diff options
Diffstat (limited to 'merge-ort.c')
| -rw-r--r-- | merge-ort.c | 1927 |
1 files changed, 1886 insertions, 41 deletions
diff --git a/merge-ort.c b/merge-ort.c index 31103d2140..ba35600d4e 100644 --- a/merge-ort.c +++ b/merge-ort.c @@ -25,8 +25,11 @@ #include "diff.h" #include "diffcore.h" #include "dir.h" +#include "ll-merge.h" #include "object-store.h" +#include "revision.h" #include "strmap.h" +#include "submodule.h" #include "tree.h" #include "unpack-trees.h" #include "xdiff-interface.h" @@ -48,6 +51,53 @@ enum merge_side { MERGE_SIDE2 = 2 }; +struct rename_info { + /* + * All variables that are arrays of size 3 correspond to data tracked + * for the sides in enum merge_side. Index 0 is almost always unused + * because we often only need to track information for MERGE_SIDE1 and + * MERGE_SIDE2 (MERGE_BASE can't have rename information since renames + * are determined relative to what changed since the MERGE_BASE). + */ + + /* + * pairs: pairing of filenames from diffcore_rename() + */ + struct diff_queue_struct pairs[3]; + + /* + * dirs_removed: directories removed on a given side of history. + */ + struct strset dirs_removed[3]; + + /* + * dir_rename_count: tracking where parts of a directory were renamed to + * + * When files in a directory are renamed, they may not all go to the + * same location. Each strmap here tracks: + * old_dir => {new_dir => int} + * That is, dir_rename_count[side] is a strmap to a strintmap. + */ + struct strmap dir_rename_count[3]; + + /* + * dir_renames: computed directory renames + * + * This is a map of old_dir => new_dir and is derived in part from + * dir_rename_count. + */ + struct strmap dir_renames[3]; + + /* + * needed_limit: value needed for inexact rename detection to run + * + * If the current rename limit wasn't high enough for inexact + * rename detection to run, this records the limit needed. Otherwise, + * this value remains 0. + */ + int needed_limit; +}; + struct merge_options_internal { /* * paths: primary data structure in all of merge ort. @@ -116,12 +166,20 @@ struct merge_options_internal { struct strmap output; /* - * current_dir_name: temporary var used in collect_merge_info_callback() + * renames: various data relating to rename detection + */ + struct rename_info renames; + + /* + * current_dir_name, toplevel_dir: temporary vars * - * Used to set merged_info.directory_name; see documentation for that - * variable and the requirements placed on that field. + * These are used in collect_merge_info_callback(), and will set the + * various merged_info.directory_name for the various paths we get; + * see documentation for that variable and the requirements placed on + * that field. */ const char *current_dir_name; + const char *toplevel_dir; /* call_depth: recursion level counter for merging merge bases */ int call_depth; @@ -256,8 +314,12 @@ static void free_strmap_strings(struct strmap *map) static void clear_or_reinit_internal_opts(struct merge_options_internal *opti, int reinitialize) { + struct rename_info *renames = &opti->renames; + int i; void (*strmap_func)(struct strmap *, int) = reinitialize ? strmap_partial_clear : strmap_clear; + void (*strset_func)(struct strset *) = + reinitialize ? strset_partial_clear : strset_clear; /* * We marked opti->paths with strdup_strings = 0, so that we @@ -287,6 +349,17 @@ static void clear_or_reinit_internal_opts(struct merge_options_internal *opti, string_list_clear(&opti->paths_to_free, 0); opti->paths_to_free.strdup_strings = 0; + /* Free memory used by various renames maps */ + for (i = MERGE_SIDE1; i <= MERGE_SIDE2; ++i) { + strset_func(&renames->dirs_removed[i]); + + partial_clear_dir_rename_count(&renames->dir_rename_count[i]); + if (!reinitialize) + strmap_clear(&renames->dir_rename_count[i], 1); + + strmap_func(&renames->dir_renames[i], 0); + } + if (!reinitialize) { struct hashmap_iter iter; struct strmap_entry *e; @@ -325,6 +398,25 @@ static int err(struct merge_options *opt, const char *err, ...) return -1; } +static void format_commit(struct strbuf *sb, + int indent, + struct commit *commit) +{ + struct merge_remote_desc *desc; + struct pretty_print_context ctx = {0}; + ctx.abbrev = DEFAULT_ABBREV; + + strbuf_addchars(sb, ' ', indent); + desc = merge_remote_util(commit); + if (desc) { + strbuf_addf(sb, "virtual %s\n", desc->name); + return; + } + + format_commit_message(commit, "%h %s", sb, &ctx); + strbuf_addch(sb, '\n'); +} + __attribute__((format (printf, 4, 5))) static void path_msg(struct merge_options *opt, const char *path, @@ -346,6 +438,36 @@ static void path_msg(struct merge_options *opt, strbuf_addch(sb, '\n'); } +/* 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 strmap *existing_paths, + const char *path, + const char *branch) +{ + 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 (strmap_contains(existing_paths, newpath.buf)) { + strbuf_setlen(&newpath, base_len); + strbuf_addf(&newpath, "_%d", suffix++); + } + + return strbuf_detach(&newpath, NULL); +} + /*** Function Grouping: functions related to collect_merge_info() ***/ static void setup_path_info(struct merge_options *opt, @@ -407,6 +529,60 @@ static void setup_path_info(struct merge_options *opt, result->util = mi; } +static void add_pair(struct merge_options *opt, + struct name_entry *names, + const char *pathname, + unsigned side, + unsigned is_add /* if false, is_delete */) +{ + struct diff_filespec *one, *two; + struct rename_info *renames = &opt->priv->renames; + int names_idx = is_add ? side : 0; + + one = alloc_filespec(pathname); + two = alloc_filespec(pathname); + fill_filespec(is_add ? two : one, + &names[names_idx].oid, 1, names[names_idx].mode); + diff_queue(&renames->pairs[side], one, two); +} + +static void collect_rename_info(struct merge_options *opt, + struct name_entry *names, + const char *dirname, + const char *fullname, + unsigned filemask, + unsigned dirmask, + unsigned match_mask) +{ + struct rename_info *renames = &opt->priv->renames; + unsigned side; + + /* Update dirs_removed, as needed */ + if (dirmask == 1 || dirmask == 3 || dirmask == 5) { + /* absent_mask = 0x07 - dirmask; sides = absent_mask/2 */ + unsigned sides = (0x07 - dirmask)/2; + if (sides & 1) + strset_add(&renames->dirs_removed[1], fullname); + if (sides & 2) + strset_add(&renames->dirs_removed[2], fullname); + } + + if (filemask == 0 || filemask == 7) + return; + + for (side = MERGE_SIDE1; side <= MERGE_SIDE2; ++side) { + unsigned side_mask = (1 << side); + + /* Check for deletion on side */ + if ((filemask & 1) && !(filemask & side_mask)) + add_pair(opt, names, fullname, side, 0 /* delete */); + + /* Check for addition on side */ + if (!(filemask & 1) && (filemask & side_mask)) + add_pair(opt, names, fullname, side, 1 /* add */); + } +} + static int collect_merge_info_callback(int n, unsigned long mask, unsigned long dirmask, @@ -508,6 +684,12 @@ static int collect_merge_info_callback(int n, } /* + * Gather additional information used in rename detection. + */ + collect_rename_info(opt, names, dirname, fullpath, + filemask, dirmask, match_mask); + + /* * Record information about the path so we can resolve later in * process_entries. */ @@ -582,10 +764,10 @@ static int collect_merge_info(struct merge_options *opt, int ret; struct tree_desc t[3]; struct traverse_info info; - const char *toplevel_dir_placeholder = ""; - opt->priv->current_dir_name = toplevel_dir_placeholder; - setup_traverse_info(&info, toplevel_dir_placeholder); + opt->priv->toplevel_dir = ""; + opt->priv->current_dir_name = opt->priv->toplevel_dir; + setup_traverse_info(&info, opt->priv->toplevel_dir); info.fn = collect_merge_info_callback; info.data = opt; info.show_all_errors = 1; @@ -597,13 +779,258 @@ static int collect_merge_info(struct merge_options *opt, init_tree_desc(t + 1, side1->buffer, side1->size); init_tree_desc(t + 2, side2->buffer, side2->size); + trace2_region_enter("merge", "traverse_trees", opt->repo); ret = traverse_trees(NULL, 3, t, &info); + trace2_region_leave("merge", "traverse_trees", opt->repo); return ret; } /*** Function Grouping: functions related to threeway content merges ***/ +static int find_first_merges(struct repository *repo, + const char *path, + struct commit *a, + struct commit *b, + struct object_array *result) +{ + 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 int merge_submodule(struct merge_options *opt, + const char *path, + const struct object_id *o, + const struct object_id *a, + const struct object_id *b, + struct object_id *result) +{ + struct commit *commit_o, *commit_a, *commit_b; + int parent_count; + struct object_array merges; + struct strbuf sb = STRBUF_INIT; + + int i; + int search = !opt->priv->call_depth; + + /* store fallback answer in result in case we fail */ + oidcpy(result, opt->priv->call_depth ? o : a); + + /* we can not handle deletion conflicts */ + if (is_null_oid(o)) + return 0; + if (is_null_oid(a)) + return 0; + if (is_null_oid(b)) + return 0; + + if (add_submodule_odb(path)) { + path_msg(opt, path, 0, + _("Failed to merge submodule %s (not checked out)"), + path); + return 0; + } + + if (!(commit_o = lookup_commit_reference(opt->repo, o)) || + !(commit_a = lookup_commit_reference(opt->repo, a)) || + !(commit_b = lookup_commit_reference(opt->repo, b))) { + path_msg(opt, path, 0, + _("Failed to merge submodule %s (commits not present)"), + path); + return 0; + } + + /* check whether both changes are forward */ + if (!in_merge_bases(commit_o, commit_a) || + !in_merge_bases(commit_o, commit_b)) { + path_msg(opt, path, 0, + _("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); + path_msg(opt, path, 1, + _("Note: Fast-forwarding submodule %s to %s"), + path, oid_to_hex(b)); + return 1; + } + if (in_merge_bases(commit_b, commit_a)) { + oidcpy(result, a); + path_msg(opt, path, 1, + _("Note: Fast-forwarding submodule %s to %s"), + path, oid_to_hex(a)); + 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, path, commit_a, commit_b, + &merges); + switch (parent_count) { + case 0: + path_msg(opt, path, 0, _("Failed to merge submodule %s"), path); + break; + + case 1: + format_commit(&sb, 4, + (struct commit *)merges.objects[0].item); + path_msg(opt, path, 0, + _("Failed to merge submodule %s, but a possible merge " + "resolution exists:\n%s\n"), + path, sb.buf); + path_msg(opt, path, 1, + _("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); + strbuf_release(&sb); + break; + default: + for (i = 0; i < merges.nr; i++) + format_commit(&sb, 4, + (struct commit *)merges.objects[i].item); + path_msg(opt, path, 0, + _("Failed to merge submodule %s, but multiple " + "possible merges exist:\n%s"), path, sb.buf); + strbuf_release(&sb); + } + + object_array_clear(&merges); + return 0; +} + +static int merge_3way(struct merge_options *opt, + const char *path, + const struct object_id *o, + const struct object_id *a, + const struct object_id *b, + const char *pathnames[3], + const int extra_marker_size, + mmbuffer_t *result_buf) +{ + 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(pathnames[0] && pathnames[1] && pathnames[2] && opt->ancestor); + if (pathnames[0] == pathnames[1] && pathnames[1] == pathnames[2]) { + base = mkpathdup("%s", opt->ancestor); + name1 = mkpathdup("%s", opt->branch1); + name2 = mkpathdup("%s", opt->branch2); + } else { + base = mkpathdup("%s:%s", opt->ancestor, pathnames[0]); + name1 = mkpathdup("%s:%s", opt->branch1, pathnames[1]); + name2 = mkpathdup("%s:%s", opt->branch2, pathnames[2]); + } + + read_mmblob(&orig, o); + read_mmblob(&src1, a); + read_mmblob(&src2, b); + + merge_status = ll_merge(result_buf, 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 handle_content_merge(struct merge_options *opt, const char *path, const struct version_info *o, @@ -613,7 +1040,130 @@ static int handle_content_merge(struct merge_options *opt, const int extra_marker_size, struct version_info *result) { - die("Not yet implemented"); + /* + * path is the target location where we want to put the file, and + * is used to determine any normalization rules in ll_merge. + * + * The normal case is that path and all entries in pathnames are + * identical, though renames can affect which path we got one of + * the three blobs to merge on various sides of history. + * + * extra_marker_size is the amount to extend conflict markers in + * ll_merge; this is neeed if we have content merges of content + * merges, which happens for example with rename/rename(2to1) and + * rename/add conflicts. + */ + unsigned clean = 1; + + /* + * handle_content_merge() needs both files to be of the same type, i.e. + * both files OR both submodules OR both symlinks. Conflicting types + * needs to be handled elsewhere. + */ + assert((S_IFMT & a->mode) == (S_IFMT & b->mode)); + + /* Merge modes */ + if (a->mode == b->mode || a->mode == o->mode) + result->mode = b->mode; + else { + /* must be the 100644/100755 case */ + assert(S_ISREG(a->mode)); + result->mode = a->mode; + clean = (b->mode == o->mode); + /* + * FIXME: If opt->priv->call_depth && !clean, then we really + * should not make result->mode match either a->mode or + * b->mode; that causes t6036 "check conflicting mode for + * regular file" to fail. It would be best to use some other + * mode, but we'll confuse all kinds of stuff if we use one + * where S_ISREG(result->mode) isn't true, and if we use + * something like 0100666, then tree-walk.c's calls to + * canon_mode() will just normalize that to 100644 for us and + * thus not solve anything. + * + * Figure out if there's some kind of way we can work around + * this... + */ + } + + /* + * Trivial oid merge. + * + * Note: While one might assume that the next four lines would + * be unnecessary due to the fact that match_mask is often + * setup and already handled, renames don't always take care + * of that. + */ + if (oideq(&a->oid, &b->oid) || oideq(&a->oid, &o->oid)) + oidcpy(&result->oid, &b->oid); + else if (oideq(&b->oid, &o->oid)) + oidcpy(&result->oid, &a->oid); + + /* Remaining rules depend on file vs. submodule vs. symlink. */ + else if (S_ISREG(a->mode)) { + mmbuffer_t result_buf; + int ret = 0, merge_status; + int two_way; + + /* + * If 'o' is different type, treat it as null so we do a + * two-way merge. + */ + two_way = ((S_IFMT & o->mode) != (S_IFMT & a->mode)); + + merge_status = merge_3way(opt, path, + two_way ? &null_oid : &o->oid, + &a->oid, &b->oid, + pathnames, extra_marker_size, + &result_buf); + + 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->oid)) + ret = err(opt, _("Unable to add %s to database"), + path); + + free(result_buf.ptr); + if (ret) + return -1; + clean &= (merge_status == 0); + path_msg(opt, path, 1, _("Auto-merging %s"), path); + } else if (S_ISGITLINK(a->mode)) { + int two_way = ((S_IFMT & o->mode) != (S_IFMT & a->mode)); + clean = merge_submodule(opt, pathnames[0], + two_way ? &null_oid : &o->oid, + &a->oid, &b->oid, &result->oid); + if (opt->priv->call_depth && two_way && !clean) { + result->mode = o->mode; + oidcpy(&result->oid, &o->oid); + } + } else if (S_ISLNK(a->mode)) { + if (opt->priv->call_depth) { + clean = 0; + result->mode = o->mode; + oidcpy(&result->oid, &o->oid); + } else { + switch (opt->recursive_variant) { + case MERGE_VARIANT_NORMAL: + clean = 0; + oidcpy(&result->oid, &a->oid); + break; + case MERGE_VARIANT_OURS: + oidcpy(&result->oid, &a->oid); + break; + case MERGE_VARIANT_THEIRS: + oidcpy(&result->oid, &b->oid); + break; + } + } + } else + BUG("unsupported object type in the tree: %06o for %s", + a->mode, path); + + return clean; } /*** Function Grouping: functions related to detect_and_process_renames(), *** @@ -621,22 +1171,1010 @@ static int handle_content_merge(struct merge_options *opt, /*** Function Grouping: functions related to directory rename detection ***/ +struct collision_info { + struct string_list source_files; + unsigned reported_already:1; +}; + +/* + * Return a new string that replaces the beginning portion (which matches + * rename_info->key), with rename_info->util.new_dir. In perl-speak: + * new_path_name = (old_path =~ s/rename_info->key/rename_info->value/); + * NOTE: + * Caller must ensure that old_path starts with rename_info->key + '/'. + */ +static char *apply_dir_rename(struct strmap_entry *rename_info, + const char *old_path) +{ + struct strbuf new_path = STRBUF_INIT; + const char *old_dir = rename_info->key; + const char *new_dir = rename_info->value; + int oldlen, newlen, new_dir_len; + + oldlen = strlen(old_dir); + if (*new_dir == '\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++; + new_dir_len = strlen(new_dir); + newlen = new_dir_len + (strlen(old_path) - oldlen) + 1; + strbuf_grow(&new_path, newlen); + strbuf_add(&new_path, new_dir, new_dir_len); + strbuf_addstr(&new_path, &old_path[oldlen]); + + return strbuf_detach(&new_path, NULL); +} + +static int path_in_way(struct strmap *paths, const char *path, unsigned side_mask) +{ + struct merged_info *mi = strmap_get(paths, path); + struct conflict_info *ci; + if (!mi) + return 0; + INITIALIZE_CI(ci, mi); + return mi->clean || (side_mask & (ci->filemask | ci->dirmask)); +} + +/* + * See if there is a directory rename for path, and if there are any file + * level conflicts on the given side 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, + unsigned side_index, + struct strmap_entry *rename_info, + struct strmap *collisions) +{ + char *new_path = NULL; + struct collision_info *c_info; + 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(rename_info, path); + if (!new_path) + BUG("Failed to apply directory rename!"); + + /* + * 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. + */ + c_info = strmap_get(collisions, new_path); + if (c_info == NULL) + BUG("c_info 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 (c_info->reported_already) { + clean = 0; + } else if (path_in_way(&opt->priv->paths, new_path, 1 << side_index)) { + c_info->reported_already = 1; + strbuf_add_separated_string_list(&collision_paths, ", ", + &c_info->source_files); + path_msg(opt, new_path, 0, + _("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 (c_info->source_files.nr > 1) { + c_info->reported_already = 1; + strbuf_add_separated_string_list(&collision_paths, ", ", + &c_info->source_files); + path_msg(opt, new_path, 0, + _("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; +} + +static void get_provisional_directory_renames(struct merge_options *opt, + unsigned side, + int *clean) +{ + struct hashmap_iter iter; + struct strmap_entry *entry; + struct rename_info *renames = &opt->priv->renames; + + /* + * Collapse + * dir_rename_count: old_directory -> {new_directory -> count} + * down to + * dir_renames: old_directory -> best_new_directory + * where best_new_directory is the one with the unique highest count. + */ + strmap_for_each_entry(&renames->dir_rename_count[side], &iter, entry) { + const char *source_dir = entry->key; + struct strintmap *counts = entry->value; + struct hashmap_iter count_iter; + struct strmap_entry *count_entry; + int max = 0; + int bad_max = 0; + const char *best = NULL; + + strintmap_for_each_entry(counts, &count_iter, count_entry) { + const char *target_dir = count_entry->key; + intptr_t count = (intptr_t)count_entry->value; + + if (count == max) + bad_max = max; + else if (count > max) { + max = count; + best = target_dir; + } + } + + if (bad_max == max) { + path_msg(opt, source_dir, 0, + _("CONFLICT (directory rename split): " + "Unclear where to rename %s to; it was " + "renamed to multiple other directories, with " + "no destination getting a majority of the " + "files."), + source_dir); + /* + * We should mark this as unclean IF something attempts + * to use this rename. We do not yet have the logic + * in place to detect if this directory rename is being + * used, and optimizations that reduce the number of + * renames cause this to falsely trigger. For now, + * just disable it, causing t6423 testcase 2a to break. + * We'll later fix the detection, and when we do we + * will re-enable setting *clean to 0 (and thereby fix + * t6423 testcase 2a). + */ + /* *clean = 0; */ + } else { + strmap_put(&renames->dir_renames[side], + source_dir, (void*)best); + } + } +} + +static void handle_directory_level_conflicts(struct merge_options *opt) +{ + struct hashmap_iter iter; + struct strmap_entry *entry; + struct string_list duplicated = STRING_LIST_INIT_NODUP; + struct rename_info *renames = &opt->priv->renames; + struct strmap *side1_dir_renames = &renames->dir_renames[MERGE_SIDE1]; + struct strmap *side2_dir_renames = &renames->dir_renames[MERGE_SIDE2]; + int i; + + strmap_for_each_entry(side1_dir_renames, &iter, entry) { + if (strmap_contains(side2_dir_renames, entry->key)) + string_list_append(&duplicated, entry->key); + } + + for (i = 0; i < duplicated.nr; i++) { + strmap_remove(side1_dir_renames, duplicated.items[i].string, 0); + strmap_remove(side2_dir_renames, duplicated.items[i].string, 0); + } + string_list_clear(&duplicated, 0); +} + +static struct strmap_entry *check_dir_renamed(const char *path, + struct strmap *dir_renames) +{ + char *temp = xstrdup(path); + char *end; + struct strmap_entry *e = NULL; + + while ((end = strrchr(temp, '/'))) { + *end = '\0'; + e = strmap_get_entry(dir_renames, temp); + if (e) + break; + } + free(temp); + return e; +} + +static void compute_collisions(struct strmap *collisions, + struct strmap *dir_renames, + struct diff_queue_struct *pairs) +{ + int i; + + strmap_init_with_options(collisions, NULL, 0); + if (strmap_empty(dir_renames)) + return; + + /* + * Multiple files can be mapped to the same path due to directory + * renames done by the other side of history. Since that other + * side of history could have merged multiple directories into one, + * if our side of history added the same file basename to each of + * those directories, then all N of them would get implicitly + * renamed by the directory rename detection into the same path, + * and we'd get an add/add/.../add conflict, and all those adds + * from *this* side of history. This is not representable in the + * index, and users aren't going to easily be able to make sense of + * it. So we need to provide a good warning about what's + * happening, and fall back to no-directory-rename detection + * behavior for those paths. + * + * See testcases 9e and all of section 5 from t6043 for examples. + */ + for (i = 0; i < pairs->nr; ++i) { + struct strmap_entry *rename_info; + struct collision_info *collision_info; + char *new_path; + struct diff_filepair *pair = pairs->queue[i]; + + if (pair->status != 'A' && pair->status != 'R') + continue; + rename_info = check_dir_renamed(pair->two->path, dir_renames); + if (!rename_info) + continue; + + new_path = apply_dir_rename(rename_info, pair->two->path); + assert(new_path); + collision_info = strmap_get(collisions, new_path); + if (collision_info) { + free(new_path); + } else { + CALLOC_ARRAY(collision_info, 1); + string_list_init(&collision_info->source_files, 0); + strmap_put(collisions, new_path, collision_info); + } + string_list_insert(&collision_info->source_files, + pair->two->path); + } +} + +static char *check_for_directory_rename(struct merge_options *opt, + const char *path, + unsigned side_index, + struct strmap *dir_renames, + struct strmap *dir_rename_exclusions, + struct strmap *collisions, + int *clean_merge) +{ + char *new_path = NULL; + struct strmap_entry *rename_info; + struct strmap_entry *otherinfo = NULL; + const char *new_dir; + + if (strmap_empty(dir_renames)) + return new_path; + rename_info = check_dir_renamed(path, dir_renames); + if (!rename_info) + return new_path; + /* old_dir = rename_info->key; */ + new_dir = rename_info->value; + + /* + * This next part is a little weird. We do not want to do an + * implicit rename into a directory we renamed on our side, because + * that will result in a spurious rename/rename(1to2) conflict. An + * example: + * Base commit: dumbdir/afile, otherdir/bfile + * Side 1: smrtdir/afile, otherdir/bfile + * Side 2: dumbdir/afile, dumbdir/bfile + * Here, while working on Side 1, we could notice that otherdir was + * renamed/merged to dumbdir, and change the diff_filepair for + * otherdir/bfile into a rename into dumbdir/bfile. However, Side + * 2 will notice the rename from dumbdir to smrtdir, and do the + * transitive rename to move it from dumbdir/bfile to + * smrtdir/bfile. That gives us bfile in dumbdir vs being in + * smrtdir, a rename/rename(1to2) conflict. We really just want + * the file to end up in smrtdir. And the way to achieve that is + * to not let Side1 do the rename to dumbdir, since we know that is + * the source of one of our directory renames. + * + * That's why otherinfo and dir_rename_exclusions is here. + * + * As it turns out, this also prevents N-way transient rename + * confusion; See testcases 9c and 9d of t6043. + */ + otherinfo = strmap_get_entry(dir_rename_exclusions, new_dir); + if (otherinfo) { + path_msg(opt, rename_info->key, 1, + _("WARNING: Avoiding applying %s -> %s rename " + "to %s, because %s itself was renamed."), + rename_info->key, new_dir, path, new_dir); + return NULL; + } + + new_path = handle_path_level_conflicts(opt, path, side_index, + rename_info, collisions); + *clean_merge &= (new_path != NULL); + + return new_path; +} + +static void apply_directory_rename_modifications(struct merge_options *opt, + struct diff_filepair *pair, + char *new_path) +{ + /* + * The basic idea is to get the conflict_info from opt->priv->paths + * at old path, and insert it into new_path; basically just this: + * ci = strmap_get(&opt->priv->paths, old_path); + * strmap_remove(&opt->priv->paths, old_path, 0); + * strmap_put(&opt->priv->paths, new_path, ci); + * However, there are some factors complicating this: + * - opt->priv->paths may already have an entry at new_path + * - Each ci tracks its containing directory, so we need to + * update that + * - If another ci has the same containing directory, then + * the two char*'s MUST point to the same location. See the + * comment in struct merged_info. strcmp equality is not + * enough; we need pointer equality. + * - opt->priv->paths must hold the parent directories of any + * entries that are added. So, if this directory rename + * causes entirely new directories, we must recursively add + * parent directories. + * - For each parent directory added to opt->priv->paths, we + * also need to get its parent directory stored in its + * conflict_info->merged.directory_name with all the same + * requirements about pointer equality. + */ + struct string_list dirs_to_insert = STRING_LIST_INIT_NODUP; + struct conflict_info *ci, *new_ci; + struct strmap_entry *entry; + const char *branch_with_new_path, *branch_with_dir_rename; + const char *old_path = pair->two->path; + const char *parent_name; + const char *cur_path; + int i, len; + + entry = strmap_get_entry(&opt->priv->paths, old_path); + old_path = entry->key; + ci = entry->value; + VERIFY_CI(ci); + + /* Find parent directories missing from opt->priv->paths */ + cur_path = new_path; + while (1) { + /* Find the parent directory of cur_path */ + char *last_slash = strrchr(cur_path, '/'); + if (last_slash) { + parent_name = xstrndup(cur_path, last_slash - cur_path); + } else { + parent_name = opt->priv->toplevel_dir; + break; + } + + /* Look it up in opt->priv->paths */ + entry = strmap_get_entry(&opt->priv->paths, parent_name); + if (entry) { + free((char*)parent_name); + parent_name = entry->key; /* reuse known pointer */ + break; + } + + /* Record this is one of the directories we need to insert */ + string_list_append(&dirs_to_insert, parent_name); + cur_path = parent_name; + } + + /* Traverse dirs_to_insert and insert them into opt->priv->paths */ + for (i = dirs_to_insert.nr-1; i >= 0; --i) { + struct conflict_info *dir_ci; + char *cur_dir = dirs_to_insert.items[i].string; + + CALLOC_ARRAY(dir_ci, 1); + + dir_ci->merged.directory_name = parent_name; + len = strlen(parent_name); + /* len+1 because of trailing '/' character */ + dir_ci->merged.basename_offset = (len > 0 ? len+1 : len); + dir_ci->dirmask = ci->filemask; + strmap_put(&opt->priv->paths, cur_dir, dir_ci); + + parent_name = cur_dir; + } + + /* + * We are removing old_path from opt->priv->paths. old_path also will + * eventually need to be freed, but it may still be used by e.g. + * ci->pathnames. So, store it in another string-list for now. + */ + string_list_append(&opt->priv->paths_to_free, old_path); + + assert(ci->filemask == 2 || ci->filemask == 4); + assert(ci->dirmask == 0); + strmap_remove(&opt->priv->paths, old_path, 0); + + branch_with_new_path = (ci->filemask == 2) ? opt->branch1 : opt->branch2; + branch_with_dir_rename = (ci->filemask == 2) ? opt->branch2 : opt->branch1; + + /* Now, finally update ci and stick it into opt->priv->paths */ + ci->merged.directory_name = parent_name; + len = strlen(parent_name); + ci->merged.basename_offset = (len > 0 ? len+1 : len); + new_ci = strmap_get(&opt->priv->paths, new_path); + if (!new_ci) { + /* Place ci back into opt->priv->paths, but at new_path */ + strmap_put(&opt->priv->paths, new_path, ci); + } else { + int index; + + /* A few sanity checks */ + VERIFY_CI(new_ci); + assert(ci->filemask == 2 || ci->filemask == 4); + assert((new_ci->filemask & ci->filemask) == 0); + assert(!new_ci->merged.clean); + + /* Copy stuff from ci into new_ci */ + new_ci->filemask |= ci->filemask; + if (new_ci->dirmask) + new_ci->df_conflict = 1; + index = (ci->filemask >> 1); + new_ci->pathnames[index] = ci->pathnames[index]; + new_ci->stages[index].mode = ci->stages[index].mode; + oidcpy(&new_ci->stages[index].oid, &ci->stages[index].oid); + + free(ci); + ci = new_ci; + } + + if (opt->detect_directory_renames == MERGE_DIRECTORY_RENAMES_TRUE) { + /* Notify user of updated path */ + if (pair->status == 'A') + path_msg(opt, new_path, 1, + _("Path updated: %s added in %s inside a " + "directory that was renamed in %s; moving " + "it to %s."), + old_path, branch_with_new_path, + branch_with_dir_rename, new_path); + else + path_msg(opt, new_path, 1, + _("Path updated: %s renamed to %s in %s, " + "inside a directory that was renamed in %s; " + "moving it to %s."), + pair->one->path, old_path, branch_with_new_path, + branch_with_dir_rename, new_path); + } else { + /* + * opt->detect_directory_renames has the value + * MERGE_DIRECTORY_RENAMES_CONFLICT, so mark these as conflicts. + */ + ci->path_conflict = 1; + if (pair->status == 'A') + path_msg(opt, new_path, 0, + _("CONFLICT (file location): %s added in %s " + "inside a directory that was renamed in %s, " + "suggesting it should perhaps be moved to " + "%s."), + old_path, branch_with_new_path, + branch_with_dir_rename, new_path); + else + path_msg(opt, new_path, 0, + _("CONFLICT (file location): %s renamed to %s " + "in %s, inside a directory that was renamed " + "in %s, suggesting it should perhaps be " + "moved to %s."), + pair->one->path, old_path, branch_with_new_path, + branch_with_dir_rename, new_path); + } + + /* + * Finally, record the new location. + */ + pair->two->path = new_path; +} + /*** Function Grouping: functions related to regular rename detection ***/ +static int process_renames(struct merge_options *opt, + struct diff_queue_struct *renames) +{ + int clean_merge = 1, i; + + for (i = 0; i < renames->nr; ++i) { + const char *oldpath = NULL, *newpath; + struct diff_filepair *pair = renames->queue[i]; + struct conflict_info *oldinfo = NULL, *newinfo = NULL; + struct strmap_entry *old_ent, *new_ent; + unsigned int old_sidemask; + int target_index, other_source_index; + int source_deleted, collision, type_changed; + const char *rename_branch = NULL, *delete_branch = NULL; + + old_ent = strmap_get_entry(&opt->priv->paths, pair->one->path); + new_ent = strmap_get_entry(&opt->priv->paths, pair->two->path); + if (old_ent) { + oldpath = old_ent->key; + oldinfo = old_ent->value; + } + newpath = pair->two->path; + if (new_ent) { + newpath = new_ent->key; + newinfo = new_ent->value; + } + + /* + * If pair->one->path isn't in opt->priv->paths, that means + * that either directory rename detection removed that + * path, or a parent directory of oldpath was resolved and + * we don't even need the rename; in either case, we can + * skip it. If oldinfo->merged.clean, then the other side + * of history had no changes to oldpath and we don't need + * the rename and can skip it. + */ + if (!oldinfo || oldinfo->merged.clean) + continue; + + /* + * diff_filepairs have copies of pathnames, thus we have to + * use standard 'strcmp()' (negated) instead of '=='. + */ + if (i + 1 < renames->nr && + !strcmp(oldpath, renames->queue[i+1]->one->path)) { + /* Handle rename/rename(1to2) or rename/rename(1to1) */ + const char *pathnames[3]; + struct version_info merged; + struct conflict_info *base, *side1, *side2; + unsigned was_binary_blob = 0; + + pathnames[0] = oldpath; + pathnames[1] = newpath; + pathnames[2] = renames->queue[i+1]->two->path; + + base = strmap_get(&opt->priv->paths, pathnames[0]); + side1 = strmap_get(&opt->priv->paths, pathnames[1]); + side2 = strmap_get(&opt->priv->paths, pathnames[2]); + + VERIFY_CI(base); + VERIFY_CI(side1); + VERIFY_CI(side2); + + if (!strcmp(pathnames[1], pathnames[2])) { + /* Both sides renamed the same way */ + assert(side1 == side2); + memcpy(&side1->stages[0], &base->stages[0], + sizeof(merged)); + side1->filemask |= (1 << MERGE_BASE); + /* Mark base as resolved by removal */ + base->merged.is_null = 1; + base->merged.clean = 1; + + /* We handled both renames, i.e. i+1 handled */ + i++; + /* Move to next rename */ + continue; + } + + /* This is a rename/rename(1to2) */ + clean_merge = handle_content_merge(opt, + pair->one->path, + &base->stages[0], + &side1->stages[1], + &side2->stages[2], + pathnames, + 1 + 2 * opt->priv->call_depth, + &merged); + if (!clean_merge && + merged.mode == side1->stages[1].mode && + oideq(&merged.oid, &side1->stages[1].oid)) + was_binary_blob = 1; + memcpy(&side1->stages[1], &merged, sizeof(merged)); + if (was_binary_blob) { + /* + * Getting here means we were attempting to + * merge a binary blob. + * + * Since we can't merge binaries, + * handle_content_merge() just takes one + * side. But we don't want to copy the + * contents of one side to both paths. We + * used the contents of side1 above for + * side1->stages, let's use the contents of + * side2 for side2->stages below. + */ + oidcpy(&merged.oid, &side2->stages[2].oid); + merged.mode = side2->stages[2].mode; + } + memcpy(&side2->stages[2], &merged, sizeof(merged)); + + side1->path_conflict = 1; + side2->path_conflict = 1; + /* + * TODO: For renames we normally remove the path at the + * old name. It would thus seem consistent to do the + * same for rename/rename(1to2) cases, but we haven't + * done so traditionally and a number of the regression + * tests now encode an expectation that the file is + * left there at stage 1. If we ever decide to change + * this, add the following two lines here: + * base->merged.is_null = 1; + * base->merged.clean = 1; + * and remove the setting of base->path_conflict to 1. + */ + base->path_conflict = 1; + path_msg(opt, oldpath, 0, + _("CONFLICT (rename/rename): %s renamed to " + "%s in %s and to %s in %s."), + pathnames[0], + pathnames[1], opt->branch1, + pathnames[2], opt->branch2); + + i++; /* We handled both renames, i.e. i+1 handled */ + continue; + } + + VERIFY_CI(oldinfo); + VERIFY_CI(newinfo); + target_index = pair->score; /* from collect_renames() */ + assert(target_index == 1 || target_index == 2); + other_source_index = 3 - target_index; + old_sidemask = (1 << other_source_index); /* 2 or 4 */ + source_deleted = (oldinfo->filemask == 1); + collision = ((newinfo->filemask & old_sidemask) != 0); + type_changed = !source_deleted && + (S_ISREG(oldinfo->stages[other_source_index].mode) != + S_ISREG(newinfo->stages[target_index].mode)); + if (type_changed && collision) { + /* + * special handling so later blocks can handle this... + * + * if type_changed && collision are both true, then this + * was really a double rename, but one side wasn't + * detected due to lack of break detection. I.e. + * something like + * orig: has normal file 'foo' + * side1: renames 'foo' to 'bar', adds 'foo' symlink + * side2: renames 'foo' to 'bar' + * In this case, the foo->bar rename on side1 won't be + * detected because the new symlink named 'foo' is + * there and we don't do break detection. But we detect + * this here because we don't want to merge the content + * of the foo symlink with the foo->bar file, so we + * have some logic to handle this special case. The + * easiest way to do that is make 'bar' on side1 not + * be considered a colliding file but the other part + * of a normal rename. If the file is very different, + * well we're going to get content merge conflicts + * anyway so it doesn't hurt. And if the colliding + * file also has a different type, that'll be handled + * by the content merge logic in process_entry() too. + * + * See also t6430, 'rename vs. rename/symlink' + */ + collision = 0; + } + if (source_deleted) { + if (target_index == 1) { + rename_branch = opt->branch1; + delete_branch = opt->branch2; + } else { + rename_branch = opt->branch2; + delete_branch = opt->branch1; + } + } + + assert(source_deleted || oldinfo->filemask & old_sidemask); + + /* Need to check for special types of rename conflicts... */ + if (collision && !source_deleted) { + /* collision: rename/add or rename/rename(2to1) */ + const char *pathnames[3]; + struct version_info merged; + + struct conflict_info *base, *side1, *side2; + unsigned clean; + + pathnames[0] = oldpath; + pathnames[other_source_index] = oldpath; + pathnames[target_index] = newpath; + + base = strmap_get(&opt->priv->paths, pathnames[0]); + side1 = strmap_get(&opt->priv->paths, pathnames[1]); + side2 = strmap_get(&opt->priv->paths, pathnames[2]); + + VERIFY_CI(base); + VERIFY_CI(side1); + VERIFY_CI(side2); + + clean = handle_content_merge(opt, pair->one->path, + &base->stages[0], + &side1->stages[1], + &side2->stages[2], + pathnames, + 1 + 2 * opt->priv->call_depth, + &merged); + + memcpy(&newinfo->stages[target_index], &merged, + sizeof(merged)); + if (!clean) { + path_msg(opt, newpath, 0, + _("CONFLICT (rename involved in " + "collision): rename of %s -> %s has " + "content conflicts AND collides " + "with another path; this may result " + "in nested conflict markers."), + oldpath, newpath); + } + } else if (collision && source_deleted) { + /* + * rename/add/delete or rename/rename(2to1)/delete: + * since oldpath was deleted on the side that didn't + * do the rename, there's not much of a content merge + * we can do for the rename. oldinfo->merged.is_null + * was already set, so we just leave things as-is so + * they look like an add/add conflict. + */ + + newinfo->path_conflict = 1; + path_msg(opt, newpath, 0, + _("CONFLICT (rename/delete): %s renamed " + "to %s in %s, but deleted in %s."), + oldpath, newpath, rename_branch, delete_branch); + } else { + /* + * a few different cases...start by copying the + * existing stage(s) from oldinfo over the newinfo + * and update the pathname(s). + */ + memcpy(&newinfo->stages[0], &oldinfo->stages[0], + sizeof(newinfo->stages[0])); + newinfo->filemask |= (1 << MERGE_BASE); + newinfo->pathnames[0] = oldpath; + if (type_changed) { + /* rename vs. typechange */ + /* Mark the original as resolved by removal */ + memcpy(&oldinfo->stages[0].oid, &null_oid, + sizeof(oldinfo->stages[0].oid)); + oldinfo->stages[0].mode = 0; + oldinfo->filemask &= 0x06; + } else if (source_deleted) { + /* rename/delete */ + newinfo->path_conflict = 1; + path_msg(opt, newpath, 0, + _("CONFLICT (rename/delete): %s renamed" + " to %s in %s, but deleted in %s."), + oldpath, newpath, + rename_branch, delete_branch); + } else { + /* normal rename */ + memcpy(&newinfo->stages[other_source_index], + &oldinfo->stages[other_source_index], + sizeof(newinfo->stages[0])); + newinfo->filemask |= (1 << other_source_index); + newinfo->pathnames[other_source_index] = oldpath; + } + } + + if (!type_changed) { + /* Mark the original as resolved by removal */ + oldinfo->merged.is_null = 1; + oldinfo->merged.clean = 1; + } + + } + + return clean_merge; +} + +static void resolve_diffpair_statuses(struct diff_queue_struct *q) +{ + /* + * A simplified version of diff_resolve_rename_copy(); would probably + * just use that function but it's static... + */ + int i; + struct diff_filepair *p; + + for (i = 0; i < q->nr; ++i) { + p = q->queue[i]; + p->status = 0; /* undecided */ + if (!DIFF_FILE_VALID(p->one)) + p->status = DIFF_STATUS_ADDED; + else if (!DIFF_FILE_VALID(p->two)) + p->status = DIFF_STATUS_DELETED; + else if (DIFF_PAIR_RENAME(p)) + p->status = DIFF_STATUS_RENAMED; + } +} + +static int compare_pairs(const void *a_, const void *b_) +{ + const struct diff_filepair *a = *((const struct diff_filepair **)a_); + const struct diff_filepair *b = *((const struct diff_filepair **)b_); + + return strcmp(a->one->path, b->one->path); +} + +/* Call diffcore_rename() to compute which files have changed on given side */ +static void detect_regular_renames(struct merge_options *opt, + unsigned side_index) +{ + struct diff_options diff_opts; + struct rename_info *renames = &opt->priv->renames; + + repo_diff_setup(opt->repo, &diff_opts); + diff_opts.flags.recursive = 1; + diff_opts.flags.rename_empty = 0; + diff_opts.detect_rename = DIFF_DETECT_RENAME; + diff_opts.rename_limit = opt->rename_limit; + if (opt->rename_limit <= 0) + diff_opts.rename_limit = 1000; + diff_opts.rename_score = opt->rename_score; + diff_opts.show_rename_progress = opt->show_rename_progress; + diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; + diff_setup_done(&diff_opts); + + diff_queued_diff = renames->pairs[side_index]; + trace2_region_enter("diff", "diffcore_rename", opt->repo); + diffcore_rename_extended(&diff_opts, + &renames->dirs_removed[side_index], + &renames->dir_rename_count[side_index]); + trace2_region_leave("diff", "diffcore_rename", opt->repo); + resolve_diffpair_statuses(&diff_queued_diff); + + if (diff_opts.needed_rename_limit > renames->needed_limit) + renames->needed_limit = diff_opts.needed_rename_limit; + + renames->pairs[side_index] = diff_queued_diff; + + diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; + diff_queued_diff.nr = 0; + diff_queued_diff.queue = NULL; + diff_flush(&diff_opts); +} + +/* + * Get information of all renames which occurred in 'side_pairs', discarding + * non-renames. + */ +static int collect_renames(struct merge_options *opt, + struct diff_queue_struct *result, + unsigned side_index, + struct strmap *dir_renames_for_side, + struct strmap *rename_exclusions) +{ + int i, clean = 1; + struct strmap collisions; + struct diff_queue_struct *side_pairs; + struct hashmap_iter iter; + struct strmap_entry *entry; + struct rename_info *renames = &opt->priv->renames; + + side_pairs = &renames->pairs[side_index]; + compute_collisions(&collisions, dir_renames_for_side, side_pairs); + + for (i = 0; i < side_pairs->nr; ++i) { + struct diff_filepair *p = side_pairs->queue[i]; + char *new_path; /* non-NULL only with directory renames */ + + if (p->status != 'A' && p->status != 'R') { + diff_free_filepair(p); + continue; + } + + new_path = check_for_directory_rename(opt, p->two->path, + side_index, + dir_renames_for_side, + rename_exclusions, + &collisions, + &clean); + + if (p->status != 'R' && !new_path) { + diff_free_filepair(p); + continue; + } + + if (new_path) + apply_directory_rename_modifications(opt, p, new_path); + + /* + * p->score comes back from diffcore_rename_extended() with + * the similarity of the renamed file. The similarity is + * was used to determine that the two files were related + * and are a rename, which we have already used, but beyond + * that we have no use for the similarity. So p->score is + * now irrelevant. However, process_renames() will need to + * know which side of the merge this rename was associated + * with, so overwrite p->score with that value. + */ + p->score = side_index; + result->queue[result->nr++] = p; + } + + /* Free each value in the collisions map */ + strmap_for_each_entry(&collisions, &iter, entry) { + struct collision_info *info = entry->value; + string_list_clear(&info->source_files, 0); + } + /* + * In compute_collisions(), we set collisions.strdup_strings to 0 + * so that we wouldn't have to make another copy of the new_path + * allocated by apply_dir_rename(). But now that we've used them + * and have no other references to these strings, it is time to + * deallocate them. + */ + free_strmap_strings(&collisions); + strmap_clear(&collisions, 1); + return clean; +} + static int detect_and_process_renames(struct merge_options *opt, struct tree *merge_base, struct tree *side1, struct tree *side2) { - int clean = 1; + struct diff_queue_struct combined; + struct rename_info *renames = &opt->priv->renames; + int need_dir_renames, s, clean = 1; + + memset(&combined, 0, sizeof(combined)); + + trace2_region_enter("merge", "regular renames", opt->repo); + detect_regular_renames(opt, MERGE_SIDE1); + detect_regular_renames(opt, MERGE_SIDE2); + trace2_region_leave("merge", "regular renames", opt->repo); + + trace2_region_enter("merge", "directory renames", opt->repo); + need_dir_renames = + !opt->priv->call_depth && + (opt->detect_directory_renames == MERGE_DIRECTORY_RENAMES_TRUE || + opt->detect_directory_renames == MERGE_DIRECTORY_RENAMES_CONFLICT); + + if (need_dir_renames) { + get_provisional_directory_renames(opt, MERGE_SIDE1, &clean); + get_provisional_directory_renames(opt, MERGE_SIDE2, &clean); + handle_directory_level_conflicts(opt); + } + + ALLOC_GROW(combined.queue, + renames->pairs[1].nr + renames->pairs[2].nr, + combined.alloc); + clean &= collect_renames(opt, &combined, MERGE_SIDE1, + &renames->dir_renames[2], + &renames->dir_renames[1]); + clean &= collect_renames(opt, &combined, MERGE_SIDE2, + &renames->dir_renames[1], + &renames->dir_renames[2]); + QSORT(combined.queue, combined.nr, compare_pairs); + trace2_region_leave("merge", "directory renames", opt->repo); + + trace2_region_enter("merge", "process renames", opt->repo); + clean &= process_renames(opt, &combined); + trace2_region_leave("merge", "process renames", opt->repo); + + /* Free memory for renames->pairs[] and combined */ + for (s = MERGE_SIDE1; s <= MERGE_SIDE2; s++) { + free(renames->pairs[s].queue); + DIFF_QUEUE_CLEAR(&renames->pairs[s]); + } + if (combined.nr) { + int i; + for (i = 0; i < combined.nr; i++) + diff_free_filepair(combined.queue[i]); + free(combined.queue); + } - /* - * Rename detection works by detecting file similarity. Here we use - * a really easy-to-implement scheme: files are similar IFF they have - * the same filename. Therefore, by this scheme, there are no renames. - * - * TODO: Actually implement a real rename detection scheme. - */ return clean; } @@ -965,6 +2503,8 @@ static void process_entry(struct merge_options *opt, struct conflict_info *ci, struct directory_versions *dir_metadata) { + int df_file_index = 0; + VERIFY_CI(ci); assert(ci->filemask >= 0 && ci->filemask <= 7); /* ci->match_mask == 7 was handled in collect_merge_info_callback() */ @@ -979,14 +2519,108 @@ static void process_entry(struct merge_options *opt, assert(ci->df_conflict); } - if (ci->df_conflict) { - die("Not yet implemented."); + if (ci->df_conflict && ci->merged.result.mode == 0) { + int i; + + /* + * directory no longer in the way, but we do have a file we + * need to place here so we need to clean away the "directory + * merges to nothing" result. + */ + ci->df_conflict = 0; + assert(ci->filemask != 0); + ci->merged.clean = 0; + ci->merged.is_null = 0; + /* and we want to zero out any directory-related entries */ + ci->match_mask = (ci->match_mask & ~ci->dirmask); + ci->dirmask = 0; + for (i = MERGE_BASE; i <= MERGE_SIDE2; i++) { + if (ci->filemask & (1 << i)) + continue; + ci->stages[i].mode = 0; + oidcpy(&ci->stages[i].oid, &null_oid); + } + } else if (ci->df_conflict && ci->merged.result.mode != 0) { + /* + * This started out as a D/F conflict, and the entries in + * the competing directory were not removed by the merge as + * evidenced by write_completed_directory() writing a value + * to ci->merged.result.mode. + */ + struct conflict_info *new_ci; + const char *branch; + const char *old_path = path; + int i; + + assert(ci->merged.result.mode == S_IFDIR); + + /* + * If filemask is 1, we can just ignore the file as having + * been deleted on both sides. We do not want to overwrite + * ci->merged.result, since it stores the tree for all the + * files under it. + */ + if (ci->filemask == 1) { + ci->filemask = 0; + return; + } + + /* + * This file still exists on at least one side, and we want + * the directory to remain here, so we need to move this + * path to some new location. + */ + CALLOC_ARRAY(new_ci, 1); + /* We don't really want new_ci->merged.result copied, but it'll + * be overwritten below so it doesn't matter. We also don't + * want any directory mode/oid values copied, but we'll zero + * those out immediately. We do want the rest of ci copied. + */ + memcpy(new_ci, ci, sizeof(*ci)); + new_ci->match_mask = (new_ci->match_mask & ~new_ci->dirmask); + new_ci->dirmask = 0; + for (i = MERGE_BASE; i <= MERGE_SIDE2; i++) { + if (new_ci->filemask & (1 << i)) + continue; + /* zero out any entries related to directories */ + new_ci->stages[i].mode = 0; + oidcpy(&new_ci->stages[i].oid, &null_oid); + } + + /* + * Find out which side this file came from; note that we + * cannot just use ci->filemask, because renames could cause + * the filemask to go back to 7. So we use dirmask, then + * pick the opposite side's index. + */ + df_file_index = (ci->dirmask & (1 << 1)) ? 2 : 1; + branch = (df_file_index == 1) ? opt->branch1 : opt->branch2; + path = unique_path(&opt->priv->paths, path, branch); + strmap_put(&opt->priv->paths, path, new_ci); + + path_msg(opt, path, 0, + _("CONFLICT (file/directory): directory in the way " + "of %s from %s; moving it to %s instead."), + old_path, branch, path); + + /* + * Zero out the filemask for the old ci. At this point, ci + * was just an entry for a directory, so we don't need to + * do anything more with it. + */ + ci->filemask = 0; + + /* + * Now note that we're working on the new entry (path was + * updated above. + */ + ci = new_ci; } /* * NOTE: Below there is a long switch-like if-elseif-elseif... block * which the code goes through even for the df_conflict cases - * above. Well, it will once we don't die-not-implemented above. + * above. */ if (ci->match_mask) { ci->merged.clean = 1; @@ -1010,21 +2644,142 @@ static void process_entry(struct merge_options *opt, } else if (ci->filemask >= 6 && (S_IFMT & ci->stages[1].mode) != (S_IFMT & ci->stages[2].mode)) { - /* - * Two different items from (file/submodule/symlink) - */ - die("Not yet implemented."); + /* Two different items from (file/submodule/symlink) */ + if (opt->priv->call_depth) { + /* Just use the version from the merge base */ + ci->merged.clean = 0; + oidcpy(&ci->merged.result.oid, &ci->stages[0].oid); + ci->merged.result.mode = ci->stages[0].mode; + ci->merged.is_null = (ci->merged.result.mode == 0); + } else { + /* Handle by renaming one or both to separate paths. */ + unsigned o_mode = ci->stages[0].mode; + unsigned a_mode = ci->stages[1].mode; + unsigned b_mode = ci->stages[2].mode; + struct conflict_info *new_ci; + const char *a_path = NULL, *b_path = NULL; + int rename_a = 0, rename_b = 0; + + new_ci = xmalloc(sizeof(*new_ci)); + + if (S_ISREG(a_mode)) + rename_a = 1; + else if (S_ISREG(b_mode)) + rename_b = 1; + else { + rename_a = 1; + rename_b = 1; + } + + path_msg(opt, path, 0, + _("CONFLICT (distinct types): %s had different " + "types on each side; renamed %s of them so " + "each can be recorded somewhere."), + path, + (rename_a && rename_b) ? _("both") : _("one")); + + ci->merged.clean = 0; + memcpy(new_ci, ci, sizeof(*new_ci)); + + /* Put b into new_ci, removing a from stages */ + new_ci->merged.result.mode = ci->stages[2].mode; + oidcpy(&new_ci->merged.result.oid, &ci->stages[2].oid); + new_ci->stages[1].mode = 0; + oidcpy(&new_ci->stages[1].oid, &null_oid); + new_ci->filemask = 5; + if ((S_IFMT & b_mode) != (S_IFMT & o_mode)) { + new_ci->stages[0].mode = 0; + oidcpy(&new_ci->stages[0].oid, &null_oid); + new_ci->filemask = 4; + } + + /* Leave only a in ci, fixing stages. */ + ci->merged.result.mode = ci->stages[1].mode; + oidcpy(&ci->merged.result.oid, &ci->stages[1].oid); + ci->stages[2].mode = 0; + oidcpy(&ci->stages[2].oid, &null_oid); + ci->filemask = 3; + if ((S_IFMT & a_mode) != (S_IFMT & o_mode)) { + ci->stages[0].mode = 0; + oidcpy(&ci->stages[0].oid, &null_oid); + ci->filemask = 2; + } + + /* Insert entries into opt->priv_paths */ + assert(rename_a || rename_b); + if (rename_a) { + a_path = unique_path(&opt->priv->paths, + path, opt->branch1); + strmap_put(&opt->priv->paths, a_path, ci); + } + + if (rename_b) + b_path = unique_path(&opt->priv->paths, + path, opt->branch2); + else + b_path = path; + strmap_put(&opt->priv->paths, b_path, new_ci); + + if (rename_a && rename_b) { + strmap_remove(&opt->priv->paths, path, 0); + /* + * We removed path from opt->priv->paths. path + * will also eventually need to be freed, but + * it may still be used by e.g. ci->pathnames. + * So, store it in another string-list for now. + */ + string_list_append(&opt->priv->paths_to_free, + path); + } + + /* + * Do special handling for b_path since process_entry() + * won't be called on it specially. + */ + strmap_put(&opt->priv->conflicted, b_path, new_ci); + record_entry_for_tree(dir_metadata, b_path, + &new_ci->merged); + + /* + * Remaining code for processing this entry should + * think in terms of processing a_path. + */ + if (a_path) + path = a_path; + } } else if (ci->filemask >= 6) { - /* - * TODO: Needs a two-way or three-way content merge, but we're - * just being lazy and copying the version from HEAD and - * leaving it as conflicted. - */ - ci->merged.clean = 0; - ci->merged.result.mode = ci->stages[1].mode; - oidcpy(&ci->merged.result.oid, &ci->stages[1].oid); - /* When we fix above, we'll call handle_content_merge() */ - (void)handle_content_merge; + /* Need a two-way or three-way content merge */ + struct version_info merged_file; + unsigned clean_merge; + struct version_info *o = &ci->stages[0]; + struct version_info *a = &ci->stages[1]; + struct version_info *b = &ci->stages[2]; + + clean_merge = handle_content_merge(opt, path, o, a, b, + ci->pathnames, + opt->priv->call_depth * 2, + &merged_file); + ci->merged.clean = clean_merge && + !ci->df_conflict && !ci->path_conflict; + ci->merged.result.mode = merged_file.mode; + ci->merged.is_null = (merged_file.mode == 0); + oidcpy(&ci->merged.result.oid, &merged_file.oid); + if (clean_merge && ci->df_conflict) { + assert(df_file_index == 1 || df_file_index == 2); + ci->filemask = 1 << df_file_index; + ci->stages[df_file_index].mode = merged_file.mode; + oidcpy(&ci->stages[df_file_index].oid, &merged_file.oid); + } + if (!clean_merge) { + const char *reason = _("content"); + if (ci->filemask == 6) + reason = _("add/add"); + if (S_ISGITLINK(merged_file.mode)) + reason = _("submodule"); + path_msg(opt, path, 0, + _("CONFLICT (%s): Merge conflict in %s"), + reason, path); + } } else if (ci->filemask == 3 || ci->filemask == 5) { /* Modify/delete */ const char *modify_branch, *delete_branch; @@ -1038,24 +2793,33 @@ static void process_entry(struct merge_options *opt, modify_branch = (side == 1) ? opt->branch1 : opt->branch2; delete_branch = (side == 1) ? opt->branch2 : opt->branch1; - path_msg(opt, path, 0, - _("CONFLICT (modify/delete): %s deleted in %s " - "and modified in %s. Version %s of %s left " - "in tree."), - path, delete_branch, modify_branch, - modify_branch, path); + if (ci->path_conflict && + oideq(&ci->stages[0].oid, &ci->stages[side].oid)) { + /* + * This came from a rename/delete; no action to take, + * but avoid printing "modify/delete" conflict notice + * since the contents were not modified. + */ + } else { + path_msg(opt, path, 0, + _("CONFLICT (modify/delete): %s deleted in %s " + "and modified in %s. Version %s of %s left " + "in tree."), + path, delete_branch, modify_branch, + modify_branch, path); + } } else if (ci->filemask == 2 || ci->filemask == 4) { /* Added on one side */ int side = (ci->filemask == 4) ? 2 : 1; ci->merged.result.mode = ci->stages[side].mode; oidcpy(&ci->merged.result.oid, &ci->stages[side].oid); - ci->merged.clean = !ci->df_conflict; + ci->merged.clean = !ci->df_conflict && !ci->path_conflict; } else if (ci->filemask == 1) { /* Deleted on both sides */ ci->merged.is_null = 1; ci->merged.result.mode = 0; oidcpy(&ci->merged.result.oid, &null_oid); - ci->merged.clean = 1; + ci->merged.clean = !ci->path_conflict; } /* @@ -1079,20 +2843,30 @@ static void process_entries(struct merge_options *opt, STRING_LIST_INIT_NODUP, NULL, 0 }; + trace2_region_enter("merge", "process_entries setup", opt->repo); if (strmap_empty(&opt->priv->paths)) { oidcpy(result_oid, opt->repo->hash_algo->empty_tree); return; } /* Hack to pre-allocate plist to the desired size */ + trace2_region_enter("merge", "plist grow", opt->repo); ALLOC_GROW(plist.items, strmap_get_size(&opt->priv->paths), plist.alloc); + trace2_region_leave("merge", "plist grow", opt->repo); /* Put every entry from paths into plist, then sort */ + trace2_region_enter("merge", "plist copy", opt->repo); strmap_for_each_entry(&opt->priv->paths, &iter, e) { string_list_append(&plist, e->key)->util = e->value; } + trace2_region_leave("merge", "plist copy", opt->repo); + + trace2_region_enter("merge", "plist special sort", opt->repo); plist.cmp = string_list_df_name_compare; string_list_sort(&plist); + trace2_region_leave("merge", "plist special sort", opt->repo); + + trace2_region_leave("merge", "process_entries setup", opt->repo); /* * Iterate over the items in reverse order, so we can handle paths @@ -1103,6 +2877,7 @@ static void process_entries(struct merge_options *opt, * (because it allows us to know whether the directory is still in * the way when it is time to process the file at the same path). */ + trace2_region_enter("merge", "processing", opt->repo); for (entry = &plist.items[plist.nr-1]; entry >= plist.items; --entry) { char *path = entry->string; /* @@ -1121,7 +2896,9 @@ static void process_entries(struct merge_options *opt, process_entry(opt, path, ci, &dir_metadata); } } + trace2_region_leave("merge", "processing", opt->repo); + trace2_region_enter("merge", "process_entries cleanup", opt->repo); if (dir_metadata.offsets.nr != 1 || (uintptr_t)dir_metadata.offsets.items[0].util != 0) { printf("dir_metadata.offsets.nr = %d (should be 1)\n", @@ -1136,6 +2913,7 @@ static void process_entries(struct merge_options *opt, string_list_clear(&plist, 0); string_list_clear(&dir_metadata.versions, 0); string_list_clear(&dir_metadata.offsets, 0); + trace2_region_leave("merge", "process_entries cleanup", opt->repo); } /*** Function Grouping: functions related to merge_switch_to_result() ***/ @@ -1172,7 +2950,7 @@ static int checkout(struct merge_options *opt, unpack_opts.verbose_update = (opt->verbosity > 2); unpack_opts.fn = twoway_merge; if (1/* FIXME: opts->overwrite_ignore*/) { - unpack_opts.dir = xcalloc(1, sizeof(*unpack_opts.dir)); + CALLOC_ARRAY(unpack_opts.dir, 1); unpack_opts.dir->flags |= DIR_SHOW_IGNORED; setup_standard_excludes(unpack_opts.dir); } @@ -1294,12 +3072,15 @@ void merge_switch_to_result(struct merge_options *opt, if (result->clean >= 0 && update_worktree_and_index) { struct merge_options_internal *opti = result->priv; + trace2_region_enter("merge", "checkout", opt->repo); if (checkout(opt, head, result->tree)) { /* failure to function */ result->clean = -1; return; } + trace2_region_leave("merge", "checkout", opt->repo); + trace2_region_enter("merge", "record_conflicted", opt->repo); if (record_conflicted_index_entries(opt, opt->repo->index, &opti->paths, &opti->conflicted)) { @@ -1307,6 +3088,7 @@ void merge_switch_to_result(struct merge_options *opt, result->clean = -1; return; } + trace2_region_leave("merge", "record_conflicted", opt->repo); } if (display_update_msgs) { @@ -1316,6 +3098,8 @@ void merge_switch_to_result(struct merge_options *opt, struct string_list olist = STRING_LIST_INIT_NODUP; int i; + trace2_region_enter("merge", "display messages", opt->repo); + /* Hack to pre-allocate olist to the desired size */ ALLOC_GROW(olist.items, strmap_get_size(&opti->output), olist.alloc); @@ -1333,6 +3117,12 @@ void merge_switch_to_result(struct merge_options *opt, printf("%s", sb->buf); } string_list_clear(&olist, 0); + + /* Also include needed rename limit adjustment now */ + diff_warn_rename_limit("merge.renamelimit", + opti->renames.needed_limit, 0); + + trace2_region_leave("merge", "display messages", opt->repo); } merge_finalize(opt, result); @@ -1370,7 +3160,11 @@ static struct commit *make_virtual_commit(struct repository *repo, static void merge_start(struct merge_options *opt, struct merge_result *result) { + struct rename_info *renames; + int i; + /* Sanity checks on opt */ + trace2_region_enter("merge", "sanity checks", opt->repo); assert(opt->repo); assert(opt->branch1 && opt->branch2); @@ -1397,13 +3191,43 @@ static void merge_start(struct merge_options *opt, struct merge_result *result) assert(opt->obuf.len == 0); assert(opt->priv == NULL); + if (result->priv) { + opt->priv = result->priv; + result->priv = NULL; + /* + * opt->priv non-NULL means we had results from a previous + * run; do a few sanity checks that user didn't mess with + * it in an obvious fashion. + */ + assert(opt->priv->call_depth == 0); + assert(!opt->priv->toplevel_dir || + 0 == strlen(opt->priv->toplevel_dir)); + } + trace2_region_leave("merge", "sanity checks", opt->repo); /* Default to histogram diff. Actually, just hardcode it...for now. */ opt->xdl_opts = DIFF_WITH_ALG(opt, HISTOGRAM_DIFF); /* Initialization of opt->priv, our internal merge data */ + trace2_region_enter("merge", "allocate/init", opt->repo); + if (opt->priv) { + clear_or_reinit_internal_opts(opt->priv, 1); + trace2_region_leave("merge", "allocate/init", opt->repo); + return; + } opt->priv = xcalloc(1, sizeof(*opt->priv)); + /* Initialization of various renames fields */ + renames = &opt->priv->renames; + for (i = MERGE_SIDE1; i <= MERGE_SIDE2; i++) { + strset_init_with_options(&renames->dirs_removed[i], + NULL, 0); + strmap_init_with_options(&renames->dir_rename_count[i], + NULL, 1); + strmap_init_with_options(&renames->dir_renames[i], + NULL, 0); + } + /* * Although we initialize opt->priv->paths with strdup_strings=0, * that's just to avoid making yet another copy of an allocated @@ -1423,6 +3247,8 @@ static void merge_start(struct merge_options *opt, struct merge_result *result) * subset of the overall paths that have special output. */ strmap_init(&opt->priv->output); + + trace2_region_leave("merge", "allocate/init", opt->repo); } /*** Function Grouping: merge_incore_*() and their internal variants ***/ @@ -1438,6 +3264,7 @@ static void merge_ort_nonrecursive_internal(struct merge_options *opt, { struct object_id working_tree_oid; + trace2_region_enter("merge", "collect_merge_info", opt->repo); if (collect_merge_info(opt, merge_base, side1, side2) != 0) { /* * TRANSLATORS: The %s arguments are: 1) tree hash of a merge @@ -1450,10 +3277,16 @@ static void merge_ort_nonrecursive_internal(struct merge_options *opt, result->clean = -1; return; } + trace2_region_leave("merge", "collect_merge_info", opt->repo); + trace2_region_enter("merge", "renames", opt->repo); result->clean = detect_and_process_renames(opt, merge_base, side1, side2); + trace2_region_leave("merge", "renames", opt->repo); + + trace2_region_enter("merge", "process_entries", opt->repo); process_entries(opt, &working_tree_oid); + trace2_region_leave("merge", "process_entries", opt->repo); /* Set return values */ result->tree = parse_tree_indirect(&working_tree_oid); @@ -1554,9 +3387,15 @@ void merge_incore_nonrecursive(struct merge_options *opt, struct tree *side2, struct merge_result *result) { + trace2_region_enter("merge", "incore_nonrecursive", opt->repo); + + trace2_region_enter("merge", "merge_start", opt->repo); assert(opt->ancestor != NULL); merge_start(opt, result); + trace2_region_leave("merge", "merge_start", opt->repo); + merge_ort_nonrecursive_internal(opt, merge_base, side1, side2, result); + trace2_region_leave("merge", "incore_nonrecursive", opt->repo); } void merge_incore_recursive(struct merge_options *opt, @@ -1565,9 +3404,15 @@ void merge_incore_recursive(struct merge_options *opt, struct commit *side2, struct merge_result *result) { + trace2_region_enter("merge", "incore_recursive", opt->repo); + /* We set the ancestor label based on the merge_bases */ assert(opt->ancestor == NULL); + trace2_region_enter("merge", "merge_start", opt->repo); merge_start(opt, result); + trace2_region_leave("merge", "merge_start", opt->repo); + merge_ort_internal(opt, merge_bases, side1, side2, result); + trace2_region_leave("merge", "incore_recursive", opt->repo); } |