/* * Recursive Merge algorithm stolen from git-merge-recursive.py by * Fredrik Kuivinen. * The thieves were Alex Riesen and Johannes Schindelin, in June/July 2006 */ #include "cache.h" #include "merge-recursive.h" #include "advice.h" #include "alloc.h" #include "attr.h" #include "blob.h" #include "builtin.h" #include "cache-tree.h" #include "commit.h" #include "commit-reach.h" #include "config.h" #include "diff.h" #include "diffcore.h" #include "dir.h" #include "ll-merge.h" #include "lockfile.h" #include "object-store.h" #include "repository.h" #include "revision.h" #include "string-list.h" #include "submodule.h" #include "tag.h" #include "tree-walk.h" #include "unpack-trees.h" #include "xdiff-interface.h" struct merge_options_internal { int call_depth; int needed_rename_limit; struct hashmap current_file_dir_set; struct string_list df_conflict_file_set; struct unpack_trees_options unpack_opts; struct index_state orig_index; }; struct path_hashmap_entry { struct hashmap_entry e; char path[FLEX_ARRAY]; }; static int path_hashmap_cmp(const void *cmp_data, const struct hashmap_entry *eptr, const struct hashmap_entry *entry_or_key, const void *keydata) { const struct path_hashmap_entry *a, *b; const char *key = keydata; a = container_of(eptr, const struct path_hashmap_entry, e); b = container_of(entry_or_key, const struct path_hashmap_entry, e); 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); } /* * For dir_rename_entry, directory names are stored as a full path from the * toplevel of the repository and do not include a trailing '/'. Also: * * dir: original name of directory being renamed * non_unique_new_dir: if true, could not determine new_dir * new_dir: final name of directory being renamed * possible_new_dirs: temporary used to help determine new_dir; see comments * in get_directory_renames() for details */ struct dir_rename_entry { struct hashmap_entry ent; char *dir; unsigned non_unique_new_dir:1; struct strbuf new_dir; struct string_list possible_new_dirs; }; 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.ent, strhash(dir)); key.dir = dir; return hashmap_get_entry(hashmap, &key, ent, NULL); } static int dir_rename_cmp(const void *unused_cmp_data, const struct hashmap_entry *eptr, const struct hashmap_entry *entry_or_key, const void *unused_keydata) { const struct dir_rename_entry *e1, *e2; e1 = container_of(eptr, const struct dir_rename_entry, ent); e2 = container_of(entry_or_key, const struct dir_rename_entry, ent); 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->ent, 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); } struct collision_entry { struct hashmap_entry ent; char *target_file; struct string_list source_files; unsigned reported_already:1; }; static struct collision_entry *collision_find_entry(struct hashmap *hashmap, char *target_file) { struct collision_entry key; hashmap_entry_init(&key.ent, strhash(target_file)); key.target_file = target_file; return hashmap_get_entry(hashmap, &key, ent, NULL); } static int collision_cmp(const void *unused_cmp_data, const struct hashmap_entry *eptr, const struct hashmap_entry *entry_or_key, const void *unused_keydata) { const struct collision_entry *e1, *e2; e1 = container_of(eptr, const struct collision_entry, ent); e2 = container_of(entry_or_key, const struct collision_entry, ent); return strcmp(e1->target_file, e2->target_file); } static void collision_init(struct hashmap *map) { hashmap_init(map, collision_cmp, NULL, 0); } static void flush_output(struct merge_options *opt) { if (opt->buffer_output < 2 && opt->obuf.len) { fputs(opt->obuf.buf, stdout); strbuf_reset(&opt->obuf); } } static int err(struct merge_options *opt, const char *err, ...) { va_list params; if (opt->buffer_output < 2) flush_output(opt); else { strbuf_complete(&opt->obuf, '\n'); strbuf_addstr(&opt->obuf, "error: "); } va_start(params, err); strbuf_vaddf(&opt->obuf, err, params); va_end(params); if (opt->buffer_output > 1) strbuf_addch(&opt->obuf, '\n'); else { error("%s", opt->obuf.buf); strbuf_reset(&opt->obuf); } return -1; } static struct tree *shift_tree_object(struct repository *repo, struct tree *one, struct tree *two, const char *subtree_shift) { struct object_id shifted; if (!*subtree_shift) { shift_tree(repo, &one->object.oid, &two->object.oid, &shifted, 0); } else { shift_tree_by(repo, &one->object.oid, &two->object.oid, &shifted, subtree_shift); } if (oideq(&two->object.oid, &shifted)) return two; return lookup_tree(repo, &shifted); } static inline void set_commit_tree(struct commit *c, struct tree *t) { c->maybe_tree = t; } static struct commit *make_virtual_commit(struct repository *repo, struct tree *tree, const char *comment) { struct commit *commit = alloc_commit_node(repo); set_merge_remote_desc(commit, comment, (struct object *)commit); set_commit_tree(commit, tree); commit->object.parsed = 1; return commit; } enum rename_type { RENAME_NORMAL = 0, RENAME_VIA_DIR, RENAME_ADD, RENAME_DELETE, RENAME_ONE_FILE_TO_ONE, RENAME_ONE_FILE_TO_TWO, RENAME_TWO_FILES_TO_ONE }; /* * Since we want to write the index eventually, we cannot reuse the index * for these (temporary) data. */ struct stage_data { struct diff_filespec stages[4]; /* mostly for oid & mode; maybe path */ struct rename_conflict_info *rename_conflict_info; unsigned processed:1; }; struct rename { unsigned processed:1; struct diff_filepair *pair; const char *branch; /* branch that the rename occurred on */ /* * If directory rename detection affected this rename, what was its * original type ('A' or 'R') and it's original destination before * the directory rename (otherwise, '\0' and NULL for these two vars). */ char dir_rename_original_type; char *dir_rename_original_dest; /* * 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; }; struct rename_conflict_info { enum rename_type rename_type; struct rename *ren1; struct rename *ren2; }; static inline void setup_rename_conflict_info(enum rename_type rename_type, struct merge_options *opt, struct rename *ren1, struct rename *ren2) { struct rename_conflict_info *ci; /* * When we have two renames involved, it's easiest to get the * correct things into stage 2 and 3, and to make sure that the * content merge puts HEAD before the other branch if we just * ensure that branch1 == opt->branch1. So, simply flip arguments * around if we don't have that. */ if (ren2 && ren1->branch != opt->branch1) { setup_rename_conflict_info(rename_type, opt, ren2, ren1); return; } CALLOC_ARRAY(ci, 1); ci->rename_type = rename_type; ci->ren1 = ren1; ci->ren2 = ren2; ci->ren1->dst_entry->processed = 0; ci->ren1->dst_entry->rename_conflict_info = ci; if (ren2) { ci->ren2->dst_entry->rename_conflict_info = ci; } } static int show(struct merge_options *opt, int v) { return (!opt->priv->call_depth && opt->verbosity >= v) || opt->verbosity >= 5; } __attribute__((format (printf, 3, 4))) static void output(struct merge_options *opt, int v, const char *fmt, ...) { va_list ap; if (!show(opt, v)) return; strbuf_addchars(&opt->obuf, ' ', opt->priv->call_depth * 2); va_start(ap, fmt); strbuf_vaddf(&opt->obuf, fmt, ap); va_end(ap); strbuf_addch(&opt->obuf, '\n'); if (!opt->buffer_output) flush_output(opt); } static void output_commit_title(struct merge_options *opt, struct commit *commit) { struct merge_remote_desc *desc; strbuf_addchars(&opt->obuf, ' ', opt->priv->call_depth * 2); desc = merge_remote_util(commit); if (desc) strbuf_addf(&opt->obuf, "virtual %s\n", desc->name); else { strbuf_add_unique_abbrev(&opt->obuf, &commit->object.oid, DEFAULT_ABBREV); strbuf_addch(&opt->obuf, ' '); if (parse_commit(commit) != 0) strbuf_addstr(&opt->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) strbuf_addf(&opt->obuf, "%.*s\n", len, title); unuse_commit_buffer(commit, msg); } } flush_output(opt); } static int add_cacheinfo(struct merge_options *opt, const struct diff_filespec *blob, const char *path, int stage, int refresh, int options) { struct index_state *istate = opt->repo->index; struct cache_entry *ce; int ret; ce = make_cache_entry(istate, blob->mode, &blob->oid, path, stage, 0); if (!ce) return err(opt, _("add_cacheinfo failed for path '%s'; merge aborting."), path); ret = add_index_entry(istate, ce, options); if (refresh) { struct cache_entry *nce; nce = refresh_cache_entry(istate, ce, CE_MATCH_REFRESH | CE_MATCH_IGNORE_MISSING); if (!nce) return err(opt, _("add_cacheinfo failed to refresh for path '%s'; merge aborting."), path); if (nce != ce) ret = add_index_entry(istate, nce, options); } return ret; } static inline int merge_detect_rename(struct merge_options *opt) { return (opt->detect_renames >= 0) ? opt->detect_renames : 1; } static void init_tree_desc_from_tree(struct tree_desc *desc, struct tree *tree) { parse_tree(tree); init_tree_desc(desc, tree->buffer, tree->size); } static int unpack_trees_start(struct merge_options *opt, struct tree *common, struct tree *head, struct tree *merge) { int rc; struct tree_desc t[3]; struct index_state tmp_index = { NULL }; memset(&opt->priv->unpack_opts, 0, sizeof(opt->priv->unpack_opts)); if (opt->priv->call_depth) opt->priv->unpack_opts.index_only = 1; else opt->priv->unpack_opts.update = 1; opt->priv->unpack_opts.merge = 1; opt->priv->unpack_opts.head_idx = 2; opt->priv->unpack_opts.fn = threeway_merge; opt->priv->unpack_opts.src_index = opt->repo->index; opt->priv->unpack_opts.dst_index = &tmp_index; opt->priv->unpack_opts.aggressive = !merge_detect_rename(opt); setup_unpack_trees_porcelain(&opt->priv->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, &opt->priv->unpack_opts); cache_tree_free(&opt->repo->index->cache_tree); /* * Update opt->repo->index to match the new results, AFTER saving a * copy in opt->priv->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.) */ opt->priv->orig_index = *opt->repo->index; *opt->repo->index = tmp_index; opt->priv->unpack_opts.src_index = &opt->priv->orig_index; return rc; } static void unpack_trees_finish(struct merge_options *opt) { discard_index(&opt->priv->orig_index); clear_unpack_trees_porcelain(&opt->priv->unpack_opts); } static int save_files_dirs(const struct object_id *oid, struct strbuf *base, const char *path, unsigned int mode, void *context) { struct path_hashmap_entry *entry; int baselen = base->len; struct merge_options *opt = context; strbuf_addstr(base, path); FLEX_ALLOC_MEM(entry, path, base->buf, base->len); hashmap_entry_init(&entry->e, path_hash(entry->path)); hashmap_add(&opt->priv->current_file_dir_set, &entry->e); strbuf_setlen(base, baselen); return (S_ISDIR(mode) ? READ_TREE_RECURSIVE : 0); } static void get_files_dirs(struct merge_options *opt, struct tree *tree) { struct pathspec match_all; memset(&match_all, 0, sizeof(match_all)); read_tree(opt->repo, tree, &match_all, save_files_dirs, opt); } static int get_tree_entry_if_blob(struct repository *r, const struct object_id *tree, const char *path, struct diff_filespec *dfs) { int ret; ret = get_tree_entry(r, tree, path, &dfs->oid, &dfs->mode); if (S_ISDIR(dfs->mode)) { oidcpy(&dfs->oid, &null_oid); dfs->mode = 0; } return ret; } /* * Returns an index_entry instance which doesn't have to correspond to * a real cache entry in Git's index. */ static struct stage_data *insert_stage_data(struct repository *r, const char *path, struct tree *o, struct tree *a, struct tree *b, struct string_list *entries) { struct string_list_item *item; struct stage_data *e = xcalloc(1, sizeof(struct stage_data)); get_tree_entry_if_blob(r, &o->object.oid, path, &e->stages[1]); get_tree_entry_if_blob(r, &a->object.oid, path, &e->stages[2]); get_tree_entry_if_blob(r, &b->object.oid, path, &e->stages[3]); item = string_list_insert(entries, path); item->util = e; return e; } /* * Create a dictionary mapping file names to stage_data objects. The * dictionary contains one entry for every path with a non-zero stage entry. */ static struct string_list *get_unmerged(struct index_state *istate) { struct string_list *unmerged = xcalloc(1, sizeof(struct string_list)); int i; unmerged->strdup_strings = 1; for (i = 0; i < istate->cache_nr; i++) { struct string_list_item *item; struct stage_data *e; const struct cache_entry *ce = istate->cache[i]; if (!ce_stage(ce)) continue; item = string_list_lookup(unmerged, ce->name); if (!item) { item = string_list_insert(unmerged, ce->name); item->util = xcalloc(1, sizeof(struct stage_data)); } e = item->util; e->stages[ce_stage(ce)].mode = ce->ce_mode; oidcpy(&e->stages[ce_stage(ce)].oid, &ce->oid); } return unmerged; } static int string_list_df_name_compare(const char *one, const char *two) { 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 * appearing before files below the corresponding directory. * The order of the rest of the list is irrelevant for us. * * To achieve this, we sort with df_name_compare and provide * the mode S_IFDIR so that D/F conflicts will sort correctly. * We use the mode S_IFDIR for everything else for simplicity, * since in other cases any changes in their order due to * sorting cause no problems for us. */ 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'. */ if (cmp) return cmp; return onelen - twolen; } static void record_df_conflict_files(struct merge_options *opt, struct string_list *entries) { /* If there is a D/F conflict and the file for such a conflict * 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 * conflict. If the D/F directory ends up being removed by the * merge, then we won't have to touch the D/F file. If the D/F * directory needs to be written to the working copy, then the D/F * file will simply be removed (in make_room_for_path()) to make * room for the necessary paths. Note that if both the directory * 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 = STRING_LIST_INIT_NODUP; const char *last_file = NULL; int last_len = 0; int i; /* * If we're merging merge-bases, we don't want to bother with * any working directory changes. */ if (opt->priv->call_depth) return; /* Ensure D/F conflicts are adjacent in the entries 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; } df_sorted_entries.cmp = string_list_df_name_compare; string_list_sort(&df_sorted_entries); string_list_clear(&opt->priv->df_conflict_file_set, 1); for (i = 0; i < df_sorted_entries.nr; i++) { const char *path = df_sorted_entries.items[i].string; int len = strlen(path); struct stage_data *e = df_sorted_entries.items[i].util; /* * Check if last_file & path correspond to a D/F conflict; * i.e. whether path is last_file+'/'+. * If so, record that it's okay to remove last_file to make * room for path and friends if needed. */ if (last_file && len > last_len && memcmp(path, last_file, last_len) == 0 && path[last_len] == '/') { string_list_insert(&opt->priv->df_conflict_file_set, last_file); } /* * Determine whether path could exist as a file in the * working directory as a possible D/F conflict. This * will only occur when it exists in stage 2 as a * file. */ if (S_ISREG(e->stages[2].mode) || S_ISLNK(e->stages[2].mode)) { last_file = path; last_len = len; } else { last_file = NULL; } } string_list_clear(&df_sorted_entries, 0); } 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) { /* * NOTE: It is usually a bad idea to call update_stages on a path * before calling update_file on that same path, since it can * sometimes lead to spurious "refusing to lose untracked file..." * messages from update_file (via make_room_for path via * would_lose_untracked). Instead, reverse the order of the calls * (executing update_file first and then update_stages). */ int clear = 1; int options = ADD_CACHE_OK_TO_ADD | ADD_CACHE_SKIP_DFCHECK; if (clear) if (remove_file_from_index(opt->repo->index, path)) return -1; if (o) if (add_cacheinfo(opt, o, path, 1, 0, options)) return -1; if (a) if (add_cacheinfo(opt, a, path, 2, 0, options)) return -1; if (b) if (add_cacheinfo(opt, b, path, 3, 0, options)) return -1; return 0; } static void update_entry(struct stage_data *entry, struct diff_filespec *o, struct diff_filespec *a, struct diff_filespec *b) { entry->processed = 0; entry->stages[1].mode = o->mode; entry->stages[2].mode = a->mode; entry->stages[3].mode = b->mode; 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 *opt, int clean, const char *path, int no_wd) { int update_cache = opt->priv->call_depth || clean; int update_working_directory = !opt->priv->call_depth && !no_wd; if (update_cache) { if (remove_file_from_index(opt->repo->index, path)) return -1; } if (update_working_directory) { if (ignore_case) { struct cache_entry *ce; ce = index_file_exists(opt->repo->index, path, strlen(path), ignore_case); if (ce && ce_stage(ce) == 0 && strcmp(path, ce->name)) return 0; } if (remove_path(path)) return -1; } return 0; } /* add a string to a strbuf, but converting "/" to "_" */ static void add_flattened_path(struct strbuf *out, const char *s) { size_t i = out->len; strbuf_addstr(out, s); for (; i < out->len; i++) if (out->buf[i] == '/') out->buf[i] = '_'; } static char *unique_path(struct merge_options *opt, const char *path, const char *branch) { struct path_hashmap_entry *entry; struct strbuf newpath = STRBUF_INIT; int suffix = 0; size_t base_len; strbuf_addf(&newpath, "%s~", path); add_flattened_path(&newpath, branch); base_len = newpath.len; while (hashmap_get_from_hash(&opt->priv->current_file_dir_set, path_hash(newpath.buf), newpath.buf) || (!opt->priv->call_depth && file_exists(newpath.buf))) { strbuf_setlen(&newpath, base_len); strbuf_addf(&newpath, "_%d", suffix++); } FLEX_ALLOC_MEM(entry, path, newpath.buf, newpath.len); hashmap_entry_init(&entry->e, path_hash(entry->path)); hashmap_add(&opt->priv->current_file_dir_set, &entry->e); return strbuf_detach(&newpath, NULL); } /** * 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(struct index_state *istate, const char *path, int check_working_copy, int empty_ok) { int pos; struct strbuf dirpath = STRBUF_INIT; struct stat st; strbuf_addstr(&dirpath, path); strbuf_addch(&dirpath, '/'); pos = index_name_pos(istate, dirpath.buf, dirpath.len); if (pos < 0) pos = -1 - pos; if (pos < istate->cache_nr && !strncmp(dirpath.buf, istate->cache[pos]->name, dirpath.len)) { strbuf_release(&dirpath); return 1; } strbuf_release(&dirpath); return check_working_copy && !lstat(path, &st) && S_ISDIR(st.st_mode) && !(empty_ok && is_empty_dir(path)) && !has_symlink_leading_path(path, strlen(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 *opt, const char *path, const struct diff_filespec *blob) { int pos = index_name_pos(&opt->priv->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 = opt->priv->orig_index.cache[pos]; return (oideq(&ce->oid, &blob->oid) && ce->ce_mode == blob->mode); } /* * Returns whether path was tracked in the index before the merge started */ static int was_tracked(struct merge_options *opt, const char *path) { int pos = index_name_pos(&opt->priv->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(struct merge_options *opt, const char *path) { struct index_state *istate = opt->repo->index; /* * This may look like it can be simplified to: * return !was_tracked(opt, 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 = index_name_pos(istate, path, strlen(path)); if (pos < 0) pos = -1 - pos; while (pos < istate->cache_nr && !strcmp(path, istate->cache[pos]->name)) { /* * If stage #0, it is definitely tracked. * If it has stage #2 then it was tracked * before this merge started. All other * cases the path was not tracked. */ switch (ce_stage(istate->cache[pos])) { case 0: case 2: return 0; } pos++; } return file_exists(path); } static int was_dirty(struct merge_options *opt, const char *path) { struct cache_entry *ce; int dirty = 1; if (opt->priv->call_depth || !was_tracked(opt, path)) return !dirty; ce = index_file_exists(opt->priv->unpack_opts.src_index, path, strlen(path), ignore_case); dirty = verify_uptodate(ce, &opt->priv->unpack_opts) != 0; return dirty; } static int make_room_for_path(struct merge_options *opt, const char *path) { int status, i; const char *msg = _("failed to create path '%s'%s"); /* Unlink any D/F conflict files that are in the way */ for (i = 0; i < opt->priv->df_conflict_file_set.nr; i++) { const char *df_path = opt->priv->df_conflict_file_set.items[i].string; size_t pathlen = strlen(path); size_t df_pathlen = strlen(df_path); if (df_pathlen < pathlen && path[df_pathlen] == '/' && strncmp(path, df_path, df_pathlen) == 0) { output(opt, 3, _("Removing %s to make room for subdirectory\n"), df_path); unlink(df_path); unsorted_string_list_delete_item(&opt->priv->df_conflict_file_set, i, 0); break; } } /* Make sure leading directories are created */ status = safe_create_leading_directories_const(path); if (status) { if (status == SCLD_EXISTS) /* something else exists */ return err(opt, msg, path, _(": perhaps a D/F conflict?")); return err(opt, msg, path, ""); } /* * Do not unlink a file in the work tree if we are not * tracking it. */ if (would_lose_untracked(opt, path)) return err(opt, _("refusing to lose untracked file at '%s'"), path); /* Successful unlink is good.. */ if (!unlink(path)) return 0; /* .. and so is no existing file */ if (errno == ENOENT) return 0; /* .. but not some other error (who really cares what?) */ return err(opt, msg, path, _(": perhaps a D/F conflict?")); } static int update_file_flags(struct merge_options *opt, const struct diff_filespec *contents, const char *path, int update_cache, int update_wd) { int ret = 0; if (opt->priv->call_depth) update_wd = 0; if (update_wd) { enum object_type type; void *buf; unsigned long size; if (S_ISGITLINK(contents->mode)) { /* * We may later decide to recursively descend into * the submodule directory and update its index * and/or work tree, but we do not do that now. */ update_wd = 0; goto update_index; } buf = read_object_file(&contents->oid, &type, &size); if (!buf) { ret = err(opt, _("cannot read object %s '%s'"), oid_to_hex(&contents->oid), path); goto free_buf; } if (type != OBJ_BLOB) { ret = err(opt, _("blob expected for %s '%s'"), oid_to_hex(&contents->oid), path); goto free_buf; } if (S_ISREG(contents->mode)) { struct strbuf strbuf = STRBUF_INIT; if (convert_to_working_tree(opt->repo->index, path, buf, size, &strbuf, NULL)) { free(buf); size = strbuf.len; buf = strbuf_detach(&strbuf, NULL); } } if (make_room_for_path(opt, path) < 0) { update_wd = 0; goto free_buf; } if (S_ISREG(contents->mode) || (!has_symlinks && S_ISLNK(contents->mode))) { int fd; int mode = (contents->mode & 0100 ? 0777 : 0666); fd = open(path, O_WRONLY | O_TRUNC | O_CREAT, mode); if (fd < 0) { ret = err(opt, _("failed to open '%s': %s"), path, strerror(errno)); goto free_buf; } write_in_full(fd, buf, size); close(fd); } else if (S_ISLNK(contents->mode)) { char *lnk = xmemdupz(buf, size); safe_create_leading_directories_const(path); unlink(path); if (symlink(lnk, path)) ret = err(opt, _("failed to symlink '%s': %s"), path, strerror(errno)); free(lnk); } else ret = err(opt, _("do not know what to do with %06o %s '%s'"), contents->mode, oid_to_hex(&contents->oid), path); free_buf: free(buf); } update_index: if (!ret && update_cache) { int refresh = (!opt->priv->call_depth && contents->mode != S_IFGITLINK); if (add_cacheinfo(opt, contents, path, 0, refresh, ADD_CACHE_OK_TO_ADD)) return -1; } return ret; } static int update_file(struct merge_options *opt, int clean, const struct diff_filespec *contents, const char *path) { return update_file_flags(opt, contents, path, opt->priv->call_depth || clean, !opt->priv->call_depth); } /* Low level file merging, update and removal */ struct merge_file_info { struct diff_filespec blob; /* mostly use oid & mode; sometimes path */ unsigned clean:1, merge:1; }; static int merge_3way(struct merge_options *opt, mmbuffer_t *result_buf, const struct diff_filespec *o, const struct diff_filespec *a, const struct diff_filespec *b, const char *branch1, const char *branch2, const int extra_marker_size) { mmfile_t orig, src1, src2; struct ll_merge_options ll_opts = {0}; char *base, *name1, *name2; int merge_status; ll_opts.renormalize = opt->renormalize; ll_opts.extra_marker_size = extra_marker_size; ll_opts.xdl_opts = opt->xdl_opts; if (opt->priv->call_depth) { ll_opts.virtual_ancestor = 1; ll_opts.variant = 0; } else { switch (opt->recursive_variant) { case MERGE_VARIANT_OURS: ll_opts.variant = XDL_MERGE_FAVOR_OURS; break; case MERGE_VARIANT_THEIRS: ll_opts.variant = XDL_MERGE_FAVOR_THEIRS; break; default: ll_opts.variant = 0; break; } } assert(a->path && b->path && o->path && opt->ancestor); if (strcmp(a->path, b->path) || strcmp(a->path, o->path) != 0) { base = mkpathdup("%s:%s", opt->ancestor, o->path); name1 = mkpathdup("%s:%s", branch1, a->path); name2 = mkpathdup("%s:%s", branch2, b->path); } else { base = mkpathdup("%s", opt->ancestor); name1 = mkpathdup("%s", branch1); name2 = mkpathdup("%s", branch2); } read_mmblob(&orig, &o->oid); read_mmblob(&src1, &a->oid); read_mmblob(&src2, &b->oid); merge_status = ll_merge(result_buf, a->path, &orig, base, &src1, name1, &src2, name2, opt->repo->index, &ll_opts); free(base); free(name1); free(name2); free(orig.ptr); free(src1.ptr); free(src2.ptr); return merge_status; } static int find_first_merges(struct repository *repo, 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[GIT_MAX_HEXSZ + 2]; 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)); repo_init_revisions(repo, &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 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 is_valid(const struct diff_filespec *dfs) { return dfs->mode != 0 && !is_null_oid(&dfs->oid); } static int merge_submodule(struct merge_options *opt, 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 = !opt->priv->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(opt, 1, _("Failed to merge submodule %s (not checked out)"), path); return 0; } if (!(commit_base = lookup_commit_reference(opt->repo, base)) || !(commit_a = lookup_commit_reference(opt->repo, a)) || !(commit_b = lookup_commit_reference(opt->repo, b))) { output(opt, 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(opt, 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(opt, 3)) { output(opt, 3, _("Fast-forwarding submodule %s to the following commit:"), path); output_commit_title(opt, commit_b); } else if (show(opt, 2)) output(opt, 2, _("Fast-forwarding submodule %s"), path); else ; /* no output */ return 1; } if (in_merge_bases(commit_b, commit_a)) { oidcpy(result, a); if (show(opt, 3)) { output(opt, 3, _("Fast-forwarding submodule %s to the following commit:"), path); output_commit_title(opt, commit_a); } else if (show(opt, 2)) output(opt, 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(opt->repo, &merges, path, commit_a, commit_b); switch (parent_count) { case 0: output(opt, 1, _("Failed to merge submodule %s (merge following commits not found)"), path); break; case 1: output(opt, 1, _("Failed to merge submodule %s (not fast-forward)"), path); output(opt, 2, _("Found a possible merge resolution for the submodule:\n")); print_commit((struct commit *) merges.objects[0].item); output(opt, 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(opt, 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_mode_and_contents(struct merge_options *opt, const struct diff_filespec *o, const struct diff_filespec *a, const struct diff_filespec *b, const char *filename, const char *branch1, const char *branch2, const int extra_marker_size, struct merge_file_info *result) { if (opt->branch1 != branch1) { /* * It's weird getting a reverse merge with HEAD on the bottom * side of the conflict markers and the other branch on the * top. Fix that. */ return merge_mode_and_contents(opt, o, b, a, filename, branch2, branch1, extra_marker_size, result); } result->merge = 0; result->clean = 1; if ((S_IFMT & a->mode) != (S_IFMT & b->mode)) { result->clean = 0; if (S_ISREG(a->mode)) { result->blob.mode = a->mode; oidcpy(&result->blob.oid, &a->oid); } else { result->blob.mode = b->mode; oidcpy(&result->blob.oid, &b->oid); } } else { if (!oideq(&a->oid, &o->oid) && !oideq(&b->oid, &o->oid)) result->merge = 1; /* * Merge modes */ if (a->mode == b->mode || a->mode == o->mode) result->blob.mode = b->mode; else { result->blob.mode = a->mode; if (b->mode != o->mode) { result->clean = 0; result->merge = 1; } } if (oideq(&a->oid, &b->oid) || oideq(&a->oid, &o->oid)) oidcpy(&result->blob.oid, &b->oid); else if (oideq(&b->oid, &o->oid)) oidcpy(&result->blob.oid, &a->oid); else if (S_ISREG(a->mode)) { mmbuffer_t result_buf; int ret = 0, merge_status; merge_status = merge_3way(opt, &result_buf, o, a, b, branch1, branch2, extra_marker_size); if ((merge_status < 0) || !result_buf.ptr) ret = err(opt, _("Failed to execute internal merge")); if (!ret && write_object_file(result_buf.ptr, result_buf.size, blob_type, &result->blob.oid)) ret = err(opt, _("Unable to add %s to database"), a->path); free(result_buf.ptr); if (ret) return ret; result->clean = (merge_status == 0); } else if (S_ISGITLINK(a->mode)) { result->clean = merge_submodule(opt, &result->blob.oid, o->path, &o->oid, &a->oid, &b->oid); } else if (S_ISLNK(a->mode)) { switch (opt->recursive_variant) { case MERGE_VARIANT_NORMAL: oidcpy(&result->blob.oid, &a->oid); if (!oideq(&a->oid, &b->oid)) result->clean = 0; break; case MERGE_VARIANT_OURS: oidcpy(&result->blob.oid, &a->oid); break; case MERGE_VARIANT_THEIRS: oidcpy(&result->blob.oid, &b->oid); break; } } else BUG("unsupported object type in the tree"); } if (result->merge) output(opt, 2, _("Auto-merging %s"), filename); return 0; } static int handle_rename_via_dir(struct merge_options *opt, struct rename_conflict_info *ci) { /* * 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 rename *ren = ci->ren1; const struct diff_filespec *dest = ren->pair->two; char *file_path = dest->path; int mark_conflicted = (opt->detect_directory_renames == MERGE_DIRECTORY_RENAMES_CONFLICT); assert(ren->dir_rename_original_dest); if (!opt->priv->call_depth && would_lose_untracked(opt, dest->path)) { mark_conflicted = 1; file_path = unique_path(opt, dest->path, ren->branch); output(opt, 1, _("Error: Refusing to lose untracked file at %s; " "writing to %s instead."), dest->path, file_path); } if (mark_conflicted) { /* * Write the file in worktree at file_path. In the index, * only record the file at dest->path in the appropriate * higher stage. */ if (update_file(opt, 0, dest, file_path)) return -1; if (file_path != dest->path) free(file_path); if (update_stages(opt, dest->path, NULL, ren->branch == opt->branch1 ? dest : NULL, ren->branch == opt->branch1 ? NULL : dest)) return -1; return 0; /* not clean, but conflicted */ } else { /* Update dest->path both in index and in worktree */ if (update_file(opt, 1, dest, dest->path)) return -1; return 1; /* clean */ } } static int handle_change_delete(struct merge_options *opt, const char *path, const char *old_path, const struct diff_filespec *o, const struct diff_filespec *changed, const char *change_branch, const char *delete_branch, const char *change, const char *change_past) { char *alt_path = NULL; const char *update_path = path; int ret = 0; if (dir_in_way(opt->repo->index, path, !opt->priv->call_depth, 0) || (!opt->priv->call_depth && would_lose_untracked(opt, path))) { update_path = alt_path = unique_path(opt, path, change_branch); } if (opt->priv->call_depth) { /* * We cannot arbitrarily accept either a_sha or b_sha as * correct; since there is no true "middle point" between * them, simply reuse the base version for virtual merge base. */ ret = remove_file_from_index(opt->repo->index, path); if (!ret) ret = update_file(opt, 0, o, update_path); } else { /* * 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(opt, 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(opt, 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 { if (!old_path) { output(opt, 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(opt, 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 change_branch == * opt->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 != opt->branch1 || alt_path) ret = update_file(opt, 0, changed, update_path); } free(alt_path); return ret; } static int handle_rename_delete(struct merge_options *opt, struct rename_conflict_info *ci) { const struct rename *ren = ci->ren1; const struct diff_filespec *orig = ren->pair->one; const struct diff_filespec *dest = ren->pair->two; const char *rename_branch = ren->branch; const char *delete_branch = (opt->branch1 == ren->branch ? opt->branch2 : opt->branch1); if (handle_change_delete(opt, opt->priv->call_depth ? orig->path : dest->path, opt->priv->call_depth ? NULL : orig->path, orig, dest, rename_branch, delete_branch, _("rename"), _("renamed"))) return -1; if (opt->priv->call_depth) return remove_file_from_index(opt->repo->index, dest->path); else return update_stages(opt, dest->path, NULL, rename_branch == opt->branch1 ? dest : NULL, rename_branch == opt->branch1 ? NULL : dest); } static int handle_file_collision(struct merge_options *opt, const char *collide_path, const char *prev_path1, const char *prev_path2, const char *branch1, const char *branch2, struct diff_filespec *a, struct diff_filespec *b) { struct merge_file_info mfi; struct diff_filespec null; char *alt_path = NULL; const char *update_path = collide_path; /* * It's easiest to get the correct things into stage 2 and 3, and * to make sure that the content merge puts HEAD before the other * branch if we just ensure that branch1 == opt->branch1. So, simply * flip arguments around if we don't have that. */ if (branch1 != opt->branch1) { return handle_file_collision(opt, collide_path, prev_path2, prev_path1, branch2, branch1, b, a); } /* Remove rename sources if rename/add or rename/rename(2to1) */ if (prev_path1) remove_file(opt, 1, prev_path1, opt->priv->call_depth || would_lose_untracked(opt, prev_path1)); if (prev_path2) remove_file(opt, 1, prev_path2, opt->priv->call_depth || would_lose_untracked(opt, prev_path2)); /* * Remove the collision path, if it wouldn't cause dirty contents * or an untracked file to get lost. We'll either overwrite with * merged contents, or just write out to differently named files. */ if (was_dirty(opt, collide_path)) { output(opt, 1, _("Refusing to lose dirty file at %s"), collide_path); update_path = alt_path = unique_path(opt, collide_path, "merged"); } else if (would_lose_untracked(opt, collide_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(opt, 1, _("Refusing to lose untracked file at " "%s, even though it's in the way."), collide_path); update_path = alt_path = unique_path(opt, collide_path, "merged"); } else { /* * FIXME: It's possible that the two files are identical * and that the current working copy happens to match, in * which case we are unnecessarily touching the working * tree file. It's not a likely enough scenario that I * want to code up the checks for it and a better fix is * available if we restructure how unpack_trees() and * merge-recursive interoperate anyway, so punting for * now... */ remove_file(opt, 0, collide_path, 0); } /* Store things in diff_filespecs for functions that need it */ null.path = (char *)collide_path; oidcpy(&null.oid, &null_oid); null.mode = 0; if (merge_mode_and_contents(opt, &null, a, b, collide_path, branch1, branch2, opt->priv->call_depth * 2, &mfi)) return -1; mfi.clean &= !alt_path; if (update_file(opt, mfi.clean, &mfi.blob, update_path)) return -1; if (!mfi.clean && !opt->priv->call_depth && update_stages(opt, collide_path, NULL, a, b)) return -1; free(alt_path); /* * FIXME: If both a & b both started with conflicts (only possible * if they came from a rename/rename(2to1)), but had IDENTICAL * contents including those conflicts, then in the next line we claim * it was clean. If someone cares about this case, we should have the * caller notify us if we started with conflicts. */ return mfi.clean; } static int handle_rename_add(struct merge_options *opt, struct rename_conflict_info *ci) { /* a was renamed to c, and a separate c was added. */ struct diff_filespec *a = ci->ren1->pair->one; struct diff_filespec *c = ci->ren1->pair->two; char *path = c->path; char *prev_path_desc; struct merge_file_info mfi; const char *rename_branch = ci->ren1->branch; const char *add_branch = (opt->branch1 == rename_branch ? opt->branch2 : opt->branch1); int other_stage = (ci->ren1->branch == opt->branch1 ? 3 : 2); output(opt, 1, _("CONFLICT (rename/add): " "Rename %s->%s in %s. Added %s in %s"), a->path, c->path, rename_branch, c->path, add_branch); prev_path_desc = xstrfmt("version of %s from %s", path, a->path); ci->ren1->src_entry->stages[other_stage].path = a->path; if (merge_mode_and_contents(opt, a, c, &ci->ren1->src_entry->stages[other_stage], prev_path_desc, opt->branch1, opt->branch2, 1 + opt->priv->call_depth * 2, &mfi)) return -1; free(prev_path_desc); ci->ren1->dst_entry->stages[other_stage].path = mfi.blob.path = c->path; return handle_file_collision(opt, c->path, a->path, NULL, rename_branch, add_branch, &mfi.blob, &ci->ren1->dst_entry->stages[other_stage]); } static char *find_path_for_conflict(struct merge_options *opt, const char *path, const char *branch1, const char *branch2) { char *new_path = NULL; if (dir_in_way(opt->repo->index, path, !opt->priv->call_depth, 0)) { new_path = unique_path(opt, path, branch1); output(opt, 1, _("%s is a directory in %s adding " "as %s instead"), path, branch2, new_path); } else if (would_lose_untracked(opt, path)) { new_path = unique_path(opt, path, branch1); output(opt, 1, _("Refusing to lose untracked file" " at %s; adding as %s instead"), path, new_path); } return new_path; } /* * Toggle the stage number between "ours" and "theirs" (2 and 3). */ static inline int flip_stage(int stage) { return (2 + 3) - stage; } static int handle_rename_rename_1to2(struct merge_options *opt, struct rename_conflict_info *ci) { /* One file was renamed in both branches, but to different names. */ struct merge_file_info mfi; struct diff_filespec *add; struct diff_filespec *o = ci->ren1->pair->one; struct diff_filespec *a = ci->ren1->pair->two; struct diff_filespec *b = ci->ren2->pair->two; char *path_desc; output(opt, 1, _("CONFLICT (rename/rename): " "Rename \"%s\"->\"%s\" in branch \"%s\" " "rename \"%s\"->\"%s\" in \"%s\"%s"), o->path, a->path, ci->ren1->branch, o->path, b->path, ci->ren2->branch, opt->priv->call_depth ? _(" (left unresolved)") : ""); path_desc = xstrfmt("%s and %s, both renamed from %s", a->path, b->path, o->path); if (merge_mode_and_contents(opt, o, a, b, path_desc, ci->ren1->branch, ci->ren2->branch, opt->priv->call_depth * 2, &mfi)) return -1; free(path_desc); if (opt->priv->call_depth) remove_file_from_index(opt->repo->index, o->path); /* * For each destination path, we need to see if there is a * rename/add collision. If not, we can write the file out * to the specified location. */ add = &ci->ren1->dst_entry->stages[flip_stage(2)]; if (is_valid(add)) { add->path = mfi.blob.path = a->path; if (handle_file_collision(opt, a->path, NULL, NULL, ci->ren1->branch, ci->ren2->branch, &mfi.blob, add) < 0) return -1; } else { char *new_path = find_path_for_conflict(opt, a->path, ci->ren1->branch, ci->ren2->branch); if (update_file(opt, 0, &mfi.blob, new_path ? new_path : a->path)) return -1; free(new_path); if (!opt->priv->call_depth && update_stages(opt, a->path, NULL, a, NULL)) return -1; } if (!mfi.clean && mfi.blob.mode == a->mode && oideq(&mfi.blob.oid, &a->oid)) { /* * Getting here means we were attempting to merge a binary * blob. Since we can't merge binaries, the merge algorithm * just takes one side. But we don't want to copy the * contents of one side to both paths; we'd rather use the * original content at the given path for each path. */ oidcpy(&mfi.blob.oid, &b->oid); mfi.blob.mode = b->mode; } add = &ci->ren2->dst_entry->stages[flip_stage(3)]; if (is_valid(add)) { add->path = mfi.blob.path = b->path; if (handle_file_collision(opt, b->path, NULL, NULL, ci->ren1->branch, ci->ren2->branch, add, &mfi.blob) < 0) return -1; } else { char *new_path = find_path_for_conflict(opt, b->path, ci->ren2->branch, ci->ren1->branch); if (update_file(opt, 0, &mfi.blob, new_path ? new_path : b->path)) return -1; free(new_path); if (!opt->priv->call_depth && update_stages(opt, b->path, NULL, NULL, b)) return -1; } return 0; } static int handle_rename_rename_2to1(struct merge_options *opt, struct rename_conflict_info *ci) { /* Two files, a & b, were renamed to the same thing, c. */ struct diff_filespec *a = ci->ren1->pair->one; struct diff_filespec *b = ci->ren2->pair->one; struct diff_filespec *c1 = ci->ren1->pair->two; struct diff_filespec *c2 = ci->ren2->pair->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 ostage1, ostage2; output(opt, 1, _("CONFLICT (rename/rename): " "Rename %s->%s in %s. " "Rename %s->%s in %s"), a->path, c1->path, ci->ren1->branch, b->path, c2->path, ci->ren2->branch); path_side_1_desc = xstrfmt("version of %s from %s", path, a->path); path_side_2_desc = xstrfmt("version of %s from %s", path, b->path); ostage1 = ci->ren1->branch == opt->branch1 ? 3 : 2; ostage2 = flip_stage(ostage1); ci->ren1->src_entry->stages[ostage1].path = a->path; ci->ren2->src_entry->stages[ostage2].path = b->path; if (merge_mode_and_contents(opt, a, c1, &ci->ren1->src_entry->stages[ostage1], path_side_1_desc, opt->branch1, opt->branch2, 1 + opt->priv->call_depth * 2, &mfi_c1) || merge_mode_and_contents(opt, b, &ci->ren2->src_entry->stages[ostage2], c2, path_side_2_desc, opt->branch1, opt->branch2, 1 + opt->priv->call_depth * 2, &mfi_c2)) return -1; free(path_side_1_desc); free(path_side_2_desc); mfi_c1.blob.path = path; mfi_c2.blob.path = path; return handle_file_collision(opt, path, a->path, b->path, ci->ren1->branch, ci->ren2->branch, &mfi_c1.blob, &mfi_c2.blob); } /* * Get the diff_filepairs changed between o_tree and tree. */ static struct diff_queue_struct *get_diffpairs(struct merge_options *opt, struct tree *o_tree, struct tree *tree) { struct diff_queue_struct *ret; struct diff_options opts; repo_diff_setup(opt->repo, &opts); opts.flags.recursive = 1; opts.flags.rename_empty = 0; opts.detect_rename = merge_detect_rename(opt); /* * 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 = (opt->rename_limit >= 0) ? opt->rename_limit : 1000; opts.rename_score = opt->rename_score; opts.show_rename_progress = opt->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 > opt->priv->needed_rename_limit) opt->priv->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 repository *r, struct tree *tree, const char *path) { struct object_id hashy; unsigned short mode_o; return !get_tree_entry(r, &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); if (entry->new_dir.len == 0) /* * If someone renamed/merged a subdirectory into the root * directory (e.g. 'some/subdir' -> ''), then we want to * avoid returning * '' + '/filename' * as the rename; we need to make old_path + oldlen advance * past the '/' character. */ oldlen++; 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; /* Default return values: NULL, meaning no rename */ *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. */ /* * 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 is NULL, old_path wasn't in a directory, so there * could not be a directory rename (our rule elsewhere that a * directory which still exists is not considered to have been * renamed means the root directory can never be renamed -- because * the root directory always exists). */ if (end_of_old == NULL) return; /* Note: *old_dir and *new_dir are still NULL */ /* * If new_path contains no directory (end_of_new is NULL), then we * have a rename of old_path's directory to the root directory. */ if (end_of_new == NULL) { *old_dir = xstrndup(old_path, end_of_old - old_path); *new_dir = xstrdup(""); return; } /* Find the first non-matching character traversing backwards */ while (*--end_of_new == *--end_of_old && end_of_old != old_path && end_of_new != new_path) ; /* Do nothing; all in the while loop */ /* * If both got back to the beginning of their strings, then the * directory didn't change at all, only the basename did. */ if (end_of_old == old_path && end_of_new == new_path && *end_of_old == *end_of_new) return; /* Note: *old_dir and *new_dir are still NULL */ /* * If end_of_new got back to the beginning of its string, and * end_of_old got back to the beginning of some subdirectory, then * we have a rename/merge of a subdirectory into the root, which * needs slightly special handling. * * Note: There is no need to consider the opposite case, with a * rename/merge of the root directory into some subdirectory * because as noted above the root directory always exists so it * cannot be considered to be renamed. */ if (end_of_new == new_path && end_of_old != old_path && end_of_old[-1] == '/') { *old_dir = xstrndup(old_path, --end_of_old - old_path); *new_dir = xstrdup(""); return; } /* * We've found the first non-matching character in the directory * paths. That means the current characters we were looking at * were part of the first non-matching subdir name going back from * the end of the strings. Get the whole name by advancing both * end_of_old and end_of_new to the NEXT '/' character. That will * represent the entire directory rename. * * The reason for the increment is cases like * a/b/star/foo/whatever.c -> a/b/tar/foo/random.c * After dropping the basename and going back to the first * non-matching character, we're now comparing: * a/b/s and a/b/ * and we want to be comparing: * a/b/star/ and a/b/tar/ * but without the pre-increment, the one on the right would stay * a/b/. */ end_of_old = strchr(++end_of_old, '/'); end_of_new = strchr(++end_of_new, '/'); /* Copy the old and new directories into *old_dir and *new_dir. */ *old_dir = xstrndup(old_path, end_of_old - old_path); *new_dir = xstrndup(new_path, end_of_new - new_path); } 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->ent, 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 *opt, 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(opt, 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(opt->repo, tree, new_path)) { collision_ent->reported_already = 1; strbuf_add_separated_string_list(&collision_paths, ", ", &collision_ent->source_files); output(opt, 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(opt, 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 affec