diff options
Diffstat (limited to 'object-file.c')
-rw-r--r-- | object-file.c | 515 |
1 files changed, 331 insertions, 184 deletions
diff --git a/object-file.c b/object-file.c index 5b270f0..610b1f4 100644 --- a/object-file.c +++ b/object-file.c @@ -6,33 +6,37 @@ * This handles basic git object files - packing, unpacking, * creation etc. */ -#include "cache.h" +#include "git-compat-util.h" +#include "abspath.h" #include "config.h" +#include "convert.h" +#include "environment.h" +#include "gettext.h" +#include "hex.h" #include "string-list.h" #include "lockfile.h" -#include "delta.h" #include "pack.h" -#include "blob.h" #include "commit.h" #include "run-command.h" -#include "tag.h" -#include "tree.h" -#include "tree-walk.h" #include "refs.h" -#include "pack-revindex.h" -#include "hash-lookup.h" #include "bulk-checkin.h" #include "repository.h" #include "replace-object.h" #include "streaming.h" #include "dir.h" #include "list.h" -#include "mergesort.h" #include "quote.h" #include "packfile.h" +#include "object-file.h" #include "object-store.h" +#include "oidtree.h" +#include "path.h" #include "promisor-remote.h" +#include "setup.h" #include "submodule.h" +#include "fsck.h" +#include "loose.h" +#include "object-file-convert.h" /* The maximum size for an object header. */ #define MAX_HEADER_LEN 32 @@ -140,27 +144,32 @@ static void git_hash_sha256_final_oid(struct object_id *oid, git_hash_ctx *ctx) oid->algo = GIT_HASH_SHA256; } -static void git_hash_unknown_init(git_hash_ctx *ctx) +static void git_hash_unknown_init(git_hash_ctx *ctx UNUSED) { BUG("trying to init unknown hash"); } -static void git_hash_unknown_clone(git_hash_ctx *dst, const git_hash_ctx *src) +static void git_hash_unknown_clone(git_hash_ctx *dst UNUSED, + const git_hash_ctx *src UNUSED) { BUG("trying to clone unknown hash"); } -static void git_hash_unknown_update(git_hash_ctx *ctx, const void *data, size_t len) +static void git_hash_unknown_update(git_hash_ctx *ctx UNUSED, + const void *data UNUSED, + size_t len UNUSED) { BUG("trying to update unknown hash"); } -static void git_hash_unknown_final(unsigned char *hash, git_hash_ctx *ctx) +static void git_hash_unknown_final(unsigned char *hash UNUSED, + git_hash_ctx *ctx UNUSED) { BUG("trying to finalize unknown hash"); } -static void git_hash_unknown_final_oid(struct object_id *oid, git_hash_ctx *ctx) +static void git_hash_unknown_final_oid(struct object_id *oid UNUSED, + git_hash_ctx *ctx UNUSED) { BUG("trying to finalize unknown hash"); } @@ -261,7 +270,7 @@ int hash_algo_by_length(int len) /* * This is meant to hold a *small* number of objects that you would - * want read_object_file() to be able to return, but yet you do not want + * want repo_read_object_file() to be able to return, but yet you do not want * to write them into the object store (e.g. a browse-only * application). */ @@ -503,7 +512,9 @@ static int link_alt_odb_entry(struct repository *r, const struct strbuf *entry, { struct object_directory *ent; struct strbuf pathbuf = STRBUF_INIT; + struct strbuf tmp = STRBUF_INIT; khiter_t pos; + int ret = -1; if (!is_absolute_path(entry->buf) && relative_base) { strbuf_realpath(&pathbuf, relative_base, 1); @@ -511,12 +522,12 @@ static int link_alt_odb_entry(struct repository *r, const struct strbuf *entry, } strbuf_addbuf(&pathbuf, entry); - if (strbuf_normalize_path(&pathbuf) < 0 && relative_base) { + if (!strbuf_realpath(&tmp, pathbuf.buf, 0)) { error(_("unable to normalize alternate object path: %s"), pathbuf.buf); - strbuf_release(&pathbuf); - return -1; + goto error; } + strbuf_swap(&pathbuf, &tmp); /* * The trailing slash after the directory name is given by @@ -525,10 +536,8 @@ static int link_alt_odb_entry(struct repository *r, const struct strbuf *entry, while (pathbuf.len && pathbuf.buf[pathbuf.len - 1] == '/') strbuf_setlen(&pathbuf, pathbuf.len - 1); - if (!alt_odb_usable(r->objects, &pathbuf, normalized_objdir, &pos)) { - strbuf_release(&pathbuf); - return -1; - } + if (!alt_odb_usable(r->objects, &pathbuf, normalized_objdir, &pos)) + goto error; CALLOC_ARRAY(ent, 1); /* pathbuf.buf is already in r->objects->odb_by_path */ @@ -543,8 +552,11 @@ static int link_alt_odb_entry(struct repository *r, const struct strbuf *entry, /* recursively add alternates */ read_info_alternates(r, ent->path, depth + 1); - - return 0; + ret = 0; + error: + strbuf_release(&tmp); + strbuf_release(&pathbuf); + return ret; } static const char *parse_alt_odb_entry(const char *string, @@ -591,10 +603,7 @@ static void link_alt_odb_entries(struct repository *r, const char *alt, return; } - strbuf_add_absolute_path(&objdirbuf, r->objects->odb->path); - if (strbuf_normalize_path(&objdirbuf) < 0) - die(_("unable to normalize object directory: %s"), - objdirbuf.buf); + strbuf_realpath(&objdirbuf, r->objects->odb->path, 1); while (*alt) { alt = parse_alt_odb_entry(alt, sep, &entry); @@ -938,6 +947,12 @@ void prepare_alt_odb(struct repository *r) r->objects->loaded_alternates = 1; } +int has_alt_odb(struct repository *r) +{ + prepare_alt_odb(r); + return !!r->objects->odb->next; +} + /* Returns 1 if we have successfully freshened the file, 0 otherwise. */ static int freshen_file(const char *fn) { @@ -1071,9 +1086,11 @@ int check_object_signature(struct repository *r, const struct object_id *oid, void *buf, unsigned long size, enum object_type type) { + const struct git_hash_algo *algo = + oid->algo ? &hash_algos[oid->algo] : r->hash_algo; struct object_id real_oid; - hash_object_file(r->hash_algo, buf, size, type, &real_oid); + hash_object_file(algo, buf, size, type, &real_oid); return !oideq(oid, &real_oid) ? -1 : 0; } @@ -1206,35 +1223,25 @@ static int quick_has_loose(struct repository *r, } /* - * Map the loose object at "path" if it is not NULL, or the path found by - * searching for a loose object named "oid". + * Map and close the given loose object fd. The path argument is used for + * error reporting. */ -static void *map_loose_object_1(struct repository *r, const char *path, - const struct object_id *oid, unsigned long *size) +static void *map_fd(int fd, const char *path, unsigned long *size) { - void *map; - int fd; - - if (path) - fd = git_open(path); - else - fd = open_loose_object(r, oid, &path); - map = NULL; - if (fd >= 0) { - struct stat st; + void *map = NULL; + struct stat st; - if (!fstat(fd, &st)) { - *size = xsize_t(st.st_size); - if (!*size) { - /* mmap() is forbidden on empty files */ - error(_("object file %s is empty"), path); - close(fd); - return NULL; - } - map = xmmap(NULL, *size, PROT_READ, MAP_PRIVATE, fd, 0); + if (!fstat(fd, &st)) { + *size = xsize_t(st.st_size); + if (!*size) { + /* mmap() is forbidden on empty files */ + error(_("object file %s is empty"), path); + close(fd); + return NULL; } - close(fd); + map = xmmap(NULL, *size, PROT_READ, MAP_PRIVATE, fd, 0); } + close(fd); return map; } @@ -1242,7 +1249,12 @@ void *map_loose_object(struct repository *r, const struct object_id *oid, unsigned long *size) { - return map_loose_object_1(r, NULL, oid, size); + const char *p; + int fd = open_loose_object(r, oid, &p); + + if (fd < 0) + return NULL; + return map_fd(fd, p, size); } enum unpack_loose_header_result unpack_loose_header(git_zstream *stream, @@ -1422,7 +1434,9 @@ static int loose_object_info(struct repository *r, struct object_info *oi, int flags) { int status = 0; + int fd; unsigned long mapsize; + const char *path; void *map; git_zstream stream; char hdr[MAX_HEADER_LEN]; @@ -1443,7 +1457,6 @@ static int loose_object_info(struct repository *r, * object even exists. */ if (!oi->typep && !oi->type_name && !oi->sizep && !oi->contentp) { - const char *path; struct stat st; if (!oi->disk_sizep && (flags & OBJECT_INFO_QUICK)) return quick_has_loose(r, oid) ? 0 : -1; @@ -1454,7 +1467,13 @@ static int loose_object_info(struct repository *r, return 0; } - map = map_loose_object(r, oid, &mapsize); + fd = open_loose_object(r, oid, &path); + if (fd < 0) { + if (errno != ENOENT) + error_errno(_("unable to open loose object %s"), oid_to_hex(oid)); + return -1; + } + map = map_fd(fd, path, &mapsize); if (!map) return -1; @@ -1492,6 +1511,10 @@ static int loose_object_info(struct repository *r, break; } + if (status && (flags & OBJECT_INFO_DIE_IF_CORRUPT)) + die(_("loose object %s (stored in %s) is corrupt"), + oid_to_hex(oid), path); + git_inflate_end(&stream); cleanup: munmap(map, mapsize); @@ -1570,9 +1593,6 @@ static int do_oid_object_info_extended(struct repository *r, if (find_pack_entry(r, real, &e)) break; - if (flags & OBJECT_INFO_IGNORE_LOOSE) - return -1; - /* Most likely it's a loose object. */ if (!loose_object_info(r, real, oi, flags)) return 0; @@ -1599,15 +1619,20 @@ static int do_oid_object_info_extended(struct repository *r, if (fetch_if_missing && repo_has_promisor_remote(r) && !already_retried && !(flags & OBJECT_INFO_SKIP_FETCH_OBJECT)) { - /* - * TODO Investigate checking promisor_remote_get_direct() - * TODO return value and stopping on error here. - */ promisor_remote_get_direct(r, real, 1); already_retried = 1; continue; } + if (flags & OBJECT_INFO_DIE_IF_CORRUPT) { + const struct packed_git *p; + if ((flags & OBJECT_INFO_LOOKUP_REPLACE) && !oideq(real, oid)) + die(_("replacement %s not found for %s"), + oid_to_hex(real), oid_to_hex(oid)); + if ((p = has_packed_and_bad(r, real))) + die(_("packed object %s (stored in %s) is corrupt"), + oid_to_hex(real), p->pack_name); + } return -1; } @@ -1631,10 +1656,101 @@ static int do_oid_object_info_extended(struct repository *r, return 0; } +static int oid_object_info_convert(struct repository *r, + const struct object_id *input_oid, + struct object_info *input_oi, unsigned flags) +{ + const struct git_hash_algo *input_algo = &hash_algos[input_oid->algo]; + int do_die = flags & OBJECT_INFO_DIE_IF_CORRUPT; + struct strbuf type_name = STRBUF_INIT; + struct object_id oid, delta_base_oid; + struct object_info new_oi, *oi; + unsigned long size; + void *content; + int ret; + + if (repo_oid_to_algop(r, input_oid, the_hash_algo, &oid)) { + if (do_die) + die(_("missing mapping of %s to %s"), + oid_to_hex(input_oid), the_hash_algo->name); + return -1; + } + + /* Is new_oi needed? */ + oi = input_oi; + if (input_oi && (input_oi->delta_base_oid || input_oi->sizep || + input_oi->contentp)) { + new_oi = *input_oi; + /* Does delta_base_oid need to be converted? */ + if (input_oi->delta_base_oid) + new_oi.delta_base_oid = &delta_base_oid; + /* Will the attributes differ when converted? */ + if (input_oi->sizep || input_oi->contentp) { + new_oi.contentp = &content; + new_oi.sizep = &size; + new_oi.type_name = &type_name; + } + oi = &new_oi; + } + + ret = oid_object_info_extended(r, &oid, oi, flags); + if (ret) + return -1; + if (oi == input_oi) + return ret; + + if (new_oi.contentp) { + struct strbuf outbuf = STRBUF_INIT; + enum object_type type; + + type = type_from_string_gently(type_name.buf, type_name.len, + !do_die); + if (type == -1) + return -1; + if (type != OBJ_BLOB) { + ret = convert_object_file(&outbuf, + the_hash_algo, input_algo, + content, size, type, !do_die); + if (ret == -1) + return -1; + free(content); + size = outbuf.len; + content = strbuf_detach(&outbuf, NULL); + } + if (input_oi->sizep) + *input_oi->sizep = size; + if (input_oi->contentp) + *input_oi->contentp = content; + else + free(content); + if (input_oi->type_name) + *input_oi->type_name = type_name; + else + strbuf_release(&type_name); + } + if (new_oi.delta_base_oid == &delta_base_oid) { + if (repo_oid_to_algop(r, &delta_base_oid, input_algo, + input_oi->delta_base_oid)) { + if (do_die) + die(_("missing mapping of %s to %s"), + oid_to_hex(&delta_base_oid), + input_algo->name); + return -1; + } + } + input_oi->whence = new_oi.whence; + input_oi->u = new_oi.u; + return ret; +} + int oid_object_info_extended(struct repository *r, const struct object_id *oid, struct object_info *oi, unsigned flags) { int ret; + + if (oid->algo && (hash_algo_by_ptr(r->hash_algo) != oid->algo)) + return oid_object_info_convert(r, oid, oi, flags); + obj_read_lock(); ret = do_oid_object_info_extended(r, oid, oi, flags); obj_read_unlock(); @@ -1658,28 +1774,13 @@ int oid_object_info(struct repository *r, return type; } -static void *read_object(struct repository *r, - const struct object_id *oid, enum object_type *type, - unsigned long *size) -{ - struct object_info oi = OBJECT_INFO_INIT; - void *content; - oi.typep = type; - oi.sizep = size; - oi.contentp = &content; - - if (oid_object_info_extended(r, oid, &oi, 0) < 0) - return NULL; - return content; -} - int pretend_object_file(void *buf, unsigned long len, enum object_type type, struct object_id *oid) { struct cached_object *co; hash_object_file(the_hash_algo, buf, len, type, oid); - if (has_object_file_with_flags(oid, OBJECT_INFO_QUICK | OBJECT_INFO_SKIP_FETCH_OBJECT) || + if (repo_has_object_file_with_flags(the_repository, oid, OBJECT_INFO_QUICK | OBJECT_INFO_SKIP_FETCH_OBJECT) || find_cached_object(oid)) return 0; ALLOC_GROW(cached_objects, cached_object_nr + 1, cached_object_alloc); @@ -1694,46 +1795,25 @@ int pretend_object_file(void *buf, unsigned long len, enum object_type type, /* * This function dies on corrupt objects; the callers who want to - * deal with them should arrange to call read_object() and give error - * messages themselves. + * deal with them should arrange to call oid_object_info_extended() and give + * error messages themselves. */ -void *read_object_file_extended(struct repository *r, - const struct object_id *oid, - enum object_type *type, - unsigned long *size, - int lookup_replace) +void *repo_read_object_file(struct repository *r, + const struct object_id *oid, + enum object_type *type, + unsigned long *size) { + struct object_info oi = OBJECT_INFO_INIT; + unsigned flags = OBJECT_INFO_DIE_IF_CORRUPT | OBJECT_INFO_LOOKUP_REPLACE; void *data; - const struct packed_git *p; - const char *path; - struct stat st; - const struct object_id *repl = lookup_replace ? - lookup_replace_object(r, oid) : oid; - - errno = 0; - data = read_object(r, repl, type, size); - if (data) - return data; - - obj_read_lock(); - if (errno && errno != ENOENT) - die_errno(_("failed to read object %s"), oid_to_hex(oid)); - - /* die if we replaced an object with one that does not exist */ - if (repl != oid) - die(_("replacement %s not found for %s"), - oid_to_hex(repl), oid_to_hex(oid)); - - if (!stat_loose_object(r, repl, &st, &path)) - die(_("loose object %s (stored in %s) is corrupt"), - oid_to_hex(repl), path); - if ((p = has_packed_and_bad(r, repl))) - die(_("packed object %s (stored in %s) is corrupt"), - oid_to_hex(repl), p->pack_name); - obj_read_unlock(); + oi.typep = type; + oi.sizep = size; + oi.contentp = &data; + if (oid_object_info_extended(r, oid, &oi, flags)) + return NULL; - return NULL; + return data; } void *read_object_with_reference(struct repository *r, @@ -1863,13 +1943,6 @@ out: return 0; } -static int write_buffer(int fd, const void *buf, size_t len) -{ - if (write_in_full(fd, buf, len) < 0) - return error_errno(_("file write error")); - return 0; -} - static void hash_object_file_literally(const struct git_hash_algo *algo, const void *buf, unsigned long len, const char *type, struct object_id *oid) @@ -1966,9 +2039,12 @@ static int start_loose_object_common(struct strbuf *tmp_file, const char *filename, unsigned flags, git_zstream *stream, unsigned char *buf, size_t buflen, - git_hash_ctx *c, + git_hash_ctx *c, git_hash_ctx *compat_c, char *hdr, int hdrlen) { + struct repository *repo = the_repository; + const struct git_hash_algo *algo = repo->hash_algo; + const struct git_hash_algo *compat = repo->compat_hash_algo; int fd; fd = create_tmpfile(tmp_file, filename); @@ -1988,14 +2064,18 @@ static int start_loose_object_common(struct strbuf *tmp_file, git_deflate_init(stream, zlib_compression_level); stream->next_out = buf; stream->avail_out = buflen; - the_hash_algo->init_fn(c); + algo->init_fn(c); + if (compat && compat_c) + compat->init_fn(compat_c); /* Start to feed header to zlib stream */ stream->next_in = (unsigned char *)hdr; stream->avail_in = hdrlen; while (git_deflate(stream, 0) == Z_OK) ; /* nothing */ - the_hash_algo->update_fn(c, hdr, hdrlen); + algo->update_fn(c, hdr, hdrlen); + if (compat && compat_c) + compat->update_fn(compat_c, hdr, hdrlen); return fd; } @@ -2004,18 +2084,23 @@ static int start_loose_object_common(struct strbuf *tmp_file, * Common steps for the inner git_deflate() loop for writing loose * objects. Returns what git_deflate() returns. */ -static int write_loose_object_common(git_hash_ctx *c, +static int write_loose_object_common(git_hash_ctx *c, git_hash_ctx *compat_c, git_zstream *stream, const int flush, unsigned char *in0, const int fd, unsigned char *compressed, const size_t compressed_len) { + struct repository *repo = the_repository; + const struct git_hash_algo *algo = repo->hash_algo; + const struct git_hash_algo *compat = repo->compat_hash_algo; int ret; ret = git_deflate(stream, flush ? Z_FINISH : 0); - the_hash_algo->update_fn(c, in0, stream->next_in - in0); - if (write_buffer(fd, compressed, stream->next_out - compressed) < 0) - die(_("unable to write loose object file")); + algo->update_fn(c, in0, stream->next_in - in0); + if (compat && compat_c) + compat->update_fn(compat_c, in0, stream->next_in - in0); + if (write_in_full(fd, compressed, stream->next_out - compressed) < 0) + die_errno(_("unable to write loose object file")); stream->next_out = compressed; stream->avail_out = compressed_len; @@ -2028,15 +2113,21 @@ static int write_loose_object_common(git_hash_ctx *c, * - End the compression of zlib stream. * - Get the calculated oid to "oid". */ -static int end_loose_object_common(git_hash_ctx *c, git_zstream *stream, - struct object_id *oid) +static int end_loose_object_common(git_hash_ctx *c, git_hash_ctx *compat_c, + git_zstream *stream, struct object_id *oid, + struct object_id *compat_oid) { + struct repository *repo = the_repository; + const struct git_hash_algo *algo = repo->hash_algo; + const struct git_hash_algo *compat = repo->compat_hash_algo; int ret; ret = git_deflate_end_gently(stream); if (ret != Z_OK) return ret; - the_hash_algo->final_oid_fn(oid, c); + algo->final_oid_fn(oid, c); + if (compat && compat_c) + compat->final_oid_fn(compat_oid, compat_c); return Z_OK; } @@ -2060,7 +2151,7 @@ static int write_loose_object(const struct object_id *oid, char *hdr, fd = start_loose_object_common(&tmp_file, filename.buf, flags, &stream, compressed, sizeof(compressed), - &c, hdr, hdrlen); + &c, NULL, hdr, hdrlen); if (fd < 0) return -1; @@ -2070,14 +2161,14 @@ static int write_loose_object(const struct object_id *oid, char *hdr, do { unsigned char *in0 = stream.next_in; - ret = write_loose_object_common(&c, &stream, 1, in0, fd, + ret = write_loose_object_common(&c, NULL, &stream, 1, in0, fd, compressed, sizeof(compressed)); } while (ret == Z_OK); if (ret != Z_STREAM_END) die(_("unable to deflate new object %s (%d)"), oid_to_hex(oid), ret); - ret = end_loose_object_common(&c, &stream, ¶no_oid); + ret = end_loose_object_common(&c, NULL, &stream, ¶no_oid, NULL); if (ret != Z_OK) die(_("deflateEnd on object %s failed (%d)"), oid_to_hex(oid), ret); @@ -2122,10 +2213,12 @@ static int freshen_packed_object(const struct object_id *oid) int stream_loose_object(struct input_stream *in_stream, size_t len, struct object_id *oid) { + const struct git_hash_algo *compat = the_repository->compat_hash_algo; + struct object_id compat_oid; int fd, ret, err = 0, flush = 0; unsigned char compressed[4096]; git_zstream stream; - git_hash_ctx c; + git_hash_ctx c, compat_c; struct strbuf tmp_file = STRBUF_INIT; struct strbuf filename = STRBUF_INIT; int dirlen; @@ -2149,7 +2242,7 @@ int stream_loose_object(struct input_stream *in_stream, size_t len, */ fd = start_loose_object_common(&tmp_file, filename.buf, 0, &stream, compressed, sizeof(compressed), - &c, hdr, hdrlen); + &c, &compat_c, hdr, hdrlen); if (fd < 0) { err = -1; goto cleanup; @@ -2167,7 +2260,7 @@ int stream_loose_object(struct input_stream *in_stream, size_t len, if (in_stream->is_finished) flush = 1; } - ret = write_loose_object_common(&c, &stream, flush, in0, fd, + ret = write_loose_object_common(&c, &compat_c, &stream, flush, in0, fd, compressed, sizeof(compressed)); /* * Unlike write_loose_object(), we do not have the entire @@ -2190,7 +2283,7 @@ int stream_loose_object(struct input_stream *in_stream, size_t len, */ if (ret != Z_STREAM_END) die(_("unable to stream deflate new object (%d)"), ret); - ret = end_loose_object_common(&c, &stream, oid); + ret = end_loose_object_common(&c, &compat_c, &stream, oid, &compat_oid); if (ret != Z_OK) die(_("deflateEnd on stream object failed (%d)"), ret); close_loose_object(fd, tmp_file.buf); @@ -2217,6 +2310,8 @@ int stream_loose_object(struct input_stream *in_stream, size_t len, } err = finalize_object_file(tmp_file.buf, filename.buf); + if (!err && compat) + err = repo_add_loose_object_map(the_repository, oid, &compat_oid); cleanup: strbuf_release(&tmp_file); strbuf_release(&filename); @@ -2225,19 +2320,42 @@ cleanup: int write_object_file_flags(const void *buf, unsigned long len, enum object_type type, struct object_id *oid, - unsigned flags) + struct object_id *compat_oid_in, unsigned flags) { + struct repository *repo = the_repository; + const struct git_hash_algo *algo = repo->hash_algo; + const struct git_hash_algo *compat = repo->compat_hash_algo; + struct object_id compat_oid; char hdr[MAX_HEADER_LEN]; int hdrlen = sizeof(hdr); + /* Generate compat_oid */ + if (compat) { + if (compat_oid_in) + oidcpy(&compat_oid, compat_oid_in); + else if (type == OBJ_BLOB) + hash_object_file(compat, buf, len, type, &compat_oid); + else { + struct strbuf converted = STRBUF_INIT; + convert_object_file(&converted, algo, compat, + buf, len, type, 0); + hash_object_file(compat, converted.buf, converted.len, + type, &compat_oid); + strbuf_release(&converted); + } + } + /* Normally if we have it in the pack then we do not bother writing * it out into .git/objects/??/?{38} file. */ - write_object_file_prepare(the_hash_algo, buf, len, type, oid, hdr, - &hdrlen); + write_object_file_prepare(algo, buf, len, type, oid, hdr, &hdrlen); if (freshen_packed_object(oid) || freshen_loose_object(oid)) return 0; - return write_loose_object(oid, hdr, hdrlen, buf, len, 0, flags); + if (write_loose_object(oid, hdr, hdrlen, buf, len, 0, flags)) + return -1; + if (compat) + return repo_add_loose_object_map(repo, oid, &compat_oid); + return 0; } int write_object_file_literally(const void *buf, unsigned long len, @@ -2245,7 +2363,27 @@ int write_object_file_literally(const void *buf, unsigned long len, unsigned flags) { char *header; + struct repository *repo = the_repository; + const struct git_hash_algo *algo = repo->hash_algo; + const struct git_hash_algo *compat = repo->compat_hash_algo; + struct object_id compat_oid; int hdrlen, status = 0; + int compat_type = -1; + + if (compat) { + compat_type = type_from_string_gently(type, -1, 1); + if (compat_type == OBJ_BLOB) + hash_object_file(compat, buf, len, compat_type, + &compat_oid); + else if (compat_type != -1) { + struct strbuf converted = STRBUF_INIT; + convert_object_file(&converted, algo, compat, + buf, len, compat_type, 0); + hash_object_file(compat, converted.buf, converted.len, + compat_type, &compat_oid); + strbuf_release(&converted); + } + } /* type string, SP, %lu of the length plus NUL must fit this */ hdrlen = strlen(type) + MAX_HEADER_LEN; @@ -2258,6 +2396,8 @@ int write_object_file_literally(const void *buf, unsigned long len, if (freshen_packed_object(oid) || freshen_loose_object(oid)) goto cleanup; status = write_loose_object(oid, header, hdrlen, buf, len, 0, 0); + if (compat_type != -1) + return repo_add_loose_object_map(repo, oid, &compat_oid); cleanup: free(header); @@ -2266,8 +2406,12 @@ cleanup: int force_object_loose(const struct object_id *oid, time_t mtime) { + struct repository *repo = the_repository; + const struct git_hash_algo *compat = repo->compat_hash_algo; void *buf; unsigned long len; + struct object_info oi = OBJECT_INFO_INIT; + struct object_id compat_oid; enum object_type type; char hdr[MAX_HEADER_LEN]; int hdrlen; @@ -2275,11 +2419,20 @@ int force_object_loose(const struct object_id *oid, time_t mtime) if (has_loose_object(oid)) return 0; - buf = read_object(the_repository, oid, &type, &len); - if (!buf) + oi.typep = &type; + oi.sizep = &len; + oi.contentp = &buf; + if (oid_object_info_extended(the_repository, oid, &oi, 0)) return error(_("cannot read object for %s"), oid_to_hex(oid)); + if (compat) { + if (repo_oid_to_algop(repo, oid, compat, &compat_oid)) + return error(_("cannot map object %s to %s"), + oid_to_hex(oid), compat->name); + } hdrlen = format_object_header(hdr, sizeof(hdr), type, len); ret = write_loose_object(oid, hdr, hdrlen, buf, len, mtime, 0); + if (!ret && compat) + ret = repo_add_loose_object_map(the_repository, oid, &compat_oid); free(buf); return ret; @@ -2311,32 +2464,21 @@ int repo_has_object_file(struct repository *r, return repo_has_object_file_with_flags(r, oid, 0); } -static void check_tree(const void *buf, size_t size) -{ - struct tree_desc desc; - struct name_entry entry; - - init_tree_desc(&desc, buf, size); - while (tree_entry(&desc, &entry)) - /* do nothing - * tree_entry() will die() on malformed entries */ - ; -} - -static void check_commit(const void *buf, size_t size) -{ - struct commit c; - memset(&c, 0, sizeof(c)); - if (parse_commit_buffer(the_repository, &c, buf, size, 0)) - die(_("corrupt commit")); -} - -static void check_tag(const void *buf, size_t size) -{ - struct tag t; - memset(&t, 0, sizeof(t)); - if (parse_tag_buffer(the_repository, &t, buf, size)) - die(_("corrupt tag")); +/* + * We can't use the normal fsck_error_function() for index_mem(), + * because we don't yet have a valid oid for it to report. Instead, + * report the minimal fsck error here, and rely on the caller to + * give more context. + */ +static int hash_format_check_report(struct fsck_options *opts UNUSED, + const struct object_id *oid UNUSED, + enum object_type object_type UNUSED, + enum fsck_msg_type msg_type UNUSED, + enum fsck_msg_id msg_id UNUSED, + const char *message) +{ + error(_("object fails fsck: %s"), message); + return 1; } static int index_mem(struct index_state *istate, @@ -2363,12 +2505,13 @@ static int index_mem(struct index_state *istate, } } if (flags & HASH_FORMAT_CHECK) { - if (type == OBJ_TREE) - check_tree(buf, size); - if (type == OBJ_COMMIT) - check_commit(buf, size); - if (type == OBJ_TAG) - check_tag(buf, size); + struct fsck_options opts = FSCK_OPTIONS_DEFAULT; + + opts.strict = 1; + opts.error_func = hash_format_check_report; + if (fsck_buffer(null_oid(), type, buf, size, &opts)) + die(_("refusing to create malformed object")); + fsck_finish(&opts); } if (write_object) @@ -2467,11 +2610,11 @@ static int index_core(struct index_state *istate, * binary blobs, they generally do not want to get any conversion, and * callers should avoid this code path when filters are requested. */ -static int index_stream(struct object_id *oid, int fd, size_t size, - enum object_type type, const char *path, - unsigned flags) +static int index_blob_stream(struct object_id *oid, int fd, size_t size, + const char *path, + unsigned flags) { - return index_bulk_checkin(oid, fd, size, type, path, flags); + return index_blob_bulk_checkin(oid, fd, size, path, flags); } int index_fd(struct index_state *istate, struct object_id *oid, @@ -2493,8 +2636,8 @@ int index_fd(struct index_state *istate, struct object_id *oid, ret = index_core(istate, oid, fd, xsize_t(st->st_size), type, path, flags); else - ret = index_stream(oid, fd, xsize_t(st->st_size), type, path, - flags); + ret = index_blob_stream(oid, fd, xsize_t(st->st_size), path, + flags); close(fd); return ret; } @@ -2680,7 +2823,8 @@ int for_each_loose_object(each_loose_object_fn cb, void *data, return 0; } -static int append_loose_object(const struct object_id *oid, const char *path, +static int append_loose_object(const struct object_id *oid, + const char *path UNUSED, void *data) { oidtree_insert(data, oid); @@ -2791,13 +2935,16 @@ int read_loose_object(const char *path, struct object_info *oi) { int ret = -1; + int fd; void *map = NULL; unsigned long mapsize; git_zstream stream; char hdr[MAX_HEADER_LEN]; unsigned long *size = oi->sizep; - map = map_loose_object_1(the_repository, path, NULL, &mapsize); + fd = git_open(path); + if (fd >= 0) + map = map_fd(fd, path, &mapsize); if (!map) { error_errno(_("unable to mmap %s"), path); goto out; |