#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 [-
o <index-file>] { <pack-file> | --stdin [<pack-file>] }";
+"git-index-pack [-
v] [-o <index-file>] [{ ---keep | --keep=<msg> }] { <pack-file> | --stdin [--fix-thin] [<pack-file>] }";
struct object_entry
{
struct delta_entry
{
- struct object_entry *obj;
union delta_base base;
+ int obj_no;
};
static struct object_entry *objects;
static struct delta_entry *deltas;
static int nr_objects;
static int nr_deltas;
+static int nr_resolved_deltas;
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;
+}
/* We always read in 4kB chunks. */
static unsigned char input_buffer[4096];
static SHA_CTX input_ctx;
static int input_fd, output_fd, mmap_fd;
+/* Discard current buffer used content. */
+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);
+ input_offset = 0;
+ }
+}
+
/*
* Make sure at least "min" bytes are available in the buffer, and
* return the pointer to the buffer.
*/
-static void * fill(int min)
+static void *fill(int min)
{
if (min <= input_len)
return input_buffer + input_offset;
if (min > sizeof(input_buffer))
die("cannot fill %d bytes", min);
- 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);
- input_offset = 0;
- }
+ flush();
do {
int ret = xread(input_fd, input_buffer + input_len,
sizeof(input_buffer) - input_len);
consumed_bytes += bytes;
}
-static const char * open_pack_file(const char *pack_name)
+static const char *open_pack_file(const char *pack_name)
{
if (from_stdin) {
input_fd = 0;
nr_objects = ntohl(hdr->hdr_entries);
use(sizeof(struct pack_header));
- /*fprintf(stderr, "Indexing %d objects\n", nr_objects);*/
}
static void bad_object(unsigned long offset, const char *format,
return unpack_entry_data(obj->offset, obj->size);
}
-static void * get_data_from_pack(struct object_entry *obj)
+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;
return -first-1;
}
-static int find_delta_childs(const union delta_base *base,
- int *first_index, int *last_index)
+static int find_delta_children(const union delta_base *base,
+ int *first_index, int *last_index)
{
int first = find_delta(base);
int last = first;
SHA1_Final(sha1, &ctx);
}
-static void resolve_delta(struct delta_entry *delta, void *base_data,
+static void resolve_delta(struct object_entry *delta_obj, void *base_data,
unsigned long base_size, enum object_type type)
{
- struct object_entry *obj = delta->obj;
void *delta_data;
unsigned long delta_size;
void *result;
union delta_base delta_base;
int j, first, last;
- obj->real_type = type;
- delta_data = get_data_from_pack(obj);
- delta_size = obj->size;
+ delta_obj->real_type = type;
+ delta_data = get_data_from_pack(delta_obj);
+ delta_size = delta_obj->size;
result = patch_delta(base_data, base_size, delta_data, delta_size,
&result_size);
free(delta_data);
if (!result)
- bad_object(obj->offset, "failed to apply delta");
- sha1_object(result, result_size, type, obj->sha1);
-
- hashcpy(delta_base.sha1, obj->sha1);
- if (!find_delta_childs(&delta_base, &first, &last)) {
- for (j = first; j <= last; j++)
- if (deltas[j].obj->type == OBJ_REF_DELTA)
- resolve_delta(&deltas[j], result, result_size, type);
+ bad_object(delta_obj->offset, "failed to apply delta");
+ sha1_object(result, result_size, type, delta_obj->sha1);
+ nr_resolved_deltas++;
+
+ hashcpy(delta_base.sha1, delta_obj->sha1);
+ if (!find_delta_children(&delta_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, result, result_size, type);
+ }
}
memset(&delta_base, 0, sizeof(delta_base));
- delta_base.offset = obj->offset;
- if (!find_delta_childs(&delta_base, &first, &last)) {
- for (j = first; j <= last; j++)
- if (deltas[j].obj->type == OBJ_OFS_DELTA)
- resolve_delta(&deltas[j], result, result_size, type);
+ delta_base.offset = delta_obj->offset;
+ if (!find_delta_children(&delta_base, &first, &last)) {
+ for (j = first; j <= last; j++) {
+ struct object_entry *child = objects + deltas[j].obj_no;
+ if (child->real_type == OBJ_OFS_DELTA)
+ resolve_delta(child, result, result_size, type);
+ }
}
free(result);
/* Parse all objects and return the pack content SHA1 hash */
static void parse_pack_objects(unsigned char *sha1)
{
- int i;
+ int i, percent = -1;
struct delta_entry *delta = deltas;
void *data;
struct stat st;
* First pass:
* - find locations of all objects;
* - calculate SHA1 of all non-delta objects;
- * - remember base SHA1 for all deltas.
+ * - remember base (SHA1 or offset) for all deltas.
*/
+ if (verbose)
+ fprintf(stderr, "Indexing %d objects.\n", nr_objects);
for (i = 0; i < nr_objects; i++) {
struct object_entry *obj = &objects[i];
data = unpack_raw_entry(obj, &delta->base);
obj->real_type = obj->type;
if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA) {
nr_deltas++;
- delta->obj = obj;
+ delta->obj_no = i;
delta++;
} else
sha1_object(data, obj->size, obj->type, obj->sha1);
free(data);
+ if (verbose)
+ percent = display_progress(i+1, nr_objects, percent);
}
objects[i].offset = consumed_bytes;
+ if (verbose)
+ fputc('\n', stderr);
/* Check pack integrity */
- SHA1_Update(&input_ctx, input_buffer, input_offset);
+ flush();
SHA1_Final(sha1, &input_ctx);
if (hashcmp(fill(20), sha1))
die("pack is corrupted (SHA1 mismatch)");
use(20);
- if (output_fd >= 0)
- write_or_die(output_fd, input_buffer, input_offset);
/* If input_fd is a file, we should have reached its end now. */
if (fstat(input_fd, &st))
if (S_ISREG(st.st_mode) && st.st_size != consumed_bytes)
die("pack has junk at the end");
+ if (!nr_deltas)
+ return;
+
/* Sort deltas by base SHA1/offset for fast searching */
qsort(deltas, nr_deltas, sizeof(struct delta_entry),
compare_delta_entry);
* recursively checking if the resulting object is used as a base
* for some more deltas.
*/
+ if (verbose)
+ fprintf(stderr, "Resolving %d deltas.\n", 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);
- ref = !find_delta_childs(&base, &ref_first, &ref_last);
+ ref = !find_delta_children(&base, &ref_first, &ref_last);
memset(&base, 0, sizeof(base));
base.offset = obj->offset;
- ofs = !find_delta_childs(&base, &ofs_first, &ofs_last);
+ ofs = !find_delta_children(&base, &ofs_first, &ofs_last);
if (!ref && !ofs)
continue;
data = get_data_from_pack(obj);
if (ref)
- for (j = ref_first; j <= ref_last; j++)
- if (deltas[j].obj->type == OBJ_REF_DELTA)
- resolve_delta(&deltas[j], data,
+ for (j = ref_first; j <= ref_last; j++) {
+ struct object_entry *child = objects + deltas[j].obj_no;
+ if (child->real_type == OBJ_REF_DELTA)
+ resolve_delta(child, data,
obj->size, obj->type);
+ }
if (ofs)
- for (j = ofs_first; j <= ofs_last; j++)
- if (deltas[j].obj->type == OBJ_OFS_DELTA)
- resolve_delta(&deltas[j], data,
+ for (j = ofs_first; j <= ofs_last; j++) {
+ struct object_entry *child = objects + deltas[j].obj_no;
+ if (child->real_type == OBJ_OFS_DELTA)
+ resolve_delta(child, data,
obj->size, obj->type);
+ }
free(data);
+ if (verbose)
+ percent = display_progress(nr_resolved_deltas,
+ nr_deltas, percent);
+ }
+ if (verbose && nr_resolved_deltas == nr_deltas)
+ fputc('\n', stderr);
+}
+
+static int write_compressed(int fd, void *in, unsigned int size)
+{
+ z_stream stream;
+ unsigned long maxsize;
+ void *out;
+
+ memset(&stream, 0, sizeof(stream));
+ deflateInit(&stream, zlib_compression_level);
+ 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);
+ deflateEnd(&stream);
+
+ size = stream.total_out;
+ write_or_die(fd, out, size);
+ free(out);
+ return size;
+}
+
+static void append_obj_to_pack(void *buf,
+ unsigned long size, enum object_type type)
+{
+ struct object_entry *obj = &objects[nr_objects++];
+ unsigned char header[10];
+ unsigned long s = size;
+ int n = 0;
+ unsigned char c = (type << 4) | (s & 15);
+ s >>= 4;
+ while (s) {
+ header[n++] = c | 0x80;
+ c = s & 0x7f;
+ s >>= 7;
}
+ 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);
+}
+
+static int delta_pos_compare(const void *_a, const void *_b)
+{
+ struct delta_entry *a = *(struct delta_entry **)_a;
+ struct delta_entry *b = *(struct delta_entry **)_b;
+ return a->obj_no - b->obj_no;
+}
+
+static void fix_unresolved_deltas(int nr_unresolved)
+{
+ struct delta_entry **sorted_by_pos;
+ int i, n = 0, percent = -1;
- /* Check for unresolved deltas */
+ /*
+ * Since many unresolved deltas may well be themselves base objects
+ * for more unresolved deltas, we really want to include the
+ * smallest number of base objects that would cover as much delta
+ * as possible by picking the
+ * trunc deltas first, allowing for other deltas to resolve without
+ * additional base objects. Since most base objects are to be found
+ * before deltas depending on them, a good heuristic is to start
+ * resolving deltas in the same order as their position in the pack.
+ */
+ sorted_by_pos = xmalloc(nr_unresolved * sizeof(*sorted_by_pos));
for (i = 0; i < nr_deltas; i++) {
- if (deltas[i].obj->real_type == OBJ_REF_DELTA ||
- deltas[i].obj->real_type == OBJ_OFS_DELTA)
- die("pack has unresolved deltas");
+ if (objects[deltas[i].obj_no].real_type != OBJ_REF_DELTA)
+ continue;
+ sorted_by_pos[n++] = &deltas[i];
+ }
+ qsort(sorted_by_pos, n, sizeof(*sorted_by_pos), delta_pos_compare);
+
+ for (i = 0; i < n; i++) {
+ struct delta_entry *d = sorted_by_pos[i];
+ void *data;
+ unsigned long size;
+ char type[10];
+ enum object_type obj_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);
+ 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);
+ }
+
+ append_obj_to_pack(data, size, obj_type);
+ free(data);
+ if (verbose)
+ percent = display_progress(nr_resolved_deltas,
+ nr_deltas, percent);
}
+ 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 (xread(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)
* 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)
+static const char *write_index_file(const char *index_name, unsigned char *sha1)
{
struct sha1file *f;
struct object_entry **sorted_by_sha, **list, **last;
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)
{
+ char *report = "pack";
char name[PATH_MAX];
int err;
chmod(curr_pack_name, 0444);
}
+ 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 (final_pack_name != curr_pack_name) {
if (!final_pack_name) {
snprintf(name, sizeof(name), "%s/pack/pack-%s.pack",
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));
+ xwrite(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;
+ 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++) {
if (*arg == '-') {
if (!strcmp(arg, "--stdin")) {
from_stdin = 1;
+ } else if (!strcmp(arg, "--fix-thin")) {
+ fix_thin_pack = 1;
+ } else if (!strcmp(arg, "--keep")) {
+ keep_msg = "";
+ } else if (!strncmp(arg, "--keep=", 7)) {
+ keep_msg = arg + 7;
+ } else if (!strncmp(arg, "--pack_header=", 14)) {
+ 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);
if (!pack_name && !from_stdin)
usage(index_pack_usage);
+ if (fix_thin_pack && !from_stdin)
+ die("--fix-thin cannot be used without --stdin");
if (!index_name && pack_name) {
int len = strlen(pack_name);
if (!has_extension(pack_name, ".pack"))
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();
- objects = xcalloc(nr_objects + 1, sizeof(struct object_entry));
- deltas = xcalloc(nr_objects, sizeof(struct delta_entry));
+ 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 (fix_thin_pack) {
+ int nr_unresolved = nr_deltas - nr_resolved_deltas;
+ int nr_objects_initial = nr_objects;
+ if (nr_unresolved <= 0)
+ die("confusion beyond insanity");
+ objects = xrealloc(objects,
+ (nr_objects + nr_unresolved + 1)
+ * sizeof(*objects));
+ fix_unresolved_deltas(nr_unresolved);
+ if (verbose)
+ fprintf(stderr, "%d objects were added to complete this thin pack.\n",
+ nr_objects - nr_objects_initial);
+ readjust_pack_header_and_sha1(sha1);
+ }
+ 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);
- 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);
-
- printf("%s\n", sha1_to_hex(sha1));
+ free(keep_name_buf);
return 0;
}