X-Git-Url: https://git.octo.it/?a=blobdiff_plain;f=sha1_file.c;h=e45679975e7fcbfae0497f25ab56b6bbd0ff1155;hb=40a10462498bdd23d4e49f02867b8be50eb78704;hp=63cbdded86ca43e4c28626c4644037c3d1d2c694;hpb=f9253394a271a9fefdd234a86c228adeb6d0136a;p=git.git diff --git a/sha1_file.c b/sha1_file.c index 63cbdded..e4567997 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -20,6 +20,8 @@ #endif #endif +const unsigned char null_sha1[20] = { 0, }; + static unsigned int sha1_file_open_flag = O_NOATIME; static unsigned hexval(char c) @@ -46,88 +48,23 @@ int get_sha1_hex(const char *hex, unsigned char *sha1) return 0; } -static int get_sha1_file(const char *path, unsigned char *result) -{ - char buffer[60]; - int fd = open(path, O_RDONLY); - int len; - - if (fd < 0) - return -1; - len = read(fd, buffer, sizeof(buffer)); - close(fd); - if (len < 40) - return -1; - return get_sha1_hex(buffer, result); -} - -static char *git_dir, *git_object_dir, *git_index_file, *git_refs_dir; -static void setup_git_env(void) -{ - git_dir = gitenv(GIT_DIR_ENVIRONMENT); - if (!git_dir) - git_dir = DEFAULT_GIT_DIR_ENVIRONMENT; - git_object_dir = gitenv(DB_ENVIRONMENT); - if (!git_object_dir) { - git_object_dir = xmalloc(strlen(git_dir) + 9); - sprintf(git_object_dir, "%s/objects", git_dir); - } - git_refs_dir = xmalloc(strlen(git_dir) + 6); - sprintf(git_refs_dir, "%s/refs", git_dir); - git_index_file = gitenv(INDEX_ENVIRONMENT); - if (!git_index_file) { - git_index_file = xmalloc(strlen(git_dir) + 7); - sprintf(git_index_file, "%s/index", git_dir); - } -} - -char *get_object_directory(void) -{ - if (!git_object_dir) - setup_git_env(); - return git_object_dir; -} - -char *get_refs_directory(void) -{ - if (!git_refs_dir) - setup_git_env(); - return git_refs_dir; -} - -char *get_index_file(void) -{ - if (!git_index_file) - setup_git_env(); - return git_index_file; -} - -int get_sha1(const char *str, unsigned char *sha1) +int safe_create_leading_directories(char *path) { - static char pathname[PATH_MAX]; - static const char *prefix[] = { - "", - "refs", - "refs/tags", - "refs/heads", - "refs/snap", - NULL - }; - const char **p; - - if (!get_sha1_hex(str, sha1)) - return 0; + char *pos = path; - if (!git_dir) - setup_git_env(); - for (p = prefix; *p; p++) { - snprintf(pathname, sizeof(pathname), "%s/%s/%s", - git_dir, *p, str); - if (!get_sha1_file(pathname, sha1)) - return 0; + while (pos) { + pos = strchr(pos, '/'); + if (!pos) + break; + *pos = 0; + if (mkdir(path, 0777) < 0) + if (errno != EEXIST) { + *pos = '/'; + return -1; + } + *pos++ = '/'; } - - return -1; + return 0; } char * sha1_to_hex(const unsigned char *sha1) @@ -185,84 +122,173 @@ char *sha1_file_name(const unsigned char *sha1) return base; } -struct alternate_object_database *alt_odb; +char *sha1_pack_name(const unsigned char *sha1) +{ + static const char hex[] = "0123456789abcdef"; + static char *name, *base, *buf; + int i; + + if (!base) { + const char *sha1_file_directory = get_object_directory(); + int len = strlen(sha1_file_directory); + base = xmalloc(len + 60); + sprintf(base, "%s/pack/pack-1234567890123456789012345678901234567890.pack", sha1_file_directory); + name = base + len + 11; + } + + buf = name; + + for (i = 0; i < 20; i++) { + unsigned int val = *sha1++; + *buf++ = hex[val >> 4]; + *buf++ = hex[val & 0xf]; + } + + return base; +} + +char *sha1_pack_index_name(const unsigned char *sha1) +{ + static const char hex[] = "0123456789abcdef"; + static char *name, *base, *buf; + int i; + + if (!base) { + const char *sha1_file_directory = get_object_directory(); + int len = strlen(sha1_file_directory); + base = xmalloc(len + 60); + sprintf(base, "%s/pack/pack-1234567890123456789012345678901234567890.idx", sha1_file_directory); + name = base + len + 11; + } + + buf = name; + + for (i = 0; i < 20; i++) { + unsigned int val = *sha1++; + *buf++ = hex[val >> 4]; + *buf++ = hex[val & 0xf]; + } + + return base; +} + +struct alternate_object_database *alt_odb_list; +static struct alternate_object_database **alt_odb_tail; /* * Prepare alternate object database registry. - * alt_odb points at an array of struct alternate_object_database. - * This array is terminated with an element that has both its base - * and name set to NULL. alt_odb[n] comes from n'th non-empty - * element from colon separated ALTERNATE_DB_ENVIRONMENT environment - * variable, and its base points at a statically allocated buffer - * that contains "/the/directory/corresponding/to/.git/objects/...", - * while its name points just after the slash at the end of - * ".git/objects/" in the example above, and has enough space to hold - * 40-byte hex SHA1, an extra slash for the first level indirection, - * and the terminating NUL. - * This function allocates the alt_odb array and all the strings - * pointed by base fields of the array elements with one xmalloc(); - * the string pool immediately follows the array. + * + * The variable alt_odb_list points at the list of struct + * alternate_object_database. The elements on this list come from + * non-empty elements from colon separated ALTERNATE_DB_ENVIRONMENT + * environment variable, and $GIT_OBJECT_DIRECTORY/info/alternates, + * whose contents is exactly in the same format as that environment + * variable. Its base points at a statically allocated buffer that + * contains "/the/directory/corresponding/to/.git/objects/...", while + * its name points just after the slash at the end of ".git/objects/" + * in the example above, and has enough space to hold 40-byte hex + * SHA1, an extra slash for the first level indirection, and the + * terminating NUL. */ -void prepare_alt_odb(void) +static void link_alt_odb_entries(const char *alt, const char *ep, int sep, + const char *relative_base) { - int pass, totlen, i; const char *cp, *last; - char *op = NULL; - const char *alt = gitenv(ALTERNATE_DB_ENVIRONMENT) ? : ""; + struct alternate_object_database *ent; + int base_len = -1; + + last = alt; + while (last < ep) { + cp = last; + if (cp < ep && *cp == '#') { + while (cp < ep && *cp != sep) + cp++; + last = cp + 1; + continue; + } + for ( ; cp < ep && *cp != sep; cp++) + ; + if (last != cp) { + /* 43 = 40-byte + 2 '/' + terminating NUL */ + int pfxlen = cp - last; + int entlen = pfxlen + 43; + + if (*last != '/' && relative_base) { + /* Relative alt-odb */ + if (base_len < 0) + base_len = strlen(relative_base) + 1; + entlen += base_len; + pfxlen += base_len; + } + ent = xmalloc(sizeof(*ent) + entlen); + *alt_odb_tail = ent; + alt_odb_tail = &(ent->next); + ent->next = NULL; + if (*last != '/' && relative_base) { + memcpy(ent->base, relative_base, base_len - 1); + ent->base[base_len - 1] = '/'; + memcpy(ent->base + base_len, + last, cp - last); + } + else + memcpy(ent->base, last, pfxlen); + ent->name = ent->base + pfxlen + 1; + ent->base[pfxlen] = ent->base[pfxlen + 3] = '/'; + ent->base[entlen-1] = 0; + } + while (cp < ep && *cp == sep) + cp++; + last = cp; + } +} + +void prepare_alt_odb(void) +{ + char path[PATH_MAX]; + char *map; + int fd; + struct stat st; + char *alt; - if (alt_odb) + alt = getenv(ALTERNATE_DB_ENVIRONMENT); + if (!alt) alt = ""; + + if (alt_odb_tail) + return; + alt_odb_tail = &alt_odb_list; + link_alt_odb_entries(alt, alt + strlen(alt), ':', NULL); + + sprintf(path, "%s/info/alternates", get_object_directory()); + fd = open(path, O_RDONLY); + if (fd < 0) + return; + if (fstat(fd, &st) || (st.st_size == 0)) { + close(fd); return; - /* The first pass counts how large an area to allocate to - * hold the entire alt_odb structure, including array of - * structs and path buffers for them. The second pass fills - * the structure and prepares the path buffers for use by - * fill_sha1_path(). - */ - for (totlen = pass = 0; pass < 2; pass++) { - last = alt; - i = 0; - do { - cp = strchr(last, ':') ? : last + strlen(last); - if (last != cp) { - /* 43 = 40-byte + 2 '/' + terminating NUL */ - int pfxlen = cp - last; - int entlen = pfxlen + 43; - if (pass == 0) - totlen += entlen; - else { - alt_odb[i].base = op; - alt_odb[i].name = op + pfxlen + 1; - memcpy(op, last, pfxlen); - op[pfxlen] = op[pfxlen + 3] = '/'; - op[entlen-1] = 0; - op += entlen; - } - i++; - } - while (*cp && *cp == ':') - cp++; - last = cp; - } while (*cp); - if (pass) - break; - alt_odb = xmalloc(sizeof(*alt_odb) * (i + 1) + totlen); - alt_odb[i].base = alt_odb[i].name = NULL; - op = (char*)(&alt_odb[i+1]); } + map = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0); + close(fd); + if (map == MAP_FAILED) + return; + + link_alt_odb_entries(map, map + st.st_size, '\n', + get_object_directory()); + munmap(map, st.st_size); } static char *find_sha1_file(const unsigned char *sha1, struct stat *st) { - int i; char *name = sha1_file_name(sha1); + struct alternate_object_database *alt; if (!stat(name, st)) return name; prepare_alt_odb(); - for (i = 0; (name = alt_odb[i].name) != NULL; i++) { + for (alt = alt_odb_list; alt; alt = alt->next) { + name = alt->name; fill_sha1_path(name, sha1); - if (!stat(alt_odb[i].base, st)) - return alt_odb[i].base; + if (!stat(alt->base, st)) + return alt->base; } return NULL; } @@ -272,12 +298,6 @@ static int pack_used_ctr; static unsigned long pack_mapped; struct packed_git *packed_git; -struct pack_entry { - unsigned int offset; - unsigned char sha1[20]; - struct packed_git *p; -}; - static int check_packed_git_idx(const char *path, unsigned long *idx_size_, void **idx_map_) { @@ -300,6 +320,8 @@ static int check_packed_git_idx(const char *path, unsigned long *idx_size_, return -1; index = idx_map; + *idx_map_ = idx_map; + *idx_size_ = idx_size; /* check index map */ if (idx_size < 4*256 + 20 + 20) @@ -322,8 +344,6 @@ static int check_packed_git_idx(const char *path, unsigned long *idx_size_, if (idx_size != 4*256 + nr * 24 + 20 + 20) return error("wrong index file size"); - *idx_map_ = idx_map; - *idx_size_ = idx_size; return 0; } @@ -351,6 +371,14 @@ void unuse_packed_git(struct packed_git *p) int use_packed_git(struct packed_git *p) { + if (!p->pack_size) { + struct stat st; + // We created the struct before we had the pack + stat(p->pack_name, &st); + if (!S_ISREG(st.st_mode)) + die("packfile %s not a regular file", p->pack_name); + p->pack_size = st.st_size; + } if (!p->pack_base) { int fd; struct stat st; @@ -378,15 +406,17 @@ int use_packed_git(struct packed_git *p) * this is cheap. */ if (memcmp((char*)(p->index_base) + p->index_size - 40, - p->pack_base + p->pack_size - 20, 20)) + p->pack_base + p->pack_size - 20, 20)) { + die("packfile %s does not match index.", p->pack_name); + } } p->pack_last_used = pack_used_ctr++; p->pack_use_cnt++; return 0; } -struct packed_git *add_packed_git(char *path, int path_len) +struct packed_git *add_packed_git(char *path, int path_len, int local) { struct stat st; struct packed_git *p; @@ -414,10 +444,48 @@ struct packed_git *add_packed_git(char *path, int path_len) p->pack_base = NULL; p->pack_last_used = 0; p->pack_use_cnt = 0; + p->pack_local = local; + return p; +} + +struct packed_git *parse_pack_index(unsigned char *sha1) +{ + char *path = sha1_pack_index_name(sha1); + return parse_pack_index_file(sha1, path); +} + +struct packed_git *parse_pack_index_file(const unsigned char *sha1, char *idx_path) +{ + struct packed_git *p; + unsigned long idx_size; + void *idx_map; + char *path; + + if (check_packed_git_idx(idx_path, &idx_size, &idx_map)) + return NULL; + + path = sha1_pack_name(sha1); + + p = xmalloc(sizeof(*p) + strlen(path) + 2); + strcpy(p->pack_name, path); + p->index_size = idx_size; + p->pack_size = 0; + p->index_base = idx_map; + p->next = NULL; + p->pack_base = NULL; + p->pack_last_used = 0; + p->pack_use_cnt = 0; + memcpy(p->sha1, sha1, 20); return p; } -static void prepare_packed_git_one(char *objdir) +void install_packed_git(struct packed_git *pack) +{ + pack->next = packed_git; + packed_git = pack; +} + +static void prepare_packed_git_one(char *objdir, int local) { char path[PATH_MAX]; int len; @@ -439,28 +507,29 @@ static void prepare_packed_git_one(char *objdir) /* we have .idx. Is it a file we can map? */ strcpy(path + len, de->d_name); - p = add_packed_git(path, len + namelen); + p = add_packed_git(path, len + namelen, local); if (!p) continue; p->next = packed_git; packed_git = p; } + closedir(dir); } void prepare_packed_git(void) { - int i; static int run_once = 0; + struct alternate_object_database *alt; - if (run_once++) + if (run_once) return; - - prepare_packed_git_one(get_object_directory()); + prepare_packed_git_one(get_object_directory(), 1); prepare_alt_odb(); - for (i = 0; alt_odb[i].base != NULL; i++) { - alt_odb[i].name[0] = 0; - prepare_packed_git_one(alt_odb[i].base); + for (alt = alt_odb_list; alt; alt = alt->next) { + alt->name[0] = 0; + prepare_packed_git_one(alt->base, 0); } + run_once = 1; } int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long size, const char *type) @@ -477,8 +546,7 @@ int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long siz } static void *map_sha1_file_internal(const unsigned char *sha1, - unsigned long *size, - int say_error) + unsigned long *size) { struct stat st; void *map; @@ -486,8 +554,6 @@ static void *map_sha1_file_internal(const unsigned char *sha1, char *filename = find_sha1_file(sha1, &st); if (!filename) { - if (say_error) - error("cannot map sha1 file %s", sha1_to_hex(sha1)); return NULL; } @@ -501,8 +567,6 @@ static void *map_sha1_file_internal(const unsigned char *sha1, break; /* Fallthrough */ case 0: - if (say_error) - perror(filename); return NULL; } @@ -513,17 +577,12 @@ static void *map_sha1_file_internal(const unsigned char *sha1, } map = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0); close(fd); - if (-1 == (int)(long)map) + if (map == MAP_FAILED) return NULL; *size = st.st_size; return map; } -void *map_sha1_file(const unsigned char *sha1, unsigned long *size) -{ - return map_sha1_file_internal(sha1, size, 1); -} - int unpack_sha1_header(z_stream *stream, void *map, unsigned long mapsize, void *buffer, unsigned long size) { /* Get the data stream */ @@ -537,7 +596,7 @@ int unpack_sha1_header(z_stream *stream, void *map, unsigned long mapsize, void return inflate(stream, 0); } -void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size) +static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size) { int bytes = strlen(buffer) + 1; unsigned char *buf = xmalloc(1+size); @@ -618,47 +677,67 @@ void * unpack_sha1_file(void *map, unsigned long mapsize, char *type, unsigned l return unpack_sha1_rest(&stream, hdr, *size); } +/* forward declaration for a mutually recursive function */ +static int packed_object_info(struct pack_entry *entry, + char *type, unsigned long *sizep); + static int packed_delta_info(unsigned char *base_sha1, unsigned long delta_size, unsigned long left, char *type, - unsigned long *sizep) + unsigned long *sizep, + struct packed_git *p) { - const unsigned char *data; - unsigned char delta_head[64]; - unsigned long result_size, base_size, verify_base_size; - z_stream stream; - int st; + struct pack_entry base_ent; if (left < 20) die("truncated pack file"); - if (sha1_object_info(base_sha1, type, &base_size)) - die("cannot get info for delta-pack base"); - memset(&stream, 0, sizeof(stream)); + /* The base entry _must_ be in the same pack */ + if (!find_pack_entry_one(base_sha1, &base_ent, p)) + die("failed to find delta-pack base object %s", + sha1_to_hex(base_sha1)); - data = stream.next_in = base_sha1 + 20; - stream.avail_in = left - 20; - stream.next_out = delta_head; - stream.avail_out = sizeof(delta_head); + /* We choose to only get the type of the base object and + * ignore potentially corrupt pack file that expects the delta + * based on a base with a wrong size. This saves tons of + * inflate() calls. + */ - inflateInit(&stream); - st = inflate(&stream, Z_FINISH); - inflateEnd(&stream); - if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) - die("delta data unpack-initial failed"); + if (packed_object_info(&base_ent, type, NULL)) + die("cannot get info for delta-pack base"); - /* Examine the initial part of the delta to figure out - * the result size. Verify the base size while we are at it. - */ - data = delta_head; - verify_base_size = get_delta_hdr_size(&data); - if (verify_base_size != base_size) - die("delta base size mismatch"); + if (sizep) { + const unsigned char *data; + unsigned char delta_head[64]; + unsigned long result_size; + z_stream stream; + int st; + + memset(&stream, 0, sizeof(stream)); + + data = stream.next_in = base_sha1 + 20; + stream.avail_in = left - 20; + stream.next_out = delta_head; + stream.avail_out = sizeof(delta_head); + + inflateInit(&stream); + st = inflate(&stream, Z_FINISH); + inflateEnd(&stream); + if ((st != Z_STREAM_END) && + stream.total_out != sizeof(delta_head)) + die("delta data unpack-initial failed"); + + /* Examine the initial part of the delta to figure out + * the result size. + */ + data = delta_head; + get_delta_hdr_size(&data); /* ignore base size */ - /* Read the result size */ - result_size = get_delta_hdr_size(&data); - *sizep = result_size; + /* Read the result size */ + result_size = get_delta_hdr_size(&data); + *sizep = result_size; + } return 0; } @@ -690,6 +769,58 @@ static unsigned long unpack_object_header(struct packed_git *p, unsigned long of return offset; } +void packed_object_info_detail(struct pack_entry *e, + char *type, + unsigned long *size, + unsigned long *store_size, + int *delta_chain_length, + unsigned char *base_sha1) +{ + struct packed_git *p = e->p; + unsigned long offset, left; + unsigned char *pack; + enum object_type kind; + + offset = unpack_object_header(p, e->offset, &kind, size); + pack = p->pack_base + offset; + left = p->pack_size - offset; + if (kind != OBJ_DELTA) + *delta_chain_length = 0; + else { + int chain_length = 0; + memcpy(base_sha1, pack, 20); + do { + struct pack_entry base_ent; + unsigned long junk; + + find_pack_entry_one(pack, &base_ent, p); + offset = unpack_object_header(p, base_ent.offset, + &kind, &junk); + pack = p->pack_base + offset; + chain_length++; + } while (kind == OBJ_DELTA); + *delta_chain_length = chain_length; + } + switch (kind) { + case OBJ_COMMIT: + strcpy(type, "commit"); + break; + case OBJ_TREE: + strcpy(type, "tree"); + break; + case OBJ_BLOB: + strcpy(type, "blob"); + break; + case OBJ_TAG: + strcpy(type, "tag"); + break; + default: + die("corrupted pack file %s containing object of kind %d", + p->pack_name, kind); + } + *store_size = 0; /* notyet */ +} + static int packed_object_info(struct pack_entry *entry, char *type, unsigned long *sizep) { @@ -708,7 +839,7 @@ static int packed_object_info(struct pack_entry *entry, switch (kind) { case OBJ_DELTA: - retval = packed_delta_info(pack, size, left, type, sizep); + retval = packed_delta_info(pack, size, left, type, sizep, p); unuse_packed_git(p); return retval; case OBJ_COMMIT: @@ -724,9 +855,11 @@ static int packed_object_info(struct pack_entry *entry, strcpy(type, "tag"); break; default: - die("corrupted pack file"); + die("corrupted pack file %s containing object of kind %d", + p->pack_name, kind); } - *sizep = size; + if (sizep) + *sizep = size; unuse_packed_git(p); return 0; } @@ -738,8 +871,10 @@ static void *unpack_delta_entry(unsigned char *base_sha1, unsigned long delta_size, unsigned long left, char *type, - unsigned long *sizep) + unsigned long *sizep, + struct packed_git *p) { + struct pack_entry base_ent; void *data, *delta_data, *result, *base; unsigned long data_size, result_size, base_size; z_stream stream; @@ -764,8 +899,11 @@ static void *unpack_delta_entry(unsigned char *base_sha1, if ((st != Z_STREAM_END) || stream.total_out != delta_size) die("delta data unpack failed"); - /* This may recursively unpack the base, which is what we want */ - base = read_sha1_file(base_sha1, type, &base_size); + /* The base entry _must_ be in the same pack */ + if (!find_pack_entry_one(base_sha1, &base_ent, p)) + die("failed to find delta-pack base object %s", + sha1_to_hex(base_sha1)); + base = unpack_entry_gently(&base_ent, type, &base_size); if (!base) die("failed to read delta-pack base object %s", sha1_to_hex(base_sha1)); @@ -786,7 +924,7 @@ static void *unpack_non_delta_entry(unsigned char *data, { int st; z_stream stream; - char *buffer; + unsigned char *buffer; buffer = xmalloc(size + 1); buffer[size] = 0; @@ -811,21 +949,33 @@ static void *unpack_entry(struct pack_entry *entry, char *type, unsigned long *sizep) { struct packed_git *p = entry->p; - unsigned long offset, size, left; - unsigned char *pack; - enum object_type kind; void *retval; if (use_packed_git(p)) die("cannot map packed file"); + retval = unpack_entry_gently(entry, type, sizep); + unuse_packed_git(p); + if (!retval) + die("corrupted pack file %s", p->pack_name); + return retval; +} + +/* The caller is responsible for use_packed_git()/unuse_packed_git() pair */ +void *unpack_entry_gently(struct pack_entry *entry, + char *type, unsigned long *sizep) +{ + struct packed_git *p = entry->p; + unsigned long offset, size, left; + unsigned char *pack; + enum object_type kind; + void *retval; offset = unpack_object_header(p, entry->offset, &kind, &size); pack = p->pack_base + offset; left = p->pack_size - offset; switch (kind) { case OBJ_DELTA: - retval = unpack_delta_entry(pack, size, left, type, sizep); - unuse_packed_git(p); + retval = unpack_delta_entry(pack, size, left, type, sizep, p); return retval; case OBJ_COMMIT: strcpy(type, "commit"); @@ -840,11 +990,10 @@ static void *unpack_entry(struct pack_entry *entry, strcpy(type, "tag"); break; default: - die("corrupted pack file"); + return NULL; } *sizep = size; retval = unpack_non_delta_entry(pack, size, left); - unuse_packed_git(p); return retval; } @@ -864,10 +1013,10 @@ int nth_packed_object_sha1(const struct packed_git *p, int n, return 0; } -static int find_pack_entry_1(const unsigned char *sha1, - struct pack_entry *e, struct packed_git *p) +int find_pack_entry_one(const unsigned char *sha1, + struct pack_entry *e, struct packed_git *p) { - int *level1_ofs = p->index_base; + unsigned int *level1_ofs = p->index_base; int hi = ntohl(level1_ofs[*sha1]); int lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1])); void *index = p->index_base + 256; @@ -895,12 +1044,26 @@ static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e) prepare_packed_git(); for (p = packed_git; p; p = p->next) { - if (find_pack_entry_1(sha1, e, p)) + if (find_pack_entry_one(sha1, e, p)) return 1; } return 0; } +struct packed_git *find_sha1_pack(const unsigned char *sha1, + struct packed_git *packs) +{ + struct packed_git *p; + struct pack_entry e; + + for (p = packs; p; p = p->next) { + if (find_pack_entry_one(sha1, &e, p)) + return p; + } + return NULL; + +} + int sha1_object_info(const unsigned char *sha1, char *type, unsigned long *sizep) { int status; @@ -909,18 +1072,13 @@ int sha1_object_info(const unsigned char *sha1, char *type, unsigned long *sizep z_stream stream; char hdr[128]; - map = map_sha1_file_internal(sha1, &mapsize, 0); + map = map_sha1_file_internal(sha1, &mapsize); if (!map) { struct pack_entry e; if (!find_pack_entry(sha1, &e)) return error("unable to find %s", sha1_to_hex(sha1)); - if (!packed_object_info(&e, type, sizep)) - return 0; - /* sheesh */ - map = unpack_entry(&e, type, sizep); - free(map); - return (map == NULL) ? 0 : -1; + return packed_object_info(&e, type, sizep); } if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0) status = error("unable to unpack %s header", @@ -929,7 +1087,8 @@ int sha1_object_info(const unsigned char *sha1, char *type, unsigned long *sizep status = error("unable to parse %s header", sha1_to_hex(sha1)); else { status = 0; - *sizep = size; + if (sizep) + *sizep = size; } inflateEnd(&stream); munmap(map, mapsize); @@ -951,14 +1110,17 @@ void * read_sha1_file(const unsigned char *sha1, char *type, unsigned long *size { unsigned long mapsize; void *map, *buf; + struct pack_entry e; - map = map_sha1_file_internal(sha1, &mapsize, 0); + if (find_pack_entry(sha1, &e)) + return read_packed_sha1(sha1, type, size); + map = map_sha1_file_internal(sha1, &mapsize); if (map) { buf = unpack_sha1_file(map, mapsize, type, size); munmap(map, mapsize); return buf; } - return read_packed_sha1(sha1, type, size); + return NULL; } void *read_object_with_reference(const unsigned char *sha1, @@ -1001,17 +1163,18 @@ void *read_object_with_reference(const unsigned char *sha1, free(buffer); return NULL; } + free(buffer); /* Now we have the ID of the referred-to object in * actual_sha1. Check again. */ } } -static char *write_sha1_file_prepare(void *buf, - unsigned long len, - const char *type, - unsigned char *sha1, - unsigned char *hdr, - int *hdrlen) +char *write_sha1_file_prepare(void *buf, + unsigned long len, + const char *type, + unsigned char *sha1, + unsigned char *hdr, + int *hdrlen) { SHA_CTX c; @@ -1027,6 +1190,73 @@ static char *write_sha1_file_prepare(void *buf, return sha1_file_name(sha1); } +/* + * Link the tempfile to the final place, possibly creating the + * last directory level as you do so. + * + * Returns the errno on failure, 0 on success. + */ +static int link_temp_to_file(const char *tmpfile, char *filename) +{ + int ret; + + if (!link(tmpfile, filename)) + return 0; + + /* + * Try to mkdir the last path component if that failed + * with an ENOENT. + * + * Re-try the "link()" regardless of whether the mkdir + * succeeds, since a race might mean that somebody + * else succeeded. + */ + ret = errno; + if (ret == ENOENT) { + char *dir = strrchr(filename, '/'); + if (dir) { + *dir = 0; + mkdir(filename, 0777); + *dir = '/'; + if (!link(tmpfile, filename)) + return 0; + ret = errno; + } + } + return ret; +} + +/* + * Move the just written object into its final resting place + */ +int move_temp_to_file(const char *tmpfile, char *filename) +{ + int ret = link_temp_to_file(tmpfile, filename); + if (ret) { + /* + * Coda hack - coda doesn't like cross-directory links, + * so we fall back to a rename, which will mean that it + * won't be able to check collisions, but that's not a + * big deal. + * + * When this succeeds, we just return 0. We have nothing + * left to unlink. + */ + if (ret == EXDEV && !rename(tmpfile, filename)) + return 0; + } + unlink(tmpfile); + if (ret) { + if (ret != EEXIST) { + fprintf(stderr, "unable to write sha1 filename %s: %s", filename, strerror(ret)); + return -1; + } + /* FIXME!!! Collision check here ? */ + } + + return 0; +} + int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned char *returnsha1) { int size; @@ -1036,7 +1266,7 @@ int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned cha char *filename; static char tmpfile[PATH_MAX]; unsigned char hdr[50]; - int fd, hdrlen, ret; + int fd, hdrlen; /* Normally if we have it in the pack then we do not bother writing * it out into .git/objects/??/?{38} file. @@ -1099,50 +1329,94 @@ int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned cha close(fd); free(compressed); - ret = link(tmpfile, filename); - if (ret < 0) { - ret = errno; + return move_temp_to_file(tmpfile, filename); +} - /* - * Coda hack - coda doesn't like cross-directory links, - * so we fall back to a rename, which will mean that it - * won't be able to check collisions, but that's not a - * big deal. - * - * When this succeeds, we just return 0. We have nothing - * left to unlink. - */ - if (ret == EXDEV && !rename(tmpfile, filename)) - return 0; +int write_sha1_to_fd(int fd, const unsigned char *sha1) +{ + ssize_t size; + unsigned long objsize; + int posn = 0; + void *map = map_sha1_file_internal(sha1, &objsize); + void *buf = map; + void *temp_obj = NULL; + z_stream stream; + + if (!buf) { + unsigned char *unpacked; + unsigned long len; + char type[20]; + char hdr[50]; + int hdrlen; + // need to unpack and recompress it by itself + unpacked = read_packed_sha1(sha1, type, &len); + + hdrlen = sprintf(hdr, "%s %lu", type, len) + 1; + + /* Set it up */ + memset(&stream, 0, sizeof(stream)); + deflateInit(&stream, Z_BEST_COMPRESSION); + size = deflateBound(&stream, len + hdrlen); + temp_obj = buf = xmalloc(size); + + /* Compress it */ + stream.next_out = buf; + stream.avail_out = size; + + /* First header.. */ + stream.next_in = (void *)hdr; + stream.avail_in = hdrlen; + while (deflate(&stream, 0) == Z_OK) + /* nothing */; + + /* Then the data itself.. */ + stream.next_in = unpacked; + stream.avail_in = len; + while (deflate(&stream, Z_FINISH) == Z_OK) + /* nothing */; + deflateEnd(&stream); + free(unpacked); + + objsize = stream.total_out; } - unlink(tmpfile); - if (ret) { - if (ret != EEXIST) { - fprintf(stderr, "unable to write sha1 filename %s: %s", filename, strerror(ret)); + + do { + size = write(fd, buf + posn, objsize - posn); + if (size <= 0) { + if (!size) { + fprintf(stderr, "write closed"); + } else { + perror("write "); + } return -1; } - /* FIXME!!! Collision check here ? */ - } + posn += size; + } while (posn < objsize); + + if (map) + munmap(map, objsize); + if (temp_obj) + free(temp_obj); return 0; } -int write_sha1_from_fd(const unsigned char *sha1, int fd) +int write_sha1_from_fd(const unsigned char *sha1, int fd, char *buffer, + size_t bufsize, size_t *bufposn) { - char *filename = sha1_file_name(sha1); - + char tmpfile[PATH_MAX]; int local; z_stream stream; unsigned char real_sha1[20]; - unsigned char buf[4096]; unsigned char discard[4096]; int ret; SHA_CTX c; - local = open(filename, O_WRONLY | O_CREAT | O_EXCL, 0666); + snprintf(tmpfile, sizeof(tmpfile), "%s/obj_XXXXXX", get_object_directory()); + local = mkstemp(tmpfile); if (local < 0) - return error("Couldn't open %s\n", filename); + return error("Couldn't open %s for %s\n", tmpfile, sha1_to_hex(sha1)); memset(&stream, 0, sizeof(stream)); @@ -1152,41 +1426,70 @@ int write_sha1_from_fd(const unsigned char *sha1, int fd) do { ssize_t size; - size = read(fd, buf, 4096); + if (*bufposn) { + stream.avail_in = *bufposn; + stream.next_in = (unsigned char *) buffer; + do { + stream.next_out = discard; + stream.avail_out = sizeof(discard); + ret = inflate(&stream, Z_SYNC_FLUSH); + SHA1_Update(&c, discard, sizeof(discard) - + stream.avail_out); + } while (stream.avail_in && ret == Z_OK); + write(local, buffer, *bufposn - stream.avail_in); + memmove(buffer, buffer + *bufposn - stream.avail_in, + stream.avail_in); + *bufposn = stream.avail_in; + if (ret != Z_OK) + break; + } + size = read(fd, buffer + *bufposn, bufsize - *bufposn); if (size <= 0) { close(local); - unlink(filename); + unlink(tmpfile); if (!size) return error("Connection closed?"); perror("Reading from connection"); return -1; } - write(local, buf, size); - stream.avail_in = size; - stream.next_in = buf; - do { - stream.next_out = discard; - stream.avail_out = sizeof(discard); - ret = inflate(&stream, Z_SYNC_FLUSH); - SHA1_Update(&c, discard, sizeof(discard) - - stream.avail_out); - } while (stream.avail_in && ret == Z_OK); - - } while (ret == Z_OK); + *bufposn += size; + } while (1); inflateEnd(&stream); close(local); SHA1_Final(real_sha1, &c); if (ret != Z_STREAM_END) { - unlink(filename); + unlink(tmpfile); return error("File %s corrupted", sha1_to_hex(sha1)); } if (memcmp(sha1, real_sha1, 20)) { - unlink(filename); + unlink(tmpfile); return error("File %s has bad hash\n", sha1_to_hex(sha1)); } - - return 0; + + return move_temp_to_file(tmpfile, sha1_file_name(sha1)); +} + +int has_pack_index(const unsigned char *sha1) +{ + struct stat st; + if (stat(sha1_pack_index_name(sha1), &st)) + return 0; + return 1; +} + +int has_pack_file(const unsigned char *sha1) +{ + struct stat st; + if (stat(sha1_pack_name(sha1), &st)) + return 0; + return 1; +} + +int has_sha1_pack(const unsigned char *sha1) +{ + struct pack_entry e; + return find_pack_entry(sha1, &e); } int has_sha1_file(const unsigned char *sha1) @@ -1194,26 +1497,74 @@ int has_sha1_file(const unsigned char *sha1) struct stat st; struct pack_entry e; - if (find_sha1_file(sha1, &st)) + if (find_pack_entry(sha1, &e)) return 1; - return find_pack_entry(sha1, &e); + return find_sha1_file(sha1, &st) ? 1 : 0; } -int index_fd(unsigned char *sha1, int fd, struct stat *st) +int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, const char *type) { unsigned long size = st->st_size; void *buf; int ret; + unsigned char hdr[50]; + int hdrlen; buf = ""; if (size) buf = mmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0); close(fd); - if ((int)(long)buf == -1) + if (buf == MAP_FAILED) return -1; - ret = write_sha1_file(buf, size, "blob", sha1); + if (!type) + type = "blob"; + if (write_object) + ret = write_sha1_file(buf, size, type, sha1); + else { + write_sha1_file_prepare(buf, size, type, sha1, hdr, &hdrlen); + ret = 0; + } if (size) munmap(buf, size); return ret; } + +int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object) +{ + int fd; + char *target; + + switch (st->st_mode & S_IFMT) { + case S_IFREG: + fd = open(path, O_RDONLY); + if (fd < 0) + return error("open(\"%s\"): %s", path, + strerror(errno)); + if (index_fd(sha1, fd, st, write_object, NULL) < 0) + return error("%s: failed to insert into database", + path); + break; + case S_IFLNK: + target = xmalloc(st->st_size+1); + if (readlink(path, target, st->st_size+1) != st->st_size) { + char *errstr = strerror(errno); + free(target); + return error("readlink(\"%s\"): %s", path, + errstr); + } + if (!write_object) { + unsigned char hdr[50]; + int hdrlen; + write_sha1_file_prepare(target, st->st_size, "blob", + sha1, hdr, &hdrlen); + } else if (write_sha1_file(target, st->st_size, "blob", sha1)) + return error("%s: failed to insert into database", + path); + free(target); + break; + default: + return error("%s: unsupported file type", path); + } + return 0; +}