#include "pack.h"
#include "blob.h"
#include "commit.h"
+#include "run-command.h"
#include "tag.h"
#include "tree.h"
#include "tree-walk.h"
{
struct lock_file *lock = xcalloc(1, sizeof(struct lock_file));
int fd = hold_lock_file_for_append(lock, git_path("objects/info/alternates"), LOCK_DIE_ON_ERROR);
- char *alt = mkpath("%s/objects\n", reference);
+ char *alt = mkpath("%s\n", reference);
write_or_die(fd, alt, strlen(alt));
if (commit_lock_file(lock))
die("could not close alternates file");
unsigned char *use_pack(struct packed_git *p,
struct pack_window **w_cursor,
off_t offset,
- unsigned int *left)
+ unsigned long *left)
{
struct pack_window *win = *w_cursor;
return -1;
}
-static void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
+void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
{
void *map;
int fd;
return map;
}
-static int legacy_loose_object(unsigned char *map)
+/*
+ * There used to be a second loose object header format which
+ * was meant to mimic the in-pack format, allowing for direct
+ * copy of the object data. This format turned up not to be
+ * really worth it and we no longer write loose objects in that
+ * format.
+ */
+static int experimental_loose_object(unsigned char *map)
{
unsigned int word;
/*
- * Is it a zlib-compressed buffer? If so, the first byte
- * must be 0x78 (15-bit window size, deflated), and the
- * first 16-bit word is evenly divisible by 31
+ * We must determine if the buffer contains the standard
+ * zlib-deflated stream or the experimental format based
+ * on the in-pack object format. Compare the header byte
+ * for each format:
+ *
+ * RFC1950 zlib w/ deflate : 0www1000 : 0 <= www <= 7
+ * Experimental pack-based : Stttssss : ttt = 1,2,3,4
+ *
+ * If bit 7 is clear and bits 0-3 equal 8, the buffer MUST be
+ * in standard loose-object format, UNLESS it is a Git-pack
+ * format object *exactly* 8 bytes in size when inflated.
+ *
+ * However, RFC1950 also specifies that the 1st 16-bit word
+ * must be divisible by 31 - this checksum tells us our buffer
+ * is in the standard format, giving a false positive only if
+ * the 1st word of the Git-pack format object happens to be
+ * divisible by 31, ie:
+ * ((byte0 * 256) + byte1) % 31 = 0
+ * => 0ttt10000www1000 % 31 = 0
+ *
+ * As it happens, this case can only arise for www=3 & ttt=1
+ * - ie, a Commit object, which would have to be 8 bytes in
+ * size. As no Commit can be that small, we find that the
+ * combination of these two criteria (bitmask & checksum)
+ * can always correctly determine the buffer format.
*/
word = (map[0] << 8) + map[1];
- if (map[0] == 0x78 && !(word % 31))
- return 1;
- else
+ if ((map[0] & 0x8F) == 0x08 && !(word % 31))
return 0;
+ else
+ return 1;
}
unsigned long unpack_object_header_buffer(const unsigned char *buf,
return used;
}
-static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz)
+int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz)
{
unsigned long size, used;
static const char valid_loose_object_type[8] = {
stream->next_out = buffer;
stream->avail_out = bufsiz;
- if (legacy_loose_object(map)) {
- git_inflate_init(stream);
- return git_inflate(stream, 0);
- }
-
+ if (experimental_loose_object(map)) {
+ /*
+ * The old experimental format we no longer produce;
+ * we can still read it.
+ */
+ used = unpack_object_header_buffer(map, mapsize, &type, &size);
+ if (!used || !valid_loose_object_type[type])
+ return -1;
+ map += used;
+ mapsize -= used;
- /*
- * There used to be a second loose object header format which
- * was meant to mimic the in-pack format, allowing for direct
- * copy of the object data. This format turned up not to be
- * really worth it and we don't write it any longer. But we
- * can still read it.
- */
- used = unpack_object_header_buffer(map, mapsize, &type, &size);
- if (!used || !valid_loose_object_type[type])
- return -1;
- map += used;
- mapsize -= used;
+ /* Set up the stream for the rest.. */
+ stream->next_in = map;
+ stream->avail_in = mapsize;
+ git_inflate_init(stream);
- /* Set up the stream for the rest.. */
- stream->next_in = map;
- stream->avail_in = mapsize;
+ /* And generate the fake traditional header */
+ stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu",
+ typename(type), size);
+ return 0;
+ }
git_inflate_init(stream);
-
- /* And generate the fake traditional header */
- stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu",
- typename(type), size);
- return 0;
+ return git_inflate(stream, 0);
}
-static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size, const unsigned char *sha1)
+static void *unpack_sha1_rest(git_zstream *stream, void *buffer, unsigned long size, const unsigned char *sha1)
{
int bytes = strlen(buffer) + 1;
unsigned char *buf = xmallocz(size);
* too permissive for what we want to check. So do an anal
* object header parse by hand.
*/
-static int parse_sha1_header(const char *hdr, unsigned long *sizep)
+int parse_sha1_header(const char *hdr, unsigned long *sizep)
{
char type[10];
int i;
static void *unpack_sha1_file(void *map, unsigned long mapsize, enum object_type *type, unsigned long *size, const unsigned char *sha1)
{
int ret;
- z_stream stream;
+ git_zstream stream;
char hdr[8192];
ret = unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr));
{
const unsigned char *data;
unsigned char delta_head[20], *in;
- z_stream stream;
+ git_zstream stream;
int st;
memset(&stream, 0, sizeof(stream));
/* forward declaration for a mutually recursive function */
static int packed_object_info(struct packed_git *p, off_t offset,
- unsigned long *sizep);
+ unsigned long *sizep, int *rtype);
static int packed_delta_info(struct packed_git *p,
struct pack_window **w_curs,
base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset);
if (!base_offset)
return OBJ_BAD;
- type = packed_object_info(p, base_offset, NULL);
+ type = packed_object_info(p, base_offset, NULL, NULL);
if (type <= OBJ_NONE) {
struct revindex_entry *revidx;
const unsigned char *base_sha1;
return type;
}
-static int unpack_object_header(struct packed_git *p,
- struct pack_window **w_curs,
- off_t *curpos,
- unsigned long *sizep)
+int unpack_object_header(struct packed_git *p,
+ struct pack_window **w_curs,
+ off_t *curpos,
+ unsigned long *sizep)
{
unsigned char *base;
- unsigned int left;
+ unsigned long left;
unsigned long used;
enum object_type type;
return type;
}
-const char *packed_object_info_detail(struct packed_git *p,
- off_t obj_offset,
- unsigned long *size,
- unsigned long *store_size,
- unsigned int *delta_chain_length,
- unsigned char *base_sha1)
-{
- struct pack_window *w_curs = NULL;
- off_t curpos;
- unsigned long dummy;
- unsigned char *next_sha1;
- enum object_type type;
- struct revindex_entry *revidx;
-
- *delta_chain_length = 0;
- curpos = obj_offset;
- type = unpack_object_header(p, &w_curs, &curpos, size);
-
- revidx = find_pack_revindex(p, obj_offset);
- *store_size = revidx[1].offset - obj_offset;
-
- for (;;) {
- switch (type) {
- default:
- die("pack %s contains unknown object type %d",
- p->pack_name, type);
- case OBJ_COMMIT:
- case OBJ_TREE:
- case OBJ_BLOB:
- case OBJ_TAG:
- unuse_pack(&w_curs);
- return typename(type);
- case OBJ_OFS_DELTA:
- obj_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset);
- if (!obj_offset)
- die("pack %s contains bad delta base reference of type %s",
- p->pack_name, typename(type));
- if (*delta_chain_length == 0) {
- revidx = find_pack_revindex(p, obj_offset);
- hashcpy(base_sha1, nth_packed_object_sha1(p, revidx->nr));
- }
- break;
- case OBJ_REF_DELTA:
- next_sha1 = use_pack(p, &w_curs, curpos, NULL);
- if (*delta_chain_length == 0)
- hashcpy(base_sha1, next_sha1);
- obj_offset = find_pack_entry_one(next_sha1, p);
- break;
- }
- (*delta_chain_length)++;
- curpos = obj_offset;
- type = unpack_object_header(p, &w_curs, &curpos, &dummy);
- }
-}
-
static int packed_object_info(struct packed_git *p, off_t obj_offset,
- unsigned long *sizep)
+ unsigned long *sizep, int *rtype)
{
struct pack_window *w_curs = NULL;
unsigned long size;
enum object_type type;
type = unpack_object_header(p, &w_curs, &curpos, &size);
+ if (rtype)
+ *rtype = type; /* representation type */
switch (type) {
case OBJ_OFS_DELTA:
unsigned long size)
{
int st;
- z_stream stream;
+ git_zstream stream;
unsigned char *buffer, *in;
buffer = xmallocz(size);
return hash % MAX_DELTA_CACHE;
}
+static int in_delta_base_cache(struct packed_git *p, off_t base_offset)
+{
+ unsigned long hash = pack_entry_hash(p, base_offset);
+ struct delta_base_cache_entry *ent = delta_base_cache + hash;
+ return (ent->data && ent->p == p && ent->base_offset == base_offset);
+}
+
static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset,
unsigned long *base_size, enum object_type *type, int keep_cache)
{
return result;
}
+static void write_pack_access_log(struct packed_git *p, off_t obj_offset)
+{
+ static FILE *log_file;
+
+ if (!log_file) {
+ log_file = fopen(log_pack_access, "w");
+ if (!log_file) {
+ error("cannot open pack access log '%s' for writing: %s",
+ log_pack_access, strerror(errno));
+ log_pack_access = NULL;
+ return;
+ }
+ }
+ fprintf(log_file, "%s %"PRIuMAX"\n",
+ p->pack_name, (uintmax_t)obj_offset);
+ fflush(log_file);
+}
+
int do_check_packed_object_crc;
void *unpack_entry(struct packed_git *p, off_t obj_offset,
off_t curpos = obj_offset;
void *data;
+ if (log_pack_access)
+ write_pack_access_log(p, obj_offset);
+
if (do_check_packed_object_crc && p->index_version > 1) {
struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
unsigned long len = revidx[1].offset - obj_offset;
int status;
unsigned long mapsize, size;
void *map;
- z_stream stream;
+ git_zstream stream;
char hdr[32];
map = map_sha1_file(sha1, &mapsize);
return status;
}
-int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
+/* returns enum object_type or negative */
+int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi)
{
struct cached_object *co;
struct pack_entry e;
- int status;
+ int status, rtype;
co = find_cached_object(sha1);
if (co) {
- if (sizep)
- *sizep = co->size;
+ if (oi->sizep)
+ *(oi->sizep) = co->size;
+ oi->whence = OI_CACHED;
return co->type;
}
if (!find_pack_entry(sha1, &e)) {
/* Most likely it's a loose object. */
- status = sha1_loose_object_info(sha1, sizep);
- if (status >= 0)
+ status = sha1_loose_object_info(sha1, oi->sizep);
+ if (status >= 0) {
+ oi->whence = OI_LOOSE;
return status;
+ }
/* Not a loose object; someone else may have just packed it. */
reprepare_packed_git();
return status;
}
- status = packed_object_info(e.p, e.offset, sizep);
+ status = packed_object_info(e.p, e.offset, oi->sizep, &rtype);
if (status < 0) {
mark_bad_packed_object(e.p, sha1);
- status = sha1_object_info(sha1, sizep);
+ status = sha1_object_info_extended(sha1, oi);
+ } else if (in_delta_base_cache(e.p, e.offset)) {
+ oi->whence = OI_DBCACHED;
+ } else {
+ oi->whence = OI_PACKED;
+ oi->u.packed.offset = e.offset;
+ oi->u.packed.pack = e.p;
+ oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA ||
+ rtype == OBJ_OFS_DELTA);
}
return status;
}
+int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
+{
+ struct object_info oi;
+
+ oi.sizep = sizep;
+ return sha1_object_info_extended(sha1, &oi);
+}
+
static void *read_packed_sha1(const unsigned char *sha1,
enum object_type *type, unsigned long *size)
{
* deal with them should arrange to call read_object() and give error
* messages themselves.
*/
-void *read_sha1_file_repl(const unsigned char *sha1,
- enum object_type *type,
- unsigned long *size,
- const unsigned char **replacement)
+void *read_sha1_file_extended(const unsigned char *sha1,
+ enum object_type *type,
+ unsigned long *size,
+ unsigned flag)
{
- const unsigned char *repl = lookup_replace_object(sha1);
void *data;
char *path;
const struct packed_git *p;
+ const unsigned char *repl = (flag & READ_SHA1_FILE_REPLACE)
+ ? lookup_replace_object(sha1) : sha1;
errno = 0;
data = read_object(repl, type, size);
- if (data) {
- if (replacement)
- *replacement = repl;
+ if (data)
return data;
- }
if (errno && errno != ENOENT)
die_errno("failed to read object %s", sha1_to_hex(sha1));
{
int fd, ret;
unsigned char compressed[4096];
- z_stream stream;
+ git_zstream stream;
git_SHA_CTX c;
unsigned char parano_sha1[20];
char *filename;
}
static int index_mem(unsigned char *sha1, void *buf, size_t size,
- int write_object, enum object_type type,
- const char *path, int format_check)
+ enum object_type type,
+ const char *path, unsigned flags)
{
int ret, re_allocated = 0;
+ int write_object = flags & HASH_WRITE_OBJECT;
if (!type)
type = OBJ_BLOB;
re_allocated = 1;
}
}
- if (format_check) {
+ if (flags & HASH_FORMAT_CHECK) {
if (type == OBJ_TREE)
check_tree(buf, size);
if (type == OBJ_COMMIT)
return ret;
}
+static int index_pipe(unsigned char *sha1, int fd, enum object_type type,
+ const char *path, unsigned flags)
+{
+ struct strbuf sbuf = STRBUF_INIT;
+ int ret;
+
+ if (strbuf_read(&sbuf, fd, 4096) >= 0)
+ ret = index_mem(sha1, sbuf.buf, sbuf.len, type, path, flags);
+ else
+ ret = -1;
+ strbuf_release(&sbuf);
+ return ret;
+}
+
#define SMALL_FILE_SIZE (32*1024)
-int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
- enum object_type type, const char *path, int format_check)
+static int index_core(unsigned char *sha1, int fd, size_t size,
+ enum object_type type, const char *path,
+ unsigned flags)
{
int ret;
- size_t size = xsize_t(st->st_size);
- if (!S_ISREG(st->st_mode)) {
- struct strbuf sbuf = STRBUF_INIT;
- if (strbuf_read(&sbuf, fd, 4096) >= 0)
- ret = index_mem(sha1, sbuf.buf, sbuf.len, write_object,
- type, path, format_check);
- else
- ret = -1;
- strbuf_release(&sbuf);
- } else if (!size) {
- ret = index_mem(sha1, NULL, size, write_object, type, path,
- format_check);
+ if (!size) {
+ ret = index_mem(sha1, NULL, size, type, path, flags);
} else if (size <= SMALL_FILE_SIZE) {
char *buf = xmalloc(size);
if (size == read_in_full(fd, buf, size))
- ret = index_mem(sha1, buf, size, write_object, type,
- path, format_check);
+ ret = index_mem(sha1, buf, size, type, path, flags);
else
ret = error("short read %s", strerror(errno));
free(buf);
} else {
void *buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
- ret = index_mem(sha1, buf, size, write_object, type, path,
- format_check);
+ ret = index_mem(sha1, buf, size, type, path, flags);
munmap(buf, size);
}
+ return ret;
+}
+
+/*
+ * This creates one packfile per large blob, because the caller
+ * immediately wants the result sha1, and fast-import can report the
+ * object name via marks mechanism only by closing the created
+ * packfile.
+ *
+ * This also bypasses the usual "convert-to-git" dance, and that is on
+ * purpose. We could write a streaming version of the converting
+ * functions and insert that before feeding the data to fast-import
+ * (or equivalent in-core API described above), but the primary
+ * motivation for trying to stream from the working tree file and to
+ * avoid mmaping it in core is to deal with large binary blobs, and
+ * by definition they do _not_ want to get any conversion.
+ */
+static int index_stream(unsigned char *sha1, int fd, size_t size,
+ enum object_type type, const char *path,
+ unsigned flags)
+{
+ struct child_process fast_import;
+ char export_marks[512];
+ const char *argv[] = { "fast-import", "--quiet", export_marks, NULL };
+ char tmpfile[512];
+ char fast_import_cmd[512];
+ char buf[512];
+ int len, tmpfd;
+
+ strcpy(tmpfile, git_path("hashstream_XXXXXX"));
+ tmpfd = git_mkstemp_mode(tmpfile, 0600);
+ if (tmpfd < 0)
+ die_errno("cannot create tempfile: %s", tmpfile);
+ if (close(tmpfd))
+ die_errno("cannot close tempfile: %s", tmpfile);
+ sprintf(export_marks, "--export-marks=%s", tmpfile);
+
+ memset(&fast_import, 0, sizeof(fast_import));
+ fast_import.in = -1;
+ fast_import.argv = argv;
+ fast_import.git_cmd = 1;
+ if (start_command(&fast_import))
+ die_errno("index-stream: git fast-import failed");
+
+ len = sprintf(fast_import_cmd, "blob\nmark :1\ndata %lu\n",
+ (unsigned long) size);
+ write_or_whine(fast_import.in, fast_import_cmd, len,
+ "index-stream: feeding fast-import");
+ while (size) {
+ char buf[10240];
+ size_t sz = size < sizeof(buf) ? size : sizeof(buf);
+ ssize_t actual;
+
+ actual = read_in_full(fd, buf, sz);
+ if (actual < 0)
+ die_errno("index-stream: reading input");
+ if (write_in_full(fast_import.in, buf, actual) != actual)
+ die_errno("index-stream: feeding fast-import");
+ size -= actual;
+ }
+ if (close(fast_import.in))
+ die_errno("index-stream: closing fast-import");
+ if (finish_command(&fast_import))
+ die_errno("index-stream: finishing fast-import");
+
+ tmpfd = open(tmpfile, O_RDONLY);
+ if (tmpfd < 0)
+ die_errno("index-stream: cannot open fast-import mark");
+ len = read(tmpfd, buf, sizeof(buf));
+ if (len < 0)
+ die_errno("index-stream: reading fast-import mark");
+ if (close(tmpfd) < 0)
+ die_errno("index-stream: closing fast-import mark");
+ if (unlink(tmpfile))
+ die_errno("index-stream: unlinking fast-import mark");
+ if (len != 44 ||
+ memcmp(":1 ", buf, 3) ||
+ get_sha1_hex(buf + 3, sha1))
+ die_errno("index-stream: unexpected fast-import mark: <%s>", buf);
+ return 0;
+}
+
+int index_fd(unsigned char *sha1, int fd, struct stat *st,
+ enum object_type type, const char *path, unsigned flags)
+{
+ int ret;
+ size_t size = xsize_t(st->st_size);
+
+ if (!S_ISREG(st->st_mode))
+ ret = index_pipe(sha1, fd, type, path, flags);
+ else if (size <= big_file_threshold || type != OBJ_BLOB)
+ ret = index_core(sha1, fd, size, type, path, flags);
+ else
+ ret = index_stream(sha1, fd, size, type, path, flags);
close(fd);
return ret;
}
-int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object)
+int index_path(unsigned char *sha1, const char *path, struct stat *st, unsigned flags)
{
int fd;
struct strbuf sb = STRBUF_INIT;
if (fd < 0)
return error("open(\"%s\"): %s", path,
strerror(errno));
- if (index_fd(sha1, fd, st, write_object, OBJ_BLOB, path, 0) < 0)
+ if (index_fd(sha1, fd, st, OBJ_BLOB, path, flags) < 0)
return error("%s: failed to insert into database",
path);
break;
return error("readlink(\"%s\"): %s", path,
errstr);
}
- if (!write_object)
+ if (!(flags & HASH_WRITE_OBJECT))
hash_sha1_file(sb.buf, sb.len, blob_type, sha1);
else if (write_sha1_file(sb.buf, sb.len, blob_type, sha1))
return error("%s: failed to insert into database",