diff options
Diffstat (limited to 'merge-recursive.c')
| -rw-r--r-- | merge-recursive.c | 2703 |
1 files changed, 2123 insertions, 580 deletions
diff --git a/merge-recursive.c b/merge-recursive.c index b880ae50e7..dcdc93019c 100644 --- a/merge-recursive.c +++ b/merge-recursive.c @@ -4,9 +4,12 @@ * The thieves were Alex Riesen and Johannes Schindelin, in June/July 2006 */ #include "cache.h" +#include "config.h" #include "advice.h" #include "lockfile.h" #include "cache-tree.h" +#include "object-store.h" +#include "repository.h" #include "commit.h" #include "blob.h" #include "builtin.h" @@ -14,6 +17,7 @@ #include "diff.h" #include "diffcore.h" #include "tag.h" +#include "alloc.h" #include "unpack-trees.h" #include "string-list.h" #include "xdiff-interface.h" @@ -22,6 +26,124 @@ #include "merge-recursive.h" #include "dir.h" #include "submodule.h" +#include "revision.h" + +struct path_hashmap_entry { + struct hashmap_entry e; + char path[FLEX_ARRAY]; +}; + +static int path_hashmap_cmp(const void *cmp_data, + const void *entry, + const void *entry_or_key, + const void *keydata) +{ + const struct path_hashmap_entry *a = entry; + const struct path_hashmap_entry *b = entry_or_key; + const char *key = keydata; + + if (ignore_case) + return strcasecmp(a->path, key ? key : b->path); + else + return strcmp(a->path, key ? key : b->path); +} + +static unsigned int path_hash(const char *path) +{ + 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) { + fputs(o->obuf.buf, stdout); + strbuf_reset(&o->obuf); + } +} + +static int err(struct merge_options *o, const char *err, ...) +{ + va_list params; + + if (o->buffer_output < 2) + flush_output(o); + else { + strbuf_complete(&o->obuf, '\n'); + strbuf_addstr(&o->obuf, "error: "); + } + va_start(params, err); + strbuf_vaddf(&o->obuf, err, params); + va_end(params); + if (o->buffer_output > 1) + strbuf_addch(&o->obuf, '\n'); + else { + error("%s", o->obuf.buf); + strbuf_reset(&o->obuf); + } + + return -1; +} static struct tree *shift_tree_object(struct tree *one, struct tree *two, const char *subtree_shift) @@ -29,25 +151,22 @@ static struct tree *shift_tree_object(struct tree *one, struct tree *two, struct object_id shifted; if (!*subtree_shift) { - shift_tree(one->object.oid.hash, two->object.oid.hash, shifted.hash, 0); + shift_tree(&one->object.oid, &two->object.oid, &shifted, 0); } else { - shift_tree_by(one->object.oid.hash, two->object.oid.hash, shifted.hash, + shift_tree_by(&one->object.oid, &two->object.oid, &shifted, subtree_shift); } if (!oidcmp(&two->object.oid, &shifted)) return two; - return lookup_tree(shifted.hash); + return lookup_tree(the_repository, &shifted); } static struct commit *make_virtual_commit(struct tree *tree, const char *comment) { - struct commit *commit = alloc_commit_node(); - struct merge_remote_desc *desc = xmalloc(sizeof(*desc)); + struct commit *commit = alloc_commit_node(the_repository); - desc->name = comment; - desc->obj = (struct object *)commit; - commit->tree = tree; - commit->util = desc; + set_merge_remote_desc(commit, comment, (struct object *)commit); + commit->maybe_tree = tree; commit->object.parsed = 1; return commit; } @@ -56,15 +175,16 @@ static struct commit *make_virtual_commit(struct tree *tree, const char *comment * Since we use get_tree_entry(), which does not put the read object into * the object pool, we cannot rely on a == b. */ -static int sha_eq(const unsigned char *a, const unsigned char *b) +static int oid_eq(const struct object_id *a, const struct object_id *b) { if (!a && !b) return 2; - return a && b && hashcmp(a, b) == 0; + return a && b && oidcmp(a, b) == 0; } enum rename_type { RENAME_NORMAL = 0, + RENAME_VIA_DIR, RENAME_DELETE, RENAME_ONE_FILE_TO_ONE, RENAME_ONE_FILE_TO_TWO, @@ -90,7 +210,7 @@ struct rename_conflict_info { struct stage_data { struct { unsigned mode; - unsigned char sha[20]; + struct object_id oid; } stages[4]; struct rename_conflict_info *rename_conflict_info; unsigned processed:1; @@ -134,11 +254,11 @@ static inline void setup_rename_conflict_info(enum rename_type rename_type, int ostage2 = ostage1 ^ 1; ci->ren1_other.path = pair1->one->path; - hashcpy(ci->ren1_other.sha1, src_entry1->stages[ostage1].sha); + oidcpy(&ci->ren1_other.oid, &src_entry1->stages[ostage1].oid); ci->ren1_other.mode = src_entry1->stages[ostage1].mode; ci->ren2_other.path = pair2->one->path; - hashcpy(ci->ren2_other.sha1, src_entry2->stages[ostage2].sha); + oidcpy(&ci->ren2_other.oid, &src_entry2->stages[ostage2].oid); ci->ren2_other.mode = src_entry2->stages[ostage2].mode; } } @@ -148,14 +268,6 @@ static int show(struct merge_options *o, int v) return (!o->call_depth && o->verbosity >= v) || o->verbosity >= 5; } -static void flush_output(struct merge_options *o) -{ - if (o->obuf.len) { - fputs(o->obuf.buf, stdout); - strbuf_reset(&o->obuf); - } -} - __attribute__((format (printf, 3, 4))) static void output(struct merge_options *o, int v, const char *fmt, ...) { @@ -177,37 +289,52 @@ static void output(struct merge_options *o, int v, const char *fmt, ...) static void output_commit_title(struct merge_options *o, struct commit *commit) { - int i; - flush_output(o); - for (i = o->call_depth; i--;) - fputs(" ", stdout); - if (commit->util) - printf("virtual %s\n", merge_remote_util(commit)->name); + struct merge_remote_desc *desc; + + strbuf_addchars(&o->obuf, ' ', o->call_depth * 2); + desc = merge_remote_util(commit); + if (desc) + strbuf_addf(&o->obuf, "virtual %s\n", desc->name); else { - printf("%s ", find_unique_abbrev(commit->object.oid.hash, DEFAULT_ABBREV)); + strbuf_add_unique_abbrev(&o->obuf, &commit->object.oid, + DEFAULT_ABBREV); + strbuf_addch(&o->obuf, ' '); if (parse_commit(commit) != 0) - printf(_("(bad commit)\n")); + strbuf_addstr(&o->obuf, _("(bad commit)\n")); else { const char *title; const char *msg = get_commit_buffer(commit, NULL); int len = find_commit_subject(msg, &title); if (len) - printf("%.*s\n", len, title); + strbuf_addf(&o->obuf, "%.*s\n", len, title); unuse_commit_buffer(commit, msg); } } + flush_output(o); } -static int add_cacheinfo(unsigned int mode, const unsigned char *sha1, - const char *path, int stage, int refresh, int options) +static int add_cacheinfo(struct merge_options *o, + unsigned int mode, const struct object_id *oid, + const char *path, int stage, int refresh, int options) { struct cache_entry *ce; - ce = make_cache_entry(mode, sha1 ? sha1 : null_sha1, path, stage, - (refresh ? (CE_MATCH_REFRESH | - CE_MATCH_IGNORE_MISSING) : 0 )); + int ret; + + ce = make_cache_entry(&the_index, mode, oid ? oid : &null_oid, path, stage, 0); if (!ce) - return error(_("addinfo_cache failed for path '%s'"), path); - return add_cache_entry(ce, options); + return err(o, _("add_cacheinfo failed for path '%s'; merge aborting."), path); + + ret = add_cache_entry(ce, options); + if (refresh) { + struct cache_entry *nce; + + nce = refresh_cache_entry(&the_index, ce, CE_MATCH_REFRESH | CE_MATCH_IGNORE_MISSING); + if (!nce) + return err(o, _("add_cacheinfo failed to refresh for path '%s'; merge aborting."), path); + if (nce != ce) + ret = add_cache_entry(nce, options); + } + return ret; } static void init_tree_desc_from_tree(struct tree_desc *desc, struct tree *tree) @@ -216,36 +343,54 @@ static void init_tree_desc_from_tree(struct tree_desc *desc, struct tree *tree) init_tree_desc(desc, tree->buffer, tree->size); } -static int git_merge_trees(int index_only, - struct tree *common, - struct tree *head, - struct tree *merge) +static int unpack_trees_start(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; + struct index_state tmp_index = { NULL }; - 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 = &tmp_index; + o->unpack_opts.aggressive = !merge_detect_rename(o); + 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); cache_tree_free(&active_cache_tree); + + /* + * Update the_index to match the new results, AFTER saving a copy + * in o->orig_index. Update src_index to point to the saved copy. + * (verify_uptodate() checks src_index, and the original index is + * the one that had the necessary modification timestamps.) + */ + o->orig_index = the_index; + the_index = tmp_index; + o->unpack_opts.src_index = &o->orig_index; + return rc; } +static void unpack_trees_finish(struct merge_options *o) +{ + discard_index(&o->orig_index); + clear_unpack_trees_porcelain(&o->unpack_opts); +} + struct tree *write_tree_from_memory(struct merge_options *o) { struct tree *result = NULL; @@ -259,48 +404,61 @@ struct tree *write_tree_from_memory(struct merge_options *o) fprintf(stderr, "BUG: %d %.*s\n", ce_stage(ce), (int)ce_namelen(ce), ce->name); } - die("Bug in merge-recursive.c"); + BUG("unmerged index entries in merge-recursive.c"); } if (!active_cache_tree) active_cache_tree = cache_tree(); if (!cache_tree_fully_valid(active_cache_tree) && - cache_tree_update(&the_index, 0) < 0) - die(_("error building trees")); + cache_tree_update(&the_index, 0) < 0) { + err(o, _("error building trees")); + return NULL; + } - result = lookup_tree(active_cache_tree->sha1); + result = lookup_tree(the_repository, &active_cache_tree->oid); return result; } -static int save_files_dirs(const unsigned char *sha1, - struct strbuf *base, const char *path, - unsigned int mode, int stage, void *context) +static int save_files_dirs(const struct object_id *oid, + struct strbuf *base, const char *path, + unsigned int mode, int stage, void *context) { + struct path_hashmap_entry *entry; int baselen = base->len; struct merge_options *o = context; strbuf_addstr(base, path); - if (S_ISDIR(mode)) - string_list_insert(&o->current_directory_set, base->buf); - else - string_list_insert(&o->current_file_set, base->buf); + FLEX_ALLOC_MEM(entry, path, base->buf, base->len); + hashmap_entry_init(entry, path_hash(entry->path)); + hashmap_add(&o->current_file_dir_set, entry); strbuf_setlen(base, baselen); return (S_ISDIR(mode) ? READ_TREE_RECURSIVE : 0); } -static int get_files_dirs(struct merge_options *o, struct tree *tree) +static void get_files_dirs(struct merge_options *o, struct tree *tree) { - int n; struct pathspec match_all; memset(&match_all, 0, sizeof(match_all)); - if (read_tree_recursive(tree, "", 0, 0, &match_all, save_files_dirs, o)) - return 0; - n = o->current_file_set.nr + o->current_directory_set.nr; - return n; + read_tree_recursive(tree, "", 0, 0, &match_all, save_files_dirs, o); +} + +static int get_tree_entry_if_blob(const struct object_id *tree, + const char *path, + struct object_id *hashy, + unsigned int *mode_o) +{ + int ret; + + ret = get_tree_entry(tree, path, hashy, mode_o); + if (S_ISDIR(*mode_o)) { + oidcpy(hashy, &null_oid); + *mode_o = 0; + } + return ret; } /* @@ -313,12 +471,12 @@ static struct stage_data *insert_stage_data(const char *path, { 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].sha, &e->stages[1].mode); - get_tree_entry(a->object.oid.hash, path, - e->stages[2].sha, &e->stages[2].mode); - get_tree_entry(b->object.oid.hash, path, - e->stages[3].sha, &e->stages[3].mode); + get_tree_entry_if_blob(&o->object.oid, path, + &e->stages[1].oid, &e->stages[1].mode); + get_tree_entry_if_blob(&a->object.oid, path, + &e->stages[2].oid, &e->stages[2].mode); + get_tree_entry_if_blob(&b->object.oid, path, + &e->stages[3].oid, &e->stages[3].mode); item = string_list_insert(entries, path); item->util = e; return e; @@ -349,18 +507,16 @@ static struct string_list *get_unmerged(void) } e = item->util; e->stages[ce_stage(ce)].mode = ce->ce_mode; - hashcpy(e->stages[ce_stage(ce)].sha, ce->sha1); + oidcpy(&e->stages[ce_stage(ce)].oid, &ce->oid); } return unmerged; } -static int string_list_df_name_compare(const void *a, const void *b) +static int string_list_df_name_compare(const char *one, const char *two) { - const struct string_list_item *one = a; - const struct string_list_item *two = b; - int onelen = strlen(one->string); - int twolen = strlen(two->string); + int onelen = strlen(one); + int twolen = strlen(two); /* * Here we only care that entries for D/F conflicts are * adjacent, in particular with the file of the D/F conflict @@ -373,8 +529,8 @@ static int string_list_df_name_compare(const void *a, const void *b) * since in other cases any changes in their order due to * sorting cause no problems for us. */ - int cmp = df_name_compare(one->string, onelen, S_IFDIR, - two->string, twolen, S_IFDIR); + int cmp = df_name_compare(one, onelen, S_IFDIR, + two, twolen, S_IFDIR); /* * Now that 'foo' and 'foo/bar' compare equal, we have to make sure * that 'foo' comes before 'foo/bar'. @@ -388,7 +544,7 @@ static void record_df_conflict_files(struct merge_options *o, struct string_list *entries) { /* If there is a D/F conflict and the file for such a conflict - * currently exist in the working tree, we want to allow it to be + * currently exists in the working tree, we want to allow it to be * removed to make room for the corresponding directory if needed. * The files underneath the directories of such D/F conflicts will * be processed before the corresponding file involved in the D/F @@ -400,7 +556,7 @@ static void record_df_conflict_files(struct merge_options *o, * and the file need to be present, then the D/F file will be * reinstated with a new unique name at the time it is processed. */ - struct string_list df_sorted_entries; + struct string_list df_sorted_entries = STRING_LIST_INIT_NODUP; const char *last_file = NULL; int last_len = 0; int i; @@ -413,14 +569,13 @@ static void record_df_conflict_files(struct merge_options *o, return; /* Ensure D/F conflicts are adjacent in the entries list. */ - memset(&df_sorted_entries, 0, sizeof(struct string_list)); for (i = 0; i < entries->nr; i++) { struct string_list_item *next = &entries->items[i]; string_list_append(&df_sorted_entries, next->string)->util = next->util; } - qsort(df_sorted_entries.items, entries->nr, sizeof(*entries->items), - string_list_df_name_compare); + df_sorted_entries.cmp = string_list_df_name_compare; + string_list_sort(&df_sorted_entries); string_list_clear(&o->df_conflict_file_set, 1); for (i = 0; i < df_sorted_entries.nr; i++) { @@ -459,81 +614,33 @@ static void record_df_conflict_files(struct merge_options *o, 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); - DIFF_OPT_SET(&opts, RECURSIVE); - DIFF_OPT_CLR(&opts, RENAME_EMPTY); - 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_sha1(o_tree->object.oid.hash, tree->object.oid.hash, "", &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(const char *path, const struct diff_filespec *o, +static int update_stages(struct merge_options *opt, const char *path, + const struct diff_filespec *o, const struct diff_filespec *a, const struct diff_filespec *b) { @@ -552,17 +659,38 @@ static int update_stages(const char *path, const struct diff_filespec *o, if (remove_file_from_cache(path)) return -1; if (o) - if (add_cacheinfo(o->mode, o->sha1, path, 1, 0, options)) + if (add_cacheinfo(opt, o->mode, &o->oid, path, 1, 0, options)) return -1; if (a) - if (add_cacheinfo(a->mode, a->sha1, path, 2, 0, options)) + if (add_cacheinfo(opt, a->mode, &a->oid, path, 2, 0, options)) return -1; if (b) - if (add_cacheinfo(b->mode, b->sha1, path, 3, 0, options)) + if (add_cacheinfo(opt, b->mode, &b->oid, path, 3, 0, options)) return -1; 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, @@ -572,9 +700,9 @@ static void update_entry(struct stage_data *entry, entry->stages[1].mode = o->mode; entry->stages[2].mode = a->mode; entry->stages[3].mode = b->mode; - hashcpy(entry->stages[1].sha, o->sha1); - hashcpy(entry->stages[2].sha, a->sha1); - hashcpy(entry->stages[3].sha, b->sha1); + oidcpy(&entry->stages[1].oid, &o->oid); + oidcpy(&entry->stages[2].oid, &a->oid); + oidcpy(&entry->stages[3].oid, &b->oid); } static int remove_file(struct merge_options *o, int clean, @@ -591,7 +719,7 @@ static int remove_file(struct merge_options *o, int clean, if (ignore_case) { struct cache_entry *ce; ce = cache_file_exists(path, strlen(path), ignore_case); - if (ce && ce_stage(ce) == 0) + if (ce && ce_stage(ce) == 0 && strcmp(path, ce->name)) return 0; } if (remove_path(path)) @@ -612,6 +740,7 @@ static void add_flattened_path(struct strbuf *out, const char *s) static char *unique_path(struct merge_options *o, const char *path, const char *branch) { + struct path_hashmap_entry *entry; struct strbuf newpath = STRBUF_INIT; int suffix = 0; size_t base_len; @@ -620,18 +749,26 @@ static char *unique_path(struct merge_options *o, const char *path, const char * add_flattened_path(&newpath, branch); base_len = newpath.len; - while (string_list_has_string(&o->current_file_set, newpath.buf) || - string_list_has_string(&o->current_directory_set, newpath.buf) || - file_exists(newpath.buf)) { + while (hashmap_get_from_hash(&o->current_file_dir_set, + path_hash(newpath.buf), newpath.buf) || + (!o->call_depth && file_exists(newpath.buf))) { strbuf_setlen(&newpath, base_len); strbuf_addf(&newpath, "_%d", suffix++); } - string_list_insert(&o->current_file_set, newpath.buf); + FLEX_ALLOC_MEM(entry, path, newpath.buf, newpath.len); + hashmap_entry_init(entry, path_hash(entry->path)); + hashmap_add(&o->current_file_dir_set, entry); return strbuf_detach(&newpath, NULL); } -static int dir_in_way(const char *path, int check_working_copy) +/** + * Check whether a directory in the index is in the way of an incoming + * file. Return 1 if so. If check_working_copy is non-zero, also + * check the working directory. If empty_ok is non-zero, also return + * 0 in the case where the working-tree dir exists but is empty. + */ +static int dir_in_way(const char *path, int check_working_copy, int empty_ok) { int pos; struct strbuf dirpath = STRBUF_INIT; @@ -651,11 +788,62 @@ static int dir_in_way(const char *path, int check_working_copy) } strbuf_release(&dirpath); - return check_working_copy && !lstat(path, &st) && S_ISDIR(st.st_mode); + return check_working_copy && !lstat(path, &st) && S_ISDIR(st.st_mode) && + !(empty_ok && is_empty_dir(path)); +} + +/* + * Returns whether path was tracked in the index before the merge started, + * and its oid and mode match the specified values + */ +static int was_tracked_and_matches(struct merge_options *o, const char *path, + const struct object_id *oid, unsigned mode) +{ + int pos = index_name_pos(&o->orig_index, path, strlen(path)); + struct cache_entry *ce; + + if (0 > pos) + /* we were not tracking this path before the merge */ + return 0; + + /* See if the file we were tracking before matches */ + ce = o->orig_index.cache[pos]; + return (oid_eq(&ce->oid, oid) && ce->ce_mode == mode); } -static int was_tracked(const char *path) +/* + * Returns whether path was tracked in the index before the merge started + */ +static int was_tracked(struct merge_options *o, const char *path) { + int pos = index_name_pos(&o->orig_index, path, strlen(path)); + + if (0 <= pos) + /* we were tracking this path before the merge */ + return 1; + + return 0; +} + +static int would_lose_untracked(const char *path) +{ + /* + * This may look like it can be simplified to: + * return !was_tracked(o, path) && file_exists(path) + * but it can't. This function needs to know whether path was in + * the working tree due to EITHER having been tracked in the index + * before the merge OR having been put into the working copy and + * index by unpack_trees(). Due to that either-or requirement, we + * check the current index instead of the original one. + * + * Note that we do not need to worry about merge-recursive itself + * updating the index after unpack_trees() and before calling this + * function, because we strictly require all code paths in + * merge-recursive to update the working tree first and the index + * second. Doing otherwise would break + * update_file()/would_lose_untracked(); see every comment in this + * file which mentions "update_stages". + */ int pos = cache_name_pos(path, strlen(path)); if (pos < 0) @@ -671,16 +859,25 @@ static int was_tracked(const char *path) switch (ce_stage(active_cache[pos])) { case 0: case 2: - return 1; + return 0; } pos++; } - return 0; + return file_exists(path); } -static int would_lose_untracked(const char *path) +static int was_dirty(struct merge_options *o, const char *path) { - return !was_tracked(path) && file_exists(path); + struct cache_entry *ce; + int dirty = 1; + + if (o->call_depth || !was_tracked(o, path)) + return !dirty; + + ce = index_file_exists(o->unpack_opts.src_index, + path, strlen(path), ignore_case); + dirty = verify_uptodate(ce, &o->unpack_opts) != 0; + return dirty; } static int make_room_for_path(struct merge_options *o, const char *path) @@ -709,12 +906,10 @@ static int make_room_for_path(struct merge_options *o, const char *path) /* Make sure leading directories are created */ status = safe_create_leading_directories_const(path); if (status) { - if (status == SCLD_EXISTS) { + if (status == SCLD_EXISTS) /* something else exists */ - error(msg, path, _(": perhaps a D/F conflict?")); - return -1; - } - die(msg, path, ""); + return err(o, msg, path, _(": perhaps a D/F conflict?")); + return err(o, msg, path, ""); } /* @@ -722,8 +917,8 @@ static int make_room_for_path(struct merge_options *o, const char *path) * tracking it. */ if (would_lose_untracked(path)) - return error(_("refusing to lose untracked file at '%s'"), - path); + return err(o, _("refusing to lose untracked file at '%s'"), + path); /* Successful unlink is good.. */ if (!unlink(path)) @@ -732,16 +927,18 @@ static int make_room_for_path(struct merge_options *o, const char *path) if (errno == ENOENT) return 0; /* .. but not some other error (who really cares what?) */ - return error(msg, path, _(": perhaps a D/F conflict?")); + return err(o, msg, path, _(": perhaps a D/F conflict?")); } -static void update_file_flags(struct merge_options *o, - const unsigned char *sha, - unsigned mode, - const char *path, - int update_cache, - int update_wd) +static int update_file_flags(struct merge_options *o, + const struct object_id *oid, + unsigned mode, + const char *path, + int update_cache, + int update_wd) { + int ret = 0; + if (o->call_depth) update_wd = 0; @@ -760,14 +957,16 @@ static void update_file_flags(struct merge_options *o, goto update_index; } - buf = read_sha1_file(sha, &type, &size); + buf = read_object_file(oid, &type, &size); if (!buf) - die(_("cannot read object %s '%s'"), sha1_to_hex(sha), path); - if (type != OBJ_BLOB) - die(_("blob expected for %s '%s'"), sha1_to_hex(sha), path); + return err(o, _("cannot read object %s '%s'"), oid_to_hex(oid), path); + if (type != OBJ_BLOB) { + ret = err(o, _("blob expected for %s '%s'"), oid_to_hex(oid), path); + goto free_buf; + } if (S_ISREG(mode)) { struct strbuf strbuf = STRBUF_INIT; - if (convert_to_working_tree(path, buf, size, &strbuf)) { + if (convert_to_working_tree(&the_index, path, buf, size, &strbuf)) { free(buf); size = strbuf.len; buf = strbuf_detach(&strbuf, NULL); @@ -776,8 +975,7 @@ static void update_file_flags(struct merge_options *o, if (make_room_for_path(o, path) < 0) { update_wd = 0; - free(buf); - goto update_index; + goto free_buf; } if (S_ISREG(mode) || (!has_symlinks && S_ISLNK(mode))) { int fd; @@ -786,8 +984,11 @@ static void update_file_flags(struct merge_options *o, else mode = 0666; fd = open(path, O_WRONLY | O_TRUNC | O_CREAT, mode); - if (fd < 0) - die_errno(_("failed to open '%s'"), path); + if (fd < 0) { + ret = err(o, _("failed to open '%s': %s"), + path, strerror(errno)); + goto free_buf; + } write_in_full(fd, buf, size); close(fd); } else if (S_ISLNK(mode)) { @@ -795,31 +996,37 @@ static void update_file_flags(struct merge_options *o, safe_create_leading_directories_const(path); unlink(path); if (symlink(lnk, path)) - die_errno(_("failed to symlink '%s'"), path); + ret = err(o, _("failed to symlink '%s': %s"), + path, strerror(errno)); free(lnk); } else - die(_("do not know what to do with %06o %s '%s'"), - mode, sha1_to_hex(sha), path); + ret = err(o, + _("do not know what to do with %06o %s '%s'"), + mode, oid_to_hex(oid), path); + free_buf: free(buf); } - update_index: - if (update_cache) - add_cacheinfo(mode, sha, path, 0, update_wd, ADD_CACHE_OK_TO_ADD); +update_index: + if (!ret && update_cache) + if (add_cacheinfo(o, mode, oid, path, 0, update_wd, + ADD_CACHE_OK_TO_ADD)) + return -1; + return ret; } -static void update_file(struct merge_options *o, - int clean, - const unsigned char *sha, - unsigned mode, - const char *path) +static int update_file(struct merge_options *o, + int clean, + const struct object_id *oid, + unsigned mode, + const char *path) { - update_file_flags(o, sha, mode, path, o->call_depth || clean, !o->call_depth); + return update_file_flags(o, oid, mode, path, o->call_depth || clean, !o->call_depth); } /* Low level file merging, update and removal */ struct merge_file_info { - unsigned char sha[20]; + struct object_id oid; unsigned mode; unsigned clean:1, merge:1; @@ -871,9 +1078,9 @@ static int merge_3way(struct merge_options *o, name2 = mkpathdup("%s", branch2); } - read_mmblob(&orig, one->sha1); - read_mmblob(&src1, a->sha1); - read_mmblob(&src2, b->sha1); + read_mmblob(&orig, &one->oid); + read_mmblob(&src1, &a->oid); + read_mmblob(&src2, &b->oid); merge_status = ll_merge(result_buf, a->path, &orig, base_name, &src1, name1, &src2, name2, &ll_opts); @@ -887,138 +1094,381 @@ static int merge_3way(struct merge_options *o, return merge_status; } -static struct merge_file_info merge_file_1(struct merge_options *o, - const struct diff_filespec *one, - const struct diff_filespec *a, - const struct diff_filespec *b, - const char *branch1, - const char *branch2) +static int find_first_merges(struct object_array *result, const char *path, + struct commit *a, struct commit *b) +{ + int i, j; + struct object_array merges = OBJECT_ARRAY_INIT; + struct commit *commit; + int contains_another; + + char merged_revision[42]; + const char *rev_args[] = { "rev-list", "--merges", "--ancestry-path", + "--all", merged_revision, NULL }; + struct rev_info revs; + struct setup_revision_opt rev_opts; + + memset(result, 0, sizeof(struct object_array)); + memset(&rev_opts, 0, sizeof(rev_opts)); + + /* get all revisions that merge commit a */ + xsnprintf(merged_revision, sizeof(merged_revision), "^%s", + oid_to_hex(&a->object.oid)); + init_revisions(&revs, NULL); + rev_opts.submodule = path; + /* FIXME: can't handle linked worktrees in submodules yet */ + revs.single_worktree = path != NULL; + setup_revisions(ARRAY_SIZE(rev_args)-1, rev_args, &revs, &rev_opts); + + /* save all revisions from the above list that contain b */ + if (prepare_revision_walk(&revs)) + die("revision walk setup failed"); + while ((commit = get_revision(&revs)) != NULL) { + struct object *o = &(commit->object); + if (in_merge_bases(b, commit)) + add_object_array(o, NULL, &merges); + } + reset_revision_walk(); + + /* Now we've got all merges that contain a and b. Prune all + * merges that contain another found merge and save them in + * result. + */ + for (i = 0; i < merges.nr; i++) { + struct commit *m1 = (struct commit *) merges.objects[i].item; + + contains_another = 0; + for (j = 0; j < merges.nr; j++) { + struct commit *m2 = (struct commit *) merges.objects[j].item; + if (i != j && in_merge_bases(m2, m1)) { + contains_another = 1; + break; + } + } + + if (!contains_another) + add_object_array(merges.objects[i].item, NULL, result); + } + + object_array_clear(&merges); + return result->nr; +} + +static void print_commit(struct commit *commit) { - struct merge_file_info result; - result.merge = 0; - result.clean = 1; + struct strbuf sb = STRBUF_INIT; + struct pretty_print_context ctx = {0}; + ctx.date_mode.type = DATE_NORMAL; + format_commit_message(commit, " %h: %m %s", &sb, &ctx); + fprintf(stderr, "%s\n", sb.buf); + strbuf_release(&sb); +} + +static int merge_submodule(struct merge_options *o, + struct object_id *result, const char *path, + const struct object_id *base, const struct object_id *a, + const struct object_id *b) +{ + struct commit *commit_base, *commit_a, *commit_b; + int parent_count; + struct object_array merges; + + int i; + int search = !o->call_depth; + + /* store a in result in case we fail */ + oidcpy(result, a); + + /* we can not handle deletion conflicts */ + if (is_null_oid(base)) + return 0; + if (is_null_oid(a)) + return 0; + if (is_null_oid(b)) + return 0; + + if (add_submodule_odb(path)) { + output(o, 1, _("Failed to merge submodule %s (not checked out)"), path); + return 0; + } + + if (!(commit_base = lookup_commit_reference(the_repository, base)) || + !(commit_a = lookup_commit_reference(the_repository, a)) || + !(commit_b = lookup_commit_reference(the_repository, b))) { + output(o, 1, _("Failed to merge submodule %s (commits not present)"), path); + return 0; + } + + /* check whether both changes are forward */ + if (!in_merge_bases(commit_base, commit_a) || + !in_merge_bases(commit_base, commit_b)) { + output(o, 1, _("Failed to merge submodule %s (commits don't follow merge-base)"), path); + return 0; + } + + /* Case #1: a is contained in b or vice versa */ + if (in_merge_bases(commit_a, commit_b)) { + oidcpy(result, b); + if (show(o, 3)) { + output(o, 3, _("Fast-forwarding submodule %s to the following commit:"), path); + output_commit_title(o, commit_b); + } else if (show(o, 2)) + output(o, 2, _("Fast-forwarding submodule %s"), path); + else + ; /* no output */ + + return 1; + } + if (in_merge_bases(commit_b, commit_a)) { + oidcpy(result, a); + if (show(o, 3)) { + output(o, 3, _("Fast-forwarding submodule %s to the following commit:"), path); + output_commit_title(o, commit_a); + } else if (show(o, 2)) + output(o, 2, _("Fast-forwarding submodule %s"), path); + else + ; /* no output */ + + return 1; + } + + /* + * Case #2: There are one or more merges that contain a and b in + * the submodule. If there is only one, then present it as a + * suggestion to the user, but leave it marked unmerged so the + * user needs to confirm the resolution. + */ + + /* Skip the search if makes no sense to the calling context. */ + if (!search) + return 0; + + /* find commit which merges them */ + parent_count = find_first_merges(&merges, path, commit_a, commit_b); + switch (parent_count) { + case 0: + output(o, 1, _("Failed to merge submodule %s (merge following commits not found)"), path); + break; + + case 1: + output(o, 1, _("Failed to merge submodule %s (not fast-forward)"), path); + output(o, 2, _("Found a possible merge resolution for the submodule:\n")); + print_commit((struct commit *) merges.objects[0].item); + output(o, 2, _( + "If this is correct simply add it to the index " + "for example\n" + "by using:\n\n" + " git update-index --cacheinfo 160000 %s \"%s\"\n\n" + "which will accept this suggestion.\n"), + oid_to_hex(&merges.objects[0].item->oid), path); + break; + + default: + output(o, 1, _("Failed to merge submodule %s (multiple merges found)"), path); + for (i = 0; i < merges.nr; i++) + print_commit((struct commit *) merges.objects[i].item); + } + + object_array_clear(&merges); + return 0; +} + +static int merge_file_1(struct merge_options *o, + const struct diff_filespec *one, + const struct diff_filespec *a, + const struct diff_filespec *b, + const char *filename, + const char *branch1, + const char *branch2, + struct merge_file_info *result) +{ + result->merge = 0; + result->clean = 1; if ((S_IFMT & a->mode) != (S_IFMT & b->mode)) { - result.clean = 0; + result->clean = 0; if (S_ISREG(a->mode)) { - result.mode = a->mode; - hashcpy(result.sha, a->sha1); + result->mode = a->mode; + oidcpy(&result->oid, &a->oid); } else { - result.mode = b->mode; - hashcpy(result.sha, b->sha1); + result->mode = b->mode; + oidcpy(&result->oid, &b->oid); } } else { - if (!sha_eq(a->sha1, one->sha1) && !sha_eq(b->sha1, one->sha1)) - result.merge = 1; + if (!oid_eq(&a->oid, &one->oid) && !oid_eq(&b->oid, &one->oid)) + result->merge = 1; /* * Merge modes */ if (a->mode == b->mode || a->mode == one->mode) - result.mode = b->mode; + result->mode = b->mode; else { - result.mode = a->mode; + result->mode = a->mode; if (b->mode != one->mode) { - result.clean = 0; - result.merge = 1; + result->clean = 0; + result->merge = 1; } } - if (sha_eq(a->sha1, b->sha1) || sha_eq(a->sha1, one->sha1)) - hashcpy(result.sha, b->sha1); - else if (sha_eq(b->sha1, one->sha1)) - hashcpy(result.sha, a->sha1); + if (oid_eq(&a->oid, &b->oid) || oid_eq(&a->oid, &one->oid)) + oidcpy(&result->oid, &b->oid); + else if (oid_eq(&b->oid, &one->oid)) + oidcpy(&result->oid, &a->oid); else if (S_ISREG(a->mode)) { mmbuffer_t result_buf; - int merge_status; + int ret = 0, merge_status; merge_status = merge_3way(o, &result_buf, one, a, b, branch1, branch2); if ((merge_status < 0) || !result_buf.ptr) - die(_("Failed to execute internal merge")); + ret = err(o, _("Failed to execute internal merge")); - if (write_sha1_file(result_buf.ptr, result_buf.size, - blob_type, result.sha)) - die(_("Unable to add %s to database"), - a->path); + 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); free(result_buf.ptr); - result.clean = (merge_status == 0); + if (ret) + return ret; + result->clean = (merge_status == 0); } else if (S_ISGITLINK(a->mode)) { - result.clean = merge_submodule(result.sha, - one->path, one->sha1, - a->sha1, b->sha1, - !o->call_depth); + result->clean = merge_submodule(o, &result->oid, + one->path, + &one->oid, + &a->oid, + &b->oid); } else if (S_ISLNK(a->mode)) { - hashcpy(result.sha, a->sha1); - - if (!sha_eq(a->sha1, b->sha1)) - result.clean = 0; - } else { - die(_("unsupported object type in the tree")); - } + switch (o->recursive_variant) { + case MERGE_RECURSIVE_NORMAL: + oidcpy(&result->oid, &a->oid); + if (!oid_eq(&a->oid, &b->oid)) + result->clean = 0; + break; + case MERGE_RECURSIVE_OURS: + oidcpy(&result->oid, &a->oid); + break; + case MERGE_RECURSIVE_THEIRS: + oidcpy(&result->oid, &b->oid); + break; + } + } else + BUG("unsupported object type in the tree"); } - return result; + if (result->merge) + output(o, 2, _("Auto-merging %s"), filename); + + return 0; } -static struct merge_file_info -merge_file_special_markers(struct merge_options *o, - const struct diff_filespec *one, - const struct diff_filespec *a, - const struct diff_filespec *b, - const char *branch1, - const char *filename1, - const char *branch2, - const char *filename2) +static int merge_file_special_markers(struct merge_options *o, + const struct diff_filespec *one, + const struct diff_filespec *a, + const struct diff_filespec *b, + const char *target_filename, + const char *branch1, + const char *filename1, + const char *branch2, + const char *filename2, + struct merge_file_info *mfi) { char *side1 = NULL; char *side2 = NULL; - struct merge_file_info mfi; + int ret; if (filename1) side1 = xstrfmt("%s:%s", branch1, filename1); if (filename2) side2 = xstrfmt("%s:%s", branch2, filename2); - mfi = merge_file_1(o, one, a, b, - side1 ? side1 : branch1, side2 ? side2 : branch2); + ret = merge_file_1(o, one, a, b, target_filename, + side1 ? side1 : branch1, + side2 ? side2 : branch2, mfi); + free(side1); free(side2); - return mfi; + return ret; } -static struct merge_file_info merge_file_one(struct merge_options *o, - const char *path, - const unsigned char *o_sha, int o_mode, - const unsigned char *a_sha, int a_mode, - const unsigned char *b_sha, int b_mode, - const char *branch1, - const char *branch2) +static int merge_file_one(struct merge_options *o, + const char *path, + const struct object_id *o_oid, int o_mode, + const struct object_id *a_oid, int a_mode, + const struct object_id *b_oid, int b_mode, + const char *branch1, + const char *branch2, + struct merge_file_info *mfi) { struct diff_filespec one, a, b; one.path = a.path = b.path = (char *)path; - hashcpy(one.sha1, o_sha); + oidcpy(&one.oid, o_oid); one.mode = o_mode; - hashcpy(a.sha1, a_sha); + oidcpy(&a.oid, a_oid); a.mode = a_mode; - hashcpy(b.sha1, b_sha); + oidcpy(&b.oid, b_oid); b.mode = b_mode; - return merge_file_1(o, &one, &a, &b, branch1, branch2); + return merge_file_1(o, &one, &a, &b, path, branch1, branch2, mfi); +} + +static int handle_rename_via_dir(struct merge_options *o, + struct diff_filepair *pair, + const char *rename_branch, + const char *other_branch) +{ + /* + * Handle file adds that need to be renamed due to directory rename + * detection. This differs from handle_rename_normal, because + * there is no content merge to do; just move the file into the + * desired final location. + */ + 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 void handle_change_delete(struct merge_options *o, - const char *path, - const unsigned char *o_sha, int o_mode, - const unsigned char *a_sha, int a_mode, - const unsigned char *b_sha, int b_mode, - const char *change, const char *change_past) +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, + const struct object_id *changed_oid, + int changed_mode, + const char *change_branch, + const char *delete_branch, + const char *change, const char *change_past) { - char *renamed = NULL; - if (dir_in_way(path, !o->call_depth)) { - renamed = unique_path(o, path, a_sha ? o->branch1 : o->branch2); + char *alt_path = NULL; + const char *update_path = path; + int ret = 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); } if (o->call_depth) { @@ -1027,96 +1477,103 @@ static void handle_change_delete(struct merge_options *o, * correct; since there is no true "middle point" between * them, simply reuse the base version for virtual merge base. */ - remove_file_from_cache(path); - update_file(o, 0, o_sha, o_mode, renamed ? renamed : path); - } else if (!a_sha) { - if (!renamed) { - output(o, 1, _("CONFLICT (%s/delete): %s deleted in %s " - "and %s in %s. Version %s of %s left in tree."), - change, path, o->branch1, change_past, - o->branch2, o->branch2, path); - update_file(o, 0, b_sha, b_mode, path); - } else { - output(o, 1, _("CONFLICT (%s/delete): %s deleted in %s " - "and %s in %s. Version %s of %s left in tree at %s."), - change, path, o->branch1, change_past, - o->branch2, o->branch2, path, renamed); - update_file(o, 0, b_sha, b_mode, renamed); - } + ret = remove_file_from_cache(path); + if (!ret) + ret = update_file(o, 0, o_oid, o_mode, update_path); } else { - if (!renamed) { - output(o, 1, _("CONFLICT (%s/delete): %s deleted in %s " - "and %s in %s. Version %s of %s left in tree."), - change, path, o->branch2, change_past, - o->branch1, o->branch1, path); + /* + * Despite the four nearly duplicate messages and argument + * lists below and the ugliness of the nested if-statements, + * having complete messages makes the job easier for + * translators. + * + * The slight variance among the cases is due to the fact + * that: + * 1) directory/file conflicts (in effect if + * !alt_path) could cause us to need to write the + * file to a different path. + * 2) renames (in effect if !old_path) could mean that + * there are two names for the path that the user + * may know the file by. + */ + if (!alt_path) { + if (!old_path) { + output(o, 1, _("CONFLICT (%s/delete): %s deleted in %s " + "and %s in %s. Version %s of %s left in tree."), + change, path, delete_branch, change_past, + change_branch, change_branch, path); + } else { + output(o, 1, _("CONFLICT (%s/delete): %s deleted in %s " + "and %s to %s in %s. Version %s of %s left in tree."), + change, old_path, delete_branch, change_past, path, + change_branch, change_branch, path); + } } else { - output(o, 1, _("CONFLICT (%s/delete): %s deleted in %s " - "and %s in %s. Version %s of %s left in tree at %s."), - change, path, o->branch2, change_past, - o->branch1, o->branch1, path, renamed); - update_file(o, 0, a_sha, a_mode, renamed); + if (!old_path) { + output(o, 1, _("CONFLICT (%s/delete): %s deleted in %s " + "and %s in %s. Version %s of %s left in tree at %s."), + change, path, delete_branch, change_past, + change_branch, change_branch, path, alt_path); + } else { + output(o, 1, _("CONFLICT (%s/delete): %s deleted in %s " + "and %s to %s in %s. Version %s of %s left in tree at %s."), + change, old_path, delete_branch, change_past, path, + change_branch, change_branch, path, alt_path); + } } /* - * No need to call update_file() on path when !renamed, since - * that would needlessly touch path. We could call - * update_file_flags() with update_cache=0 and update_wd=0, - * but that's a no-op. + * No need to call update_file() on path when change_branch == + * o->branch1 && !alt_path, since that would needlessly touch + * path. We could call update_file_flags() with update_cache=0 + * and update_wd=0, but that's a no-op. */ + if (change_branch != o->branch1 || alt_path) + ret = update_file(o, 0, changed_oid, changed_mode, update_path); } - free(renamed); + free(alt_path); + + return ret; } -static void conflict_rename_delete(struct merge_options *o, - struct diff_filepair *pair, - const char *rename_branch, - const char *other_branch) +static int handle_rename_delete(struct merge_options *o, + struct diff_filepair *pair, + const char *rename_branch, + const char *delete_branch) { const struct diff_filespec *orig = pair->one; const struct diff_filespec *dest = pair->two; - const unsigned char *a_sha = NULL; - const unsigned char *b_sha = NULL; - int a_mode = 0; - int b_mode = 0; - - if (rename_branch == o->branch1) { - a_sha = dest->sha1; - a_mode = dest->mode; - } else { - b_sha = dest->sha1; - b_mode = dest->mode; - } - - handle_change_delete(o, - o->call_depth ? orig->path : dest->path, - orig->sha1, orig->mode, - a_sha, a_mode, - b_sha, b_mode, - _("rename"), _("renamed")); - if (o->call_depth) { - remove_file_from_cache(dest->path); - } else { - update_stages(dest->path, NULL, - rename_branch == o->branch1 ? dest : NULL, - rename_branch == o->branch1 ? NULL : dest); - } + if (handle_change_delete(o, + o->call_depth ? orig->path : dest->path, + o->call_depth ? NULL : orig->path, + &orig->oid, orig->mode, + &dest->oid, dest->mode, + rename_branch, delete_branch, + _("rename"), _("renamed"))) + return -1; + if (o->call_depth) + return remove_file_from_cache(dest->path); + else + return update_stages(o, dest->path, NULL, + rename_branch == o->branch1 ? dest : NULL, + rename_branch == o->branch1 ? NULL : dest); } static struct diff_filespec *filespec_from_entry(struct diff_filespec *target, struct stage_data *entry, int stage) { - unsigned char *sha = entry->stages[stage].sha; + struct object_id *oid = &entry->stages[stage].oid; unsigned mode = entry->stages[stage].mode; - if (mode == 0 || is_null_sha1(sha)) + if (mode == 0 || is_null_oid(oid)) return NULL; - hashcpy(target->sha1, sha); + oidcpy(&target->oid, oid); target->mode = mode; return target; } -static void handle_file(struct merge_options *o, +static int handle_file(struct merge_options *o, struct diff_filespec *rename, int stage, struct rename_conflict_info *ci) @@ -1126,6 +1583,7 @@ static void handle_file(struct merge_options *o, const char *cur_branch, *other_branch; struct diff_filespec other; struct diff_filespec *add; + int ret; if (stage == 2) { dst_entry = ci->dst_entry1; @@ -1139,30 +1597,51 @@ static void handle_file(struct merge_options *o, 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); - update_file(o, 0, add->sha1, add->mode, add_name); + 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)) { + 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); } } - update_file(o, 0, rename->sha1, rename->mode, dst_name); - if (stage == 2) - update_stages(rename->path, NULL, rename, add); + if ((ret = update_file(o, 0, &rename->oid, rename->mode, dst_name))) + ; /* fall through, do allow dst_name to be released */ + else if (stage == 2) + ret = update_stages(o, rename->path, NULL, rename, add); else - update_stages(rename->path, NULL, add, rename); + ret = update_stages(o, rename->path, NULL, add, rename); if (dst_name != rename->path) free(dst_name); + + return ret; } -static void conflict_rename_rename_1to2(struct merge_options *o, - struct rename_conflict_info *ci) +static int handle_rename_rename_1to2(struct merge_options *o, + struct rename_conflict_info *ci) { /* One file was renamed in both branches, but to different names. */ struct diff_filespec *one = ci->pair1->one; @@ -1179,18 +1658,21 @@ static void conflict_rename_rename_1to2(struct merge_options *o, struct merge_file_info mfi; struct diff_filespec other; struct diff_filespec *add; - mfi = merge_file_one(o, one->path, - one->sha1, one->mode, - a->sha1, a->mode, - b->sha1, b->mode, - ci->branch1, ci->branch2); + if (merge_file_one(o, one->path, + &one->oid, one->mode, + &a->oid, a->mode, + &b->oid, b->mode, + ci->branch1, ci->branch2, &mfi)) + return -1; + /* * FIXME: For rename/add-source conflicts (if we could detect * such), this is wrong. We should instead find a unique * pathname and then either rename the add-source file to that * unique path, or use that unique path instead of src here. */ - update_file(o, 0, mfi.sha, mfi.mode, one->path); + if (update_file(o, 0, &mfi.oid, mfi.mode, one->path)) + return -1; /* * Above, we put the merged content at the merge-base's @@ -1201,23 +1683,27 @@ static void conflict_rename_rename_1to2(struct merge_options *o, * resolving the conflict at that path in its favor. */ add = filespec_from_entry(&other, ci->dst_entry1, 2 ^ 1); - if (add) - update_file(o, 0, add->sha1, add->mode, a->path); + if (add) { + if (update_file(o, 0, &add->oid, add->mode, a->path)) + return -1; + } else remove_file_from_cache(a->path); add = filespec_from_entry(&other, ci->dst_entry2, 3 ^ 1); - if (add) - update_file(o, 0, add->sha1, add->mode, b->path); + if (add) { + if (update_file(o, 0, &add->oid, add->mode, b->path)) + return -1; + } else remove_file_from_cache(b->path); - } else { - handle_file(o, a, 2, ci); - handle_file(o, b, 3, ci); - } + } else if (handle_file(o, a, 2, ci) || handle_file(o, b, 3, ci)) + return -1; + + return 0; } -static void conflict_rename_rename_2to1(struct merge_options *o, - struct rename_conflict_info *ci) +static int handle_rename_rename_2to1(struct merge_options *o, + struct rename_conflict_info *ci) { /* Two files, a & b, were renamed to the same thing, c. */ struct diff_filespec *a = ci->pair1->one; @@ -1225,8 +1711,11 @@ static void conflict_rename_rename_2to1(struct merge_options *o, struct diff_filespec *c1 = ci->pair1->two; struct diff_filespec *c2 = ci->pair2->two; char *path = c1->path; /* == c2->path */ + char *path_side_1_desc; + char *path_side_2_desc; struct merge_file_info mfi_c1; struct merge_file_info mfi_c2; + int ret; output(o, 1, _("CONFLICT (rename/rename): " "Rename %s->%s in %s. " @@ -1234,15 +1723,22 @@ static void conflict_rename_rename_2to1(struct merge_options *o, a->path, c1->path, ci->branch1, b->path, c2->path, ci->branch2); - remove_file(o, 1, a->path, would_lose_untracked(a->path)); - remove_file(o, 1, b->path, would_lose_untracked(b->path)); - - mfi_c1 = merge_file_special_markers(o, a, c1, &ci->ren1_other, - o->branch1, c1->path, - o->branch2, ci->ren1_other.path); - mfi_c2 = merge_file_special_markers(o, b, &ci->ren2_other, c2, - o->branch1, ci->ren2_other.path, - o->branch2, c2->path); + remove_file(o, 1, a->path, o->call_depth || would_lose_untracked(a->path)); + remove_file(o, 1, b->path, o->call_depth || would_lose_untracked(b->path)); + + path_side_1_desc = xstrfmt("%s (was %s)", path, a->path); + path_side_2_desc = xstrfmt("%s (was %s)", path, b->path); + if (merge_file_special_markers(o, a, c1, &ci->ren1_other, + path_side_1_desc, + o->branch1, c1->path, + o->branch2, ci->ren1_other.path, &mfi_c1) || + merge_file_special_markers(o, b, &ci->ren2_other, c2, + path_side_2_desc, + o->branch1, ci->ren2_other.path, + o->branch2, c2->path, &mfi_c2)) + return -1; + free(path_side_1_desc); + free(path_side_2_desc); if (o->call_depth) { /* @@ -1253,19 +1749,813 @@ static void conflict_rename_rename_2to1(struct merge_options *o, * again later for the non-recursive merge. */ remove_file(o, 0, path, 0); - update_file(o, 0, mfi_c1.sha, mfi_c1.mode, a->path); - update_file(o, 0, mfi_c2.sha, mfi_c2.mode, b->path); + ret = update_file(o, 0, &mfi_c1.oid, mfi_c1.mode, a->path); + if (!ret) + ret = update_file(o, 0, &mfi_c2.oid, mfi_c2.mode, + b->path); } else { char *new_path1 = unique_path(o, path, ci->branch1); 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); - update_file(o, 0, mfi_c1.sha, mfi_c1.mode, new_path1); - update_file(o, 0, mfi_c2.sha, mfi_c2.mode, new_path2); + 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); } + + 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 = merge_detect_rename(o); + /* + * We do not have logic to handle the detection of copies. In + * fact, it may not even make sense to add such logic: would we + * really want a change to a base file to be propagated through + * multiple other files by a merge? + */ + if (opts.detect_rename > DIFF_DETECT_RENAME) + 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(*dir_renames)); + 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(*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 = xstrdup(path); + char *end; + struct dir_rename_entry *entry = NULL;; + + while ((end = strrchr(temp, '/'))) { + *end = '\0'; + entry = dir_rename_find_entry(dir_renames, temp); + if (entry) + break; + } + free(temp); + return entry; +} + +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 handle_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, @@ -1315,14 +2605,11 @@ static int process_renames(struct merge_options *o, branch1 = o->branch1; branch2 = o->branch2; } else { - struct rename *tmp; renames1 = b_renames; renames2Dst = &a_by_dst; branch1 = o->branch2; branch2 = o->branch1; - tmp = ren2; - ren2 = ren1; - ren1 = tmp; + SWAP(ren2, ren1); } if (ren1->processed) @@ -1343,7 +2630,7 @@ static int process_renames(struct merge_options *o, const char *ren2_dst = ren2->pair->two->path; enum rename_type rename_type; if (strcmp(ren1_src, ren2_src) != 0) - die("ren1_src != ren2_src"); + BUG("ren1_src != ren2_src"); ren2->dst_entry->processed = 1; ren2->processed = 1; if (strcmp(ren1_dst, ren2_dst) != 0) { @@ -1377,7 +2664,7 @@ static int process_renames(struct merge_options *o, ren2 = lookup->util; ren2_dst = ren2->pair->two->path; if (strcmp(ren1_dst, ren2_dst) != 0) - die("ren1_dst != ren2_dst"); + BUG("ren1_dst != ren2_dst"); clean_merge = 0; ren2->processed = 1; @@ -1419,15 +2706,29 @@ static int process_renames(struct merge_options *o, * add-source case). */ remove_file(o, 1, ren1_src, - renamed_stage == 2 || !was_tracked(ren1_src)); + renamed_stage == 2 || !was_tracked(o, ren1_src)); - hashcpy(src_other.sha1, ren1->src_entry->stages[other_stage].sha); + oidcpy(&src_other.oid, + &ren1->src_entry->stages[other_stage].oid); src_other.mode = ren1->src_entry->stages[other_stage].mode; - hashcpy(dst_other.sha1, ren1->dst_entry->stages[other_stage].sha); + oidcpy(&dst_other.oid, + &ren1->dst_entry->stages[other_stage].oid); dst_other.mode = ren1->dst_entry->stages[other_stage].mode; try_merge = 0; - if (sha_eq(src_other.sha1, null_sha1)) { + if (oid_eq(&src_other.oid, &null_oid) && + ren1->add_turned_into_rename) { + setup_rename_conflict_info(RENAME_VIA_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, @@ -1439,7 +2740,7 @@ static int process_renames(struct merge_options *o, NULL, NULL); } else if ((dst_other.mode == ren1->pair->two->mode) && - sha_eq(dst_other.sha1, ren1->pair->two->sha1)) { + oid_eq(&dst_other.oid, &ren1->pair->two->oid)) { /* * Added file on the other side identical to * the file being renamed: clean merge. @@ -1448,13 +2749,14 @@ static int process_renames(struct merge_options *o, * update_file_flags() instead of * update_file(). */ - update_file_flags(o, - ren1->pair->two->sha1, - ren1->pair->two->mode, - ren1_dst, - 1, /* update_cache */ - 0 /* update_wd */); - } else if (!sha_eq(dst_other.sha1, null_sha1)) { + if (update_file_flags(o, + &ren1->pair->two->oid, + ren1->pair->two->mode, + ren1_dst, + 1, /* update_cache */ + 0 /* update_wd */)) + clean_merge = -1; + } else if (!oid_eq(&dst_other.oid, &null_oid)) { clean_merge = 0; try_merge = 1; output(o, 1, _("CONFLICT (rename/add): Rename %s->%s in %s. " @@ -1463,22 +2765,33 @@ static int process_renames(struct merge_options *o, ren1_dst, branch2); if (o->call_depth) { struct merge_file_info mfi; - mfi = merge_file_one(o, ren1_dst, null_sha1, 0, - ren1->pair->two->sha1, ren1->pair->two->mode, - dst_other.sha1, dst_other.mode, - branch1, branch2); + if (merge_file_one(o, ren1_dst, &null_oid, 0, + &ren1->pair->two->oid, + ren1->pair->two->mode, + &dst_other.oid, + dst_other.mode, + branch1, branch2, &mfi)) { + clean_merge = -1; + goto cleanup_and_return; + } output(o, 1, _("Adding merged %s"), ren1_dst); - update_file(o, 0, mfi.sha, mfi.mode, ren1_dst); + if (update_file(o, 0, &mfi.oid, + mfi.mode, ren1_dst)) + clean_merge = -1; try_merge = 0; } else { char *new_path = unique_path(o, ren1_dst, branch2); output(o, 1, _("Adding as %s instead"), new_path); - update_file(o, 0, dst_other.sha1, dst_other.mode, new_path); + if (update_file(o, 0, &dst_other.oid, + dst_other.mode, new_path)) + clean_merge = -1; free(new_path); } } else try_merge = 1; + if (clean_merge < 0) + goto cleanup_and_return; if (try_merge) { struct diff_filespec *one, *a, *b; src_other.path = (char *)ren1_src; @@ -1505,36 +2818,139 @@ static int process_renames(struct merge_options *o, } } } +cleanup_and_return: string_list_clear(&a_by_dst, 0); string_list_clear(&b_by_dst, 0); return clean_merge; } -static unsigned char *stage_sha(const unsigned char *sha, unsigned mode) +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 detect_and_process_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 (!merge_detect_rename(o)) + 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) { - return (is_null_sha1(sha) || mode == 0) ? NULL: (unsigned char *)sha; + final_cleanup_rename(re_info->head_renames); + final_cleanup_rename(re_info->merge_renames); } -static int read_sha1_strbuf(const unsigned char *sha1, struct strbuf *dst) +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; +} + +static int read_oid_strbuf(struct merge_options *o, + const struct object_id *oid, + struct strbuf *dst) { void *buf; enum object_type type; unsigned long size; - buf = read_sha1_file(sha1, &type, &size); + buf = read_object_file(oid, &type, &size); if (!buf) - return error(_("cannot read object %s"), sha1_to_hex(sha1)); + return err(o, _("cannot read object %s"), oid_to_hex(oid)); if (type != OBJ_BLOB) { free(buf); - return error(_("object %s is not a blob"), sha1_to_hex(sha1)); + return err(o, _("object %s is not a blob"), oid_to_hex(oid)); } strbuf_attach(dst, buf, size, size + 1); return 0; } -static int blob_unchanged(const unsigned char *o_sha, +static int blob_unchanged(struct merge_options *opt, + const struct object_id *o_oid, unsigned o_mode, - const unsigned char *a_sha, + const struct object_id *a_oid, unsigned a_mode, int renormalize, const char *path) { @@ -1544,21 +2960,21 @@ static int blob_unchanged(const unsigned char *o_sha, if (a_mode != o_mode) return 0; - if (sha_eq(o_sha, a_sha)) + if (oid_eq(o_oid, a_oid)) return 1; if (!renormalize) return 0; - assert(o_sha && a_sha); - if (read_sha1_strbuf(o_sha, &o) || read_sha1_strbuf(a_sha, &a)) + assert(o_oid && a_oid); + if (read_oid_strbuf(opt, o_oid, &o) || read_oid_strbuf(opt, a_oid, &a)) goto error_return; /* * Note: binary | is used so that both renormalizations are * performed. Comparison can be skipped if both files are * unchanged since their sha1s have already been compared. */ - if (renormalize_buffer(path, o.buf, o.len, &o) | - renormalize_buffer(path, a.buf, a.len, &a)) + if (renormalize_buffer(&the_index, path, o.buf, o.len, &o) | + renormalize_buffer(&the_index, path, a.buf, a.len, &a)) ret = (o.len == a.len && !memcmp(o.buf, a.buf, o.len)); error_return: @@ -1567,25 +2983,42 @@ error_return: return ret; } -static void handle_modify_delete(struct merge_options *o, - const char *path, - unsigned char *o_sha, int o_mode, - unsigned char *a_sha, int a_mode, - unsigned char *b_sha, int b_mode) +static int handle_modify_delete(struct merge_options *o, + const char *path, + struct object_id *o_oid, int o_mode, + struct object_id *a_oid, int a_mode, + struct object_id *b_oid, int b_mode) { - handle_change_delete(o, - path, - o_sha, o_mode, - a_sha, a_mode, - b_sha, b_mode, - _("modify"), _("modified")); + const char *modify_branch, *delete_branch; + struct object_id *changed_oid; + int changed_mode; + + if (a_oid) { + modify_branch = o->branch1; + delete_branch = o->branch2; + changed_oid = a_oid; + changed_mode = a_mode; + } else { + modify_branch = o->branch2; + delete_branch = o->branch1; + changed_oid = b_oid; + changed_mode = b_mode; + } + + return handle_change_delete(o, + path, NULL, + o_oid, o_mode, + changed_oid, changed_mode, + modify_branch, delete_branch, + _("modify"), _("modified")); } static int merge_content(struct merge_options *o, const char *path, - unsigned char *o_sha, int o_mode, - unsigned char *a_sha, int a_mode, - unsigned char *b_sha, int b_mode, + int is_dirty, + struct object_id *o_oid, int o_mode, + struct object_id *a_oid, int a_mode, + struct object_id *b_oid, int b_mode, struct rename_conflict_info *rename_conflict_info) { const char *reason = _("content"); @@ -1594,16 +3027,16 @@ static int merge_content(struct merge_options *o, struct diff_filespec one, a, b; unsigned df_conflict_remains = 0; - if (!o_sha) { + if (!o_oid) { reason = _("add/add"); - o_sha = (unsigned char *)null_sha1; + o_oid = (struct object_id *)&null_oid; } one.path = a.path = b.path = (char *)path; - hashcpy(one.sha1, o_sha); + oidcpy(&one.oid, o_oid); one.mode = o_mode; - hashcpy(a.sha1, a_sha); + oidcpy(&a.oid, a_oid); a.mode = a_mode; - hashcpy(b.sha1, b_sha); + oidcpy(&b.oid, b_oid); b.mode = b_mode; if (rename_conflict_info) { @@ -1619,31 +3052,46 @@ static int merge_content(struct merge_options *o, o->branch2 == rename_conflict_info->branch1) ? pair1->two->path : pair1->one->path; - if (dir_in_way(path, !o->call_depth)) + if (dir_in_way(path, !o->call_depth, + S_ISGITLINK(pair1->two->mode))) df_conflict_remains = 1; } - mfi = merge_file_special_markers(o, &one, &a, &b, - o->branch1, path1, - o->branch2, path2); + if (merge_file_special_markers(o, &one, &a, &b, path, + o->branch1, path1, + o->branch2, path2, &mfi)) + return -1; + + /* + * We can skip updating the working tree file iff: + * a) The merge is clean + * b) The merge matches what was in HEAD (content, mode, pathname) + * c) The target path is usable (i.e. not involved in D/F conflict) + */ + if (mfi.clean && + was_tracked_and_matches(o, path, &mfi.oid, mfi.mode) && + !df_conflict_remains) { + int pos; + struct cache_entry *ce; - if (mfi.clean && !df_conflict_remains && - sha_eq(mfi.sha, a_sha) && mfi.mode == a_mode) { - int path_renamed_outside_HEAD; output(o, 3, _("Skipped %s (merged same as existing)"), path); + if (add_cacheinfo(o, mfi.mode, &mfi.oid, path, + 0, (!o->call_depth && !is_dirty), 0)) + return -1; /* - * The content merge resulted in the same file contents we - * already had. We can return early if those file contents - * are recorded at the correct path (which may not be true - * if the merge involves a rename). + * However, add_cacheinfo() will delete the old cache entry + * and add a new one. We need to copy over any skip_worktree + * flag to avoid making the file appear as if it were + * deleted by the user. */ - path_renamed_outside_HEAD = !path2 || !strcmp(path, path2); - if (!path_renamed_outside_HEAD) { - add_cacheinfo(mfi.mode, mfi.sha, path, - 0, (!o->call_depth), 0); - return mfi.clean; + pos = index_name_pos(&o->orig_index, path, strlen(path)); + ce = o->orig_index.cache[pos]; + if (ce_skip_worktree(ce)) { + pos = index_name_pos(&the_index, path, strlen(path)); + ce = the_index.cache[pos]; + ce->ce_flags |= CE_SKIP_WORKTREE; } - } else - output(o, 2, _("Auto-merging %s"), path); + return mfi.clean; + } if (!mfi.clean) { if (S_ISGITLINK(mfi.mode)) @@ -1651,38 +3099,59 @@ static int merge_content(struct merge_options *o, output(o, 1, _("CONFLICT (%s): Merge conflict in %s"), reason, path); if (rename_conflict_info && !df_conflict_remains) - update_stages(path, &one, &a, &b); + if (update_stages(o, path, &one, &a, &b)) + return -1; } - if (df_conflict_remains) { + if (df_conflict_remains || is_dirty) { char *new_path; if (o->call_depth) { remove_file_from_cache(path); } else { - if (!mfi.clean) - update_stages(path, &one, &a, &b); - else { - int file_from_stage2 = was_tracked(path); + if (!mfi.clean) { + if (update_stages(o, path, &one, &a, &b)) + return -1; + } else { + int file_from_stage2 = was_tracked(o, path); struct diff_filespec merged; - hashcpy(merged.sha1, mfi.sha); + oidcpy(&merged.oid, &mfi.oid); merged.mode = mfi.mode; - update_stages(path, NULL, - file_from_stage2 ? &merged : NULL, - file_from_stage2 ? NULL : &merged); + if (update_stages(o, path, NULL, + file_from_stage2 ? &merged : NULL, + file_from_stage2 ? NULL : &merged)) + return -1; } } new_path = unique_path(o, path, rename_conflict_info->branch1); + if (is_dirty) { + output(o, 1, _("Refusing to lose dirty file at %s"), + path); + } output(o, 1, _("Adding as %s instead"), new_path); - update_file(o, 0, mfi.sha, mfi.mode, new_path); + if (update_file(o, 0, &mfi.oid, mfi.mode, new_path)) { + free(new_path); + return -1; + } free(new_path); mfi.clean = 0; - } else { - update_file(o, mfi.clean, mfi.sha, mfi.mode, path); - } - return mfi.clean; + } else if (update_file(o, mfi.clean, &mfi.oid, mfi.mode, path)) + return -1; + return !is_dirty && mfi.clean; +} +static int handle_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) +{ + /* Merge the content and write it out */ + return merge_content(o, path, was_dirty(o, path), + o_oid, o_mode, a_oid, a_mode, b_oid, b_mode, + ci); } /* Per entry merge function */ @@ -1694,9 +3163,9 @@ static int process_entry(struct merge_options *o, unsigned o_mode = entry->stages[1].mode; unsigned a_mode = entry->stages[2].mode; unsigned b_mode = entry->stages[3].mode; - unsigned char *o_sha = stage_sha(entry->stages[1].sha, o_mode); - unsigned char *a_sha = stage_sha(entry->stages[2].sha, a_mode); - unsigned char *b_sha = stage_sha(entry->stages[3].sha, b_mode); + struct object_id *o_oid = stage_oid(&entry->stages[1].oid, o_mode); + struct object_id *a_oid = stage_oid(&entry->stages[2].oid, a_mode); + struct object_id *b_oid = stage_oid(&entry->stages[3].oid, b_mode); entry->processed = 1; if (entry->rename_conflict_info) { @@ -1704,100 +3173,119 @@ static int process_entry(struct merge_options *o, switch (conflict_info->rename_type) { case RENAME_NORMAL: case RENAME_ONE_FILE_TO_ONE: - clean_merge = merge_content(o, path, - o_sha, o_mode, a_sha, a_mode, b_sha, b_mode, - conflict_info); + clean_merge = handle_rename_normal(o, + path, + o_oid, o_mode, + a_oid, a_mode, + b_oid, b_mode, + conflict_info); + break; + case RENAME_VIA_DIR: + clean_merge = 1; + if (handle_rename_via_dir(o, + conflict_info->pair1, + conflict_info->branch1, + conflict_info->branch2)) + clean_merge = -1; break; case RENAME_DELETE: clean_merge = 0; - conflict_rename_delete(o, conflict_info->pair1, - conflict_info->branch1, - conflict_info->branch2); + if (handle_rename_delete(o, + conflict_info->pair1, + conflict_info->branch1, + conflict_info->branch2)) + clean_merge = -1; break; case RENAME_ONE_FILE_TO_TWO: clean_merge = 0; - conflict_rename_rename_1to2(o, conflict_info); + if (handle_rename_rename_1to2(o, conflict_info)) + clean_merge = -1; break; case RENAME_TWO_FILES_TO_ONE: clean_merge = 0; - conflict_rename_rename_2to1(o, conflict_info); + if (handle_rename_rename_2to1(o, conflict_info)) + clean_merge = -1; break; default: entry->processed = 0; break; } - } else if (o_sha && (!a_sha || !b_sha)) { + } else if (o_oid && (!a_oid || !b_oid)) { /* Case A: Deleted in one */ - if ((!a_sha && !b_sha) || - (!b_sha && blob_unchanged(o_sha, o_mode, a_sha, a_mode, normalize, path)) || - (!a_sha && blob_unchanged(o_sha, o_mode, b_sha, b_mode, normalize, path))) { + if ((!a_oid && !b_oid) || + (!b_oid && blob_unchanged(o, o_oid, o_mode, a_oid, a_mode, normalize, path)) || + (!a_oid && blob_unchanged(o, o_oid, o_mode, b_oid, b_mode, normalize, path))) { /* Deleted in both or deleted in one and * unchanged in the other */ - if (a_sha) + if (a_oid) output(o, 2, _("Removing %s"), path); /* do not touch working file if it did not exist */ - remove_file(o, 1, path, !a_sha); + remove_file(o, 1, path, !a_oid); } else { /* Modify/delete; deleted side may have put a directory in the way */ clean_merge = 0; - handle_modify_delete(o, path, o_sha, o_mode, - a_sha, a_mode, b_sha, b_mode); + if (handle_modify_delete(o, path, o_oid, o_mode, + a_oid, a_mode, b_oid, b_mode)) + clean_merge = -1; } - } else if ((!o_sha && a_sha && !b_sha) || - (!o_sha && !a_sha && b_sha)) { + } else if ((!o_oid && a_oid && !b_oid) || + (!o_oid && !a_oid && b_oid)) { /* Case B: Added in one. */ /* [nothing|directory] -> ([nothing|directory], file) */ const char *add_branch; const char *other_branch; unsigned mode; - const unsigned char *sha; + const struct object_id *oid; const char *conf; - if (a_sha) { + if (a_oid) { add_branch = o->branch1; other_branch = o->branch2; mode = a_mode; - sha = a_sha; + oid = a_oid; conf = _("file/directory"); } else { add_branch = o->branch2; other_branch = o->branch1; mode = b_mode; - sha = b_sha; + oid = b_oid; conf = _("directory/file"); } - if (dir_in_way(path, !o->call_depth)) { + if (dir_in_way(path, + !o->call_depth && !S_ISGITLINK(a_mode), + 0)) { char *new_path = unique_path(o, path, add_branch); clean_merge = 0; output(o, 1, _("CONFLICT (%s): There is a directory with name %s in %s. " "Adding %s as %s"), conf, path, other_branch, path, new_path); - if (o->call_depth) - remove_file_from_cache(path); - update_file(o, 0, sha, mode, new_path); - if (o->call_depth) + if (update_file(o, 0, oid, mode, new_path)) + clean_merge = -1; + else if (o->call_depth) remove_file_from_cache(path); free(new_path); } else { output(o, 2, _("Adding %s"), path); /* do not overwrite file if already present */ - update_file_flags(o, sha, mode, path, 1, !a_sha); + if (update_file_flags(o, oid, mode, path, 1, !a_oid)) + clean_merge = -1; } - } else if (a_sha && b_sha) { + } 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, - o_sha, o_mode, a_sha, a_mode, b_sha, b_mode, + int is_dirty = 0; /* unpack_trees would have bailed if dirty */ + clean_merge = merge_content(o, path, is_dirty, + o_oid, o_mode, a_oid, a_mode, b_oid, b_mode, NULL); - } else if (!o_sha && !a_sha && !b_sha) { + } else if (!o_oid && !a_oid && !b_oid) { /* * this entry was deleted altogether. a_mode == 0 means * we had that path and want to actively remove it. */ remove_file(o, 1, path, !a_mode); } else - die(_("Fatal merge failure, shouldn't happen.")); + BUG("fatal merge failure, shouldn't happen."); return clean_merge; } @@ -1809,69 +3297,97 @@ int merge_trees(struct merge_options *o, struct tree **result) { int code, clean; + struct strbuf sb = STRBUF_INIT; + + if (!o->call_depth && index_has_changes(&the_index, head, &sb)) { + err(o, _("Your local changes to the following files would be overwritten by merge:\n %s"), + sb.buf); + return -1; + } if (o->subtree_shift) { merge = shift_tree_object(head, merge, o->subtree_shift); common = shift_tree_object(head, common, o->subtree_shift); } - if (sha_eq(common->object.oid.hash, merge->object.oid.hash)) { - output(o, 0, _("Already up-to-date!")); + if (oid_eq(&common->object.oid, &merge->object.oid)) { + output(o, 0, _("Already up to date!")); *result = head; return 1; } - code = git_merge_trees(o->call_depth, common, head, merge); + code = unpack_trees_start(o, common, head, merge); if (code != 0) { if (show(o, 4) || o->call_depth) - die(_("merging of trees %s and %s failed"), + err(o, _("merging of trees %s and %s failed"), oid_to_hex(&head->object.oid), oid_to_hex(&merge->object.oid)); - else - exit(128); + unpack_trees_finish(o); + return -1; } if (unmerged_cache()) { - struct string_list *entries, *re_head, *re_merge; + struct string_list *entries; + struct rename_info re_info; int i; - string_list_clear(&o->current_file_set, 1); - string_list_clear(&o->current_directory_set, 1); + /* + * Only need the hashmap while processing entries, so + * initialize it here and free it when we are done running + * through the entries. Keeping it in the merge_options as + * opposed to decaring a local hashmap is for convenience + * so that we don't have to pass it to around. + */ + hashmap_init(&o->current_file_dir_set, path_hashmap_cmp, NULL, 512); get_files_dirs(o, head); get_files_dirs(o, merge); entries = get_unmerged(); + clean = detect_and_process_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--) { const char *path = entries->items[i].string; struct stage_data *e = entries->items[i].util; - if (!e->processed - && !process_entry(o, path, e)) - clean = 0; + if (!e->processed) { + int ret = process_entry(o, path, e); + if (!ret) + clean = 0; + else if (ret < 0) { + clean = ret; + goto cleanup; + } + } } for (i = 0; i < entries->nr; i++) { struct stage_data *e = entries->items[i].util; if (!e->processed) - die(_("Unprocessed path??? %s"), + BUG("unprocessed path??? %s", entries->items[i].string); } - string_list_clear(re_merge, 0); - string_list_clear(re_head, 0); - string_list_clear(entries, 1); + cleanup: + final_cleanup_renames(&re_info); - free(re_merge); - free(re_head); + string_list_clear(entries, 1); free(entries); + + hashmap_free(&o->current_file_dir_set, 1); + + if (clean < 0) { + unpack_trees_finish(o); + return clean; + } } else clean = 1; - if (o->call_depth) - *result = write_tree_from_memory(o); + unpack_trees_finish(o); + + if (o->call_depth && !(*result = write_tree_from_memory(o))) + return -1; return clean; } @@ -1899,7 +3415,7 @@ int merge_recursive(struct merge_options *o, { struct commit_list *iter; struct commit *merged_common_ancestors; - struct tree *mrtree = mrtree; + struct tree *mrtree; int clean; if (show(o, 4)) { @@ -1927,7 +3443,7 @@ int merge_recursive(struct merge_options *o, /* if there is no common ancestor, use an empty tree */ struct tree *tree; - tree = lookup_tree(EMPTY_TREE_SHA1_BIN); + tree = lookup_tree(the_repository, the_repository->hash_algo->empty_tree); merged_common_ancestors = make_virtual_commit(tree, "ancestor"); } @@ -1937,23 +3453,25 @@ int merge_recursive(struct merge_options *o, /* * When the merge fails, the result contains files * with conflict markers. The cleanness flag is - * ignored, it was never actually used, as result of - * merge_trees has always overwritten it: the committed - * "conflicts" were already resolved. + * ignored (unless indicating an error), it was never + * actually used, as result of merge_trees has always + * overwritten it: the committed "conflicts" were + * already resolved. */ discard_cache(); saved_b1 = o->branch1; saved_b2 = o->branch2; o->branch1 = "Temporary merge branch 1"; o->branch2 = "Temporary merge branch 2"; - merge_recursive(o, merged_common_ancestors, iter->item, - NULL, &merged_common_ancestors); + if (merge_recursive(o, merged_common_ancestors, iter->item, + NULL, &merged_common_ancestors) < 0) + return -1; o->branch1 = saved_b1; o->branch2 = saved_b2; o->call_depth--; if (!merged_common_ancestors) - die(_("merge returned no commit")); + return err(o, _("merge returned no commit")); } discard_cache(); @@ -1961,8 +3479,13 @@ int merge_recursive(struct merge_options *o, read_cache(); o->ancestor = "merged common ancestors"; - clean = merge_trees(o, h1->tree, h2->tree, merged_common_ancestors->tree, + clean = merge_trees(o, get_commit_tree(h1), get_commit_tree(h2), + get_commit_tree(merged_common_ancestors), &mrtree); + if (clean < 0) { + flush_output(o); + return clean; + } if (o->call_depth) { *result = make_virtual_commit(mrtree, "merged tree"); @@ -1970,17 +3493,21 @@ int merge_recursive(struct merge_options *o, commit_list_insert(h2, &(*result)->parents->next); } flush_output(o); + if (!o->call_depth && o->buffer_output < 2) + strbuf_release(&o->obuf); if (show(o, 2)) diff_warn_rename_limit("merge.renamelimit", o->needed_rename_limit, 0); return clean; } -static struct commit *get_ref(const unsigned char *sha1, const char *name) +static struct commit *get_ref(const struct object_id *oid, const char *name) { struct object *object; - object = deref_tag(parse_object(sha1), name, strlen(name)); + object = deref_tag(the_repository, parse_object(the_repository, oid), + name, + strlen(name)); if (!object) return NULL; if (object->type == OBJ_TREE) @@ -1993,14 +3520,14 @@ static struct commit *get_ref(const unsigned char *sha1, const char *name) } int merge_recursive_generic(struct merge_options *o, - const unsigned char *head, - const unsigned char *merge, + const struct object_id *head, + const struct object_id *merge, int num_base_list, - const unsigned char **base_list, + const struct object_id **base_list, struct commit **result) { int clean; - struct lock_file *lock = xcalloc(1, sizeof(struct lock_file)); + struct lock_file lock = LOCK_INIT; struct commit *head_commit = get_ref(head, o->branch1); struct commit *next_commit = get_ref(merge, o->branch2); struct commit_list *ca = NULL; @@ -2009,49 +3536,63 @@ int merge_recursive_generic(struct merge_options *o, int i; for (i = 0; i < num_base_list; ++i) { struct commit *base; - if (!(base = get_ref(base_list[i], sha1_to_hex(base_list[i])))) - return error(_("Could not parse object '%s'"), - sha1_to_hex(base_list[i])); + if (!(base = get_ref(base_list[i], oid_to_hex(base_list[i])))) + return err(o, _("Could not parse object '%s'"), + oid_to_hex(base_list[i])); commit_list_insert(base, &ca); } } - hold_locked_index(lock, 1); + hold_locked_index(&lock, LOCK_DIE_ON_ERROR); clean = merge_recursive(o, head_commit, next_commit, ca, - result); - if (active_cache_changed && - write_locked_index(&the_index, lock, COMMIT_LOCK)) - return error(_("Unable to write index.")); + result); + if (clean < 0) { + rollback_lock_file(&lock); + return clean; + } + + if (write_locked_index(&the_index, &lock, + COMMIT_LOCK | SKIP_IF_UNCHANGED)) + return err(o, _("Unable to write index.")); return clean ? 0 : 1; } static void merge_recursive_config(struct merge_options *o) { + char *value = NULL; git_config_get_int("merge.verbosity", &o->verbosity); git_config_get_int("diff.renamelimit", &o->diff_rename_limit); git_config_get_int("merge.renamelimit", &o->merge_rename_limit); + if (!git_config_get_string("diff.renames", &value)) { + o->diff_detect_rename = git_config_rename("diff.renames", value); + free(value); + } + if (!git_config_get_string("merge.renames", &value)) { + o->merge_detect_rename = git_config_rename("merge.renames", value); + free(value); + } git_config(git_xmerge_config, NULL); } void init_merge_options(struct merge_options *o) { + const char *merge_verbosity; memset(o, 0, sizeof(struct merge_options)); o->verbosity = 2; o->buffer_output = 1; o->diff_rename_limit = -1; o->merge_rename_limit = -1; o->renormalize = 0; - o->detect_rename = 1; + o->diff_detect_rename = -1; + o->merge_detect_rename = -1; merge_recursive_config(o); - if (getenv("GIT_MERGE_VERBOSITY")) - o->verbosity = - strtol(getenv("GIT_MERGE_VERBOSITY"), NULL, 10); + merge_verbosity = getenv("GIT_MERGE_VERBOSITY"); + if (merge_verbosity) + o->verbosity = strtol(merge_verbosity, NULL, 10); if (o->verbosity >= 5) o->buffer_output = 0; strbuf_init(&o->obuf, 0); - string_list_init(&o->current_file_set, 1); - string_list_init(&o->current_directory_set, 1); string_list_init(&o->df_conflict_file_set, 1); } @@ -2083,26 +3624,28 @@ int parse_merge_opt(struct merge_options *o, const char *s) o->xdl_opts |= value; } else if (!strcmp(s, "ignore-space-change")) - o->xdl_opts |= XDF_IGNORE_WHITESPACE_CHANGE; + DIFF_XDL_SET(o, IGNORE_WHITESPACE_CHANGE); else if (!strcmp(s, "ignore-all-space")) - o->xdl_opts |= XDF_IGNORE_WHITESPACE; + DIFF_XDL_SET(o, IGNORE_WHITESPACE); else if (!strcmp(s, "ignore-space-at-eol")) - o->xdl_opts |= XDF_IGNORE_WHITESPACE_AT_EOL; + DIFF_XDL_SET(o, IGNORE_WHITESPACE_AT_EOL); + else if (!strcmp(s, "ignore-cr-at-eol")) + DIFF_XDL_SET(o, IGNORE_CR_AT_EOL); else if (!strcmp(s, "renormalize")) o->renormalize = 1; else if (!strcmp(s, "no-renormalize")) o->renormalize = 0; else if (!strcmp(s, "no-renames")) - o->detect_rename = 0; + o->merge_detect_rename = 0; else if (!strcmp(s, "find-renames")) { - o->detect_rename = 1; + o->merge_detect_rename = 1; o->rename_score = 0; } else if (skip_prefix(s, "find-renames=", &arg) || skip_prefix(s, "rename-threshold=", &arg)) { if ((o->rename_score = parse_rename_score(&arg)) == -1 || *arg != 0) return -1; - o->detect_rename = 1; + o->merge_detect_rename = 1; } else return -1; |