#include "tree.h"
static const char index_pack_usage[] =
-"git-index-pack [-
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
{
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 unsigned long input_offset, input_len, consumed_bytes;
static SHA_CTX input_ctx;
-static int input_fd, output_fd, mmap_fd;
+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;
}
}
* 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;
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;
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;
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,
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);
}
-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;
- unsigned pg_offset = from % getpagesize();
- unsigned char *map, *data;
+ 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);
+ if (pread(pack_fd, src, len, from) != len)
+ die("cannot pread pack file: %s", strerror(errno));
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;
}
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;
nr_resolved_deltas++;
hashcpy(delta_base.sha1, delta_obj->sha1);
- if (!find_delta_childs(&delta_base, &first, &last)) {
+ 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)
memset(&delta_base, 0, sizeof(delta_base));
delta_base.offset = delta_obj->offset;
- if (!find_delta_childs(&delta_base, &first, &last)) {
+ 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)
/* 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);
} 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 */
flush();
SHA1_Final(sha1, &input_ctx);
if (hashcmp(fill(20), sha1))
die("pack is corrupted (SHA1 mismatch)");
+ use(20);
/* 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 + 20)
+ 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)
+ 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);
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)
static void fix_unresolved_deltas(int nr_unresolved)
{
struct delta_entry **sorted_by_pos;
- int i, n = 0;
+ int i, n = 0, percent = -1;
/*
* Since many unresolved deltas may well be themselves base objects
else die("base object %s is of type '%s'",
sha1_to_hex(d->base.sha1), type);
- find_delta_childs(&d->base, &first, &last);
+ 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)
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)
/* 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)
* 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));
+ 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 (!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);
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 = 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)
nr_deltas - nr_resolved_deltas);
} else {
/* Flush remaining pack final 20-byte SHA1. */
- use(20);
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;
}