mirror of
https://github.com/git/git.git
synced 2024-11-13 20:53:02 +01:00
4d4fcc5451
Since it is now OK to pass a null pointer to display_progress() and stop_progress() resulting in a no-op, then we can simplify the code and remove a bunch of lines by not making those calls conditional all the time. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
402 lines
8.6 KiB
C
402 lines
8.6 KiB
C
#include "builtin.h"
|
|
#include "cache.h"
|
|
#include "object.h"
|
|
#include "delta.h"
|
|
#include "pack.h"
|
|
#include "blob.h"
|
|
#include "commit.h"
|
|
#include "tag.h"
|
|
#include "tree.h"
|
|
#include "progress.h"
|
|
|
|
static int dry_run, quiet, recover, has_errors;
|
|
static const char unpack_usage[] = "git-unpack-objects [-n] [-q] [-r] < pack-file";
|
|
|
|
/* We always read in 4kB chunks. */
|
|
static unsigned char buffer[4096];
|
|
static unsigned int offset, len;
|
|
static off_t consumed_bytes;
|
|
static SHA_CTX ctx;
|
|
|
|
/*
|
|
* Make sure at least "min" bytes are available in the buffer, and
|
|
* return the pointer to the buffer.
|
|
*/
|
|
static void *fill(int min)
|
|
{
|
|
if (min <= len)
|
|
return buffer + offset;
|
|
if (min > sizeof(buffer))
|
|
die("cannot fill %d bytes", min);
|
|
if (offset) {
|
|
SHA1_Update(&ctx, buffer, offset);
|
|
memmove(buffer, buffer + offset, len);
|
|
offset = 0;
|
|
}
|
|
do {
|
|
ssize_t ret = xread(0, buffer + len, sizeof(buffer) - len);
|
|
if (ret <= 0) {
|
|
if (!ret)
|
|
die("early EOF");
|
|
die("read error on input: %s", strerror(errno));
|
|
}
|
|
len += ret;
|
|
} while (len < min);
|
|
return buffer;
|
|
}
|
|
|
|
static void use(int bytes)
|
|
{
|
|
if (bytes > len)
|
|
die("used more bytes than were available");
|
|
len -= bytes;
|
|
offset += bytes;
|
|
|
|
/* make sure off_t is sufficiently large not to wrap */
|
|
if (consumed_bytes > consumed_bytes + bytes)
|
|
die("pack too large for current definition of off_t");
|
|
consumed_bytes += bytes;
|
|
}
|
|
|
|
static void *get_data(unsigned long size)
|
|
{
|
|
z_stream stream;
|
|
void *buf = xmalloc(size);
|
|
|
|
memset(&stream, 0, sizeof(stream));
|
|
|
|
stream.next_out = buf;
|
|
stream.avail_out = size;
|
|
stream.next_in = fill(1);
|
|
stream.avail_in = len;
|
|
inflateInit(&stream);
|
|
|
|
for (;;) {
|
|
int ret = inflate(&stream, 0);
|
|
use(len - stream.avail_in);
|
|
if (stream.total_out == size && ret == Z_STREAM_END)
|
|
break;
|
|
if (ret != Z_OK) {
|
|
error("inflate returned %d\n", ret);
|
|
free(buf);
|
|
buf = NULL;
|
|
if (!recover)
|
|
exit(1);
|
|
has_errors = 1;
|
|
break;
|
|
}
|
|
stream.next_in = fill(1);
|
|
stream.avail_in = len;
|
|
}
|
|
inflateEnd(&stream);
|
|
return buf;
|
|
}
|
|
|
|
struct delta_info {
|
|
unsigned char base_sha1[20];
|
|
unsigned nr;
|
|
off_t base_offset;
|
|
unsigned long size;
|
|
void *delta;
|
|
struct delta_info *next;
|
|
};
|
|
|
|
static struct delta_info *delta_list;
|
|
|
|
static void add_delta_to_list(unsigned nr, unsigned const char *base_sha1,
|
|
off_t base_offset,
|
|
void *delta, unsigned long size)
|
|
{
|
|
struct delta_info *info = xmalloc(sizeof(*info));
|
|
|
|
hashcpy(info->base_sha1, base_sha1);
|
|
info->base_offset = base_offset;
|
|
info->size = size;
|
|
info->delta = delta;
|
|
info->nr = nr;
|
|
info->next = delta_list;
|
|
delta_list = info;
|
|
}
|
|
|
|
struct obj_info {
|
|
off_t offset;
|
|
unsigned char sha1[20];
|
|
};
|
|
|
|
static struct obj_info *obj_list;
|
|
|
|
static void added_object(unsigned nr, enum object_type type,
|
|
void *data, unsigned long size);
|
|
|
|
static void write_object(unsigned nr, enum object_type type,
|
|
void *buf, unsigned long size)
|
|
{
|
|
if (write_sha1_file(buf, size, typename(type), obj_list[nr].sha1) < 0)
|
|
die("failed to write object");
|
|
added_object(nr, type, buf, size);
|
|
}
|
|
|
|
static void resolve_delta(unsigned nr, enum object_type type,
|
|
void *base, unsigned long base_size,
|
|
void *delta, unsigned long delta_size)
|
|
{
|
|
void *result;
|
|
unsigned long result_size;
|
|
|
|
result = patch_delta(base, base_size,
|
|
delta, delta_size,
|
|
&result_size);
|
|
if (!result)
|
|
die("failed to apply delta");
|
|
free(delta);
|
|
write_object(nr, type, result, result_size);
|
|
free(result);
|
|
}
|
|
|
|
static void added_object(unsigned nr, enum object_type type,
|
|
void *data, unsigned long size)
|
|
{
|
|
struct delta_info **p = &delta_list;
|
|
struct delta_info *info;
|
|
|
|
while ((info = *p) != NULL) {
|
|
if (!hashcmp(info->base_sha1, obj_list[nr].sha1) ||
|
|
info->base_offset == obj_list[nr].offset) {
|
|
*p = info->next;
|
|
p = &delta_list;
|
|
resolve_delta(info->nr, type, data, size,
|
|
info->delta, info->size);
|
|
free(info);
|
|
continue;
|
|
}
|
|
p = &info->next;
|
|
}
|
|
}
|
|
|
|
static void unpack_non_delta_entry(enum object_type type, unsigned long size,
|
|
unsigned nr)
|
|
{
|
|
void *buf = get_data(size);
|
|
|
|
if (!dry_run && buf)
|
|
write_object(nr, type, buf, size);
|
|
free(buf);
|
|
}
|
|
|
|
static void unpack_delta_entry(enum object_type type, unsigned long delta_size,
|
|
unsigned nr)
|
|
{
|
|
void *delta_data, *base;
|
|
unsigned long base_size;
|
|
unsigned char base_sha1[20];
|
|
|
|
if (type == OBJ_REF_DELTA) {
|
|
hashcpy(base_sha1, fill(20));
|
|
use(20);
|
|
delta_data = get_data(delta_size);
|
|
if (dry_run || !delta_data) {
|
|
free(delta_data);
|
|
return;
|
|
}
|
|
if (!has_sha1_file(base_sha1)) {
|
|
hashcpy(obj_list[nr].sha1, null_sha1);
|
|
add_delta_to_list(nr, base_sha1, 0, delta_data, delta_size);
|
|
return;
|
|
}
|
|
} else {
|
|
unsigned base_found = 0;
|
|
unsigned char *pack, c;
|
|
off_t base_offset;
|
|
unsigned lo, mid, hi;
|
|
|
|
pack = fill(1);
|
|
c = *pack;
|
|
use(1);
|
|
base_offset = c & 127;
|
|
while (c & 128) {
|
|
base_offset += 1;
|
|
if (!base_offset || MSB(base_offset, 7))
|
|
die("offset value overflow for delta base object");
|
|
pack = fill(1);
|
|
c = *pack;
|
|
use(1);
|
|
base_offset = (base_offset << 7) + (c & 127);
|
|
}
|
|
base_offset = obj_list[nr].offset - base_offset;
|
|
|
|
delta_data = get_data(delta_size);
|
|
if (dry_run || !delta_data) {
|
|
free(delta_data);
|
|
return;
|
|
}
|
|
lo = 0;
|
|
hi = nr;
|
|
while (lo < hi) {
|
|
mid = (lo + hi)/2;
|
|
if (base_offset < obj_list[mid].offset) {
|
|
hi = mid;
|
|
} else if (base_offset > obj_list[mid].offset) {
|
|
lo = mid + 1;
|
|
} else {
|
|
hashcpy(base_sha1, obj_list[mid].sha1);
|
|
base_found = !is_null_sha1(base_sha1);
|
|
break;
|
|
}
|
|
}
|
|
if (!base_found) {
|
|
/* The delta base object is itself a delta that
|
|
has not been resolved yet. */
|
|
hashcpy(obj_list[nr].sha1, null_sha1);
|
|
add_delta_to_list(nr, null_sha1, base_offset, delta_data, delta_size);
|
|
return;
|
|
}
|
|
}
|
|
|
|
base = read_sha1_file(base_sha1, &type, &base_size);
|
|
if (!base) {
|
|
error("failed to read delta-pack base object %s",
|
|
sha1_to_hex(base_sha1));
|
|
if (!recover)
|
|
exit(1);
|
|
has_errors = 1;
|
|
return;
|
|
}
|
|
resolve_delta(nr, type, base, base_size, delta_data, delta_size);
|
|
free(base);
|
|
}
|
|
|
|
static void unpack_one(unsigned nr)
|
|
{
|
|
unsigned shift;
|
|
unsigned char *pack, c;
|
|
unsigned long size;
|
|
enum object_type type;
|
|
|
|
obj_list[nr].offset = consumed_bytes;
|
|
|
|
pack = fill(1);
|
|
c = *pack;
|
|
use(1);
|
|
type = (c >> 4) & 7;
|
|
size = (c & 15);
|
|
shift = 4;
|
|
while (c & 0x80) {
|
|
pack = fill(1);
|
|
c = *pack;
|
|
use(1);
|
|
size += (c & 0x7f) << shift;
|
|
shift += 7;
|
|
}
|
|
|
|
switch (type) {
|
|
case OBJ_COMMIT:
|
|
case OBJ_TREE:
|
|
case OBJ_BLOB:
|
|
case OBJ_TAG:
|
|
unpack_non_delta_entry(type, size, nr);
|
|
return;
|
|
case OBJ_REF_DELTA:
|
|
case OBJ_OFS_DELTA:
|
|
unpack_delta_entry(type, size, nr);
|
|
return;
|
|
default:
|
|
error("bad object type %d", type);
|
|
has_errors = 1;
|
|
if (recover)
|
|
return;
|
|
exit(1);
|
|
}
|
|
}
|
|
|
|
static void unpack_all(void)
|
|
{
|
|
int i;
|
|
struct progress *progress = NULL;
|
|
struct pack_header *hdr = fill(sizeof(struct pack_header));
|
|
unsigned nr_objects = ntohl(hdr->hdr_entries);
|
|
|
|
if (ntohl(hdr->hdr_signature) != PACK_SIGNATURE)
|
|
die("bad pack file");
|
|
if (!pack_version_ok(hdr->hdr_version))
|
|
die("unknown pack file version %d", ntohl(hdr->hdr_version));
|
|
use(sizeof(struct pack_header));
|
|
|
|
if (!quiet)
|
|
progress = start_progress("Unpacking objects", nr_objects);
|
|
obj_list = xmalloc(nr_objects * sizeof(*obj_list));
|
|
for (i = 0; i < nr_objects; i++) {
|
|
unpack_one(i);
|
|
display_progress(progress, i + 1);
|
|
}
|
|
stop_progress(&progress);
|
|
|
|
if (delta_list)
|
|
die("unresolved deltas left after unpacking");
|
|
}
|
|
|
|
int cmd_unpack_objects(int argc, const char **argv, const char *prefix)
|
|
{
|
|
int i;
|
|
unsigned char sha1[20];
|
|
|
|
git_config(git_default_config);
|
|
|
|
quiet = !isatty(2);
|
|
|
|
for (i = 1 ; i < argc; i++) {
|
|
const char *arg = argv[i];
|
|
|
|
if (*arg == '-') {
|
|
if (!strcmp(arg, "-n")) {
|
|
dry_run = 1;
|
|
continue;
|
|
}
|
|
if (!strcmp(arg, "-q")) {
|
|
quiet = 1;
|
|
continue;
|
|
}
|
|
if (!strcmp(arg, "-r")) {
|
|
recover = 1;
|
|
continue;
|
|
}
|
|
if (!prefixcmp(arg, "--pack_header=")) {
|
|
struct pack_header *hdr;
|
|
char *c;
|
|
|
|
hdr = (struct pack_header *)buffer;
|
|
hdr->hdr_signature = htonl(PACK_SIGNATURE);
|
|
hdr->hdr_version = htonl(strtoul(arg + 14, &c, 10));
|
|
if (*c != ',')
|
|
die("bad %s", arg);
|
|
hdr->hdr_entries = htonl(strtoul(c + 1, &c, 10));
|
|
if (*c)
|
|
die("bad %s", arg);
|
|
len = sizeof(*hdr);
|
|
continue;
|
|
}
|
|
usage(unpack_usage);
|
|
}
|
|
|
|
/* We don't take any non-flag arguments now.. Maybe some day */
|
|
usage(unpack_usage);
|
|
}
|
|
SHA1_Init(&ctx);
|
|
unpack_all();
|
|
SHA1_Update(&ctx, buffer, offset);
|
|
SHA1_Final(sha1, &ctx);
|
|
if (hashcmp(fill(20), sha1))
|
|
die("final sha1 did not match");
|
|
use(20);
|
|
|
|
/* Write the last part of the buffer to stdout */
|
|
while (len) {
|
|
int ret = xwrite(1, buffer + offset, len);
|
|
if (ret <= 0)
|
|
break;
|
|
len -= ret;
|
|
offset += ret;
|
|
}
|
|
|
|
/* All done */
|
|
return has_errors;
|
|
}
|