/* * 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 "config.h" #include "advice.h" #include "lockfile.h" #include "cache-tree.h" #include "object-store.h" #include "commit.h" #include "blob.h" #include "builtin.h" #include "tree-walk.h" #include "diff.h" #include "diffcore.h" #include "tag.h" #include "alloc.h" #include "unpack-trees.h" #include "string-list.h" #include "xdiff-interface.h" #include "ll-merge.h" #include "attr.h" #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) { struct object_id shifted; if (!*subtree_shift) { shift_tree(&one->object.oid, &two->object.oid, &shifted, 0); } else { shift_tree_by(&one->object.oid, &two->object.oid, &shifted, subtree_shift); } if (!oidcmp(&two->object.oid, &shifted)) return two; return lookup_tree(&shifted); } static struct commit *make_virtual_commit(struct tree *tree, const char *comment) { struct commit *commit = alloc_commit_node(the_repository); set_merge_remote_desc(commit, comment, (struct object *)commit); commit->maybe_tree = tree; commit->object.parsed = 1; return commit; } /* * 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 oid_eq(const struct object_id *a, const struct object_id *b) { if (!a && !b) return 2; return a && b && oidcmp(a, b) == 0; } enum rename_type { RENAME_NORMAL = 0, RENAME_DIR, RENAME_DELETE, RENAME_ONE_FILE_TO_ONE, RENAME_ONE_FILE_TO_TWO, RENAME_TWO_FILES_TO_ONE }; struct rename_conflict_info { enum rename_type rename_type; struct diff_filepair *pair1; struct diff_filepair *pair2; const char *branch1; const char *branch2; struct stage_data *dst_entry1; struct stage_data *dst_entry2; struct diff_filespec ren1_other; struct diff_filespec ren2_other; }; /* * Since we want to write the index eventually, we cannot reuse the index * for these (temporary) data. */ struct stage_data { struct { unsigned mode; struct object_id oid; } stages[4]; struct rename_conflict_info *rename_conflict_info; unsigned processed:1; }; static inline void setup_rename_conflict_info(enum rename_type rename_type, struct diff_filepair *pair1, struct diff_filepair *pair2, const char *branch1, const char *branch2, struct stage_data *dst_entry1, struct stage_data *dst_entry2, struct merge_options *o, struct stage_data *src_entry1, struct stage_data *src_entry2) { struct rename_conflict_info *ci = xcalloc(1, sizeof(struct rename_conflict_info)); ci->rename_type = rename_type; ci->pair1 = pair1; ci->branch1 = branch1; ci->branch2 = branch2; ci->dst_entry1 = dst_entry1; dst_entry1->rename_conflict_info = ci; dst_entry1->processed = 0; assert(!pair2 == !dst_entry2); if (dst_entry2) { ci->dst_entry2 = dst_entry2; ci->pair2 = pair2; dst_entry2->rename_conflict_info = ci; } if (rename_type == RENAME_TWO_FILES_TO_ONE) { /* * For each rename, there could have been * modifications on the side of history where that * file was not renamed. */ int ostage1 = o->branch1 == branch1 ? 3 : 2; int ostage2 = ostage1 ^ 1; ci->ren1_other.path = pair1->one->path; 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; oidcpy(&ci->ren2_other.oid, &src_entry2->stages[ostage2].oid); ci->ren2_other.mode = src_entry2->stages[ostage2].mode; } } static int show(struct merge_options *o, int v) { return (!o->call_depth && o->verbosity >= v) || o->verbosity >= 5; } __attribute__((format (printf, 3, 4))) static void output(struct merge_options *o, int v, const char *fmt, ...) { va_list ap; if (!show(o, v)) return; strbuf_addchars(&o->obuf, ' ', o->call_depth * 2); va_start(ap, fmt); strbuf_vaddf(&o->obuf, fmt, ap); va_end(ap); strbuf_addch(&o->obuf, '\n'); if (!o->buffer_output) flush_output(o); } static void output_commit_title(struct merge_options *o, struct commit *commit) { 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 { strbuf_add_unique_abbrev(&o->obuf, &commit->object.oid, DEFAULT_ABBREV); strbuf_addch(&o->obuf, ' '); if (parse_commit(commit) != 0) 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) strbuf_addf(&o->obuf, "%.*s\n", len, title); unuse_commit_buffer(commit, msg); } } flush_output(o); } 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; int ret; ce = make_cache_entry(mode, oid ? oid->hash : null_sha1, path, stage, 0); if (!ce) 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(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) { parse_tree(tree); init_tree_desc(desc, tree->buffer, tree->size); } 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 index_state tmp_index = { NULL }; memset(&o->unpack_opts, 0, sizeof(o->unpack_opts)); if (o->call_depth) o->unpack_opts.index_only = 1; else 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, &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; if (unmerged_cache()) { int i; fprintf(stderr, "BUG: There are unmerged index entries:\n"); for (i = 0; i < active_nr; i++) { const struct cache_entry *ce = active_cache[i]; if (ce_stage(ce)) fprintf(stderr, "BUG: %d %.*s\n", ce_stage(ce), (int)ce_namelen(ce), ce->name); } 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) { err(o, _("error building trees")); return NULL; } result = lookup_tree(&active_cache_tree->oid); return result; } 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); 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 void get_files_dirs(struct merge_options *o, struct tree *tree) { struct pathspec match_all; memset(&match_all, 0, sizeof(match_all)); 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; } /* * 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(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(&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; } /* * 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(void) { struct string_list *unmerged = xcalloc(1, sizeof(struct string_list)); int i; unmerged->strdup_strings = 1; for (i = 0; i < active_nr; i++) { struct string_list_item *item; struct stage_data *e; const struct cache_entry *ce = active_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 *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 * 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 (o->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(&o->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(&o->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); } 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; }; 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_cache(path)) return -1; if (o) if (add_cacheinfo(opt, o->mode, &o->oid, path, 1, 0, options)) return -1; if (a) if (add_cacheinfo(opt, a->mode, &a->oid, path, 2, 0, options)) return -1; if (b) 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, 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 *o, int clean, const char *path, int no_wd) { int update_cache = o->call_depth || clean; int update_working_directory = !o->call_depth && !no_wd; if (update_cache) { if (remove_file_from_cache(path)) return -1; } if (update_working_directory) { if (ignore_case) { struct cache_entry *ce; ce = cache_file_exists(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 *o, 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(&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++); } 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); } /** * 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; struct stat st; strbuf_addstr(&dirpath, path); strbuf_addch(&dirpath, '/'); pos = cache_name_pos(dirpath.buf, dirpath.len); if (pos < 0) pos = -1 - pos; if (pos < active_nr && !strncmp(dirpath.buf, active_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)); } /* * 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); } /* * 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) pos = -1 - pos; while (pos < active_nr && !strcmp(path, active_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(active_cache[pos])) { case 0: case 2: return 0; } pos++; } return file_exists(path); } static int was_dirty(struct merge_options *o, const char *path) { struct cache_entry *ce; int dirty = 1; if (o->call_depth || !was_tracked(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) { 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 < o->df_conflict_file_set.nr; i++) { const char *df_path = o->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(o, 3, _("Removing %s to make room for subdirectory\n"), df_path); unlink(df_path); unsorted_string_list_delete_item(&o->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(o, msg, path, _(": perhaps a D/F conflict?")); return err(o, msg, path, ""); } /* * Do not unlink a file in the work tree if we are not * tracking it. */ if (would_lose_untracked(path)) return err(o, _("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(o, msg, path, _(": perhaps a D/F conflict?")); } 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; if (update_wd) { enum object_type type; void *buf; unsigned long size; if (S_ISGITLINK(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(oid, &type, &size); if (!buf) 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)) { free(buf); size = strbuf.len; buf = strbuf_detach(&strbuf, NULL); } } if (make_room_for_path(o, path) < 0) { update_wd = 0; goto free_buf; } if (S_ISREG(mode) || (!has_symlinks && S_ISLNK(mode))) { int fd; if (mode & 0100) mode = 0777; else mode = 0666; fd = open(path, O_WRONLY | O_TRUNC | O_CREAT, mode); 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)) { char *lnk = xmemdupz(buf, size); safe_create_leading_directories_const(path); unlink(path); if (symlink(lnk, path)) ret = err(o, _("failed to symlink '%s': %s"), path, strerror(errno)); free(lnk); } else 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 (!ret && update_cache) if (add_cacheinfo(o, mode, oid, path, 0, update_wd, ADD_CACHE_OK_TO_ADD)) return -1; return ret; } static int update_file(struct merge_options *o, int clean, const struct object_id *oid, unsigned mode, const char *path) { 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 { struct object_id oid; unsigned mode; unsigned clean:1, merge:1; }; static int merge_3way(struct merge_options *o, mmbuffer_t *result_buf, const struct diff_filespec *one, const struct diff_filespec *a, const struct diff_filespec *b, const char *branch1, const char *branch2) { mmfile_t orig, src1, src2; struct ll_merge_options ll_opts = {0}; char *base_name, *name1, *name2; int merge_status; ll_opts.renormalize = o->renormalize; ll_opts.xdl_opts = o->xdl_opts; if (o->call_depth) { ll_opts.virtual_ancestor = 1; ll_opts.variant = 0; } else { switch (o->recursive_variant) { case MERGE_RECURSIVE_OURS: ll_opts.variant = XDL_MERGE_FAVOR_OURS; break; case MERGE_RECURSIVE_THEIRS: ll_opts.variant = XDL_MERGE_FAVOR_THEIRS; break; default: ll_opts.variant = 0; break; } } if (strcmp(a->path, b->path) || (o->ancestor != NULL && strcmp(a->path, one->path) != 0)) { base_name = o->ancestor == NULL ? NULL : mkpathdup("%s:%s", o->ancestor, one->path); name1 = mkpathdup("%s:%s", branch1, a->path); name2 = mkpathdup("%s:%s", branch2, b->path); } else { base_name = o->ancestor == NULL ? NULL : mkpathdup("%s", o->ancestor); name1 = mkpathdup("%s", branch1); name2 = mkpathdup("%s", branch2); } 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); free(base_name); free(name1); free(name2); free(orig.ptr); free(src1.ptr); free(src2.ptr); return merge_status; } 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 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(base)) || !(commit_a = lookup_commit_reference(a)) || !(commit_b = lookup_commit_reference(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; if (S_ISREG(a->mode)) { result->mode = a->mode; oidcpy(&result->oid, &a->oid); } else { result->mode = b->mode; oidcpy(&result->oid, &b->oid); } } else { 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; else { result->mode = a->mode; if (b->mode != one->mode) { result->clean = 0; result->merge = 1; } } 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 ret = 0, merge_status; merge_status = merge_3way(o, &result_buf, one, a, b, branch1, branch2); if ((merge_status < 0) || !result_buf.ptr) ret = err(o, _("Failed to execute internal merge")); 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); if (ret) return ret; result->clean = (merge_status == 0); } else if (S_ISGITLINK(a->mode)) { result->clean = merge_submodule(o, &result->oid, one->path, &one->oid, &a->oid, &b->oid); } else if (S_ISLNK(a->mode)) { 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"); } if (result->merge) output(o, 2, _("Auto-merging %s"), filename); return 0; } 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; int ret; if (filename1) side1 = xstrfmt("%s:%s", branch1, filename1); if (filename2) side2 = xstrfmt("%s:%s", branch2, filename2); ret = merge_file_1(o, one, a, b, target_filename, side1 ? side1 : branch1, side2 ? side2 : branch2, mfi); free(side1); free(side2); return ret; } 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; oidcpy(&one.oid, o_oid); one.mode = o_mode; oidcpy(&a.oid, a_oid); a.mode = a_mode; oidcpy(&b.oid, b_oid); b.mode = b_mode; return merge_file_1(o, &one, &a, &b, path, branch1, branch2, mfi); } static int conflict_rename_dir(struct merge_options *o, struct diff_filepair *pair, const char *rename_branch, const char *other_branch) { const struct diff_filespec *dest = pair->two; if (!o->call_depth && would_lose_untracked(dest->path)) { char *alt_path = unique_path(o, dest->path, rename_branch); output(o, 1, _("Error: Refusing to lose untracked file at %s; " "writing to %s instead."), dest->path, alt_path); /* * Write the file in worktree at alt_path, but not in the * index. Instead, write to dest->path for the index but * only at the higher appropriate stage. */ if (update_file(o, 0, &dest->oid, dest->mode, alt_path)) return -1; free(alt_path); return update_stages(o, dest->path, NULL, rename_branch == o->branch1 ? dest : NULL, rename_branch == o->branch1 ? NULL : dest); } /* Update dest->path both in index and in worktree */ if (update_file(o, 1, &dest->oid, dest->mode, dest->path)) return -1; return 0; } static int handle_change_delete(struct merge_options *o, const char *path, const char *old_path, const struct object_id *o_oid, int o_mode, 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 *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) { /* * 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_cache(path); if (!ret) ret = update_file(o, 0, o_oid, o_mode, update_path); } else { 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 { 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 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(alt_path); return ret; } static int conflict_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; 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) { struct object_id *oid = &entry->stages[stage].oid; unsigned mode = entry->stages[stage].mode; if (mode == 0 || is_null_oid(oid)) return NULL; oidcpy(&target->oid, oid); target->mode = mode; return target; } static int handle_file(struct merge_options *o, struct diff_filespec *rename, int stage, struct rename_conflict_info *ci) { char *dst_name = rename->path; struct stage_data *dst_entry; const char *cur_branch, *other_branch; struct diff_filespec other; struct diff_filespec *add; int ret; if (stage == 2) { dst_entry = ci->dst_entry1; cur_branch = ci->branch1; other_branch = ci->branch2; } else { dst_entry = ci->dst_entry2; cur_branch = ci->branch2; other_branch = ci->branch1; } add = filespec_from_entry(&other, dst_entry, stage ^ 1); if (add) { int ren_src_was_dirty = was_dirty(o, rename->path); char *add_name = unique_path(o, rename->path, other_branch); if (update_file(o, 0, &add->oid, add->mode, add_name)) return -1; if (ren_src_was_dirty) { output(o, 1, _("Refusing to lose dirty file at %s"), rename->path); } /* * Because the double negatives somehow keep confusing me... * 1) update_wd iff !ren_src_was_dirty. * 2) no_wd iff !update_wd * 3) so, no_wd == !!ren_src_was_dirty == ren_src_was_dirty */ remove_file(o, 0, rename->path, ren_src_was_dirty); dst_name = unique_path(o, rename->path, cur_branch); } else { if (dir_in_way(rename->path, !o->call_depth, 0)) { dst_name = unique_path(o, rename->path, cur_branch); output(o, 1, _("%s is a directory in %s adding as %s instead"), rename->path, other_branch, dst_name); } else if (!o->call_depth && would_lose_untracked(rename->path)) { dst_name = unique_path(o, rename->path, cur_branch); output(o, 1, _("Refusing to lose untracked file at %s; " "adding as %s instead"), rename->path, dst_name); } } if ((ret = update_file(o, 0, &rename->oid, rename->mode, dst_name))) ; /* fall through, do allow dst_name to be released */ else if (stage == 2) ret = update_stages(o, rename->path, NULL, rename, add); else ret = update_stages(o, rename->path, NULL, add, rename); if (dst_name != rename->path) free(dst_name); return ret; } static int conflict_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; struct diff_filespec *a = ci->pair1->two; struct diff_filespec *b = ci->pair2->two; output(o, 1, _("CONFLICT (rename/rename): " "Rename \"%s\"->\"%s\" in branch \"%s\" " "rename \"%s\"->\"%s\" in \"%s\"%s"), one->path, a->path, ci->branch1, one->path, b->path, ci->branch2, o->call_depth ? _(" (left unresolved)") : ""); if (o->call_depth) { struct merge_file_info mfi; struct diff_filespec other; struct diff_filespec *add; 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. */ if (update_file(o, 0, &mfi.oid, mfi.mode, one->path)) return -1; /* * Above, we put the merged content at the merge-base's * path. Now we usually need to delete both a->path and * b->path. However, the rename on each side of the merge * could also be involved in a rename/add conflict. In * such cases, we should keep the added file around, * resolving the conflict at that path in its favor. */ add = filespec_from_entry(&other, ci->dst_entry1, 2 ^ 1); 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) { if (update_file(o, 0, &add->oid, add->mode, b->path)) return -1; } else remove_file_from_cache(b->path); } else if (handle_file(o, a, 2, ci) || handle_file(o, b, 3, ci)) return -1; return 0; } static int conflict_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; struct diff_filespec *b = ci->pair2->one; 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. " "Rename %s->%s in %s"), a->path, c1->path, ci->branch1, b->path, c2->path, ci->branch2); 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) { /* * If mfi_c1.clean && mfi_c2.clean, then it might make * sense to do a two-way merge of those results. But, I * think in all cases, it makes sense to have the virtual * merge base just undo the renames; they can be detected * again later for the non-recursive merge. */ remove_file(o, 0, path, 0); 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); 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]