#include "cache.h"
#include "object.h"
#include "delta.h"
+#include "pack.h"
+#include "csum-file.h"
-static const char pack_usage[] = "git-pack-objects [--window=N] [--depth=N] base-name < object-list";
-
-enum object_type {
- OBJ_NONE,
- OBJ_COMMIT,
- OBJ_TREE,
- OBJ_BLOB,
- OBJ_DELTA // NOTE! This is _not_ the same as a "delta" object in the filesystem
-};
+static const char pack_usage[] = "git-pack-objects [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list";
struct object_entry {
unsigned char sha1[20];
unsigned long size;
unsigned long offset;
unsigned int depth;
- unsigned int flags;
+ unsigned int hash;
enum object_type type;
unsigned long delta_size;
struct object_entry *delta;
};
+static unsigned char object_list_sha1[20];
+static int non_empty = 0;
+static int local = 0;
+static int incremental = 0;
static struct object_entry **sorted_by_sha, **sorted_by_type;
static struct object_entry *objects = NULL;
static int nr_objects = 0, nr_alloc = 0;
static const char *base_name;
-
-struct myfile {
- int fd;
- unsigned long chars;
- unsigned char buffer[8192];
-};
-
-static FILE *create_file(const char *suffix)
-{
- static char filename[PATH_MAX];
- unsigned len;
-
- len = snprintf(filename, PATH_MAX, "%s.%s", base_name, suffix);
- if (len >= PATH_MAX)
- die("you wascally wabbit, you");
- return fopen(filename, "w");
-}
-
-static unsigned long fwrite_compressed(void *in, unsigned long size, FILE *f)
-{
- z_stream stream;
- unsigned long maxsize;
- void *out;
-
- memset(&stream, 0, sizeof(stream));
- deflateInit(&stream, Z_DEFAULT_COMPRESSION);
- maxsize = deflateBound(&stream, size);
- out = xmalloc(maxsize);
-
- /* Compress it */
- stream.next_in = in;
- stream.avail_in = size;
-
- stream.next_out = out;
- stream.avail_out = maxsize;
-
- while (deflate(&stream, Z_FINISH) == Z_OK)
- /* nothing */;
- deflateEnd(&stream);
-
- size = stream.total_out;
- fwrite(out, size, 1, f);
- free(out);
- return size;
-}
+static unsigned char pack_file_sha1[20];
static void *delta_against(void *buf, unsigned long size, struct object_entry *entry)
{
if (!otherbuf)
die("unable to read %s", sha1_to_hex(entry->delta->sha1));
delta_buf = diff_delta(otherbuf, othersize,
- buf, size, &delta_size, ~0UL);
+ buf, size, &delta_size, 0);
if (!delta_buf || delta_size != entry->delta_size)
die("delta size changed");
free(buf);
return delta_buf;
}
-static unsigned long write_object(FILE *f, struct object_entry *entry)
+/*
+ * The per-object header is a pretty dense thing, which is
+ * - first byte: low four bits are "size", then three bits of "type",
+ * and the high bit is "size continues".
+ * - each byte afterwards: low seven bits are size continuation,
+ * with the high bit being "size continues"
+ */
+static int encode_header(enum object_type type, unsigned long size, unsigned char *hdr)
+{
+ int n = 1;
+ unsigned char c;
+
+ if (type < OBJ_COMMIT || type > OBJ_DELTA)
+ die("bad type %d", type);
+
+ c = (type << 4) | (size & 15);
+ size >>= 4;
+ while (size) {
+ *hdr++ = c | 0x80;
+ c = size & 0x7f;
+ size >>= 7;
+ n++;
+ }
+ *hdr = c;
+ return n;
+}
+
+static unsigned long write_object(struct sha1file *f, struct object_entry *entry)
{
unsigned long size;
char type[10];
void *buf = read_sha1_file(entry->sha1, type, &size);
- char header[25];
+ unsigned char header[10];
unsigned hdrlen, datalen;
+ enum object_type obj_type;
if (!buf)
die("unable to read %s", sha1_to_hex(entry->sha1));
die("object %s size inconsistency (%lu vs %lu)", sha1_to_hex(entry->sha1), size, entry->size);
/*
- * The object header is a byte of 'type' followed by four bytes of
- * length, except for deltas that has the 20 bytes of delta sha
- * instead.
+ * The object header is a byte of 'type' followed by zero or
+ * more bytes of length. For deltas, the 20 bytes of delta sha1
+ * follows that.
*/
- header[0] = ".CTB"[entry->type];
- hdrlen = 5;
+ obj_type = entry->type;
if (entry->delta) {
- header[0] = 'D';
- memcpy(header+5, entry->delta, 20);
buf = delta_against(buf, size, entry);
size = entry->delta_size;
- hdrlen = 25;
+ obj_type = OBJ_DELTA;
}
- datalen = htonl(size);
- memcpy(header+1, &datalen, 4);
- fwrite(header, hdrlen, 1, f);
- datalen = fwrite_compressed(buf, size, f);
+ hdrlen = encode_header(obj_type, size, header);
+ sha1write(f, header, hdrlen);
+ if (entry->delta) {
+ sha1write(f, entry->delta, 20);
+ hdrlen += 20;
+ }
+ datalen = sha1write_compressed(f, buf, size);
free(buf);
return hdrlen + datalen;
}
+static unsigned long write_one(struct sha1file *f,
+ struct object_entry *e,
+ unsigned long offset)
+{
+ if (e->offset)
+ /* offset starts from header size and cannot be zero
+ * if it is written already.
+ */
+ return offset;
+ e->offset = offset;
+ offset += write_object(f, e);
+ /* if we are delitified, write out its base object. */
+ if (e->delta)
+ offset = write_one(f, e->delta, offset);
+ return offset;
+}
+
static void write_pack_file(void)
{
int i;
- FILE *f = create_file("pack");
- unsigned long offset = 0;
+ struct sha1file *f;
+ unsigned long offset;
unsigned long mb;
+ struct pack_header hdr;
- for (i = 0; i < nr_objects; i++) {
- struct object_entry *entry = objects + i;
- entry->offset = offset;
- offset += write_object(f, entry);
- }
- fclose(f);
+ if (!base_name)
+ f = sha1fd(1, "<stdout>");
+ else
+ f = sha1create("%s-%s.%s", base_name, sha1_to_hex(object_list_sha1), "pack");
+ hdr.hdr_signature = htonl(PACK_SIGNATURE);
+ hdr.hdr_version = htonl(PACK_VERSION);
+ hdr.hdr_entries = htonl(nr_objects);
+ sha1write(f, &hdr, sizeof(hdr));
+ offset = sizeof(hdr);
+ for (i = 0; i < nr_objects; i++)
+ offset = write_one(f, objects + i, offset);
+
+ sha1close(f, pack_file_sha1, 1);
mb = offset >> 20;
offset &= 0xfffff;
}
static void write_index_file(void)
{
int i;
- FILE *f = create_file("idx");
+ struct sha1file *f = sha1create("%s-%s.%s", base_name, sha1_to_hex(object_list_sha1), "idx");
struct object_entry **list = sorted_by_sha;
struct object_entry **last = list + nr_objects;
unsigned int array[256];
/*
* Write the first-level table (the list is sorted,
* but we use a 256-entry lookup to be able to avoid
- * having to do eight extra binary search iterations)
+ * having to do eight extra binary search iterations).
*/
for (i = 0; i < 256; i++) {
struct object_entry **next = list;
array[i] = htonl(next - sorted_by_sha);
list = next;
}
- fwrite(array, 256, sizeof(int), f);
+ sha1write(f, array, 256 * sizeof(int));
/*
* Write the actual SHA1 entries..
for (i = 0; i < nr_objects; i++) {
struct object_entry *entry = *list++;
unsigned int offset = htonl(entry->offset);
- fwrite(&offset, 4, 1, f);
- fwrite(entry->sha1, 20, 1, f);
+ sha1write(f, &offset, 4);
+ sha1write(f, entry->sha1, 20);
}
- fclose(f);
+ sha1write(f, pack_file_sha1, 20);
+ sha1close(f, NULL, 1);
}
-static void add_object_entry(unsigned char *sha1)
+static int add_object_entry(unsigned char *sha1, unsigned int hash)
{
unsigned int idx = nr_objects;
struct object_entry *entry;
+ if (incremental || local) {
+ struct packed_git *p;
+
+ for (p = packed_git; p; p = p->next) {
+ struct pack_entry e;
+
+ if (find_pack_entry_one(sha1, &e, p)) {
+ if (incremental)
+ return 0;
+ if (local && !p->pack_local)
+ return 0;
+ }
+ }
+ }
+
if (idx >= nr_alloc) {
unsigned int needed = (idx + 1024) * 3 / 2;
objects = xrealloc(objects, needed * sizeof(*entry));
entry = objects + idx;
memset(entry, 0, sizeof(*entry));
memcpy(entry->sha1, sha1, 20);
+ entry->hash = hash;
nr_objects = idx+1;
+ return 1;
}
static void check_object(struct object_entry *entry)
{
- char buffer[128];
- char type[10];
- unsigned long mapsize;
- z_stream stream;
- void *map;
-
- map = map_sha1_file(entry->sha1, &mapsize);
- if (!map)
- die("unable to map %s", sha1_to_hex(entry->sha1));
- if (unpack_sha1_header(&stream, map, mapsize, buffer, sizeof(buffer)) < 0)
- die("unable to unpack %s header", sha1_to_hex(entry->sha1));
- munmap(map, mapsize);
- if (parse_sha1_header(buffer, type, &entry->size) < 0)
- die("unable to parse %s header", sha1_to_hex(entry->sha1));
- if (!strcmp(type, "commit")) {
- entry->type = OBJ_COMMIT;
- } else if (!strcmp(type, "tree")) {
- entry->type = OBJ_TREE;
- } else if (!strcmp(type, "blob")) {
- entry->type = OBJ_BLOB;
- } else
- die("unable to pack object %s of type %s", sha1_to_hex(entry->sha1), type);
+ char type[20];
+
+ if (!sha1_object_info(entry->sha1, type, &entry->size)) {
+ if (!strcmp(type, "commit")) {
+ entry->type = OBJ_COMMIT;
+ } else if (!strcmp(type, "tree")) {
+ entry->type = OBJ_TREE;
+ } else if (!strcmp(type, "blob")) {
+ entry->type = OBJ_BLOB;
+ } else if (!strcmp(type, "tag")) {
+ entry->type = OBJ_TAG;
+ } else
+ die("unable to pack object %s of type %s",
+ sha1_to_hex(entry->sha1), type);
+ }
+ else
+ die("unable to get type of object %s",
+ sha1_to_hex(entry->sha1));
}
static void get_object_details(void)
return -1;
if (a->type > b->type)
return 1;
+ if (a->hash < b->hash)
+ return -1;
+ if (a->hash > b->hash)
+ return 1;
if (a->size < b->size)
return -1;
if (a->size > b->size)
max_size = size / 2 - 20;
if (cur_entry->delta)
max_size = cur_entry->delta_size-1;
+ if (sizediff >= max_size)
+ return -1;
delta_buf = diff_delta(old->data, oldsize,
cur->data, size, &delta_size, max_size);
if (!delta_buf)
if (idx >= window)
idx = 0;
}
+
+ for (i = 0; i < window; ++i)
+ free(array[i].data);
+ free(array);
+}
+
+static void prepare_pack(int window, int depth)
+{
+ get_object_details();
+
+ fprintf(stderr, "Packing %d objects\n", nr_objects);
+
+ sorted_by_type = create_sorted_list(type_size_sort);
+ if (window && depth)
+ find_deltas(sorted_by_type, window+1, depth);
+ write_pack_file();
+}
+
+static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout)
+{
+ static const char cache[] = "pack-cache/pack-%s.%s";
+ char *cached_pack, *cached_idx;
+ int ifd, ofd, ifd_ix = -1;
+
+ cached_pack = git_path(cache, sha1_to_hex(sha1), "pack");
+ ifd = open(cached_pack, O_RDONLY);
+ if (ifd < 0)
+ return 0;
+
+ if (!pack_to_stdout) {
+ cached_idx = git_path(cache, sha1_to_hex(sha1), "idx");
+ ifd_ix = open(cached_idx, O_RDONLY);
+ if (ifd_ix < 0) {
+ close(ifd);
+ return 0;
+ }
+ }
+
+ fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects,
+ sha1_to_hex(sha1));
+
+ if (pack_to_stdout) {
+ if (copy_fd(ifd, 1))
+ exit(1);
+ close(ifd);
+ }
+ else {
+ char name[PATH_MAX];
+ snprintf(name, sizeof(name),
+ "%s-%s.%s", base_name, sha1_to_hex(sha1), "pack");
+ ofd = open(name, O_CREAT | O_EXCL | O_WRONLY, 0666);
+ if (ofd < 0)
+ die("unable to open %s (%s)", name, strerror(errno));
+ if (copy_fd(ifd, ofd))
+ exit(1);
+ close(ifd);
+
+ snprintf(name, sizeof(name),
+ "%s-%s.%s", base_name, sha1_to_hex(sha1), "idx");
+ ofd = open(name, O_CREAT | O_EXCL | O_WRONLY, 0666);
+ if (ofd < 0)
+ die("unable to open %s (%s)", name, strerror(errno));
+ if (copy_fd(ifd_ix, ofd))
+ exit(1);
+ close(ifd_ix);
+ puts(sha1_to_hex(sha1));
+ }
+
+ return 1;
}
int main(int argc, char **argv)
{
- char line[128];
- int window = 10, depth = 10;
+ SHA_CTX ctx;
+ char line[PATH_MAX + 20];
+ int window = 10, depth = 10, pack_to_stdout = 0;
+ struct object_entry **list;
int i;
+ setup_git_directory();
+
for (i = 1; i < argc; i++) {
const char *arg = argv[i];
if (*arg == '-') {
+ if (!strcmp("--non-empty", arg)) {
+ non_empty = 1;
+ continue;
+ }
+ if (!strcmp("--local", arg)) {
+ local = 1;
+ continue;
+ }
+ if (!strcmp("--incremental", arg)) {
+ incremental = 1;
+ continue;
+ }
if (!strncmp("--window=", arg, 9)) {
char *end;
window = strtoul(arg+9, &end, 0);
usage(pack_usage);
continue;
}
+ if (!strcmp("--stdout", arg)) {
+ pack_to_stdout = 1;
+ continue;
+ }
usage(pack_usage);
}
if (base_name)
base_name = arg;
}
- if (!base_name)
+ if (pack_to_stdout != !base_name)
usage(pack_usage);
+ prepare_packed_git();
while (fgets(line, sizeof(line), stdin) != NULL) {
+ unsigned int hash;
+ char *p;
unsigned char sha1[20];
+
if (get_sha1_hex(line, sha1))
- die("expected sha1, got garbage");
- add_object_entry(sha1);
+ die("expected sha1, got garbage:\n %s", line);
+ hash = 0;
+ p = line+40;
+ while (*p) {
+ unsigned char c = *p++;
+ if (isspace(c))
+ continue;
+ hash = hash * 11 + c;
+ }
+ add_object_entry(sha1, hash);
}
- get_object_details();
-
- printf("Packing %d objects\n", nr_objects);
+ if (non_empty && !nr_objects)
+ return 0;
sorted_by_sha = create_sorted_list(sha1_sort);
- sorted_by_type = create_sorted_list(type_size_sort);
- if (window && depth)
- find_deltas(sorted_by_type, window+1, depth);
-
- write_pack_file();
- write_index_file();
+ SHA1_Init(&ctx);
+ list = sorted_by_sha;
+ for (i = 0; i < nr_objects; i++) {
+ struct object_entry *entry = *list++;
+ SHA1_Update(&ctx, entry->sha1, 20);
+ }
+ SHA1_Final(object_list_sha1, &ctx);
+
+ if (reuse_cached_pack(object_list_sha1, pack_to_stdout))
+ ;
+ else {
+ prepare_pack(window, depth);
+ if (!pack_to_stdout) {
+ write_index_file();
+ puts(sha1_to_hex(object_list_sha1));
+ }
+ }
return 0;
}