
const char *msg_id, const char *msg_type)
|
|
|
|
{
|
|
|
|
int id = parse_msg_id(msg_id), type;
|
|
|
|
|
|
|
|
if (id < 0)
|
|
|
|
die("Unhandled message id: %s", msg_id);
|
|
|
|
type = parse_msg_type(msg_type);
|
|
|
|
|
2015-06-22 18:26:42 +03:00
|
|
|
if (type != FSCK_ERROR && msg_id_info[id].msg_type == FSCK_FATAL)
|
|
|
|
die("Cannot demote %s to %s", msg_id, msg_type);
|
|
|
|
|
2015-06-22 18:25:25 +03:00
|
|
|
if (!options->msg_type) {
|
|
|
|
int i;
|
2016-02-23 01:44:25 +03:00
|
|
|
int *msg_type;
|
|
|
|
ALLOC_ARRAY(msg_type, FSCK_MSG_MAX);
|
2015-06-22 18:25:25 +03:00
|
|
|
for (i = 0; i < FSCK_MSG_MAX; i++)
|
|
|
|
msg_type[i] = fsck_msg_type(i, options);
|
|
|
|
options->msg_type = msg_type;
|
|
|
|
}
|
|
|
|
|
|
|
|
options->msg_type[id] = type;
|
|
|
|
}
|
|
|
|
|
|
|
|
void fsck_set_msg_types(struct fsck_options *options, const char *values)
|
|
|
|
{
|
|
|
|
char *buf = xstrdup(values), *to_free = buf;
|
|
|
|
int done = 0;
|
|
|
|
|
|
|
|
while (!done) {
|
|
|
|
int len = strcspn(buf, " ,|"), equal;
|
|
|
|
|
|
|
|
done = !buf[len];
|
|
|
|
if (!len) {
|
|
|
|
buf++;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
buf[len] = '\0';
|
|
|
|
|
|
|
|
for (equal = 0;
|
|
|
|
equal < len && buf[equal] != '=' && buf[equal] != ':';
|
|
|
|
equal++)
|
|
|
|
buf[equal] = tolower(buf[equal]);
|
|
|
|
buf[equal] = '\0';
|
|
|
|
|
2015-06-22 18:27:18 +03:00
|
|
|
if (!strcmp(buf, "skiplist")) {
|
|
|
|
if (equal == len)
|
|
|
|
die("skiplist requires a path");
|
|
|
|
init_skiplist(options, buf + equal + 1);
|
|
|
|
buf += len + 1;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2015-06-22 18:25:25 +03:00
|
|
|
if (equal == len)
|
|
|
|
die("Missing '=': '%s'", buf);
|
2008-02-26 00:46:04 +03:00
|
|
|
|
2015-06-22 18:25:25 +03:00
|
|
|
fsck_set_msg_type(options, buf, buf + equal + 1);
|
|
|
|
buf += len + 1;
|
|
|
|
}
|
|
|
|
free(to_free);
|
|
|
|
}
|
|
|
|
|
2015-06-22 18:25:52 +03:00
|
|
|
static void append_msg_id(struct strbuf *sb, const char *msg_id)
|
|
|
|
{
|
|
|
|
for (;;) {
|
|
|
|
char c = *(msg_id)++;
|
|
|
|
|
|
|
|
if (!c)
|
|
|
|
break;
|
|
|
|
if (c != '_')
|
|
|
|
strbuf_addch(sb, tolower(c));
|
|
|
|
else {
|
|
|
|
assert(*msg_id);
|
|
|
|
strbuf_addch(sb, *(msg_id)++);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
strbuf_addstr(sb, ": ");
|
|
|
|
}
|
|
|
|
|
2015-06-22 18:25:09 +03:00
|
|
|
__attribute__((format (printf, 4, 5)))
|
|
|
|
static int report(struct fsck_options *options, struct object *object,
|
|
|
|
enum fsck_msg_id id, const char *fmt, ...)
|
|
|
|
{
|
|
|
|
va_list ap;
|
|
|
|
struct strbuf sb = STRBUF_INIT;
|
|
|
|
int msg_type = fsck_msg_type(id, options), result;
|
|
|
|
|
2015-06-22 18:26:48 +03:00
|
|
|
if (msg_type == FSCK_IGNORE)
|
|
|
|
return 0;
|
|
|
|
|
2015-06-22 18:27:18 +03:00
|
|
|
if (options->skiplist && object &&
|
2017-03-31 04:40:00 +03:00
|
|
|
oid_array_lookup(options->skiplist, &object->oid) >= 0)
|
2015-06-22 18:27:18 +03:00
|
|
|
return 0;
|
|
|
|
|
2015-06-22 18:26:42 +03:00
|
|
|
if (msg_type == FSCK_FATAL)
|
|
|
|
msg_type = FSCK_ERROR;
|
2015-06-22 18:26:54 +03:00
|
|
|
else if (msg_type == FSCK_INFO)
|
|
|
|
msg_type = FSCK_WARN;
|
2015-06-22 18:26:42 +03:00
|
|
|
|
2015-06-22 18:25:52 +03:00
|
|
|
append_msg_id(&sb, msg_id_info[id].id_string);
|
|
|
|
|
2015-06-22 18:25:09 +03:00
|
|
|
va_start(ap, fmt);
|
|
|
|
strbuf_vaddf(&sb, fmt, ap);
|
2016-07-17 13:59:57 +03:00
|
|
|
result = options->error_func(options, object, msg_type, sb.buf);
|
2015-06-22 18:25:09 +03:00
|
|
|
strbuf_release(&sb);
|
|
|
|
va_end(ap);
|
|
|
|
|
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
2016-07-17 13:59:49 +03:00
|
|
|
static char *get_object_name(struct fsck_options *options, struct object *obj)
|
|
|
|
{
|
|
|
|
if (!options->object_names)
|
|
|
|
return NULL;
|
|
|
|
return lookup_decoration(options->object_names, obj);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void put_object_name(struct fsck_options *options, struct object *obj,
|
|
|
|
const char *fmt, ...)
|
|
|
|
{
|
|
|
|
va_list ap;
|
|
|
|
struct strbuf buf = STRBUF_INIT;
|
|
|
|
char *existing;
|
|
|
|
|
|
|
|
if (!options->object_names)
|
|
|
|
return;
|
|
|
|
existing = lookup_decoration(options->object_names, obj);
|
|
|
|
if (existing)
|
|
|
|
return;
|
|
|
|
va_start(ap, fmt);
|
|
|
|
strbuf_vaddf(&buf, fmt, ap);
|
|
|
|
add_decoration(options->object_names, obj, strbuf_detach(&buf, NULL));
|
|
|
|
va_end(ap);
|
|
|
|
}
|
|
|
|
|
2016-07-17 14:00:02 +03:00
|
|
|
static const char *describe_object(struct fsck_options *o, struct object *obj)
|
|
|
|
{
|
|
|
|
static struct strbuf buf = STRBUF_INIT;
|
|
|
|
char *name;
|
|
|
|
|
|
|
|
strbuf_reset(&buf);
|
|
|
|
strbuf_addstr(&buf, oid_to_hex(&obj->oid));
|
|
|
|
if (o->object_names && (name = lookup_decoration(o->object_names, obj)))
|
|
|
|
strbuf_addf(&buf, " (%s)", name);
|
|
|
|
|
|
|
|
return buf.buf;
|
|
|
|
}
|
|
|
|
|
2015-06-22 18:25:00 +03:00
|
|
|
static int fsck_walk_tree(struct tree *tree, void *data, struct fsck_options *options)
|
2008-02-26 00:46:04 +03:00
|
|
|
{
|
|
|
|
struct tree_desc desc;
|
|
|
|
struct name_entry entry;
|
|
|
|
int res = 0;
|
2016-07-17 13:59:49 +03:00
|
|
|
const char *name;
|
2008-02-26 00:46:04 +03:00
|
|
|
|
|
|
|
if (parse_tree(tree))
|
|
|
|
return -1;
|
|
|
|
|
2016-07-17 13:59:49 +03:00
|
|
|
name = get_object_name(options, &tree->object);
|
2016-09-27 23:59:51 +03:00
|
|
|
if (init_tree_desc_gently(&desc, tree->buffer, tree->size))
|
|
|
|
return -1;
|
|
|
|
while (tree_entry_gently(&desc, &entry)) {
|
2016-07-17 13:59:49 +03:00
|
|
|
struct object *obj;
|
2008-02-26 00:46:04 +03:00
|
|
|
int result;
|
|
|
|
|
|
|
|
if (S_ISGITLINK(entry.mode))
|
|
|
|
continue;
|
2016-07-17 13:59:49 +03:00
|
|
|
|
|
|
|
if (S_ISDIR(entry.mode)) {
|
2017-05-07 01:10:17 +03:00
|
|
|
obj = &lookup_tree(entry.oid)->object;
|
2016-07-17 13:59:49 +03:00
|
|
|
if (name)
|
|
|
|
put_object_name(options, obj, "%s%s/", name,
|
|
|
|
entry.path);
|
|
|
|
result = options->walk(obj, OBJ_TREE, data, options);
|
|
|
|
}
|
|
|
|
else if (S_ISREG(entry.mode) || S_ISLNK(entry.mode)) {
|
2017-05-07 01:10:14 +03:00
|
|
|
obj = &lookup_blob(entry.oid)->object;
|
2016-07-17 13:59:49 +03:00
|
|
|
if (name)
|
|
|
|
put_object_name(options, obj, "%s%s", name,
|
|
|
|
entry.path);
|
|
|
|
result = options->walk(obj, OBJ_BLOB, data, options);
|
|
|
|
}
|
2008-02-26 00:46:04 +03:00
|
|
|
else {
|
2012-04-30 04:28:45 +04:00
|
|
|
result = error("in tree %s: entry %s has bad mode %.6o",
|
2016-07-17 14:00:02 +03:00
|
|
|
describe_object(options, &tree->object), entry.path, entry.mode);
|
2008-02-26 00:46:04 +03:00
|
|
|
}
|
|
|
|
if (result < 0)
|
|
|
|
return result;
|
|
|
|
if (!res)
|
|
|
|
res = result;
|
|
|
|
}
|
|
|
|
return res;
|
|
|
|
}
|
|
|
|
|
2015-06-22 18:25:00 +03:00
|
|
|
static int fsck_walk_commit(struct commit *commit, void *data, struct fsck_options *options)
|
2008-02-26 00:46:04 +03:00
|
|
|
{
|
2016-07-17 13:59:49 +03:00
|
|
|
int counter = 0, generation = 0, name_prefix_len = 0;
|
2008-02-26 00:46:04 +03:00
|
|
|
struct commit_list *parents;
|
|
|
|
int res;
|
|
|
|
int result;
|
2016-07-17 13:59:49 +03:00
|
|
|
const char *name;
|
2008-02-26 00:46:04 +03:00
|
|
|
|
|
|
|
if (parse_commit(commit))
|
|
|
|
return -1;
|
|
|
|
|
2016-07-17 13:59:49 +03:00
|
|
|
name = get_object_name(options, &commit->object);
|
|
|
|
if (name)
|
|
|
|
put_object_name(options, &commit->tree->object, "%s:", name);
|
|
|
|
|
2015-06-22 18:25:00 +03:00
|
|
|
result = options->walk((struct object *)commit->tree, OBJ_TREE, data, options);
|
2008-02-26 00:46:04 +03:00
|
|
|
if (result < 0)
|
|
|
|
return result;
|
|
|
|
res = result;
|
|
|
|
|
|
|
|
parents = commit->parents;
|
2016-07-17 13:59:49 +03:00
|
|
|
if (name && parents) {
|
|
|
|
int len = strlen(name), power;
|
|
|
|
|
|
|
|
if (len && name[len - 1] == '^') {
|
|
|
|
generation = 1;
|
|
|
|
name_prefix_len = len - 1;
|
|
|
|
}
|
|
|
|
else { /* parse ~<generation> suffix */
|
|
|
|
for (generation = 0, power = 1;
|
|
|
|
len && isdigit(name[len - 1]);
|
|
|
|
power *= 10)
|
|
|
|
generation += power * (name[--len] - '0');
|
|
|
|
if (power > 1 && len && name[len - 1] == '~')
|
|
|
|
name_prefix_len = len - 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2008-02-26 00:46:04 +03:00
|
|
|
while (parents) {
|
2016-07-17 13:59:49 +03:00
|
|
|
if (name) {
|
|
|
|
struct object *obj = &parents->item->object;
|
|
|
|
|
|
|
|
if (++counter > 1)
|
|
|
|
put_object_name(options, obj, "%s^%d",
|
|
|
|
name, counter);
|
|
|
|
else if (generation > 0)
|
|
|
|
put_object_name(options, obj, "%.*s~%d",
|
|
|
|
name_prefix_len, name, generation + 1);
|
|
|
|
else
|
|
|
|
put_object_name(options, obj, "%s^", name);
|
|
|
|
}
|
2015-06-22 18:25:00 +03:00
|
|
|
result = options->walk((struct object *)parents->item, OBJ_COMMIT, data, options);
|
2008-02-26 00:46:04 +03:00
|
|
|
if (result < 0)
|
|
|
|
return result;
|
|
|
|
if (!res)
|
|
|
|
res = result;
|
|
|
|
parents = parents->next;
|
|
|
|
}
|
|
|
|
return res;
|
|
|
|
}
|
|
|
|
|
2015-06-22 18:25:00 +03:00
|
|
|
static int fsck_walk_tag(struct tag *tag, void *data, struct fsck_options *options)
|
2008-02-26 00:46:04 +03:00
|
|
|
{
|
2016-07-17 13:59:49 +03:00
|
|
|
char *name = get_object_name(options, &tag->object);
|
|
|
|
|
2008-02-26 00:46:04 +03:00
|
|
|
if (parse_tag(tag))
|
|
|
|
return -1;
|
2016-07-17 13:59:49 +03:00
|
|
|
if (name)
|
|
|
|
put_object_name(options, tag->tagged, "%s", name);
|
2015-06-22 18:25:00 +03:00
|
|
|
return options->walk(tag->tagged, OBJ_ANY, data, options);
|
2008-02-26 00:46:04 +03:00
|
|
|
}
|
|
|
|
|
2015-06-22 18:25:00 +03:00
|
|
|
int fsck_walk(struct object *obj, void *data, struct fsck_options *options)
|
2008-02-26 00:46:04 +03:00
|
|
|
{
|
|
|
|
if (!obj)
|
|
|
|
return -1;
|
fsck: lazily load types under --connectivity-only
The recent fixes to "fsck --connectivity-only" load all of
the objects with their correct types. This keeps the
connectivity-only code path close to the regular one, but it
also introduces some unnecessary inefficiency. While getting
the type of an object is cheap compared to actually opening
and parsing the object (as the non-connectivity-only case
would do), it's still not free.
For reachable non-blob objects, we end up having to parse
them later anyway (to see what they point to), making our
type lookup here redundant.
For unreachable objects, we might never hit them at all in
the reachability traversal, making the lookup completely
wasted. And in some cases, we might have quite a few
unreachable objects (e.g., when alternates are used for
shared object storage between repositories, it's normal for
there to be objects reachable from other repositories but
not the one running fsck).
The comment in mark_object_for_connectivity() claims two
benefits to getting the type up front:
1. We need to know the types during fsck_walk(). (And not
explicitly mentioned, but we also need them when
printing the types of broken or dangling commits).
We can address this by lazy-loading the types as
necessary. Most objects never need this lazy-load at
all, because they fall into one of these categories:
a. Reachable from our tips, and are coerced into the
correct type as we traverse (e.g., a parent link
will call lookup_commit(), which converts OBJ_NONE
to OBJ_COMMIT).
b. Unreachable, but not at the tip of a chunk of
unreachable history. We only mention the tips as
"dangling", so an unreachable commit which links
to hundreds of other objects needs only report the
type of the tip commit.
2. It serves as a cross-check that the coercion in (1a) is
correct (i.e., we'll complain about a parent link that
points to a blob). But we get most of this for free
already, because right after coercing, we'll parse any
non-blob objects. So we'd notice then if we expected a
commit and got a blob.
The one exception is when we expect a blob, in which
case we never actually read the object contents.
So this is a slight weakening, but given that the whole
point of --connectivity-only is to sacrifice some data
integrity checks for speed, this seems like an
acceptable tradeoff.
Here are before and after timings for an extreme case with
~5M reachable objects and another ~12M unreachable (it's the
torvalds/linux repository on GitHub, connected to shared
storage for all of the other kernel forks):
[before]
$ time git fsck --no-dangling --connectivity-only
real 3m4.323s
user 1m25.121s
sys 1m38.710s
[after]
$ time git fsck --no-dangling --connectivity-only
real 0m51.497s
user 0m49.575s
sys 0m1.776s
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-01-26 07:12:07 +03:00
|
|
|
|
|
|
|
if (obj->type == OBJ_NONE)
|
object: convert parse_object* to take struct object_id
Make parse_object, parse_object_or_die, and parse_object_buffer take a
pointer to struct object_id. Remove the temporary variables inserted
earlier, since they are no longer necessary. Transform all of the
callers using the following semantic patch:
@@
expression E1;
@@
- parse_object(E1.hash)
+ parse_object(&E1)
@@
expression E1;
@@
- parse_object(E1->hash)
+ parse_object(E1)
@@
expression E1, E2;
@@
- parse_object_or_die(E1.hash, E2)
+ parse_object_or_die(&E1, E2)
@@
expression E1, E2;
@@
- parse_object_or_die(E1->hash, E2)
+ parse_object_or_die(E1, E2)
@@
expression E1, E2, E3, E4, E5;
@@
- parse_object_buffer(E1.hash, E2, E3, E4, E5)
+ parse_object_buffer(&E1, E2, E3, E4, E5)
@@
expression E1, E2, E3, E4, E5;
@@
- parse_object_buffer(E1->hash, E2, E3, E4, E5)
+ parse_object_buffer(E1, E2, E3, E4, E5)
Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-07 01:10:38 +03:00
|
|
|
parse_object(&obj->oid);
|
fsck: lazily load types under --connectivity-only
The recent fixes to "fsck --connectivity-only" load all of
the objects with their correct types. This keeps the
connectivity-only code path close to the regular one, but it
also introduces some unnecessary inefficiency. While getting
the type of an object is cheap compared to actually opening
and parsing the object (as the non-connectivity-only case
would do), it's still not free.
For reachable non-blob objects, we end up having to parse
them later anyway (to see what they point to), making our
type lookup here redundant.
For unreachable objects, we might never hit them at all in
the reachability traversal, making the lookup completely
wasted. And in some cases, we might have quite a few
unreachable objects (e.g., when alternates are used for
shared object storage between repositories, it's normal for
there to be objects reachable from other repositories but
not the one running fsck).
The comment in mark_object_for_connectivity() claims two
benefits to getting the type up front:
1. We need to know the types during fsck_walk(). (And not
explicitly mentioned, but we also need them when
printing the types of broken or dangling commits).
We can address this by lazy-loading the types as
necessary. Most objects never need this lazy-load at
all, because they fall into one of these categories:
a. Reachable from our tips, and are coerced into the
correct type as we traverse (e.g., a parent link
will call lookup_commit(), which converts OBJ_NONE
to OBJ_COMMIT).
b. Unreachable, but not at the tip of a chunk of
unreachable history. We only mention the tips as
"dangling", so an unreachable commit which links
to hundreds of other objects needs only report the
type of the tip commit.
2. It serves as a cross-check that the coercion in (1a) is
correct (i.e., we'll complain about a parent link that
points to a blob). But we get most of this for free
already, because right after coercing, we'll parse any
non-blob objects. So we'd notice then if we expected a
commit and got a blob.
The one exception is when we expect a blob, in which
case we never actually read the object contents.
So this is a slight weakening, but given that the whole
point of --connectivity-only is to sacrifice some data
integrity checks for speed, this seems like an
acceptable tradeoff.
Here are before and after timings for an extreme case with
~5M reachable objects and another ~12M unreachable (it's the
torvalds/linux repository on GitHub, connected to shared
storage for all of the other kernel forks):
[before]
$ time git fsck --no-dangling --connectivity-only
real 3m4.323s
user 1m25.121s
sys 1m38.710s
[after]
$ time git fsck --no-dangling --connectivity-only
real 0m51.497s
user 0m49.575s
sys 0m1.776s
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-01-26 07:12:07 +03:00
|
|
|
|
2008-02-26 00:46:04 +03:00
|
|
|
switch (obj->type) {
|
|
|
|
case OBJ_BLOB:
|
|
|
|
return 0;
|
|
|
|
case OBJ_TREE:
|
2015-06-22 18:25:00 +03:00
|
|
|
return fsck_walk_tree((struct tree *)obj, data, options);
|
2008-02-26 00:46:04 +03:00
|
|
|
case OBJ_COMMIT:
|
2015-06-22 18:25:00 +03:00
|
|
|
return fsck_walk_commit((struct commit *)obj, data, options);
|
2008-02-26 00:46:04 +03:00
|
|
|
case OBJ_TAG:
|
2015-06-22 18:25:00 +03:00
|
|
|
return fsck_walk_tag((struct tag *)obj, data, options);
|
2008-02-26 00:46:04 +03:00
|
|
|
default:
|
2016-07-17 14:00:02 +03:00
|
|
|
error("Unknown object type for %s", describe_object(options, obj));
|
2008-02-26 00:46:04 +03:00
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
}
|
2008-02-26 00:46:08 +03:00
|
|
|
|
|
|
|
/*
|
|
|
|
* The entries in a tree are ordered in the _path_ order,
|
|
|
|
* which means that a directory entry is ordered by adding
|
|
|
|
* a slash to the end of it.
|
|
|
|
*
|
|
|
|
* So a directory called "a" is ordered _after_ a file
|
|
|
|
* called "a.c", because "a/" sorts after "a.c".
|
|
|
|
*/
|
|
|
|
#define TREE_UNORDERED (-1)
|
|
|
|
#define TREE_HAS_DUPS (-2)
|
|
|
|
|
|
|
|
static int verify_ordered(unsigned mode1, const char *name1, unsigned mode2, const char *name2)
|
|
|
|
{
|
|
|
|
int len1 = strlen(name1);
|
|
|
|
int len2 = strlen(name2);
|
|
|
|
int len = len1 < len2 ? len1 : len2;
|
|
|
|
unsigned char c1, c2;
|
|
|
|
int cmp;
|
|
|
|
|
|
|
|
cmp = memcmp(name1, name2, len);
|
|
|
|
if (cmp < 0)
|
|
|
|
return 0;
|
|
|
|
if (cmp > 0)
|
|
|
|
return TREE_UNORDERED;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Ok, the first <len> characters are the same.
|
|
|
|
* Now we need to order the next one, but turn
|
|
|
|
* a '\0' into a '/' for a directory entry.
|
|
|
|
*/
|
|
|
|
c1 = name1[len];
|
|
|
|
c2 = name2[len];
|
|
|
|
if (!c1 && !c2)
|
|
|
|
/*
|
|
|
|
* git-write-tree used to write out a nonsense tree that has
|
|
|
|
* entries with the same name, one blob and one tree. Make
|
|
|
|
* sure we do not have duplicate entries.
|
|
|
|
*/
|
|
|
|
return TREE_HAS_DUPS;
|
|
|
|
if (!c1 && S_ISDIR(mode1))
|
|
|
|
c1 = '/';
|
|
|
|
if (!c2 && S_ISDIR(mode2))
|
|
|
|
c2 = '/';
|
|
|
|
return c1 < c2 ? 0 : TREE_UNORDERED;
|
|
|
|
}
|
|
|
|
|
2015-06-22 18:25:00 +03:00
|
|
|
static int fsck_tree(struct tree *item, struct fsck_options *options)
|
2008-02-26 00:46:08 +03:00
|
|
|
{
|
2016-09-27 23:59:51 +03:00
|
|
|
int retval = 0;
|
2012-07-28 19:06:29 +04:00
|
|
|
int has_null_sha1 = 0;
|
2008-02-26 00:46:08 +03:00
|
|
|
int has_full_path = 0;
|
|
|
|
int has_empty_name = 0;
|
2012-11-28 06:27:37 +04:00
|
|
|
int has_dot = 0;
|
|
|
|
int has_dotdot = 0;
|
2012-11-29 01:35:29 +04:00
|
|
|
int has_dotgit = 0;
|
2008-02-26 00:46:08 +03:00
|
|
|
int has_zero_pad = 0;
|
|
|
|
int has_bad_modes = 0;
|
|
|
|
int has_dup_entries = 0;
|
|
|
|
int not_properly_sorted = 0;
|
|
|
|
struct tree_desc desc;
|
|
|
|
unsigned o_mode;
|
|
|
|
const char *o_name;
|
|
|
|
|
2016-09-27 23:59:51 +03:00
|
|
|
if (init_tree_desc_gently(&desc, item->buffer, item->size)) {
|
|
|
|
retval += report(options, &item->object, FSCK_MSG_BAD_TREE, "cannot be parsed as a tree");
|
|
|
|
return retval;
|
|
|
|
}
|
2008-02-26 00:46:08 +03:00
|
|
|
|
|
|
|
o_mode = 0;
|
|
|
|
o_name = NULL;
|
|
|
|
|
|
|
|
while (desc.size) {
|
|
|
|
unsigned mode;
|
|
|
|
const char *name;
|
2016-04-18 02:10:40 +03:00
|
|
|
const struct object_id *oid;
|
2008-02-26 00:46:08 +03:00
|
|
|
|
2016-04-18 02:10:40 +03:00
|
|
|
oid = tree_entry_extract(&desc, &name, &mode);
|
2008-02-26 00:46:08 +03:00
|
|
|
|
2016-04-18 02:10:40 +03:00
|
|
|
has_null_sha1 |= is_null_oid(oid);
|
2014-03-20 03:02:04 +04:00
|
|
|
has_full_path |= !!strchr(name, '/');
|
|
|
|
has_empty_name |= !*name;
|
|
|
|
has_dot |= !strcmp(name, ".");
|
|
|
|
has_dotdot |= !strcmp(name, "..");
|
2014-12-17 22:28:02 +03:00
|
|
|
has_dotgit |= (!strcmp(name, ".git") ||
|
|
|
|
is_hfs_dotgit(name) ||
|
|
|
|
is_ntfs_dotgit(name));
|
2008-02-26 00:46:08 +03:00
|
|
|
has_zero_pad |= *(char *)desc.buffer == '0';
|
2016-09-27 23:59:51 +03:00
|
|
|
if (update_tree_entry_gently(&desc)) {
|
|
|
|
retval += report(options, &item->object, FSCK_MSG_BAD_TREE, "cannot be parsed as a tree");
|
|
|
|
break;
|
|
|
|
}
|
2008-02-26 00:46:08 +03:00
|
|
|
|
|
|
|
switch (mode) {
|
|
|
|
/*
|
|
|
|
* Standard modes..
|
|
|
|
*/
|
|
|
|
case S_IFREG | 0755:
|
|
|
|
case S_IFREG | 0644:
|
|
|
|
case S_IFLNK:
|
|
|
|
case S_IFDIR:
|
|
|
|
case S_IFGITLINK:
|
|
|
|
break;
|
|
|
|
/*
|
|
|
|
* This is nonstandard, but we had a few of these
|
|
|
|
* early on when we honored the full set of mode
|
|
|
|
* bits..
|
|
|
|
*/
|
|
|
|
case S_IFREG | 0664:
|
2015-06-22 18:25:00 +03:00
|
|
|
if (!options->strict)
|
2008-02-26 00:46:08 +03:00
|
|
|
break;
|
|
|
|
default:
|
|
|
|
has_bad_modes = 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (o_name) {
|
|
|
|
switch (verify_ordered(o_mode, o_name, mode, name)) {
|
|
|
|
case TREE_UNORDERED:
|
|
|
|
not_properly_sorted = 1;
|
|
|
|
break;
|
|
|
|
case TREE_HAS_DUPS:
|
|
|
|
has_dup_entries = 1;
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
o_mode = mode;
|
|
|
|
o_name = name;
|
|
|
|
}
|
|
|
|
|
2012-07-28 19:06:29 +04:00
|
|
|
if (has_null_sha1)
|
2015-06-22 18:25:09 +03:00
|
|
|
retval += report(options, &item->object, FSCK_MSG_NULL_SHA1, "contains entries pointing to null sha1");
|
2008-02-26 00:46:08 +03:00
|
|
|
if (has_full_path)
|
2015-06-22 18:25:09 +03:00
|
|
|
retval += report(options, &item->object, FSCK_MSG_FULL_PATHNAME, "contains full pathnames");
|
2008-02-26 00:46:08 +03:00
|
|
|
if (has_empty_name)
|
2015-06-22 18:25:09 +03:00
|
|
|
retval += report(options, &item->object, FSCK_MSG_EMPTY_NAME, "contains empty pathname");
|
2012-11-28 06:27:37 +04:00
|
|
|
if (has_dot)
|
2015-06-22 18:25:09 +03:00
|
|
|
retval += report(options, &item->object, FSCK_MSG_HAS_DOT, "contains '.'");
|
2012-11-28 06:27:37 +04:00
|
|
|
if (has_dotdot)
|
2015-06-22 18:25:09 +03:00
|
|
|
retval += report(options, &item->object, FSCK_MSG_HAS_DOTDOT, "contains '..'");
|
2012-11-29 01:35:29 +04:00
|
|
|
if (has_dotgit)
|
2015-06-22 18:25:09 +03:00
|
|
|
retval += report(options, &item->object, FSCK_MSG_HAS_DOTGIT, "contains '.git'");
|
2008-02-26 00:46:08 +03:00
|
|
|
if (has_zero_pad)
|
2015-06-22 18:25:09 +03:00
|
|
|
retval += report(options, &item->object, FSCK_MSG_ZERO_PADDED_FILEMODE, "contains zero-padded file modes");
|
2008-02-26 00:46:08 +03:00
|
|
|
if (has_bad_modes)
|
2015-06-22 18:25:09 +03:00
|
|
|
retval += report(options, &item->object, FSCK_MSG_BAD_FILEMODE, "contains bad file modes");
|
2008-02-26 00:46:08 +03:00
|
|
|
if (has_dup_entries)
|
2015-06-22 18:25:09 +03:00
|
|
|
retval += report(options, &item->object, FSCK_MSG_DUPLICATE_ENTRIES, "contains duplicate file entries");
|
2008-02-26 00:46:08 +03:00
|
|
|
if (not_properly_sorted)
|
2015-06-22 18:25:09 +03:00
|
|
|
retval += report(options, &item->object, FSCK_MSG_TREE_NOT_SORTED, "not properly sorted");
|
2008-02-26 00:46:08 +03:00
|
|
|
return retval;
|
|
|
|
}
|
|
|
|
|
2015-06-28 21:18:31 +03:00
|
|
|
static int verify_headers(const void *data, unsigned long size,
|
2015-08-03 21:01:18 +03:00
|
|
|
struct object *obj, struct fsck_options *options)
|
2014-09-11 18:26:33 +04:00
|
|
|
{
|
|
|
|
const char *buffer = (const char *)data;
|
|
|
|
unsigned long i;
|
|
|
|
|
|
|
|
for (i = 0; i < size; i++) {
|
|
|
|
switch (buffer[i]) {
|
|
|
|
case '\0':
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, obj,
|
|
|
|
FSCK_MSG_NUL_IN_HEADER,
|
|
|
|
"unterminated header: NUL at offset %ld", i);
|
2014-09-11 18:26:33 +04:00
|
|
|
case '\n':
|
|
|
|
if (i + 1 < size && buffer[i + 1] == '\n')
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-06-28 21:18:31 +03:00
|
|
|
/*
|
|
|
|
* We did not find double-LF that separates the header
|
|
|
|
* and the body. Not having a body is not a crime but
|
|
|
|
* we do want to see the terminating LF for the last header
|
|
|
|
* line.
|
|
|
|
*/
|
|
|
|
if (size && buffer[size - 1] == '\n')
|
|
|
|
return 0;
|
|
|
|
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, obj,
|
|
|
|
FSCK_MSG_UNTERMINATED_HEADER, "unterminated header");
|
2014-09-11 18:26:33 +04:00
|
|
|
}
|
|
|
|
|
2015-06-22 18:25:00 +03:00
|
|
|
static int fsck_ident(const char **ident, struct object *obj, struct fsck_options *options)
|
2010-04-24 20:06:08 +04:00
|
|
|
{
|
2015-06-22 18:26:03 +03:00
|
|
|
const char *p = *ident;
|
fsck: report integer overflow in author timestamps
When we check commit objects, we complain if commit->date is
ULONG_MAX, which is an indication that we saw integer
overflow when parsing it. However, we do not do any check at
all for author lines, which also contain a timestamp.
Let's actually check the timestamps on each ident line
with strtoul. This catches both author and committer lines,
and we can get rid of the now-redundant commit->date check.
Note that like the existing check, we compare only against
ULONG_MAX. Now that we are calling strtoul at the site of
the check, we could be slightly more careful and also check
that errno is set to ERANGE. However, this will make further
refactoring in future patches a little harder, and it
doesn't really matter in practice.
For 32-bit systems, one would have to create a commit at the
exact wrong second in 2038. But by the time we get close to
that, all systems will hopefully have moved to 64-bit (and
if they haven't, they have a real problem one second later).
For 64-bit systems, by the time we get close to ULONG_MAX,
all systems will hopefully have been consumed in the fiery
wrath of our expanding Sun.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-02-24 11:39:04 +04:00
|
|
|
char *end;
|
|
|
|
|
2015-06-22 18:26:03 +03:00
|
|
|
*ident = strchrnul(*ident, '\n');
|
|
|
|
if (**ident == '\n')
|
|
|
|
(*ident)++;
|
|
|
|
|
|
|
|
if (*p == '<')
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, obj, FSCK_MSG_MISSING_NAME_BEFORE_EMAIL, "invalid author/committer line - missing space before email");
|
2015-06-22 18:26:03 +03:00
|
|
|
p += strcspn(p, "<>\n");
|
|
|
|
if (*p == '>')
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, obj, FSCK_MSG_BAD_NAME, "invalid author/committer line - bad name");
|
2015-06-22 18:26:03 +03:00
|
|
|
if (*p != '<')
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, obj, FSCK_MSG_MISSING_EMAIL, "invalid author/committer line - missing email");
|
2015-06-22 18:26:03 +03:00
|
|
|
if (p[-1] != ' ')
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, obj, FSCK_MSG_MISSING_SPACE_BEFORE_EMAIL, "invalid author/committer line - missing space before email");
|
2015-06-22 18:26:03 +03:00
|
|
|
p++;
|
|
|
|
p += strcspn(p, "<>\n");
|
|
|
|
if (*p != '>')
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, obj, FSCK_MSG_BAD_EMAIL, "invalid author/committer line - bad email");
|
2015-06-22 18:26:03 +03:00
|
|
|
p++;
|
|
|
|
if (*p != ' ')
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, obj, FSCK_MSG_MISSING_SPACE_BEFORE_DATE, "invalid author/committer line - missing space before date");
|
2015-06-22 18:26:03 +03:00
|
|
|
p++;
|
|
|
|
if (*p == '0' && p[1] != ' ')
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, obj, FSCK_MSG_ZERO_PADDED_DATE, "invalid author/committer line - zero-padded date");
|
2017-04-21 13:45:44 +03:00
|
|
|
if (date_overflows(parse_timestamp(p, &end, 10)))
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, obj, FSCK_MSG_BAD_DATE_OVERFLOW, "invalid author/committer line - date causes integer overflow");
|
2015-06-22 18:26:03 +03:00
|
|
|
if ((end == p || *end != ' '))
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, obj, FSCK_MSG_BAD_DATE, "invalid author/committer line - bad date");
|
2015-06-22 18:26:03 +03:00
|
|
|
p = end + 1;
|
|
|
|
if ((*p != '+' && *p != '-') ||
|
|
|
|
!isdigit(p[1]) ||
|
|
|
|
!isdigit(p[2]) ||
|
|
|
|
!isdigit(p[3]) ||
|
|
|
|
!isdigit(p[4]) ||
|
|
|
|
(p[5] != '\n'))
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, obj, FSCK_MSG_BAD_TIMEZONE, "invalid author/committer line - bad time zone");
|
2015-06-22 18:26:03 +03:00
|
|
|
p += 6;
|
2010-04-24 20:06:08 +04:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2014-06-11 01:41:51 +04:00
|
|
|
static int fsck_commit_buffer(struct commit *commit, const char *buffer,
|
2015-06-22 18:25:00 +03:00
|
|
|
unsigned long size, struct fsck_options *options)
|
2008-02-26 00:46:08 +03:00
|
|
|
{
|
|
|
|
unsigned char tree_sha1[20], sha1[20];
|
|
|
|
struct commit_graft *graft;
|
2015-06-22 18:26:23 +03:00
|
|
|
unsigned parent_count, parent_line_count = 0, author_count;
|
2010-04-24 20:06:08 +04:00
|
|
|
int err;
|
2016-04-14 20:58:22 +03:00
|
|
|
const char *buffer_begin = buffer;
|
2008-02-26 00:46:08 +03:00
|
|
|
|
2015-08-03 21:01:18 +03:00
|
|
|
if (verify_headers(buffer, size, &commit->object, options))
|
2014-09-11 18:26:33 +04:00
|
|
|
return -1;
|
|
|
|
|
refactor skip_prefix to return a boolean
The skip_prefix() function returns a pointer to the content
past the prefix, or NULL if the prefix was not found. While
this is nice and simple, in practice it makes it hard to use
for two reasons:
1. When you want to conditionally skip or keep the string
as-is, you have to introduce a temporary variable.
For example:
tmp = skip_prefix(buf, "foo");
if (tmp)
buf = tmp;
2. It is verbose to check the outcome in a conditional, as
you need extra parentheses to silence compiler
warnings. For example:
if ((cp = skip_prefix(buf, "foo"))
/* do something with cp */
Both of these make it harder to use for long if-chains, and
we tend to use starts_with() instead. However, the first line
of "do something" is often to then skip forward in buf past
the prefix, either using a magic constant or with an extra
strlen(3) (which is generally computed at compile time, but
means we are repeating ourselves).
This patch refactors skip_prefix() to return a simple boolean,
and to provide the pointer value as an out-parameter. If the
prefix is not found, the out-parameter is untouched. This
lets you write:
if (skip_prefix(arg, "foo ", &arg))
do_foo(arg);
else if (skip_prefix(arg, "bar ", &arg))
do_bar(arg);
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-06-18 23:44:19 +04:00
|
|
|
if (!skip_prefix(buffer, "tree ", &buffer))
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, &commit->object, FSCK_MSG_MISSING_TREE, "invalid format - expected 'tree' line");
|
2015-06-22 18:26:11 +03:00
|
|
|
if (get_sha1_hex(buffer, tree_sha1) || buffer[40] != '\n') {
|
|
|
|
err = report(options, &commit->object, FSCK_MSG_BAD_TREE_SHA1, "invalid 'tree' line format - bad sha1");
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
}
|
2014-03-13 08:45:51 +04:00
|
|
|
buffer += 41;
|
refactor skip_prefix to return a boolean
The skip_prefix() function returns a pointer to the content
past the prefix, or NULL if the prefix was not found. While
this is nice and simple, in practice it makes it hard to use
for two reasons:
1. When you want to conditionally skip or keep the string
as-is, you have to introduce a temporary variable.
For example:
tmp = skip_prefix(buf, "foo");
if (tmp)
buf = tmp;
2. It is verbose to check the outcome in a conditional, as
you need extra parentheses to silence compiler
warnings. For example:
if ((cp = skip_prefix(buf, "foo"))
/* do something with cp */
Both of these make it harder to use for long if-chains, and
we tend to use starts_with() instead. However, the first line
of "do something" is often to then skip forward in buf past
the prefix, either using a magic constant or with an extra
strlen(3) (which is generally computed at compile time, but
means we are repeating ourselves).
This patch refactors skip_prefix() to return a simple boolean,
and to provide the pointer value as an out-parameter. If the
prefix is not found, the out-parameter is untouched. This
lets you write:
if (skip_prefix(arg, "foo ", &arg))
do_foo(arg);
else if (skip_prefix(arg, "bar ", &arg))
do_bar(arg);
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-06-18 23:44:19 +04:00
|
|
|
while (skip_prefix(buffer, "parent ", &buffer)) {
|
2015-06-22 18:26:11 +03:00
|
|
|
if (get_sha1_hex(buffer, sha1) || buffer[40] != '\n') {
|
|
|
|
err = report(options, &commit->object, FSCK_MSG_BAD_PARENT_SHA1, "invalid 'parent' line format - bad sha1");
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
}
|
2014-03-13 08:45:51 +04:00
|
|
|
buffer += 41;
|
2014-07-10 13:48:26 +04:00
|
|
|
parent_line_count++;
|
2008-02-26 00:46:08 +03:00
|
|
|
}
|
2017-07-13 03:44:14 +03:00
|
|
|
graft = lookup_commit_graft(&commit->object.oid);
|
2014-07-10 13:48:26 +04:00
|
|
|
parent_count = commit_list_count(commit->parents);
|
2008-02-26 00:46:08 +03:00
|
|
|
if (graft) {
|
2014-07-10 13:48:26 +04:00
|
|
|
if (graft->nr_parent == -1 && !parent_count)
|
2008-02-26 00:46:08 +03:00
|
|
|
; /* shallow commit */
|
2015-06-22 18:26:11 +03:00
|
|
|
else if (graft->nr_parent != parent_count) {
|
|
|
|
err = report(options, &commit->object, FSCK_MSG_MISSING_GRAFT, "graft objects missing");
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
}
|
2008-02-26 00:46:08 +03:00
|
|
|
} else {
|
2015-06-22 18:26:11 +03:00
|
|
|
if (parent_count != parent_line_count) {
|
|
|
|
err = report(options, &commit->object, FSCK_MSG_MISSING_PARENT, "parent objects missing");
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
}
|
2008-02-26 00:46:08 +03:00
|
|
|
}
|
2015-06-22 18:26:23 +03:00
|
|
|
author_count = 0;
|
|
|
|
while (skip_prefix(buffer, "author ", &buffer)) {
|
|
|
|
author_count++;
|
|
|
|
err = fsck_ident(&buffer, &commit->object, options);
|
|
|
|
if (err)
|
|
|
|
return err;
|
2008-02-26 00:46:08 +03:00
|
|
|
}
|
2015-06-22 18:26:23 +03:00
|
|
|
if (author_count < 1)
|
|
|
|
err = report(options, &commit->object, FSCK_MSG_MISSING_AUTHOR, "invalid format - expected 'author' line");
|
|
|
|
else if (author_count > 1)
|
|
|
|
err = report(options, &commit->object, FSCK_MSG_MULTIPLE_AUTHORS, "invalid format - multiple 'author' lines");
|
2010-04-24 20:06:08 +04:00
|
|
|
if (err)
|
|
|
|
return err;
|
refactor skip_prefix to return a boolean
The skip_prefix() function returns a pointer to the content
past the prefix, or NULL if the prefix was not found. While
this is nice and simple, in practice it makes it hard to use
for two reasons:
1. When you want to conditionally skip or keep the string
as-is, you have to introduce a temporary variable.
For example:
tmp = skip_prefix(buf, "foo");
if (tmp)
buf = tmp;
2. It is verbose to check the outcome in a conditional, as
you need extra parentheses to silence compiler
warnings. For example:
if ((cp = skip_prefix(buf, "foo"))
/* do something with cp */
Both of these make it harder to use for long if-chains, and
we tend to use starts_with() instead. However, the first line
of "do something" is often to then skip forward in buf past
the prefix, either using a magic constant or with an extra
strlen(3) (which is generally computed at compile time, but
means we are repeating ourselves).
This patch refactors skip_prefix() to return a simple boolean,
and to provide the pointer value as an out-parameter. If the
prefix is not found, the out-parameter is untouched. This
lets you write:
if (skip_prefix(arg, "foo ", &arg))
do_foo(arg);
else if (skip_prefix(arg, "bar ", &arg))
do_bar(arg);
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-06-18 23:44:19 +04:00
|
|
|
if (!skip_prefix(buffer, "committer ", &buffer))
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, &commit->object, FSCK_MSG_MISSING_COMMITTER, "invalid format - expected 'committer' line");
|
2015-06-22 18:25:00 +03:00
|
|
|
err = fsck_ident(&buffer, &commit->object, options);
|
2010-04-24 20:06:08 +04:00
|
|
|
if (err)
|
|
|
|
return err;
|
2016-04-14 20:18:11 +03:00
|
|
|
if (!commit->tree) {
|
|
|
|
err = report(options, &commit->object, FSCK_MSG_BAD_TREE, "could not load commit's tree %s", sha1_to_hex(tree_sha1));
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
}
|
2016-04-14 20:58:22 +03:00
|
|
|
if (memchr(buffer_begin, '\0', size)) {
|
|
|
|
err = report(options, &commit->object, FSCK_MSG_NUL_IN_COMMIT,
|
|
|
|
"NUL byte in the commit object body");
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
}
|
2008-02-26 00:46:08 +03:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2014-09-10 17:52:51 +04:00
|
|
|
static int fsck_commit(struct commit *commit, const char *data,
|
2015-06-22 18:25:00 +03:00
|
|
|
unsigned long size, struct fsck_options *options)
|
2014-06-11 01:41:51 +04:00
|
|
|
{
|
2014-09-10 17:52:51 +04:00
|
|
|
const char *buffer = data ? data : get_commit_buffer(commit, &size);
|
2015-06-22 18:25:00 +03:00
|
|
|
int ret = fsck_commit_buffer(commit, buffer, size, options);
|
2014-09-10 17:52:51 +04:00
|
|
|
if (!data)
|
|
|
|
unuse_commit_buffer(commit, buffer);
|
2014-06-11 01:41:51 +04:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2014-09-11 18:26:38 +04:00
|
|
|
static int fsck_tag_buffer(struct tag *tag, const char *data,
|
2015-06-22 18:25:00 +03:00
|
|
|
unsigned long size, struct fsck_options *options)
|
2014-09-11 18:26:38 +04:00
|
|
|
{
|
|
|
|
unsigned char sha1[20];
|
|
|
|
int ret = 0;
|
|
|
|
const char *buffer;
|
|
|
|
char *to_free = NULL, *eol;
|
|
|
|
struct strbuf sb = STRBUF_INIT;
|
|
|
|
|
|
|
|
if (data)
|
|
|
|
buffer = data;
|
|
|
|
else {
|
|
|
|
enum object_type type;
|
|
|
|
|
|
|
|
buffer = to_free =
|
2015-11-10 05:22:29 +03:00
|
|
|
read_sha1_file(tag->object.oid.hash, &type, &size);
|
2014-09-11 18:26:38 +04:00
|
|
|
if (!buffer)
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, &tag->object,
|
|
|
|
FSCK_MSG_MISSING_TAG_OBJECT,
|
2014-09-11 18:26:38 +04:00
|
|
|
"cannot read tag object");
|
|
|
|
|
|
|
|
if (type != OBJ_TAG) {
|
2015-06-22 18:25:09 +03:00
|
|
|
ret = report(options, &tag->object,
|
|
|
|
FSCK_MSG_TAG_OBJECT_NOT_TAG,
|
2014-09-11 18:26:38 +04:00
|
|
|
"expected tag got %s",
|
|
|
|
typename(type));
|
|
|
|
goto done;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-11-19 19:25:31 +03:00
|
|
|
ret = verify_headers(buffer, size, &tag->object, options);
|
|
|
|
if (ret)
|
2014-09-11 18:26:38 +04:00
|
|
|
goto done;
|
|
|
|
|
|
|
|
if (!skip_prefix(buffer, "object ", &buffer)) {
|
2015-06-22 18:25:09 +03:00
|
|
|
ret = report(options, &tag->object, FSCK_MSG_MISSING_OBJECT, "invalid format - expected 'object' line");
|
2014-09-11 18:26:38 +04:00
|
|
|
goto done;
|
|
|
|
}
|
|
|
|
if (get_sha1_hex(buffer, sha1) || buffer[40] != '\n') {
|
2015-06-22 18:25:09 +03:00
|
|
|
ret = report(options, &tag->object, FSCK_MSG_BAD_OBJECT_SHA1, "invalid 'object' line format - bad sha1");
|
2015-06-22 18:26:30 +03:00
|
|
|
if (ret)
|
|
|
|
goto done;
|
2014-09-11 18:26:38 +04:00
|
|
|
}
|
|
|
|
buffer += 41;
|
|
|
|
|
|
|
|
if (!skip_prefix(buffer, "type ", &buffer)) {
|
2015-06-22 18:25:09 +03:00
|
|
|
ret = report(options, &tag->object, FSCK_MSG_MISSING_TYPE_ENTRY, "invalid format - expected 'type' line");
|
2014-09-11 18:26:38 +04:00
|
|
|
goto done;
|
|
|
|
}
|
|
|
|
eol = strchr(buffer, '\n');
|
|
|
|
if (!eol) {
|
2015-06-22 18:25:09 +03:00
|
|
|
ret = report(options, &tag->object, FSCK_MSG_MISSING_TYPE, "invalid format - unexpected end after 'type' line");
|
2014-09-11 18:26:38 +04:00
|
|
|
goto done;
|
|
|
|
}
|
|
|
|
if (type_from_string_gently(buffer, eol - buffer, 1) < 0)
|
2015-06-22 18:25:09 +03:00
|
|
|
ret = report(options, &tag->object, FSCK_MSG_BAD_TYPE, "invalid 'type' value");
|
2014-09-11 18:26:38 +04:00
|
|
|
if (ret)
|
|
|
|
goto done;
|
|
|
|
buffer = eol + 1;
|
|
|
|
|
|
|
|
if (!skip_prefix(buffer, "tag ", &buffer)) {
|
2015-06-22 18:25:09 +03:00
|
|
|
ret = report(options, &tag->object, FSCK_MSG_MISSING_TAG_ENTRY, "invalid format - expected 'tag' line");
|
2014-09-11 18:26:38 +04:00
|
|
|
goto done;
|
|
|
|
}
|
|
|
|
eol = strchr(buffer, '\n');
|
|
|
|
if (!eol) {
|
2015-06-22 18:25:09 +03:00
|
|
|
ret = report(options, &tag->object, FSCK_MSG_MISSING_TAG, "invalid format - unexpected end after 'type' line");
|
2014-09-11 18:26:38 +04:00
|
|
|
goto done;
|
|
|
|
}
|
|
|
|
strbuf_addf(&sb, "refs/tags/%.*s", (int)(eol - buffer), buffer);
|
2015-06-22 18:26:54 +03:00
|
|
|
if (check_refname_format(sb.buf, 0)) {
|
|
|
|
ret = report(options, &tag->object, FSCK_MSG_BAD_TAG_NAME,
|
2015-06-22 18:25:09 +03:00
|
|
|
"invalid 'tag' name: %.*s",
|
2014-12-08 08:48:13 +03:00
|
|
|
(int)(eol - buffer), buffer);
|
2015-06-22 18:26:54 +03:00
|
|
|
if (ret)
|
|
|
|
goto done;
|
|
|
|
}
|
2014-09-11 18:26:38 +04:00
|
|
|
buffer = eol + 1;
|
|
|
|
|
2015-06-22 18:26:54 +03:00
|
|
|
if (!skip_prefix(buffer, "tagger ", &buffer)) {
|
2014-09-11 18:26:38 +04:00
|
|
|
/* early tags do not contain 'tagger' lines; warn only */
|
2015-06-22 18:26:54 +03:00
|
|
|
ret = report(options, &tag->object, FSCK_MSG_MISSING_TAGGER_ENTRY, "invalid format - expected 'tagger' line");
|
|
|
|
if (ret)
|
|
|
|
goto done;
|
|
|
|
}
|
2014-09-11 18:26:38 +04:00
|
|
|
else
|
2015-06-22 18:25:00 +03:00
|
|
|
ret = fsck_ident(&buffer, &tag->object, options);
|
2014-09-11 18:26:38 +04:00
|
|
|
|
|
|
|
done:
|
|
|
|
strbuf_release(&sb);
|
|
|
|
free(to_free);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2014-09-10 17:52:51 +04:00
|
|
|
static int fsck_tag(struct tag *tag, const char *data,
|
2015-06-22 18:25:00 +03:00
|
|
|
unsigned long size, struct fsck_options *options)
|
2008-02-26 00:46:08 +03:00
|
|
|
{
|
|
|
|
struct object *tagged = tag->tagged;
|
|
|
|
|
|
|
|
if (!tagged)
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, &tag->object, FSCK_MSG_BAD_TAG_OBJECT, "could not load tagged object");
|
2014-09-11 18:26:38 +04:00
|
|
|
|
2015-06-22 18:25:00 +03:00
|
|
|
return fsck_tag_buffer(tag, data, size, options);
|
2008-02-26 00:46:08 +03:00
|
|
|
}
|
|
|
|
|
2014-09-10 17:52:51 +04:00
|
|
|
int fsck_object(struct object *obj, void *data, unsigned long size,
|
2015-06-22 18:25:00 +03:00
|
|
|
struct fsck_options *options)
|
2008-02-26 00:46:08 +03:00
|
|
|
{
|
|
|
|
if (!obj)
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, obj, FSCK_MSG_BAD_OBJECT_SHA1, "no valid object to fsck");
|
2008-02-26 00:46:08 +03:00
|
|
|
|
|
|
|
if (obj->type == OBJ_BLOB)
|
|
|
|
return 0;
|
|
|
|
if (obj->type == OBJ_TREE)
|
2015-06-22 18:25:00 +03:00
|
|
|
return fsck_tree((struct tree *) obj, options);
|
2008-02-26 00:46:08 +03:00
|
|
|
if (obj->type == OBJ_COMMIT)
|
2014-09-10 17:52:51 +04:00
|
|
|
return fsck_commit((struct commit *) obj, (const char *) data,
|
2015-06-22 18:25:00 +03:00
|
|
|
size, options);
|
2008-02-26 00:46:08 +03:00
|
|
|
if (obj->type == OBJ_TAG)
|
2014-09-10 17:52:51 +04:00
|
|
|
return fsck_tag((struct tag *) obj, (const char *) data,
|
2015-06-22 18:25:00 +03:00
|
|
|
size, options);
|
2008-02-26 00:46:08 +03:00
|
|
|
|
2015-06-22 18:25:09 +03:00
|
|
|
return report(options, obj, FSCK_MSG_UNKNOWN_TYPE, "unknown type '%d' (internal fsck error)",
|
2008-02-26 00:46:08 +03:00
|
|
|
obj->type);
|
|
|
|
}
|
2008-02-26 00:46:09 +03:00
|
|
|
|
2016-07-17 13:59:57 +03:00
|
|
|
int fsck_error_function(struct fsck_options *o,
|
|
|
|
struct object *obj, int msg_type, const char *message)
|
2008-02-26 00:46:09 +03:00
|
|
|
{
|
2015-06-22 18:25:25 +03:00
|
|
|
if (msg_type == FSCK_WARN) {
|
2016-07-17 14:00:02 +03:00
|
|
|
warning("object %s: %s", describe_object(o, obj), message);
|
2015-06-22 18:25:25 +03:00
|
|
|
return 0;
|
|
|
|
}
|
2016-07-17 14:00:02 +03:00
|
|
|
error("object %s: %s", describe_object(o, obj), message);
|
2008-02-26 00:46:09 +03:00
|
|
|
return 1;
|
|
|
|
}
|