mirrors/git
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

git-unpack-objects: re-write to read from stdin

Browse Source 
It gets a bit more complicated to unpack in a streaming environment, but
here it is.  The rewrite is actually a lot cleaner in other ways, it's
just a bit more subtle.
This commit is contained in:
Linus Torvalds
2005-06-28 20:34:23 -07:00
parent 75c660ac93
commit 67e5a5ece4
1 changed files with 191 additions and 229 deletions
Download Patch File Download Diff File Expand all files Collapse all files

418
unpack-objects.c
View File

@ -4,278 +4,213 @@
#include "pack.h" #include "pack.h"
static int dry_run; static int dry_run;
static int nr_entries; static const char unpack_usage[] = "git-unpack-objects < pack-file";
static const char *base_name;
static const char unpack_usage[] = "git-unpack-objects basename";
struct pack_entry { /* We always read in 4kB chunks. */
unsigned int offset; /* network byte order */ static unsigned char buffer[4096];
unsigned char sha1[20]; static unsigned long offset, len, eof;
static SHA_CTX ctx;
/*
* Make sure at least "min" bytes are available in the buffer, and
* return the pointer to the buffer.
*/
static void * fill(int min)
{
if (min <= len)
return buffer + offset;
if (eof)
die("unable to fill input");
if (min > sizeof(buffer))
die("cannot fill %d bytes", min);
if (offset) {
SHA1_Update(&ctx, buffer, offset);
memcpy(buffer, buffer + offset, len);
offset = 0;
}
do {
int ret = read(0, buffer + len, sizeof(buffer) - len);
if (ret <= 0) {
if (!ret)
die("early EOF");
if (errno == EAGAIN || errno == EINTR)
continue;
die("read error on input: %s", strerror(errno));
}
len += ret;
} while (len < min);
return buffer;
}
static void use(int bytes)
{
if (bytes > len)
die("used more bytes than were available");
len -= bytes;
offset += bytes;
}
static void *get_data(unsigned long size)
{
z_stream stream;
void *buf = xmalloc(size);
if (!size)
return buf;
memset(&stream, 0, sizeof(stream));
stream.next_out = buf;
stream.avail_out = size;
stream.next_in = fill(1);
stream.avail_in = len;
inflateInit(&stream);
for (;;) {
int ret = inflate(&stream, 0);
use(len - stream.avail_in);
if (stream.total_out == size && ret == Z_STREAM_END)
break;
if (ret != Z_OK)
die("inflate returned %d\n", ret);
stream.next_in = fill(1);
stream.avail_in = len;
}
return buf;
}
struct delta_info {
unsigned char base_sha1[20];
unsigned long size;
void *delta;
struct delta_info *next;
}; };
static void *pack_base; static struct delta_info *delta_list;
static unsigned long pack_size;
static void *index_base;
static unsigned long index_size;
static struct pack_entry **pack_list; static void add_delta_to_list(unsigned char *base_sha1, void *delta, unsigned long size)
static void *map_file(const char *suffix, unsigned long *sizep)
{ {
static char pathname[PATH_MAX]; struct delta_info *info = xmalloc(sizeof(*info));
unsigned long len;
int fd;
struct stat st;
void *map;
len = snprintf(pathname, PATH_MAX, "%s.%s", base_name, suffix); memcpy(info->base_sha1, base_sha1, 20);
if (len >= PATH_MAX) info->size = size;
die("bad pack base-name"); info->delta = delta;
fd = open(pathname, O_RDONLY); info->next = delta_list;
if (fd < 0 || fstat(fd, &st)) delta_list = info;
die("unable to open '%s'", pathname);
len = st.st_size;
if (!len)
die("bad pack file '%s'", pathname);
map = mmap(NULL, len, PROT_READ, MAP_PRIVATE, fd, 0);
if (-1 == (int)(long)map)
die("unable to mmap '%s'", pathname);
close(fd);
*sizep = len;
return map;
} }
static int sort_by_offset(const void *_a, const void *_b) static void added_object(unsigned char *sha1, char *type, void *data, unsigned long size);
static int resolve_delta(char *type,
void *base, unsigned long base_size,
void *delta, unsigned long delta_size)
{ {
struct pack_entry *a = *(struct pack_entry **)_a; void *result;
struct pack_entry *b = *(struct pack_entry **)_b; unsigned long result_size;
unsigned int o1, o2; unsigned char sha1[20];
o1 = ntohl(a->offset); result = patch_delta(base, base_size,
o2 = ntohl(b->offset); delta, delta_size,
return o1 < o2 ? -1 : 1; &result_size);
} if (!result)
die("failed to apply delta");
free(delta);
static int check_index(void) if (write_sha1_file(result, result_size, type, sha1) < 0)
{ die("failed to write object");
unsigned int *array = index_base; added_object(sha1, type, result, result_size);
unsigned int nr; free(result);
int i;
if (index_size < 4*256 + 20)
return error("index file too small");
nr = 0;
for (i = 0; i < 256; i++) {
unsigned int n = ntohl(array[i]);
if (n < nr)
return error("non-monotonic index");
nr = n;
}
/*
* Total size:
* - 256 index entries 4 bytes each
* - 24-byte entries * nr (20-byte sha1 + 4-byte offset)
* - 20-byte SHA1 of the packfile
* - 20-byte SHA1 file checksum
*/
if (index_size != 4*256 + nr * 24 + 20 + 20)
return error("wrong index file size");
nr_entries = nr;
pack_list = xmalloc(nr * sizeof(struct pack_entry *));
for (i = 0; i < nr; i++)
pack_list[i] = index_base + 4*256 + i*24;
qsort(pack_list, nr, sizeof(*pack_list), sort_by_offset);
printf("%d entries\n", nr);
return 0; return 0;
} }
static int unpack_non_delta_entry(struct pack_entry *entry, static void added_object(unsigned char *sha1, char *type, void *data, unsigned long size)
enum object_type kind,
unsigned char *data,
unsigned long size,
unsigned long left)
{ {
int st; struct delta_info **p = &delta_list;
z_stream stream; struct delta_info *info;
char *buffer;
while ((info = *p) != NULL) {
if (!memcmp(info->base_sha1, sha1, 20)) {
*p = info->next;
p = &delta_list;
resolve_delta(type, data, size, info->delta, info->size);
free(info);
continue;
}
p = &info->next;
}
}
static int unpack_non_delta_entry(enum object_type kind, unsigned long size)
{
void *buf = get_data(size);
unsigned char sha1[20]; unsigned char sha1[20];
char *type; char *type;
printf("%s %c %lu\n", sha1_to_hex(entry->sha1), ".CTBGD"[kind], size);
if (dry_run)
return 0;
buffer = xmalloc(size + 1);
buffer[size] = 0;
memset(&stream, 0, sizeof(stream));
stream.next_in = data;
stream.avail_in = left;
stream.next_out = buffer;
stream.avail_out = size;
inflateInit(&stream);
st = inflate(&stream, Z_FINISH);
inflateEnd(&stream);
if ((st != Z_STREAM_END) || stream.total_out != size)
goto err_finish;
switch (kind) { switch (kind) {
case OBJ_COMMIT: type = "commit"; break; case OBJ_COMMIT: type = "commit"; break;
case OBJ_TREE: type = "tree"; break; case OBJ_TREE: type = "tree"; break;
case OBJ_BLOB: type = "blob"; break; case OBJ_BLOB: type = "blob"; break;
case OBJ_TAG: type = "tag"; break; case OBJ_TAG: type = "tag"; break;
default: goto err_finish; default: die("bad type %d", kind);
} }
if (write_sha1_file(buffer, size, type, sha1) < 0) if (write_sha1_file(buf, size, type, sha1) < 0)
die("failed to write %s (%s)", die("failed to write object");
sha1_to_hex(entry->sha1), type); added_object(sha1, type, buf, size);
printf("%s %s\n", sha1_to_hex(sha1), type); free(buf);
if (memcmp(sha1, entry->sha1, 20))
die("resulting %s have wrong SHA1", type);
finish:
st = 0;
free(buffer);
return st;
err_finish:
st = -1;
goto finish;
}
static int find_pack_entry(unsigned char *sha1, struct pack_entry **ent)
{
int *level1_ofs = index_base;
int hi = ntohl(level1_ofs[*sha1]);
int lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1]));
void *index = index_base + 4*256;
do {
int mi = (lo + hi) / 2;
int cmp = memcmp(index + 24 * mi + 4, sha1, 20);
if (!cmp) {
*ent = index + 24 * mi;
return 1;
}
if (cmp > 0)
hi = mi;
else
lo = mi+1;
} while (lo < hi);
return 0; return 0;
} }
/* forward declaration for a mutually recursive function */ static int unpack_delta_entry(unsigned long delta_size)
static void unpack_entry(struct pack_entry *);
static int unpack_delta_entry(struct pack_entry *entry,
unsigned char *base_sha1,
unsigned long delta_size,
unsigned long left)
{ {
void *data, *delta_data, *result, *base; void *delta_data, *base;
unsigned long data_size, result_size, base_size; unsigned long base_size;
z_stream stream;
int st;
char type[20]; char type[20];
unsigned char sha1[20]; unsigned char base_sha1[20];
if (left < 20) memcpy(base_sha1, fill(20), 20);
die("truncated pack file"); use(20);
data = base_sha1 + 20;
data_size = left - 20;
printf("%s D %lu", sha1_to_hex(entry->sha1), delta_size);
printf(" %s\n", sha1_to_hex(base_sha1));
if (dry_run) delta_data = get_data(delta_size);
return 0;
/* pack+5 is the base sha1, unless we have it, we need to
* unpack it first.
*/
if (!has_sha1_file(base_sha1)) { if (!has_sha1_file(base_sha1)) {
struct pack_entry *base; add_delta_to_list(base_sha1, delta_data, delta_size);
if (!find_pack_entry(base_sha1, &base)) return 0;
die("cannot find delta-pack base object");
unpack_entry(base);
} }
delta_data = xmalloc(delta_size);
memset(&stream, 0, sizeof(stream));
stream.next_in = data;
stream.avail_in = data_size;
stream.next_out = delta_data;
stream.avail_out = delta_size;
inflateInit(&stream);
st = inflate(&stream, Z_FINISH);
inflateEnd(&stream);
if ((st != Z_STREAM_END) || stream.total_out != delta_size)
die("delta data unpack failed");
base = read_sha1_file(base_sha1, type, &base_size); base = read_sha1_file(base_sha1, type, &base_size);
if (!base) if (!base)
die("failed to read delta-pack base object %s", sha1_to_hex(base_sha1)); die("failed to read delta-pack base object %s", sha1_to_hex(base_sha1));
result = patch_delta(base, base_size, return resolve_delta(type, base, base_size, delta_data, delta_size);
delta_data, delta_size,
&result_size);
if (!result)
die("failed to apply delta");
free(delta_data);
if (write_sha1_file(result, result_size, type, sha1) < 0)
die("failed to write %s (%s)",
sha1_to_hex(entry->sha1), type);
free(result);
printf("%s %s\n", sha1_to_hex(sha1), type);
if (memcmp(sha1, entry->sha1, 20))
die("resulting %s have wrong SHA1", type);
return 0;
} }
static void unpack_entry(struct pack_entry *entry) static void unpack_one(void)
{ {
unsigned long offset, size, left;
unsigned char *pack, c; unsigned char *pack, c;
int type; unsigned long size;
enum object_type type;
/* Have we done this one already due to deltas based on it? */ pack = fill(1);
if (lookup_object(entry->sha1)) c = *pack;
return; use(1);
offset = ntohl(entry->offset);
if (offset >= pack_size)
goto bad;
pack = pack_base + offset;
c = *pack++;
offset++;
type = (c >> 4) & 7; type = (c >> 4) & 7;
size = (c & 15); size = (c & 15);
while (c & 0x80) { while (c & 0x80) {
if (offset >= pack_size) pack = fill(1);
goto bad;
offset++;
c = *pack++; c = *pack++;
use(1);
size = (size << 7) + (c & 0x7f); size = (size << 7) + (c & 0x7f);
} }
left = pack_size - offset;
switch (type) { switch (type) {
case OBJ_COMMIT: case OBJ_COMMIT:
case OBJ_TREE: case OBJ_TREE:
case OBJ_BLOB: case OBJ_BLOB:
case OBJ_TAG: case OBJ_TAG:
unpack_non_delta_entry(entry, type, pack, size, left); unpack_non_delta_entry(type, size);
return; return;
case OBJ_DELTA: case OBJ_DELTA:
unpack_delta_entry(entry, pack, size, left); unpack_delta_entry(size);
return; return;
default:
die("bad object type %d", type);
} }
bad:
die("corrupted pack file");
} }
/* /*
@ -285,17 +220,28 @@ bad:
*/ */
static void unpack_all(void) static void unpack_all(void)
{ {
int i = nr_entries; int i;
struct pack_header *hdr = fill(sizeof(struct pack_header));
unsigned version = ntohl(hdr->hdr_version);
unsigned nr_objects = ntohl(hdr->hdr_entries);
while (--i >= 0) { if (ntohl(hdr->hdr_signature) != PACK_SIGNATURE)
struct pack_entry *entry = pack_list[i]; die("bad pack file");
unpack_entry(entry); if (version != 1)
} die("unable to handle pack file version %d", version);
fprintf(stderr, "Unpacking %d objects\n", nr_objects);
use(sizeof(struct pack_header));
for (i = 0; i < nr_objects; i++)
unpack_one();
if (delta_list)
die("unresolved deltas left after unpacking");
} }
int main(int argc, char **argv) int main(int argc, char **argv)
{ {
int i; int i;
unsigned char sha1[20];
for (i = 1 ; i < argc; i++) { for (i = 1 ; i < argc; i++) {
const char *arg = argv[i]; const char *arg = argv[i];
@ -307,16 +253,32 @@ int main(int argc, char **argv)
} }
usage(unpack_usage); usage(unpack_usage);
} }
if (base_name)
/* We don't take any non-flag arguments now.. Maybe some day */
usage(unpack_usage); usage(unpack_usage);
base_name = arg;
} }
if (!base_name) SHA1_Init(&ctx);
usage(unpack_usage);
index_base = map_file("idx", &index_size);
pack_base = map_file("pack", &pack_size);
if (check_index() < 0)
die("bad index file");
unpack_all(); unpack_all();
SHA1_Update(&ctx, buffer, offset);
SHA1_Final(sha1, &ctx);
if (memcmp(fill(20), sha1, 20))
die("final sha1 did not match");
use(20);
/* Write the last part of the buffer to stdout */
while (len) {
int ret = write(1, buffer + offset, len);
if (!ret)
break;
if (ret < 0) {
if (errno == EAGAIN || errno == EINTR)
continue;
break;
}
len -= ret;
offset += ret;
}
/* All done */
return 0; return 0;
} }