#include "streaming.h"
#include "thread-utils.h"
#include "packfile.h"
+#include "object-store.h"
static const char index_pack_usage[] =
"git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
int pack_fd;
};
+/* Remember to update object flag allocation in object.h */
#define FLAG_LINK (1u<<20)
#define FLAG_CHECKED (1u<<21)
};
struct ref_delta_entry {
- unsigned char sha1[20];
+ struct object_id oid;
int obj_no;
};
static off_t consumed_bytes;
static off_t max_input_size;
static unsigned deepest_delta;
-static git_SHA_CTX input_ctx;
+static git_hash_ctx input_ctx;
static uint32_t input_crc32;
static int input_fd, output_fd;
static const char *curr_pack;
if (!(obj->flags & FLAG_CHECKED)) {
unsigned long size;
- int type = sha1_object_info(obj->oid.hash, &size);
+ int type = oid_object_info(&obj->oid, &size);
if (type <= 0)
die(_("did not receive expected object %s"),
oid_to_hex(&obj->oid));
if (type != obj->type)
die(_("object %s: expected type %s, found %s"),
oid_to_hex(&obj->oid),
- typename(obj->type), typename(type));
+ type_name(obj->type), type_name(type));
obj->flags |= FLAG_CHECKED;
return 1;
}
if (input_offset) {
if (output_fd >= 0)
write_or_die(output_fd, input_buffer, input_offset);
- git_SHA1_Update(&input_ctx, input_buffer, input_offset);
+ the_hash_algo->update_fn(&input_ctx, input_buffer, input_offset);
memmove(input_buffer, input_buffer + input_offset, input_len);
input_offset = 0;
}
output_fd = -1;
nothread_data.pack_fd = input_fd;
}
- git_SHA1_Init(&input_ctx);
+ the_hash_algo->init_fn(&input_ctx);
return pack_name;
}
}
static void *unpack_entry_data(off_t offset, unsigned long size,
- enum object_type type, unsigned char *sha1)
+ enum object_type type, struct object_id *oid)
{
static char fixed_buf[8192];
int status;
git_zstream stream;
void *buf;
- git_SHA_CTX c;
+ git_hash_ctx c;
char hdr[32];
int hdrlen;
if (!is_delta_type(type)) {
- hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %lu", typename(type), size) + 1;
- git_SHA1_Init(&c);
- git_SHA1_Update(&c, hdr, hdrlen);
+ hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %lu", type_name(type), size) + 1;
+ the_hash_algo->init_fn(&c);
+ the_hash_algo->update_fn(&c, hdr, hdrlen);
} else
- sha1 = NULL;
+ oid = NULL;
if (type == OBJ_BLOB && size > big_file_threshold)
buf = fixed_buf;
else
stream.avail_in = input_len;
status = git_inflate(&stream, 0);
use(input_len - stream.avail_in);
- if (sha1)
- git_SHA1_Update(&c, last_out, stream.next_out - last_out);
+ if (oid)
+ the_hash_algo->update_fn(&c, last_out, stream.next_out - last_out);
if (buf == fixed_buf) {
stream.next_out = buf;
stream.avail_out = sizeof(fixed_buf);
if (stream.total_out != size || status != Z_STREAM_END)
bad_object(offset, _("inflate returned %d"), status);
git_inflate_end(&stream);
- if (sha1)
- git_SHA1_Final(sha1, &c);
+ if (oid)
+ the_hash_algo->final_fn(oid->hash, &c);
return buf == fixed_buf ? NULL : buf;
}
static void *unpack_raw_entry(struct object_entry *obj,
off_t *ofs_offset,
- unsigned char *ref_sha1,
- unsigned char *sha1)
+ struct object_id *ref_oid,
+ struct object_id *oid)
{
unsigned char *p;
unsigned long size, c;
switch (obj->type) {
case OBJ_REF_DELTA:
- hashcpy(ref_sha1, fill(20));
- use(20);
+ hashcpy(ref_oid->hash, fill(the_hash_algo->rawsz));
+ use(the_hash_algo->rawsz);
break;
case OBJ_OFS_DELTA:
p = fill(1);
}
obj->hdr_size = consumed_bytes - obj->idx.offset;
- data = unpack_entry_data(obj->idx.offset, obj->size, obj->type, sha1);
+ data = unpack_entry_data(obj->idx.offset, obj->size, obj->type, oid);
obj->idx.crc32 = input_crc32;
return data;
}
*last_index = last;
}
-static int compare_ref_delta_bases(const unsigned char *sha1,
- const unsigned char *sha2,
+static int compare_ref_delta_bases(const struct object_id *oid1,
+ const struct object_id *oid2,
enum object_type type1,
enum object_type type2)
{
int cmp = type1 - type2;
if (cmp)
return cmp;
- return hashcmp(sha1, sha2);
+ return oidcmp(oid1, oid2);
}
-static int find_ref_delta(const unsigned char *sha1, enum object_type type)
+static int find_ref_delta(const struct object_id *oid, enum object_type type)
{
int first = 0, last = nr_ref_deltas;
struct ref_delta_entry *delta = &ref_deltas[next];
int cmp;
- cmp = compare_ref_delta_bases(sha1, delta->sha1,
+ cmp = compare_ref_delta_bases(oid, &delta->oid,
type, objects[delta->obj_no].type);
if (!cmp)
return next;
return -first-1;
}
-static void find_ref_delta_children(const unsigned char *sha1,
+static void find_ref_delta_children(const struct object_id *oid,
int *first_index, int *last_index,
enum object_type type)
{
- int first = find_ref_delta(sha1, type);
+ int first = find_ref_delta(oid, type);
int last = first;
int end = nr_ref_deltas - 1;
*last_index = -1;
return;
}
- while (first > 0 && !hashcmp(ref_deltas[first - 1].sha1, sha1))
+ while (first > 0 && !oidcmp(&ref_deltas[first - 1].oid, oid))
--first;
- while (last < end && !hashcmp(ref_deltas[last + 1].sha1, sha1))
+ while (last < end && !oidcmp(&ref_deltas[last + 1].oid, oid))
++last;
*first_index = first;
*last_index = last;
memset(&data, 0, sizeof(data));
data.entry = entry;
- data.st = open_istream(entry->idx.oid.hash, &type, &size, NULL);
+ data.st = open_istream(&entry->idx.oid, &type, &size, NULL);
if (!data.st)
return -1;
if (size != entry->size || type != entry->type)
enum object_type has_type;
unsigned long has_size;
read_lock();
- has_type = sha1_object_info(oid->hash, &has_size);
+ has_type = oid_object_info(oid, &has_size);
if (has_type < 0)
die(_("cannot read existing object info %s"), oid_to_hex(oid));
if (has_type != type || has_size != size)
die(_("SHA1 COLLISION FOUND WITH %s !"), oid_to_hex(oid));
- has_data = read_sha1_file(oid->hash, &has_type, &has_size);
+ has_data = read_object_file(oid, &has_type, &has_size);
read_unlock();
if (!data)
data = new_data = get_data_from_pack(obj_entry);
free(has_data);
}
- if (strict) {
+ if (strict || do_fsck_object) {
read_lock();
if (type == OBJ_BLOB) {
struct blob *blob = lookup_blob(oid);
obj = parse_object_buffer(oid, type, size, buf,
&eaten);
if (!obj)
- die(_("invalid %s"), typename(type));
+ die(_("invalid %s"), type_name(type));
if (do_fsck_object &&
fsck_object(obj, buf, size, &fsck_options))
die(_("Error in object"));
- if (fsck_walk(obj, NULL, &fsck_options))
+ if (strict && fsck_walk(obj, NULL, &fsck_options))
die(_("Not all child objects of %s are reachable"), oid_to_hex(&obj->oid));
if (obj->type == OBJ_TREE) {
free(delta_data);
if (!result->data)
bad_object(delta_obj->idx.offset, _("failed to apply delta"));
- hash_sha1_file(result->data, result->size,
- typename(delta_obj->real_type),
- delta_obj->idx.oid.hash);
+ hash_object_file(result->data, result->size,
+ type_name(delta_obj->real_type), &delta_obj->idx.oid);
sha1_object(result->data, NULL, result->size, delta_obj->real_type,
&delta_obj->idx.oid);
counter_lock();
struct base_data *prev_base)
{
if (base->ref_last == -1 && base->ofs_last == -1) {
- find_ref_delta_children(base->obj->idx.oid.hash,
+ find_ref_delta_children(&base->obj->idx.oid,
&base->ref_first, &base->ref_last,
OBJ_REF_DELTA);
const struct ref_delta_entry *delta_a = a;
const struct ref_delta_entry *delta_b = b;
- return hashcmp(delta_a->sha1, delta_b->sha1);
+ return oidcmp(&delta_a->oid, &delta_b->oid);
}
static void resolve_base(struct object_entry *obj)
* - calculate SHA1 of all non-delta objects;
* - remember base (SHA1 or offset) for all deltas.
*/
-static void parse_pack_objects(unsigned char *sha1)
+static void parse_pack_objects(unsigned char *hash)
{
int i, nr_delays = 0;
struct ofs_delta_entry *ofs_delta = ofs_deltas;
- unsigned char ref_delta_sha1[20];
+ struct object_id ref_delta_oid;
struct stat st;
if (verbose)
for (i = 0; i < nr_objects; i++) {
struct object_entry *obj = &objects[i];
void *data = unpack_raw_entry(obj, &ofs_delta->offset,
- ref_delta_sha1,
- obj->idx.oid.hash);
+ &ref_delta_oid,
+ &obj->idx.oid);
obj->real_type = obj->type;
if (obj->type == OBJ_OFS_DELTA) {
nr_ofs_deltas++;
ofs_delta++;
} else if (obj->type == OBJ_REF_DELTA) {
ALLOC_GROW(ref_deltas, nr_ref_deltas + 1, ref_deltas_alloc);
- hashcpy(ref_deltas[nr_ref_deltas].sha1, ref_delta_sha1);
+ oidcpy(&ref_deltas[nr_ref_deltas].oid, &ref_delta_oid);
ref_deltas[nr_ref_deltas].obj_no = i;
nr_ref_deltas++;
} else if (!data) {
/* Check pack integrity */
flush();
- git_SHA1_Final(sha1, &input_ctx);
- if (hashcmp(fill(20), sha1))
+ the_hash_algo->final_fn(hash, &input_ctx);
+ if (hashcmp(fill(the_hash_algo->rawsz), hash))
die(_("pack is corrupted (SHA1 mismatch)"));
- use(20);
+ use(the_hash_algo->rawsz);
/* If input_fd is a file, we should have reached its end now. */
if (fstat(input_fd, &st))
/*
* Third pass:
* - append objects to convert thin pack to full pack if required
- * - write the final 20-byte SHA-1
+ * - write the final pack hash
*/
-static void fix_unresolved_deltas(struct sha1file *f);
-static void conclude_pack(int fix_thin_pack, const char *curr_pack, unsigned char *pack_sha1)
+static void fix_unresolved_deltas(struct hashfile *f);
+static void conclude_pack(int fix_thin_pack, const char *curr_pack, unsigned char *pack_hash)
{
if (nr_ref_deltas + nr_ofs_deltas == nr_resolved_deltas) {
stop_progress(&progress);
- /* Flush remaining pack final 20-byte SHA1. */
+ /* Flush remaining pack final hash. */
flush();
return;
}
if (fix_thin_pack) {
- struct sha1file *f;
- unsigned char read_sha1[20], tail_sha1[20];
+ struct hashfile *f;
+ unsigned char read_hash[GIT_MAX_RAWSZ], tail_hash[GIT_MAX_RAWSZ];
struct strbuf msg = STRBUF_INIT;
int nr_unresolved = nr_ofs_deltas + nr_ref_deltas - nr_resolved_deltas;
int nr_objects_initial = nr_objects;
REALLOC_ARRAY(objects, nr_objects + nr_unresolved + 1);
memset(objects + nr_objects + 1, 0,
nr_unresolved * sizeof(*objects));
- f = sha1fd(output_fd, curr_pack);
+ f = hashfd(output_fd, curr_pack);
fix_unresolved_deltas(f);
strbuf_addf(&msg, Q_("completed with %d local object",
"completed with %d local objects",
nr_objects - nr_objects_initial);
stop_progress_msg(&progress, msg.buf);
strbuf_release(&msg);
- sha1close(f, tail_sha1, 0);
- hashcpy(read_sha1, pack_sha1);
- fixup_pack_header_footer(output_fd, pack_sha1,
+ hashclose(f, tail_hash, 0);
+ hashcpy(read_hash, pack_hash);
+ fixup_pack_header_footer(output_fd, pack_hash,
curr_pack, nr_objects,
- read_sha1, consumed_bytes-20);
- if (hashcmp(read_sha1, tail_sha1) != 0)
+ read_hash, consumed_bytes-the_hash_algo->rawsz);
+ if (hashcmp(read_hash, tail_hash) != 0)
die(_("Unexpected tail checksum for %s "
"(disk corruption?)"), curr_pack);
}
nr_ofs_deltas + nr_ref_deltas - nr_resolved_deltas);
}
-static int write_compressed(struct sha1file *f, void *in, unsigned int size)
+static int write_compressed(struct hashfile *f, void *in, unsigned int size)
{
git_zstream stream;
int status;
stream.next_out = outbuf;
stream.avail_out = sizeof(outbuf);
status = git_deflate(&stream, Z_FINISH);
- sha1write(f, outbuf, sizeof(outbuf) - stream.avail_out);
+ hashwrite(f, outbuf, sizeof(outbuf) - stream.avail_out);
} while (status == Z_OK);
if (status != Z_STREAM_END)
return size;
}
-static struct object_entry *append_obj_to_pack(struct sha1file *f,
+static struct object_entry *append_obj_to_pack(struct hashfile *f,
const unsigned char *sha1, void *buf,
unsigned long size, enum object_type type)
{
}
header[n++] = c;
crc32_begin(f);
- sha1write(f, header, n);
+ hashwrite(f, header, n);
obj[0].size = size;
obj[0].hdr_size = n;
obj[0].type = type;
obj[1].idx.offset = obj[0].idx.offset + n;
obj[1].idx.offset += write_compressed(f, buf, size);
obj[0].idx.crc32 = crc32_end(f);
- sha1flush(f);
+ hashflush(f);
hashcpy(obj->idx.oid.hash, sha1);
return obj;
}
return a->obj_no - b->obj_no;
}
-static void fix_unresolved_deltas(struct sha1file *f)
+static void fix_unresolved_deltas(struct hashfile *f)
{
struct ref_delta_entry **sorted_by_pos;
int i;
if (objects[d->obj_no].real_type != OBJ_REF_DELTA)
continue;
- base_obj->data = read_sha1_file(d->sha1, &type, &base_obj->size);
+ base_obj->data = read_object_file(&d->oid, &type,
+ &base_obj->size);
if (!base_obj->data)
continue;
- if (check_sha1_signature(d->sha1, base_obj->data,
- base_obj->size, typename(type)))
- die(_("local object %s is corrupt"), sha1_to_hex(d->sha1));
- base_obj->obj = append_obj_to_pack(f, d->sha1,
+ if (check_object_signature(&d->oid, base_obj->data,
+ base_obj->size, type_name(type)))
+ die(_("local object %s is corrupt"), oid_to_hex(&d->oid));
+ base_obj->obj = append_obj_to_pack(f, d->oid.hash,
base_obj->data, base_obj->size, type);
find_unresolved_deltas(base_obj);
display_progress(progress, nr_resolved_deltas);
free(sorted_by_pos);
}
+static const char *derive_filename(const char *pack_name, const char *suffix,
+ struct strbuf *buf)
+{
+ size_t len;
+ if (!strip_suffix(pack_name, ".pack", &len))
+ die(_("packfile name '%s' does not end with '.pack'"),
+ pack_name);
+ strbuf_add(buf, pack_name, len);
+ strbuf_addch(buf, '.');
+ strbuf_addstr(buf, suffix);
+ return buf->buf;
+}
+
+static void write_special_file(const char *suffix, const char *msg,
+ const char *pack_name, const unsigned char *hash,
+ const char **report)
+{
+ struct strbuf name_buf = STRBUF_INIT;
+ const char *filename;
+ int fd;
+ int msg_len = strlen(msg);
+
+ if (pack_name)
+ filename = derive_filename(pack_name, suffix, &name_buf);
+ else
+ filename = odb_pack_name(&name_buf, hash, suffix);
+
+ fd = odb_pack_keep(filename);
+ if (fd < 0) {
+ if (errno != EEXIST)
+ die_errno(_("cannot write %s file '%s'"),
+ suffix, filename);
+ } else {
+ if (msg_len > 0) {
+ write_or_die(fd, msg, msg_len);
+ write_or_die(fd, "\n", 1);
+ }
+ if (close(fd) != 0)
+ die_errno(_("cannot close written %s file '%s'"),
+ suffix, filename);
+ if (report)
+ *report = suffix;
+ }
+ strbuf_release(&name_buf);
+}
+
static void final(const char *final_pack_name, const char *curr_pack_name,
const char *final_index_name, const char *curr_index_name,
- const char *keep_name, const char *keep_msg,
- unsigned char *sha1)
+ const char *keep_msg, const char *promisor_msg,
+ unsigned char *hash)
{
const char *report = "pack";
struct strbuf pack_name = STRBUF_INIT;
struct strbuf index_name = STRBUF_INIT;
- struct strbuf keep_name_buf = STRBUF_INIT;
int err;
if (!from_stdin) {
die_errno(_("error while closing pack file"));
}
- if (keep_msg) {
- int keep_fd, keep_msg_len = strlen(keep_msg);
-
- if (!keep_name)
- keep_name = odb_pack_name(&keep_name_buf, sha1, "keep");
-
- keep_fd = odb_pack_keep(keep_name);
- if (keep_fd < 0) {
- if (errno != EEXIST)
- die_errno(_("cannot write keep file '%s'"),
- keep_name);
- } else {
- if (keep_msg_len > 0) {
- write_or_die(keep_fd, keep_msg, keep_msg_len);
- write_or_die(keep_fd, "\n", 1);
- }
- if (close(keep_fd) != 0)
- die_errno(_("cannot close written keep file '%s'"),
- keep_name);
- report = "keep";
- }
- }
+ if (keep_msg)
+ write_special_file("keep", keep_msg, final_pack_name, hash,
+ &report);
+ if (promisor_msg)
+ write_special_file("promisor", promisor_msg, final_pack_name,
+ hash, NULL);
if (final_pack_name != curr_pack_name) {
if (!final_pack_name)
- final_pack_name = odb_pack_name(&pack_name, sha1, "pack");
+ final_pack_name = odb_pack_name(&pack_name, hash, "pack");
if (finalize_object_file(curr_pack_name, final_pack_name))
die(_("cannot store pack file"));
} else if (from_stdin)
if (final_index_name != curr_index_name) {
if (!final_index_name)
- final_index_name = odb_pack_name(&index_name, sha1, "idx");
+ final_index_name = odb_pack_name(&index_name, hash, "idx");
if (finalize_object_file(curr_index_name, final_index_name))
die(_("cannot store index file"));
} else
chmod(final_index_name, 0444);
if (!from_stdin) {
- printf("%s\n", sha1_to_hex(sha1));
+ printf("%s\n", sha1_to_hex(hash));
} else {
struct strbuf buf = STRBUF_INIT;
- strbuf_addf(&buf, "%s\t%s\n", report, sha1_to_hex(sha1));
+ strbuf_addf(&buf, "%s\t%s\n", report, sha1_to_hex(hash));
write_or_die(1, buf.buf, buf.len);
strbuf_release(&buf);
strbuf_release(&index_name);
strbuf_release(&pack_name);
- strbuf_release(&keep_name_buf);
}
static int git_index_pack_config(const char *k, const char *v, void *cb)
continue;
printf("%s %-6s %lu %lu %"PRIuMAX,
oid_to_hex(&obj->idx.oid),
- typename(obj->real_type), obj->size,
+ type_name(obj->real_type), obj->size,
(unsigned long)(obj[1].idx.offset - obj->idx.offset),
(uintmax_t)obj->idx.offset);
if (is_delta_type(obj->type)) {
}
}
-static const char *derive_filename(const char *pack_name, const char *suffix,
- struct strbuf *buf)
-{
- size_t len;
- if (!strip_suffix(pack_name, ".pack", &len))
- die(_("packfile name '%s' does not end with '.pack'"),
- pack_name);
- strbuf_add(buf, pack_name, len);
- strbuf_addstr(buf, suffix);
- return buf->buf;
-}
-
int cmd_index_pack(int argc, const char **argv, const char *prefix)
{
int i, fix_thin_pack = 0, verify = 0, stat_only = 0;
const char *curr_index;
const char *index_name = NULL, *pack_name = NULL;
- const char *keep_name = NULL, *keep_msg = NULL;
- struct strbuf index_name_buf = STRBUF_INIT,
- keep_name_buf = STRBUF_INIT;
+ const char *keep_msg = NULL;
+ const char *promisor_msg = NULL;
+ struct strbuf index_name_buf = STRBUF_INIT;
struct pack_idx_entry **idx_objects;
struct pack_idx_option opts;
- unsigned char pack_sha1[20];
+ unsigned char pack_hash[GIT_MAX_RAWSZ];
unsigned foreign_nr = 1; /* zero is a "good" value, assume bad */
int report_end_of_input = 0;
+ /*
+ * index-pack never needs to fetch missing objects, since it only
+ * accesses the repo to do hash collision checks
+ */
+ fetch_if_missing = 0;
+
if (argc == 2 && !strcmp(argv[1], "-h"))
usage(index_pack_usage);
} else if (!strcmp(arg, "--check-self-contained-and-connected")) {
strict = 1;
check_self_contained_and_connected = 1;
+ } else if (!strcmp(arg, "--fsck-objects")) {
+ do_fsck_object = 1;
} else if (!strcmp(arg, "--verify")) {
verify = 1;
} else if (!strcmp(arg, "--verify-stat")) {
stat_only = 1;
} else if (skip_to_optional_arg(arg, "--keep", &keep_msg)) {
; /* nothing to do */
+ } else if (skip_to_optional_arg(arg, "--promisor", &promisor_msg)) {
+ ; /* already parsed */
} else if (starts_with(arg, "--threads=")) {
char *end;
nr_threads = strtoul(arg+10, &end, 0);
if (from_stdin && !startup_info->have_repository)
die(_("--stdin requires a git repository"));
if (!index_name && pack_name)
- index_name = derive_filename(pack_name, ".idx", &index_name_buf);
- if (keep_msg && !keep_name && pack_name)
- keep_name = derive_filename(pack_name, ".keep", &keep_name_buf);
+ index_name = derive_filename(pack_name, "idx", &index_name_buf);
if (verify) {
if (!index_name)
if (show_stat)
obj_stat = xcalloc(st_add(nr_objects, 1), sizeof(struct object_stat));
ofs_deltas = xcalloc(nr_objects, sizeof(struct ofs_delta_entry));
- parse_pack_objects(pack_sha1);
+ parse_pack_objects(pack_hash);
if (report_end_of_input)
write_in_full(2, "\0", 1);
resolve_deltas();
- conclude_pack(fix_thin_pack, curr_pack, pack_sha1);
+ conclude_pack(fix_thin_pack, curr_pack, pack_hash);
free(ofs_deltas);
free(ref_deltas);
if (strict)
ALLOC_ARRAY(idx_objects, nr_objects);
for (i = 0; i < nr_objects; i++)
idx_objects[i] = &objects[i].idx;
- curr_index = write_idx_file(index_name, idx_objects, nr_objects, &opts, pack_sha1);
+ curr_index = write_idx_file(index_name, idx_objects, nr_objects, &opts, pack_hash);
free(idx_objects);
if (!verify)
final(pack_name, curr_pack,
index_name, curr_index,
- keep_name, keep_msg,
- pack_sha1);
+ keep_msg, promisor_msg,
+ pack_hash);
else
close(input_fd);
free(objects);
strbuf_release(&index_name_buf);
- strbuf_release(&keep_name_buf);
if (pack_name == NULL)
free((void *) curr_pack);
if (index_name == NULL)