From: Junio C Hamano Date: Tue, 20 Mar 2018 21:22:50 +0000 (-0700) Subject: Merge branch 'rj/warning-uninitialized-fix' into next X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/9ac9d02b0bb5a12c247f9cbeaa8c30b8aed3f167?hp=-c Merge branch 'rj/warning-uninitialized-fix' into next Compilation fix. * rj/warning-uninitialized-fix: read-cache: fix an -Wmaybe-uninitialized warning -Wuninitialized: remove some 'init-self' workarounds --- 9ac9d02b0bb5a12c247f9cbeaa8c30b8aed3f167 diff --combined builtin/rev-list.c index 2fd72c0be5,fbfc62de41..fadd3ec14c --- a/builtin/rev-list.c +++ b/builtin/rev-list.c @@@ -15,7 -15,6 +15,7 @@@ #include "progress.h" #include "reflog-walk.h" #include "oidset.h" +#include "packfile.h" static const char rev_list_usage[] = "git rev-list [OPTION] ... [ -- paths... ]\n" @@@ -68,7 -67,6 +68,7 @@@ enum missing_action MA_ERROR = 0, /* fail if any missing objects are encountered */ MA_ALLOW_ANY, /* silently allow ALL missing objects */ MA_PRINT, /* print ALL missing objects in special section */ + MA_ALLOW_PROMISOR, /* silently allow all missing PROMISOR objects */ }; static enum missing_action arg_missing_action; @@@ -108,7 -106,7 +108,7 @@@ static void show_commit(struct commit * if (!revs->graph) fputs(get_revision_mark(revs, commit), stdout); if (revs->abbrev_commit && revs->abbrev) - fputs(find_unique_abbrev(commit->object.oid.hash, revs->abbrev), + fputs(find_unique_abbrev(&commit->object.oid, revs->abbrev), stdout); else fputs(oid_to_hex(&commit->object.oid), stdout); @@@ -134,7 -132,7 +134,7 @@@ else putchar('\n'); - if (revs->verbose_header && get_cached_commit_buffer(commit, NULL)) { + if (revs->verbose_header) { struct strbuf buf = STRBUF_INIT; struct pretty_print_context ctx = {0}; ctx.abbrev = revs->abbrev; @@@ -199,12 -197,6 +199,12 @@@ static void finish_commit(struct commi static inline void finish_object__ma(struct object *obj) { + /* + * Whether or not we try to dynamically fetch missing objects + * from the server, we currently DO NOT have the object. We + * can either print, allow (ignore), or conditionally allow + * (ignore) them. + */ switch (arg_missing_action) { case MA_ERROR: die("missing blob object '%s'", oid_to_hex(&obj->oid)); @@@ -217,36 -209,25 +217,36 @@@ oidset_insert(&missing_objects, &obj->oid); return; + case MA_ALLOW_PROMISOR: + if (is_promisor_object(&obj->oid)) + return; + die("unexpected missing blob object '%s'", + oid_to_hex(&obj->oid)); + return; + default: BUG("unhandled missing_action"); return; } } -static void finish_object(struct object *obj, const char *name, void *cb_data) +static int finish_object(struct object *obj, const char *name, void *cb_data) { struct rev_list_info *info = cb_data; - if (obj->type == OBJ_BLOB && !has_object_file(&obj->oid)) + if (obj->type == OBJ_BLOB && !has_object_file(&obj->oid)) { finish_object__ma(obj); + return 1; + } if (info->revs->verify_objects && !obj->parsed && obj->type != OBJ_COMMIT) parse_object(&obj->oid); + return 0; } static void show_object(struct object *obj, const char *name, void *cb_data) { struct rev_list_info *info = cb_data; - finish_object(obj, name, cb_data); + if (finish_object(obj, name, cb_data)) + return; display_progress(progress, ++progress_counter); if (info->flags & REV_LIST_QUIET) return; @@@ -334,19 -315,11 +334,19 @@@ static inline int parse_missing_action_ if (!strcmp(value, "allow-any")) { arg_missing_action = MA_ALLOW_ANY; + fetch_if_missing = 0; return 1; } if (!strcmp(value, "print")) { arg_missing_action = MA_PRINT; + fetch_if_missing = 0; + return 1; + } + + if (!strcmp(value, "allow-promisor")) { + arg_missing_action = MA_ALLOW_PROMISOR; + fetch_if_missing = 0; return 1; } @@@ -371,35 -344,6 +371,35 @@@ int cmd_rev_list(int argc, const char * init_revisions(&revs, prefix); revs.abbrev = DEFAULT_ABBREV; revs.commit_format = CMIT_FMT_UNSPECIFIED; + + /* + * Scan the argument list before invoking setup_revisions(), so that we + * know if fetch_if_missing needs to be set to 0. + * + * "--exclude-promisor-objects" acts as a pre-filter on missing objects + * by not crossing the boundary from realized objects to promisor + * objects. + * + * Let "--missing" to conditionally set fetch_if_missing. + */ + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + if (!strcmp(arg, "--exclude-promisor-objects")) { + fetch_if_missing = 0; + revs.exclude_promisor_objects = 1; + break; + } + } + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + if (skip_prefix(arg, "--missing=", &arg)) { + if (revs.exclude_promisor_objects) + die(_("cannot combine --exclude-promisor-objects and --missing")); + if (parse_missing_action_value(arg)) + break; + } + } + argc = setup_revisions(argc, argv, &revs, NULL); memset(&info, 0, sizeof(info)); @@@ -460,7 -404,7 +460,7 @@@ continue; } if (!strcmp(arg, ("--no-" CL_ARG__FILTER))) { - list_objects_filter_release(&filter_options); + list_objects_filter_set_no_filter(&filter_options); continue; } if (!strcmp(arg, "--filter-print-omitted")) { @@@ -468,10 -412,9 +468,10 @@@ continue; } - if (skip_prefix(arg, "--missing=", &arg) && - parse_missing_action_value(arg)) - continue; + if (!strcmp(arg, "--exclude-promisor-objects")) + continue; /* already handled above */ + if (skip_prefix(arg, "--missing=", &arg)) + continue; /* already handled above */ usage(rev_list_usage); @@@ -536,7 -479,7 +536,7 @@@ mark_edges_uninteresting(&revs, show_edge); if (bisect_list) { - int reaches = reaches, all = all; + int reaches, all; find_bisection(&revs.commits, &reaches, &all, bisect_find_all); diff --combined fast-import.c index b300e4416d,1f01a22055..a2e8b1d763 --- a/fast-import.c +++ b/fast-import.c @@@ -316,7 -316,7 +316,7 @@@ static struct atom_str **atom_table /* The .pack file being generated */ static struct pack_idx_option pack_idx_opts; static unsigned int pack_id; -static struct sha1file *pack_file; +static struct hashfile *pack_file; static struct packed_git *pack_data; static struct packed_git **all_packs; static off_t pack_size; @@@ -905,12 -905,12 +905,12 @@@ static void start_packfile(void p->pack_fd = pack_fd; p->do_not_close = 1; - pack_file = sha1fd(pack_fd, p->pack_name); + pack_file = hashfd(pack_fd, p->pack_name); hdr.hdr_signature = htonl(PACK_SIGNATURE); hdr.hdr_version = htonl(2); hdr.hdr_entries = 0; - sha1write(pack_file, &hdr, sizeof(hdr)); + hashwrite(pack_file, &hdr, sizeof(hdr)); pack_data = p; pack_size = sizeof(hdr); @@@ -1016,7 -1016,7 +1016,7 @@@ static void end_packfile(void struct tag *t; close_pack_windows(pack_data); - sha1close(pack_file, cur_pack_oid.hash, 0); + hashclose(pack_file, cur_pack_oid.hash, 0); fixup_pack_header_footer(pack_data->pack_fd, pack_data->sha1, pack_data->pack_name, object_count, cur_pack_oid.hash, pack_size); @@@ -1092,15 -1092,15 +1092,15 @@@ static int store_object unsigned char hdr[96]; struct object_id oid; unsigned long hdrlen, deltalen; - git_SHA_CTX c; + git_hash_ctx c; git_zstream s; hdrlen = xsnprintf((char *)hdr, sizeof(hdr), "%s %lu", - typename(type), (unsigned long)dat->len) + 1; - git_SHA1_Init(&c); - git_SHA1_Update(&c, hdr, hdrlen); - git_SHA1_Update(&c, dat->buf, dat->len); - git_SHA1_Final(oid.hash, &c); + type_name(type), (unsigned long)dat->len) + 1; + the_hash_algo->init_fn(&c); + the_hash_algo->update_fn(&c, hdr, hdrlen); + the_hash_algo->update_fn(&c, dat->buf, dat->len); + the_hash_algo->final_fn(oid.hash, &c); if (oidout) oidcpy(oidout, &oid); @@@ -1118,13 -1118,11 +1118,13 @@@ return 1; } - if (last && last->data.buf && last->depth < max_depth && dat->len > 20) { + if (last && last->data.buf && last->depth < max_depth + && dat->len > the_hash_algo->rawsz) { + delta_count_attempts_by_type[type]++; delta = diff_delta(last->data.buf, last->data.len, dat->buf, dat->len, - &deltalen, dat->len - 20); + &deltalen, dat->len - the_hash_algo->rawsz); } else delta = NULL; @@@ -1182,23 -1180,23 +1182,23 @@@ hdrlen = encode_in_pack_object_header(hdr, sizeof(hdr), OBJ_OFS_DELTA, deltalen); - sha1write(pack_file, hdr, hdrlen); + hashwrite(pack_file, hdr, hdrlen); pack_size += hdrlen; hdr[pos] = ofs & 127; while (ofs >>= 7) hdr[--pos] = 128 | (--ofs & 127); - sha1write(pack_file, hdr + pos, sizeof(hdr) - pos); + hashwrite(pack_file, hdr + pos, sizeof(hdr) - pos); pack_size += sizeof(hdr) - pos; } else { e->depth = 0; hdrlen = encode_in_pack_object_header(hdr, sizeof(hdr), type, dat->len); - sha1write(pack_file, hdr, hdrlen); + hashwrite(pack_file, hdr, hdrlen); pack_size += hdrlen; } - sha1write(pack_file, out, s.total_out); + hashwrite(pack_file, out, s.total_out); pack_size += s.total_out; e->idx.crc32 = crc32_end(pack_file); @@@ -1217,9 -1215,9 +1217,9 @@@ return 0; } -static void truncate_pack(struct sha1file_checkpoint *checkpoint) +static void truncate_pack(struct hashfile_checkpoint *checkpoint) { - if (sha1file_truncate(pack_file, checkpoint)) + if (hashfile_truncate(pack_file, checkpoint)) die_errno("cannot truncate pack to skip duplicate"); pack_size = checkpoint->offset; } @@@ -1233,9 -1231,9 +1233,9 @@@ static void stream_blob(uintmax_t len, struct object_id oid; unsigned long hdrlen; off_t offset; - git_SHA_CTX c; + git_hash_ctx c; git_zstream s; - struct sha1file_checkpoint checkpoint; + struct hashfile_checkpoint checkpoint; int status = Z_OK; /* Determine if we should auto-checkpoint. */ @@@ -1243,13 -1241,13 +1243,13 @@@ || (pack_size + 60 + len) < pack_size) cycle_packfile(); - sha1file_checkpoint(pack_file, &checkpoint); + hashfile_checkpoint(pack_file, &checkpoint); offset = checkpoint.offset; hdrlen = xsnprintf((char *)out_buf, out_sz, "blob %" PRIuMAX, len) + 1; - git_SHA1_Init(&c); - git_SHA1_Update(&c, out_buf, hdrlen); + the_hash_algo->init_fn(&c); + the_hash_algo->update_fn(&c, out_buf, hdrlen); crc32_begin(pack_file); @@@ -1267,7 -1265,7 +1267,7 @@@ if (!n && feof(stdin)) die("EOF in data (%" PRIuMAX " bytes remaining)", len); - git_SHA1_Update(&c, in_buf, n); + the_hash_algo->update_fn(&c, in_buf, n); s.next_in = in_buf; s.avail_in = n; len -= n; @@@ -1277,7 -1275,7 +1277,7 @@@ if (!s.avail_out || status == Z_STREAM_END) { size_t n = s.next_out - out_buf; - sha1write(pack_file, out_buf, n); + hashwrite(pack_file, out_buf, n); pack_size += n; s.next_out = out_buf; s.avail_out = out_sz; @@@ -1293,7 -1291,7 +1293,7 @@@ } } git_deflate_end(&s); - git_SHA1_Final(oid.hash, &c); + the_hash_algo->final_fn(oid.hash, &c); if (oidout) oidcpy(oidout, &oid); @@@ -1352,25 -1350,25 +1352,25 @@@ static void *gfi_unpack_entry { enum object_type type; struct packed_git *p = all_packs[oe->pack_id]; - if (p == pack_data && p->pack_size < (pack_size + 20)) { + if (p == pack_data && p->pack_size < (pack_size + the_hash_algo->rawsz)) { /* The object is stored in the packfile we are writing to * and we have modified it since the last time we scanned * back to read a previously written object. If an old - * window covered [p->pack_size, p->pack_size + 20) its + * window covered [p->pack_size, p->pack_size + rawsz) its * data is stale and is not valid. Closing all windows * and updating the packfile length ensures we can read * the newly written data. */ close_pack_windows(p); - sha1flush(pack_file); + hashflush(pack_file); - /* We have to offer 20 bytes additional on the end of + /* We have to offer rawsz bytes additional on the end of * the packfile as the core unpacker code assumes the * footer is present at the file end and must promise - * at least 20 bytes within any window it maps. But + * at least rawsz bytes within any window it maps. But * we don't actually create the footer here. */ - p->pack_size = pack_size + 20; + p->pack_size = pack_size + the_hash_algo->rawsz; } return unpack_entry(p, oe->idx.offset, &type, sizep); } @@@ -1412,7 -1410,7 +1412,7 @@@ static void load_tree(struct tree_entr die("Can't load tree %s", oid_to_hex(oid)); } else { enum object_type type; - buf = read_sha1_file(oid->hash, &type, &size); + buf = read_object_file(oid, &type, &size); if (!buf || type != OBJ_TREE) die("Can't load tree %s", oid_to_hex(oid)); } @@@ -1913,7 -1911,7 +1913,7 @@@ static void read_marks(void die("corrupt mark line: %s", line); e = find_object(&oid); if (!e) { - enum object_type type = sha1_object_info(oid.hash, NULL); + enum object_type type = oid_object_info(&oid, NULL); if (type < 0) die("object not found: %s", oid_to_hex(&oid)); e = insert_object(&oid); @@@ -2206,7 -2204,7 +2206,7 @@@ static void construct_path_with_fanout( unsigned char fanout, char *path) { unsigned int i = 0, j = 0; - if (fanout >= 20) + if (fanout >= the_hash_algo->rawsz) die("Too large fanout (%u)", fanout); while (fanout) { path[i++] = hex_sha1[j++]; @@@ -2214,8 -2212,8 +2214,8 @@@ path[i++] = '/'; fanout--; } - memcpy(path + i, hex_sha1 + j, GIT_SHA1_HEXSZ - j); - path[i + GIT_SHA1_HEXSZ - j] = '\0'; + memcpy(path + i, hex_sha1 + j, the_hash_algo->hexsz - j); + path[i + the_hash_algo->hexsz - j] = '\0'; } static uintmax_t do_change_note_fanout( @@@ -2423,7 -2421,7 +2423,7 @@@ static void file_change_m(const char *p else if (oe) { if (oe->type != OBJ_COMMIT) die("Not a commit (actually a %s): %s", - typename(oe->type), command_buf.buf); + type_name(oe->type), command_buf.buf); } /* * Accept the sha1 without checking; it expected to be in @@@ -2443,14 -2441,14 +2443,14 @@@ enum object_type expected = S_ISDIR(mode) ? OBJ_TREE: OBJ_BLOB; enum object_type type = oe ? oe->type : - sha1_object_info(oid.hash, NULL); + oid_object_info(&oid, NULL); if (type < 0) die("%s not found: %s", S_ISDIR(mode) ? "Tree" : "Blob", command_buf.buf); if (type != expected) die("Not a %s (actually a %s): %s", - typename(expected), typename(type), + type_name(expected), type_name(type), command_buf.buf); } @@@ -2583,9 -2581,8 +2583,9 @@@ static void note_change_n(const char *p oidcpy(&commit_oid, &commit_oe->idx.oid); } else if (!get_oid(p, &commit_oid)) { unsigned long size; - char *buf = read_object_with_reference(commit_oid.hash, - commit_type, &size, commit_oid.hash); + char *buf = read_object_with_reference(&commit_oid, + commit_type, &size, + &commit_oid); if (!buf || size < 46) die("Not a valid commit: %s", p); free(buf); @@@ -2602,14 -2599,14 +2602,14 @@@ } else if (oe) { if (oe->type != OBJ_BLOB) die("Not a blob (actually a %s): %s", - typename(oe->type), command_buf.buf); + type_name(oe->type), command_buf.buf); } else if (!is_null_oid(&oid)) { - enum object_type type = sha1_object_info(oid.hash, NULL); + enum object_type type = oid_object_info(&oid, NULL); if (type < 0) die("Blob not found: %s", command_buf.buf); if (type != OBJ_BLOB) die("Not a blob (actually a %s): %s", - typename(type), command_buf.buf); + type_name(type), command_buf.buf); } construct_path_with_fanout(oid_to_hex(&commit_oid), *old_fanout, path); @@@ -2654,8 -2651,9 +2654,8 @@@ static void parse_from_existing(struct unsigned long size; char *buf; - buf = read_object_with_reference(b->oid.hash, - commit_type, &size, - b->oid.hash); + buf = read_object_with_reference(&b->oid, commit_type, &size, + &b->oid); parse_from_commit(b, buf, size); free(buf); } @@@ -2732,9 -2730,8 +2732,9 @@@ static struct hash_list *parse_merge(un oidcpy(&n->oid, &oe->idx.oid); } else if (!get_oid(from, &n->oid)) { unsigned long size; - char *buf = read_object_with_reference(n->oid.hash, - commit_type, &size, n->oid.hash); + char *buf = read_object_with_reference(&n->oid, + commit_type, + &size, &n->oid); if (!buf || size < 46) die("Not a valid commit: %s", from); free(buf); @@@ -2891,7 -2888,7 +2891,7 @@@ static void parse_new_tag(const char *a } else if (!get_oid(from, &oid)) { struct object_entry *oe = find_object(&oid); if (!oe) { - type = sha1_object_info(oid.hash, NULL); + type = oid_object_info(&oid, NULL); if (type < 0) die("Not a valid object: %s", from); } else @@@ -2917,7 -2914,7 +2917,7 @@@ "object %s\n" "type %s\n" "tag %s\n", - oid_to_hex(&oid), typename(type), t->name); + oid_to_hex(&oid), type_name(type), t->name); if (tagger) strbuf_addf(&new_data, "tagger %s\n", tagger); @@@ -2967,7 -2964,7 +2967,7 @@@ static void cat_blob(struct object_entr char *buf; if (!oe || oe->pack_id == MAX_PACK_ID) { - buf = read_sha1_file(oid->hash, &type, &size); + buf = read_object_file(oid, &type, &size); } else { type = oe->type; buf = gfi_unpack_entry(oe, &size); @@@ -2988,10 -2985,10 +2988,10 @@@ die("Can't read object %s", oid_to_hex(oid)); if (type != OBJ_BLOB) die("Object %s is a %s but a blob was expected.", - oid_to_hex(oid), typename(type)); + oid_to_hex(oid), type_name(type)); strbuf_reset(&line); strbuf_addf(&line, "%s %s %lu\n", oid_to_hex(oid), - typename(type), size); + type_name(type), size); cat_blob_write(line.buf, line.len); strbuf_release(&line); cat_blob_write(buf, size); @@@ -3006,7 -3003,7 +3006,7 @@@ static void parse_get_mark(const char *p) { - struct object_entry *oe = oe; + struct object_entry *oe; char output[GIT_MAX_HEXSZ + 2]; /* get-mark SP LF */ @@@ -3023,7 -3020,7 +3023,7 @@@ static void parse_cat_blob(const char *p) { - struct object_entry *oe = oe; + struct object_entry *oe; struct object_id oid; /* cat-blob SP LF */ @@@ -3049,7 -3046,7 +3049,7 @@@ static struct object_entry *dereference unsigned long size; char *buf = NULL; if (!oe) { - enum object_type type = sha1_object_info(oid->hash, NULL); + enum object_type type = oid_object_info(oid, NULL); if (type < 0) die("object not found: %s", oid_to_hex(oid)); /* cache it! */ @@@ -3072,7 -3069,7 +3072,7 @@@ buf = gfi_unpack_entry(oe, &size); } else { enum object_type unused; - buf = read_sha1_file(oid->hash, &unused, &size); + buf = read_object_file(oid, &unused, &size); } if (!buf) die("Can't load object %s", oid_to_hex(oid)); diff --combined merge-recursive.c index 408d30e300,7dad164692..9c05eb7f70 --- a/merge-recursive.c +++ b/merge-recursive.c @@@ -49,67 -49,6 +49,67 @@@ static unsigned int path_hash(const cha return ignore_case ? strihash(path) : strhash(path); } +static struct dir_rename_entry *dir_rename_find_entry(struct hashmap *hashmap, + char *dir) +{ + struct dir_rename_entry key; + + if (dir == NULL) + return NULL; + hashmap_entry_init(&key, strhash(dir)); + key.dir = dir; + return hashmap_get(hashmap, &key, NULL); +} + +static int dir_rename_cmp(const void *unused_cmp_data, + const void *entry, + const void *entry_or_key, + const void *unused_keydata) +{ + const struct dir_rename_entry *e1 = entry; + const struct dir_rename_entry *e2 = entry_or_key; + + return strcmp(e1->dir, e2->dir); +} + +static void dir_rename_init(struct hashmap *map) +{ + hashmap_init(map, dir_rename_cmp, NULL, 0); +} + +static void dir_rename_entry_init(struct dir_rename_entry *entry, + char *directory) +{ + hashmap_entry_init(entry, strhash(directory)); + entry->dir = directory; + entry->non_unique_new_dir = 0; + strbuf_init(&entry->new_dir, 0); + string_list_init(&entry->possible_new_dirs, 0); +} + +static struct collision_entry *collision_find_entry(struct hashmap *hashmap, + char *target_file) +{ + struct collision_entry key; + + hashmap_entry_init(&key, strhash(target_file)); + key.target_file = target_file; + return hashmap_get(hashmap, &key, NULL); +} + +static int collision_cmp(void *unused_cmp_data, + const struct collision_entry *e1, + const struct collision_entry *e2, + const void *unused_keydata) +{ + return strcmp(e1->target_file, e2->target_file); +} + +static void collision_init(struct hashmap *map) +{ + hashmap_init(map, (hashmap_cmp_fn) collision_cmp, NULL, 0); +} + static void flush_output(struct merge_options *o) { if (o->buffer_output < 2 && o->obuf.len) { @@@ -180,7 -119,6 +180,7 @@@ static int oid_eq(const struct object_i enum rename_type { RENAME_NORMAL = 0, + RENAME_DIR, RENAME_DELETE, RENAME_ONE_FILE_TO_ONE, RENAME_ONE_FILE_TO_TWO, @@@ -290,7 -228,7 +290,7 @@@ static void output_commit_title(struct strbuf_addf(&o->obuf, "virtual %s\n", merge_remote_util(commit)->name); else { - strbuf_add_unique_abbrev(&o->obuf, commit->object.oid.hash, + strbuf_add_unique_abbrev(&o->obuf, &commit->object.oid, DEFAULT_ABBREV); strbuf_addch(&o->obuf, ' '); if (parse_commit(commit) != 0) @@@ -337,37 -275,32 +337,37 @@@ static void init_tree_desc_from_tree(st init_tree_desc(desc, tree->buffer, tree->size); } -static int git_merge_trees(int index_only, +static int git_merge_trees(struct merge_options *o, struct tree *common, struct tree *head, struct tree *merge) { int rc; struct tree_desc t[3]; - struct unpack_trees_options opts; - memset(&opts, 0, sizeof(opts)); - if (index_only) - opts.index_only = 1; + memset(&o->unpack_opts, 0, sizeof(o->unpack_opts)); + if (o->call_depth) + o->unpack_opts.index_only = 1; else - opts.update = 1; - opts.merge = 1; - opts.head_idx = 2; - opts.fn = threeway_merge; - opts.src_index = &the_index; - opts.dst_index = &the_index; - setup_unpack_trees_porcelain(&opts, "merge"); + o->unpack_opts.update = 1; + o->unpack_opts.merge = 1; + o->unpack_opts.head_idx = 2; + o->unpack_opts.fn = threeway_merge; + o->unpack_opts.src_index = &the_index; + o->unpack_opts.dst_index = &the_index; + setup_unpack_trees_porcelain(&o->unpack_opts, "merge"); init_tree_desc_from_tree(t+0, common); init_tree_desc_from_tree(t+1, head); init_tree_desc_from_tree(t+2, merge); - rc = unpack_trees(3, t, &opts); + rc = unpack_trees(3, t, &o->unpack_opts); + /* + * unpack_trees NULLifies src_index, but it's used in verify_uptodate, + * so set to the new index which will usually have modification + * timestamp info copied over. + */ + o->unpack_opts.src_index = &the_index; cache_tree_free(&active_cache_tree); return rc; } @@@ -402,7 -335,7 +402,7 @@@ struct tree *write_tree_from_memory(str return result; } -static int save_files_dirs(const unsigned char *sha1, +static int save_files_dirs(const struct object_id *oid, struct strbuf *base, const char *path, unsigned int mode, int stage, void *context) { @@@ -427,21 -360,6 +427,21 @@@ static void get_files_dirs(struct merge read_tree_recursive(tree, "", 0, 0, &match_all, save_files_dirs, o); } +static int get_tree_entry_if_blob(struct tree *tree, + const char *path, + struct object_id *hashy, + unsigned int *mode_o) +{ + int ret; + + ret = get_tree_entry(&tree->object.oid, path, hashy, mode_o); + if (S_ISDIR(*mode_o)) { + oidcpy(hashy, &null_oid); + *mode_o = 0; + } + return ret; +} + /* * Returns an index_entry instance which doesn't have to correspond to * a real cache entry in Git's index. @@@ -452,12 -370,12 +452,12 @@@ static struct stage_data *insert_stage_ { struct string_list_item *item; struct stage_data *e = xcalloc(1, sizeof(struct stage_data)); - get_tree_entry(o->object.oid.hash, path, - e->stages[1].oid.hash, &e->stages[1].mode); - get_tree_entry(a->object.oid.hash, path, - e->stages[2].oid.hash, &e->stages[2].mode); - get_tree_entry(b->object.oid.hash, path, - e->stages[3].oid.hash, &e->stages[3].mode); + get_tree_entry_if_blob(o, path, + &e->stages[1].oid, &e->stages[1].mode); + get_tree_entry_if_blob(a, path, + &e->stages[2].oid, &e->stages[2].mode); + get_tree_entry_if_blob(b, path, + &e->stages[3].oid, &e->stages[3].mode); item = string_list_insert(entries, path); item->util = e; return e; @@@ -595,31 -513,80 +595,31 @@@ static void record_df_conflict_files(st struct rename { struct diff_filepair *pair; + /* + * Purpose of src_entry and dst_entry: + * + * If 'before' is renamed to 'after' then src_entry will contain + * the versions of 'before' from the merge_base, HEAD, and MERGE in + * stages 1, 2, and 3; dst_entry will contain the respective + * versions of 'after' in corresponding locations. Thus, we have a + * total of six modes and oids, though some will be null. (Stage 0 + * is ignored; we're interested in handling conflicts.) + * + * Since we don't turn on break-rewrites by default, neither + * src_entry nor dst_entry can have all three of their stages have + * non-null oids, meaning at most four of the six will be non-null. + * Also, since this is a rename, both src_entry and dst_entry will + * have at least one non-null oid, meaning at least two will be + * non-null. Of the six oids, a typical rename will have three be + * non-null. Only two implies a rename/delete, and four implies a + * rename/add. + */ struct stage_data *src_entry; struct stage_data *dst_entry; + unsigned add_turned_into_rename:1; unsigned processed:1; }; -/* - * Get information of all renames which occurred between 'o_tree' and - * 'tree'. We need the three trees in the merge ('o_tree', 'a_tree' and - * 'b_tree') to be able to associate the correct cache entries with - * the rename information. 'tree' is always equal to either a_tree or b_tree. - */ -static struct string_list *get_renames(struct merge_options *o, - struct tree *tree, - struct tree *o_tree, - struct tree *a_tree, - struct tree *b_tree, - struct string_list *entries) -{ - int i; - struct string_list *renames; - struct diff_options opts; - - renames = xcalloc(1, sizeof(struct string_list)); - if (!o->detect_rename) - return renames; - - diff_setup(&opts); - opts.flags.recursive = 1; - opts.flags.rename_empty = 0; - opts.detect_rename = DIFF_DETECT_RENAME; - opts.rename_limit = o->merge_rename_limit >= 0 ? o->merge_rename_limit : - o->diff_rename_limit >= 0 ? o->diff_rename_limit : - 1000; - opts.rename_score = o->rename_score; - opts.show_rename_progress = o->show_rename_progress; - opts.output_format = DIFF_FORMAT_NO_OUTPUT; - diff_setup_done(&opts); - diff_tree_oid(&o_tree->object.oid, &tree->object.oid, "", &opts); - diffcore_std(&opts); - if (opts.needed_rename_limit > o->needed_rename_limit) - o->needed_rename_limit = opts.needed_rename_limit; - for (i = 0; i < diff_queued_diff.nr; ++i) { - struct string_list_item *item; - struct rename *re; - struct diff_filepair *pair = diff_queued_diff.queue[i]; - if (pair->status != 'R') { - diff_free_filepair(pair); - continue; - } - re = xmalloc(sizeof(*re)); - re->processed = 0; - re->pair = pair; - item = string_list_lookup(entries, re->pair->one->path); - if (!item) - re->src_entry = insert_stage_data(re->pair->one->path, - o_tree, a_tree, b_tree, entries); - else - re->src_entry = item->util; - - item = string_list_lookup(entries, re->pair->two->path); - if (!item) - re->dst_entry = insert_stage_data(re->pair->two->path, - o_tree, a_tree, b_tree, entries); - else - re->dst_entry = item->util; - item = string_list_insert(renames, pair->one->path); - item->util = re; - } - opts.output_format = DIFF_FORMAT_NO_OUTPUT; - diff_queued_diff.nr = 0; - diff_flush(&opts); - return renames; -} - static int update_stages(struct merge_options *opt, const char *path, const struct diff_filespec *o, const struct diff_filespec *a, @@@ -651,27 -618,6 +651,27 @@@ return 0; } +static int update_stages_for_stage_data(struct merge_options *opt, + const char *path, + const struct stage_data *stage_data) +{ + struct diff_filespec o, a, b; + + o.mode = stage_data->stages[1].mode; + oidcpy(&o.oid, &stage_data->stages[1].oid); + + a.mode = stage_data->stages[2].mode; + oidcpy(&a.oid, &stage_data->stages[2].oid); + + b.mode = stage_data->stages[3].mode; + oidcpy(&b.oid, &stage_data->stages[3].oid); + + return update_stages(opt, path, + is_null_oid(&o.oid) ? NULL : &o, + is_null_oid(&a.oid) ? NULL : &a, + is_null_oid(&b.oid) ? NULL : &b); +} + static void update_entry(struct stage_data *entry, struct diff_filespec *o, struct diff_filespec *a, @@@ -800,20 -746,6 +800,20 @@@ static int would_lose_untracked(const c return !was_tracked(path) && file_exists(path); } +static int was_dirty(struct merge_options *o, const char *path) +{ + struct cache_entry *ce; + int dirty = 1; + + if (o->call_depth || !was_tracked(path)) + return !dirty; + + ce = cache_file_exists(path, strlen(path), ignore_case); + dirty = (ce->ce_stat_data.sd_mtime.sec > 0 && + verify_uptodate(ce, &o->unpack_opts) != 0); + return dirty; +} + static int make_room_for_path(struct merge_options *o, const char *path) { int status, i; @@@ -891,7 -823,7 +891,7 @@@ static int update_file_flags(struct mer goto update_index; } - buf = read_sha1_file(oid->hash, &type, &size); + buf = read_object_file(oid, &type, &size); if (!buf) return err(o, _("cannot read object %s '%s'"), oid_to_hex(oid), path); if (type != OBJ_BLOB) { @@@ -1077,9 -1009,8 +1077,9 @@@ static int merge_file_1(struct merge_op if ((merge_status < 0) || !result_buf.ptr) ret = err(o, _("Failed to execute internal merge")); - if (!ret && write_sha1_file(result_buf.ptr, result_buf.size, - blob_type, result->oid.hash)) + if (!ret && + write_object_file(result_buf.ptr, result_buf.size, + blob_type, &result->oid)) ret = err(o, _("Unable to add %s to database"), a->path); @@@ -1163,38 -1094,6 +1163,38 @@@ static int merge_file_one(struct merge_ return merge_file_1(o, &one, &a, &b, branch1, branch2, mfi); } +static int conflict_rename_dir(struct merge_options *o, + struct diff_filepair *pair, + const char *rename_branch, + const char *other_branch) +{ + const struct diff_filespec *dest = pair->two; + + if (!o->call_depth && would_lose_untracked(dest->path)) { + char *alt_path = unique_path(o, dest->path, rename_branch); + + output(o, 1, _("Error: Refusing to lose untracked file at %s; " + "writing to %s instead."), + dest->path, alt_path); + /* + * Write the file in worktree at alt_path, but not in the + * index. Instead, write to dest->path for the index but + * only at the higher appropriate stage. + */ + if (update_file(o, 0, &dest->oid, dest->mode, alt_path)) + return -1; + free(alt_path); + return update_stages(o, dest->path, NULL, + rename_branch == o->branch1 ? dest : NULL, + rename_branch == o->branch1 ? NULL : dest); + } + + /* Update dest->path both in index and in worktree */ + if (update_file(o, 1, &dest->oid, dest->mode, dest->path)) + return -1; + return 0; +} + static int handle_change_delete(struct merge_options *o, const char *path, const char *old_path, const struct object_id *o_oid, int o_mode, @@@ -1208,8 -1107,7 +1208,8 @@@ const char *update_path = path; int ret = 0; - if (dir_in_way(path, !o->call_depth, 0)) { + if (dir_in_way(path, !o->call_depth, 0) || + (!o->call_depth && would_lose_untracked(path))) { update_path = alt_path = unique_path(o, path, change_branch); } @@@ -1324,34 -1222,17 +1324,34 @@@ static int handle_file(struct merge_opt add = filespec_from_entry(&other, dst_entry, stage ^ 1); if (add) { + int ren_src_was_dirty = was_dirty(o, rename->path); char *add_name = unique_path(o, rename->path, other_branch); if (update_file(o, 0, &add->oid, add->mode, add_name)) return -1; - remove_file(o, 0, rename->path, 0); + if (ren_src_was_dirty) { + output(o, 1, _("Refusing to lose dirty file at %s"), + rename->path); + } + /* + * Because the double negatives somehow keep confusing me... + * 1) update_wd iff !ren_src_was_dirty. + * 2) no_wd iff !update_wd + * 3) so, no_wd == !!ren_src_was_dirty == ren_src_was_dirty + */ + remove_file(o, 0, rename->path, ren_src_was_dirty); dst_name = unique_path(o, rename->path, cur_branch); } else { if (dir_in_way(rename->path, !o->call_depth, 0)) { dst_name = unique_path(o, rename->path, cur_branch); output(o, 1, _("%s is a directory in %s adding as %s instead"), rename->path, other_branch, dst_name); + } else if (!o->call_depth && + would_lose_untracked(rename->path)) { + dst_name = unique_path(o, rename->path, cur_branch); + output(o, 1, _("Refusing to lose untracked file at %s; " + "adding as %s instead"), + rename->path, dst_name); } } if ((ret = update_file(o, 0, &rename->oid, rename->mode, dst_name))) @@@ -1477,43 -1358,11 +1477,43 @@@ static int conflict_rename_rename_2to1( char *new_path2 = unique_path(o, path, ci->branch2); output(o, 1, _("Renaming %s to %s and %s to %s instead"), a->path, new_path1, b->path, new_path2); - remove_file(o, 0, path, 0); + if (was_dirty(o, path)) + output(o, 1, _("Refusing to lose dirty file at %s"), + path); + else if (would_lose_untracked(path)) + /* + * Only way we get here is if both renames were from + * a directory rename AND user had an untracked file + * at the location where both files end up after the + * two directory renames. See testcase 10d of t6043. + */ + output(o, 1, _("Refusing to lose untracked file at " + "%s, even though it's in the way."), + path); + else + remove_file(o, 0, path, 0); ret = update_file(o, 0, &mfi_c1.oid, mfi_c1.mode, new_path1); if (!ret) ret = update_file(o, 0, &mfi_c2.oid, mfi_c2.mode, new_path2); + /* + * unpack_trees() actually populates the index for us for + * "normal" rename/rename(2to1) situtations so that the + * correct entries are at the higher stages, which would + * make the call below to update_stages_for_stage_data + * unnecessary. However, if either of the renames came + * from a directory rename, then unpack_trees() will not + * have gotten the right data loaded into the index, so we + * need to do so now. (While it'd be tempting to move this + * call to update_stages_for_stage_data() to + * apply_directory_rename_modifications(), that would break + * our intermediate calls to would_lose_untracked() since + * those rely on the current in-memory index. See also the + * big "NOTE" in update_stages()). + */ + if (update_stages_for_stage_data(o, path, ci->dst_entry1)) + ret = -1; + free(new_path2); free(new_path1); } @@@ -1521,754 -1370,6 +1521,754 @@@ return ret; } +/* + * Get the diff_filepairs changed between o_tree and tree. + */ +static struct diff_queue_struct *get_diffpairs(struct merge_options *o, + struct tree *o_tree, + struct tree *tree) +{ + struct diff_queue_struct *ret; + struct diff_options opts; + + diff_setup(&opts); + opts.flags.recursive = 1; + opts.flags.rename_empty = 0; + opts.detect_rename = DIFF_DETECT_RENAME; + opts.rename_limit = o->merge_rename_limit >= 0 ? o->merge_rename_limit : + o->diff_rename_limit >= 0 ? o->diff_rename_limit : + 1000; + opts.rename_score = o->rename_score; + opts.show_rename_progress = o->show_rename_progress; + opts.output_format = DIFF_FORMAT_NO_OUTPUT; + diff_setup_done(&opts); + diff_tree_oid(&o_tree->object.oid, &tree->object.oid, "", &opts); + diffcore_std(&opts); + if (opts.needed_rename_limit > o->needed_rename_limit) + o->needed_rename_limit = opts.needed_rename_limit; + + ret = xmalloc(sizeof(*ret)); + *ret = diff_queued_diff; + + opts.output_format = DIFF_FORMAT_NO_OUTPUT; + diff_queued_diff.nr = 0; + diff_queued_diff.queue = NULL; + diff_flush(&opts); + return ret; +} + +static int tree_has_path(struct tree *tree, const char *path) +{ + struct object_id hashy; + unsigned int mode_o; + + return !get_tree_entry(&tree->object.oid, path, + &hashy, &mode_o); +} + +/* + * Return a new string that replaces the beginning portion (which matches + * entry->dir), with entry->new_dir. In perl-speak: + * new_path_name = (old_path =~ s/entry->dir/entry->new_dir/); + * NOTE: + * Caller must ensure that old_path starts with entry->dir + '/'. + */ +static char *apply_dir_rename(struct dir_rename_entry *entry, + const char *old_path) +{ + struct strbuf new_path = STRBUF_INIT; + int oldlen, newlen; + + if (entry->non_unique_new_dir) + return NULL; + + oldlen = strlen(entry->dir); + newlen = entry->new_dir.len + (strlen(old_path) - oldlen) + 1; + strbuf_grow(&new_path, newlen); + strbuf_addbuf(&new_path, &entry->new_dir); + strbuf_addstr(&new_path, &old_path[oldlen]); + + return strbuf_detach(&new_path, NULL); +} + +static void get_renamed_dir_portion(const char *old_path, const char *new_path, + char **old_dir, char **new_dir) +{ + char *end_of_old, *end_of_new; + int old_len, new_len; + + *old_dir = NULL; + *new_dir = NULL; + + /* + * For + * "a/b/c/d/e/foo.c" -> "a/b/some/thing/else/e/foo.c" + * the "e/foo.c" part is the same, we just want to know that + * "a/b/c/d" was renamed to "a/b/some/thing/else" + * so, for this example, this function returns "a/b/c/d" in + * *old_dir and "a/b/some/thing/else" in *new_dir. + * + * Also, if the basename of the file changed, we don't care. We + * want to know which portion of the directory, if any, changed. + */ + end_of_old = strrchr(old_path, '/'); + end_of_new = strrchr(new_path, '/'); + + if (end_of_old == NULL || end_of_new == NULL) + return; + while (*--end_of_new == *--end_of_old && + end_of_old != old_path && + end_of_new != new_path) + ; /* Do nothing; all in the while loop */ + /* + * We've found the first non-matching character in the directory + * paths. That means the current directory we were comparing + * represents the rename. Move end_of_old and end_of_new back + * to the full directory name. + */ + if (*end_of_old == '/') + end_of_old++; + if (*end_of_old != '/') + end_of_new++; + end_of_old = strchr(end_of_old, '/'); + end_of_new = strchr(end_of_new, '/'); + + /* + * It may have been the case that old_path and new_path were the same + * directory all along. Don't claim a rename if they're the same. + */ + old_len = end_of_old - old_path; + new_len = end_of_new - new_path; + + if (old_len != new_len || strncmp(old_path, new_path, old_len)) { + *old_dir = xstrndup(old_path, old_len); + *new_dir = xstrndup(new_path, new_len); + } +} + +static void remove_hashmap_entries(struct hashmap *dir_renames, + struct string_list *items_to_remove) +{ + int i; + struct dir_rename_entry *entry; + + for (i = 0; i < items_to_remove->nr; i++) { + entry = items_to_remove->items[i].util; + hashmap_remove(dir_renames, entry, NULL); + } + string_list_clear(items_to_remove, 0); +} + +/* + * See if there is a directory rename for path, and if there are any file + * level conflicts for the renamed location. If there is a rename and + * there are no conflicts, return the new name. Otherwise, return NULL. + */ +static char *handle_path_level_conflicts(struct merge_options *o, + const char *path, + struct dir_rename_entry *entry, + struct hashmap *collisions, + struct tree *tree) +{ + char *new_path = NULL; + struct collision_entry *collision_ent; + int clean = 1; + struct strbuf collision_paths = STRBUF_INIT; + + /* + * entry has the mapping of old directory name to new directory name + * that we want to apply to path. + */ + new_path = apply_dir_rename(entry, path); + + if (!new_path) { + /* This should only happen when entry->non_unique_new_dir set */ + if (!entry->non_unique_new_dir) + BUG("entry->non_unqiue_dir not set and !new_path"); + output(o, 1, _("CONFLICT (directory rename split): " + "Unclear where to place %s because directory " + "%s was renamed to multiple other directories, " + "with no destination getting a majority of the " + "files."), + path, entry->dir); + clean = 0; + return NULL; + } + + /* + * The caller needs to have ensured that it has pre-populated + * collisions with all paths that map to new_path. Do a quick check + * to ensure that's the case. + */ + collision_ent = collision_find_entry(collisions, new_path); + if (collision_ent == NULL) + BUG("collision_ent is NULL"); + + /* + * Check for one-sided add/add/.../add conflicts, i.e. + * where implicit renames from the other side doing + * directory rename(s) can affect this side of history + * to put multiple paths into the same location. Warn + * and bail on directory renames for such paths. + */ + if (collision_ent->reported_already) { + clean = 0; + } else if (tree_has_path(tree, new_path)) { + collision_ent->reported_already = 1; + strbuf_add_separated_string_list(&collision_paths, ", ", + &collision_ent->source_files); + output(o, 1, _("CONFLICT (implicit dir rename): Existing " + "file/dir at %s in the way of implicit " + "directory rename(s) putting the following " + "path(s) there: %s."), + new_path, collision_paths.buf); + clean = 0; + } else if (collision_ent->source_files.nr > 1) { + collision_ent->reported_already = 1; + strbuf_add_separated_string_list(&collision_paths, ", ", + &collision_ent->source_files); + output(o, 1, _("CONFLICT (implicit dir rename): Cannot map " + "more than one path to %s; implicit directory " + "renames tried to put these paths there: %s"), + new_path, collision_paths.buf); + clean = 0; + } + + /* Free memory we no longer need */ + strbuf_release(&collision_paths); + if (!clean && new_path) { + free(new_path); + return NULL; + } + + return new_path; +} + +/* + * There are a couple things we want to do at the directory level: + * 1. Check for both sides renaming to the same thing, in order to avoid + * implicit renaming of files that should be left in place. (See + * testcase 6b in t6043 for details.) + * 2. Prune directory renames if there are still files left in the + * the original directory. These represent a partial directory rename, + * i.e. a rename where only some of the files within the directory + * were renamed elsewhere. (Technically, this could be done earlier + * in get_directory_renames(), except that would prevent us from + * doing the previous check and thus failing testcase 6b.) + * 3. Check for rename/rename(1to2) conflicts (at the directory level). + * In the future, we could potentially record this info as well and + * omit reporting rename/rename(1to2) conflicts for each path within + * the affected directories, thus cleaning up the merge output. + * NOTE: We do NOT check for rename/rename(2to1) conflicts at the + * directory level, because merging directories is fine. If it + * causes conflicts for files within those merged directories, then + * that should be detected at the individual path level. + */ +static void handle_directory_level_conflicts(struct merge_options *o, + struct hashmap *dir_re_head, + struct tree *head, + struct hashmap *dir_re_merge, + struct tree *merge) +{ + struct hashmap_iter iter; + struct dir_rename_entry *head_ent; + struct dir_rename_entry *merge_ent; + + struct string_list remove_from_head = STRING_LIST_INIT_NODUP; + struct string_list remove_from_merge = STRING_LIST_INIT_NODUP; + + hashmap_iter_init(dir_re_head, &iter); + while ((head_ent = hashmap_iter_next(&iter))) { + merge_ent = dir_rename_find_entry(dir_re_merge, head_ent->dir); + if (merge_ent && + !head_ent->non_unique_new_dir && + !merge_ent->non_unique_new_dir && + !strbuf_cmp(&head_ent->new_dir, &merge_ent->new_dir)) { + /* 1. Renamed identically; remove it from both sides */ + string_list_append(&remove_from_head, + head_ent->dir)->util = head_ent; + strbuf_release(&head_ent->new_dir); + string_list_append(&remove_from_merge, + merge_ent->dir)->util = merge_ent; + strbuf_release(&merge_ent->new_dir); + } else if (tree_has_path(head, head_ent->dir)) { + /* 2. This wasn't a directory rename after all */ + string_list_append(&remove_from_head, + head_ent->dir)->util = head_ent; + strbuf_release(&head_ent->new_dir); + } + } + + remove_hashmap_entries(dir_re_head, &remove_from_head); + remove_hashmap_entries(dir_re_merge, &remove_from_merge); + + hashmap_iter_init(dir_re_merge, &iter); + while ((merge_ent = hashmap_iter_next(&iter))) { + head_ent = dir_rename_find_entry(dir_re_head, merge_ent->dir); + if (tree_has_path(merge, merge_ent->dir)) { + /* 2. This wasn't a directory rename after all */ + string_list_append(&remove_from_merge, + merge_ent->dir)->util = merge_ent; + } else if (head_ent && + !head_ent->non_unique_new_dir && + !merge_ent->non_unique_new_dir) { + /* 3. rename/rename(1to2) */ + /* + * We can assume it's not rename/rename(1to1) because + * that was case (1), already checked above. So we + * know that head_ent->new_dir and merge_ent->new_dir + * are different strings. + */ + output(o, 1, _("CONFLICT (rename/rename): " + "Rename directory %s->%s in %s. " + "Rename directory %s->%s in %s"), + head_ent->dir, head_ent->new_dir.buf, o->branch1, + head_ent->dir, merge_ent->new_dir.buf, o->branch2); + string_list_append(&remove_from_head, + head_ent->dir)->util = head_ent; + strbuf_release(&head_ent->new_dir); + string_list_append(&remove_from_merge, + merge_ent->dir)->util = merge_ent; + strbuf_release(&merge_ent->new_dir); + } + } + + remove_hashmap_entries(dir_re_head, &remove_from_head); + remove_hashmap_entries(dir_re_merge, &remove_from_merge); +} + +static struct hashmap *get_directory_renames(struct diff_queue_struct *pairs, + struct tree *tree) +{ + struct hashmap *dir_renames; + struct hashmap_iter iter; + struct dir_rename_entry *entry; + int i; + + /* + * Typically, we think of a directory rename as all files from a + * certain directory being moved to a target directory. However, + * what if someone first moved two files from the original + * directory in one commit, and then renamed the directory + * somewhere else in a later commit? At merge time, we just know + * that files from the original directory went to two different + * places, and that the bulk of them ended up in the same place. + * We want each directory rename to represent where the bulk of the + * files from that directory end up; this function exists to find + * where the bulk of the files went. + * + * The first loop below simply iterates through the list of file + * renames, finding out how often each directory rename pair + * possibility occurs. + */ + dir_renames = xmalloc(sizeof(struct hashmap)); + dir_rename_init(dir_renames); + for (i = 0; i < pairs->nr; ++i) { + struct string_list_item *item; + int *count; + struct diff_filepair *pair = pairs->queue[i]; + char *old_dir, *new_dir; + + /* File not part of directory rename if it wasn't renamed */ + if (pair->status != 'R') + continue; + + get_renamed_dir_portion(pair->one->path, pair->two->path, + &old_dir, &new_dir); + if (!old_dir) + /* Directory didn't change at all; ignore this one. */ + continue; + + entry = dir_rename_find_entry(dir_renames, old_dir); + if (!entry) { + entry = xmalloc(sizeof(struct dir_rename_entry)); + dir_rename_entry_init(entry, old_dir); + hashmap_put(dir_renames, entry); + } else { + free(old_dir); + } + item = string_list_lookup(&entry->possible_new_dirs, new_dir); + if (!item) { + item = string_list_insert(&entry->possible_new_dirs, + new_dir); + item->util = xcalloc(1, sizeof(int)); + } else { + free(new_dir); + } + count = item->util; + *count += 1; + } + + /* + * For each directory with files moved out of it, we find out which + * target directory received the most files so we can declare it to + * be the "winning" target location for the directory rename. This + * winner gets recorded in new_dir. If there is no winner + * (multiple target directories received the same number of files), + * we set non_unique_new_dir. Once we've determined the winner (or + * that there is no winner), we no longer need possible_new_dirs. + */ + hashmap_iter_init(dir_renames, &iter); + while ((entry = hashmap_iter_next(&iter))) { + int max = 0; + int bad_max = 0; + char *best = NULL; + + for (i = 0; i < entry->possible_new_dirs.nr; i++) { + int *count = entry->possible_new_dirs.items[i].util; + + if (*count == max) + bad_max = max; + else if (*count > max) { + max = *count; + best = entry->possible_new_dirs.items[i].string; + } + } + if (bad_max == max) + entry->non_unique_new_dir = 1; + else { + assert(entry->new_dir.len == 0); + strbuf_addstr(&entry->new_dir, best); + } + /* + * The relevant directory sub-portion of the original full + * filepaths were xstrndup'ed before inserting into + * possible_new_dirs, and instead of manually iterating the + * list and free'ing each, just lie and tell + * possible_new_dirs that it did the strdup'ing so that it + * will free them for us. + */ + entry->possible_new_dirs.strdup_strings = 1; + string_list_clear(&entry->possible_new_dirs, 1); + } + + return dir_renames; +} + +static struct dir_rename_entry *check_dir_renamed(const char *path, + struct hashmap *dir_renames) +{ + char temp[PATH_MAX]; + char *end; + struct dir_rename_entry *entry; + + strcpy(temp, path); + while ((end = strrchr(temp, '/'))) { + *end = '\0'; + entry = dir_rename_find_entry(dir_renames, temp); + if (entry) + return entry; + } + return NULL; +} + +static void compute_collisions(struct hashmap *collisions, + struct hashmap *dir_renames, + struct diff_queue_struct *pairs) +{ + int i; + + /* + * Multiple files can be mapped to the same path due to directory + * renames done by the other side of history. Since that other + * side of history could have merged multiple directories into one, + * if our side of history added the same file basename to each of + * those directories, then all N of them would get implicitly + * renamed by the directory rename detection into the same path, + * and we'd get an add/add/.../add conflict, and all those adds + * from *this* side of history. This is not representable in the + * index, and users aren't going to easily be able to make sense of + * it. So we need to provide a good warning about what's + * happening, and fall back to no-directory-rename detection + * behavior for those paths. + * + * See testcases 9e and all of section 5 from t6043 for examples. + */ + collision_init(collisions); + + for (i = 0; i < pairs->nr; ++i) { + struct dir_rename_entry *dir_rename_ent; + struct collision_entry *collision_ent; + char *new_path; + struct diff_filepair *pair = pairs->queue[i]; + + if (pair->status != 'A' && pair->status != 'R') + continue; + dir_rename_ent = check_dir_renamed(pair->two->path, + dir_renames); + if (!dir_rename_ent) + continue; + + new_path = apply_dir_rename(dir_rename_ent, pair->two->path); + if (!new_path) + /* + * dir_rename_ent->non_unique_new_path is true, which + * means there is no directory rename for us to use, + * which means it won't cause us any additional + * collisions. + */ + continue; + collision_ent = collision_find_entry(collisions, new_path); + if (!collision_ent) { + collision_ent = xcalloc(1, + sizeof(struct collision_entry)); + hashmap_entry_init(collision_ent, strhash(new_path)); + hashmap_put(collisions, collision_ent); + collision_ent->target_file = new_path; + } else { + free(new_path); + } + string_list_insert(&collision_ent->source_files, + pair->two->path); + } +} + +static char *check_for_directory_rename(struct merge_options *o, + const char *path, + struct tree *tree, + struct hashmap *dir_renames, + struct hashmap *dir_rename_exclusions, + struct hashmap *collisions, + int *clean_merge) +{ + char *new_path = NULL; + struct dir_rename_entry *entry = check_dir_renamed(path, dir_renames); + struct dir_rename_entry *oentry = NULL; + + if (!entry) + return new_path; + + /* + * This next part is a little weird. We do not want to do an + * implicit rename into a directory we renamed on our side, because + * that will result in a spurious rename/rename(1to2) conflict. An + * example: + * Base commit: dumbdir/afile, otherdir/bfile + * Side 1: smrtdir/afile, otherdir/bfile + * Side 2: dumbdir/afile, dumbdir/bfile + * Here, while working on Side 1, we could notice that otherdir was + * renamed/merged to dumbdir, and change the diff_filepair for + * otherdir/bfile into a rename into dumbdir/bfile. However, Side + * 2 will notice the rename from dumbdir to smrtdir, and do the + * transitive rename to move it from dumbdir/bfile to + * smrtdir/bfile. That gives us bfile in dumbdir vs being in + * smrtdir, a rename/rename(1to2) conflict. We really just want + * the file to end up in smrtdir. And the way to achieve that is + * to not let Side1 do the rename to dumbdir, since we know that is + * the source of one of our directory renames. + * + * That's why oentry and dir_rename_exclusions is here. + * + * As it turns out, this also prevents N-way transient rename + * confusion; See testcases 9c and 9d of t6043. + */ + oentry = dir_rename_find_entry(dir_rename_exclusions, entry->new_dir.buf); + if (oentry) { + output(o, 1, _("WARNING: Avoiding applying %s -> %s rename " + "to %s, because %s itself was renamed."), + entry->dir, entry->new_dir.buf, path, entry->new_dir.buf); + } else { + new_path = handle_path_level_conflicts(o, path, entry, + collisions, tree); + *clean_merge &= (new_path != NULL); + } + + return new_path; +} + +static void apply_directory_rename_modifications(struct merge_options *o, + struct diff_filepair *pair, + char *new_path, + struct rename *re, + struct tree *tree, + struct tree *o_tree, + struct tree *a_tree, + struct tree *b_tree, + struct string_list *entries, + int *clean) +{ + struct string_list_item *item; + int stage = (tree == a_tree ? 2 : 3); + int update_wd; + + /* + * In all cases where we can do directory rename detection, + * unpack_trees() will have read pair->two->path into the + * index and the working copy. We need to remove it so that + * we can instead place it at new_path. It is guaranteed to + * not be untracked (unpack_trees() would have errored out + * saying the file would have been overwritten), but it might + * be dirty, though. + */ + update_wd = !was_dirty(o, pair->two->path); + if (!update_wd) + output(o, 1, _("Refusing to lose dirty file at %s"), + pair->two->path); + remove_file(o, 1, pair->two->path, !update_wd); + + /* Find or create a new re->dst_entry */ + item = string_list_lookup(entries, new_path); + if (item) { + /* + * Since we're renaming on this side of history, and it's + * due to a directory rename on the other side of history + * (which we only allow when the directory in question no + * longer exists on the other side of history), the + * original entry for re->dst_entry is no longer + * necessary... + */ + re->dst_entry->processed = 1; + + /* + * ...because we'll be using this new one. + */ + re->dst_entry = item->util; + } else { + /* + * re->dst_entry is for the before-dir-rename path, and we + * need it to hold information for the after-dir-rename + * path. Before creating a new entry, we need to mark the + * old one as unnecessary (...unless it is shared by + * src_entry, i.e. this didn't use to be a rename, in which + * case we can just allow the normal processing to happen + * for it). + */ + if (pair->status == 'R') + re->dst_entry->processed = 1; + + re->dst_entry = insert_stage_data(new_path, + o_tree, a_tree, b_tree, + entries); + item = string_list_insert(entries, new_path); + item->util = re->dst_entry; + } + + /* + * Update the stage_data with the information about the path we are + * moving into place. That slot will be empty and available for us + * to write to because of the collision checks in + * handle_path_level_conflicts(). In other words, + * re->dst_entry->stages[stage].oid will be the null_oid, so it's + * open for us to write to. + * + * It may be tempting to actually update the index at this point as + * well, using update_stages_for_stage_data(), but as per the big + * "NOTE" in update_stages(), doing so will modify the current + * in-memory index which will break calls to would_lose_untracked() + * that we need to make. Instead, we need to just make sure that + * the various conflict_rename_*() functions update the index + * explicitly rather than relying on unpack_trees() to have done it. + */ + get_tree_entry(&tree->object.oid, + pair->two->path, + &re->dst_entry->stages[stage].oid, + &re->dst_entry->stages[stage].mode); + + /* Update pair status */ + if (pair->status == 'A') { + /* + * Recording rename information for this add makes it look + * like a rename/delete conflict. Make sure we can + * correctly handle this as an add that was moved to a new + * directory instead of reporting a rename/delete conflict. + */ + re->add_turned_into_rename = 1; + } + /* + * We don't actually look at pair->status again, but it seems + * pedagogically correct to adjust it. + */ + pair->status = 'R'; + + /* + * Finally, record the new location. + */ + pair->two->path = new_path; +} + +/* + * Get information of all renames which occurred in 'pairs', making use of + * any implicit directory renames inferred from the other side of history. + * We need the three trees in the merge ('o_tree', 'a_tree' and 'b_tree') + * to be able to associate the correct cache entries with the rename + * information; tree is always equal to either a_tree or b_tree. + */ +static struct string_list *get_renames(struct merge_options *o, + struct diff_queue_struct *pairs, + struct hashmap *dir_renames, + struct hashmap *dir_rename_exclusions, + struct tree *tree, + struct tree *o_tree, + struct tree *a_tree, + struct tree *b_tree, + struct string_list *entries, + int *clean_merge) +{ + int i; + struct hashmap collisions; + struct hashmap_iter iter; + struct collision_entry *e; + struct string_list *renames; + + compute_collisions(&collisions, dir_renames, pairs); + renames = xcalloc(1, sizeof(struct string_list)); + + for (i = 0; i < pairs->nr; ++i) { + struct string_list_item *item; + struct rename *re; + struct diff_filepair *pair = pairs->queue[i]; + char *new_path; /* non-NULL only with directory renames */ + + if (pair->status != 'A' && pair->status != 'R') { + diff_free_filepair(pair); + continue; + } + new_path = check_for_directory_rename(o, pair->two->path, tree, + dir_renames, + dir_rename_exclusions, + &collisions, + clean_merge); + if (pair->status != 'R' && !new_path) { + diff_free_filepair(pair); + continue; + } + + re = xmalloc(sizeof(*re)); + re->processed = 0; + re->add_turned_into_rename = 0; + re->pair = pair; + item = string_list_lookup(entries, re->pair->one->path); + if (!item) + re->src_entry = insert_stage_data(re->pair->one->path, + o_tree, a_tree, b_tree, entries); + else + re->src_entry = item->util; + + item = string_list_lookup(entries, re->pair->two->path); + if (!item) + re->dst_entry = insert_stage_data(re->pair->two->path, + o_tree, a_tree, b_tree, entries); + else + re->dst_entry = item->util; + item = string_list_insert(renames, pair->one->path); + item->util = re; + if (new_path) + apply_directory_rename_modifications(o, pair, new_path, + re, tree, o_tree, + a_tree, b_tree, + entries, + clean_merge); + } + + hashmap_iter_init(&collisions, &iter); + while ((e = hashmap_iter_next(&iter))) { + free(e->target_file); + string_list_clear(&e->source_files, 0); + } + hashmap_free(&collisions, 1); + return renames; +} + static int process_renames(struct merge_options *o, struct string_list *a_renames, struct string_list *b_renames) @@@ -2427,19 -1528,7 +2427,19 @@@ dst_other.mode = ren1->dst_entry->stages[other_stage].mode; try_merge = 0; - if (oid_eq(&src_other.oid, &null_oid)) { + if (oid_eq(&src_other.oid, &null_oid) && + ren1->add_turned_into_rename) { + setup_rename_conflict_info(RENAME_DIR, + ren1->pair, + NULL, + branch1, + branch2, + ren1->dst_entry, + NULL, + o, + NULL, + NULL); + } else if (oid_eq(&src_other.oid, &null_oid)) { setup_rename_conflict_info(RENAME_DELETE, ren1->pair, NULL, @@@ -2536,105 -1625,6 +2536,105 @@@ cleanup_and_return return clean_merge; } +struct rename_info { + struct string_list *head_renames; + struct string_list *merge_renames; +}; + +static void initial_cleanup_rename(struct diff_queue_struct *pairs, + struct hashmap *dir_renames) +{ + struct hashmap_iter iter; + struct dir_rename_entry *e; + + hashmap_iter_init(dir_renames, &iter); + while ((e = hashmap_iter_next(&iter))) { + free(e->dir); + strbuf_release(&e->new_dir); + /* possible_new_dirs already cleared in get_directory_renames */ + } + hashmap_free(dir_renames, 1); + free(dir_renames); + + free(pairs->queue); + free(pairs); +} + +static int handle_renames(struct merge_options *o, + struct tree *common, + struct tree *head, + struct tree *merge, + struct string_list *entries, + struct rename_info *ri) +{ + struct diff_queue_struct *head_pairs, *merge_pairs; + struct hashmap *dir_re_head, *dir_re_merge; + int clean = 1; + + ri->head_renames = NULL; + ri->merge_renames = NULL; + + if (!o->detect_rename) + return 1; + + head_pairs = get_diffpairs(o, common, head); + merge_pairs = get_diffpairs(o, common, merge); + + dir_re_head = get_directory_renames(head_pairs, head); + dir_re_merge = get_directory_renames(merge_pairs, merge); + + handle_directory_level_conflicts(o, + dir_re_head, head, + dir_re_merge, merge); + + ri->head_renames = get_renames(o, head_pairs, + dir_re_merge, dir_re_head, head, + common, head, merge, entries, + &clean); + if (clean < 0) + goto cleanup; + ri->merge_renames = get_renames(o, merge_pairs, + dir_re_head, dir_re_merge, merge, + common, head, merge, entries, + &clean); + if (clean < 0) + goto cleanup; + clean &= process_renames(o, ri->head_renames, ri->merge_renames); + +cleanup: + /* + * Some cleanup is deferred until cleanup_renames() because the + * data structures are still needed and referenced in + * process_entry(). But there are a few things we can free now. + */ + initial_cleanup_rename(head_pairs, dir_re_head); + initial_cleanup_rename(merge_pairs, dir_re_merge); + + return clean; +} + +static void final_cleanup_rename(struct string_list *rename) +{ + const struct rename *re; + int i; + + if (rename == NULL) + return; + + for (i = 0; i < rename->nr; i++) { + re = rename->items[i].util; + diff_free_filepair(re->pair); + } + string_list_clear(rename, 1); + free(rename); +} + +static void final_cleanup_renames(struct rename_info *re_info) +{ + final_cleanup_rename(re_info->head_renames); + final_cleanup_rename(re_info->merge_renames); +} + static struct object_id *stage_oid(const struct object_id *oid, unsigned mode) { return (is_null_oid(oid) || mode == 0) ? NULL: (struct object_id *)oid; @@@ -2646,7 -1636,7 +2646,7 @@@ static int read_oid_strbuf(struct merge void *buf; enum object_type type; unsigned long size; - buf = read_sha1_file(oid->hash, &type, &size); + buf = read_object_file(oid, &type, &size); if (!buf) return err(o, _("cannot read object %s"), oid_to_hex(oid)); if (type != OBJ_BLOB) { @@@ -2725,7 -1715,6 +2725,7 @@@ static int handle_modify_delete(struct static int merge_content(struct merge_options *o, const char *path, + int file_in_way, struct object_id *o_oid, int o_mode, struct object_id *a_oid, int a_mode, struct object_id *b_oid, int b_mode, @@@ -2773,6 -1762,7 +2773,6 @@@ if (mfi.clean && !df_conflict_remains && oid_eq(&mfi.oid, a_oid) && mfi.mode == a_mode) { - int path_renamed_outside_HEAD; output(o, 3, _("Skipped %s (merged same as existing)"), path); /* * The content merge resulted in the same file contents we @@@ -2780,7 -1770,8 +2780,7 @@@ * are recorded at the correct path (which may not be true * if the merge involves a rename). */ - path_renamed_outside_HEAD = !path2 || !strcmp(path, path2); - if (!path_renamed_outside_HEAD) { + if (was_tracked(path)) { add_cacheinfo(o, mfi.mode, &mfi.oid, path, 0, (!o->call_depth), 0); return mfi.clean; @@@ -2798,7 -1789,7 +2798,7 @@@ return -1; } - if (df_conflict_remains) { + if (df_conflict_remains || file_in_way) { char *new_path; if (o->call_depth) { remove_file_from_cache(path); @@@ -2832,30 -1823,6 +2832,30 @@@ return mfi.clean; } +static int conflict_rename_normal(struct merge_options *o, + const char *path, + struct object_id *o_oid, unsigned int o_mode, + struct object_id *a_oid, unsigned int a_mode, + struct object_id *b_oid, unsigned int b_mode, + struct rename_conflict_info *ci) +{ + int clean_merge; + int file_in_the_way = 0; + + if (was_dirty(o, path)) { + file_in_the_way = 1; + output(o, 1, _("Refusing to lose dirty file at %s"), path); + } + + /* Merge the content and write it out */ + clean_merge = merge_content(o, path, file_in_the_way, + o_oid, o_mode, a_oid, a_mode, b_oid, b_mode, + ci); + if (clean_merge > 0 && file_in_the_way) + clean_merge = 0; + return clean_merge; +} + /* Per entry merge function */ static int process_entry(struct merge_options *o, const char *path, struct stage_data *entry) @@@ -2875,20 -1842,9 +2875,20 @@@ switch (conflict_info->rename_type) { case RENAME_NORMAL: case RENAME_ONE_FILE_TO_ONE: - clean_merge = merge_content(o, path, - o_oid, o_mode, a_oid, a_mode, b_oid, b_mode, - conflict_info); + clean_merge = conflict_rename_normal(o, + path, + o_oid, o_mode, + a_oid, a_mode, + b_oid, b_mode, + conflict_info); + break; + case RENAME_DIR: + clean_merge = 1; + if (conflict_rename_dir(o, + conflict_info->pair1, + conflict_info->branch1, + conflict_info->branch2)) + clean_merge = -1; break; case RENAME_DELETE: clean_merge = 0; @@@ -2976,7 -1932,7 +2976,7 @@@ } else if (a_oid && b_oid) { /* Case C: Added in both (check for same permissions) and */ /* case D: Modified in both, but differently. */ - clean_merge = merge_content(o, path, + clean_merge = merge_content(o, path, 0 /* file_in_way */, o_oid, o_mode, a_oid, a_mode, b_oid, b_mode, NULL); } else if (!o_oid && !a_oid && !b_oid) { @@@ -3017,7 -1973,7 +3017,7 @@@ int merge_trees(struct merge_options *o return 1; } - code = git_merge_trees(o->call_depth, common, head, merge); + code = git_merge_trees(o, common, head, merge); if (code != 0) { if (show(o, 4) || o->call_depth) @@@ -3028,8 -1984,7 +3028,8 @@@ } if (unmerged_cache()) { - struct string_list *entries, *re_head, *re_merge; + struct string_list *entries; + struct rename_info re_info; int i; /* * Only need the hashmap while processing entries, so @@@ -3043,9 -1998,10 +3043,9 @@@ get_files_dirs(o, merge); entries = get_unmerged(); + clean = handle_renames(o, common, head, merge, entries, + &re_info); record_df_conflict_files(o, entries); - re_head = get_renames(o, head, common, head, merge, entries); - re_merge = get_renames(o, merge, common, head, merge, entries); - clean = process_renames(o, re_head, re_merge); if (clean < 0) goto cleanup; for (i = entries->nr-1; 0 <= i; i--) { @@@ -3069,13 -2025,16 +3069,13 @@@ } cleanup: - string_list_clear(re_merge, 0); - string_list_clear(re_head, 0); + final_cleanup_renames(&re_info); + string_list_clear(entries, 1); + free(entries); hashmap_free(&o->current_file_dir_set, 1); - free(re_merge); - free(re_head); - free(entries); - if (clean < 0) return clean; } @@@ -3111,7 -2070,7 +3111,7 @@@ int merge_recursive(struct merge_option { struct commit_list *iter; struct commit *merged_common_ancestors; - struct tree *mrtree = mrtree; + struct tree *mrtree; int clean; if (show(o, 4)) { @@@ -3239,13 -2198,11 +3239,13 @@@ int merge_recursive_generic(struct merg hold_locked_index(&lock, LOCK_DIE_ON_ERROR); clean = merge_recursive(o, head_commit, next_commit, ca, result); - if (clean < 0) + if (clean < 0) { + rollback_lock_file(&lock); return clean; + } - if (active_cache_changed && - write_locked_index(&the_index, &lock, COMMIT_LOCK)) + if (write_locked_index(&the_index, &lock, + COMMIT_LOCK | SKIP_IF_UNCHANGED)) return err(o, _("Unable to write index.")); return clean ? 0 : 1; diff --combined read-cache.c index f23d9a4731,49607ddcd7..10f1c6bb8a --- a/read-cache.c +++ b/read-cache.c @@@ -62,7 -62,6 +62,7 @@@ static void replace_index_entry(struct replace_index_entry_in_base(istate, old, ce); remove_name_hash(istate, old); free(old); + ce->ce_flags &= ~CE_HASHED; set_index_entry(istate, nr, ce); ce->ce_flags |= CE_UPDATE_IN_BASE; mark_fsmonitor_invalid(istate, ce); @@@ -71,20 -70,20 +71,20 @@@ void rename_index_entry_at(struct index_state *istate, int nr, const char *new_name) { - struct cache_entry *old = istate->cache[nr], *new; + struct cache_entry *old_entry = istate->cache[nr], *new_entry; int namelen = strlen(new_name); - new = xmalloc(cache_entry_size(namelen)); - copy_cache_entry(new, old); - new->ce_flags &= ~CE_HASHED; - new->ce_namelen = namelen; - new->index = 0; - memcpy(new->name, new_name, namelen + 1); + new_entry = xmalloc(cache_entry_size(namelen)); + copy_cache_entry(new_entry, old_entry); + new_entry->ce_flags &= ~CE_HASHED; + new_entry->ce_namelen = namelen; + new_entry->index = 0; + memcpy(new_entry->name, new_name, namelen + 1); - cache_tree_invalidate_path(istate, old->name); - untracked_cache_remove_from_index(istate, old->name); + cache_tree_invalidate_path(istate, old_entry->name); + untracked_cache_remove_from_index(istate, old_entry->name); remove_index_entry_at(istate, nr); - add_index_entry(istate, new, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE); + add_index_entry(istate, new_entry, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE); } void fill_stat_data(struct stat_data *sd, struct stat *st) @@@ -185,7 -184,7 +185,7 @@@ static int ce_compare_link(const struc if (strbuf_readlink(&sb, ce->name, expected_size)) return -1; - buffer = read_sha1_file(ce->oid.hash, &type, &size); + buffer = read_object_file(&ce->oid, &type, &size); if (buffer) { if (size == sb.len) match = memcmp(buffer, sb.buf, size); @@@ -616,26 -615,26 +616,26 @@@ static struct cache_entry *create_alias struct cache_entry *alias) { int len; - struct cache_entry *new; + struct cache_entry *new_entry; if (alias->ce_flags & CE_ADDED) die("Will not add file alias '%s' ('%s' already exists in index)", ce->name, alias->name); /* Ok, create the new entry using the name of the existing alias */ len = ce_namelen(alias); - new = xcalloc(1, cache_entry_size(len)); - memcpy(new->name, alias->name, len); - copy_cache_entry(new, ce); + new_entry = xcalloc(1, cache_entry_size(len)); + memcpy(new_entry->name, alias->name, len); + copy_cache_entry(new_entry, ce); save_or_free_index_entry(istate, ce); - return new; + return new_entry; } void set_object_name_for_intent_to_add_entry(struct cache_entry *ce) { - unsigned char sha1[20]; - if (write_sha1_file("", 0, blob_type, sha1)) + struct object_id oid; + if (write_object_file("", 0, blob_type, &oid)) die("cannot create an empty blob in the object database"); - hashcpy(ce->oid.hash, sha1); + oidcpy(&ce->oid, &oid); } int add_to_index(struct index_state *istate, const char *path, struct stat *st, int flags) @@@ -1218,8 -1217,9 +1218,8 @@@ int add_index_entry(struct index_state /* Add it in.. */ istate->cache_nr++; if (istate->cache_nr > pos + 1) - memmove(istate->cache + pos + 1, - istate->cache + pos, - (istate->cache_nr - pos - 1) * sizeof(ce)); + MOVE_ARRAY(istate->cache + pos + 1, istate->cache + pos, + istate->cache_nr - pos - 1); set_index_entry(istate, pos, ce); istate->cache_changed |= CE_ENTRY_ADDED; return 0; @@@ -1325,8 -1325,7 +1325,8 @@@ static struct cache_entry *refresh_cach size = ce_size(ce); updated = xmalloc(size); - memcpy(updated, ce, size); + copy_cache_entry(updated, ce); + memcpy(updated->name, ce->name, ce->ce_namelen + 1); fill_stat_cache_info(updated, &st); /* * If ignore_valid is not set, we should leave CE_VALID bit @@@ -1373,7 -1372,6 +1373,7 @@@ int refresh_index(struct index_state *i const char *typechange_fmt; const char *added_fmt; const char *unmerged_fmt; + uint64_t start = getnanotime(); modified_fmt = (in_porcelain ? "M\t%s\n" : "%s: needs update\n"); deleted_fmt = (in_porcelain ? "D\t%s\n" : "%s: needs update\n"); @@@ -1381,7 -1379,7 +1381,7 @@@ added_fmt = (in_porcelain ? "A\t%s\n" : "%s needs update\n"); unmerged_fmt = (in_porcelain ? "U\t%s\n" : "%s: needs merge\n"); for (i = 0; i < istate->cache_nr; i++) { - struct cache_entry *ce, *new; + struct cache_entry *ce, *new_entry; int cache_errno = 0; int changed = 0; int filtered = 0; @@@ -1410,10 -1408,10 +1410,10 @@@ if (filtered) continue; - new = refresh_cache_ent(istate, ce, options, &cache_errno, &changed); - if (new == ce) + new_entry = refresh_cache_ent(istate, ce, options, &cache_errno, &changed); + if (new_entry == ce) continue; - if (!new) { + if (!new_entry) { const char *fmt; if (really && cache_errno == EINVAL) { @@@ -1442,9 -1440,8 +1442,9 @@@ continue; } - replace_index_entry(istate, i, new); + replace_index_entry(istate, i, new_entry); } + trace_performance_since(start, "refresh index"); return has_errors; } @@@ -1548,8 -1545,8 +1548,8 @@@ int verify_ce_order static int verify_hdr(struct cache_header *hdr, unsigned long size) { - git_SHA_CTX c; - unsigned char sha1[20]; + git_hash_ctx c; + unsigned char hash[GIT_MAX_RAWSZ]; int hdr_version; if (hdr->hdr_signature != htonl(CACHE_SIGNATURE)) @@@ -1561,10 -1558,10 +1561,10 @@@ if (!verify_index_checksum) return 0; - git_SHA1_Init(&c); - git_SHA1_Update(&c, hdr, size - 20); - git_SHA1_Final(sha1, &c); - if (hashcmp(sha1, (unsigned char *)hdr + size - 20)) + the_hash_algo->init_fn(&c); + the_hash_algo->update_fn(&c, hdr, size - the_hash_algo->rawsz); + the_hash_algo->final_fn(hash, &c); + if (hashcmp(hash, (unsigned char *)hdr + size - the_hash_algo->rawsz)) return error("bad index file sha1 signature"); return 0; } @@@ -1606,7 -1603,7 +1606,7 @@@ int hold_locked_index(struct lock_file int read_index(struct index_state *istate) { - return read_index_from(istate, get_index_file()); + return read_index_from(istate, get_index_file(), get_git_dir()); } static struct cache_entry *cache_entry_from_ondisk(struct ondisk_cache_entry *ondisk, @@@ -1794,7 -1791,7 +1794,7 @@@ int do_read_index(struct index_state *i die_errno("cannot stat the open index"); mmap_size = xsize_t(st.st_size); - if (mmap_size < sizeof(struct cache_header) + 20) + if (mmap_size < sizeof(struct cache_header) + the_hash_algo->rawsz) die("index file smaller than expected"); mmap = xmmap(NULL, mmap_size, PROT_READ, MAP_PRIVATE, fd, 0); @@@ -1806,7 -1803,7 +1806,7 @@@ if (verify_hdr(hdr, mmap_size) < 0) goto unmap; - hashcpy(istate->sha1, (const unsigned char *)hdr + mmap_size - 20); + hashcpy(istate->sha1, (const unsigned char *)hdr + mmap_size - the_hash_algo->rawsz); istate->version = ntohl(hdr->hdr_version); istate->cache_nr = ntohl(hdr->hdr_entries); istate->cache_alloc = alloc_nr(istate->cache_nr); @@@ -1834,7 -1831,7 +1834,7 @@@ istate->timestamp.sec = st.st_mtime; istate->timestamp.nsec = ST_MTIME_NSEC(st); - while (src_offset <= mmap_size - 20 - 8) { + while (src_offset <= mmap_size - the_hash_algo->rawsz - 8) { /* After an array of active_nr index entries, * there can be arbitrary number of extended * sections, each of which is prefixed with @@@ -1866,27 -1863,26 +1866,27 @@@ unmap * This way, shared index can be removed if they have not been used * for some time. */ -static void freshen_shared_index(char *base_sha1_hex, int warn) +static void freshen_shared_index(const char *shared_index, int warn) { - char *shared_index = git_pathdup("sharedindex.%s", base_sha1_hex); if (!check_and_freshen_file(shared_index, 1) && warn) warning("could not freshen shared index '%s'", shared_index); - free(shared_index); } -int read_index_from(struct index_state *istate, const char *path) +int read_index_from(struct index_state *istate, const char *path, + const char *gitdir) { + uint64_t start = getnanotime(); struct split_index *split_index; int ret; char *base_sha1_hex; - const char *base_path; + char *base_path; /* istate->initialized covers both .git/index and .git/sharedindex.xxx */ if (istate->initialized) return istate->cache_nr; ret = do_read_index(istate, path, 0); + trace_performance_since(start, "read cache %s", path); split_index = istate->split_index; if (!split_index || is_null_sha1(split_index->base_sha1)) { @@@ -1900,18 -1896,16 +1900,18 @@@ split_index->base = xcalloc(1, sizeof(*split_index->base)); base_sha1_hex = sha1_to_hex(split_index->base_sha1); - base_path = git_path("sharedindex.%s", base_sha1_hex); + base_path = xstrfmt("%s/sharedindex.%s", gitdir, base_sha1_hex); ret = do_read_index(split_index->base, base_path, 1); if (hashcmp(split_index->base_sha1, split_index->base->sha1)) die("broken index, expect %s in %s, got %s", base_sha1_hex, base_path, sha1_to_hex(split_index->base->sha1)); - freshen_shared_index(base_sha1_hex, 0); + freshen_shared_index(base_path, 0); merge_base_index(istate); post_read_index_from(istate); + trace_performance_since(start, "read cache %s", base_path); + free(base_path); return ret; } @@@ -1963,11 -1957,11 +1963,11 @@@ int unmerged_index(const struct index_s static unsigned char write_buffer[WRITE_BUFFER_SIZE]; static unsigned long write_buffer_len; -static int ce_write_flush(git_SHA_CTX *context, int fd) +static int ce_write_flush(git_hash_ctx *context, int fd) { unsigned int buffered = write_buffer_len; if (buffered) { - git_SHA1_Update(context, write_buffer, buffered); + the_hash_algo->update_fn(context, write_buffer, buffered); if (write_in_full(fd, write_buffer, buffered) < 0) return -1; write_buffer_len = 0; @@@ -1975,7 -1969,7 +1975,7 @@@ return 0; } -static int ce_write(git_SHA_CTX *context, int fd, void *data, unsigned int len) +static int ce_write(git_hash_ctx *context, int fd, void *data, unsigned int len) { while (len) { unsigned int buffered = write_buffer_len; @@@ -1997,7 -1991,7 +1997,7 @@@ return 0; } -static int write_index_ext_header(git_SHA_CTX *context, int fd, +static int write_index_ext_header(git_hash_ctx *context, int fd, unsigned int ext, unsigned int sz) { ext = htonl(ext); @@@ -2006,26 -2000,26 +2006,26 @@@ (ce_write(context, fd, &sz, 4) < 0)) ? -1 : 0; } -static int ce_flush(git_SHA_CTX *context, int fd, unsigned char *sha1) +static int ce_flush(git_hash_ctx *context, int fd, unsigned char *hash) { unsigned int left = write_buffer_len; if (left) { write_buffer_len = 0; - git_SHA1_Update(context, write_buffer, left); + the_hash_algo->update_fn(context, write_buffer, left); } - /* Flush first if not enough space for SHA1 signature */ - if (left + 20 > WRITE_BUFFER_SIZE) { + /* Flush first if not enough space for hash signature */ + if (left + the_hash_algo->rawsz > WRITE_BUFFER_SIZE) { if (write_in_full(fd, write_buffer, left) < 0) return -1; left = 0; } - /* Append the SHA1 signature at the end */ - git_SHA1_Final(write_buffer + left, context); - hashcpy(sha1, write_buffer + left); - left += 20; + /* Append the hash signature at the end */ + the_hash_algo->final_fn(write_buffer + left, context); + hashcpy(hash, write_buffer + left); + left += the_hash_algo->rawsz; return (write_in_full(fd, write_buffer, left) < 0) ? -1 : 0; } @@@ -2106,17 -2100,19 +2106,19 @@@ static void copy_cache_entry_to_ondisk( } } -static int ce_write_entry(git_SHA_CTX *c, int fd, struct cache_entry *ce, +static int ce_write_entry(git_hash_ctx *c, int fd, struct cache_entry *ce, struct strbuf *previous_name, struct ondisk_cache_entry *ondisk) { int size; - int saved_namelen = saved_namelen; /* compiler workaround */ int result; + unsigned int saved_namelen; + int stripped_name = 0; static unsigned char padding[8] = { 0x00 }; if (ce->ce_flags & CE_STRIP_NAME) { saved_namelen = ce_namelen(ce); ce->ce_namelen = 0; + stripped_name = 1; } if (ce->ce_flags & CE_EXTENDED) @@@ -2156,7 -2152,7 +2158,7 @@@ strbuf_splice(previous_name, common, to_remove, ce->name + common, ce_namelen(ce) - common); } - if (ce->ce_flags & CE_STRIP_NAME) { + if (stripped_name) { ce->ce_namelen = saved_namelen; ce->ce_flags &= ~CE_STRIP_NAME; } @@@ -2173,7 -2169,7 +2175,7 @@@ static int verify_index_from(const stru int fd; ssize_t n; struct stat st; - unsigned char sha1[20]; + unsigned char hash[GIT_MAX_RAWSZ]; if (!istate->initialized) return 0; @@@ -2185,14 -2181,14 +2187,14 @@@ if (fstat(fd, &st)) goto out; - if (st.st_size < sizeof(struct cache_header) + 20) + if (st.st_size < sizeof(struct cache_header) + the_hash_algo->rawsz) goto out; - n = pread_in_full(fd, sha1, 20, st.st_size - 20); - if (n != 20) + n = pread_in_full(fd, hash, the_hash_algo->rawsz, st.st_size - the_hash_algo->rawsz); + if (n != the_hash_algo->rawsz) goto out; - if (hashcmp(istate->sha1, sha1)) + if (hashcmp(istate->sha1, hash)) goto out; close(fd); @@@ -2240,9 -2236,8 +2242,9 @@@ void update_index_if_able(struct index_ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, int strip_extensions) { + uint64_t start = getnanotime(); int newfd = tempfile->fd; - git_SHA_CTX c; + git_hash_ctx c; struct cache_header hdr; int i, err = 0, removed, extended, hdr_version; struct cache_entry **cache = istate->cache; @@@ -2250,7 -2245,7 +2252,7 @@@ struct stat st; struct ondisk_cache_entry_extended ondisk; struct strbuf previous_name_buf = STRBUF_INIT, *previous_name; - int drop_cache_tree = 0; + int drop_cache_tree = istate->drop_cache_tree; for (i = removed = extended = 0; i < entries; i++) { if (cache[i]->ce_flags & CE_REMOVE) @@@ -2280,7 -2275,7 +2282,7 @@@ hdr.hdr_version = htonl(hdr_version); hdr.hdr_entries = htonl(entries - removed); - git_SHA1_Init(&c); + the_hash_algo->init_fn(&c); if (ce_write(&c, newfd, &hdr, sizeof(hdr)) < 0) return -1; @@@ -2381,7 -2376,6 +2383,7 @@@ return -1; istate->timestamp.sec = (unsigned int)st.st_mtime; istate->timestamp.nsec = ST_MTIME_NSEC(st); + trace_performance_since(start, "write index, changed mask = %x", istate->cache_changed); return 0; } @@@ -2480,21 -2474,32 +2482,21 @@@ static int clean_shared_index_files(con } static int write_shared_index(struct index_state *istate, - struct lock_file *lock, unsigned flags) + struct tempfile **temp) { - struct tempfile *temp; struct split_index *si = istate->split_index; int ret; - temp = mks_tempfile(git_path("sharedindex_XXXXXX")); - if (!temp) { - hashclr(si->base_sha1); - return do_write_locked_index(istate, lock, flags); - } move_cache_to_base_index(istate); - ret = do_write_index(si->base, temp, 1); - if (ret) { - delete_tempfile(&temp); + ret = do_write_index(si->base, *temp, 1); + if (ret) return ret; - } - ret = adjust_shared_perm(get_tempfile_path(temp)); + ret = adjust_shared_perm(get_tempfile_path(*temp)); if (ret) { - int save_errno = errno; - error("cannot fix permission bits on %s", get_tempfile_path(temp)); - delete_tempfile(&temp); - errno = save_errno; + error("cannot fix permission bits on %s", get_tempfile_path(*temp)); return ret; } - ret = rename_tempfile(&temp, + ret = rename_tempfile(temp, git_path("sharedindex.%s", sha1_to_hex(si->base->sha1))); if (!ret) { hashcpy(si->base_sha1, si->base->sha1); @@@ -2540,12 -2545,6 +2542,12 @@@ int write_locked_index(struct index_sta int new_shared_index, ret; struct split_index *si = istate->split_index; + if ((flags & SKIP_IF_UNCHANGED) && !istate->cache_changed) { + if (flags & COMMIT_LOCK) + rollback_lock_file(lock); + return 0; + } + if (istate->fsmonitor_last_update) fill_fsmonitor_bitmap(istate); @@@ -2568,22 -2567,7 +2570,22 @@@ new_shared_index = istate->cache_changed & SPLIT_INDEX_ORDERED; if (new_shared_index) { - ret = write_shared_index(istate, lock, flags); + struct tempfile *temp; + int saved_errno; + + temp = mks_tempfile(git_path("sharedindex_XXXXXX")); + if (!temp) { + hashclr(si->base_sha1); + ret = do_write_locked_index(istate, lock, flags); + goto out; + } + ret = write_shared_index(istate, &temp); + + saved_errno = errno; + if (is_tempfile_active(temp)) + delete_tempfile(&temp); + errno = saved_errno; + if (ret) goto out; } @@@ -2591,11 -2575,8 +2593,11 @@@ ret = write_split_index(istate, lock, flags); /* Freshen the shared index only if the split-index was written */ - if (!ret && !new_shared_index) - freshen_shared_index(sha1_to_hex(si->base_sha1), 1); + if (!ret && !new_shared_index) { + const char *shared_index = git_path("sharedindex.%s", + sha1_to_hex(si->base_sha1)); + freshen_shared_index(shared_index, 1); + } out: if (flags & COMMIT_LOCK) @@@ -2691,7 -2672,7 +2693,7 @@@ void *read_blob_data_from_index(const s } if (pos < 0) return NULL; - data = read_sha1_file(istate->cache[pos]->oid.hash, &type, &sz); + data = read_object_file(&istate->cache[pos]->oid, &type, &sz); if (!data || type != OBJ_BLOB) { free(data); return NULL;