static int window = 10;
static uint32_t pack_size_limit, pack_size_limit_cfg;
static int depth = 50;
-static int delta_search_threads = 1;
+static int delta_search_threads;
static int pack_to_stdout;
static int num_preferred_base;
static struct progress *progress_state;
int st;
memset(&stream, 0, sizeof(stream));
- inflateInit(&stream);
+ git_inflate_init(&stream);
do {
in = use_pack(p, w_curs, offset, &stream.avail_in);
stream.next_in = in;
stream.next_out = fakebuf;
stream.avail_out = sizeof(fakebuf);
- st = inflate(&stream, Z_FINISH);
+ st = git_inflate(&stream, Z_FINISH);
offset += stream.next_in - in;
} while (st == Z_OK || st == Z_BUF_ERROR);
- inflateEnd(&stream);
+ git_inflate_end(&stream);
return (st == Z_STREAM_END &&
stream.total_out == expect &&
stream.total_in == len) ? 0 : -1;
*/
if (!to_reuse) {
+ no_reuse:
if (!usable_delta) {
buf = read_sha1_file(entry->idx.sha1, &type, &size);
if (!buf)
struct revindex_entry *revidx;
off_t offset;
- if (entry->delta) {
+ if (entry->delta)
type = (allow_ofs_delta && entry->delta->idx.offset) ?
OBJ_OFS_DELTA : OBJ_REF_DELTA;
- reused_delta++;
- }
hdrlen = encode_header(type, entry->size, header);
+
offset = entry->in_pack_offset;
revidx = find_pack_revindex(p, offset);
datalen = revidx[1].offset - offset;
if (!pack_to_stdout && p->index_version > 1 &&
- check_pack_crc(p, &w_curs, offset, datalen, revidx->nr))
- die("bad packed object CRC for %s", sha1_to_hex(entry->idx.sha1));
+ check_pack_crc(p, &w_curs, offset, datalen, revidx->nr)) {
+ error("bad packed object CRC for %s", sha1_to_hex(entry->idx.sha1));
+ unuse_pack(&w_curs);
+ goto no_reuse;
+ }
+
offset += entry->in_pack_header_size;
datalen -= entry->in_pack_header_size;
+ if (!pack_to_stdout && p->index_version == 1 &&
+ check_pack_inflate(p, &w_curs, offset, datalen, entry->size)) {
+ error("corrupt packed object for %s", sha1_to_hex(entry->idx.sha1));
+ unuse_pack(&w_curs);
+ goto no_reuse;
+ }
+
if (type == OBJ_OFS_DELTA) {
off_t ofs = entry->idx.offset - entry->delta->idx.offset;
unsigned pos = sizeof(dheader) - 1;
dheader[pos] = ofs & 127;
while (ofs >>= 7)
dheader[--pos] = 128 | (--ofs & 127);
- if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit)
+ if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) {
+ unuse_pack(&w_curs);
return 0;
+ }
sha1write(f, header, hdrlen);
sha1write(f, dheader + pos, sizeof(dheader) - pos);
hdrlen += sizeof(dheader) - pos;
+ reused_delta++;
} else if (type == OBJ_REF_DELTA) {
- if (limit && hdrlen + 20 + datalen + 20 >= limit)
+ if (limit && hdrlen + 20 + datalen + 20 >= limit) {
+ unuse_pack(&w_curs);
return 0;
+ }
sha1write(f, header, hdrlen);
sha1write(f, entry->delta->idx.sha1, 20);
hdrlen += 20;
+ reused_delta++;
} else {
- if (limit && hdrlen + datalen + 20 >= limit)
+ if (limit && hdrlen + datalen + 20 >= limit) {
+ unuse_pack(&w_curs);
return 0;
+ }
sha1write(f, header, hdrlen);
}
-
- if (!pack_to_stdout && p->index_version == 1 &&
- check_pack_inflate(p, &w_curs, offset, datalen, entry->size))
- die("corrupt packed object for %s", sha1_to_hex(entry->idx.sha1));
copy_pack_data(f, p, &w_curs, offset, datalen);
unuse_pack(&w_curs);
reused++;
* We want in_pack_type even if we do not reuse delta
* since non-delta representations could still be reused.
*/
- used = unpack_object_header_gently(buf, avail,
+ used = unpack_object_header_buffer(buf, avail,
&entry->in_pack_type,
&entry->size);
+ if (used == 0)
+ goto give_up;
/*
* Determine if this is a delta and if so whether we can
/* Not a delta hence we've already got all we need. */
entry->type = entry->in_pack_type;
entry->in_pack_header_size = used;
+ if (entry->type < OBJ_COMMIT || entry->type > OBJ_BLOB)
+ goto give_up;
unuse_pack(&w_curs);
return;
case OBJ_REF_DELTA:
ofs = c & 127;
while (c & 128) {
ofs += 1;
- if (!ofs || MSB(ofs, 7))
- die("delta base offset overflow in pack for %s",
- sha1_to_hex(entry->idx.sha1));
+ if (!ofs || MSB(ofs, 7)) {
+ error("delta base offset overflow in pack for %s",
+ sha1_to_hex(entry->idx.sha1));
+ goto give_up;
+ }
c = buf[used_0++];
ofs = (ofs << 7) + (c & 127);
}
- if (ofs >= entry->in_pack_offset)
- die("delta base offset out of bound for %s",
- sha1_to_hex(entry->idx.sha1));
ofs = entry->in_pack_offset - ofs;
+ if (ofs <= 0 || ofs >= entry->in_pack_offset) {
+ error("delta base offset out of bound for %s",
+ sha1_to_hex(entry->idx.sha1));
+ goto give_up;
+ }
if (reuse_delta && !entry->preferred_base) {
struct revindex_entry *revidx;
revidx = find_pack_revindex(p, ofs);
+ if (!revidx)
+ goto give_up;
base_ref = nth_packed_object_sha1(p, revidx->nr);
}
entry->in_pack_header_size = used + used_0;
*/
entry->type = entry->in_pack_type;
entry->delta = base_entry;
+ entry->delta_size = entry->size;
entry->delta_sibling = base_entry->delta_child;
base_entry->delta_child = entry;
unuse_pack(&w_curs);
*/
entry->size = get_size_from_delta(p, &w_curs,
entry->in_pack_offset + entry->in_pack_header_size);
+ if (entry->size == 0)
+ goto give_up;
unuse_pack(&w_curs);
return;
}
* with sha1_object_info() to find about the object type
* at this point...
*/
+ give_up:
unuse_pack(&w_curs);
}
int window, int depth, unsigned *processed)
{
uint32_t i, idx = 0, count = 0;
- unsigned int array_size = window * sizeof(struct unpacked);
struct unpacked *array;
unsigned long mem_usage = 0;
- array = xmalloc(array_size);
- memset(array, 0, array_size);
+ array = xcalloc(window, sizeof(struct unpacked));
for (;;) {
struct object_entry *entry;
find_deltas(list, &list_size, window, depth, processed);
return;
}
+ if (progress > pack_to_stdout)
+ fprintf(stderr, "Delta compression using %d threads.\n",
+ delta_search_threads);
/* Partition the work amongst work threads. */
for (i = 0; i < delta_search_threads; i++) {
unsigned sub_size = list_size / (delta_search_threads - i);
+ /* don't use too small segments or no deltas will be found */
+ if (sub_size < 2*window && i+1 < delta_search_threads)
+ sub_size = 0;
+
p[i].window = window;
p[i].depth = depth;
p[i].processed = processed;
get_object_details();
+ /*
+ * If we're locally repacking then we need to be doubly careful
+ * from now on in order to make sure no stealth corruption gets
+ * propagated to the new pack. Clients receiving streamed packs
+ * should validate everything they get anyway so no need to incur
+ * the additional cost here in that case.
+ */
+ if (!pack_to_stdout)
+ do_check_packed_object_crc = 1;
+
if (!nr_objects || !window || !depth)
return;
if (entry->type < 0)
die("unable to get type of object %s",
sha1_to_hex(entry->idx.sha1));
+ } else {
+ if (entry->type < 0) {
+ /*
+ * This object is not found, but we
+ * don't have to include it anyway.
+ */
+ continue;
+ }
}
delta_list[n++] = entry;