uint32_t version, nr, i, *index;
int fd = git_open(path);
struct stat st;
+ const unsigned int hashsz = the_hash_algo->rawsz;
if (fd < 0)
return -1;
return -1;
}
idx_size = xsize_t(st.st_size);
- if (idx_size < 4 * 256 + 20 + 20) {
+ if (idx_size < 4 * 256 + hashsz + hashsz) {
close(fd);
return error("index file %s is too small", path);
}
/*
* Total size:
* - 256 index entries 4 bytes each
- * - 24-byte entries * nr (20-byte sha1 + 4-byte offset)
- * - 20-byte SHA1 of the packfile
- * - 20-byte SHA1 file checksum
+ * - 24-byte entries * nr (object ID + 4-byte offset)
+ * - hash of the packfile
+ * - file checksum
*/
- if (idx_size != 4*256 + nr * 24 + 20 + 20) {
+ if (idx_size != 4*256 + nr * (hashsz + 4) + hashsz + hashsz) {
munmap(idx_map, idx_size);
return error("wrong index v1 file size in %s", path);
}
* Minimum size:
* - 8 bytes of header
* - 256 index entries 4 bytes each
- * - 20-byte sha1 entry * nr
+ * - object ID entry * nr
* - 4-byte crc entry * nr
* - 4-byte offset entry * nr
- * - 20-byte SHA1 of the packfile
- * - 20-byte SHA1 file checksum
+ * - hash of the packfile
+ * - file checksum
* And after the 4-byte offset table might be a
* variable sized table containing 8-byte entries
* for offsets larger than 2^31.
*/
- unsigned long min_size = 8 + 4*256 + nr*(20 + 4 + 4) + 20 + 20;
+ unsigned long min_size = 8 + 4*256 + nr*(hashsz + 4 + 4) + hashsz + hashsz;
unsigned long max_size = min_size;
if (nr)
max_size += (nr - 1)*8;
{
struct stat st;
struct pack_header hdr;
- unsigned char sha1[20];
- unsigned char *idx_sha1;
+ unsigned char hash[GIT_MAX_RAWSZ];
+ unsigned char *idx_hash;
long fd_flag;
ssize_t read_result;
+ const unsigned hashsz = the_hash_algo->rawsz;
if (!p->index_data && open_pack_index(p))
return error("packfile %s index unavailable", p->pack_name);
" while index indicates %"PRIu32" objects",
p->pack_name, ntohl(hdr.hdr_entries),
p->num_objects);
- if (lseek(p->pack_fd, p->pack_size - sizeof(sha1), SEEK_SET) == -1)
+ if (lseek(p->pack_fd, p->pack_size - hashsz, SEEK_SET) == -1)
return error("end of packfile %s is unavailable", p->pack_name);
- read_result = read_in_full(p->pack_fd, sha1, sizeof(sha1));
+ read_result = read_in_full(p->pack_fd, hash, hashsz);
if (read_result < 0)
return error_errno("error reading from %s", p->pack_name);
- if (read_result != sizeof(sha1))
+ if (read_result != hashsz)
return error("packfile %s signature is unavailable", p->pack_name);
- idx_sha1 = ((unsigned char *)p->index_data) + p->index_size - 40;
- if (hashcmp(sha1, idx_sha1))
+ idx_hash = ((unsigned char *)p->index_data) + p->index_size - hashsz * 2;
+ if (hashcmp(hash, idx_hash))
return error("packfile %s does not match index", p->pack_name);
return 0;
}
static int in_window(struct pack_window *win, off_t offset)
{
- /* We must promise at least 20 bytes (one hash) after the
+ /* We must promise at least one full hash after the
* offset is available from this window, otherwise the offset
* is not actually in this window and a different window (which
* has that one hash excess) must be used. This is to support
*/
off_t win_off = win->offset;
return win_off <= offset
- && (offset + 20) <= (win_off + win->len);
+ && (offset + the_hash_algo->rawsz) <= (win_off + win->len);
}
unsigned char *use_pack(struct packed_git *p,
*/
if (!p->pack_size && p->pack_fd == -1 && open_packed_git(p))
die("packfile %s cannot be accessed", p->pack_name);
- if (offset > (p->pack_size - 20))
+ if (offset > (p->pack_size - the_hash_algo->rawsz))
die("offset beyond end of packfile (truncated pack?)");
if (offset < 0)
die(_("offset before end of packfile (broken .idx?)"));
p->pack_size = st.st_size;
p->pack_local = local;
p->mtime = st.st_mtime;
- if (path_len < 40 || get_sha1_hex(path + path_len - 40, p->sha1))
+ if (path_len < the_hash_algo->hexsz ||
+ get_sha1_hex(path + path_len - the_hash_algo->hexsz, p->sha1))
hashclr(p->sha1);
return p;
}
strbuf_release(&path);
}
+static void prepare_packed_git(struct repository *r);
/*
* Give a fast, rough count of the number of objects in the repository. This
* ignores loose objects completely. If you have a lot of them, then either
list_add_tail(&p->mru, &r->objects->packed_git_mru);
}
-void prepare_packed_git_the_repository(void)
+static void prepare_packed_git(struct repository *r)
{
struct alternate_object_database *alt;
- if (the_repository->objects->packed_git_initialized)
+ if (r->objects->packed_git_initialized)
return;
- prepare_packed_git_one(the_repository, get_object_directory(), 1);
- prepare_alt_odb(the_repository);
- for (alt = the_repository->objects->alt_odb_list; alt; alt = alt->next)
- prepare_packed_git_one(the_repository, alt->path, 0);
- rearrange_packed_git(the_repository);
- prepare_packed_git_mru(the_repository);
- the_repository->objects->packed_git_initialized = 1;
+ prepare_packed_git_one(r, r->objects->objectdir, 1);
+ prepare_alt_odb(r);
+ for (alt = r->objects->alt_odb_list; alt; alt = alt->next)
+ prepare_packed_git_one(r, alt->path, 0);
+ rearrange_packed_git(r);
+ prepare_packed_git_mru(r);
+ r->objects->packed_git_initialized = 1;
}
-void reprepare_packed_git_the_repository(void)
+void reprepare_packed_git(struct repository *r)
{
- the_repository->objects->approximate_object_count_valid = 0;
- the_repository->objects->packed_git_initialized = 0;
- prepare_packed_git(the_repository);
+ r->objects->approximate_object_count_valid = 0;
+ r->objects->packed_git_initialized = 0;
+ prepare_packed_git(r);
}
struct packed_git *get_packed_git(struct repository *r)
{
+ prepare_packed_git(r);
return r->objects->packed_git;
}
struct list_head *get_packed_git_mru(struct repository *r)
{
+ prepare_packed_git(r);
return &r->objects->packed_git_mru;
}
for (p = the_repository->objects->packed_git; p; p = p->next)
for (i = 0; i < p->num_bad_objects; i++)
- if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i))
+ if (!hashcmp(sha1,
+ p->bad_object_sha1 + the_hash_algo->rawsz * i))
return p;
return NULL;
}
} else if (type == OBJ_REF_DELTA) {
/* The base entry _must_ be in the same pack */
base_offset = find_pack_entry_one(base_info, p);
- *curpos += 20;
+ *curpos += the_hash_algo->rawsz;
} else
die("I am totally screwed");
return base_offset;
{
int type;
struct revindex_entry *revidx;
- const unsigned char *sha1;
+ struct object_id oid;
revidx = find_pack_revindex(p, obj_offset);
if (!revidx)
return OBJ_BAD;
- sha1 = nth_packed_object_sha1(p, revidx->nr);
- mark_bad_packed_object(p, sha1);
- type = sha1_object_info(sha1, NULL);
+ nth_packed_object_oid(&oid, p, revidx->nr);
+ mark_bad_packed_object(p, oid.hash);
+ type = oid_object_info(&oid, NULL);
if (type <= OBJ_NONE)
return OBJ_BAD;
return type;
*oi->disk_sizep = revidx[1].offset - obj_offset;
}
- if (oi->typep || oi->typename) {
+ if (oi->typep || oi->type_name) {
enum object_type ptot;
ptot = packed_to_object_type(p, obj_offset, type, &w_curs,
curpos);
if (oi->typep)
*oi->typep = ptot;
- if (oi->typename) {
- const char *tn = typename(ptot);
+ if (oi->type_name) {
+ const char *tn = type_name(ptot);
if (tn)
- strbuf_addstr(oi->typename, tn);
+ strbuf_addstr(oi->type_name, tn);
}
if (ptot < 0) {
type = OBJ_BAD;
unsigned long size;
};
-static void *read_object(const unsigned char *sha1, enum object_type *type,
+static void *read_object(const struct object_id *oid, enum object_type *type,
unsigned long *size)
{
struct object_info oi = OBJECT_INFO_INIT;
oi.sizep = size;
oi.contentp = &content;
- if (sha1_object_info_extended(sha1, &oi, 0) < 0)
+ if (oid_object_info_extended(oid, &oi, 0) < 0)
return NULL;
return content;
}
struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
off_t len = revidx[1].offset - obj_offset;
if (check_pack_crc(p, &w_curs, obj_offset, len, revidx->nr)) {
- const unsigned char *sha1 =
- nth_packed_object_sha1(p, revidx->nr);
+ struct object_id oid;
+ nth_packed_object_oid(&oid, p, revidx->nr);
error("bad packed object CRC for %s",
- sha1_to_hex(sha1));
- mark_bad_packed_object(p, sha1);
+ oid_to_hex(&oid));
+ mark_bad_packed_object(p, oid.hash);
data = NULL;
goto out;
}
* of a corrupted pack, and is better than failing outright.
*/
struct revindex_entry *revidx;
- const unsigned char *base_sha1;
+ struct object_id base_oid;
revidx = find_pack_revindex(p, obj_offset);
if (revidx) {
- base_sha1 = nth_packed_object_sha1(p, revidx->nr);
+ nth_packed_object_oid(&base_oid, p, revidx->nr);
error("failed to read delta base object %s"
" at offset %"PRIuMAX" from %s",
- sha1_to_hex(base_sha1), (uintmax_t)obj_offset,
+ oid_to_hex(&base_oid), (uintmax_t)obj_offset,
p->pack_name);
- mark_bad_packed_object(p, base_sha1);
- base = read_object(base_sha1, &type, &base_size);
+ mark_bad_packed_object(p, base_oid.hash);
+ base = read_object(&base_oid, &type, &base_size);
external_base = base;
}
}
return data;
}
+int bsearch_pack(const struct object_id *oid, const struct packed_git *p, uint32_t *result)
+{
+ const unsigned char *index_fanout = p->index_data;
+ const unsigned char *index_lookup;
+ const unsigned int hashsz = the_hash_algo->rawsz;
+ int index_lookup_width;
+
+ if (!index_fanout)
+ BUG("bsearch_pack called without a valid pack-index");
+
+ index_lookup = index_fanout + 4 * 256;
+ if (p->index_version == 1) {
+ index_lookup_width = hashsz + 4;
+ index_lookup += 4;
+ } else {
+ index_lookup_width = hashsz;
+ index_fanout += 8;
+ index_lookup += 8;
+ }
+
+ return bsearch_hash(oid->hash, (const uint32_t*)index_fanout,
+ index_lookup, index_lookup_width, result);
+}
+
const unsigned char *nth_packed_object_sha1(struct packed_git *p,
uint32_t n)
{
const unsigned char *index = p->index_data;
+ const unsigned int hashsz = the_hash_algo->rawsz;
if (!index) {
if (open_pack_index(p))
return NULL;
return NULL;
index += 4 * 256;
if (p->index_version == 1) {
- return index + 24 * n + 4;
+ return index + (hashsz + 4) * n + 4;
} else {
index += 8;
- return index + 20 * n;
+ return index + hashsz * n;
}
}
off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n)
{
const unsigned char *index = p->index_data;
+ const unsigned int hashsz = the_hash_algo->rawsz;
index += 4 * 256;
if (p->index_version == 1) {
- return ntohl(*((uint32_t *)(index + 24 * n)));
+ return ntohl(*((uint32_t *)(index + (hashsz + 4) * n)));
} else {
uint32_t off;
- index += 8 + p->num_objects * (20 + 4);
+ index += 8 + p->num_objects * (hashsz + 4);
off = ntohl(*((uint32_t *)(index + 4 * n)));
if (!(off & 0x80000000))
return off;
off_t find_pack_entry_one(const unsigned char *sha1,
struct packed_git *p)
{
- const uint32_t *level1_ofs = p->index_data;
const unsigned char *index = p->index_data;
- unsigned hi, lo, stride;
- static int debug_lookup = -1;
-
- if (debug_lookup < 0)
- debug_lookup = !!getenv("GIT_DEBUG_LOOKUP");
+ struct object_id oid;
+ uint32_t result;
if (!index) {
if (open_pack_index(p))
return 0;
- level1_ofs = p->index_data;
- index = p->index_data;
- }
- if (p->index_version > 1) {
- level1_ofs += 2;
- index += 8;
- }
- index += 4 * 256;
- hi = ntohl(level1_ofs[*sha1]);
- lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1]));
- if (p->index_version > 1) {
- stride = 20;
- } else {
- stride = 24;
- index += 4;
}
- if (debug_lookup)
- printf("%02x%02x%02x... lo %u hi %u nr %"PRIu32"\n",
- sha1[0], sha1[1], sha1[2], lo, hi, p->num_objects);
-
- while (lo < hi) {
- unsigned mi = lo + (hi - lo) / 2;
- int cmp = hashcmp(index + mi * stride, sha1);
-
- if (debug_lookup)
- printf("lo %u hi %u rg %u mi %u\n",
- lo, hi, hi - lo, mi);
- if (!cmp)
- return nth_packed_object_offset(p, mi);
- if (cmp > 0)
- hi = mi;
- else
- lo = mi+1;
- }
+ hashcpy(oid.hash, sha1);
+ if (bsearch_pack(&oid, p, &result))
+ return nth_packed_object_offset(p, result);
return 0;
}
}
-static int fill_pack_entry(const unsigned char *sha1,
+static int fill_pack_entry(const struct object_id *oid,
struct pack_entry *e,
struct packed_git *p)
{
if (p->num_bad_objects) {
unsigned i;
for (i = 0; i < p->num_bad_objects; i++)
- if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i))
+ if (!hashcmp(oid->hash,
+ p->bad_object_sha1 + the_hash_algo->rawsz * i))
return 0;
}
- offset = find_pack_entry_one(sha1, p);
+ offset = find_pack_entry_one(oid->hash, p);
if (!offset)
return 0;
return 0;
e->offset = offset;
e->p = p;
- hashcpy(e->sha1, sha1);
return 1;
}
-/*
- * Iff a pack file contains the object named by sha1, return true and
- * store its location to e.
- */
-int find_pack_entry(const unsigned char *sha1, struct pack_entry *e)
+int find_pack_entry(struct repository *r, const struct object_id *oid, struct pack_entry *e)
{
struct list_head *pos;
- prepare_packed_git(the_repository);
- if (!the_repository->objects->packed_git)
+ prepare_packed_git(r);
+ if (!r->objects->packed_git)
return 0;
- list_for_each(pos, &the_repository->objects->packed_git_mru) {
+ list_for_each(pos, &r->objects->packed_git_mru) {
struct packed_git *p = list_entry(pos, struct packed_git, mru);
- if (fill_pack_entry(sha1, e, p)) {
- list_move(&p->mru,
- &the_repository->objects->packed_git_mru);
+ if (fill_pack_entry(oid, e, p)) {
+ list_move(&p->mru, &r->objects->packed_git_mru);
return 1;
}
}
return 0;
}
-int has_sha1_pack(const unsigned char *sha1)
+int has_object_pack(const struct object_id *oid)
{
struct pack_entry e;
- return find_pack_entry(sha1, &e);
+ return find_pack_entry(the_repository, oid, &e);
}
int has_pack_index(const unsigned char *sha1)