#include "commit.h"
#include "tag.h"
#include "tree.h"
+#include "progress.h"
static const char index_pack_usage[] =
"git-index-pack [-v] [-o <index-file>] [{ ---keep | --keep=<msg> }] { <pack-file> | --stdin [--fix-thin] [<pack-file>] }";
struct object_entry
{
- unsigned long offset;
+ struct pack_idx_entry idx;
unsigned long size;
unsigned int hdr_size;
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;
};
/*
static int from_stdin;
static int verbose;
-static volatile sig_atomic_t progress_update;
-
-static void progress_interval(int signum)
-{
- progress_update = 1;
-}
-
-static void setup_progress_signal(void)
-{
- struct sigaction sa;
- struct itimerval v;
-
- memset(&sa, 0, sizeof(sa));
- sa.sa_handler = progress_interval;
- sigemptyset(&sa.sa_mask);
- sa.sa_flags = SA_RESTART;
- sigaction(SIGALRM, &sa, NULL);
-
- v.it_interval.tv_sec = 1;
- v.it_interval.tv_usec = 0;
- v.it_value = v.it_interval;
- setitimer(ITIMER_REAL, &v, NULL);
-
-}
-
-static unsigned display_progress(unsigned n, unsigned total, unsigned last_pc)
-{
- unsigned percent = n * 100 / total;
- if (percent != last_pc || progress_update) {
- fprintf(stderr, "%4u%% (%u/%u) done\r", percent, n, total);
- progress_update = 0;
- }
- return percent;
-}
+static struct progress progress;
/* 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 uint32_t input_crc32;
static int input_fd, output_fd, pack_fd;
/* Discard current buffer used content. */
die("cannot fill %d bytes", min);
flush();
do {
- int ret = xread(input_fd, input_buffer + input_len,
+ ssize_t ret = xread(input_fd, input_buffer + input_len,
sizeof(input_buffer) - input_len);
if (ret <= 0) {
if (!ret)
{
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
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;
+ obj->idx.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))
- bad_object(obj->offset, "offset value overflow for delta base object");
+ if (!base_offset || MSB(base_offset, 7))
+ 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:
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;
- return unpack_entry_data(obj->offset, obj->size);
+ 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;
+ unsigned long 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;
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,
&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;
/* Parse all objects and return the pack content SHA1 hash */
static void parse_pack_objects(unsigned char *sha1)
{
- int i, percent = -1;
+ int i;
struct delta_entry *delta = deltas;
void *data;
struct stat st;
* - remember base (SHA1 or offset) for all deltas.
*/
if (verbose)
- fprintf(stderr, "Indexing %d objects.\n", nr_objects);
+ start_progress(&progress, "Indexing %u 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)
- percent = display_progress(i+1, nr_objects, percent);
+ display_progress(&progress, i+1);
}
- objects[i].offset = consumed_bytes;
+ objects[i].idx.offset = consumed_bytes;
if (verbose)
- fputc('\n', stderr);
+ stop_progress(&progress);
/* Check pack integrity */
flush();
/* 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)
* for some more deltas.
*/
if (verbose)
- fprintf(stderr, "Resolving %d deltas.\n", nr_deltas);
+ start_progress(&progress, "Resolving %u 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;
}
free(data);
if (verbose)
- percent = display_progress(nr_resolved_deltas,
- nr_deltas, percent);
+ display_progress(&progress, nr_resolved_deltas);
}
- if (verbose && nr_resolved_deltas == 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[1].offset = obj[0].offset + n;
- obj[1].offset += write_compressed(output_fd, buf, size);
- sha1_object(buf, size, type, obj->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)
static void fix_unresolved_deltas(int nr_unresolved)
{
struct delta_entry **sorted_by_pos;
- int i, n = 0, percent = -1;
+ int i, n = 0;
/*
* Since many unresolved deltas may well be themselves base objects
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,
- nr_deltas, percent);
+ display_progress(&progress, nr_resolved_deltas);
}
free(sorted_by_pos);
- if (verbose)
- fputc('\n', stderr);
-}
-
-static void readjust_pack_header_and_sha1(unsigned char *sha1)
-{
- struct pack_header hdr;
- SHA_CTX ctx;
- int size;
-
- /* Rewrite pack header with updated object number */
- if (lseek(output_fd, 0, SEEK_SET) != 0)
- die("cannot seek back: %s", strerror(errno));
- 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)
- die("cannot seek back: %s", strerror(errno));
- write_or_die(output_fd, &hdr, sizeof(hdr));
- if (lseek(output_fd, 0, SEEK_SET) != 0)
- die("cannot seek back: %s", strerror(errno));
-
- /* Recompute and store the new pack's SHA1 */
- SHA1_Init(&ctx);
- do {
- unsigned char *buf[4096];
- size = xread(output_fd, buf, sizeof(buf));
- if (size < 0)
- die("cannot read pack data back: %s", strerror(errno));
- SHA1_Update(&ctx, buf, size);
- } while (size > 0);
- SHA1_Final(sha1, &ctx);
- write_or_die(output_fd, sha1, 20);
-}
-
-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;
- unsigned int array[256];
- int i, fd;
- SHA_CTX ctx;
-
- 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/index_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);
-
- /*
- * 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 * sizeof(int));
-
- /* recompute the SHA1 hash of sorted object names.
- * currently pack-objects does not do this, but that
- * can be fixed.
- */
- 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);
- sha1write(f, obj->sha1, 20);
- SHA1_Update(&ctx, obj->sha1, 20);
- }
- 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 *keep_name, const char *keep_msg,
unsigned char *sha1)
{
- char *report = "pack";
+ const char *report = "pack";
char name[PATH_MAX];
int err;
const 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];
for (i = 1; i < argc; i++) {
fix_thin_pack = 1;
} else if (!strcmp(arg, "--keep")) {
keep_msg = "";
- } else if (!strncmp(arg, "--keep=", 7)) {
+ } else if (!prefixcmp(arg, "--keep=")) {
keep_msg = arg + 7;
- } else if (!strncmp(arg, "--pack_header=", 14)) {
+ } else if (!prefixcmp(arg, "--pack_header=")) {
struct pack_header *hdr;
char *c;
if (index_name || (i+1) >= argc)
usage(index_pack_usage);
index_name = argv[++i];
+ } else if (!prefixcmp(arg, "--index-version=")) {
+ char *c;
+ pack_idx_default_version = strtoul(arg + 16, &c, 10);
+ if (pack_idx_default_version > 2)
+ die("bad %s", arg);
+ if (*c == ',')
+ 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);
continue;
parse_pack_header();
objects = xmalloc((nr_objects + 1) * sizeof(struct object_entry));
deltas = xmalloc(nr_objects * sizeof(struct delta_entry));
- if (verbose)
- setup_progress_signal();
parse_pack_objects(sha1);
- if (nr_deltas != nr_resolved_deltas) {
+ if (nr_deltas == nr_resolved_deltas) {
+ if (verbose)
+ stop_progress(&progress);
+ /* Flush remaining pack final 20-byte SHA1. */
+ flush();
+ } else {
if (fix_thin_pack) {
int nr_unresolved = nr_deltas - nr_resolved_deltas;
int nr_objects_initial = nr_objects;
(nr_objects + nr_unresolved + 1)
* sizeof(*objects));
fix_unresolved_deltas(nr_unresolved);
- if (verbose)
+ if (verbose) {
+ stop_progress(&progress);
fprintf(stderr, "%d objects were added to complete this thin pack.\n",
nr_objects - nr_objects_initial);
- readjust_pack_header_and_sha1(sha1);
+ }
+ fixup_pack_header_footer(output_fd, sha1,
+ curr_pack, nr_objects);
}
if (nr_deltas != nr_resolved_deltas)
die("pack has %d unresolved deltas",
nr_deltas - nr_resolved_deltas);
- } else {
- /* Flush remaining pack final 20-byte SHA1. */
- flush();
}
free(deltas);
- curr_index = write_index_file(index_name, sha1);
+
+ 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,