#include "pack.h"
#include "csum-file.h"
#include "tree-walk.h"
-#include <sys/time.h>
-#include <signal.h>
+#include "diff.h"
+#include "revision.h"
+#include "list-objects.h"
-static const char pack_usage[] = "git-pack-objects [-q] [--no-reuse-delta] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list";
+static const char pack_usage[] = "\
+git-pack-objects [{ -q | --progress | --all-progress }] \n\
+ [--local] [--incremental] [--window=N] [--depth=N] \n\
+ [--no-reuse-delta] [--delta-base-offset] [--non-empty] \n\
+ [--revs [--unpacked | --all]*] [--reflog] [--stdout | base-name] \n\
+ [<ref-list | <object-list]";
struct object_entry {
unsigned char sha1[20];
unsigned long size; /* uncompressed size */
- unsigned long offset; /* offset into the final pack file;
+ off_t offset; /* offset into the final pack file;
* nonzero if already written.
*/
unsigned int depth; /* delta depth */
enum object_type type;
enum object_type in_pack_type; /* could be delta */
unsigned long delta_size; /* delta data size (uncompressed) */
+#define in_pack_header_size delta_size /* only when reusing pack data */
struct object_entry *delta; /* delta base object */
struct packed_git *in_pack; /* already in pack */
- unsigned int in_pack_offset;
+ off_t in_pack_offset;
struct object_entry *delta_child; /* deltified objects who bases me */
struct object_entry *delta_sibling; /* other deltified objects who
* uses the same base as me
static int no_reuse_delta;
static int local;
static int incremental;
+static int allow_ofs_delta;
+
static struct object_entry **sorted_by_sha, **sorted_by_type;
static struct object_entry *objects;
-static int nr_objects, nr_alloc, nr_result;
+static uint32_t nr_objects, nr_alloc, nr_result;
static const char *base_name;
static unsigned char pack_file_sha1[20];
static int progress = 1;
static volatile sig_atomic_t progress_update;
static int window = 10;
static int pack_to_stdout;
+static int num_preferred_base;
/*
* The object names in objects array are hashed with this hashtable,
* Pack index for existing packs give us easy access to the offsets into
* corresponding pack file where each object's data starts, but the entries
* do not store the size of the compressed representation (uncompressed
- * size is easily available by examining the pack entry header). We build
- * a hashtable of existing packs (pack_revindex), and keep reverse index
- * here -- pack index file is sorted by object name mapping to offset; this
- * pack_revindex[].revindex array is an ordered list of offsets, so if you
- * know the offset of an object, next offset is where its packed
- * representation ends.
+ * size is easily available by examining the pack entry header). It is
+ * also rather expensive to find the sha1 for an object given its offset.
+ *
+ * We build a hashtable of existing packs (pack_revindex), and keep reverse
+ * index here -- pack index file is sorted by object name mapping to offset;
+ * this pack_revindex[].revindex array is a list of offset/index_nr pairs
+ * ordered by offset, so if you know the offset of an object, next offset
+ * is where its packed representation ends and the index_nr can be used to
+ * get the object sha1 from the main index.
*/
+struct revindex_entry {
+ off_t offset;
+ unsigned int nr;
+};
struct pack_revindex {
struct packed_git *p;
- unsigned long *revindex;
-} *pack_revindex = NULL;
+ struct revindex_entry *revindex;
+};
+static struct pack_revindex *pack_revindex;
static int pack_revindex_hashsz;
/*
* stats
*/
-static int written;
-static int written_delta;
-static int reused;
-static int reused_delta;
+static uint32_t written, written_delta;
+static uint32_t reused, reused_delta;
static int pack_revindex_ix(struct packed_git *p)
{
static int cmp_offset(const void *a_, const void *b_)
{
- unsigned long a = *(unsigned long *) a_;
- unsigned long b = *(unsigned long *) b_;
- if (a < b)
- return -1;
- else if (a == b)
- return 0;
- else
- return 1;
+ const struct revindex_entry *a = a_;
+ const struct revindex_entry *b = b_;
+ return (a->offset < b->offset) ? -1 : (a->offset > b->offset) ? 1 : 0;
}
/*
int i;
void *index = p->index_base + 256;
- rix->revindex = xmalloc(sizeof(unsigned long) * (num_ent + 1));
+ rix->revindex = xmalloc(sizeof(*rix->revindex) * (num_ent + 1));
for (i = 0; i < num_ent; i++) {
unsigned int hl = *((unsigned int *)((char *) index + 24*i));
- rix->revindex[i] = ntohl(hl);
+ rix->revindex[i].offset = ntohl(hl);
+ rix->revindex[i].nr = i;
}
/* This knows the pack format -- the 20-byte trailer
* follows immediately after the last object data.
*/
- rix->revindex[num_ent] = p->pack_size - 20;
- qsort(rix->revindex, num_ent, sizeof(unsigned long), cmp_offset);
+ rix->revindex[num_ent].offset = p->pack_size - 20;
+ rix->revindex[num_ent].nr = -1;
+ qsort(rix->revindex, num_ent, sizeof(*rix->revindex), cmp_offset);
}
-static unsigned long find_packed_object_size(struct packed_git *p,
- unsigned long ofs)
+static struct revindex_entry * find_packed_object(struct packed_git *p,
+ off_t ofs)
{
int num;
int lo, hi;
struct pack_revindex *rix;
- unsigned long *revindex;
+ struct revindex_entry *revindex;
num = pack_revindex_ix(p);
if (num < 0)
die("internal error: pack revindex uninitialized");
hi = num_packed_objects(p) + 1;
do {
int mi = (lo + hi) / 2;
- if (revindex[mi] == ofs) {
- return revindex[mi+1] - ofs;
+ if (revindex[mi].offset == ofs) {
+ return revindex + mi;
}
- else if (ofs < revindex[mi])
+ else if (ofs < revindex[mi].offset)
hi = mi;
else
lo = mi + 1;
die("internal error: pack revindex corrupt");
}
+static off_t find_packed_object_size(struct packed_git *p, off_t ofs)
+{
+ struct revindex_entry *entry = find_packed_object(p, ofs);
+ return entry[1].offset - ofs;
+}
+
+static unsigned char *find_packed_object_name(struct packed_git *p,
+ off_t ofs)
+{
+ struct revindex_entry *entry = find_packed_object(p, ofs);
+ return (unsigned char *)(p->index_base + 256) + 24 * entry->nr + 4;
+}
+
static void *delta_against(void *buf, unsigned long size, struct object_entry *entry)
{
unsigned long othersize, delta_size;
- char type[10];
- void *otherbuf = read_sha1_file(entry->delta->sha1, type, &othersize);
+ enum object_type type;
+ void *otherbuf = read_sha1_file(entry->delta->sha1, &type, &othersize);
void *delta_buf;
if (!otherbuf)
int n = 1;
unsigned char c;
- if (type < OBJ_COMMIT || type > OBJ_DELTA)
+ if (type < OBJ_COMMIT || type > OBJ_REF_DELTA)
die("bad type %d", type);
c = (type << 4) | (size & 15);
return n;
}
-static int revalidate_one(struct object_entry *entry,
- void *data, char *type, unsigned long size)
-{
- int err;
- if (!data)
- return -1;
- if (size != entry->size)
- return -1;
- err = check_sha1_signature(entry->sha1, data, size,
- type_names[entry->type]);
- free(data);
- return err;
-}
-
/*
- * we are going to reuse the existing pack entry data. make
+ * we are going to reuse the existing object data as is. make
* sure it is not corrupt.
*/
-static int revalidate_pack_entry(struct object_entry *entry)
+static int check_pack_inflate(struct packed_git *p,
+ struct pack_window **w_curs,
+ off_t offset,
+ off_t len,
+ unsigned long expect)
{
- void *data;
- char type[20];
- unsigned long size;
- struct pack_entry e;
+ z_stream stream;
+ unsigned char fakebuf[4096], *in;
+ int st;
- if (pack_to_stdout)
- return 0;
+ memset(&stream, 0, sizeof(stream));
+ inflateInit(&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);
+ offset += stream.next_in - in;
+ } while (st == Z_OK || st == Z_BUF_ERROR);
+ inflateEnd(&stream);
+ return (st == Z_STREAM_END &&
+ stream.total_out == expect &&
+ stream.total_in == len) ? 0 : -1;
+}
- e.p = entry->in_pack;
- e.offset = entry->in_pack_offset;
+static void copy_pack_data(struct sha1file *f,
+ struct packed_git *p,
+ struct pack_window **w_curs,
+ off_t offset,
+ off_t len)
+{
+ unsigned char *in;
+ unsigned int avail;
+
+ while (len) {
+ in = use_pack(p, w_curs, offset, &avail);
+ if (avail > len)
+ avail = (unsigned int)len;
+ sha1write(f, in, avail);
+ offset += avail;
+ len -= avail;
+ }
+}
- /* the caller has already called use_packed_git() for us */
- data = unpack_entry_gently(&e, type, &size);
- return revalidate_one(entry, data, type, size);
+static int check_loose_inflate(unsigned char *data, unsigned long len, unsigned long expect)
+{
+ z_stream stream;
+ unsigned char fakebuf[4096];
+ int st;
+
+ memset(&stream, 0, sizeof(stream));
+ stream.next_in = data;
+ stream.avail_in = len;
+ stream.next_out = fakebuf;
+ stream.avail_out = sizeof(fakebuf);
+ inflateInit(&stream);
+
+ while (1) {
+ st = inflate(&stream, Z_FINISH);
+ if (st == Z_STREAM_END || st == Z_OK) {
+ st = (stream.total_out == expect &&
+ stream.total_in == len) ? 0 : -1;
+ break;
+ }
+ if (st != Z_BUF_ERROR) {
+ st = -1;
+ break;
+ }
+ stream.next_out = fakebuf;
+ stream.avail_out = sizeof(fakebuf);
+ }
+ inflateEnd(&stream);
+ return st;
}
static int revalidate_loose_object(struct object_entry *entry,
unsigned long mapsize)
{
/* we already know this is a loose object with new type header. */
- void *data;
- char type[20];
- unsigned long size;
+ enum object_type type;
+ unsigned long size, used;
if (pack_to_stdout)
return 0;
- data = unpack_sha1_file(map, mapsize, type, &size);
- return revalidate_one(entry, data, type, size);
+ used = unpack_object_header_gently(map, mapsize, &type, &size);
+ if (!used)
+ return -1;
+ map += used;
+ mapsize -= used;
+ return check_loose_inflate(map, mapsize, size);
}
-static unsigned long write_object(struct sha1file *f,
+static off_t write_object(struct sha1file *f,
struct object_entry *entry)
{
unsigned long size;
- char type[10];
+ enum object_type type;
void *buf;
unsigned char header[10];
- unsigned hdrlen, datalen;
+ unsigned hdrlen;
+ off_t datalen;
enum object_type obj_type;
int to_reuse = 0;
- if (entry->preferred_base)
- return 0;
-
obj_type = entry->type;
if (! entry->in_pack)
to_reuse = 0; /* can't reuse what we don't have */
- else if (obj_type == OBJ_DELTA)
+ else if (obj_type == OBJ_REF_DELTA || obj_type == OBJ_OFS_DELTA)
to_reuse = 1; /* check_object() decided it for us */
else if (obj_type != entry->in_pack_type)
to_reuse = 0; /* pack has delta which is unusable */
}
if (!to_reuse) {
- buf = read_sha1_file(entry->sha1, type, &size);
+ buf = read_sha1_file(entry->sha1, &type, &size);
if (!buf)
die("unable to read %s", sha1_to_hex(entry->sha1));
if (size != entry->size)
if (entry->delta) {
buf = delta_against(buf, size, entry);
size = entry->delta_size;
- obj_type = OBJ_DELTA;
+ obj_type = (allow_ofs_delta && entry->delta->offset) ?
+ OBJ_OFS_DELTA : OBJ_REF_DELTA;
}
/*
* 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.
+ * more bytes of length.
*/
hdrlen = encode_header(obj_type, size, header);
sha1write(f, header, hdrlen);
- if (entry->delta) {
- sha1write(f, entry->delta, 20);
+ if (obj_type == OBJ_OFS_DELTA) {
+ /*
+ * Deltas with relative base contain an additional
+ * encoding of the relative offset for the delta
+ * base from this object's position in the pack.
+ */
+ off_t ofs = entry->offset - entry->delta->offset;
+ unsigned pos = sizeof(header) - 1;
+ header[pos] = ofs & 127;
+ while (ofs >>= 7)
+ header[--pos] = 128 | (--ofs & 127);
+ sha1write(f, header + pos, sizeof(header) - pos);
+ hdrlen += sizeof(header) - pos;
+ } else if (obj_type == OBJ_REF_DELTA) {
+ /*
+ * Deltas with a base reference contain
+ * an additional 20 bytes for the base sha1.
+ */
+ sha1write(f, entry->delta->sha1, 20);
hdrlen += 20;
}
datalen = sha1write_compressed(f, buf, size);
}
else {
struct packed_git *p = entry->in_pack;
- use_packed_git(p);
+ struct pack_window *w_curs = NULL;
+ off_t offset;
- datalen = find_packed_object_size(p, entry->in_pack_offset);
- buf = (char *) p->pack_base + entry->in_pack_offset;
+ if (entry->delta) {
+ obj_type = (allow_ofs_delta && entry->delta->offset) ?
+ OBJ_OFS_DELTA : OBJ_REF_DELTA;
+ reused_delta++;
+ }
+ hdrlen = encode_header(obj_type, entry->size, header);
+ sha1write(f, header, hdrlen);
+ if (obj_type == OBJ_OFS_DELTA) {
+ off_t ofs = entry->offset - entry->delta->offset;
+ unsigned pos = sizeof(header) - 1;
+ header[pos] = ofs & 127;
+ while (ofs >>= 7)
+ header[--pos] = 128 | (--ofs & 127);
+ sha1write(f, header + pos, sizeof(header) - pos);
+ hdrlen += sizeof(header) - pos;
+ } else if (obj_type == OBJ_REF_DELTA) {
+ sha1write(f, entry->delta->sha1, 20);
+ hdrlen += 20;
+ }
- if (revalidate_pack_entry(entry))
+ offset = entry->in_pack_offset + entry->in_pack_header_size;
+ datalen = find_packed_object_size(p, entry->in_pack_offset)
+ - entry->in_pack_header_size;
+ if (!pack_to_stdout && check_pack_inflate(p, &w_curs,
+ offset, datalen, entry->size))
die("corrupt delta in pack %s", sha1_to_hex(entry->sha1));
- sha1write(f, buf, datalen);
- unuse_packed_git(p);
- hdrlen = 0; /* not really */
- if (obj_type == OBJ_DELTA)
- reused_delta++;
+ copy_pack_data(f, p, &w_curs, offset, datalen);
+ unuse_pack(&w_curs);
reused++;
}
- if (obj_type == OBJ_DELTA)
+ if (entry->delta)
written_delta++;
written++;
return hdrlen + datalen;
}
-static unsigned long write_one(struct sha1file *f,
+static off_t write_one(struct sha1file *f,
struct object_entry *e,
- unsigned long offset)
+ off_t offset)
{
- if (e->offset)
+ if (e->offset || e->preferred_base)
/* 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 deltified, write out its base object. */
+ /* if we are deltified, write out its base object first. */
if (e->delta)
offset = write_one(f, e->delta, offset);
- return offset;
+ e->offset = offset;
+ return offset + write_object(f, e);
}
static void write_pack_file(void)
{
- int i;
+ uint32_t i;
struct sha1file *f;
- unsigned long offset;
+ off_t offset;
struct pack_header hdr;
unsigned last_percent = 999;
- int do_progress = 0;
+ int do_progress = progress;
- if (!base_name)
+ if (!base_name) {
f = sha1fd(1, "<stdout>");
- else {
+ do_progress >>= 1;
+ }
+ else
f = sha1create("%s-%s.%s", base_name,
sha1_to_hex(object_list_sha1), "pack");
- do_progress = progress;
- }
if (do_progress)
- fprintf(stderr, "Writing %d objects.\n", nr_result);
+ fprintf(stderr, "Writing %u objects.\n", nr_result);
hdr.hdr_signature = htonl(PACK_SIGNATURE);
hdr.hdr_version = htonl(PACK_VERSION);
if (do_progress)
fputc('\n', stderr);
done:
+ if (written != nr_result)
+ die("wrote %u objects while expecting %u", written, nr_result);
sha1close(f, pack_file_sha1, 1);
}
static void write_index_file(void)
{
- int i;
+ uint32_t i;
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_result;
- unsigned int array[256];
+ uint32_t array[256];
/*
* Write the first-level table (the list is sorted,
array[i] = htonl(next - sorted_by_sha);
list = next;
}
- sha1write(f, array, 256 * sizeof(int));
+ sha1write(f, array, 256 * 4);
/*
* Write the actual SHA1 entries..
list = sorted_by_sha;
for (i = 0; i < nr_result; i++) {
struct object_entry *entry = *list++;
- unsigned int offset = htonl(entry->offset);
+ uint32_t offset = htonl(entry->offset);
sha1write(f, &offset, 4);
sha1write(f, entry->sha1, 20);
}
static void rehash_objects(void)
{
- int i;
+ uint32_t i;
struct object_entry *oe;
object_ix_hashsz = nr_objects * 3;
static int add_object_entry(const unsigned char *sha1, unsigned hash, int exclude)
{
- unsigned int idx = nr_objects;
+ uint32_t idx = nr_objects;
struct object_entry *entry;
struct packed_git *p;
- unsigned int found_offset = 0;
+ off_t found_offset = 0;
struct packed_git *found_pack = NULL;
int ix, status = 0;
if (!exclude) {
for (p = packed_git; p; p = p->next) {
- struct pack_entry e;
- if (find_pack_entry_one(sha1, &e, p)) {
+ off_t offset = find_pack_entry_one(sha1, p);
+ if (offset) {
if (incremental)
return 0;
if (local && !p->pack_local)
return 0;
if (!found_pack) {
- found_offset = e.offset;
- found_pack = e.p;
+ found_offset = offset;
+ found_pack = p;
}
}
}
goto already_added;
if (idx >= nr_alloc) {
- unsigned int needed = (idx + 1024) * 3 / 2;
- objects = xrealloc(objects, needed * sizeof(*entry));
- nr_alloc = needed;
+ nr_alloc = (idx + 1024) * 3 / 2;
+ objects = xrealloc(objects, nr_alloc * sizeof(*entry));
}
entry = objects + idx;
nr_objects = idx + 1;
already_added:
if (progress_update) {
- fprintf(stderr, "Counting objects...%d\r", nr_objects);
+ fprintf(stderr, "Counting objects...%u\r", nr_objects);
progress_update = 0;
}
if (exclude)
struct pbase_tree_cache *ent, *nent;
void *data;
unsigned long size;
- char type[20];
+ enum object_type type;
int neigh;
int my_ix = pbase_tree_cache_ix(sha1);
int available_ix = -1;
/* Did not find one. Either we got a bogus request or
* we need to read and perhaps cache.
*/
- data = read_sha1_file(sha1, type, &size);
+ data = read_sha1_file(sha1, &type, &size);
if (!data)
return NULL;
- if (strcmp(type, tree_type)) {
+ if (type != OBJ_TREE) {
free(data);
return NULL;
}
while (tree_entry(tree,&entry)) {
unsigned long size;
- char type[20];
+ enum object_type type;
if (entry.pathlen != cmplen ||
memcmp(entry.path, name, cmplen) ||
!has_sha1_file(entry.sha1) ||
- sha1_object_info(entry.sha1, type, &size))
+ (type = sha1_object_info(entry.sha1, &size)) < 0)
continue;
if (name[cmplen] != '/') {
unsigned hash = name_hash(fullname);
add_object_entry(entry.sha1, hash, 1);
return;
}
- if (!strcmp(type, tree_type)) {
+ if (type == OBJ_TREE) {
struct tree_desc sub;
struct pbase_tree_cache *tree;
const char *down = name+cmplen+1;
return 0;
}
-static void add_preferred_base_object(char *name, unsigned hash)
+static void add_preferred_base_object(const char *name, unsigned hash)
{
struct pbase_tree *it;
int cmplen = name_cmp_len(name);
unsigned long size;
unsigned char tree_sha1[20];
+ if (window <= num_preferred_base++)
+ return;
+
data = read_object_with_reference(sha1, tree_type, &size, tree_sha1);
if (!data)
return;
static void check_object(struct object_entry *entry)
{
- char type[20];
-
if (entry->in_pack && !entry->preferred_base) {
- unsigned char base[20];
- unsigned long size;
- struct object_entry *base_entry;
+ struct packed_git *p = entry->in_pack;
+ struct pack_window *w_curs = NULL;
+ unsigned long size, used;
+ unsigned int avail;
+ unsigned char *buf;
+ struct object_entry *base_entry = NULL;
+
+ buf = use_pack(p, &w_curs, entry->in_pack_offset, &avail);
/* We want in_pack_type even if we do not reuse delta.
* There is no point not reusing non-delta representations.
*/
- check_reuse_pack_delta(entry->in_pack,
- entry->in_pack_offset,
- base, &size,
- &entry->in_pack_type);
+ used = unpack_object_header_gently(buf, avail,
+ &entry->in_pack_type, &size);
/* Check if it is delta, and the base is also an object
* we are going to pack. If so we will reuse the existing
* delta.
*/
- if (!no_reuse_delta &&
- entry->in_pack_type == OBJ_DELTA &&
- (base_entry = locate_object_entry(base)) &&
- (!base_entry->preferred_base)) {
+ if (!no_reuse_delta) {
+ unsigned char c, *base_name;
+ off_t ofs;
+ unsigned long used_0;
+ /* there is at least 20 bytes left in the pack */
+ switch (entry->in_pack_type) {
+ case OBJ_REF_DELTA:
+ base_name = use_pack(p, &w_curs,
+ entry->in_pack_offset + used, NULL);
+ used += 20;
+ break;
+ case OBJ_OFS_DELTA:
+ buf = use_pack(p, &w_curs,
+ entry->in_pack_offset + used, NULL);
+ used_0 = 0;
+ c = buf[used_0++];
+ ofs = c & 127;
+ while (c & 128) {
+ ofs += 1;
+ if (!ofs || ofs & ~(~0UL >> 7))
+ die("delta base offset overflow in pack for %s",
+ sha1_to_hex(entry->sha1));
+ 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->sha1));
+ ofs = entry->in_pack_offset - ofs;
+ base_name = find_packed_object_name(p, ofs);
+ used += used_0;
+ break;
+ default:
+ base_name = NULL;
+ }
+ if (base_name)
+ base_entry = locate_object_entry(base_name);
+ }
+ unuse_pack(&w_curs);
+ entry->in_pack_header_size = used;
+
+ if (base_entry) {
/* Depth value does not matter - find_deltas()
* will never consider reused delta as the
*/
/* uncompressed size of the delta data */
- entry->size = entry->delta_size = size;
+ entry->size = size;
entry->delta = base_entry;
- entry->type = OBJ_DELTA;
+ entry->type = entry->in_pack_type;
entry->delta_sibling = base_entry->delta_child;
base_entry->delta_child = entry;
/* Otherwise we would do the usual */
}
- if (sha1_object_info(entry->sha1, type, &entry->size))
+ entry->type = sha1_object_info(entry->sha1, &entry->size);
+ if (entry->type < 0)
die("unable to get type of object %s",
sha1_to_hex(entry->sha1));
-
- if (!strcmp(type, commit_type)) {
- entry->type = OBJ_COMMIT;
- } else if (!strcmp(type, tree_type)) {
- entry->type = OBJ_TREE;
- } else if (!strcmp(type, blob_type)) {
- entry->type = OBJ_BLOB;
- } else if (!strcmp(type, tag_type)) {
- entry->type = OBJ_TAG;
- } else
- die("unable to pack object %s of type %s",
- sha1_to_hex(entry->sha1), type);
}
static unsigned int check_delta_limit(struct object_entry *me, unsigned int n)
static void get_object_details(void)
{
- int i;
+ uint32_t i;
struct object_entry *entry;
prepare_pack_ix();
static struct object_entry **create_sorted_list(entry_sort_t sort)
{
struct object_entry **list = xmalloc(nr_objects * sizeof(struct object_entry *));
- int i;
+ uint32_t i;
for (i = 0; i < nr_objects; i++)
list[i] = objects + i;
static struct object_entry **create_final_object_list(void)
{
struct object_entry **list;
- int i, j;
+ uint32_t i, j;
for (i = nr_result = 0; i < nr_objects; i++)
if (!objects[i].preferred_base)
struct object_entry *trg_entry = trg->entry;
struct object_entry *src_entry = src->entry;
unsigned long trg_size, src_size, delta_size, sizediff, max_size, sz;
- char type[10];
+ enum object_type type;
void *delta_buf;
/* Don't bother doing diffs between different types */
* on an earlier try, but only when reusing delta data.
*/
if (!no_reuse_delta && trg_entry->in_pack &&
- trg_entry->in_pack == src_entry->in_pack)
+ trg_entry->in_pack == src_entry->in_pack &&
+ trg_entry->in_pack_type != OBJ_REF_DELTA &&
+ trg_entry->in_pack_type != OBJ_OFS_DELTA)
return 0;
/*
/* Load data if not already done */
if (!trg->data) {
- trg->data = read_sha1_file(trg_entry->sha1, type, &sz);
+ trg->data = read_sha1_file(trg_entry->sha1, &type, &sz);
if (sz != trg_size)
die("object %s inconsistent object length (%lu vs %lu)",
sha1_to_hex(trg_entry->sha1), sz, trg_size);
}
if (!src->data) {
- src->data = read_sha1_file(src_entry->sha1, type, &sz);
+ src->data = read_sha1_file(src_entry->sha1, &type, &sz);
if (sz != src_size)
die("object %s inconsistent object length (%lu vs %lu)",
sha1_to_hex(src_entry->sha1), sz, src_size);
static void find_deltas(struct object_entry **list, int window, int depth)
{
- int i, idx;
+ uint32_t i = nr_objects, idx = 0, processed = 0;
unsigned int array_size = window * sizeof(struct unpacked);
- struct unpacked *array = xmalloc(array_size);
- unsigned processed = 0;
+ struct unpacked *array;
unsigned last_percent = 999;
+ if (!nr_objects)
+ return;
+ array = xmalloc(array_size);
memset(array, 0, array_size);
- i = nr_objects;
- idx = 0;
if (progress)
- fprintf(stderr, "Deltifying %d objects.\n", nr_result);
+ fprintf(stderr, "Deltifying %u objects.\n", nr_result);
- while (--i >= 0) {
- struct object_entry *entry = list[i];
+ do {
+ struct object_entry *entry = list[--i];
struct unpacked *n = array + idx;
int j;
j = window;
while (--j > 0) {
- unsigned int other_idx = idx + j;
+ uint32_t other_idx = idx + j;
struct unpacked *m;
if (other_idx >= window)
other_idx -= window;
idx++;
if (idx >= window)
idx = 0;
- }
+ } while (i > 0);
if (progress)
fputc('\n', stderr);
}
if (progress)
- fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects,
+ fprintf(stderr, "Reusing %u objects pack %s\n", nr_objects,
sha1_to_hex(sha1));
if (pack_to_stdout) {
return git_default_config(k, v);
}
+static void read_object_list_from_stdin(void)
+{
+ char line[40 + 1 + PATH_MAX + 2];
+ unsigned char sha1[20];
+ unsigned hash;
+
+ for (;;) {
+ if (!fgets(line, sizeof(line), stdin)) {
+ if (feof(stdin))
+ break;
+ if (!ferror(stdin))
+ die("fgets returned NULL, not EOF, not error!");
+ if (errno != EINTR)
+ die("fgets: %s", strerror(errno));
+ clearerr(stdin);
+ continue;
+ }
+ if (line[0] == '-') {
+ if (get_sha1_hex(line+1, sha1))
+ die("expected edge sha1, got garbage:\n %s",
+ line);
+ add_preferred_base(sha1);
+ continue;
+ }
+ if (get_sha1_hex(line, sha1))
+ die("expected sha1, got garbage:\n %s", line);
+
+ hash = name_hash(line+41);
+ add_preferred_base_object(line+41, hash);
+ add_object_entry(sha1, hash, 0);
+ }
+}
+
+static void show_commit(struct commit *commit)
+{
+ unsigned hash = name_hash("");
+ add_preferred_base_object("", hash);
+ add_object_entry(commit->object.sha1, hash, 0);
+}
+
+static void show_object(struct object_array_entry *p)
+{
+ unsigned hash = name_hash(p->name);
+ add_preferred_base_object(p->name, hash);
+ add_object_entry(p->item->sha1, hash, 0);
+}
+
+static void show_edge(struct commit *commit)
+{
+ add_preferred_base(commit->object.sha1);
+}
+
+static void get_object_list(int ac, const char **av)
+{
+ struct rev_info revs;
+ char line[1000];
+ int flags = 0;
+
+ init_revisions(&revs, NULL);
+ save_commit_buffer = 0;
+ track_object_refs = 0;
+ setup_revisions(ac, av, &revs, NULL);
+
+ while (fgets(line, sizeof(line), stdin) != NULL) {
+ int len = strlen(line);
+ if (line[len - 1] == '\n')
+ line[--len] = 0;
+ if (!len)
+ break;
+ if (*line == '-') {
+ if (!strcmp(line, "--not")) {
+ flags ^= UNINTERESTING;
+ continue;
+ }
+ die("not a rev '%s'", line);
+ }
+ if (handle_revision_arg(line, &revs, flags, 1))
+ die("bad revision '%s'", line);
+ }
+
+ prepare_revision_walk(&revs);
+ mark_edges_uninteresting(revs.commits, &revs, show_edge);
+ traverse_commit_list(&revs, show_commit, show_object);
+}
+
int cmd_pack_objects(int argc, const char **argv, const char *prefix)
{
SHA_CTX ctx;
- char line[40 + 1 + PATH_MAX + 2];
int depth = 10;
struct object_entry **list;
- int num_preferred_base = 0;
- int i;
+ int use_internal_rev_list = 0;
+ int thin = 0;
+ uint32_t i;
+ const char **rp_av;
+ int rp_ac_alloc = 64;
+ int rp_ac;
+
+ rp_av = xcalloc(rp_ac_alloc, sizeof(*rp_av));
+
+ rp_av[0] = "pack-objects";
+ rp_av[1] = "--objects"; /* --thin will make it --objects-edge */
+ rp_ac = 2;
git_config(git_pack_config);
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("--progress", arg)) {
- progress = 1;
- continue;
- }
- if (!strcmp("--incremental", arg)) {
- incremental = 1;
- continue;
- }
- if (!strncmp("--window=", arg, 9)) {
- char *end;
- window = strtoul(arg+9, &end, 0);
- if (!arg[9] || *end)
- usage(pack_usage);
- continue;
- }
- if (!strncmp("--depth=", arg, 8)) {
- char *end;
- depth = strtoul(arg+8, &end, 0);
- if (!arg[8] || *end)
- usage(pack_usage);
- continue;
- }
- if (!strcmp("--progress", arg)) {
- progress = 1;
- continue;
- }
- if (!strcmp("-q", arg)) {
- progress = 0;
- continue;
- }
- if (!strcmp("--no-reuse-delta", arg)) {
- no_reuse_delta = 1;
- continue;
- }
- if (!strcmp("--stdout", arg)) {
- pack_to_stdout = 1;
- continue;
+ if (*arg != '-')
+ break;
+
+ if (!strcmp("--non-empty", arg)) {
+ non_empty = 1;
+ continue;
+ }
+ if (!strcmp("--local", arg)) {
+ local = 1;
+ continue;
+ }
+ if (!strcmp("--incremental", arg)) {
+ incremental = 1;
+ continue;
+ }
+ if (!prefixcmp(arg, "--window=")) {
+ char *end;
+ window = strtoul(arg+9, &end, 0);
+ if (!arg[9] || *end)
+ usage(pack_usage);
+ continue;
+ }
+ if (!prefixcmp(arg, "--depth=")) {
+ char *end;
+ depth = strtoul(arg+8, &end, 0);
+ if (!arg[8] || *end)
+ usage(pack_usage);
+ continue;
+ }
+ if (!strcmp("--progress", arg)) {
+ progress = 1;
+ continue;
+ }
+ if (!strcmp("--all-progress", arg)) {
+ progress = 2;
+ continue;
+ }
+ if (!strcmp("-q", arg)) {
+ progress = 0;
+ continue;
+ }
+ if (!strcmp("--no-reuse-delta", arg)) {
+ no_reuse_delta = 1;
+ continue;
+ }
+ if (!strcmp("--delta-base-offset", arg)) {
+ allow_ofs_delta = 1;
+ continue;
+ }
+ if (!strcmp("--stdout", arg)) {
+ pack_to_stdout = 1;
+ continue;
+ }
+ if (!strcmp("--revs", arg)) {
+ use_internal_rev_list = 1;
+ continue;
+ }
+ if (!strcmp("--unpacked", arg) ||
+ !prefixcmp(arg, "--unpacked=") ||
+ !strcmp("--reflog", arg) ||
+ !strcmp("--all", arg)) {
+ use_internal_rev_list = 1;
+ if (rp_ac >= rp_ac_alloc - 1) {
+ rp_ac_alloc = alloc_nr(rp_ac_alloc);
+ rp_av = xrealloc(rp_av,
+ rp_ac_alloc * sizeof(*rp_av));
}
- usage(pack_usage);
+ rp_av[rp_ac++] = arg;
+ continue;
}
- if (base_name)
- usage(pack_usage);
- base_name = arg;
+ if (!strcmp("--thin", arg)) {
+ use_internal_rev_list = 1;
+ thin = 1;
+ rp_av[1] = "--objects-edge";
+ continue;
+ }
+ usage(pack_usage);
}
+ /* Traditionally "pack-objects [options] base extra" failed;
+ * we would however want to take refs parameter that would
+ * have been given to upstream rev-list ourselves, which means
+ * we somehow want to say what the base name is. So the
+ * syntax would be:
+ *
+ * pack-objects [options] base <refs...>
+ *
+ * in other words, we would treat the first non-option as the
+ * base_name and send everything else to the internal revision
+ * walker.
+ */
+
+ if (!pack_to_stdout)
+ base_name = argv[i++];
+
if (pack_to_stdout != !base_name)
usage(pack_usage);
+ if (!pack_to_stdout && thin)
+ die("--thin cannot be used to build an indexable pack.");
+
prepare_packed_git();
if (progress) {
setup_progress_signal();
}
- for (;;) {
- unsigned char sha1[20];
- unsigned hash;
-
- if (!fgets(line, sizeof(line), stdin)) {
- if (feof(stdin))
- break;
- if (!ferror(stdin))
- die("fgets returned NULL, not EOF, not error!");
- if (errno != EINTR)
- die("fgets: %s", strerror(errno));
- clearerr(stdin);
- continue;
- }
-
- if (line[0] == '-') {
- if (get_sha1_hex(line+1, sha1))
- die("expected edge sha1, got garbage:\n %s",
- line+1);
- if (num_preferred_base++ < window)
- add_preferred_base(sha1);
- continue;
- }
- if (get_sha1_hex(line, sha1))
- die("expected sha1, got garbage:\n %s", line);
- hash = name_hash(line+41);
- add_preferred_base_object(line+41, hash);
- add_object_entry(sha1, hash, 0);
+ if (!use_internal_rev_list)
+ read_object_list_from_stdin();
+ else {
+ rp_av[rp_ac] = NULL;
+ get_object_list(rp_ac, rp_av);
}
+
if (progress)
- fprintf(stderr, "Done counting %d objects.\n", nr_objects);
+ fprintf(stderr, "Done counting %u objects.\n", nr_objects);
sorted_by_sha = create_final_object_list();
if (non_empty && !nr_result)
return 0;
}
SHA1_Final(object_list_sha1, &ctx);
if (progress && (nr_objects != nr_result))
- fprintf(stderr, "Result has %d objects.\n", nr_result);
+ fprintf(stderr, "Result has %u objects.\n", nr_result);
if (reuse_cached_pack(object_list_sha1))
;
else {
if (nr_result)
prepare_pack(window, depth);
- if (progress && pack_to_stdout) {
+ if (progress == 1 && pack_to_stdout) {
/* the other end usually displays progress itself */
struct itimerval v = {{0,},};
setitimer(ITIMER_REAL, &v, NULL);
}
}
if (progress)
- fprintf(stderr, "Total %d, written %d (delta %d), reused %d (delta %d)\n",
- nr_result, written, written_delta, reused, reused_delta);
+ fprintf(stderr, "Total %u (delta %u), reused %u (delta %u)\n",
+ written, written_delta, reused, reused_delta);
return 0;
}