#include "commit.h"
#include "tag.h"
#include "tree.h"
-#include <sys/time.h>
-#include <signal.h>
static const char index_pack_usage[] =
-"git-index-pack [-v] [-o <index-file>] { <pack-file> | --stdin [--fix-thin] [<pack-file>] }";
+"git-index-pack [-v] [-o <index-file>]
[{ ---keep | --keep=<msg> }] { <pack-file> | --stdin [--fix-thin] [<pack-file>] }";
struct object_entry
{
- unsigned long offset;
+ off_t offset;
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 {
unsigned char sha1[20];
- unsigned long offset;
+ off_t offset;
};
/*
/* We always read in 4kB chunks. */
static unsigned char input_buffer[4096];
-static unsigned long input_offset, input_len, consumed_bytes;
+static unsigned int input_offset, input_len;
+static off_t consumed_bytes;
static SHA_CTX input_ctx;
-static int input_fd, output_fd, mmap_fd;
+static uint32_t input_crc32;
+static int input_fd, output_fd, pack_fd;
/* Discard current buffer used content. */
-static void flush()
+static void flush(void)
{
if (input_offset) {
if (output_fd >= 0)
write_or_die(output_fd, input_buffer, input_offset);
SHA1_Update(&input_ctx, input_buffer, input_offset);
- memcpy(input_buffer, input_buffer + input_offset, input_len);
+ memmove(input_buffer, input_buffer + input_offset, input_len);
input_offset = 0;
}
}
{
if (bytes > input_len)
die("used more bytes than were available");
+ input_crc32 = crc32(input_crc32, input_buffer + input_offset, bytes);
input_len -= bytes;
input_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;
}
if (!pack_name) {
static char tmpfile[PATH_MAX];
snprintf(tmpfile, sizeof(tmpfile),
- "%s/pack_XXXXXX", get_object_directory());
+ "%s/tmp_pack_XXXXXX", get_object_directory());
output_fd = mkstemp(tmpfile);
pack_name = xstrdup(tmpfile);
} else
output_fd = open(pack_name, O_CREAT|O_EXCL|O_RDWR, 0600);
if (output_fd < 0)
die("unable to create %s: %s\n", pack_name, strerror(errno));
- mmap_fd = output_fd;
+ pack_fd = output_fd;
} else {
input_fd = open(pack_name, O_RDONLY);
if (input_fd < 0)
die("cannot open packfile '%s': %s",
pack_name, strerror(errno));
output_fd = -1;
- mmap_fd = input_fd;
+ pack_fd = input_fd;
}
SHA1_Init(&input_ctx);
return pack_name;
static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_base)
{
unsigned char *p, c;
- unsigned long size, base_offset;
+ unsigned long size;
+ off_t base_offset;
unsigned shift;
+ void *data;
obj->offset = consumed_bytes;
+ input_crc32 = crc32(0, Z_NULL, 0);
p = fill(1);
c = *p;
base_offset = c & 127;
while (c & 128) {
base_offset += 1;
- if (!base_offset || base_offset & ~(~0UL >> 7))
+ if (!base_offset || MSB(base_offset, 7))
bad_object(obj->offset, "offset value overflow for delta base object");
p = fill(1);
c = *p;
case OBJ_TAG:
break;
default:
- bad_object(obj->offset, "bad object type %d", obj->type);
+ bad_object(obj->offset, "unknown object type %d", obj->type);
}
obj->hdr_size = consumed_bytes - obj->offset;
- return unpack_entry_data(obj->offset, obj->size);
+ data = unpack_entry_data(obj->offset, obj->size);
+ obj->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;
- unsigned pg_offset = from % getpagesize();
- unsigned char *map, *data;
+ unsigned long rdy = 0;
+ unsigned char *src, *data;
z_stream stream;
int st;
- map = mmap(NULL, len + pg_offset, PROT_READ, MAP_PRIVATE,
- mmap_fd, from - pg_offset);
- if (map == MAP_FAILED)
- die("cannot mmap pack file: %s", strerror(errno));
+ src = xmalloc(len);
+ data = src;
+ do {
+ ssize_t n = pread(pack_fd, data + rdy, len - rdy, from + rdy);
+ if (n <= 0)
+ die("cannot pread pack file: %s", strerror(errno));
+ rdy += n;
+ } while (rdy < len);
data = xmalloc(obj->size);
memset(&stream, 0, sizeof(stream));
stream.next_out = data;
stream.avail_out = obj->size;
- stream.next_in = map + pg_offset;
+ stream.next_in = src;
stream.avail_in = len;
inflateInit(&stream);
while ((st = inflate(&stream, Z_FINISH)) == Z_OK);
inflateEnd(&stream);
if (st != Z_STREAM_END || stream.total_out != obj->size)
die("serious inflate inconsistency");
- munmap(map, len + pg_offset);
+ free(src);
return data;
}
static void sha1_object(const void *data, unsigned long size,
enum object_type type, unsigned char *sha1)
{
- SHA_CTX ctx;
- char header[50];
- int header_size;
- const char *type_str;
-
- switch (type) {
- case OBJ_COMMIT: type_str = commit_type; break;
- case OBJ_TREE: type_str = tree_type; break;
- case OBJ_BLOB: type_str = blob_type; break;
- case OBJ_TAG: type_str = tag_type; break;
- default:
- die("bad type %d", type);
+ hash_sha1_file(data, size, typename(type), sha1);
+ if (has_sha1_file(sha1)) {
+ void *has_data;
+ enum object_type has_type;
+ unsigned long has_size;
+ has_data = read_sha1_file(sha1, &has_type, &has_size);
+ if (!has_data)
+ die("cannot read existing object %s", sha1_to_hex(sha1));
+ if (size != has_size || type != has_type ||
+ memcmp(data, has_data, size) != 0)
+ die("SHA1 COLLISION FOUND WITH %s !", sha1_to_hex(sha1));
+ free(has_data);
}
-
- header_size = sprintf(header, "%s %lu", type_str, size) + 1;
-
- SHA1_Init(&ctx);
- SHA1_Update(&ctx, header, header_size);
- SHA1_Update(&ctx, data, size);
- SHA1_Final(sha1, &ctx);
}
static void resolve_delta(struct object_entry *delta_obj, void *base_data,
/* If input_fd is a file, we should have reached its end now. */
if (fstat(input_fd, &st))
die("cannot fstat packfile: %s", strerror(errno));
- if (S_ISREG(st.st_mode) && st.st_size != consumed_bytes)
+ if (S_ISREG(st.st_mode) &&
+ lseek(input_fd, 0, SEEK_CUR) - input_len != st.st_size)
die("pack has junk at the end");
if (!nr_deltas)
fputc('\n', stderr);
}
-static int write_compressed(int fd, void *in, unsigned int size)
+static int write_compressed(int fd, void *in, unsigned int size, uint32_t *obj_crc)
{
z_stream stream;
unsigned long maxsize;
size = stream.total_out;
write_or_die(fd, out, size);
+ *obj_crc = crc32(*obj_crc, out, size);
free(out);
return size;
}
-static void append_obj_to_pack(void *buf,
+static void append_obj_to_pack(const unsigned char *sha1, void *buf,
unsigned long size, enum object_type type)
{
struct object_entry *obj = &objects[nr_objects++];
}
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);
- sha1_object(buf, size, type, obj->sha1);
+ obj[1].offset += write_compressed(output_fd, buf, size, &obj[0].crc32);
+ hashcpy(obj->sha1, sha1);
}
static int delta_pos_compare(const void *_a, const void *_b)
struct delta_entry *d = sorted_by_pos[i];
void *data;
unsigned long size;
- char type[10];
- enum object_type obj_type;
+ enum object_type type;
int j, first, last;
if (objects[d->obj_no].real_type != OBJ_REF_DELTA)
continue;
- data = read_sha1_file(d->base.sha1, type, &size);
+ data = read_sha1_file(d->base.sha1, &type, &size);
if (!data)
continue;
- if (!strcmp(type, blob_type)) obj_type = OBJ_BLOB;
- else if (!strcmp(type, tree_type)) obj_type = OBJ_TREE;
- else if (!strcmp(type, commit_type)) obj_type = OBJ_COMMIT;
- else if (!strcmp(type, tag_type)) obj_type = OBJ_TAG;
- else die("base object %s is of type '%s'",
- sha1_to_hex(d->base.sha1), type);
find_delta_children(&d->base, &first, &last);
for (j = first; j <= last; j++) {
struct object_entry *child = objects + deltas[j].obj_no;
if (child->real_type == OBJ_REF_DELTA)
- resolve_delta(child, data, size, obj_type);
+ resolve_delta(child, data, size, type);
}
- append_obj_to_pack(data, size, obj_type);
+ if (check_sha1_signature(d->base.sha1, data, size, typename(type)))
+ 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)
percent = display_progress(nr_resolved_deltas,
/* Rewrite pack header with updated object number */
if (lseek(output_fd, 0, SEEK_SET) != 0)
die("cannot seek back: %s", strerror(errno));
- if (xread(output_fd, &hdr, sizeof(hdr)) != sizeof(hdr))
+ if (read_in_full(output_fd, &hdr, sizeof(hdr)) != sizeof(hdr))
die("cannot read pack header back: %s", strerror(errno));
hdr.hdr_entries = htonl(nr_objects);
if (lseek(output_fd, 0, SEEK_SET) != 0)
write_or_die(output_fd, sha1, 20);
}
+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 sha1file *f;
struct object_entry **sorted_by_sha, **list, **last;
- unsigned int array[256];
+ uint32_t array[256];
int i, fd;
SHA_CTX ctx;
+ uint32_t index_version;
if (nr_objects) {
sorted_by_sha =
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/index_XXXXXX", get_object_directory());
+ "%s/tmp_idx_XXXXXX", get_object_directory());
fd = mkstemp(tmpfile);
index_name = xstrdup(tmpfile);
} else {
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
array[i] = htonl(next - sorted_by_sha);
list = next;
}
- sha1write(f, array, 256 * sizeof(int));
+ sha1write(f, array, 256 * 4);
- /* recompute the SHA1 hash of sorted object names.
- * currently pack-objects does not do this, but that
- * can be fixed.
- */
+ /* 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++;
- unsigned int offset = htonl(obj->offset);
- sha1write(f, &offset, 4);
+ 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);
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,
unsigned char *sha1)
{
+ const char *report = "pack";
char name[PATH_MAX];
int err;
if (err)
die("error while closing pack file: %s", strerror(errno));
chmod(curr_pack_name, 0444);
+ }
- /*
- * Let's just mimic git-unpack-objects here and write
- * the last part of the buffer to stdout.
- */
- while (input_len) {
- err = xwrite(1, input_buffer + input_offset, input_len);
- if (err <= 0)
- break;
- input_len -= err;
- input_offset += err;
+ if (keep_msg) {
+ int keep_fd, keep_msg_len = strlen(keep_msg);
+ if (!keep_name) {
+ snprintf(name, sizeof(name), "%s/pack/pack-%s.keep",
+ get_object_directory(), sha1_to_hex(sha1));
+ keep_name = name;
+ }
+ keep_fd = open(keep_name, O_RDWR|O_CREAT|O_EXCL, 0600);
+ if (keep_fd < 0) {
+ if (errno != EEXIST)
+ die("cannot write keep file");
+ } else {
+ if (keep_msg_len > 0) {
+ write_or_die(keep_fd, keep_msg, keep_msg_len);
+ write_or_die(keep_fd, "\n", 1);
+ }
+ close(keep_fd);
+ report = "keep";
}
}
if (move_temp_to_file(curr_index_name, final_index_name))
die("cannot store index file");
}
+
+ if (!from_stdin) {
+ printf("%s\n", sha1_to_hex(sha1));
+ } else {
+ char buf[48];
+ int len = snprintf(buf, sizeof(buf), "%s\t%s\n",
+ report, sha1_to_hex(sha1));
+ write_or_die(1, buf, len);
+
+ /*
+ * Let's just mimic git-unpack-objects here and write
+ * the last part of the input buffer to stdout.
+ */
+ while (input_len) {
+ err = xwrite(1, input_buffer + input_offset, input_len);
+ if (err <= 0)
+ break;
+ input_len -= err;
+ input_offset += err;
+ }
+ }
}
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 *index_name_buf = NULL;
+ const char *keep_name = NULL, *keep_msg = NULL;
+ char *index_name_buf = NULL, *keep_name_buf = NULL;
unsigned char sha1[20];
for (i = 1; i < argc; i++) {
from_stdin = 1;
} else if (!strcmp(arg, "--fix-thin")) {
fix_thin_pack = 1;
+ } else if (!strcmp(arg, "--keep")) {
+ keep_msg = "";
+ } else if (!prefixcmp(arg, "--keep=")) {
+ keep_msg = arg + 7;
+ } else if (!prefixcmp(arg, "--pack_header=")) {
+ struct pack_header *hdr;
+ char *c;
+
+ hdr = (struct pack_header *)input_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);
+ input_len = sizeof(*hdr);
} else if (!strcmp(arg, "-v")) {
verbose = 1;
} else if (!strcmp(arg, "-o")) {
if (index_name || (i+1) >= argc)
usage(index_pack_usage);
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)
+ die("bad %s", arg);
+ if (*c == ',')
+ index_off32_limit = strtoul(c+1, &c, 0);
+ if (*c || index_off32_limit & 0x80000000)
+ die("bad %s", arg);
} else
usage(index_pack_usage);
continue;
strcpy(index_name_buf + len - 5, ".idx");
index_name = index_name_buf;
}
+ if (keep_msg && !keep_name && pack_name) {
+ int len = strlen(pack_name);
+ if (!has_extension(pack_name, ".pack"))
+ die("packfile name '%s' does not end with '.pack'",
+ pack_name);
+ keep_name_buf = xmalloc(len);
+ memcpy(keep_name_buf, pack_name, len - 5);
+ strcpy(keep_name_buf + len - 5, ".keep");
+ keep_name = keep_name_buf;
+ }
curr_pack = open_pack_file(pack_name);
parse_pack_header();
}
free(deltas);
curr_index = write_index_file(index_name, sha1);
- final(pack_name, curr_pack, index_name, curr_index, sha1);
+ final(pack_name, curr_pack,
+ index_name, curr_index,
+ keep_name, keep_msg,
+ sha1);
free(objects);
free(index_name_buf);
-
- if (!from_stdin)
- printf("%s\n", sha1_to_hex(sha1));
+ free(keep_name_buf);
return 0;
}