From: Junio C Hamano Date: Mon, 29 Aug 2011 04:19:21 +0000 (-0700) Subject: Merge branch 'jc/maint-clone-alternates' X-Git-Tag: v1.7.7-rc1~38 X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/2478bd8318c3ad6eceb7b99f01db29499f63b759?ds=inline;hp=-c Merge branch 'jc/maint-clone-alternates' * jc/maint-clone-alternates: clone: clone from a repository with relative alternates clone: allow more than one --reference Conflicts: builtin/clone.c --- 2478bd8318c3ad6eceb7b99f01db29499f63b759 diff --combined builtin/clone.c index 7663bc22c9,16b4fba71f..4d66a7f4e8 --- a/builtin/clone.c +++ b/builtin/clone.c @@@ -39,14 -39,23 +39,24 @@@ static const char * const builtin_clone static int option_no_checkout, option_bare, option_mirror; static int option_local, option_no_hardlinks, option_shared, option_recursive; - static char *option_template, *option_reference, *option_depth; + static char *option_template, *option_depth; static char *option_origin = NULL; static char *option_branch = NULL; static const char *real_git_dir; static char *option_upload_pack = "git-upload-pack"; static int option_verbosity; static int option_progress; +static struct string_list option_config; + static struct string_list option_reference; + + static int opt_parse_reference(const struct option *opt, const char *arg, int unset) + { + struct string_list *option_reference = opt->value; + if (!arg) + return -1; + string_list_append(option_reference, arg); + return 0; + } static struct option builtin_clone_options[] = { OPT__VERBOSITY(&option_verbosity), @@@ -72,8 -81,8 +82,8 @@@ "initialize submodules in the clone"), OPT_STRING(0, "template", &option_template, "template-directory", "directory from which templates will be used"), - OPT_STRING(0, "reference", &option_reference, "repo", - "reference repository"), + OPT_CALLBACK(0 , "reference", &option_reference, "repo", + "reference repository", &opt_parse_reference), OPT_STRING('o', "origin", &option_origin, "branch", "use instead of 'origin' to track upstream"), OPT_STRING('b', "branch", &option_branch, "branch", @@@ -84,8 -93,7 +94,8 @@@ "create a shallow clone of that depth"), OPT_STRING(0, "separate-git-dir", &real_git_dir, "gitdir", "separate git dir from working tree"), - + OPT_STRING_LIST('c', "config", &option_config, "key=value", + "set config inside the new repository"), OPT_END() }; @@@ -199,39 -207,80 +209,80 @@@ static void strip_trailing_slashes(cha *end = '\0'; } - static void setup_reference(const char *repo) + static int add_one_reference(struct string_list_item *item, void *cb_data) { - const char *ref_git; - char *ref_git_copy; - + char *ref_git; + struct strbuf alternate = STRBUF_INIT; struct remote *remote; struct transport *transport; const struct ref *extra; - ref_git = real_path(option_reference); - - if (is_directory(mkpath("%s/.git/objects", ref_git))) - ref_git = mkpath("%s/.git", ref_git); - else if (!is_directory(mkpath("%s/objects", ref_git))) + /* Beware: real_path() and mkpath() return static buffer */ + ref_git = xstrdup(real_path(item->string)); + if (is_directory(mkpath("%s/.git/objects", ref_git))) { + char *ref_git_git = xstrdup(mkpath("%s/.git", ref_git)); + free(ref_git); + ref_git = ref_git_git; + } else if (!is_directory(mkpath("%s/objects", ref_git))) die(_("reference repository '%s' is not a local directory."), - option_reference); - - ref_git_copy = xstrdup(ref_git); + item->string); - add_to_alternates_file(ref_git_copy); + strbuf_addf(&alternate, "%s/objects", ref_git); + add_to_alternates_file(alternate.buf); + strbuf_release(&alternate); - remote = remote_get(ref_git_copy); - transport = transport_get(remote, ref_git_copy); + remote = remote_get(ref_git); + transport = transport_get(remote, ref_git); for (extra = transport_get_remote_refs(transport); extra; extra = extra->next) add_extra_ref(extra->name, extra->old_sha1, 0); transport_disconnect(transport); + free(ref_git); + return 0; + } - free(ref_git_copy); + static void setup_reference(void) + { + for_each_string_list(&option_reference, add_one_reference, NULL); } - static void copy_or_link_directory(struct strbuf *src, struct strbuf *dest) + static void copy_alternates(struct strbuf *src, struct strbuf *dst, + const char *src_repo) + { + /* + * Read from the source objects/info/alternates file + * and copy the entries to corresponding file in the + * destination repository with add_to_alternates_file(). + * Both src and dst have "$path/objects/info/alternates". + * + * Instead of copying bit-for-bit from the original, + * we need to append to existing one so that the already + * created entry via "clone -s" is not lost, and also + * to turn entries with paths relative to the original + * absolute, so that they can be used in the new repository. + */ + FILE *in = fopen(src->buf, "r"); + struct strbuf line = STRBUF_INIT; + + while (strbuf_getline(&line, in, '\n') != EOF) { + char *abs_path, abs_buf[PATH_MAX]; + if (!line.len || line.buf[0] == '#') + continue; + if (is_absolute_path(line.buf)) { + add_to_alternates_file(line.buf); + continue; + } + abs_path = mkpath("%s/objects/%s", src_repo, line.buf); + normalize_path_copy(abs_buf, abs_path); + add_to_alternates_file(abs_buf); + } + strbuf_release(&line); + fclose(in); + } + + static void copy_or_link_directory(struct strbuf *src, struct strbuf *dest, + const char *src_repo, int src_baselen) { struct dirent *de; struct stat buf; @@@ -267,7 -316,14 +318,14 @@@ } if (S_ISDIR(buf.st_mode)) { if (de->d_name[0] != '.') - copy_or_link_directory(src, dest); + copy_or_link_directory(src, dest, + src_repo, src_baselen); + continue; + } + + /* Files that cannot be copied bit-for-bit... */ + if (!strcmp(src->buf + src_baselen, "/info/alternates")) { + copy_alternates(src, dest, src_repo); continue; } @@@ -290,17 -346,20 +348,20 @@@ static const struct ref *clone_local(co const char *dest_repo) { const struct ref *ret; - struct strbuf src = STRBUF_INIT; - struct strbuf dest = STRBUF_INIT; struct remote *remote; struct transport *transport; - if (option_shared) - add_to_alternates_file(src_repo); - else { + if (option_shared) { + struct strbuf alt = STRBUF_INIT; + strbuf_addf(&alt, "%s/objects", src_repo); + add_to_alternates_file(alt.buf); + strbuf_release(&alt); + } else { + struct strbuf src = STRBUF_INIT; + struct strbuf dest = STRBUF_INIT; strbuf_addf(&src, "%s/objects", src_repo); strbuf_addf(&dest, "%s/objects", dest_repo); - copy_or_link_directory(&src, &dest); + copy_or_link_directory(&src, &dest, src_repo, src.len); strbuf_release(&src); strbuf_release(&dest); } @@@ -345,9 -404,8 +406,9 @@@ static void remove_junk_on_signal(int s static struct ref *wanted_peer_refs(const struct ref *refs, struct refspec *refspec) { - struct ref *local_refs = NULL; - struct ref **tail = &local_refs; + struct ref *head = copy_ref(find_ref_by_name(refs, "HEAD")); + struct ref *local_refs = head; + struct ref **tail = head ? &head->next : &local_refs; get_fetch_map(refs, refspec, &tail, 0); if (!option_mirror) @@@ -360,32 -418,13 +421,32 @@@ static void write_remote_refs(const str { const struct ref *r; - for (r = local_refs; r; r = r->next) + for (r = local_refs; r; r = r->next) { + if (!r->peer_ref) + continue; add_extra_ref(r->peer_ref->name, r->old_sha1, 0); + } pack_refs(PACK_REFS_ALL); clear_extra_refs(); } +static int write_one_config(const char *key, const char *value, void *data) +{ + return git_config_set_multivar(key, value ? value : "true", "^$", 0); +} + +static void write_config(struct string_list *config) +{ + int i; + + for (i = 0; i < config->nr; i++) { + if (git_config_parse_parameter(config->items[i].string, + write_one_config, NULL) < 0) + die("unable to write parameters to config file"); + } +} + int cmd_clone(int argc, const char **argv, const char *prefix) { int is_bundle = 0, is_local; @@@ -504,7 -543,6 +565,7 @@@ printf(_("Cloning into %s...\n"), dir); } init_db(option_template, INIT_DB_QUIET); + write_config(&option_config); /* * At this point, the config exists, so we do not need the @@@ -544,8 -582,8 +605,8 @@@ git_config_set(key.buf, repo); strbuf_reset(&key); - if (option_reference) - setup_reference(git_dir); + if (option_reference.nr) + setup_reference(); fetch_pattern = value.buf; refspec = parse_fetch_refspec(1, &fetch_pattern); diff --combined sha1_file.c index 44444ae8f4,f7c3408de6..e002056b85 --- a/sha1_file.c +++ b/sha1_file.c @@@ -380,7 -380,7 +380,7 @@@ void add_to_alternates_file(const char { 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"); @@@ -834,7 -834,7 +834,7 @@@ static int in_window(struct pack_windo 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; @@@ -1186,7 -1186,7 +1186,7 @@@ static int open_sha1_file(const unsigne 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; @@@ -1205,49 -1205,20 +1205,49 @@@ 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, @@@ -1274,7 -1245,7 +1274,7 @@@ 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] = { @@@ -1291,32 -1262,37 +1291,32 @@@ 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); @@@ -1366,7 -1342,7 +1366,7 @@@ * 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; @@@ -1415,7 -1391,7 +1415,7 @@@ 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)); @@@ -1431,7 -1407,7 +1431,7 @@@ unsigned long get_size_from_delta(struc { const unsigned char *data; unsigned char delta_head[20], *in; - z_stream stream; + git_zstream stream; int st; memset(&stream, 0, sizeof(stream)); @@@ -1505,7 -1481,7 +1505,7 @@@ static off_t get_delta_base(struct pack /* 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, @@@ -1519,7 -1495,7 +1519,7 @@@ 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; @@@ -1547,13 -1523,13 +1547,13 @@@ 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; @@@ -1573,8 -1549,63 +1573,8 @@@ 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; @@@ -1582,8 -1613,6 +1582,8 @@@ 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: @@@ -1613,7 -1642,7 +1613,7 @@@ static void *unpack_compressed_entry(st unsigned long size) { int st; - z_stream stream; + git_zstream stream; unsigned char *buffer, *in; buffer = xmallocz(size); @@@ -1666,13 -1695,6 +1666,13 @@@ static unsigned long pack_entry_hash(st 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) { @@@ -1817,24 -1839,6 +1817,24 @@@ static void *unpack_delta_entry(struct 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, @@@ -1844,9 -1848,6 +1844,9 @@@ 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; @@@ -2074,7 -2075,7 +2074,7 @@@ static int sha1_loose_object_info(cons int status; unsigned long mapsize, size; void *map; - z_stream stream; + git_zstream stream; char hdr[32]; map = map_sha1_file(sha1, &mapsize); @@@ -2092,28 -2093,24 +2092,28 @@@ 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(); @@@ -2121,31 -2118,15 +2121,31 @@@ 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) { @@@ -2443,7 -2424,7 +2443,7 @@@ static int write_loose_object(const uns { int fd, ret; unsigned char compressed[4096]; - z_stream stream; + git_zstream stream; git_SHA_CTX c; unsigned char parano_sha1[20]; char *filename; @@@ -2460,7 -2441,7 +2460,7 @@@ /* Set it up */ memset(&stream, 0, sizeof(stream)); - deflateInit(&stream, zlib_compression_level); + git_deflate_init(&stream, zlib_compression_level); stream.next_out = compressed; stream.avail_out = sizeof(compressed); git_SHA1_Init(&c); @@@ -2468,8 -2449,8 +2468,8 @@@ /* First header.. */ stream.next_in = (unsigned char *)hdr; stream.avail_in = hdrlen; - while (deflate(&stream, 0) == Z_OK) - /* nothing */; + while (git_deflate(&stream, 0) == Z_OK) + ; /* nothing */ git_SHA1_Update(&c, hdr, hdrlen); /* Then the data itself.. */ @@@ -2477,7 -2458,7 +2477,7 @@@ stream.avail_in = len; do { unsigned char *in0 = stream.next_in; - ret = deflate(&stream, Z_FINISH); + ret = git_deflate(&stream, Z_FINISH); git_SHA1_Update(&c, in0, stream.next_in - in0); if (write_buffer(fd, compressed, stream.next_out - compressed) < 0) die("unable to write sha1 file"); @@@ -2487,7 -2468,7 +2487,7 @@@ if (ret != Z_STREAM_END) die("unable to deflate new object %s (%d)", sha1_to_hex(sha1), ret); - ret = deflateEnd(&stream); + ret = git_deflate_end_gently(&stream); if (ret != Z_OK) die("deflateEnd on object %s failed (%d)", sha1_to_hex(sha1), ret); git_SHA1_Final(parano_sha1, &c); @@@ -2723,7 -2704,7 +2723,7 @@@ static int index_stream(unsigned char * while (size) { char buf[10240]; size_t sz = size < sizeof(buf) ? size : sizeof(buf); - size_t actual; + ssize_t actual; actual = read_in_full(fd, buf, sz); if (actual < 0)