![[tokkee]](http://tokkee.org/images/avatar.png){kind=avatar}
diff --git a/index-pack.c b/index-pack.c
index 58c4a9c41dd7a05b86d40e6eeee33ba0a3fb6c4f..9c0c27813fd6736218d1caaed6248e4ae4d388b5 100644 (file)
--- a/index-pack.c
+++ b/index-pack.c
#include "tag.h"
#include "tree.h"
#include "progress.h"
+#include "fsck.h"
static const char index_pack_usage[] =
-"git-index-pack [-v] [-o <index-file>] [{ ---keep | --keep=<msg> }] { <pack-file> | --stdin [--fix-thin] [<pack-file>] }";
+"git-index-pack [-v] [-o <index-file>] [{ ---keep | --keep=<msg> }] [--strict] { <pack-file> | --stdin [--fix-thin] [<pack-file>] }";
struct object_entry
{
- off_t offset;
+ struct pack_idx_entry idx;
unsigned long size;
unsigned int hdr_size;
- uint32_t crc32;
enum object_type type;
enum object_type real_type;
- unsigned char sha1[20];
};
union delta_base {
*/
#define UNION_BASE_SZ 20
+#define FLAG_LINK (1u<<20)
+#define FLAG_CHECKED (1u<<21)
+
struct delta_entry
{
union delta_base base;
static int nr_resolved_deltas;
static int from_stdin;
+static int strict;
static int verbose;
-static struct progress progress;
+static struct progress *progress;
/* We always read in 4kB chunks. */
static unsigned char input_buffer[4096];
static uint32_t input_crc32;
static int input_fd, output_fd, pack_fd;
+static int mark_link(struct object *obj, int type, void *data)
+{
+ if (!obj)
+ return -1;
+
+ if (type != OBJ_ANY && obj->type != type)
+ die("object type mismatch at %s", sha1_to_hex(obj->sha1));
+
+ obj->flags |= FLAG_LINK;
+ return 0;
+}
+
+/* The content of each linked object must have been checked
+ or it must be already present in the object database */
+static void check_object(struct object *obj)
+{
+ if (!obj)
+ return;
+
+ if (!(obj->flags & FLAG_LINK))
+ return;
+
+ if (!(obj->flags & FLAG_CHECKED)) {
+ unsigned long size;
+ int type = sha1_object_info(obj->sha1, &size);
+ if (type != obj->type || type <= 0)
+ die("object of unexpected type");
+ obj->flags |= FLAG_CHECKED;
+ return;
+ }
+}
+
+static void check_objects(void)
+{
+ unsigned i, max;
+
+ max = get_max_object_index();
+ for (i = 0; i < max; i++)
+ check_object(get_indexed_object(i));
+}
+
+
/* Discard current buffer used content. */
static void flush(void)
{
die("read error on input: %s", strerror(errno));
}
input_len += ret;
+ if (from_stdin)
+ display_throughput(progress, consumed_bytes + input_len);
} while (input_len < min);
return input_buffer;
}
consumed_bytes += bytes;
}
-static const char *open_pack_file(const char *pack_name)
+static char *open_pack_file(char *pack_name)
{
if (from_stdin) {
input_fd = 0;
static char tmpfile[PATH_MAX];
snprintf(tmpfile, sizeof(tmpfile),
"%s/tmp_pack_XXXXXX", get_object_directory());
- output_fd = mkstemp(tmpfile);
+ output_fd = xmkstemp(tmpfile);
pack_name = xstrdup(tmpfile);
} else
output_fd = open(pack_name, O_CREAT|O_EXCL|O_RDWR, 0600);
@@ -197,7 +244,7 @@ static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_
unsigned shift;
void *data;
- obj->offset = consumed_bytes;
+ obj->idx.offset = consumed_bytes;
input_crc32 = crc32(0, Z_NULL, 0);
p = fill(1);
@@ -229,15 +276,15 @@ static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_
while (c & 128) {
base_offset += 1;
if (!base_offset || MSB(base_offset, 7))
- bad_object(obj->offset, "offset value overflow for delta base object");
+ bad_object(obj->idx.offset, "offset value overflow for delta base object");
p = fill(1);
c = *p;
use(1);
base_offset = (base_offset << 7) + (c & 127);
}
- delta_base->offset = obj->offset - base_offset;
- if (delta_base->offset >= obj->offset)
- bad_object(obj->offset, "delta base offset is out of bound");
+ delta_base->offset = obj->idx.offset - base_offset;
+ if (delta_base->offset >= obj->idx.offset)
+ bad_object(obj->idx.offset, "delta base offset is out of bound");
break;
case OBJ_COMMIT:
case OBJ_TREE:
@@ -245,19 +292,19 @@ static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_
case OBJ_TAG:
break;
default:
- bad_object(obj->offset, "unknown object type %d", obj->type);
+ bad_object(obj->idx.offset, "unknown object type %d", obj->type);
}
- obj->hdr_size = consumed_bytes - obj->offset;
+ obj->hdr_size = consumed_bytes - obj->idx.offset;
- data = unpack_entry_data(obj->offset, obj->size);
- obj->crc32 = input_crc32;
+ data = unpack_entry_data(obj->idx.offset, obj->size);
+ obj->idx.crc32 = input_crc32;
return data;
}
static void *get_data_from_pack(struct object_entry *obj)
{
- unsigned long from = obj[0].offset + obj[0].hdr_size;
- unsigned long len = obj[1].offset - from;
+ off_t from = obj[0].idx.offset + obj[0].hdr_size;
+ unsigned long len = obj[1].idx.offset - from;
unsigned long rdy = 0;
unsigned char *src, *data;
z_stream stream;
die("SHA1 COLLISION FOUND WITH %s !", sha1_to_hex(sha1));
free(has_data);
}
+ if (strict) {
+ if (type == OBJ_BLOB) {
+ struct blob *blob = lookup_blob(sha1);
+ if (blob)
+ blob->object.flags |= FLAG_CHECKED;
+ else
+ die("invalid blob object %s", sha1_to_hex(sha1));
+ } else {
+ struct object *obj;
+ int eaten;
+ void *buf = (void *) data;
+
+ /*
+ * we do not need to free the memory here, as the
+ * buf is deleted by the caller.
+ */
+ obj = parse_object_buffer(sha1, type, size, buf, &eaten);
+ if (!obj)
+ die("invalid %s", typename(type));
+ if (fsck_object(obj, 1, fsck_error_function))
+ die("Error in object");
+ if (fsck_walk(obj, mark_link, 0))
+ die("Not all child objects of %s are reachable", sha1_to_hex(obj->sha1));
+
+ if (obj->type == OBJ_TREE) {
+ struct tree *item = (struct tree *) obj;
+ item->buffer = NULL;
+ }
+ if (obj->type == OBJ_COMMIT) {
+ struct commit *commit = (struct commit *) obj;
+ commit->buffer = NULL;
+ }
+ obj->flags |= FLAG_CHECKED;
+ }
+ }
}
static void resolve_delta(struct object_entry *delta_obj, void *base_data,
&result_size);
free(delta_data);
if (!result)
- bad_object(delta_obj->offset, "failed to apply delta");
- sha1_object(result, result_size, type, delta_obj->sha1);
+ bad_object(delta_obj->idx.offset, "failed to apply delta");
+ sha1_object(result, result_size, type, delta_obj->idx.sha1);
nr_resolved_deltas++;
- hashcpy(delta_base.sha1, delta_obj->sha1);
+ hashcpy(delta_base.sha1, delta_obj->idx.sha1);
if (!find_delta_children(&delta_base, &first, &last)) {
for (j = first; j <= last; j++) {
struct object_entry *child = objects + deltas[j].obj_no;
}
memset(&delta_base, 0, sizeof(delta_base));
- delta_base.offset = delta_obj->offset;
+ delta_base.offset = delta_obj->idx.offset;
if (!find_delta_children(&delta_base, &first, &last)) {
for (j = first; j <= last; j++) {
struct object_entry *child = objects + deltas[j].obj_no;
* - remember base (SHA1 or offset) for all deltas.
*/
if (verbose)
- start_progress(&progress, "Indexing %u objects...", "", nr_objects);
+ progress = start_progress(
+ from_stdin ? "Receiving objects" : "Indexing objects",
+ nr_objects);
for (i = 0; i < nr_objects; i++) {
struct object_entry *obj = &objects[i];
data = unpack_raw_entry(obj, &delta->base);
delta->obj_no = i;
delta++;
} else
- sha1_object(data, obj->size, obj->type, obj->sha1);
+ sha1_object(data, obj->size, obj->type, obj->idx.sha1);
free(data);
- if (verbose)
- display_progress(&progress, i+1);
+ display_progress(progress, i+1);
}
- objects[i].offset = consumed_bytes;
- if (verbose)
- stop_progress(&progress);
+ objects[i].idx.offset = consumed_bytes;
+ stop_progress(&progress);
/* Check pack integrity */
flush();
* for some more deltas.
*/
if (verbose)
- start_progress(&progress, "Resolving %u deltas...", "", nr_deltas);
+ progress = start_progress("Resolving deltas", nr_deltas);
for (i = 0; i < nr_objects; i++) {
struct object_entry *obj = &objects[i];
union delta_base base;
if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA)
continue;
- hashcpy(base.sha1, obj->sha1);
+ hashcpy(base.sha1, obj->idx.sha1);
ref = !find_delta_children(&base, &ref_first, &ref_last);
memset(&base, 0, sizeof(base));
- base.offset = obj->offset;
+ base.offset = obj->idx.offset;
ofs = !find_delta_children(&base, &ofs_first, &ofs_last);
if (!ref && !ofs)
continue;
obj->size, obj->type);
}
free(data);
- if (verbose)
- display_progress(&progress, nr_resolved_deltas);
+ display_progress(progress, nr_resolved_deltas);
}
}
}
header[n++] = c;
write_or_die(output_fd, header, n);
- obj[0].crc32 = crc32(0, Z_NULL, 0);
- obj[0].crc32 = crc32(obj[0].crc32, header, n);
- obj[1].offset = obj[0].offset + n;
- obj[1].offset += write_compressed(output_fd, buf, size, &obj[0].crc32);
- hashcpy(obj->sha1, sha1);
+ obj[0].idx.crc32 = crc32(0, Z_NULL, 0);
+ obj[0].idx.crc32 = crc32(obj[0].idx.crc32, header, n);
+ obj[1].idx.offset = obj[0].idx.offset + n;
+ obj[1].idx.offset += write_compressed(output_fd, buf, size, &obj[0].idx.crc32);
+ hashcpy(obj->idx.sha1, sha1);
}
static int delta_pos_compare(const void *_a, const void *_b)
die("local object %s is corrupt", sha1_to_hex(d->base.sha1));
append_obj_to_pack(d->base.sha1, data, size, type);
free(data);
- if (verbose)
- display_progress(&progress, nr_resolved_deltas);
+ display_progress(progress, nr_resolved_deltas);
}
free(sorted_by_pos);
}
-static uint32_t index_default_version = 1;
-static uint32_t index_off32_limit = 0x7fffffff;
-
-static int sha1_compare(const void *_a, const void *_b)
-{
- struct object_entry *a = *(struct object_entry **)_a;
- struct object_entry *b = *(struct object_entry **)_b;
- return hashcmp(a->sha1, b->sha1);
-}
-
-/*
- * On entry *sha1 contains the pack content SHA1 hash, on exit it is
- * the SHA1 hash of sorted object names.
- */
-static const char *write_index_file(const char *index_name, unsigned char *sha1)
-{
- struct sha1file *f;
- struct object_entry **sorted_by_sha, **list, **last;
- uint32_t array[256];
- int i, fd;
- SHA_CTX ctx;
- uint32_t index_version;
-
- if (nr_objects) {
- sorted_by_sha =
- xcalloc(nr_objects, sizeof(struct object_entry *));
- list = sorted_by_sha;
- last = sorted_by_sha + nr_objects;
- for (i = 0; i < nr_objects; ++i)
- sorted_by_sha[i] = &objects[i];
- qsort(sorted_by_sha, nr_objects, sizeof(sorted_by_sha[0]),
- sha1_compare);
- }
- else
- sorted_by_sha = list = last = NULL;
-
- if (!index_name) {
- static char tmpfile[PATH_MAX];
- snprintf(tmpfile, sizeof(tmpfile),
- "%s/tmp_idx_XXXXXX", get_object_directory());
- fd = mkstemp(tmpfile);
- index_name = xstrdup(tmpfile);
- } else {
- unlink(index_name);
- fd = open(index_name, O_CREAT|O_EXCL|O_WRONLY, 0600);
- }
- if (fd < 0)
- die("unable to create %s: %s", index_name, strerror(errno));
- f = sha1fd(fd, index_name);
-
- /* if last object's offset is >= 2^31 we should use index V2 */
- index_version = (objects[nr_objects-1].offset >> 31) ? 2 : index_default_version;
-
- /* index versions 2 and above need a header */
- if (index_version >= 2) {
- struct pack_idx_header hdr;
- hdr.idx_signature = htonl(PACK_IDX_SIGNATURE);
- hdr.idx_version = htonl(index_version);
- sha1write(f, &hdr, sizeof(hdr));
- }
-
- /*
- * 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).
- */
- for (i = 0; i < 256; i++) {
- struct object_entry **next = list;
- while (next < last) {
- struct object_entry *obj = *next;
- if (obj->sha1[0] != i)
- break;
- next++;
- }
- array[i] = htonl(next - sorted_by_sha);
- list = next;
- }
- sha1write(f, array, 256 * 4);
-
- /* compute the SHA1 hash of sorted object names. */
- SHA1_Init(&ctx);
-
- /*
- * Write the actual SHA1 entries..
- */
- list = sorted_by_sha;
- for (i = 0; i < nr_objects; i++) {
- struct object_entry *obj = *list++;
- if (index_version < 2) {
- uint32_t offset = htonl(obj->offset);
- sha1write(f, &offset, 4);
- }
- sha1write(f, obj->sha1, 20);
- SHA1_Update(&ctx, obj->sha1, 20);
- }
-
- if (index_version >= 2) {
- unsigned int nr_large_offset = 0;
-
- /* write the crc32 table */
- list = sorted_by_sha;
- for (i = 0; i < nr_objects; i++) {
- struct object_entry *obj = *list++;
- uint32_t crc32_val = htonl(obj->crc32);
- sha1write(f, &crc32_val, 4);
- }
-
- /* write the 32-bit offset table */
- list = sorted_by_sha;
- for (i = 0; i < nr_objects; i++) {
- struct object_entry *obj = *list++;
- uint32_t offset = (obj->offset <= index_off32_limit) ?
- obj->offset : (0x80000000 | nr_large_offset++);
- offset = htonl(offset);
- sha1write(f, &offset, 4);
- }
-
- /* write the large offset table */
- list = sorted_by_sha;
- while (nr_large_offset) {
- struct object_entry *obj = *list++;
- uint64_t offset = obj->offset;
- if (offset > index_off32_limit) {
- uint32_t split[2];
- split[0] = htonl(offset >> 32);
- split[1] = htonl(offset & 0xffffffff);
- sha1write(f, split, 8);
- nr_large_offset--;
- }
- }
- }
-
- sha1write(f, sha1, 20);
- sha1close(f, NULL, 1);
- free(sorted_by_sha);
- SHA1_Final(sha1, &ctx);
- return index_name;
-}
-
static void final(const char *final_pack_name, const char *curr_pack_name,
const char *final_index_name, const char *curr_index_name,
const char *keep_name, const char *keep_msg,
write_or_die(keep_fd, keep_msg, keep_msg_len);
write_or_die(keep_fd, "\n", 1);
}
- close(keep_fd);
+ if (close(keep_fd) != 0)
+ die("cannot write keep file");
report = "keep";
}
}
}
}
+static int git_index_pack_config(const char *k, const char *v)
+{
+ if (!strcmp(k, "pack.indexversion")) {
+ pack_idx_default_version = git_config_int(k, v);
+ if (pack_idx_default_version > 2)
+ die("bad pack.indexversion=%d", pack_idx_default_version);
+ return 0;
+ }
+ return git_default_config(k, v);
+}
+
int main(int argc, char **argv)
{
int i, fix_thin_pack = 0;
- const char *curr_pack, *pack_name = NULL;
- const char *curr_index, *index_name = NULL;
+ char *curr_pack, *pack_name = NULL;
+ char *curr_index, *index_name = NULL;
const char *keep_name = NULL, *keep_msg = NULL;
char *index_name_buf = NULL, *keep_name_buf = NULL;
+ struct pack_idx_entry **idx_objects;
unsigned char sha1[20];
+ git_config(git_index_pack_config);
+
for (i = 1; i < argc; i++) {
- const char *arg = argv[i];
+ char *arg = argv[i];
if (*arg == '-') {
if (!strcmp(arg, "--stdin")) {
from_stdin = 1;
} else if (!strcmp(arg, "--fix-thin")) {
fix_thin_pack = 1;
+ } else if (!strcmp(arg, "--strict")) {
+ strict = 1;
} else if (!strcmp(arg, "--keep")) {
keep_msg = "";
} else if (!prefixcmp(arg, "--keep=")) {
index_name = argv[++i];
} else if (!prefixcmp(arg, "--index-version=")) {
char *c;
- index_default_version = strtoul(arg + 16, &c, 10);
- if (index_default_version > 2)
+ pack_idx_default_version = strtoul(arg + 16, &c, 10);
+ if (pack_idx_default_version > 2)
die("bad %s", arg);
if (*c == ',')
- index_off32_limit = strtoul(c+1, &c, 0);
- if (*c || index_off32_limit & 0x80000000)
+ pack_idx_off32_limit = strtoul(c+1, &c, 0);
+ if (*c || pack_idx_off32_limit & 0x80000000)
die("bad %s", arg);
} else
usage(index_pack_usage);
deltas = xmalloc(nr_objects * sizeof(struct delta_entry));
parse_pack_objects(sha1);
if (nr_deltas == nr_resolved_deltas) {
- if (verbose)
- stop_progress(&progress);
+ stop_progress(&progress);
/* Flush remaining pack final 20-byte SHA1. */
flush();
} else {
if (fix_thin_pack) {
+ char msg[48];
int nr_unresolved = nr_deltas - nr_resolved_deltas;
int nr_objects_initial = nr_objects;
if (nr_unresolved <= 0)
(nr_objects + nr_unresolved + 1)
* sizeof(*objects));
fix_unresolved_deltas(nr_unresolved);
- if (verbose) {
- stop_progress(&progress);
- fprintf(stderr, "%d objects were added to complete this thin pack.\n",
- nr_objects - nr_objects_initial);
- }
+ sprintf(msg, "completed with %d local objects",
+ nr_objects - nr_objects_initial);
+ stop_progress_msg(&progress, msg);
fixup_pack_header_footer(output_fd, sha1,
- curr_pack, nr_objects);
+ curr_pack, nr_objects);
}
if (nr_deltas != nr_resolved_deltas)
die("pack has %d unresolved deltas",
nr_deltas - nr_resolved_deltas);
}
free(deltas);
- curr_index = write_index_file(index_name, sha1);
+ if (strict)
+ check_objects();
+
+ idx_objects = xmalloc((nr_objects) * sizeof(struct pack_idx_entry *));
+ for (i = 0; i < nr_objects; i++)
+ idx_objects[i] = &objects[i].idx;
+ curr_index = write_idx_file(index_name, idx_objects, nr_objects, sha1);
+ free(idx_objects);
+
final(pack_name, curr_pack,
index_name, curr_index,
keep_name, keep_msg,
free(objects);
free(index_name_buf);
free(keep_name_buf);
+ if (pack_name == NULL)
+ free(curr_pack);
+ if (index_name == NULL)
+ free(curr_index);
return 0;
}