From: Junio C Hamano Date: Wed, 30 May 2018 05:04:10 +0000 (+0900) Subject: Merge branch 'bc/object-id' X-Git-Tag: v2.18.0-rc0~17 X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/42c8ce1c49f862c98b35e4d89c88aa3d489d6608?hp=-c Merge branch 'bc/object-id' Conversion from uchar[20] to struct object_id continues. * bc/object-id: (42 commits) merge-one-file: compute empty blob object ID add--interactive: compute the empty tree value Update shell scripts to compute empty tree object ID sha1_file: only expose empty object constants through git_hash_algo dir: use the_hash_algo for empty blob object ID sequencer: use the_hash_algo for empty tree object ID cache-tree: use is_empty_tree_oid sha1_file: convert cached object code to struct object_id builtin/reset: convert use of EMPTY_TREE_SHA1_BIN builtin/receive-pack: convert one use of EMPTY_TREE_SHA1_HEX wt-status: convert two uses of EMPTY_TREE_SHA1_HEX submodule: convert several uses of EMPTY_TREE_SHA1_HEX sequencer: convert one use of EMPTY_TREE_SHA1_HEX merge: convert empty tree constant to the_hash_algo builtin/merge: switch tree functions to use object_id builtin/am: convert uses of EMPTY_TREE_SHA1_BIN to the_hash_algo sha1-file: add functions for hex empty tree and blob OIDs builtin/receive-pack: avoid hard-coded constants for push certs diff: specify abbreviation size in terms of the_hash_algo upload-pack: replace use of several hard-coded constants ... --- 42c8ce1c49f862c98b35e4d89c88aa3d489d6608 diff --combined builtin/am.c index 3dc2ef4259,f445fcb593..aa989e7390 --- a/builtin/am.c +++ b/builtin/am.c @@@ -6,7 -6,7 +6,7 @@@ #include "cache.h" #include "config.h" #include "builtin.h" -#include "exec_cmd.h" +#include "exec-cmd.h" #include "parse-options.h" #include "dir.h" #include "run-command.h" @@@ -403,11 -403,11 +403,11 @@@ static void am_load(struct am_state *st struct strbuf sb = STRBUF_INIT; if (read_state_file(&sb, state, "next", 1) < 0) - die("BUG: state file 'next' does not exist"); + BUG("state file 'next' does not exist"); state->cur = strtol(sb.buf, NULL, 10); if (read_state_file(&sb, state, "last", 1) < 0) - die("BUG: state file 'last' does not exist"); + BUG("state file 'last' does not exist"); state->last = strtol(sb.buf, NULL, 10); if (read_author_script(state) < 0) @@@ -986,7 -986,7 +986,7 @@@ static int split_mail(struct am_state * case PATCH_FORMAT_MBOXRD: return split_mail_mbox(state, paths, keep_cr, 1); default: - die("BUG: invalid patch_format"); + BUG("invalid patch_format"); } return -1; } @@@ -1041,7 -1041,7 +1041,7 @@@ static void am_setup(struct am_state *s str = "b"; break; default: - die("BUG: invalid value for state->keep"); + BUG("invalid value for state->keep"); } write_state_text(state, "keep", str); @@@ -1058,7 -1058,7 +1058,7 @@@ str = "t"; break; default: - die("BUG: invalid value for state->scissors"); + BUG("invalid value for state->scissors"); } write_state_text(state, "scissors", str); @@@ -1216,7 -1216,7 +1216,7 @@@ static int parse_mail(struct am_state * mi.keep_non_patch_brackets_in_subject = 1; break; default: - die("BUG: invalid value for state->keep"); + BUG("invalid value for state->keep"); } if (state->message_id) @@@ -1232,7 -1232,7 +1232,7 @@@ mi.use_scissors = 1; break; default: - die("BUG: invalid value for state->scissors"); + BUG("invalid value for state->scissors"); } mi.input = xfopen(mail, "r"); @@@ -1463,7 -1463,7 +1463,7 @@@ static int run_apply(const struct am_st int options = 0; if (init_apply_state(&apply_state, NULL)) - die("BUG: init_apply_state() failed"); + BUG("init_apply_state() failed"); argv_array_push(&apply_opts, "apply"); argv_array_pushv(&apply_opts, state->git_apply_opts.argv); @@@ -1489,7 -1489,7 +1489,7 @@@ apply_state.apply_verbosity = verbosity_silent; if (check_apply_state(&apply_state, force_apply)) - die("BUG: check_apply_state() failed"); + BUG("check_apply_state() failed"); argv_array_push(&apply_paths, am_path(state, "patch")); @@@ -1542,7 -1542,7 +1542,7 @@@ static int fall_back_threeway(const str char *their_tree_name; if (get_oid("HEAD", &our_tree) < 0) - hashcpy(our_tree.hash, EMPTY_TREE_SHA1_BIN); + oidcpy(&our_tree, the_hash_algo->empty_tree); if (build_fake_ancestor(state, index_path)) return error("could not build fake ancestor"); @@@ -2042,7 -2042,7 +2042,7 @@@ static void am_skip(struct am_state *st am_rerere_clear(); if (get_oid("HEAD", &head)) - hashcpy(head.hash, EMPTY_TREE_SHA1_BIN); + oidcpy(&head, the_hash_algo->empty_tree); if (clean_index(&head, &head)) die(_("failed to clean index")); @@@ -2105,11 -2105,11 +2105,11 @@@ static void am_abort(struct am_state *s curr_branch = resolve_refdup("HEAD", 0, &curr_head, NULL); has_curr_head = curr_branch && !is_null_oid(&curr_head); if (!has_curr_head) - hashcpy(curr_head.hash, EMPTY_TREE_SHA1_BIN); + oidcpy(&curr_head, the_hash_algo->empty_tree); has_orig_head = !get_oid("ORIG_HEAD", &orig_head); if (!has_orig_head) - hashcpy(orig_head.hash, EMPTY_TREE_SHA1_BIN); + oidcpy(&orig_head, the_hash_algo->empty_tree); clean_index(&curr_head, &orig_head); @@@ -2407,7 -2407,7 +2407,7 @@@ int cmd_am(int argc, const char **argv ret = show_patch(&state); break; default: - die("BUG: invalid resume value"); + BUG("invalid resume value"); } am_state_release(&state); diff --combined builtin/fsck.c index 916109ac1c,3eb82ac44f..3ad4f160f9 --- a/builtin/fsck.c +++ b/builtin/fsck.c @@@ -67,8 -67,7 +67,8 @@@ static const char *printable_type(struc const char *ret; if (obj->type == OBJ_NONE) { - enum object_type type = oid_object_info(&obj->oid, NULL); + enum object_type type = oid_object_info(the_repository, + &obj->oid, NULL); if (type > 0) object_as_type(obj, type, 0); } @@@ -228,7 -227,7 +228,7 @@@ static void check_reachable_object(stru if (!(obj->flags & HAS_OBJ)) { if (is_promisor_object(&obj->oid)) return; - if (has_sha1_pack(obj->oid.hash)) + if (has_object_pack(&obj->oid)) return; /* it is in pack - forget about it */ printf("missing %s %s\n", printable_type(obj), describe_object(obj)); @@@ -340,7 -339,7 +340,7 @@@ static void check_connectivity(void } } -static int fsck_obj(struct object *obj) +static int fsck_obj(struct object *obj, void *buffer, unsigned long size) { int err; @@@ -354,7 -353,7 +354,7 @@@ if (fsck_walk(obj, NULL, &fsck_obj_options)) objerror(obj, "broken links"); - err = fsck_object(obj, NULL, 0, &fsck_obj_options); + err = fsck_object(obj, buffer, size, &fsck_obj_options); if (err) goto out; @@@ -399,7 -398,7 +399,7 @@@ static int fsck_obj_buffer(const struc } obj->flags &= ~(REACHABLE | SEEN); obj->flags |= HAS_OBJ; - return fsck_obj(obj); + return fsck_obj(obj, buffer, size); } static int default_refs; @@@ -507,42 -506,44 +507,42 @@@ static void get_default_heads(void } } -static struct object *parse_loose_object(const struct object_id *oid, - const char *path) +static int fsck_loose(const struct object_id *oid, const char *path, void *data) { struct object *obj; - void *contents; enum object_type type; unsigned long size; + void *contents; int eaten; - if (read_loose_object(path, oid, &type, &size, &contents) < 0) - return NULL; + if (read_loose_object(path, oid, &type, &size, &contents) < 0) { + errors_found |= ERROR_OBJECT; + error("%s: object corrupt or missing: %s", + oid_to_hex(oid), path); + return 0; /* keep checking other objects */ + } if (!contents && type != OBJ_BLOB) - die("BUG: read_loose_object streamed a non-blob"); + BUG("read_loose_object streamed a non-blob"); obj = parse_object_buffer(oid, type, size, contents, &eaten); - - if (!eaten) - free(contents); - return obj; -} - -static int fsck_loose(const struct object_id *oid, const char *path, void *data) -{ - struct object *obj = parse_loose_object(oid, path); - if (!obj) { errors_found |= ERROR_OBJECT; - error("%s: object corrupt or missing: %s", + error("%s: object could not be parsed: %s", oid_to_hex(oid), path); + if (!eaten) + free(contents); return 0; /* keep checking other objects */ } obj->flags &= ~(REACHABLE | SEEN); obj->flags |= HAS_OBJ; - if (fsck_obj(obj)) + if (fsck_obj(obj, contents, size)) errors_found |= ERROR_OBJECT; - return 0; + + if (!eaten) + free(contents); + return 0; /* keep checking other objects, even if we saw an error */ } static int fsck_cruft(const char *basename, const char *path, void *data) @@@ -754,9 -755,6 +754,9 @@@ int cmd_fsck(int argc, const char **arg } stop_progress(&progress); } + + if (fsck_finish(&fsck_obj_options)) + errors_found |= ERROR_OBJECT; } for (i = 0; i < argc; i++) { diff --combined builtin/index-pack.c index b3a5abcf2b,c1f94a7da6..4ab31ed388 --- a/builtin/index-pack.c +++ b/builtin/index-pack.c @@@ -9,7 -9,7 +9,7 @@@ #include "tree.h" #include "progress.h" #include "fsck.h" -#include "exec_cmd.h" +#include "exec-cmd.h" #include "streaming.h" #include "thread-utils.h" #include "packfile.h" @@@ -223,7 -223,7 +223,7 @@@ static unsigned check_object(struct obj if (!(obj->flags & FLAG_CHECKED)) { unsigned long size; - int type = oid_object_info(&obj->oid, &size); + int type = oid_object_info(the_repository, &obj->oid, &size); if (type <= 0) die(_("did not receive expected object %s"), oid_to_hex(&obj->oid)); @@@ -812,7 -812,7 +812,7 @@@ static void sha1_object(const void *dat enum object_type has_type; unsigned long has_size; read_lock(); - has_type = oid_object_info(oid, &has_size); + has_type = oid_object_info(the_repository, oid, &has_size); if (has_type < 0) die(_("cannot read existing object info %s"), oid_to_hex(oid)); if (has_type != type || has_size != size) @@@ -837,9 -837,6 +837,9 @@@ blob->object.flags |= FLAG_CHECKED; else die(_("invalid blob object %s"), oid_to_hex(oid)); + if (do_fsck_object && + fsck_object(&blob->object, (void *)data, size, &fsck_options)) + die(_("fsck error in packed object")); } else { struct object *obj; int eaten; @@@ -857,7 -854,7 +857,7 @@@ die(_("invalid %s"), type_name(type)); if (do_fsck_object && fsck_object(obj, buf, size, &fsck_options)) - die(_("Error in object")); + die(_("fsck error in packed object")); if (strict && fsck_walk(obj, NULL, &fsck_options)) die(_("Not all child objects of %s are reachable"), oid_to_hex(&obj->oid)); @@@ -869,7 -866,7 +869,7 @@@ if (obj->type == OBJ_COMMIT) { struct commit *commit = (struct commit *) obj; if (detach_commit_buffer(commit, NULL) != data) - die("BUG: parse_object_buffer transmogrified our buffer"); + BUG("parse_object_buffer transmogrified our buffer"); } obj->flags |= FLAG_CHECKED; } @@@ -1018,7 -1015,7 +1018,7 @@@ static struct base_data *find_unresolve if (!compare_and_swap_type(&child->real_type, OBJ_REF_DELTA, base->obj->real_type)) - die("BUG: child->real_type != OBJ_REF_DELTA"); + BUG("child->real_type != OBJ_REF_DELTA"); resolve_delta(child, base, result); if (base->ref_first == base->ref_last && base->ofs_last == -1) @@@ -1274,7 -1271,7 +1274,7 @@@ static void conclude_pack(int fix_thin_ nr_objects - nr_objects_initial); stop_progress_msg(&progress, msg.buf); strbuf_release(&msg); - hashclose(f, tail_hash, 0); + finalize_hashfile(f, tail_hash, 0); hashcpy(read_hash, pack_hash); fixup_pack_header_footer(output_fd, pack_hash, curr_pack, nr_objects, @@@ -1482,9 -1479,6 +1482,9 @@@ static void final(const char *final_pac } else chmod(final_index_name, 0444); + if (do_fsck_object) + add_packed_git(final_index_name, strlen(final_index_name), 0); + if (!from_stdin) { printf("%s\n", sha1_to_hex(hash)); } else { @@@ -1549,12 -1543,13 +1549,13 @@@ static void read_v2_anomalous_offsets(s { const uint32_t *idx1, *idx2; uint32_t i; + const uint32_t hashwords = the_hash_algo->rawsz / sizeof(uint32_t); /* The address of the 4-byte offset table */ idx1 = (((const uint32_t *)p->index_data) + 2 /* 8-byte header */ + 256 /* fan out */ - + 5 * p->num_objects /* 20-byte SHA-1 table */ + + hashwords * p->num_objects /* object ID table */ + p->num_objects /* CRC32 table */ ); @@@ -1599,7 -1594,7 +1600,7 @@@ static void read_idx_option(struct pack /* * Get rid of the idx file as we do not need it anymore. * NEEDSWORK: extract this bit from free_pack_by_name() in - * sha1_file.c, perhaps? It shouldn't matter very much as we + * sha1-file.c, perhaps? It shouldn't matter very much as we * know we haven't installed this pack (hence we never have * read anything from it). */ @@@ -1826,10 -1821,6 +1827,10 @@@ int cmd_index_pack(int argc, const cha pack_hash); else close(input_fd); + + if (do_fsck_object && fsck_finish(&fsck_options)) + die(_("fsck error in pack objects")); + free(objects); strbuf_release(&index_name_buf); if (pack_name == NULL) diff --combined builtin/merge.c index de62b2c5c6,7084bcfdea..fba0a7fc79 --- a/builtin/merge.c +++ b/builtin/merge.c @@@ -280,7 -280,7 +280,7 @@@ out return rc; } - static void read_empty(unsigned const char *sha1, int verbose) + static void read_empty(const struct object_id *oid, int verbose) { int i = 0; const char *args[7]; @@@ -290,15 -290,15 +290,15 @@@ args[i++] = "-v"; args[i++] = "-m"; args[i++] = "-u"; - args[i++] = EMPTY_TREE_SHA1_HEX; - args[i++] = sha1_to_hex(sha1); + args[i++] = empty_tree_oid_hex(); + args[i++] = oid_to_hex(oid); args[i] = NULL; if (run_command_v_opt(args, RUN_GIT_CMD)) die(_("read-tree failed")); } - static void reset_hard(unsigned const char *sha1, int verbose) + static void reset_hard(const struct object_id *oid, int verbose) { int i = 0; const char *args[6]; @@@ -308,7 -308,7 +308,7 @@@ args[i++] = "-v"; args[i++] = "--reset"; args[i++] = "-u"; - args[i++] = sha1_to_hex(sha1); + args[i++] = oid_to_hex(oid); args[i] = NULL; if (run_command_v_opt(args, RUN_GIT_CMD)) @@@ -324,7 -324,7 +324,7 @@@ static void restore_state(const struct if (is_null_oid(stash)) return; - reset_hard(head->hash, 1); + reset_hard(head, 1); args[2] = oid_to_hex(stash); @@@ -647,7 -647,7 +647,7 @@@ static int try_merge_strategy(const cha struct commit_list *remoteheads, struct commit *head) { - static struct lock_file lock; + struct lock_file lock = LOCK_INIT; const char *head_arg = "HEAD"; hold_locked_index(&lock, LOCK_DIE_ON_ERROR); @@@ -805,7 -805,7 +805,7 @@@ static int merge_trivial(struct commit { struct object_id result_tree, result_commit; struct commit_list *parents, **pptr = &parents; - static struct lock_file lock; + struct lock_file lock = LOCK_INIT; hold_locked_index(&lock, LOCK_DIE_ON_ERROR); refresh_cache(REFRESH_QUIET); @@@ -1297,7 -1297,7 +1297,7 @@@ int cmd_merge(int argc, const char **ar if (remoteheads->next) die(_("Can merge only exactly one commit into empty head")); remote_head_oid = &remoteheads->item->object.oid; - read_empty(remote_head_oid->hash, 0); + read_empty(remote_head_oid, 0); update_ref("initial pull", "HEAD", remote_head_oid, NULL, 0, UPDATE_REFS_DIE_ON_ERR); goto done; diff --combined builtin/pack-objects.c index 53a0fb6ef2,f014523613..e78f3f5220 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@@ -30,19 -30,6 +30,19 @@@ #include "list.h" #include "packfile.h" #include "object-store.h" +#include "dir.h" + +#define IN_PACK(obj) oe_in_pack(&to_pack, obj) +#define SIZE(obj) oe_size(&to_pack, obj) +#define SET_SIZE(obj,size) oe_set_size(&to_pack, obj, size) +#define DELTA_SIZE(obj) oe_delta_size(&to_pack, obj) +#define DELTA(obj) oe_delta(&to_pack, obj) +#define DELTA_CHILD(obj) oe_delta_child(&to_pack, obj) +#define DELTA_SIBLING(obj) oe_delta_sibling(&to_pack, obj) +#define SET_DELTA(obj, val) oe_set_delta(&to_pack, obj, val) +#define SET_DELTA_SIZE(obj, val) oe_set_delta_size(&to_pack, obj, val) +#define SET_DELTA_CHILD(obj, val) oe_set_delta_child(&to_pack, obj, val) +#define SET_DELTA_SIBLING(obj, val) oe_set_delta_sibling(&to_pack, obj, val) static const char *pack_usage[] = { N_("git pack-objects --stdout [...] [< | < ]"), @@@ -58,7 -45,7 +58,7 @@@ static struct packing_data to_pack; static struct pack_idx_entry **written_list; -static uint32_t nr_result, nr_written; +static uint32_t nr_result, nr_written, nr_seen; static int non_empty; static int reuse_delta = 1, reuse_object = 1; @@@ -68,8 -55,7 +68,8 @@@ static int pack_loose_unreachable static int local; static int have_non_local_packs; static int incremental; -static int ignore_packed_keep; +static int ignore_packed_keep_on_disk; +static int ignore_packed_keep_in_core; static int allow_ofs_delta; static struct pack_idx_option pack_idx_opts; static const char *base_name; @@@ -94,7 -80,7 +94,7 @@@ static uint16_t write_bitmap_options static int exclude_promisor_objects; static unsigned long delta_cache_size = 0; -static unsigned long max_delta_cache_size = 256 * 1024 * 1024; +static unsigned long max_delta_cache_size = DEFAULT_DELTA_CACHE_SIZE; static unsigned long cache_max_small_delta_size = 1000; static unsigned long window_memory_limit = 0; @@@ -141,14 -127,13 +141,14 @@@ static void *get_delta(struct object_en buf = read_object_file(&entry->idx.oid, &type, &size); if (!buf) die("unable to read %s", oid_to_hex(&entry->idx.oid)); - base_buf = read_object_file(&entry->delta->idx.oid, &type, &base_size); + base_buf = read_object_file(&DELTA(entry)->idx.oid, &type, + &base_size); if (!base_buf) die("unable to read %s", - oid_to_hex(&entry->delta->idx.oid)); + oid_to_hex(&DELTA(entry)->idx.oid)); delta_buf = diff_delta(base_buf, base_size, buf, size, &delta_size, 0); - if (!delta_buf || delta_size != entry->delta_size) + if (!delta_buf || delta_size != DELTA_SIZE(entry)) die("delta size changed"); free(buf); free(base_buf); @@@ -279,10 -264,11 +279,11 @@@ static unsigned long write_no_reuse_obj enum object_type type; void *buf; struct git_istream *st = NULL; + const unsigned hashsz = the_hash_algo->rawsz; if (!usable_delta) { - if (entry->type == OBJ_BLOB && - entry->size > big_file_threshold && + if (oe_type(entry) == OBJ_BLOB && + oe_size_greater_than(&to_pack, entry, big_file_threshold) && (st = open_istream(&entry->idx.oid, &type, &size, NULL)) != NULL) buf = NULL; else { @@@ -298,15 -284,15 +299,15 @@@ FREE_AND_NULL(entry->delta_data); entry->z_delta_size = 0; } else if (entry->delta_data) { - size = entry->delta_size; + size = DELTA_SIZE(entry); buf = entry->delta_data; entry->delta_data = NULL; - type = (allow_ofs_delta && entry->delta->idx.offset) ? + type = (allow_ofs_delta && DELTA(entry)->idx.offset) ? OBJ_OFS_DELTA : OBJ_REF_DELTA; } else { buf = get_delta(entry); - size = entry->delta_size; - type = (allow_ofs_delta && entry->delta->idx.offset) ? + size = DELTA_SIZE(entry); + type = (allow_ofs_delta && DELTA(entry)->idx.offset) ? OBJ_OFS_DELTA : OBJ_REF_DELTA; } @@@ -330,12 -316,12 +331,12 @@@ * encoding of the relative offset for the delta * base from this object's position in the pack. */ - off_t ofs = entry->idx.offset - entry->delta->idx.offset; + off_t ofs = entry->idx.offset - DELTA(entry)->idx.offset; unsigned pos = sizeof(dheader) - 1; dheader[pos] = ofs & 127; while (ofs >>= 7) dheader[--pos] = 128 | (--ofs & 127); - if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) { + if (limit && hdrlen + sizeof(dheader) - pos + datalen + hashsz >= limit) { if (st) close_istream(st); free(buf); @@@ -347,19 -333,19 +348,19 @@@ } else if (type == OBJ_REF_DELTA) { /* * Deltas with a base reference contain - * an additional 20 bytes for the base sha1. + * additional bytes for the base object ID. */ - if (limit && hdrlen + 20 + datalen + 20 >= limit) { + if (limit && hdrlen + hashsz + datalen + hashsz >= limit) { if (st) close_istream(st); free(buf); return 0; } hashwrite(f, header, hdrlen); - hashwrite(f, DELTA(entry)->idx.oid.hash, 20); - hdrlen += 20; - hashwrite(f, entry->delta->idx.oid.hash, hashsz); ++ hashwrite(f, DELTA(entry)->idx.oid.hash, hashsz); + hdrlen += hashsz; } else { - if (limit && hdrlen + datalen + 20 >= limit) { + if (limit && hdrlen + datalen + hashsz >= limit) { if (st) close_istream(st); free(buf); @@@ -382,22 -368,22 +383,23 @@@ static off_t write_reuse_object(struct hashfile *f, struct object_entry *entry, unsigned long limit, int usable_delta) { - struct packed_git *p = entry->in_pack; + struct packed_git *p = IN_PACK(entry); struct pack_window *w_curs = NULL; struct revindex_entry *revidx; off_t offset; - enum object_type type = entry->type; + enum object_type type = oe_type(entry); off_t datalen; unsigned char header[MAX_PACK_OBJECT_HEADER], dheader[MAX_PACK_OBJECT_HEADER]; unsigned hdrlen; + const unsigned hashsz = the_hash_algo->rawsz; + unsigned long entry_size = SIZE(entry); - if (entry->delta) - type = (allow_ofs_delta && entry->delta->idx.offset) ? + if (DELTA(entry)) + type = (allow_ofs_delta && DELTA(entry)->idx.offset) ? OBJ_OFS_DELTA : OBJ_REF_DELTA; hdrlen = encode_in_pack_object_header(header, sizeof(header), - type, entry->size); + type, entry_size); offset = entry->in_pack_offset; revidx = find_pack_revindex(p, offset); @@@ -414,7 -400,7 +416,7 @@@ datalen -= entry->in_pack_header_size; if (!pack_to_stdout && p->index_version == 1 && - check_pack_inflate(p, &w_curs, offset, datalen, entry->size)) { + check_pack_inflate(p, &w_curs, offset, datalen, entry_size)) { error("corrupt packed object for %s", oid_to_hex(&entry->idx.oid)); unuse_pack(&w_curs); @@@ -422,12 -408,12 +424,12 @@@ } if (type == OBJ_OFS_DELTA) { - off_t ofs = entry->idx.offset - entry->delta->idx.offset; + off_t ofs = entry->idx.offset - DELTA(entry)->idx.offset; unsigned pos = sizeof(dheader) - 1; dheader[pos] = ofs & 127; while (ofs >>= 7) dheader[--pos] = 128 | (--ofs & 127); - if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) { + if (limit && hdrlen + sizeof(dheader) - pos + datalen + hashsz >= limit) { unuse_pack(&w_curs); return 0; } @@@ -436,16 -422,16 +438,16 @@@ hdrlen += sizeof(dheader) - pos; reused_delta++; } else if (type == OBJ_REF_DELTA) { - if (limit && hdrlen + 20 + datalen + 20 >= limit) { + if (limit && hdrlen + hashsz + datalen + hashsz >= limit) { unuse_pack(&w_curs); return 0; } hashwrite(f, header, hdrlen); - hashwrite(f, DELTA(entry)->idx.oid.hash, 20); - hdrlen += 20; - hashwrite(f, entry->delta->idx.oid.hash, hashsz); ++ hashwrite(f, DELTA(entry)->idx.oid.hash, hashsz); + hdrlen += hashsz; reused_delta++; } else { - if (limit && hdrlen + datalen + 20 >= limit) { + if (limit && hdrlen + datalen + hashsz >= limit) { unuse_pack(&w_curs); return 0; } @@@ -481,29 -467,28 +483,29 @@@ static off_t write_object(struct hashfi else limit = pack_size_limit - write_offset; - if (!entry->delta) + if (!DELTA(entry)) usable_delta = 0; /* no delta */ else if (!pack_size_limit) usable_delta = 1; /* unlimited packfile */ - else if (entry->delta->idx.offset == (off_t)-1) + else if (DELTA(entry)->idx.offset == (off_t)-1) usable_delta = 0; /* base was written to another pack */ - else if (entry->delta->idx.offset) + else if (DELTA(entry)->idx.offset) usable_delta = 1; /* base already exists in this pack */ else usable_delta = 0; /* base could end up in another pack */ if (!reuse_object) to_reuse = 0; /* explicit */ - else if (!entry->in_pack) + else if (!IN_PACK(entry)) to_reuse = 0; /* can't reuse what we don't have */ - else if (entry->type == OBJ_REF_DELTA || entry->type == OBJ_OFS_DELTA) + else if (oe_type(entry) == OBJ_REF_DELTA || + oe_type(entry) == OBJ_OFS_DELTA) /* check_object() decided it for us ... */ to_reuse = usable_delta; /* ... but pack split may override that */ - else if (entry->type != entry->in_pack_type) + else if (oe_type(entry) != entry->in_pack_type) to_reuse = 0; /* pack has delta which is unusable */ - else if (entry->delta) + else if (DELTA(entry)) to_reuse = 0; /* we want to pack afresh */ else to_reuse = 1; /* we have it in-pack undeltified, @@@ -555,12 -540,12 +557,12 @@@ static enum write_one_status write_one( } /* if we are deltified, write out base object first. */ - if (e->delta) { + if (DELTA(e)) { e->idx.offset = 1; /* now recurse */ - switch (write_one(f, e->delta, offset)) { + switch (write_one(f, DELTA(e), offset)) { case WRITE_ONE_RECURSIVE: /* we cannot depend on this one */ - e->delta = NULL; + SET_DELTA(e, NULL); break; default: break; @@@ -622,34 -607,34 +624,34 @@@ static void add_descendants_to_write_or /* add this node... */ add_to_write_order(wo, endp, e); /* all its siblings... */ - for (s = e->delta_sibling; s; s = s->delta_sibling) { + for (s = DELTA_SIBLING(e); s; s = DELTA_SIBLING(s)) { add_to_write_order(wo, endp, s); } } /* drop down a level to add left subtree nodes if possible */ - if (e->delta_child) { + if (DELTA_CHILD(e)) { add_to_order = 1; - e = e->delta_child; + e = DELTA_CHILD(e); } else { add_to_order = 0; /* our sibling might have some children, it is next */ - if (e->delta_sibling) { - e = e->delta_sibling; + if (DELTA_SIBLING(e)) { + e = DELTA_SIBLING(e); continue; } /* go back to our parent node */ - e = e->delta; - while (e && !e->delta_sibling) { + e = DELTA(e); + while (e && !DELTA_SIBLING(e)) { /* we're on the right side of a subtree, keep * going up until we can go right again */ - e = e->delta; + e = DELTA(e); } if (!e) { /* done- we hit our original root node */ return; } /* pass it off to sibling at this level */ - e = e->delta_sibling; + e = DELTA_SIBLING(e); } }; } @@@ -660,7 -645,7 +662,7 @@@ static void add_family_to_write_order(s { struct object_entry *root; - for (root = e; root->delta; root = root->delta) + for (root = e; DELTA(root); root = DELTA(root)) ; /* nothing */ add_descendants_to_write_order(wo, endp, root); } @@@ -675,8 -660,8 +677,8 @@@ static struct object_entry **compute_wr for (i = 0; i < to_pack.nr_objects; i++) { objects[i].tagged = 0; objects[i].filled = 0; - objects[i].delta_child = NULL; - objects[i].delta_sibling = NULL; + SET_DELTA_CHILD(&objects[i], NULL); + SET_DELTA_SIBLING(&objects[i], NULL); } /* @@@ -686,11 -671,11 +688,11 @@@ */ for (i = to_pack.nr_objects; i > 0;) { struct object_entry *e = &objects[--i]; - if (!e->delta) + if (!DELTA(e)) continue; /* Mark me as the first child */ - e->delta_sibling = e->delta->delta_child; - e->delta->delta_child = e; + e->delta_sibling_idx = DELTA(e)->delta_child_idx; + SET_DELTA_CHILD(DELTA(e), e); } /* @@@ -722,8 -707,8 +724,8 @@@ * And then all remaining commits and tags. */ for (i = last_untagged; i < to_pack.nr_objects; i++) { - if (objects[i].type != OBJ_COMMIT && - objects[i].type != OBJ_TAG) + if (oe_type(&objects[i]) != OBJ_COMMIT && + oe_type(&objects[i]) != OBJ_TAG) continue; add_to_write_order(wo, &wo_end, &objects[i]); } @@@ -732,7 -717,7 +734,7 @@@ * And then all the trees. */ for (i = last_untagged; i < to_pack.nr_objects; i++) { - if (objects[i].type != OBJ_TREE) + if (oe_type(&objects[i]) != OBJ_TREE) continue; add_to_write_order(wo, &wo_end, &objects[i]); } @@@ -769,7 -754,7 +771,7 @@@ static off_t write_reused_pack(struct h die_errno("unable to seek in reused packfile"); if (reuse_packfile_offset < 0) - reuse_packfile_offset = reuse_packfile->pack_size - 20; + reuse_packfile_offset = reuse_packfile->pack_size - the_hash_algo->rawsz; total = to_write = reuse_packfile_offset - sizeof(struct pack_header); @@@ -854,11 -839,11 +856,11 @@@ static void write_pack_file(void * If so, rewrite it like in fast-import */ if (pack_to_stdout) { - hashclose(f, oid.hash, CSUM_CLOSE); + finalize_hashfile(f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_CLOSE); } else if (nr_written == nr_remaining) { - hashclose(f, oid.hash, CSUM_FSYNC); + finalize_hashfile(f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_FSYNC | CSUM_CLOSE); } else { - int fd = hashclose(f, oid.hash, 0); + int fd = finalize_hashfile(f, oid.hash, 0); fixup_pack_header_footer(fd, oid.hash, pack_tmp_name, nr_written, oid.hash, offset); close(fd); @@@ -895,8 -880,7 +897,8 @@@ if (write_bitmap_index) { bitmap_writer_set_checksum(oid.hash); - bitmap_writer_build_type_index(written_list, nr_written); + bitmap_writer_build_type_index( + &to_pack, written_list, nr_written); } finish_tmp_packfile(&tmpname, pack_tmp_name, @@@ -1000,16 -984,13 +1002,16 @@@ static int want_found_object(int exclud * Otherwise, we signal "-1" at the end to tell the caller that we do * not know either way, and it needs to check more packs. */ - if (!ignore_packed_keep && + if (!ignore_packed_keep_on_disk && + !ignore_packed_keep_in_core && (!local || !have_non_local_packs)) return 1; if (local && !p->pack_local) return 0; - if (ignore_packed_keep && p->pack_local && p->pack_keep) + if (p->pack_local && + ((ignore_packed_keep_on_disk && p->pack_keep) || + (ignore_packed_keep_in_core && p->pack_keep_in_core))) return 0; /* we don't know yet; keep looking for more packs */ @@@ -1033,7 -1014,7 +1035,7 @@@ static int want_object_in_pack(const st int want; struct list_head *pos; - if (!exclude && local && has_loose_object_nonlocal(oid->hash)) + if (!exclude && local && has_loose_object_nonlocal(oid)) return 0; /* @@@ -1087,13 -1068,14 +1089,13 @@@ static void create_object_entry(const s entry = packlist_alloc(&to_pack, oid->hash, index_pos); entry->hash = hash; - if (type) - entry->type = type; + oe_set_type(entry, type); if (exclude) entry->preferred_base = 1; else nr_result++; if (found_pack) { - entry->in_pack = found_pack; + oe_set_in_pack(&to_pack, entry, found_pack); entry->in_pack_offset = found_offset; } @@@ -1111,8 -1093,6 +1113,8 @@@ static int add_object_entry(const struc off_t found_offset = 0; uint32_t index_pos; + display_progress(progress_state, ++nr_seen); + if (have_duplicate_entry(oid, exclude, &index_pos)) return 0; @@@ -1128,6 -1108,8 +1130,6 @@@ create_object_entry(oid, type, pack_name_hash(name), exclude, name && no_try_delta(name), index_pos, found_pack, found_offset); - - display_progress(progress_state, nr_result); return 1; } @@@ -1138,8 -1120,6 +1140,8 @@@ static int add_object_entry_from_bitmap { uint32_t index_pos; + display_progress(progress_state, ++nr_seen); + if (have_duplicate_entry(oid, 0, &index_pos)) return 0; @@@ -1147,6 -1127,8 +1149,6 @@@ return 0; create_object_entry(oid, type, name_hash, 0, 0, index_pos, pack, offset); - - display_progress(progress_state, nr_result); return 1; } @@@ -1418,10 -1400,8 +1420,10 @@@ static void cleanup_preferred_base(void static void check_object(struct object_entry *entry) { - if (entry->in_pack) { - struct packed_git *p = entry->in_pack; + unsigned long canonical_size; + + if (IN_PACK(entry)) { + struct packed_git *p = IN_PACK(entry); struct pack_window *w_curs = NULL; const unsigned char *base_ref = NULL; struct object_entry *base_entry; @@@ -1429,8 -1409,6 +1431,8 @@@ unsigned long avail; off_t ofs; unsigned char *buf, c; + enum object_type type; + unsigned long in_pack_size; buf = use_pack(p, &w_curs, entry->in_pack_offset, &avail); @@@ -1439,15 -1417,11 +1441,15 @@@ * since non-delta representations could still be reused. */ used = unpack_object_header_buffer(buf, avail, - &entry->in_pack_type, - &entry->size); + &type, + &in_pack_size); if (used == 0) goto give_up; + if (type < 0) + BUG("invalid type %d", type); + entry->in_pack_type = type; + /* * Determine if this is a delta and if so whether we can * reuse it or not. Otherwise let's find out as cheaply as @@@ -1456,10 -1430,9 +1458,10 @@@ switch (entry->in_pack_type) { default: /* Not a delta hence we've already got all we need. */ - entry->type = entry->in_pack_type; + oe_set_type(entry, entry->in_pack_type); + SET_SIZE(entry, in_pack_size); entry->in_pack_header_size = used; - if (entry->type < OBJ_COMMIT || entry->type > OBJ_BLOB) + if (oe_type(entry) < OBJ_COMMIT || oe_type(entry) > OBJ_BLOB) goto give_up; unuse_pack(&w_curs); return; @@@ -1467,7 -1440,7 +1469,7 @@@ if (reuse_delta && !entry->preferred_base) base_ref = use_pack(p, &w_curs, entry->in_pack_offset + used, NULL); - entry->in_pack_header_size = used + 20; + entry->in_pack_header_size = used + the_hash_algo->rawsz; break; case OBJ_OFS_DELTA: buf = use_pack(p, &w_curs, @@@ -1513,29 -1486,25 +1515,29 @@@ * deltify other objects against, in order to avoid * circular deltas. */ - entry->type = entry->in_pack_type; - entry->delta = base_entry; - entry->delta_size = entry->size; - entry->delta_sibling = base_entry->delta_child; - base_entry->delta_child = entry; + oe_set_type(entry, entry->in_pack_type); + SET_SIZE(entry, in_pack_size); /* delta size */ + SET_DELTA(entry, base_entry); + SET_DELTA_SIZE(entry, in_pack_size); + entry->delta_sibling_idx = base_entry->delta_child_idx; + SET_DELTA_CHILD(base_entry, entry); unuse_pack(&w_curs); return; } - if (entry->type) { + if (oe_type(entry)) { + off_t delta_pos; + /* * This must be a delta and we already know what the * final object type is. Let's extract the actual * object size from the delta header. */ - entry->size = get_size_from_delta(p, &w_curs, - entry->in_pack_offset + entry->in_pack_header_size); - if (entry->size == 0) + delta_pos = entry->in_pack_offset + entry->in_pack_header_size; + canonical_size = get_size_from_delta(p, &w_curs, delta_pos); + if (canonical_size == 0) goto give_up; + SET_SIZE(entry, canonical_size); unuse_pack(&w_curs); return; } @@@ -1549,34 -1518,27 +1551,34 @@@ unuse_pack(&w_curs); } - entry->type = oid_object_info(&entry->idx.oid, &entry->size); - /* - * The error condition is checked in prepare_pack(). This is - * to permit a missing preferred base object to be ignored - * as a preferred base. Doing so can result in a larger - * pack file, but the transfer will still take place. - */ + oe_set_type(entry, + oid_object_info(the_repository, &entry->idx.oid, &canonical_size)); + if (entry->type_valid) { + SET_SIZE(entry, canonical_size); + } else { + /* + * Bad object type is checked in prepare_pack(). This is + * to permit a missing preferred base object to be ignored + * as a preferred base. Doing so can result in a larger + * pack file, but the transfer will still take place. + */ + } } static int pack_offset_sort(const void *_a, const void *_b) { const struct object_entry *a = *(struct object_entry **)_a; const struct object_entry *b = *(struct object_entry **)_b; + const struct packed_git *a_in_pack = IN_PACK(a); + const struct packed_git *b_in_pack = IN_PACK(b); /* avoid filesystem trashing with loose objects */ - if (!a->in_pack && !b->in_pack) + if (!a_in_pack && !b_in_pack) return oidcmp(&a->idx.oid, &b->idx.oid); - if (a->in_pack < b->in_pack) + if (a_in_pack < b_in_pack) return -1; - if (a->in_pack > b->in_pack) + if (a_in_pack > b_in_pack) return 1; return a->in_pack_offset < b->in_pack_offset ? -1 : (a->in_pack_offset > b->in_pack_offset); @@@ -1597,37 -1559,29 +1599,37 @@@ */ static void drop_reused_delta(struct object_entry *entry) { - struct object_entry **p = &entry->delta->delta_child; + unsigned *idx = &to_pack.objects[entry->delta_idx - 1].delta_child_idx; struct object_info oi = OBJECT_INFO_INIT; + enum object_type type; + unsigned long size; + + while (*idx) { + struct object_entry *oe = &to_pack.objects[*idx - 1]; - while (*p) { - if (*p == entry) - *p = (*p)->delta_sibling; + if (oe == entry) + *idx = oe->delta_sibling_idx; else - p = &(*p)->delta_sibling; + idx = &oe->delta_sibling_idx; } - entry->delta = NULL; + SET_DELTA(entry, NULL); entry->depth = 0; - oi.sizep = &entry->size; - oi.typep = &entry->type; - if (packed_object_info(entry->in_pack, entry->in_pack_offset, &oi) < 0) { + oi.sizep = &size; + oi.typep = &type; + if (packed_object_info(the_repository, IN_PACK(entry), entry->in_pack_offset, &oi) < 0) { /* * We failed to get the info from this pack for some reason; * fall back to sha1_object_info, which may find another copy. - * And if that fails, the error will be recorded in entry->type + * And if that fails, the error will be recorded in oe_type(entry) * and dealt with in prepare_pack(). */ - entry->type = oid_object_info(&entry->idx.oid, &entry->size); + oe_set_type(entry, + oid_object_info(the_repository, &entry->idx.oid, &size)); + } else { + oe_set_type(entry, type); } + SET_SIZE(entry, size); } /* @@@ -1651,7 -1605,7 +1653,7 @@@ static void break_delta_chains(struct o for (cur = entry, total_depth = 0; cur; - cur = cur->delta, total_depth++) { + cur = DELTA(cur), total_depth++) { if (cur->dfs_state == DFS_DONE) { /* * We've already seen this object and know it isn't @@@ -1668,7 -1622,7 +1670,7 @@@ * is a bug. */ if (cur->dfs_state != DFS_NONE) - die("BUG: confusing delta dfs state in first pass: %d", + BUG("confusing delta dfs state in first pass: %d", cur->dfs_state); /* @@@ -1676,7 -1630,7 +1678,7 @@@ * it's not a delta, we're done traversing, but we'll mark it * done to save time on future traversals. */ - if (!cur->delta) { + if (!DELTA(cur)) { cur->dfs_state = DFS_DONE; break; } @@@ -1699,7 -1653,7 +1701,7 @@@ * We keep all commits in the chain that we examined. */ cur->dfs_state = DFS_ACTIVE; - if (cur->delta->dfs_state == DFS_ACTIVE) { + if (DELTA(cur)->dfs_state == DFS_ACTIVE) { drop_reused_delta(cur); cur->dfs_state = DFS_DONE; break; @@@ -1714,7 -1668,7 +1716,7 @@@ * an extra "next" pointer to keep going after we reset cur->delta. */ for (cur = entry; cur; cur = next) { - next = cur->delta; + next = DELTA(cur); /* * We should have a chain of zero or more ACTIVE states down to @@@ -1725,7 -1679,7 +1727,7 @@@ if (cur->dfs_state == DFS_DONE) break; else if (cur->dfs_state != DFS_ACTIVE) - die("BUG: confusing delta dfs state in second pass: %d", + BUG("confusing delta dfs state in second pass: %d", cur->dfs_state); /* @@@ -1759,10 -1713,6 +1761,10 @@@ static void get_object_details(void uint32_t i; struct object_entry **sorted_by_offset; + if (progress) + progress_state = start_progress(_("Counting objects"), + to_pack.nr_objects); + sorted_by_offset = xcalloc(to_pack.nr_objects, sizeof(struct object_entry *)); for (i = 0; i < to_pack.nr_objects; i++) sorted_by_offset[i] = to_pack.objects + i; @@@ -1771,12 -1721,9 +1773,12 @@@ for (i = 0; i < to_pack.nr_objects; i++) { struct object_entry *entry = sorted_by_offset[i]; check_object(entry); - if (big_file_threshold < entry->size) + if (entry->type_valid && + oe_size_greater_than(&to_pack, entry, big_file_threshold)) entry->no_try_delta = 1; + display_progress(progress_state, i + 1); } + stop_progress(&progress_state); /* * This must happen in a second pass, since we rely on the delta @@@ -1801,14 -1748,10 +1803,14 @@@ static int type_size_sort(const void *_ { const struct object_entry *a = *(struct object_entry **)_a; const struct object_entry *b = *(struct object_entry **)_b; + enum object_type a_type = oe_type(a); + enum object_type b_type = oe_type(b); + unsigned long a_size = SIZE(a); + unsigned long b_size = SIZE(b); - if (a->type > b->type) + if (a_type > b_type) return -1; - if (a->type < b->type) + if (a_type < b_type) return 1; if (a->hash > b->hash) return -1; @@@ -1818,9 -1761,9 +1820,9 @@@ return -1; if (a->preferred_base < b->preferred_base) return 1; - if (a->size > b->size) + if (a_size > b_size) return -1; - if (a->size < b->size) + if (a_size < b_size) return 1; return a < b ? -1 : (a > b); /* newest first */ } @@@ -1873,46 -1816,6 +1875,46 @@@ static pthread_mutex_t progress_mutex #endif +/* + * Return the size of the object without doing any delta + * reconstruction (so non-deltas are true object sizes, but deltas + * return the size of the delta data). + */ +unsigned long oe_get_size_slow(struct packing_data *pack, + const struct object_entry *e) +{ + struct packed_git *p; + struct pack_window *w_curs; + unsigned char *buf; + enum object_type type; + unsigned long used, avail, size; + + if (e->type_ != OBJ_OFS_DELTA && e->type_ != OBJ_REF_DELTA) { + read_lock(); + if (oid_object_info(the_repository, &e->idx.oid, &size) < 0) + die(_("unable to get size of %s"), + oid_to_hex(&e->idx.oid)); + read_unlock(); + return size; + } + + p = oe_in_pack(pack, e); + if (!p) + BUG("when e->type is a delta, it must belong to a pack"); + + read_lock(); + w_curs = NULL; + buf = use_pack(p, &w_curs, e->in_pack_offset, &avail); + used = unpack_object_header_buffer(buf, avail, &type, &size); + if (used == 0) + die(_("unable to parse object header of %s"), + oid_to_hex(&e->idx.oid)); + + unuse_pack(&w_curs); + read_unlock(); + return size; +} + static int try_delta(struct unpacked *trg, struct unpacked *src, unsigned max_depth, unsigned long *mem_usage) { @@@ -1924,7 -1827,7 +1926,7 @@@ void *delta_buf; /* Don't bother doing diffs between different types */ - if (trg_entry->type != src_entry->type) + if (oe_type(trg_entry) != oe_type(src_entry)) return -1; /* @@@ -1935,8 -1838,8 +1937,8 @@@ * it, we will still save the transfer cost, as we already know * the other side has it and we won't send src_entry at all. */ - if (reuse_delta && trg_entry->in_pack && - trg_entry->in_pack == src_entry->in_pack && + if (reuse_delta && IN_PACK(trg_entry) && + IN_PACK(trg_entry) == IN_PACK(src_entry) && !src_entry->preferred_base && trg_entry->in_pack_type != OBJ_REF_DELTA && trg_entry->in_pack_type != OBJ_OFS_DELTA) @@@ -1947,19 -1850,19 +1949,19 @@@ return 0; /* Now some size filtering heuristics. */ - trg_size = trg_entry->size; - if (!trg_entry->delta) { + trg_size = SIZE(trg_entry); + if (!DELTA(trg_entry)) { - max_size = trg_size/2 - 20; + max_size = trg_size/2 - the_hash_algo->rawsz; ref_depth = 1; } else { - max_size = trg_entry->delta_size; + max_size = DELTA_SIZE(trg_entry); ref_depth = trg->depth; } max_size = (uint64_t)max_size * (max_depth - src->depth) / (max_depth - ref_depth + 1); if (max_size == 0) return 0; - src_size = src_entry->size; + src_size = SIZE(src_entry); sizediff = src_size < trg_size ? trg_size - src_size : 0; if (sizediff >= max_size) return 0; @@@ -2021,14 -1924,10 +2023,14 @@@ delta_buf = create_delta(src->index, trg->data, trg_size, &delta_size, max_size); if (!delta_buf) return 0; + if (delta_size >= (1U << OE_DELTA_SIZE_BITS)) { + free(delta_buf); + return 0; + } - if (trg_entry->delta) { + if (DELTA(trg_entry)) { /* Prefer only shallower same-sized deltas. */ - if (delta_size == trg_entry->delta_size && + if (delta_size == DELTA_SIZE(trg_entry) && src->depth + 1 >= trg->depth) { free(delta_buf); return 0; @@@ -2043,7 -1942,7 +2045,7 @@@ free(trg_entry->delta_data); cache_lock(); if (trg_entry->delta_data) { - delta_cache_size -= trg_entry->delta_size; + delta_cache_size -= DELTA_SIZE(trg_entry); trg_entry->delta_data = NULL; } if (delta_cacheable(src_size, trg_size, delta_size)) { @@@ -2055,8 -1954,8 +2057,8 @@@ free(delta_buf); } - trg_entry->delta = src_entry; - trg_entry->delta_size = delta_size; + SET_DELTA(trg_entry, src_entry); + SET_DELTA_SIZE(trg_entry, delta_size); trg->depth = src->depth + 1; return 1; @@@ -2064,13 -1963,13 +2066,13 @@@ static unsigned int check_delta_limit(struct object_entry *me, unsigned int n) { - struct object_entry *child = me->delta_child; + struct object_entry *child = DELTA_CHILD(me); unsigned int m = n; while (child) { unsigned int c = check_delta_limit(child, n + 1); if (m < c) m = c; - child = child->delta_sibling; + child = DELTA_SIBLING(child); } return m; } @@@ -2081,7 -1980,7 +2083,7 @@@ static unsigned long free_unpacked(stru free_delta_index(n->index); n->index = NULL; if (n->data) { - freed_mem += n->entry->size; + freed_mem += SIZE(n->entry); FREE_AND_NULL(n->data); } n->entry = NULL; @@@ -2139,7 -2038,7 +2141,7 @@@ static void find_deltas(struct object_e * otherwise they would become too deep. */ max_depth = depth; - if (entry->delta_child) { + if (DELTA_CHILD(entry)) { max_depth -= check_delta_limit(entry, 0); if (max_depth <= 0) goto next; @@@ -2177,26 -2076,19 +2179,26 @@@ * between writes at that moment. */ if (entry->delta_data && !pack_to_stdout) { - entry->z_delta_size = do_compress(&entry->delta_data, - entry->delta_size); - cache_lock(); - delta_cache_size -= entry->delta_size; - delta_cache_size += entry->z_delta_size; - cache_unlock(); + unsigned long size; + + size = do_compress(&entry->delta_data, DELTA_SIZE(entry)); + if (size < (1U << OE_Z_DELTA_BITS)) { + entry->z_delta_size = size; + cache_lock(); + delta_cache_size -= DELTA_SIZE(entry); + delta_cache_size += entry->z_delta_size; + cache_unlock(); + } else { + FREE_AND_NULL(entry->delta_data); + entry->z_delta_size = 0; + } } /* if we made n a delta, and if n is already at max * depth, leaving it in the window is pointless. we * should evict it first. */ - if (entry->delta && max_depth <= n->depth) + if (DELTA(entry) && max_depth <= n->depth) continue; /* @@@ -2204,7 -2096,7 +2206,7 @@@ * currently deltified object, to keep it longer. It will * be the first base object to be attempted next. */ - if (entry->delta) { + if (DELTA(entry)) { struct unpacked swap = array[best_base]; int dist = (window + idx - best_base) % window; int dst = best_base; @@@ -2525,14 -2417,13 +2527,14 @@@ static void prepare_pack(int window, in for (i = 0; i < to_pack.nr_objects; i++) { struct object_entry *entry = to_pack.objects + i; - if (entry->delta) + if (DELTA(entry)) /* This happens if we decided to reuse existing * delta from a pack. "reuse_delta &&" is implied. */ continue; - if (entry->size < 50) + if (!entry->type_valid || + oe_size_less_than(&to_pack, entry, 50)) continue; if (entry->no_try_delta) @@@ -2540,11 -2431,11 +2542,11 @@@ if (!entry->preferred_base) { nr_deltas++; - if (entry->type < 0) + if (oe_type(entry) < 0) die("unable to get type of object %s", oid_to_hex(&entry->idx.oid)); } else { - if (entry->type < 0) { + if (oe_type(entry) < 0) { /* * This object is not found, but we * don't have to include it anyway. @@@ -2653,7 -2544,7 +2655,7 @@@ static void read_object_list_from_stdin die("expected object ID, got garbage:\n %s", line); add_preferred_base_object(p + 1); - add_object_entry(&oid, 0, p + 1, 0); + add_object_entry(&oid, OBJ_NONE, p + 1, 0); } } @@@ -2786,7 -2677,7 +2788,7 @@@ static void add_objects_in_unpacked_pac struct object_id oid; struct object *o; - if (!p->pack_local || p->pack_keep) + if (!p->pack_local || p->pack_keep || p->pack_keep_in_core) continue; if (open_pack_index(p)) die("cannot open pack index"); @@@ -2817,7 -2708,7 +2819,7 @@@ static int add_loose_object(const struct object_id *oid, const char *path, void *data) { - enum object_type type = oid_object_info(oid, NULL); + enum object_type type = oid_object_info(the_repository, oid, NULL); if (type < 0) { warning("loose object at %s could not be examined", path); @@@ -2849,8 -2740,7 +2851,8 @@@ static int has_sha1_pack_kept_or_nonloc get_packed_git(the_repository); while (p) { - if ((!p->pack_local || p->pack_keep) && + if ((!p->pack_local || p->pack_keep || + p->pack_keep_in_core) && find_pack_entry_one(oid->hash, p)) { last_found = p; return 1; @@@ -2893,7 -2783,7 +2895,7 @@@ static void loosen_unused_packed_object struct object_id oid; for (p = get_packed_git(the_repository); p; p = p->next) { - if (!p->pack_local || p->pack_keep) + if (!p->pack_local || p->pack_keep || p->pack_keep_in_core) continue; if (open_pack_index(p)) @@@ -2919,8 -2809,7 +2921,8 @@@ static int pack_options_allow_reuse(voi { return pack_to_stdout && allow_ofs_delta && - !ignore_packed_keep && + !ignore_packed_keep_on_disk && + !ignore_packed_keep_in_core && (!local || !have_non_local_packs) && !incremental; } @@@ -3029,32 -2918,6 +3031,32 @@@ static void get_object_list(int ac, con oid_array_clear(&recent_objects); } +static void add_extra_kept_packs(const struct string_list *names) +{ + struct packed_git *p; + + if (!names->nr) + return; + + for (p = get_packed_git(the_repository); p; p = p->next) { + const char *name = basename(p->pack_name); + int i; + + if (!p->pack_local) + continue; + + for (i = 0; i < names->nr; i++) + if (!fspathcmp(name, names->items[i].string)) + break; + + if (i < names->nr) { + p->pack_keep_in_core = 1; + ignore_packed_keep_in_core = 1; + continue; + } + } +} + static int option_parse_index_version(const struct option *opt, const char *arg, int unset) { @@@ -3094,7 -2957,6 +3096,7 @@@ int cmd_pack_objects(int argc, const ch struct argv_array rp = ARGV_ARRAY_INIT; int rev_list_unpacked = 0, rev_list_all = 0, rev_list_reflog = 0; int rev_list_index = 0; + struct string_list keep_pack_list = STRING_LIST_INIT_NODUP; struct option pack_objects_options[] = { OPT_SET_INT('q', "quiet", &progress, N_("do not show progress meter"), 0), @@@ -3159,10 -3021,8 +3161,10 @@@ N_("create thin packs")), OPT_BOOL(0, "shallow", &shallow, N_("create packs suitable for shallow fetches")), - OPT_BOOL(0, "honor-pack-keep", &ignore_packed_keep, + OPT_BOOL(0, "honor-pack-keep", &ignore_packed_keep_on_disk, N_("ignore packs that have companion .keep file")), + OPT_STRING_LIST(0, "keep-pack", &keep_pack_list, N_("name"), + N_("ignore this pack")), OPT_INTEGER(0, "compression", &pack_compression_level, N_("pack compression level")), OPT_SET_INT(0, "keep-true-parents", &grafts_replace_parents, @@@ -3180,9 -3040,6 +3182,9 @@@ OPT_END(), }; + if (DFS_NUM_STATES > (1 << OE_DFS_STATE_BITS)) + BUG("too many dfs states, increase OE_DFS_STATE_BITS"); + check_replace_refs = 0; reset_pack_idx_option(&pack_idx_opts); @@@ -3199,17 -3056,6 +3201,17 @@@ if (pack_to_stdout != !base_name || argc) usage_with_options(pack_usage, pack_objects_options); + if (depth >= (1 << OE_DEPTH_BITS)) { + warning(_("delta chain depth %d is too deep, forcing %d"), + depth, (1 << OE_DEPTH_BITS) - 1); + depth = (1 << OE_DEPTH_BITS) - 1; + } + if (cache_max_small_delta_size >= (1U << OE_Z_DELTA_BITS)) { + warning(_("pack.deltaCacheLimit is too high, forcing %d"), + (1U << OE_Z_DELTA_BITS) - 1); + cache_max_small_delta_size = (1U << OE_Z_DELTA_BITS) - 1; + } + argv_array_push(&rp, "pack-objects"); if (thin) { use_internal_rev_list = 1; @@@ -3241,8 -3087,6 +3243,8 @@@ fetch_if_missing = 0; argv_array_push(&rp, "--exclude-promisor-objects"); } + if (unpack_unreachable || keep_unreachable || pack_loose_unreachable) + use_internal_rev_list = 1; if (!reuse_object) reuse_delta = 0; @@@ -3306,20 -3150,19 +3308,20 @@@ if (progress && all_progress_implied) progress = 2; - if (ignore_packed_keep) { + add_extra_kept_packs(&keep_pack_list); + if (ignore_packed_keep_on_disk) { struct packed_git *p; for (p = get_packed_git(the_repository); p; p = p->next) if (p->pack_local && p->pack_keep) break; if (!p) /* no keep-able packs found */ - ignore_packed_keep = 0; + ignore_packed_keep_on_disk = 0; } if (local) { /* - * unlike ignore_packed_keep above, we do not want to - * unset "local" based on looking at packs, as it - * also covers non-local objects + * unlike ignore_packed_keep_on_disk above, we do not + * want to unset "local" based on looking at packs, as + * it also covers non-local objects */ struct packed_git *p; for (p = get_packed_git(the_repository); p; p = p->next) { @@@ -3330,10 -3173,8 +3332,10 @@@ } } + prepare_packing_data(&to_pack); + if (progress) - progress_state = start_progress(_("Counting objects"), 0); + progress_state = start_progress(_("Enumerating objects"), 0); if (!use_internal_rev_list) read_object_list_from_stdin(); else { diff --combined builtin/receive-pack.c index d5f15cd4f6,dca523f50f..68d36e0a56 --- a/builtin/receive-pack.c +++ b/builtin/receive-pack.c @@@ -7,7 -7,7 +7,7 @@@ #include "pkt-line.h" #include "sideband.h" #include "run-command.h" -#include "exec_cmd.h" +#include "exec-cmd.h" #include "commit.h" #include "object.h" #include "remote.h" @@@ -454,21 -454,21 +454,21 @@@ static void hmac_sha1(unsigned char *ou /* RFC 2104 2. (6) & (7) */ git_SHA1_Init(&ctx); git_SHA1_Update(&ctx, k_opad, sizeof(k_opad)); - git_SHA1_Update(&ctx, out, 20); + git_SHA1_Update(&ctx, out, GIT_SHA1_RAWSZ); git_SHA1_Final(out, &ctx); } static char *prepare_push_cert_nonce(const char *path, timestamp_t stamp) { struct strbuf buf = STRBUF_INIT; - unsigned char sha1[20]; + unsigned char sha1[GIT_SHA1_RAWSZ]; strbuf_addf(&buf, "%s:%"PRItime, path, stamp); hmac_sha1(sha1, buf.buf, buf.len, cert_nonce_seed, strlen(cert_nonce_seed));; strbuf_release(&buf); /* RFC 2104 5. HMAC-SHA1-80 */ - strbuf_addf(&buf, "%"PRItime"-%.*s", stamp, 20, sha1_to_hex(sha1)); + strbuf_addf(&buf, "%"PRItime"-%.*s", stamp, GIT_SHA1_HEXSZ, sha1_to_hex(sha1)); return strbuf_detach(&buf, NULL); } @@@ -876,7 -876,7 +876,7 @@@ static void refuse_unconfigured_deny_de static int command_singleton_iterator(void *cb_data, struct object_id *oid); static int update_shallow_ref(struct command *cmd, struct shallow_info *si) { - static struct lock_file shallow_lock; + struct lock_file shallow_lock = LOCK_INIT; struct oid_array extra = OID_ARRAY_INIT; struct check_connected_options opt = CHECK_CONNECTED_INIT; uint32_t mask = 1 << (cmd->index % 32); @@@ -968,7 -968,7 +968,7 @@@ static const char *push_to_deploy(unsig return "Working directory has unstaged changes"; /* diff-index with either HEAD or an empty tree */ - diff_index[4] = head_has_history() ? "HEAD" : EMPTY_TREE_SHA1_HEX; + diff_index[4] = head_has_history() ? "HEAD" : empty_tree_oid_hex(); child_process_init(&child); child.argv = diff_index; @@@ -1378,7 -1378,7 +1378,7 @@@ static void warn_if_skipped_connectivit } } if (!checked_connectivity) - die("BUG: connectivity check skipped???"); + BUG("connectivity check skipped???"); } static void execute_commands_non_atomic(struct command *commands, @@@ -1965,12 -1965,6 +1965,12 @@@ int cmd_receive_pack(int argc, const ch unpack_limit = receive_unpack_limit; switch (determine_protocol_version_server()) { + case protocol_v2: + /* + * push support for protocol v2 has not been implemented yet, + * so ignore the request to use v2 and fallback to using v0. + */ + break; case protocol_v1: /* * v1 is just the original protocol with a version string, diff --combined cache.h index 3bbe4f8845,71b3c1b15b..08a48263b5 --- a/cache.h +++ b/cache.h @@@ -324,7 -324,7 +324,7 @@@ struct index_state drop_cache_tree : 1; struct hashmap name_hash; struct hashmap dir_hash; - unsigned char sha1[20]; + struct object_id oid; struct untracked_cache *untracked; uint64_t fsmonitor_last_update; struct ewah_bitmap *fsmonitor_dirty; @@@ -373,13 -373,6 +373,13 @@@ extern void free_name_hash(struct index #define read_blob_data_from_cache(path, sz) read_blob_data_from_index(&the_index, (path), (sz)) #endif +#define TYPE_BITS 3 + +/* + * Values in this enum (except those outside the 3 bit range) are part + * of pack file format. See Documentation/technical/pack-format.txt + * for more information. + */ enum object_type { OBJ_BAD = -1, OBJ_NONE = 0, @@@ -435,7 -428,6 +435,7 @@@ static inline enum object_type object_t #define GIT_ICASE_PATHSPECS_ENVIRONMENT "GIT_ICASE_PATHSPECS" #define GIT_QUARANTINE_ENVIRONMENT "GIT_QUARANTINE_PATH" #define GIT_OPTIONAL_LOCKS_ENVIRONMENT "GIT_OPTIONAL_LOCKS" +#define GIT_TEXT_DOMAIN_DIR_ENVIRONMENT "GIT_TEXTDOMAINDIR" /* * Environment variable used in handshaking the wire protocol. @@@ -485,7 -477,7 +485,7 @@@ extern const char *get_git_common_dir(v extern char *get_object_directory(void); extern char *get_index_file(void); extern char *get_graft_file(void); -extern int set_git_dir(const char *path); +extern void set_git_dir(const char *path); extern int get_common_dir_noenv(struct strbuf *sb, const char *gitdir); extern int get_common_dir(struct strbuf *sb, const char *gitdir); extern const char *get_git_namespace(void); @@@ -642,7 -634,7 +642,7 @@@ extern int unmerged_index(const struct */ extern int index_has_changes(struct strbuf *sb); -extern int verify_path(const char *path); +extern int verify_path(const char *path, unsigned mode); extern int strcmp_offset(const char *s1, const char *s2, size_t *first_change); extern int index_dir_exists(struct index_state *istate, const char *name, int namelen); extern void adjust_dirname_case(struct index_state *istate, char *name); @@@ -813,7 -805,6 +813,7 @@@ extern char *git_replace_ref_base extern int fsync_object_files; extern int core_preload_index; +extern int core_commit_graph; extern int core_apply_sparse_checkout; extern int precomposed_unicode; extern int protect_hfs; @@@ -1017,21 -1008,10 +1017,10 @@@ static inline void oidclr(struct object memset(oid->hash, 0, GIT_MAX_RAWSZ); } - - #define EMPTY_TREE_SHA1_HEX \ - "4b825dc642cb6eb9a060e54bf8d69288fbee4904" - #define EMPTY_TREE_SHA1_BIN_LITERAL \ - "\x4b\x82\x5d\xc6\x42\xcb\x6e\xb9\xa0\x60" \ - "\xe5\x4b\xf8\xd6\x92\x88\xfb\xee\x49\x04" - extern const struct object_id empty_tree_oid; - #define EMPTY_TREE_SHA1_BIN (empty_tree_oid.hash) - - #define EMPTY_BLOB_SHA1_HEX \ - "e69de29bb2d1d6434b8b29ae775ad8c2e48c5391" - #define EMPTY_BLOB_SHA1_BIN_LITERAL \ - "\xe6\x9d\xe2\x9b\xb2\xd1\xd6\x43\x4b\x8b" \ - "\x29\xae\x77\x5a\xd8\xc2\xe4\x8c\x53\x91" - extern const struct object_id empty_blob_oid; + static inline void oidread(struct object_id *oid, const unsigned char *hash) + { + memcpy(oid->hash, hash, the_hash_algo->rawsz); + } static inline int is_empty_blob_sha1(const unsigned char *sha1) { @@@ -1053,6 -1033,9 +1042,9 @@@ static inline int is_empty_tree_oid(con return !oidcmp(oid, the_hash_algo->empty_tree); } + const char *empty_tree_oid_hex(void); + const char *empty_blob_oid_hex(void); + /* set default permissions by passing mode arguments to open(2) */ int git_mkstemps_mode(char *pattern, int suffix_len, int mode); int git_mkstemp_mode(char *pattern, int mode); @@@ -1168,15 -1151,7 +1160,15 @@@ int normalize_path_copy(char *dst, cons int longest_ancestor_length(const char *path, struct string_list *prefixes); char *strip_path_suffix(const char *path, const char *suffix); int daemon_avoid_alias(const char *path); -extern int is_ntfs_dotgit(const char *name); + +/* + * These functions match their is_hfs_dotgit() counterparts; see utf8.h for + * details. + */ +int is_ntfs_dotgit(const char *name); +int is_ntfs_dotgitmodules(const char *name); +int is_ntfs_dotgitignore(const char *name); +int is_ntfs_dotgitattributes(const char *name); /* * Returns true iff "str" could be confused as a command-line option when @@@ -1208,8 -1183,27 +1200,8 @@@ static inline void *read_object_file(co return read_object_file_extended(oid, type, size, 1); } -/* - * This internal function is only declared here for the benefit of - * lookup_replace_object(). Please do not call it directly. - */ -extern const struct object_id *do_lookup_replace_object(const struct object_id *oid); - -/* - * If object sha1 should be replaced, return the replacement object's - * name (replaced recursively, if necessary). The return value is - * either sha1 or a pointer to a permanently-allocated value. When - * object replacement is suppressed, always return sha1. - */ -static inline const struct object_id *lookup_replace_object(const struct object_id *oid) -{ - if (!check_replace_refs) - return oid; - return do_lookup_replace_object(oid); -} - /* Read and unpack an object file into memory, write memory to an object file */ -extern int oid_object_info(const struct object_id *, unsigned long *); +int oid_object_info(struct repository *r, const struct object_id *, unsigned long *); extern int hash_object_file(const void *buf, unsigned long len, const char *type, struct object_id *oid); @@@ -1268,7 -1262,7 +1260,7 @@@ extern int has_object_file_with_flags(c * with the specified name. This function does not respect replace * references. */ - extern int has_loose_object_nonlocal(const unsigned char *sha1); + extern int has_loose_object_nonlocal(const struct object_id *oid); extern void assert_oid_type(const struct object_id *oid, enum object_type expect); @@@ -1299,7 -1293,6 +1291,6 @@@ static inline int hex2chr(const char *s #define FALLBACK_DEFAULT_ABBREV 7 struct object_context { - unsigned char tree[20]; unsigned mode; /* * symlink_path is only used by get_tree_entry_follow_symlinks, @@@ -1566,7 -1559,6 +1557,6 @@@ struct pack_window struct pack_entry { off_t offset; - unsigned char sha1[20]; struct packed_git *p; }; @@@ -1690,10 -1682,7 +1680,10 @@@ struct object_info #define OBJECT_INFO_QUICK 8 /* Do not check loose object */ #define OBJECT_INFO_IGNORE_LOOSE 16 -extern int oid_object_info_extended(const struct object_id *, struct object_info *, unsigned flags); + +int oid_object_info_extended(struct repository *r, + const struct object_id *, + struct object_info *, unsigned flags); /* * Set this to 0 to prevent sha1_object_info_extended() from fetching missing diff --combined commit.c index f9714ed74c,9617f85caa..b0e57cc440 --- a/commit.c +++ b/commit.c @@@ -1,7 -1,6 +1,7 @@@ #include "cache.h" #include "tag.h" #include "commit.h" +#include "commit-graph.h" #include "pkt-line.h" #include "utf8.h" #include "diff.h" @@@ -13,7 -12,6 +13,7 @@@ #include "prio-queue.h" #include "sha1-lookup.h" #include "wt-status.h" +#include "advice.h" static struct commit_extra_header *read_commit_extra_header_lines(const char *buf, size_t len, const char **); @@@ -178,15 -176,6 +178,15 @@@ static int read_graft_file(const char * struct strbuf buf = STRBUF_INIT; if (!fp) return -1; + if (advice_graft_file_deprecated) + advise(_("Support for /info/grafts is deprecated\n" + "and will be removed in a future Git version.\n" + "\n" + "Please use \"git replace --convert-graft-file\"\n" + "to convert the grafts into replace refs.\n" + "\n" + "Turn this message off by running\n" + "\"git config advice.graftFileDeprecated false\"")); while (!strbuf_getwholeline(&buf, fp, '\n')) { /* The format is just "Commit Parent1 Parent2 ...\n" */ struct commit_graft *graft = read_graft_line(&buf); @@@ -306,22 -295,6 +306,22 @@@ void free_commit_buffer(struct commit * } } +struct tree *get_commit_tree(const struct commit *commit) +{ + if (commit->maybe_tree || !commit->object.parsed) + return commit->maybe_tree; + + if (commit->graph_pos == COMMIT_NOT_FROM_GRAPH) + BUG("commit has NULL tree, but was not loaded from commit-graph"); + + return get_commit_tree_in_graph(commit); +} + +struct object_id *get_commit_tree_oid(const struct commit *commit) +{ + return &get_commit_tree(commit)->object.oid; +} + const void *detach_commit_buffer(struct commit *commit, unsigned long *sizep) { struct commit_buffer *v = buffer_slab_peek(&buffer_slab, commit); @@@ -358,10 -331,10 +358,10 @@@ int parse_commit_buffer(struct commit * if (tail <= bufptr + tree_entry_len + 1 || memcmp(bufptr, "tree ", 5) || bufptr[tree_entry_len] != '\n') return error("bogus commit object %s", oid_to_hex(&item->object.oid)); - if (get_sha1_hex(bufptr + 5, parent.hash) < 0) + if (get_oid_hex(bufptr + 5, &parent) < 0) return error("bad tree pointer in commit %s", oid_to_hex(&item->object.oid)); - item->tree = lookup_tree(&parent); + item->maybe_tree = lookup_tree(&parent); bufptr += tree_entry_len + 1; /* "tree " + "hex sha1" + "\n" */ pptr = &item->parents; @@@ -370,7 -343,7 +370,7 @@@ struct commit *new_parent; if (tail <= bufptr + parent_entry_len + 1 || - get_sha1_hex(bufptr + 7, parent.hash) || + get_oid_hex(bufptr + 7, &parent) || bufptr[parent_entry_len] != '\n') return error("bad parents in commit %s", oid_to_hex(&item->object.oid)); bufptr += parent_entry_len + 1; @@@ -410,8 -383,6 +410,8 @@@ int parse_commit_gently(struct commit * return -1; if (item->object.parsed) return 0; + if (parse_commit_in_graph(item)) + return 0; buffer = read_object_file(&item->object.oid, &type, &size); if (!buffer) return quiet_on_missing ? -1 : @@@ -1317,19 -1288,17 +1317,19 @@@ struct commit_extra_header *read_commit return extra; } -void for_each_mergetag(each_mergetag_fn fn, struct commit *commit, void *data) +int for_each_mergetag(each_mergetag_fn fn, struct commit *commit, void *data) { struct commit_extra_header *extra, *to_free; + int res = 0; to_free = read_commit_extra_headers(commit, NULL); - for (extra = to_free; extra; extra = extra->next) { + for (extra = to_free; !res && extra; extra = extra->next) { if (strcmp(extra->key, "mergetag")) continue; /* not a merge tag */ - fn(commit, extra, data); + res = fn(commit, extra, data); } free_commit_extra_headers(to_free); + return res; } static inline int standard_header_field(const char *field, size_t len) diff --combined diff.c index 28ee05c9ad,b1666b9b2d..136d44b455 --- a/diff.c +++ b/diff.c @@@ -177,7 -177,7 +177,7 @@@ static int parse_submodule_params(struc return 0; } -static int git_config_rename(const char *var, const char *value) +int git_config_rename(const char *var, const char *value) { if (!value) return DIFF_DETECT_RENAME; @@@ -1184,7 -1184,7 +1184,7 @@@ static void emit_diff_symbol_from_struc fputs(o->stat_sep, o->file); break; default: - die("BUG: unknown diff symbol"); + BUG("unknown diff symbol"); } strbuf_release(&sb); } @@@ -1343,7 -1343,7 +1343,7 @@@ static struct diff_tempfile *claim_diff for (i = 0; i < ARRAY_SIZE(diff_temp); i++) if (!diff_temp[i].name) return diff_temp + i; - die("BUG: diff is failing to clean up its tempfiles"); + BUG("diff is failing to clean up its tempfiles"); } static void remove_tempfile(void) @@@ -3472,7 -3472,7 +3472,7 @@@ static int reuse_worktree_file(const ch * objects however would tend to be slower as they need * to be individually opened and inflated. */ - if (!FAST_WORKING_DIRECTORY && !want_file && has_sha1_pack(oid->hash)) + if (!FAST_WORKING_DIRECTORY && !want_file && has_object_pack(oid)) return 0; /* @@@ -3638,8 -3638,7 +3638,8 @@@ int diff_populate_filespec(struct diff_ else { enum object_type type; if (size_only || (flags & CHECK_BINARY)) { - type = oid_object_info(&s->oid, &s->size); + type = oid_object_info(the_repository, &s->oid, + &s->size); if (type < 0) die("unable to read %s", oid_to_hex(&s->oid)); @@@ -3841,7 -3840,7 +3841,7 @@@ static const char *diff_abbrev_oid(cons if (abbrev < 0) abbrev = FALLBACK_DEFAULT_ABBREV; if (abbrev > GIT_SHA1_HEXSZ) - die("BUG: oid abbreviation out of range: %d", abbrev); + BUG("oid abbreviation out of range: %d", abbrev); if (abbrev) hex[abbrev] = '\0'; return hex; @@@ -3898,13 -3897,14 +3898,14 @@@ static void fill_metainfo(struct strbu *must_show_header = 0; } if (one && two && oidcmp(&one->oid, &two->oid)) { - int abbrev = o->flags.full_index ? 40 : DEFAULT_ABBREV; + const unsigned hexsz = the_hash_algo->hexsz; + int abbrev = o->flags.full_index ? hexsz : DEFAULT_ABBREV; if (o->flags.binary) { mmfile_t mf; if ((!fill_mmfile(&mf, one) && diff_filespec_is_binary(one)) || (!fill_mmfile(&mf, two) && diff_filespec_is_binary(two))) - abbrev = 40; + abbrev = hexsz; } strbuf_addf(msg, "%s%sindex %s..%s", line_prefix, set, diff_abbrev_oid(&one->oid, abbrev), @@@ -4139,6 -4139,11 +4140,11 @@@ void diff_setup_done(struct diff_option DIFF_FORMAT_NAME_STATUS | DIFF_FORMAT_CHECKDIFF | DIFF_FORMAT_NO_OUTPUT; + /* + * This must be signed because we're comparing against a potentially + * negative value. + */ + const int hexsz = the_hash_algo->hexsz; if (options->set_default) options->set_default(options); @@@ -4219,8 -4224,8 +4225,8 @@@ */ read_cache(); } - if (40 < options->abbrev) - options->abbrev = 40; /* full */ + if (hexsz < options->abbrev) + options->abbrev = hexsz; /* full */ /* * It does not make sense to show the first hit we happened @@@ -4335,7 -4340,7 +4341,7 @@@ static int stat_opt(struct diff_option int argcount = 1; if (!skip_prefix(arg, "--stat", &arg)) - die("BUG: stat option does not begin with --stat: %s", arg); + BUG("stat option does not begin with --stat: %s", arg); end = (char *)arg; switch (*arg) { @@@ -4798,8 -4803,8 +4804,8 @@@ int diff_opt_parse(struct diff_options options->abbrev = strtoul(arg, NULL, 10); if (options->abbrev < MINIMUM_ABBREV) options->abbrev = MINIMUM_ABBREV; - else if (40 < options->abbrev) - options->abbrev = 40; + else if (the_hash_algo->hexsz < options->abbrev) + options->abbrev = the_hash_algo->hexsz; } else if ((argcount = parse_long_opt("src-prefix", av, &optarg))) { options->a_prefix = optarg; @@@ -5520,7 -5525,7 +5526,7 @@@ static void diff_flush_patch_all_file_p struct diff_queue_struct *q = &diff_queued_diff; if (WSEH_NEW & WS_RULE_MASK) - die("BUG: WS rules bit mask overlaps with diff symbol flags"); + BUG("WS rules bit mask overlaps with diff symbol flags"); if (o->color_moved) o->emitted_symbols = &esm; @@@ -6054,7 -6059,7 +6060,7 @@@ size_t fill_textconv(struct userdiff_dr } if (!driver->textconv) - die("BUG: fill_textconv called with non-textconv driver"); + BUG("fill_textconv called with non-textconv driver"); if (driver->textconv_cache && df->oid_valid) { *outbuf = notes_cache_get(driver->textconv_cache, diff --combined dir.c index 7ca730fac4,e879c34c2e..ccf8b4975e --- a/dir.c +++ b/dir.c @@@ -19,7 -19,6 +19,7 @@@ #include "varint.h" #include "ewah/ewok.h" #include "fsmonitor.h" +#include "submodule-config.h" /* * Tells read_directory_recursive how a file or directory should be treated. @@@ -829,7 -828,7 +829,7 @@@ static int add_excludes(const char *fna if (size == 0) { if (oid_stat) { fill_stat_data(&oid_stat->stat, &st); - oidcpy(&oid_stat->oid, &empty_blob_oid); + oidcpy(&oid_stat->oid, the_hash_algo->empty_blob); oid_stat->valid = 1; } close(fd); @@@ -1241,11 -1240,11 +1241,11 @@@ static void prep_exclude(struct dir_str (!untracked || !untracked->valid || /* * .. and .gitignore does not exist before - * (i.e. null exclude_sha1). Then we can skip + * (i.e. null exclude_oid). Then we can skip * loading .gitignore, which would result in * ENOENT anyway. */ - !is_null_sha1(untracked->exclude_sha1))) { + !is_null_oid(&untracked->exclude_oid))) { /* * dir->basebuf gets reused by the traversal, but we * need fname to remain unchanged to ensure the src @@@ -1276,9 -1275,9 +1276,9 @@@ * order, though, if you do that. */ if (untracked && - hashcmp(oid_stat.oid.hash, untracked->exclude_sha1)) { + oidcmp(&oid_stat.oid, &untracked->exclude_oid)) { invalidate_gitignore(dir->untracked, untracked); - hashcpy(untracked->exclude_sha1, oid_stat.oid.hash); + oidcpy(&untracked->exclude_oid, &oid_stat.oid); } dir->exclude_stack = stk; current = stk->baselen; @@@ -2623,9 -2622,10 +2623,10 @@@ static void write_one_dir(struct untrac stat_data_to_disk(&stat_data, &untracked->stat_data); strbuf_add(&wd->sb_stat, &stat_data, sizeof(stat_data)); } - if (!is_null_sha1(untracked->exclude_sha1)) { + if (!is_null_oid(&untracked->exclude_oid)) { ewah_set(wd->sha1_valid, i); - strbuf_add(&wd->sb_sha1, untracked->exclude_sha1, 20); + strbuf_add(&wd->sb_sha1, untracked->exclude_oid.hash, + the_hash_algo->rawsz); } intlen = encode_varint(untracked->untracked_nr, intbuf); @@@ -2826,16 -2826,16 +2827,16 @@@ static void read_stat(size_t pos, void ud->valid = 1; } - static void read_sha1(size_t pos, void *cb) + static void read_oid(size_t pos, void *cb) { struct read_data *rd = cb; struct untracked_cache_dir *ud = rd->ucd[pos]; - if (rd->data + 20 > rd->end) { + if (rd->data + the_hash_algo->rawsz > rd->end) { rd->data = rd->end + 1; return; } - hashcpy(ud->exclude_sha1, rd->data); - rd->data += 20; + hashcpy(ud->exclude_oid.hash, rd->data); + rd->data += the_hash_algo->rawsz; } static void load_oid_stat(struct oid_stat *oid_stat, const unsigned char *data, @@@ -2918,7 -2918,7 +2919,7 @@@ struct untracked_cache *read_untracked_ ewah_each_bit(rd.check_only, set_check_only, &rd); rd.data = next + len; ewah_each_bit(rd.valid, read_stat, &rd); - ewah_each_bit(rd.sha1_valid, read_sha1, &rd); + ewah_each_bit(rd.sha1_valid, read_oid, &rd); next = rd.data; done: @@@ -2993,7 -2993,7 +2994,7 @@@ void untracked_cache_invalidate_path(st { if (!istate->untracked || !istate->untracked->root) return; - if (!safe_path && !verify_path(path)) + if (!safe_path && !verify_path(path, 0)) return; invalidate_one_component(istate->untracked, istate->untracked->root, path, strlen(path)); @@@ -3011,57 -3011,8 +3012,57 @@@ void untracked_cache_add_to_index(struc untracked_cache_invalidate_path(istate, path, 1); } -/* Update gitfile and core.worktree setting to connect work tree and git dir */ -void connect_work_tree_and_git_dir(const char *work_tree_, const char *git_dir_) +static void connect_wt_gitdir_in_nested(const char *sub_worktree, + const char *sub_gitdir) +{ + int i; + struct repository subrepo; + struct strbuf sub_wt = STRBUF_INIT; + struct strbuf sub_gd = STRBUF_INIT; + + const struct submodule *sub; + + /* If the submodule has no working tree, we can ignore it. */ + if (repo_init(&subrepo, sub_gitdir, sub_worktree)) + return; + + if (repo_read_index(&subrepo) < 0) + die("index file corrupt in repo %s", subrepo.gitdir); + + for (i = 0; i < subrepo.index->cache_nr; i++) { + const struct cache_entry *ce = subrepo.index->cache[i]; + + if (!S_ISGITLINK(ce->ce_mode)) + continue; + + while (i + 1 < subrepo.index->cache_nr && + !strcmp(ce->name, subrepo.index->cache[i + 1]->name)) + /* + * Skip entries with the same name in different stages + * to make sure an entry is returned only once. + */ + i++; + + sub = submodule_from_path(&subrepo, &null_oid, ce->name); + if (!sub || !is_submodule_active(&subrepo, ce->name)) + /* .gitmodules broken or inactive sub */ + continue; + + strbuf_reset(&sub_wt); + strbuf_reset(&sub_gd); + strbuf_addf(&sub_wt, "%s/%s", sub_worktree, sub->path); + strbuf_addf(&sub_gd, "%s/modules/%s", sub_gitdir, sub->name); + + connect_work_tree_and_git_dir(sub_wt.buf, sub_gd.buf, 1); + } + strbuf_release(&sub_wt); + strbuf_release(&sub_gd); + repo_clear(&subrepo); +} + +void connect_work_tree_and_git_dir(const char *work_tree_, + const char *git_dir_, + int recurse_into_nested) { struct strbuf gitfile_sb = STRBUF_INIT; struct strbuf cfg_sb = STRBUF_INIT; @@@ -3091,10 -3042,6 +3092,10 @@@ strbuf_release(&gitfile_sb); strbuf_release(&cfg_sb); strbuf_release(&rel_path); + + if (recurse_into_nested) + connect_wt_gitdir_in_nested(work_tree, git_dir); + free(work_tree); free(git_dir); } @@@ -3108,5 -3055,5 +3109,5 @@@ void relocate_gitdir(const char *path, die_errno(_("could not migrate git directory from '%s' to '%s'"), old_git_dir, new_git_dir); - connect_work_tree_and_git_dir(path, new_git_dir); + connect_work_tree_and_git_dir(path, new_git_dir, 0); } diff --combined dir.h index 3870193e52,de66be9f4e..f5fdedbab2 --- a/dir.h +++ b/dir.h @@@ -3,6 -3,7 +3,7 @@@ /* See Documentation/technical/api-directory-listing.txt */ + #include "cache.h" #include "strbuf.h" struct dir_entry { @@@ -118,8 -119,8 +119,8 @@@ struct untracked_cache_dir /* all data except 'dirs' in this struct are good */ unsigned int valid : 1; unsigned int recurse : 1; - /* null SHA-1 means this directory does not have .gitignore */ - unsigned char exclude_sha1[20]; + /* null object ID means this directory does not have .gitignore */ + struct object_id exclude_oid; char name[FLEX_ARRAY]; }; @@@ -359,17 -360,7 +360,17 @@@ struct untracked_cache *read_untracked_ void write_untracked_extension(struct strbuf *out, struct untracked_cache *untracked); void add_untracked_cache(struct index_state *istate); void remove_untracked_cache(struct index_state *istate); -extern void connect_work_tree_and_git_dir(const char *work_tree, const char *git_dir); + +/* + * Connect a worktree to a git directory by creating (or overwriting) a + * '.git' file containing the location of the git directory. In the git + * directory set the core.worktree setting to indicate where the worktree is. + * When `recurse_into_nested` is set, recurse into any nested submodules, + * connecting them as well. + */ +extern void connect_work_tree_and_git_dir(const char *work_tree, + const char *git_dir, + int recurse_into_nested); extern void relocate_gitdir(const char *path, const char *old_git_dir, const char *new_git_dir); diff --combined fsck.c index 4db2277ab8,768011f812..bcae2c30e6 --- a/fsck.c +++ b/fsck.c @@@ -10,13 -10,6 +10,13 @@@ #include "utf8.h" #include "sha1-array.h" #include "decorate.h" +#include "oidset.h" +#include "packfile.h" +#include "submodule-config.h" +#include "config.h" + +static struct oidset gitmodules_found = OIDSET_INIT; +static struct oidset gitmodules_done = OIDSET_INIT; #define FSCK_FATAL -1 #define FSCK_INFO -2 @@@ -51,7 -44,6 +51,7 @@@ FUNC(MISSING_TAG_ENTRY, ERROR) \ FUNC(MISSING_TAG_OBJECT, ERROR) \ FUNC(MISSING_TREE, ERROR) \ + FUNC(MISSING_TREE_OBJECT, ERROR) \ FUNC(MISSING_TYPE, ERROR) \ FUNC(MISSING_TYPE_ENTRY, ERROR) \ FUNC(MULTIPLE_AUTHORS, ERROR) \ @@@ -59,11 -51,6 +59,11 @@@ FUNC(TREE_NOT_SORTED, ERROR) \ FUNC(UNKNOWN_TYPE, ERROR) \ FUNC(ZERO_PADDED_DATE, ERROR) \ + FUNC(GITMODULES_MISSING, ERROR) \ + FUNC(GITMODULES_BLOB, ERROR) \ + FUNC(GITMODULES_PARSE, ERROR) \ + FUNC(GITMODULES_NAME, ERROR) \ + FUNC(GITMODULES_SYMLINK, ERROR) \ /* warnings */ \ FUNC(BAD_FILEMODE, WARN) \ FUNC(EMPTY_NAME, WARN) \ @@@ -409,11 -396,9 +409,11 @@@ static int fsck_walk_commit(struct comm name = get_object_name(options, &commit->object); if (name) - put_object_name(options, &commit->tree->object, "%s:", name); + put_object_name(options, &get_commit_tree(commit)->object, + "%s:", name); - result = options->walk((struct object *)commit->tree, OBJ_TREE, data, options); + result = options->walk((struct object *)get_commit_tree(commit), + OBJ_TREE, data, options); if (result < 0) return result; res = result; @@@ -576,18 -561,10 +576,18 @@@ static int fsck_tree(struct tree *item has_empty_name |= !*name; has_dot |= !strcmp(name, "."); has_dotdot |= !strcmp(name, ".."); - has_dotgit |= (!strcmp(name, ".git") || - is_hfs_dotgit(name) || - is_ntfs_dotgit(name)); + has_dotgit |= is_hfs_dotgit(name) || is_ntfs_dotgit(name); has_zero_pad |= *(char *)desc.buffer == '0'; + + if (is_hfs_dotgitmodules(name) || is_ntfs_dotgitmodules(name)) { + if (!S_ISLNK(mode)) + oidset_insert(&gitmodules_found, oid); + else + retval += report(options, &item->object, + FSCK_MSG_GITMODULES_SYMLINK, + ".gitmodules is a symbolic link"); + } + if (update_tree_entry_gently(&desc)) { retval += report(options, &item->object, FSCK_MSG_BAD_TREE, "cannot be parsed as a tree"); break; @@@ -734,30 -711,31 +734,31 @@@ static int fsck_ident(const char **iden static int fsck_commit_buffer(struct commit *commit, const char *buffer, unsigned long size, struct fsck_options *options) { - unsigned char tree_sha1[20], sha1[20]; + struct object_id tree_oid, oid; struct commit_graft *graft; unsigned parent_count, parent_line_count = 0, author_count; int err; const char *buffer_begin = buffer; + const char *p; if (verify_headers(buffer, size, &commit->object, options)) return -1; if (!skip_prefix(buffer, "tree ", &buffer)) return report(options, &commit->object, FSCK_MSG_MISSING_TREE, "invalid format - expected 'tree' line"); - if (get_sha1_hex(buffer, tree_sha1) || buffer[40] != '\n') { + if (parse_oid_hex(buffer, &tree_oid, &p) || *p != '\n') { err = report(options, &commit->object, FSCK_MSG_BAD_TREE_SHA1, "invalid 'tree' line format - bad sha1"); if (err) return err; } - buffer += 41; + buffer = p + 1; while (skip_prefix(buffer, "parent ", &buffer)) { - if (get_sha1_hex(buffer, sha1) || buffer[40] != '\n') { + if (parse_oid_hex(buffer, &oid, &p) || *p != '\n') { err = report(options, &commit->object, FSCK_MSG_BAD_PARENT_SHA1, "invalid 'parent' line format - bad sha1"); if (err) return err; } - buffer += 41; + buffer = p + 1; parent_line_count++; } graft = lookup_commit_graft(&commit->object.oid); @@@ -795,8 -773,8 +796,8 @@@ err = fsck_ident(&buffer, &commit->object, options); if (err) return err; - if (!commit->tree) { + if (!get_commit_tree(commit)) { - err = report(options, &commit->object, FSCK_MSG_BAD_TREE, "could not load commit's tree %s", sha1_to_hex(tree_sha1)); + err = report(options, &commit->object, FSCK_MSG_BAD_TREE, "could not load commit's tree %s", oid_to_hex(&tree_oid)); if (err) return err; } @@@ -822,11 -800,12 +823,12 @@@ static int fsck_commit(struct commit *c static int fsck_tag_buffer(struct tag *tag, const char *data, unsigned long size, struct fsck_options *options) { - unsigned char sha1[20]; + struct object_id oid; int ret = 0; const char *buffer; char *to_free = NULL, *eol; struct strbuf sb = STRBUF_INIT; + const char *p; if (data) buffer = data; @@@ -857,12 -836,12 +859,12 @@@ ret = report(options, &tag->object, FSCK_MSG_MISSING_OBJECT, "invalid format - expected 'object' line"); goto done; } - if (get_sha1_hex(buffer, sha1) || buffer[40] != '\n') { + if (parse_oid_hex(buffer, &oid, &p) || *p != '\n') { ret = report(options, &tag->object, FSCK_MSG_BAD_OBJECT_SHA1, "invalid 'object' line format - bad sha1"); if (ret) goto done; } - buffer += 41; + buffer = p + 1; if (!skip_prefix(buffer, "type ", &buffer)) { ret = report(options, &tag->object, FSCK_MSG_MISSING_TYPE_ENTRY, "invalid format - expected 'type' line"); @@@ -924,66 -903,6 +926,66 @@@ static int fsck_tag(struct tag *tag, co return fsck_tag_buffer(tag, data, size, options); } +struct fsck_gitmodules_data { + struct object *obj; + struct fsck_options *options; + int ret; +}; + +static int fsck_gitmodules_fn(const char *var, const char *value, void *vdata) +{ + struct fsck_gitmodules_data *data = vdata; + const char *subsection, *key; + int subsection_len; + char *name; + + if (parse_config_key(var, "submodule", &subsection, &subsection_len, &key) < 0 || + !subsection) + return 0; + + name = xmemdupz(subsection, subsection_len); + if (check_submodule_name(name) < 0) + data->ret |= report(data->options, data->obj, + FSCK_MSG_GITMODULES_NAME, + "disallowed submodule name: %s", + name); + free(name); + + return 0; +} + +static int fsck_blob(struct blob *blob, const char *buf, + unsigned long size, struct fsck_options *options) +{ + struct fsck_gitmodules_data data; + + if (!oidset_contains(&gitmodules_found, &blob->object.oid)) + return 0; + oidset_insert(&gitmodules_done, &blob->object.oid); + + if (!buf) { + /* + * A missing buffer here is a sign that the caller found the + * blob too gigantic to load into memory. Let's just consider + * that an error. + */ + return report(options, &blob->object, + FSCK_MSG_GITMODULES_PARSE, + ".gitmodules too large to parse"); + } + + data.obj = &blob->object; + data.options = options; + data.ret = 0; + if (git_config_from_mem(fsck_gitmodules_fn, CONFIG_ORIGIN_BLOB, + ".gitmodules", buf, size, &data)) + data.ret |= report(options, &blob->object, + FSCK_MSG_GITMODULES_PARSE, + "could not parse gitmodules blob"); + + return data.ret; +} + int fsck_object(struct object *obj, void *data, unsigned long size, struct fsck_options *options) { @@@ -991,7 -910,7 +993,7 @@@ return report(options, obj, FSCK_MSG_BAD_OBJECT_SHA1, "no valid object to fsck"); if (obj->type == OBJ_BLOB) - return 0; + return fsck_blob((struct blob *)obj, data, size, options); if (obj->type == OBJ_TREE) return fsck_tree((struct tree *) obj, options); if (obj->type == OBJ_COMMIT) @@@ -1015,52 -934,3 +1017,52 @@@ int fsck_error_function(struct fsck_opt error("object %s: %s", describe_object(o, obj), message); return 1; } + +int fsck_finish(struct fsck_options *options) +{ + int ret = 0; + struct oidset_iter iter; + const struct object_id *oid; + + oidset_iter_init(&gitmodules_found, &iter); + while ((oid = oidset_iter_next(&iter))) { + struct blob *blob; + enum object_type type; + unsigned long size; + char *buf; + + if (oidset_contains(&gitmodules_done, oid)) + continue; + + blob = lookup_blob(oid); + if (!blob) { + ret |= report(options, &blob->object, + FSCK_MSG_GITMODULES_BLOB, + "non-blob found at .gitmodules"); + continue; + } + + buf = read_object_file(oid, &type, &size); + if (!buf) { + if (is_promisor_object(&blob->object.oid)) + continue; + ret |= report(options, &blob->object, + FSCK_MSG_GITMODULES_MISSING, + "unable to read .gitmodules blob"); + continue; + } + + if (type == OBJ_BLOB) + ret |= fsck_blob(blob, buf, size, options); + else + ret |= report(options, &blob->object, + FSCK_MSG_GITMODULES_BLOB, + "non-blob found at .gitmodules"); + free(buf); + } + + + oidset_clear(&gitmodules_found); + oidset_clear(&gitmodules_done); + return ret; +} diff --combined git-rebase--interactive.sh index 2f4941d0fc,cc873d630d..0c92ac00fa --- a/git-rebase--interactive.sh +++ b/git-rebase--interactive.sh @@@ -81,6 -81,8 +81,8 @@@ rewritten_pending="$state_dir"/rewritte # and leaves CR at the end instead. cr=$(printf "\015") + empty_tree=$(git hash-object -t tree /dev/null) + strategy_args=${strategy:+--strategy=$strategy} test -n "$strategy_opts" && eval ' @@@ -155,19 -157,13 +157,19 @@@ reschedule_last_action () append_todo_help () { gettext " Commands: -p, pick = use commit -r, reword = use commit, but edit the commit message -e, edit = use commit, but stop for amending -s, squash = use commit, but meld into previous commit -f, fixup = like \"squash\", but discard this commit's log message -x, exec = run command (the rest of the line) using shell -d, drop = remove commit +p, pick = use commit +r, reword = use commit, but edit the commit message +e, edit = use commit, but stop for amending +s, squash = use commit, but meld into previous commit +f, fixup = like \"squash\", but discard this commit's log message +x, exec = run command (the rest of the line) using shell +d, drop = remove commit +l, label