diff options
Diffstat (limited to 'revision.c')
| -rw-r--r-- | revision.c | 3108 |
1 files changed, 2392 insertions, 716 deletions
diff --git a/revision.c b/revision.c index 59b26c7e99..cddd0542a6 100644 --- a/revision.c +++ b/revision.c @@ -1,11 +1,14 @@ #include "cache.h" +#include "object-store.h" #include "tag.h" #include "blob.h" #include "tree.h" #include "commit.h" #include "diff.h" +#include "diff-merges.h" #include "refs.h" #include "revision.h" +#include "repository.h" #include "graph.h" #include "grep.h" #include "reflog-walk.h" @@ -13,82 +16,42 @@ #include "decorate.h" #include "log-tree.h" #include "string-list.h" +#include "line-log.h" +#include "mailmap.h" +#include "commit-slab.h" +#include "dir.h" +#include "cache-tree.h" +#include "bisect.h" +#include "packfile.h" +#include "worktree.h" +#include "strvec.h" +#include "commit-reach.h" +#include "commit-graph.h" +#include "prio-queue.h" +#include "hashmap.h" +#include "utf8.h" +#include "bloom.h" +#include "json-writer.h" volatile show_early_output_fn_t show_early_output; -char *path_name(const struct name_path *path, const char *name) -{ - const struct name_path *p; - char *n, *m; - int nlen = strlen(name); - int len = nlen + 1; - - for (p = path; p; p = p->up) { - if (p->elem_len) - len += p->elem_len + 1; - } - n = xmalloc(len); - m = n + len - (nlen + 1); - strcpy(m, name); - for (p = path; p; p = p->up) { - if (p->elem_len) { - m -= p->elem_len + 1; - memcpy(m, p->elem, p->elem_len); - m[p->elem_len] = '/'; - } - } - return n; -} +static const char *term_bad; +static const char *term_good; -static int show_path_component_truncated(FILE *out, const char *name, int len) -{ - int cnt; - for (cnt = 0; cnt < len; cnt++) { - int ch = name[cnt]; - if (!ch || ch == '\n') - return -1; - fputc(ch, out); - } - return len; -} +implement_shared_commit_slab(revision_sources, char *); + +static inline int want_ancestry(const struct rev_info *revs); -static int show_path_truncated(FILE *out, const struct name_path *path) +void show_object_with_name(FILE *out, struct object *obj, const char *name) { - int emitted, ours; + const char *p; - if (!path) - return 0; - emitted = show_path_truncated(out, path->up); - if (emitted < 0) - return emitted; - if (emitted) - fputc('/', out); - ours = show_path_component_truncated(out, path->elem, path->elem_len); - if (ours < 0) - return ours; - return ours || emitted; -} - -void show_object_with_name(FILE *out, struct object *obj, const struct name_path *path, const char *component) -{ - struct name_path leaf; - leaf.up = (struct name_path *)path; - leaf.elem = component; - leaf.elem_len = strlen(component); - - fprintf(out, "%s ", sha1_to_hex(obj->sha1)); - show_path_truncated(out, &leaf); + fprintf(out, "%s ", oid_to_hex(&obj->oid)); + for (p = name; *p && *p != '\n'; p++) + fputc(*p, out); fputc('\n', out); } -void add_object(struct object *obj, - struct object_array *p, - struct name_path *path, - const char *name) -{ - add_object_array(obj, path_name(path, name), p); -} - static void mark_blob_uninteresting(struct blob *blob) { if (!blob) @@ -98,30 +61,23 @@ static void mark_blob_uninteresting(struct blob *blob) blob->object.flags |= UNINTERESTING; } -void mark_tree_uninteresting(struct tree *tree) +static void mark_tree_contents_uninteresting(struct repository *r, + struct tree *tree) { struct tree_desc desc; struct name_entry entry; - struct object *obj = &tree->object; - if (!tree) + if (parse_tree_gently(tree, 1) < 0) return; - if (obj->flags & UNINTERESTING) - return; - obj->flags |= UNINTERESTING; - if (!has_sha1_file(obj->sha1)) - return; - if (parse_tree(tree) < 0) - die("bad tree %s", sha1_to_hex(obj->sha1)); init_tree_desc(&desc, tree->buffer, tree->size); while (tree_entry(&desc, &entry)) { switch (object_type(entry.mode)) { case OBJ_TREE: - mark_tree_uninteresting(lookup_tree(entry.sha1)); + mark_tree_uninteresting(r, lookup_tree(r, &entry.oid)); break; case OBJ_BLOB: - mark_blob_uninteresting(lookup_blob(entry.sha1)); + mark_blob_uninteresting(lookup_blob(r, &entry.oid)); break; default: /* Subproject commit - not in this repository */ @@ -133,121 +89,317 @@ void mark_tree_uninteresting(struct tree *tree) * We don't care about the tree any more * after it has been marked uninteresting. */ - free(tree->buffer); - tree->buffer = NULL; + free_tree_buffer(tree); } -void mark_parents_uninteresting(struct commit *commit) +void mark_tree_uninteresting(struct repository *r, struct tree *tree) { - struct commit_list *parents = NULL, *l; + struct object *obj; - for (l = commit->parents; l; l = l->next) - commit_list_insert(l->item, &parents); + if (!tree) + return; - while (parents) { - struct commit *commit = parents->item; - l = parents; - parents = parents->next; - free(l); + obj = &tree->object; + if (obj->flags & UNINTERESTING) + return; + obj->flags |= UNINTERESTING; + mark_tree_contents_uninteresting(r, tree); +} - while (commit) { - /* - * A missing commit is ok iff its parent is marked - * uninteresting. - * - * We just mark such a thing parsed, so that when - * it is popped next time around, we won't be trying - * to parse it and get an error. - */ - if (!has_sha1_file(commit->object.sha1)) - commit->object.parsed = 1; +struct path_and_oids_entry { + struct hashmap_entry ent; + char *path; + struct oidset trees; +}; - if (commit->object.flags & UNINTERESTING) - break; +static int path_and_oids_cmp(const void *hashmap_cmp_fn_data, + const struct hashmap_entry *eptr, + const struct hashmap_entry *entry_or_key, + const void *keydata) +{ + const struct path_and_oids_entry *e1, *e2; - commit->object.flags |= UNINTERESTING; + e1 = container_of(eptr, const struct path_and_oids_entry, ent); + e2 = container_of(entry_or_key, const struct path_and_oids_entry, ent); - /* - * Normally we haven't parsed the parent - * yet, so we won't have a parent of a parent - * here. However, it may turn out that we've - * reached this commit some other way (where it - * wasn't uninteresting), in which case we need - * to mark its parents recursively too.. - */ - if (!commit->parents) - break; + return strcmp(e1->path, e2->path); +} + +static void paths_and_oids_clear(struct hashmap *map) +{ + struct hashmap_iter iter; + struct path_and_oids_entry *entry; + + hashmap_for_each_entry(map, &iter, entry, ent /* member name */) { + oidset_clear(&entry->trees); + free(entry->path); + } + + hashmap_clear_and_free(map, struct path_and_oids_entry, ent); +} + +static void paths_and_oids_insert(struct hashmap *map, + const char *path, + const struct object_id *oid) +{ + int hash = strhash(path); + struct path_and_oids_entry key; + struct path_and_oids_entry *entry; + + hashmap_entry_init(&key.ent, hash); + + /* use a shallow copy for the lookup */ + key.path = (char *)path; + oidset_init(&key.trees, 0); + + entry = hashmap_get_entry(map, &key, ent, NULL); + if (!entry) { + CALLOC_ARRAY(entry, 1); + hashmap_entry_init(&entry->ent, hash); + entry->path = xstrdup(key.path); + oidset_init(&entry->trees, 16); + hashmap_put(map, &entry->ent); + } + + oidset_insert(&entry->trees, oid); +} + +static void add_children_by_path(struct repository *r, + struct tree *tree, + struct hashmap *map) +{ + struct tree_desc desc; + struct name_entry entry; + + if (!tree) + return; - for (l = commit->parents->next; l; l = l->next) - commit_list_insert(l->item, &parents); - commit = commit->parents->item; + if (parse_tree_gently(tree, 1) < 0) + return; + + init_tree_desc(&desc, tree->buffer, tree->size); + while (tree_entry(&desc, &entry)) { + switch (object_type(entry.mode)) { + case OBJ_TREE: + paths_and_oids_insert(map, entry.path, &entry.oid); + + if (tree->object.flags & UNINTERESTING) { + struct tree *child = lookup_tree(r, &entry.oid); + if (child) + child->object.flags |= UNINTERESTING; + } + break; + case OBJ_BLOB: + if (tree->object.flags & UNINTERESTING) { + struct blob *child = lookup_blob(r, &entry.oid); + if (child) + child->object.flags |= UNINTERESTING; + } + break; + default: + /* Subproject commit - not in this repository */ + break; } } + + free_tree_buffer(tree); +} + +void mark_trees_uninteresting_sparse(struct repository *r, + struct oidset *trees) +{ + unsigned has_interesting = 0, has_uninteresting = 0; + struct hashmap map = HASHMAP_INIT(path_and_oids_cmp, NULL); + struct hashmap_iter map_iter; + struct path_and_oids_entry *entry; + struct object_id *oid; + struct oidset_iter iter; + + oidset_iter_init(trees, &iter); + while ((!has_interesting || !has_uninteresting) && + (oid = oidset_iter_next(&iter))) { + struct tree *tree = lookup_tree(r, oid); + + if (!tree) + continue; + + if (tree->object.flags & UNINTERESTING) + has_uninteresting = 1; + else + has_interesting = 1; + } + + /* Do not walk unless we have both types of trees. */ + if (!has_uninteresting || !has_interesting) + return; + + oidset_iter_init(trees, &iter); + while ((oid = oidset_iter_next(&iter))) { + struct tree *tree = lookup_tree(r, oid); + add_children_by_path(r, tree, &map); + } + + hashmap_for_each_entry(&map, &map_iter, entry, ent /* member name */) + mark_trees_uninteresting_sparse(r, &entry->trees); + + paths_and_oids_clear(&map); +} + +struct commit_stack { + struct commit **items; + size_t nr, alloc; +}; +#define COMMIT_STACK_INIT { NULL, 0, 0 } + +static void commit_stack_push(struct commit_stack *stack, struct commit *commit) +{ + ALLOC_GROW(stack->items, stack->nr + 1, stack->alloc); + stack->items[stack->nr++] = commit; } -static void add_pending_object_with_mode(struct rev_info *revs, struct object *obj, const char *name, unsigned mode) +static struct commit *commit_stack_pop(struct commit_stack *stack) { + return stack->nr ? stack->items[--stack->nr] : NULL; +} + +static void commit_stack_clear(struct commit_stack *stack) +{ + FREE_AND_NULL(stack->items); + stack->nr = stack->alloc = 0; +} + +static void mark_one_parent_uninteresting(struct commit *commit, + struct commit_stack *pending) +{ + struct commit_list *l; + + if (commit->object.flags & UNINTERESTING) + return; + commit->object.flags |= UNINTERESTING; + + /* + * Normally we haven't parsed the parent + * yet, so we won't have a parent of a parent + * here. However, it may turn out that we've + * reached this commit some other way (where it + * wasn't uninteresting), in which case we need + * to mark its parents recursively too.. + */ + for (l = commit->parents; l; l = l->next) + commit_stack_push(pending, l->item); +} + +void mark_parents_uninteresting(struct commit *commit) +{ + struct commit_stack pending = COMMIT_STACK_INIT; + struct commit_list *l; + + for (l = commit->parents; l; l = l->next) + mark_one_parent_uninteresting(l->item, &pending); + + while (pending.nr > 0) + mark_one_parent_uninteresting(commit_stack_pop(&pending), + &pending); + + commit_stack_clear(&pending); +} + +static void add_pending_object_with_path(struct rev_info *revs, + struct object *obj, + const char *name, unsigned mode, + const char *path) +{ + struct interpret_branch_name_options options = { 0 }; if (!obj) return; if (revs->no_walk && (obj->flags & UNINTERESTING)) revs->no_walk = 0; if (revs->reflog_info && obj->type == OBJ_COMMIT) { struct strbuf buf = STRBUF_INIT; - int len = interpret_branch_name(name, &buf); - int st; + size_t namelen = strlen(name); + int len = interpret_branch_name(name, namelen, &buf, &options); - if (0 < len && name[len] && buf.len) + if (0 < len && len < namelen && buf.len) strbuf_addstr(&buf, name + len); - st = add_reflog_for_walk(revs->reflog_info, - (struct commit *)obj, - buf.buf[0] ? buf.buf: name); + add_reflog_for_walk(revs->reflog_info, + (struct commit *)obj, + buf.buf[0] ? buf.buf: name); strbuf_release(&buf); - if (st) - return; + return; /* do not add the commit itself */ } - add_object_array_with_mode(obj, name, &revs->pending, mode); + add_object_array_with_path(obj, name, &revs->pending, mode, path); } -void add_pending_object(struct rev_info *revs, struct object *obj, const char *name) +static void add_pending_object_with_mode(struct rev_info *revs, + struct object *obj, + const char *name, unsigned mode) +{ + add_pending_object_with_path(revs, obj, name, mode, NULL); +} + +void add_pending_object(struct rev_info *revs, + struct object *obj, const char *name) { add_pending_object_with_mode(revs, obj, name, S_IFINVALID); } void add_head_to_pending(struct rev_info *revs) { - unsigned char sha1[20]; + struct object_id oid; struct object *obj; - if (get_sha1("HEAD", sha1)) + if (get_oid("HEAD", &oid)) return; - obj = parse_object(sha1); + obj = parse_object(revs->repo, &oid); if (!obj) return; add_pending_object(revs, obj, "HEAD"); } -static struct object *get_reference(struct rev_info *revs, const char *name, const unsigned char *sha1, unsigned int flags) +static struct object *get_reference(struct rev_info *revs, const char *name, + const struct object_id *oid, + unsigned int flags) { struct object *object; - object = parse_object(sha1); + /* + * If the repository has commit graphs, repo_parse_commit() avoids + * reading the object buffer, so use it whenever possible. + */ + if (oid_object_info(revs->repo, oid, NULL) == OBJ_COMMIT) { + struct commit *c = lookup_commit(revs->repo, oid); + if (!repo_parse_commit(revs->repo, c)) + object = (struct object *) c; + else + object = NULL; + } else { + object = parse_object(revs->repo, oid); + } + if (!object) { if (revs->ignore_missing) return object; + if (revs->exclude_promisor_objects && is_promisor_object(oid)) + return NULL; die("bad object %s", name); } object->flags |= flags; return object; } -void add_pending_sha1(struct rev_info *revs, const char *name, - const unsigned char *sha1, unsigned int flags) +void add_pending_oid(struct rev_info *revs, const char *name, + const struct object_id *oid, unsigned int flags) { - struct object *object = get_reference(revs, name, sha1, flags); + struct object *object = get_reference(revs, name, oid, flags); add_pending_object(revs, object, name); } -static struct commit *handle_commit(struct rev_info *revs, struct object *object, const char *name) +static struct commit *handle_commit(struct rev_info *revs, + struct object_array_entry *entry) { + struct object *object = entry->item; + const char *name = entry->name; + const char *path = entry->path; + unsigned int mode = entry->mode; unsigned long flags = object->flags; /* @@ -257,14 +409,23 @@ static struct commit *handle_commit(struct rev_info *revs, struct object *object struct tag *tag = (struct tag *) object; if (revs->tag_objects && !(flags & UNINTERESTING)) add_pending_object(revs, object, tag->tag); - if (!tag->tagged) - die("bad tag"); - object = parse_object(tag->tagged->sha1); + object = parse_object(revs->repo, get_tagged_oid(tag)); if (!object) { - if (flags & UNINTERESTING) + if (revs->ignore_missing_links || (flags & UNINTERESTING)) + return NULL; + if (revs->exclude_promisor_objects && + is_promisor_object(&tag->tagged->oid)) return NULL; - die("bad object %s", sha1_to_hex(tag->tagged->sha1)); + die("bad object %s", oid_to_hex(&tag->tagged->oid)); } + object->flags |= flags; + /* + * We'll handle the tagged object by looping or dropping + * through to the non-tag handlers below. Do not + * propagate path data from the tag's pending entry. + */ + path = NULL; + mode = 0; } /* @@ -273,15 +434,21 @@ static struct commit *handle_commit(struct rev_info *revs, struct object *object */ if (object->type == OBJ_COMMIT) { struct commit *commit = (struct commit *)object; - if (parse_commit(commit) < 0) + + if (repo_parse_commit(revs->repo, commit) < 0) die("unable to parse commit %s", name); if (flags & UNINTERESTING) { - commit->object.flags |= UNINTERESTING; mark_parents_uninteresting(commit); - revs->limited = 1; + + if (!revs->topo_order || !generation_numbers_enabled(the_repository)) + revs->limited = 1; + } + if (revs->sources) { + char **slot = revision_sources_at(revs->sources, commit); + + if (!*slot) + *slot = xstrdup(name); } - if (revs->show_source && !commit->util) - commit->util = (void *) name; return commit; } @@ -294,10 +461,10 @@ static struct commit *handle_commit(struct rev_info *revs, struct object *object if (!revs->tree_objects) return NULL; if (flags & UNINTERESTING) { - mark_tree_uninteresting(tree); + mark_tree_contents_uninteresting(revs->repo, tree); return NULL; } - add_pending_object(revs, object, ""); + add_pending_object_with_path(revs, object, name, mode, path); return NULL; } @@ -305,72 +472,308 @@ static struct commit *handle_commit(struct rev_info *revs, struct object *object * Blob object? You know the drill by now.. */ if (object->type == OBJ_BLOB) { - struct blob *blob = (struct blob *)object; if (!revs->blob_objects) return NULL; - if (flags & UNINTERESTING) { - mark_blob_uninteresting(blob); + if (flags & UNINTERESTING) return NULL; - } - add_pending_object(revs, object, ""); + add_pending_object_with_path(revs, object, name, mode, path); return NULL; } die("%s is unknown object", name); } -static int everybody_uninteresting(struct commit_list *orig) +static int everybody_uninteresting(struct commit_list *orig, + struct commit **interesting_cache) { struct commit_list *list = orig; + + if (*interesting_cache) { + struct commit *commit = *interesting_cache; + if (!(commit->object.flags & UNINTERESTING)) + return 0; + } + while (list) { struct commit *commit = list->item; list = list->next; if (commit->object.flags & UNINTERESTING) continue; + + *interesting_cache = commit; return 0; } return 1; } /* + * A definition of "relevant" commit that we can use to simplify limited graphs + * by eliminating side branches. + * + * A "relevant" commit is one that is !UNINTERESTING (ie we are including it + * in our list), or that is a specified BOTTOM commit. Then after computing + * a limited list, during processing we can generally ignore boundary merges + * coming from outside the graph, (ie from irrelevant parents), and treat + * those merges as if they were single-parent. TREESAME is defined to consider + * only relevant parents, if any. If we are TREESAME to our on-graph parents, + * we don't care if we were !TREESAME to non-graph parents. + * + * Treating bottom commits as relevant ensures that a limited graph's + * connection to the actual bottom commit is not viewed as a side branch, but + * treated as part of the graph. For example: + * + * ....Z...A---X---o---o---B + * . / + * W---Y + * + * When computing "A..B", the A-X connection is at least as important as + * Y-X, despite A being flagged UNINTERESTING. + * + * And when computing --ancestry-path "A..B", the A-X connection is more + * important than Y-X, despite both A and Y being flagged UNINTERESTING. + */ +static inline int relevant_commit(struct commit *commit) +{ + return (commit->object.flags & (UNINTERESTING | BOTTOM)) != UNINTERESTING; +} + +/* + * Return a single relevant commit from a parent list. If we are a TREESAME + * commit, and this selects one of our parents, then we can safely simplify to + * that parent. + */ +static struct commit *one_relevant_parent(const struct rev_info *revs, + struct commit_list *orig) +{ + struct commit_list *list = orig; + struct commit *relevant = NULL; + + if (!orig) + return NULL; + + /* + * For 1-parent commits, or if first-parent-only, then return that + * first parent (even if not "relevant" by the above definition). + * TREESAME will have been set purely on that parent. + */ + if (revs->first_parent_only || !orig->next) + return orig->item; + + /* + * For multi-parent commits, identify a sole relevant parent, if any. + * If we have only one relevant parent, then TREESAME will be set purely + * with regard to that parent, and we can simplify accordingly. + * + * If we have more than one relevant parent, or no relevant parents + * (and multiple irrelevant ones), then we can't select a parent here + * and return NULL. + */ + while (list) { + struct commit *commit = list->item; + list = list->next; + if (relevant_commit(commit)) { + if (relevant) + return NULL; + relevant = commit; + } + } + return relevant; +} + +/* * The goal is to get REV_TREE_NEW as the result only if the * diff consists of all '+' (and no other changes), REV_TREE_OLD * if the whole diff is removal of old data, and otherwise * REV_TREE_DIFFERENT (of course if the trees are the same we * want REV_TREE_SAME). - * That means that once we get to REV_TREE_DIFFERENT, we do not - * have to look any further. + * + * The only time we care about the distinction is when + * remove_empty_trees is in effect, in which case we care only about + * whether the whole change is REV_TREE_NEW, or if there's another type + * of change. Which means we can stop the diff early in either of these + * cases: + * + * 1. We're not using remove_empty_trees at all. + * + * 2. We saw anything except REV_TREE_NEW. */ static int tree_difference = REV_TREE_SAME; static void file_add_remove(struct diff_options *options, int addremove, unsigned mode, - const unsigned char *sha1, - int sha1_valid, + const struct object_id *oid, + int oid_valid, const char *fullpath, unsigned dirty_submodule) { int diff = addremove == '+' ? REV_TREE_NEW : REV_TREE_OLD; + struct rev_info *revs = options->change_fn_data; tree_difference |= diff; - if (tree_difference == REV_TREE_DIFFERENT) - DIFF_OPT_SET(options, HAS_CHANGES); + if (!revs->remove_empty_trees || tree_difference != REV_TREE_NEW) + options->flags.has_changes = 1; } static void file_change(struct diff_options *options, unsigned old_mode, unsigned new_mode, - const unsigned char *old_sha1, - const unsigned char *new_sha1, - int old_sha1_valid, int new_sha1_valid, + const struct object_id *old_oid, + const struct object_id *new_oid, + int old_oid_valid, int new_oid_valid, const char *fullpath, unsigned old_dirty_submodule, unsigned new_dirty_submodule) { tree_difference = REV_TREE_DIFFERENT; - DIFF_OPT_SET(options, HAS_CHANGES); + options->flags.has_changes = 1; +} + +static int bloom_filter_atexit_registered; +static unsigned int count_bloom_filter_maybe; +static unsigned int count_bloom_filter_definitely_not; +static unsigned int count_bloom_filter_false_positive; +static unsigned int count_bloom_filter_not_present; + +static void trace2_bloom_filter_statistics_atexit(void) +{ + struct json_writer jw = JSON_WRITER_INIT; + + jw_object_begin(&jw, 0); + jw_object_intmax(&jw, "filter_not_present", count_bloom_filter_not_present); + jw_object_intmax(&jw, "maybe", count_bloom_filter_maybe); + jw_object_intmax(&jw, "definitely_not", count_bloom_filter_definitely_not); + jw_object_intmax(&jw, "false_positive", count_bloom_filter_false_positive); + jw_end(&jw); + + trace2_data_json("bloom", the_repository, "statistics", &jw); + + jw_release(&jw); +} + +static int forbid_bloom_filters(struct pathspec *spec) +{ + if (spec->has_wildcard) + return 1; + if (spec->nr > 1) + return 1; + if (spec->magic & ~PATHSPEC_LITERAL) + return 1; + if (spec->nr && (spec->items[0].magic & ~PATHSPEC_LITERAL)) + return 1; + + return 0; } -static int rev_compare_tree(struct rev_info *revs, struct commit *parent, struct commit *commit) +static void prepare_to_use_bloom_filter(struct rev_info *revs) { - struct tree *t1 = parent->tree; - struct tree *t2 = commit->tree; + struct pathspec_item *pi; + char *path_alloc = NULL; + const char *path, *p; + size_t len; + int path_component_nr = 1; + + if (!revs->commits) + return; + + if (forbid_bloom_filters(&revs->prune_data)) + return; + + repo_parse_commit(revs->repo, revs->commits->item); + + revs->bloom_filter_settings = get_bloom_filter_settings(revs->repo); + if (!revs->bloom_filter_settings) + return; + + if (!revs->pruning.pathspec.nr) + return; + + pi = &revs->pruning.pathspec.items[0]; + + /* remove single trailing slash from path, if needed */ + if (pi->len > 0 && pi->match[pi->len - 1] == '/') { + path_alloc = xmemdupz(pi->match, pi->len - 1); + path = path_alloc; + } else + path = pi->match; + + len = strlen(path); + if (!len) { + revs->bloom_filter_settings = NULL; + free(path_alloc); + return; + } + + p = path; + while (*p) { + /* + * At this point, the path is normalized to use Unix-style + * path separators. This is required due to how the + * changed-path Bloom filters store the paths. + */ + if (*p == '/') + path_component_nr++; + p++; + } + + revs->bloom_keys_nr = path_component_nr; + ALLOC_ARRAY(revs->bloom_keys, revs->bloom_keys_nr); + + fill_bloom_key(path, len, &revs->bloom_keys[0], + revs->bloom_filter_settings); + path_component_nr = 1; + + p = path + len - 1; + while (p > path) { + if (*p == '/') + fill_bloom_key(path, p - path, + &revs->bloom_keys[path_component_nr++], + revs->bloom_filter_settings); + p--; + } + + if (trace2_is_enabled() && !bloom_filter_atexit_registered) { + atexit(trace2_bloom_filter_statistics_atexit); + bloom_filter_atexit_registered = 1; + } + + free(path_alloc); +} + +static int check_maybe_different_in_bloom_filter(struct rev_info *revs, + struct commit *commit) +{ + struct bloom_filter *filter; + int result = 1, j; + + if (!revs->repo->objects->commit_graph) + return -1; + + if (commit_graph_generation(commit) == GENERATION_NUMBER_INFINITY) + return -1; + + filter = get_bloom_filter(revs->repo, commit); + + if (!filter) { + count_bloom_filter_not_present++; + return -1; + } + + for (j = 0; result && j < revs->bloom_keys_nr; j++) { + result = bloom_filter_contains(filter, + &revs->bloom_keys[j], + revs->bloom_filter_settings); + } + + if (result) + count_bloom_filter_maybe++; + else + count_bloom_filter_definitely_not++; + + return result; +} + +static int rev_compare_tree(struct rev_info *revs, + struct commit *parent, struct commit *commit, int nth_parent) +{ + struct tree *t1 = get_commit_tree(parent); + struct tree *t2 = get_commit_tree(commit); + int bloom_ret = 1; if (!t1) return REV_TREE_NEW; @@ -382,7 +785,7 @@ static int rev_compare_tree(struct rev_info *revs, struct commit *parent, struct * If we are simplifying by decoration, then the commit * is worth showing if it has a tag pointing at it. */ - if (lookup_decoration(&name_decoration, &commit->object)) + if (get_name_decoration(&commit->object)) return REV_TREE_DIFFERENT; /* * A commit that is not pointed by a tag is uninteresting @@ -395,43 +798,157 @@ static int rev_compare_tree(struct rev_info *revs, struct commit *parent, struct return REV_TREE_SAME; } + if (revs->bloom_keys_nr && !nth_parent) { + bloom_ret = check_maybe_different_in_bloom_filter(revs, commit); + + if (bloom_ret == 0) + return REV_TREE_SAME; + } + tree_difference = REV_TREE_SAME; - DIFF_OPT_CLR(&revs->pruning, HAS_CHANGES); - if (diff_tree_sha1(t1->object.sha1, t2->object.sha1, "", - &revs->pruning) < 0) - return REV_TREE_DIFFERENT; + revs->pruning.flags.has_changes = 0; + diff_tree_oid(&t1->object.oid, &t2->object.oid, "", &revs->pruning); + + if (!nth_parent) + if (bloom_ret == 1 && tree_difference == REV_TREE_SAME) + count_bloom_filter_false_positive++; + return tree_difference; } static int rev_same_tree_as_empty(struct rev_info *revs, struct commit *commit) { - int retval; - void *tree; - unsigned long size; - struct tree_desc empty, real; - struct tree *t1 = commit->tree; + struct tree *t1 = get_commit_tree(commit); if (!t1) return 0; - tree = read_object_with_reference(t1->object.sha1, tree_type, &size, NULL); - if (!tree) - return 0; - init_tree_desc(&real, tree, size); - init_tree_desc(&empty, "", 0); - tree_difference = REV_TREE_SAME; - DIFF_OPT_CLR(&revs->pruning, HAS_CHANGES); - retval = diff_tree(&empty, &real, "", &revs->pruning); - free(tree); + revs->pruning.flags.has_changes = 0; + diff_tree_oid(NULL, &t1->object.oid, "", &revs->pruning); + + return tree_difference == REV_TREE_SAME; +} + +struct treesame_state { + unsigned int nparents; + unsigned char treesame[FLEX_ARRAY]; +}; + +static struct treesame_state *initialise_treesame(struct rev_info *revs, struct commit *commit) +{ + unsigned n = commit_list_count(commit->parents); + struct treesame_state *st = xcalloc(1, st_add(sizeof(*st), n)); + st->nparents = n; + add_decoration(&revs->treesame, &commit->object, st); + return st; +} + +/* + * Must be called immediately after removing the nth_parent from a commit's + * parent list, if we are maintaining the per-parent treesame[] decoration. + * This does not recalculate the master TREESAME flag - update_treesame() + * should be called to update it after a sequence of treesame[] modifications + * that may have affected it. + */ +static int compact_treesame(struct rev_info *revs, struct commit *commit, unsigned nth_parent) +{ + struct treesame_state *st; + int old_same; + + if (!commit->parents) { + /* + * Have just removed the only parent from a non-merge. + * Different handling, as we lack decoration. + */ + if (nth_parent != 0) + die("compact_treesame %u", nth_parent); + old_same = !!(commit->object.flags & TREESAME); + if (rev_same_tree_as_empty(revs, commit)) + commit->object.flags |= TREESAME; + else + commit->object.flags &= ~TREESAME; + return old_same; + } + + st = lookup_decoration(&revs->treesame, &commit->object); + if (!st || nth_parent >= st->nparents) + die("compact_treesame %u", nth_parent); - return retval >= 0 && (tree_difference == REV_TREE_SAME); + old_same = st->treesame[nth_parent]; + memmove(st->treesame + nth_parent, + st->treesame + nth_parent + 1, + st->nparents - nth_parent - 1); + + /* + * If we've just become a non-merge commit, update TREESAME + * immediately, and remove the no-longer-needed decoration. + * If still a merge, defer update until update_treesame(). + */ + if (--st->nparents == 1) { + if (commit->parents->next) + die("compact_treesame parents mismatch"); + if (st->treesame[0] && revs->dense) + commit->object.flags |= TREESAME; + else + commit->object.flags &= ~TREESAME; + free(add_decoration(&revs->treesame, &commit->object, NULL)); + } + + return old_same; +} + +static unsigned update_treesame(struct rev_info *revs, struct commit *commit) +{ + if (commit->parents && commit->parents->next) { + unsigned n; + struct treesame_state *st; + struct commit_list *p; + unsigned relevant_parents; + unsigned relevant_change, irrelevant_change; + + st = lookup_decoration(&revs->treesame, &commit->object); + if (!st) + die("update_treesame %s", oid_to_hex(&commit->object.oid)); + relevant_parents = 0; + relevant_change = irrelevant_change = 0; + for (p = commit->parents, n = 0; p; n++, p = p->next) { + if (relevant_commit(p->item)) { + relevant_change |= !st->treesame[n]; + relevant_parents++; + } else + irrelevant_change |= !st->treesame[n]; + } + if (relevant_parents ? relevant_change : irrelevant_change) + commit->object.flags &= ~TREESAME; + else + commit->object.flags |= TREESAME; + } + + return commit->object.flags & TREESAME; +} + +static inline int limiting_can_increase_treesame(const struct rev_info *revs) +{ + /* + * TREESAME is irrelevant unless prune && dense; + * if simplify_history is set, we can't have a mixture of TREESAME and + * !TREESAME INTERESTING parents (and we don't have treesame[] + * decoration anyway); + * if first_parent_only is set, then the TREESAME flag is locked + * against the first parent (and again we lack treesame[] decoration). + */ + return revs->prune && revs->dense && + !revs->simplify_history && + !revs->first_parent_only; } static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit) { struct commit_list **pp, *parent; - int tree_changed = 0, tree_same = 0, nth_parent = 0; + struct treesame_state *ts = NULL; + int relevant_change = 0, irrelevant_change = 0; + int relevant_parents, nth_parent; /* * If we don't do pruning, everything is interesting @@ -439,7 +956,7 @@ static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit) if (!revs->prune) return; - if (!commit->tree) + if (!get_commit_tree(commit)) return; if (!commit->parents) { @@ -455,38 +972,71 @@ static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit) if (!revs->dense && !commit->parents->next) return; - pp = &commit->parents; - while ((parent = *pp) != NULL) { + for (pp = &commit->parents, nth_parent = 0, relevant_parents = 0; + (parent = *pp) != NULL; + pp = &parent->next, nth_parent++) { struct commit *p = parent->item; + if (relevant_commit(p)) + relevant_parents++; - /* - * Do not compare with later parents when we care only about - * the first parent chain, in order to avoid derailing the - * traversal to follow a side branch that brought everything - * in the path we are limited to by the pathspec. - */ - if (revs->first_parent_only && nth_parent++) - break; - if (parse_commit(p) < 0) + if (nth_parent == 1) { + /* + * This our second loop iteration - so we now know + * we're dealing with a merge. + * + * Do not compare with later parents when we care only about + * the first parent chain, in order to avoid derailing the + * traversal to follow a side branch that brought everything + * in the path we are limited to by the pathspec. + */ + if (revs->first_parent_only) + break; + /* + * If this will remain a potentially-simplifiable + * merge, remember per-parent treesame if needed. + * Initialise the array with the comparison from our + * first iteration. + */ + if (revs->treesame.name && + !revs->simplify_history && + !(commit->object.flags & UNINTERESTING)) { + ts = initialise_treesame(revs, commit); + if (!(irrelevant_change || relevant_change)) + ts->treesame[0] = 1; + } + } + if (repo_parse_commit(revs->repo, p) < 0) die("cannot simplify commit %s (because of %s)", - sha1_to_hex(commit->object.sha1), - sha1_to_hex(p->object.sha1)); - switch (rev_compare_tree(revs, p, commit)) { + oid_to_hex(&commit->object.oid), + oid_to_hex(&p->object.oid)); + switch (rev_compare_tree(revs, p, commit, nth_parent)) { case REV_TREE_SAME: - tree_same = 1; - if (!revs->simplify_history || (p->object.flags & UNINTERESTING)) { + if (!revs->simplify_history || !relevant_commit(p)) { /* Even if a merge with an uninteresting * side branch brought the entire change * we are interested in, we do not want * to lose the other branches of this * merge, so we just keep going. */ - pp = &parent->next; + if (ts) + ts->treesame[nth_parent] = 1; continue; } parent->next = NULL; commit->parents = parent; - commit->object.flags |= TREESAME; + + /* + * A merge commit is a "diversion" if it is not + * TREESAME to its first parent but is TREESAME + * to a later parent. In the simplified history, + * we "divert" the history walk to the later + * parent. These commits are shown when "show_pulls" + * is enabled, so do not mark the object as + * TREESAME here. + */ + if (!revs->show_pulls || !nth_parent) + commit->object.flags |= TREESAME; + return; case REV_TREE_NEW: @@ -500,51 +1050,56 @@ static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit) * IOW, we pretend this parent is a * "root" commit. */ - if (parse_commit(p) < 0) + if (repo_parse_commit(revs->repo, p) < 0) die("cannot simplify commit %s (invalid %s)", - sha1_to_hex(commit->object.sha1), - sha1_to_hex(p->object.sha1)); + oid_to_hex(&commit->object.oid), + oid_to_hex(&p->object.oid)); p->parents = NULL; } /* fallthrough */ case REV_TREE_OLD: case REV_TREE_DIFFERENT: - tree_changed = 1; - pp = &parent->next; + if (relevant_commit(p)) + relevant_change = 1; + else + irrelevant_change = 1; + + if (!nth_parent) + commit->object.flags |= PULL_MERGE; + continue; } - die("bad tree compare for commit %s", sha1_to_hex(commit->object.sha1)); + die("bad tree compare for commit %s", oid_to_hex(&commit->object.oid)); } - if (tree_changed && !tree_same) - return; - commit->object.flags |= TREESAME; -} - -static void commit_list_insert_by_date_cached(struct commit *p, struct commit_list **head, - struct commit_list *cached_base, struct commit_list **cache) -{ - struct commit_list *new_entry; - if (cached_base && p->date < cached_base->item->date) - new_entry = commit_list_insert_by_date(p, &cached_base->next); - else - new_entry = commit_list_insert_by_date(p, head); - - if (cache && (!*cache || p->date < (*cache)->item->date)) - *cache = new_entry; + /* + * TREESAME is straightforward for single-parent commits. For merge + * commits, it is most useful to define it so that "irrelevant" + * parents cannot make us !TREESAME - if we have any relevant + * parents, then we only consider TREESAMEness with respect to them, + * allowing irrelevant merges from uninteresting branches to be + * simplified away. Only if we have only irrelevant parents do we + * base TREESAME on them. Note that this logic is replicated in + * update_treesame, which should be kept in sync. + */ + if (relevant_parents ? !relevant_change : !irrelevant_change) + commit->object.flags |= TREESAME; } -static int add_parents_to_list(struct rev_info *revs, struct commit *commit, - struct commit_list **list, struct commit_list **cache_ptr) +static int process_parents(struct rev_info *revs, struct commit *commit, + struct commit_list **list, struct prio_queue *queue) { struct commit_list *parent = commit->parents; unsigned left_flag; - struct commit_list *cached_base = cache_ptr ? *cache_ptr : NULL; if (commit->object.flags & ADDED) return 0; commit->object.flags |= ADDED; + if (revs->include_check && + !revs->include_check(commit, revs->include_check_data)) + return 0; + /* * If the commit is uninteresting, don't try to * prune parents - we want the maximal uninteresting @@ -563,14 +1118,17 @@ static int add_parents_to_list(struct rev_info *revs, struct commit *commit, parent = parent->next; if (p) p->object.flags |= UNINTERESTING; - if (parse_commit(p) < 0) + if (repo_parse_commit_gently(revs->repo, p, 1) < 0) continue; if (p->parents) mark_parents_uninteresting(p); if (p->object.flags & SEEN) continue; - p->object.flags |= SEEN; - commit_list_insert_by_date_cached(p, list, cached_base, cache_ptr); + p->object.flags |= (SEEN | NOT_USER_GIVEN); + if (list) + commit_list_insert_by_date(p, list); + if (queue) + prio_queue_put(queue, p); } return 0; } @@ -589,15 +1147,30 @@ static int add_parents_to_list(struct rev_info *revs, struct commit *commit, for (parent = commit->parents; parent; parent = parent->next) { struct commit *p = parent->item; - - if (parse_commit(p) < 0) + int gently = revs->ignore_missing_links || + revs->exclude_promisor_objects; + if (repo_parse_commit_gently(revs->repo, p, gently) < 0) { + if (revs->exclude_promisor_objects && + is_promisor_object(&p->object.oid)) { + if (revs->first_parent_only) + break; + continue; + } return -1; - if (revs->show_source && !p->util) - p->util = commit->util; + } + if (revs->sources) { + char **slot = revision_sources_at(revs->sources, p); + + if (!*slot) + *slot = *revision_sources_at(revs->sources, commit); + } p->object.flags |= left_flag; if (!(p->object.flags & SEEN)) { - p->object.flags |= SEEN; - commit_list_insert_by_date_cached(p, list, cached_base, cache_ptr); + p->object.flags |= (SEEN | NOT_USER_GIVEN); + if (list) + commit_list_insert_by_date(p, list); + if (queue) + prio_queue_put(queue, p); } if (revs->first_parent_only) break; @@ -629,7 +1202,7 @@ static void cherry_pick_list(struct commit_list *list, struct rev_info *revs) return; left_first = left_count < right_count; - init_patch_ids(&ids); + init_patch_ids(revs->repo, &ids); ids.diffopts.pathspec = revs->diffopt.pathspec; /* Compute patch-ids for one side */ @@ -646,7 +1219,7 @@ static void cherry_pick_list(struct commit_list *list, struct rev_info *revs) */ if (left_first != !!(flags & SYMMETRIC_LEFT)) continue; - commit->util = add_commit_patch_id(commit, &ids); + add_commit_patch_id(commit, &ids); } /* either cherry_mark or cherry_pick are true */ @@ -670,24 +1243,14 @@ static void cherry_pick_list(struct commit_list *list, struct rev_info *revs) /* * Have we seen the same patch id? */ - id = has_commit_patch_id(commit, &ids); + id = patch_id_iter_first(commit, &ids); if (!id) continue; - id->seen = 1; - commit->object.flags |= cherry_flag; - } - - /* Now check the original side for seen ones */ - for (p = list; p; p = p->next) { - struct commit *commit = p->item; - struct patch_id *ent; - ent = commit->util; - if (!ent) - continue; - if (ent->seen) - commit->object.flags |= cherry_flag; - commit->util = NULL; + commit->object.flags |= cherry_flag; + do { + id->commit->object.flags |= cherry_flag; + } while ((id = patch_id_iter_next(id, &ids))); } free_patch_ids(&ids); @@ -696,7 +1259,8 @@ static void cherry_pick_list(struct commit_list *list, struct rev_info *revs) /* How many extra uninteresting commits we want to see.. */ #define SLOP 5 -static int still_interesting(struct commit_list *src, unsigned long date, int slop) +static int still_interesting(struct commit_list *src, timestamp_t date, int slop, + struct commit **interesting_cache) { /* * No source list at all? We're definitely done.. @@ -715,7 +1279,7 @@ static int still_interesting(struct commit_list *src, unsigned long date, int sl * Does the source list still have interesting commits in * it? Definitely not done.. */ - if (!everybody_uninteresting(src)) + if (!everybody_uninteresting(src, interesting_cache)) return SLOP; /* Ok, we're closing in.. */ @@ -800,16 +1364,12 @@ static void limit_to_ancestry(struct commit_list *bottom, struct commit_list *li * to filter the result of "A..B" further to the ones that can actually * reach A. */ -static struct commit_list *collect_bottom_commits(struct rev_info *revs) +static struct commit_list *collect_bottom_commits(struct commit_list *list) { - struct commit_list *bottom = NULL; - int i; - for (i = 0; i < revs->cmdline.nr; i++) { - struct rev_cmdline_entry *elem = &revs->cmdline.rev[i]; - if ((elem->flags & UNINTERESTING) && - elem->item->type == OBJ_COMMIT) - commit_list_insert((struct commit *)elem->item, &bottom); - } + struct commit_list *elem, *bottom = NULL; + for (elem = list; elem; elem = elem->next) + if (elem->item->object.flags & BOTTOM) + commit_list_insert(elem->item, &bottom); return bottom; } @@ -833,44 +1393,40 @@ static void limit_left_right(struct commit_list *list, struct rev_info *revs) static int limit_list(struct rev_info *revs) { int slop = SLOP; - unsigned long date = ~0ul; - struct commit_list *list = revs->commits; + timestamp_t date = TIME_MAX; + struct commit_list *original_list = revs->commits; struct commit_list *newlist = NULL; struct commit_list **p = &newlist; struct commit_list *bottom = NULL; + struct commit *interesting_cache = NULL; if (revs->ancestry_path) { - bottom = collect_bottom_commits(revs); + bottom = collect_bottom_commits(original_list); if (!bottom) die("--ancestry-path given but there are no bottom commits"); } - while (list) { - struct commit_list *entry = list; - struct commit *commit = list->item; + while (original_list) { + struct commit *commit = pop_commit(&original_list); struct object *obj = &commit->object; show_early_output_fn_t show; - list = list->next; - free(entry); + if (commit == interesting_cache) + interesting_cache = NULL; if (revs->max_age != -1 && (commit->date < revs->max_age)) obj->flags |= UNINTERESTING; - if (add_parents_to_list(revs, commit, &list, NULL) < 0) + if (process_parents(revs, commit, &original_list, NULL) < 0) return -1; if (obj->flags & UNINTERESTING) { mark_parents_uninteresting(commit); - if (revs->show_all) - p = &commit_list_insert(commit, p)->next; - slop = still_interesting(list, date, slop); + slop = still_interesting(original_list, date, slop, &interesting_cache); if (slop) continue; - /* If showing all, add the whole pending list to the end */ - if (revs->show_all) - *p = list; break; } - if (revs->min_age != -1 && (commit->date > revs->min_age)) + if (revs->min_age != -1 && (commit->date > revs->min_age) && + !revs->line_level_traverse) continue; date = commit->date; p = &commit_list_insert(commit, p)->next; @@ -893,10 +1449,29 @@ static int limit_list(struct rev_info *revs) free_commit_list(bottom); } + /* + * Check if any commits have become TREESAME by some of their parents + * becoming UNINTERESTING. + */ + if (limiting_can_increase_treesame(revs)) { + struct commit_list *list = NULL; + for (list = newlist; list; list = list->next) { + struct commit *c = list->item; + if (c->object.flags & (UNINTERESTING | TREESAME)) + continue; + update_treesame(revs, c); + } + } + + free_commit_list(original_list); revs->commits = newlist; return 0; } +/* + * Add an entry to refs->cmdline with the specified information. + * *name is copied. + */ static void add_rev_cmdline(struct rev_info *revs, struct object *item, const char *name, @@ -904,30 +1479,62 @@ static void add_rev_cmdline(struct rev_info *revs, unsigned flags) { struct rev_cmdline_info *info = &revs->cmdline; - int nr = info->nr; + unsigned int nr = info->nr; ALLOC_GROW(info->rev, nr + 1, info->alloc); info->rev[nr].item = item; - info->rev[nr].name = name; + info->rev[nr].name = xstrdup(name); info->rev[nr].whence = whence; info->rev[nr].flags = flags; info->nr++; } +static void add_rev_cmdline_list(struct rev_info *revs, + struct commit_list *commit_list, + int whence, + unsigned flags) +{ + while (commit_list) { + struct object *object = &commit_list->item->object; + add_rev_cmdline(revs, object, oid_to_hex(&object->oid), + whence, flags); + commit_list = commit_list->next; + } +} + struct all_refs_cb { int all_flags; int warned_bad_reflog; struct rev_info *all_revs; const char *name_for_errormsg; + struct worktree *wt; }; -static int handle_one_ref(const char *path, const unsigned char *sha1, int flag, void *cb_data) +int ref_excluded(struct string_list *ref_excludes, const char *path) +{ + struct string_list_item *item; + + if (!ref_excludes) + return 0; + for_each_string_list_item(item, ref_excludes) { + if (!wildmatch(item->string, path, 0)) + return 1; + } + return 0; +} + +static int handle_one_ref(const char *path, const struct object_id *oid, + int flag, void *cb_data) { struct all_refs_cb *cb = cb_data; - struct object *object = get_reference(cb->all_revs, path, sha1, - cb->all_flags); + struct object *object; + + if (ref_excluded(cb->all_revs->ref_excludes, path)) + return 0; + + object = get_reference(cb->all_revs, path, oid, cb->all_flags); add_rev_cmdline(cb->all_revs, object, path, REV_CMD_REF, cb->all_flags); - add_pending_sha1(cb->all_revs, path, sha1, cb->all_flags); + add_pending_oid(cb->all_revs, path, oid, cb->all_flags); return 0; } @@ -936,21 +1543,48 @@ static void init_all_refs_cb(struct all_refs_cb *cb, struct rev_info *revs, { cb->all_revs = revs; cb->all_flags = flags; + revs->rev_input_given = 1; + cb->wt = NULL; } -static void handle_refs(const char *submodule, struct rev_info *revs, unsigned flags, - int (*for_each)(const char *, each_ref_fn, void *)) +void clear_ref_exclusion(struct string_list **ref_excludes_p) +{ + if (*ref_excludes_p) { + string_list_clear(*ref_excludes_p, 0); + free(*ref_excludes_p); + } + *ref_excludes_p = NULL; +} + +void add_ref_exclusion(struct string_list **ref_excludes_p, const char *exclude) +{ + if (!*ref_excludes_p) { + CALLOC_ARRAY(*ref_excludes_p, 1); + (*ref_excludes_p)->strdup_strings = 1; + } + string_list_append(*ref_excludes_p, exclude); +} + +static void handle_refs(struct ref_store *refs, + struct rev_info *revs, unsigned flags, + int (*for_each)(struct ref_store *, each_ref_fn, void *)) { struct all_refs_cb cb; + + if (!refs) { + /* this could happen with uninitialized submodules */ + return; + } + init_all_refs_cb(&cb, revs, flags); - for_each(submodule, handle_one_ref, &cb); + for_each(refs, handle_one_ref, &cb); } -static void handle_one_reflog_commit(unsigned char *sha1, void *cb_data) +static void handle_one_reflog_commit(struct object_id *oid, void *cb_data) { struct all_refs_cb *cb = cb_data; - if (!is_null_sha1(sha1)) { - struct object *o = parse_object(sha1); + if (!is_null_oid(oid)) { + struct object *o = parse_object(cb->all_revs->repo, oid); if (o) { o->flags |= cb->all_flags; /* ??? CMDLINEFLAGS ??? */ @@ -964,60 +1598,207 @@ static void handle_one_reflog_commit(unsigned char *sha1, void *cb_data) } } -static int handle_one_reflog_ent(unsigned char *osha1, unsigned char *nsha1, - const char *email, unsigned long timestamp, int tz, +static int handle_one_reflog_ent(struct object_id *ooid, struct object_id *noid, + const char *email, timestamp_t timestamp, int tz, const char *message, void *cb_data) { - handle_one_reflog_commit(osha1, cb_data); - handle_one_reflog_commit(nsha1, cb_data); + handle_one_reflog_commit(ooid, cb_data); + handle_one_reflog_commit(noid, cb_data); return 0; } -static int handle_one_reflog(const char *path, const unsigned char *sha1, int flag, void *cb_data) +static int handle_one_reflog(const char *refname_in_wt, + const struct object_id *oid, + int flag, void *cb_data) { struct all_refs_cb *cb = cb_data; + struct strbuf refname = STRBUF_INIT; + cb->warned_bad_reflog = 0; - cb->name_for_errormsg = path; - for_each_reflog_ent(path, handle_one_reflog_ent, cb_data); + strbuf_worktree_ref(cb->wt, &refname, refname_in_wt); + cb->name_for_errormsg = refname.buf; + refs_for_each_reflog_ent(get_main_ref_store(the_repository), + refname.buf, + handle_one_reflog_ent, cb_data); + strbuf_release(&refname); return 0; } -static void handle_reflog(struct rev_info *revs, unsigned flags) +static void add_other_reflogs_to_pending(struct all_refs_cb *cb) +{ + struct worktree **worktrees, **p; + + worktrees = get_worktrees(); + for (p = worktrees; *p; p++) { + struct worktree *wt = *p; + + if (wt->is_current) + continue; + + cb->wt = wt; + refs_for_each_reflog(get_worktree_ref_store(wt), + handle_one_reflog, + cb); + } + free_worktrees(worktrees); +} + +void add_reflogs_to_pending(struct rev_info *revs, unsigned flags) { struct all_refs_cb cb; + cb.all_revs = revs; cb.all_flags = flags; + cb.wt = NULL; for_each_reflog(handle_one_reflog, &cb); + + if (!revs->single_worktree) + add_other_reflogs_to_pending(&cb); +} + +static void add_cache_tree(struct cache_tree *it, struct rev_info *revs, + struct strbuf *path, unsigned int flags) +{ + size_t baselen = path->len; + int i; + + if (it->entry_count >= 0) { + struct tree *tree = lookup_tree(revs->repo, &it->oid); + tree->object.flags |= flags; + add_pending_object_with_path(revs, &tree->object, "", + 040000, path->buf); + } + + for (i = 0; i < it->subtree_nr; i++) { + struct cache_tree_sub *sub = it->down[i]; + strbuf_addf(path, "%s%s", baselen ? "/" : "", sub->name); + add_cache_tree(sub->cache_tree, revs, path, flags); + strbuf_setlen(path, baselen); + } + +} + +static void do_add_index_objects_to_pending(struct rev_info *revs, + struct index_state *istate, + unsigned int flags) +{ + int i; + + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(istate); + for (i = 0; i < istate->cache_nr; i++) { + struct cache_entry *ce = istate->cache[i]; + struct blob *blob; + + if (S_ISGITLINK(ce->ce_mode)) + continue; + + blob = lookup_blob(revs->repo, &ce->oid); + if (!blob) + die("unable to add index blob to traversal"); + blob->object.flags |= flags; + add_pending_object_with_path(revs, &blob->object, "", + ce->ce_mode, ce->name); + } + + if (istate->cache_tree) { + struct strbuf path = STRBUF_INIT; + add_cache_tree(istate->cache_tree, revs, &path, flags); + strbuf_release(&path); + } } -static int add_parents_only(struct rev_info *revs, const char *arg_, int flags) +void add_index_objects_to_pending(struct rev_info *revs, unsigned int flags) { - unsigned char sha1[20]; + struct worktree **worktrees, **p; + + repo_read_index(revs->repo); + do_add_index_objects_to_pending(revs, revs->repo->index, flags); + + if (revs->single_worktree) + return; + + worktrees = get_worktrees(); + for (p = worktrees; *p; p++) { + struct worktree *wt = *p; + struct index_state istate = { NULL }; + + if (wt->is_current) + continue; /* current index already taken care of */ + + if (read_index_from(&istate, + worktree_git_path(wt, "index"), + get_worktree_git_dir(wt)) > 0) + do_add_index_objects_to_pending(revs, &istate, flags); + discard_index(&istate); + } + free_worktrees(worktrees); +} + +struct add_alternate_refs_data { + struct rev_info *revs; + unsigned int flags; +}; + +static void add_one_alternate_ref(const struct object_id *oid, + void *vdata) +{ + const char *name = ".alternate"; + struct add_alternate_refs_data *data = vdata; + struct object *obj; + + obj = get_reference(data->revs, name, oid, data->flags); + add_rev_cmdline(data->revs, obj, name, REV_CMD_REV, data->flags); + add_pending_object(data->revs, obj, name); +} + +static void add_alternate_refs_to_pending(struct rev_info *revs, + unsigned int flags) +{ + struct add_alternate_refs_data data; + data.revs = revs; + data.flags = flags; + for_each_alternate_ref(add_one_alternate_ref, &data); +} + +static int add_parents_only(struct rev_info *revs, const char *arg_, int flags, + int exclude_parent) +{ + struct object_id oid; struct object *it; struct commit *commit; struct commit_list *parents; + int parent_number; const char *arg = arg_; if (*arg == '^') { - flags ^= UNINTERESTING; + flags ^= UNINTERESTING | BOTTOM; arg++; } - if (get_sha1_committish(arg, sha1)) + if (get_oid_committish(arg, &oid)) return 0; while (1) { - it = get_reference(revs, arg, sha1, 0); + it = get_reference(revs, arg, &oid, 0); if (!it && revs->ignore_missing) return 0; if (it->type != OBJ_TAG) break; if (!((struct tag*)it)->tagged) return 0; - hashcpy(sha1, ((struct tag*)it)->tagged->sha1); + oidcpy(&oid, &((struct tag*)it)->tagged->oid); } if (it->type != OBJ_COMMIT) return 0; commit = (struct commit *)it; - for (parents = commit->parents; parents; parents = parents->next) { + if (exclude_parent && + exclude_parent > commit_list_count(commit->parents)) + return 0; + for (parents = commit->parents, parent_number = 1; + parents; + parents = parents->next, parent_number++) { + if (exclude_parent && parent_number != exclude_parent) + continue; + it = &parents->item->object; it->flags |= flags; add_rev_cmdline(revs, it, arg_, REV_CMD_PARENTS_ONLY, flags); @@ -1026,18 +1807,22 @@ static int add_parents_only(struct rev_info *revs, const char *arg_, int flags) return 1; } -void init_revisions(struct rev_info *revs, const char *prefix) +void repo_init_revisions(struct repository *r, + struct rev_info *revs, + const char *prefix) { memset(revs, 0, sizeof(*revs)); + revs->repo = r; revs->abbrev = DEFAULT_ABBREV; - revs->ignore_merges = 1; revs->simplify_history = 1; - DIFF_OPT_SET(&revs->pruning, RECURSIVE); - DIFF_OPT_SET(&revs->pruning, QUICK); + revs->pruning.repo = r; + revs->pruning.flags.recursive = 1; + revs->pruning.flags.quick = 1; revs->pruning.add_remove = file_add_remove; revs->pruning.change = file_change; - revs->lifo = 1; + revs->pruning.change_fn_data = revs; + revs->sort_order = REV_SORT_IN_GRAPH_ORDER; revs->dense = 1; revs->prefix = prefix; revs->max_age = -1; @@ -1045,31 +1830,31 @@ void init_revisions(struct rev_info *revs, const char *prefix) revs->skip_count = -1; revs->max_count = -1; revs->max_parents = -1; + revs->expand_tabs_in_log = -1; revs->commit_format = CMIT_FMT_DEFAULT; + revs->expand_tabs_in_log_default = 8; - init_grep_defaults(); - grep_init(&revs->grep_filter, prefix); + grep_init(&revs->grep_filter, revs->repo, prefix); revs->grep_filter.status_only = 1; - revs->grep_filter.regflags = REG_NEWLINE; - diff_setup(&revs->diffopt); + repo_diff_setup(revs->repo, &revs->diffopt); if (prefix && !revs->diffopt.prefix) { revs->diffopt.prefix = prefix; revs->diffopt.prefix_length = strlen(prefix); } - revs->notes_opt.use_default_notes = -1; + init_display_notes(&revs->notes_opt); } static void add_pending_commit_list(struct rev_info *revs, - struct commit_list *commit_list, - unsigned int flags) + struct commit_list *commit_list, + unsigned int flags) { while (commit_list) { struct object *object = &commit_list->item->object; object->flags |= flags; - add_pending_object(revs, object, sha1_to_hex(object->sha1)); + add_pending_object(revs, object, oid_to_hex(&object->oid)); commit_list = commit_list->next; } } @@ -1078,194 +1863,261 @@ static void prepare_show_merge(struct rev_info *revs) { struct commit_list *bases; struct commit *head, *other; - unsigned char sha1[20]; + struct object_id oid; const char **prune = NULL; int i, prune_num = 1; /* counting terminating NULL */ + struct index_state *istate = revs->repo->index; - if (get_sha1("HEAD", sha1)) + if (get_oid("HEAD", &oid)) die("--merge without HEAD?"); - head = lookup_commit_or_die(sha1, "HEAD"); - if (get_sha1("MERGE_HEAD", sha1)) + head = lookup_commit_or_die(&oid, "HEAD"); + if (get_oid("MERGE_HEAD", &oid)) die("--merge without MERGE_HEAD?"); - other = lookup_commit_or_die(sha1, "MERGE_HEAD"); + other = lookup_commit_or_die(&oid, "MERGE_HEAD"); add_pending_object(revs, &head->object, "HEAD"); add_pending_object(revs, &other->object, "MERGE_HEAD"); - bases = get_merge_bases(head, other, 1); - add_pending_commit_list(revs, bases, UNINTERESTING); + bases = get_merge_bases(head, other); + add_rev_cmdline_list(revs, bases, REV_CMD_MERGE_BASE, UNINTERESTING | BOTTOM); + add_pending_commit_list(revs, bases, UNINTERESTING | BOTTOM); free_commit_list(bases); head->object.flags |= SYMMETRIC_LEFT; - if (!active_nr) - read_cache(); - for (i = 0; i < active_nr; i++) { - struct cache_entry *ce = active_cache[i]; + if (!istate->cache_nr) + repo_read_index(revs->repo); + for (i = 0; i < istate->cache_nr; i++) { + const struct cache_entry *ce = istate->cache[i]; if (!ce_stage(ce)) continue; - if (ce_path_match(ce, &revs->prune_data)) { + if (ce_path_match(istate, ce, &revs->prune_data, NULL)) { prune_num++; - prune = xrealloc(prune, sizeof(*prune) * prune_num); + REALLOC_ARRAY(prune, prune_num); prune[prune_num-2] = ce->name; prune[prune_num-1] = NULL; } - while ((i+1 < active_nr) && - ce_same_name(ce, active_cache[i+1])) + while ((i+1 < istate->cache_nr) && + ce_same_name(ce, istate->cache[i+1])) i++; } - free_pathspec(&revs->prune_data); - init_pathspec(&revs->prune_data, prune); + clear_pathspec(&revs->prune_data); + parse_pathspec(&revs->prune_data, PATHSPEC_ALL_MAGIC & ~PATHSPEC_LITERAL, + PATHSPEC_PREFER_FULL | PATHSPEC_LITERAL_PATH, "", prune); revs->limited = 1; } -int handle_revision_arg(const char *arg_, struct rev_info *revs, int flags, unsigned revarg_opt) +static int dotdot_missing(const char *arg, char *dotdot, + struct rev_info *revs, int symmetric) +{ + if (revs->ignore_missing) + return 0; + /* de-munge so we report the full argument */ + *dotdot = '.'; + die(symmetric + ? "Invalid symmetric difference expression %s" + : "Invalid revision range %s", arg); +} + +static int handle_dotdot_1(const char *arg, char *dotdot, + struct rev_info *revs, int flags, + int cant_be_filename, + struct object_context *a_oc, + struct object_context *b_oc) +{ + const char *a_name, *b_name; + struct object_id a_oid, b_oid; + struct object *a_obj, *b_obj; + unsigned int a_flags, b_flags; + int symmetric = 0; + unsigned int flags_exclude = flags ^ (UNINTERESTING | BOTTOM); + unsigned int oc_flags = GET_OID_COMMITTISH | GET_OID_RECORD_PATH; + + a_name = arg; + if (!*a_name) + a_name = "HEAD"; + + b_name = dotdot + 2; + if (*b_name == '.') { + symmetric = 1; + b_name++; + } + if (!*b_name) + b_name = "HEAD"; + + if (get_oid_with_context(revs->repo, a_name, oc_flags, &a_oid, a_oc) || + get_oid_with_context(revs->repo, b_name, oc_flags, &b_oid, b_oc)) + return -1; + + if (!cant_be_filename) { + *dotdot = '.'; + verify_non_filename(revs->prefix, arg); + *dotdot = '\0'; + } + + a_obj = parse_object(revs->repo, &a_oid); + b_obj = parse_object(revs->repo, &b_oid); + if (!a_obj || !b_obj) + return dotdot_missing(arg, dotdot, revs, symmetric); + + if (!symmetric) { + /* just A..B */ + b_flags = flags; + a_flags = flags_exclude; + } else { + /* A...B -- find merge bases between the two */ + struct commit *a, *b; + struct commit_list *exclude; + + a = lookup_commit_reference(revs->repo, &a_obj->oid); + b = lookup_commit_reference(revs->repo, &b_obj->oid); + if (!a || !b) + return dotdot_missing(arg, dotdot, revs, symmetric); + + exclude = get_merge_bases(a, b); + add_rev_cmdline_list(revs, exclude, REV_CMD_MERGE_BASE, + flags_exclude); + add_pending_commit_list(revs, exclude, flags_exclude); + free_commit_list(exclude); + + b_flags = flags; + a_flags = flags | SYMMETRIC_LEFT; + } + + a_obj->flags |= a_flags; + b_obj->flags |= b_flags; + add_rev_cmdline(revs, a_obj, a_name, REV_CMD_LEFT, a_flags); + add_rev_cmdline(revs, b_obj, b_name, REV_CMD_RIGHT, b_flags); + add_pending_object_with_path(revs, a_obj, a_name, a_oc->mode, a_oc->path); + add_pending_object_with_path(revs, b_obj, b_name, b_oc->mode, b_oc->path); + return 0; +} + +static int handle_dotdot(const char *arg, + struct rev_info *revs, int flags, + int cant_be_filename) +{ + struct object_context a_oc, b_oc; + char *dotdot = strstr(arg, ".."); + int ret; + + if (!dotdot) + return -1; + + memset(&a_oc, 0, sizeof(a_oc)); + memset(&b_oc, 0, sizeof(b_oc)); + + *dotdot = '\0'; + ret = handle_dotdot_1(arg, dotdot, revs, flags, cant_be_filename, + &a_oc, &b_oc); + *dotdot = '.'; + + free(a_oc.path); + free(b_oc.path); + + return ret; +} + +static int handle_revision_arg_1(const char *arg_, struct rev_info *revs, int flags, unsigned revarg_opt) { struct object_context oc; - char *dotdot; + char *mark; struct object *object; - unsigned char sha1[20]; + struct object_id oid; int local_flags; const char *arg = arg_; int cant_be_filename = revarg_opt & REVARG_CANNOT_BE_FILENAME; - unsigned get_sha1_flags = 0; - - dotdot = strstr(arg, ".."); - if (dotdot) { - unsigned char from_sha1[20]; - const char *next = dotdot + 2; - const char *this = arg; - int symmetric = *next == '.'; - unsigned int flags_exclude = flags ^ UNINTERESTING; - static const char head_by_default[] = "HEAD"; - unsigned int a_flags; - - *dotdot = 0; - next += symmetric; - - if (!*next) - next = head_by_default; - if (dotdot == arg) - this = head_by_default; - if (this == head_by_default && next == head_by_default && - !symmetric) { - /* - * Just ".."? That is not a range but the - * pathspec for the parent directory. - */ - if (!cant_be_filename) { - *dotdot = '.'; - return -1; - } - } - if (!get_sha1_committish(this, from_sha1) && - !get_sha1_committish(next, sha1)) { - struct commit *a, *b; - struct commit_list *exclude; - - a = lookup_commit_reference(from_sha1); - b = lookup_commit_reference(sha1); - if (!a || !b) { - if (revs->ignore_missing) - return 0; - die(symmetric ? - "Invalid symmetric difference expression %s...%s" : - "Invalid revision range %s..%s", - arg, next); - } + unsigned get_sha1_flags = GET_OID_RECORD_PATH; - if (!cant_be_filename) { - *dotdot = '.'; - verify_non_filename(revs->prefix, arg); - } + flags = flags & UNINTERESTING ? flags | BOTTOM : flags & ~BOTTOM; - if (symmetric) { - exclude = get_merge_bases(a, b, 1); - add_pending_commit_list(revs, exclude, - flags_exclude); - free_commit_list(exclude); - a_flags = flags | SYMMETRIC_LEFT; - } else - a_flags = flags_exclude; - a->object.flags |= a_flags; - b->object.flags |= flags; - add_rev_cmdline(revs, &a->object, this, - REV_CMD_LEFT, a_flags); - add_rev_cmdline(revs, &b->object, next, - REV_CMD_RIGHT, flags); - add_pending_object(revs, &a->object, this); - add_pending_object(revs, &b->object, next); - return 0; - } - *dotdot = '.'; + if (!cant_be_filename && !strcmp(arg, "..")) { + /* + * Just ".."? That is not a range but the + * pathspec for the parent directory. + */ + return -1; } - dotdot = strstr(arg, "^@"); - if (dotdot && !dotdot[2]) { - *dotdot = 0; - if (add_parents_only(revs, arg, flags)) + + if (!handle_dotdot(arg, revs, flags, revarg_opt)) + return 0; + + mark = strstr(arg, "^@"); + if (mark && !mark[2]) { + *mark = 0; + if (add_parents_only(revs, arg, flags, 0)) return 0; - *dotdot = '^'; + *mark = '^'; } - dotdot = strstr(arg, "^!"); - if (dotdot && !dotdot[2]) { - *dotdot = 0; - if (!add_parents_only(revs, arg, flags ^ UNINTERESTING)) - *dotdot = '^'; + mark = strstr(arg, "^!"); + if (mark && !mark[2]) { + *mark = 0; + if (!add_parents_only(revs, arg, flags ^ (UNINTERESTING | BOTTOM), 0)) + *mark = '^'; + } + mark = strstr(arg, "^-"); + if (mark) { + int exclude_parent = 1; + + if (mark[2]) { + char *end; + exclude_parent = strtoul(mark + 2, &end, 10); + if (*end != '\0' || !exclude_parent) + return -1; + } + + *mark = 0; + if (!add_parents_only(revs, arg, flags ^ (UNINTERESTING | BOTTOM), exclude_parent)) + *mark = '^'; } local_flags = 0; if (*arg == '^') { - local_flags = UNINTERESTING; + local_flags = UNINTERESTING | BOTTOM; arg++; } if (revarg_opt & REVARG_COMMITTISH) - get_sha1_flags = GET_SHA1_COMMITTISH; + get_sha1_flags |= GET_OID_COMMITTISH; - if (get_sha1_with_context(arg, get_sha1_flags, sha1, &oc)) + if (get_oid_with_context(revs->repo, arg, get_sha1_flags, &oid, &oc)) return revs->ignore_missing ? 0 : -1; if (!cant_be_filename) verify_non_filename(revs->prefix, arg); - object = get_reference(revs, arg, sha1, flags ^ local_flags); + object = get_reference(revs, arg, &oid, flags ^ local_flags); + if (!object) + return revs->ignore_missing ? 0 : -1; add_rev_cmdline(revs, object, arg_, REV_CMD_REV, flags ^ local_flags); - add_pending_object_with_mode(revs, object, arg, oc.mode); + add_pending_object_with_path(revs, object, arg, oc.mode, oc.path); + free(oc.path); return 0; } -struct cmdline_pathspec { - int alloc; - int nr; - const char **path; -}; - -static void append_prune_data(struct cmdline_pathspec *prune, const char **av) +int handle_revision_arg(const char *arg, struct rev_info *revs, int flags, unsigned revarg_opt) { - while (*av) { - ALLOC_GROW(prune->path, prune->nr+1, prune->alloc); - prune->path[prune->nr++] = *(av++); - } + int ret = handle_revision_arg_1(arg, revs, flags, revarg_opt); + if (!ret) + revs->rev_input_given = 1; + return ret; } -static void read_pathspec_from_stdin(struct rev_info *revs, struct strbuf *sb, - struct cmdline_pathspec *prune) +static void read_pathspec_from_stdin(struct strbuf *sb, + struct strvec *prune) { - while (strbuf_getwholeline(sb, stdin, '\n') != EOF) { - int len = sb->len; - if (len && sb->buf[len - 1] == '\n') - sb->buf[--len] = '\0'; - ALLOC_GROW(prune->path, prune->nr+1, prune->alloc); - prune->path[prune->nr++] = xstrdup(sb->buf); - } + while (strbuf_getline(sb, stdin) != EOF) + strvec_push(prune, sb->buf); } static void read_revisions_from_stdin(struct rev_info *revs, - struct cmdline_pathspec *prune) + struct strvec *prune) { struct strbuf sb; int seen_dashdash = 0; + int save_warning; + + save_warning = warn_on_object_refname_ambiguity; + warn_on_object_refname_ambiguity = 0; strbuf_init(&sb, 1000); - while (strbuf_getwholeline(&sb, stdin, '\n') != EOF) { + while (strbuf_getline(&sb, stdin) != EOF) { int len = sb.len; - if (len && sb.buf[len - 1] == '\n') - sb.buf[--len] = '\0'; if (!len) break; if (sb.buf[0] == '-') { @@ -1275,12 +2127,15 @@ static void read_revisions_from_stdin(struct rev_info *revs, } die("options not supported in --stdin mode"); } - if (handle_revision_arg(sb.buf, revs, 0, REVARG_CANNOT_BE_FILENAME)) + if (handle_revision_arg(sb.buf, revs, 0, + REVARG_CANNOT_BE_FILENAME)) die("bad revision '%s'", sb.buf); } if (seen_dashdash) - read_pathspec_from_stdin(revs, &sb, prune); + read_pathspec_from_stdin(&sb, prune); + strbuf_release(&sb); + warn_on_object_refname_ambiguity = save_warning; } static void add_grep(struct rev_info *revs, const char *ptn, enum grep_pat_token what) @@ -1299,20 +2154,25 @@ static void add_message_grep(struct rev_info *revs, const char *pattern) } static int handle_revision_opt(struct rev_info *revs, int argc, const char **argv, - int *unkc, const char **unkv) + int *unkc, const char **unkv, + const struct setup_revision_opt* opt) { const char *arg = argv[0]; const char *optarg; int argcount; + const unsigned hexsz = the_hash_algo->hexsz; /* pseudo revision arguments */ if (!strcmp(arg, "--all") || !strcmp(arg, "--branches") || !strcmp(arg, "--tags") || !strcmp(arg, "--remotes") || !strcmp(arg, "--reflog") || !strcmp(arg, "--not") || !strcmp(arg, "--no-walk") || !strcmp(arg, "--do-walk") || - !strcmp(arg, "--bisect") || !prefixcmp(arg, "--glob=") || - !prefixcmp(arg, "--branches=") || !prefixcmp(arg, "--tags=") || - !prefixcmp(arg, "--remotes=") || !prefixcmp(arg, "--no-walk=")) + !strcmp(arg, "--bisect") || starts_with(arg, "--glob=") || + !strcmp(arg, "--indexed-objects") || + !strcmp(arg, "--alternate-refs") || + starts_with(arg, "--exclude=") || + starts_with(arg, "--branches=") || starts_with(arg, "--tags=") || + starts_with(arg, "--remotes=") || starts_with(arg, "--no-walk=")) { unkv[(*unkc)++] = arg; return 1; @@ -1326,8 +2186,10 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg revs->skip_count = atoi(optarg); return argcount; } else if ((*arg == '-') && isdigit(arg[1])) { - /* accept -<digit>, like traditional "head" */ - revs->max_count = atoi(arg + 1); + /* accept -<digit>, like traditional "head" */ + if (strtol_i(arg + 1, 10, &revs->max_count) < 0 || + revs->max_count < 0) + die("'%s': not a non-negative integer", arg + 1); revs->no_walk = 0; } else if (!strcmp(arg, "-n")) { if (argc <= 1) @@ -1335,8 +2197,8 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg revs->max_count = atoi(argv[1]); revs->no_walk = 0; return 2; - } else if (!prefixcmp(arg, "-n")) { - revs->max_count = atoi(arg + 2); + } else if (skip_prefix(arg, "-n", &optarg)) { + revs->max_count = atoi(optarg); revs->no_walk = 0; } else if ((argcount = parse_long_opt("max-age", argv, &optarg))) { revs->max_age = atoi(optarg); @@ -1372,7 +2234,7 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg } else if (!strcmp(arg, "--merge")) { revs->show_merge = 1; } else if (!strcmp(arg, "--topo-order")) { - revs->lifo = 1; + revs->sort_order = REV_SORT_IN_GRAPH_ORDER; revs->topo_order = 1; } else if (!strcmp(arg, "--simplify-merges")) { revs->simplify_merges = 1; @@ -1388,20 +2250,19 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg revs->simplify_by_decoration = 1; revs->limited = 1; revs->prune = 1; - load_ref_decorations(DECORATE_SHORT_REFS); } else if (!strcmp(arg, "--date-order")) { - revs->lifo = 0; + revs->sort_order = REV_SORT_BY_COMMIT_DATE; + revs->topo_order = 1; + } else if (!strcmp(arg, "--author-date-order")) { + revs->sort_order = REV_SORT_BY_AUTHOR_DATE; + revs->topo_order = 1; + } else if (!strcmp(arg, "--early-output")) { + revs->early_output = 100; + revs->topo_order = 1; + } else if (skip_prefix(arg, "--early-output=", &optarg)) { + if (strtoul_ui(optarg, 10, &revs->early_output) < 0) + die("'%s': not a non-negative integer", optarg); revs->topo_order = 1; - } else if (!prefixcmp(arg, "--early-output")) { - int count = 100; - switch (arg[14]) { - case '=': - count = atoi(arg+15); - /* Fallthrough */ - case 0: - revs->topo_order = 1; - revs->early_output = count; - } } else if (!strcmp(arg, "--parents")) { revs->rewrite_parents = 1; revs->print_parents = 1; @@ -1409,21 +2270,21 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg revs->dense = 1; } else if (!strcmp(arg, "--sparse")) { revs->dense = 0; - } else if (!strcmp(arg, "--show-all")) { - revs->show_all = 1; + } else if (!strcmp(arg, "--in-commit-order")) { + revs->tree_blobs_in_commit_order = 1; } else if (!strcmp(arg, "--remove-empty")) { revs->remove_empty_trees = 1; } else if (!strcmp(arg, "--merges")) { revs->min_parents = 2; } else if (!strcmp(arg, "--no-merges")) { revs->max_parents = 1; - } else if (!prefixcmp(arg, "--min-parents=")) { - revs->min_parents = atoi(arg+14); - } else if (!prefixcmp(arg, "--no-min-parents")) { + } else if (skip_prefix(arg, "--min-parents=", &optarg)) { + revs->min_parents = atoi(optarg); + } else if (!strcmp(arg, "--no-min-parents")) { revs->min_parents = 0; - } else if (!prefixcmp(arg, "--max-parents=")) { - revs->max_parents = atoi(arg+14); - } else if (!prefixcmp(arg, "--no-max-parents")) { + } else if (skip_prefix(arg, "--max-parents=", &optarg)) { + revs->max_parents = atoi(optarg); + } else if (!strcmp(arg, "--no-max-parents")) { revs->max_parents = -1; } else if (!strcmp(arg, "--boundary")) { revs->boundary = 1; @@ -1466,6 +2327,12 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg revs->tree_objects = 1; revs->blob_objects = 1; revs->edge_hint = 1; + } else if (!strcmp(arg, "--objects-edge-aggressive")) { + revs->tag_objects = 1; + revs->tree_objects = 1; + revs->blob_objects = 1; + revs->edge_hint = 1; + revs->edge_hint_aggressive = 1; } else if (!strcmp(arg, "--verify-objects")) { revs->tag_objects = 1; revs->tree_objects = 1; @@ -1473,69 +2340,76 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg revs->verify_objects = 1; } else if (!strcmp(arg, "--unpacked")) { revs->unpacked = 1; - } else if (!prefixcmp(arg, "--unpacked=")) { - die("--unpacked=<packfile> no longer supported."); + } else if (starts_with(arg, "--unpacked=")) { + die(_("--unpacked=<packfile> no longer supported")); + } else if (!strcmp(arg, "--no-kept-objects")) { + revs->no_kept_objects = 1; + revs->keep_pack_cache_flags |= IN_CORE_KEEP_PACKS; + revs->keep_pack_cache_flags |= ON_DISK_KEEP_PACKS; + } else if (skip_prefix(arg, "--no-kept-objects=", &optarg)) { + revs->no_kept_objects = 1; + if (!strcmp(optarg, "in-core")) + revs->keep_pack_cache_flags |= IN_CORE_KEEP_PACKS; + if (!strcmp(optarg, "on-disk")) + revs->keep_pack_cache_flags |= ON_DISK_KEEP_PACKS; } else if (!strcmp(arg, "-r")) { revs->diff = 1; - DIFF_OPT_SET(&revs->diffopt, RECURSIVE); + revs->diffopt.flags.recursive = 1; } else if (!strcmp(arg, "-t")) { revs->diff = 1; - DIFF_OPT_SET(&revs->diffopt, RECURSIVE); - DIFF_OPT_SET(&revs->diffopt, TREE_IN_RECURSIVE); - } else if (!strcmp(arg, "-m")) { - revs->ignore_merges = 0; - } else if (!strcmp(arg, "-c")) { - revs->diff = 1; - revs->dense_combined_merges = 0; - revs->combine_merges = 1; - } else if (!strcmp(arg, "--cc")) { - revs->diff = 1; - revs->dense_combined_merges = 1; - revs->combine_merges = 1; + revs->diffopt.flags.recursive = 1; + revs->diffopt.flags.tree_in_recursive = 1; + } else if ((argcount = diff_merges_parse_opts(revs, argv))) { + return argcount; } else if (!strcmp(arg, "-v")) { revs->verbose_header = 1; } else if (!strcmp(arg, "--pretty")) { revs->verbose_header = 1; revs->pretty_given = 1; - get_commit_format(arg+8, revs); - } else if (!prefixcmp(arg, "--pretty=") || !prefixcmp(arg, "--format=")) { + get_commit_format(NULL, revs); + } else if (skip_prefix(arg, "--pretty=", &optarg) || + skip_prefix(arg, "--format=", &optarg)) { /* * Detached form ("--pretty X" as opposed to "--pretty=X") * not allowed, since the argument is optional. */ revs->verbose_header = 1; revs->pretty_given = 1; - get_commit_format(arg+9, revs); + get_commit_format(optarg, revs); + } else if (!strcmp(arg, "--expand-tabs")) { + revs->expand_tabs_in_log = 8; + } else if (!strcmp(arg, "--no-expand-tabs")) { + revs->expand_tabs_in_log = 0; + } else if (skip_prefix(arg, "--expand-tabs=", &arg)) { + int val; + if (strtol_i(arg, 10, &val) < 0 || val < 0) + die("'%s': not a non-negative integer", arg); + revs->expand_tabs_in_log = val; } else if (!strcmp(arg, "--show-notes") || !strcmp(arg, "--notes")) { - revs->show_notes = 1; + enable_default_display_notes(&revs->notes_opt, &revs->show_notes); revs->show_notes_given = 1; - revs->notes_opt.use_default_notes = 1; } else if (!strcmp(arg, "--show-signature")) { revs->show_signature = 1; - } else if (!prefixcmp(arg, "--show-notes=") || - !prefixcmp(arg, "--notes=")) { - struct strbuf buf = STRBUF_INIT; - revs->show_notes = 1; + } else if (!strcmp(arg, "--no-show-signature")) { + revs->show_signature = 0; + } else if (!strcmp(arg, "--show-linear-break")) { + revs->break_bar = " .........."; + revs->track_linear = 1; + revs->track_first_time = 1; + } else if (skip_prefix(arg, "--show-linear-break=", &optarg)) { + revs->break_bar = xstrdup(optarg); + revs->track_linear = 1; + revs->track_first_time = 1; + } else if (skip_prefix(arg, "--show-notes=", &optarg) || + skip_prefix(arg, "--notes=", &optarg)) { + if (starts_with(arg, "--show-notes=") && + revs->notes_opt.use_default_notes < 0) + revs->notes_opt.use_default_notes = 1; + enable_ref_display_notes(&revs->notes_opt, &revs->show_notes, optarg); revs->show_notes_given = 1; - if (!prefixcmp(arg, "--show-notes")) { - if (revs->notes_opt.use_default_notes < 0) - revs->notes_opt.use_default_notes = 1; - strbuf_addstr(&buf, arg+13); - } - else - strbuf_addstr(&buf, arg+8); - expand_notes_ref(&buf); - string_list_append(&revs->notes_opt.extra_notes_refs, - strbuf_detach(&buf, NULL)); } else if (!strcmp(arg, "--no-notes")) { - revs->show_notes = 0; + disable_display_notes(&revs->notes_opt, &revs->show_notes); revs->show_notes_given = 1; - revs->notes_opt.use_default_notes = -1; - /* we have been strdup'ing ourselves, so trick - * string_list into free()ing strings */ - revs->notes_opt.extra_notes_refs.strdup_strings = 1; - string_list_clear(&revs->notes_opt.extra_notes_refs, 0); - revs->notes_opt.extra_notes_refs.strdup_strings = 0; } else if (!strcmp(arg, "--standard-notes")) { revs->show_notes_given = 1; revs->notes_opt.use_default_notes = 1; @@ -1550,6 +2424,10 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg revs->topo_order = 1; revs->rewrite_parents = 1; revs->graph = graph_init(revs); + } else if (!strcmp(arg, "--encode-email-headers")) { + revs->encode_email_headers = 1; + } else if (!strcmp(arg, "--no-encode-email-headers")) { + revs->encode_email_headers = 0; } else if (!strcmp(arg, "--root")) { revs->show_root_diff = 1; } else if (!strcmp(arg, "--no-commit-id")) { @@ -1560,12 +2438,12 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg revs->abbrev = 0; } else if (!strcmp(arg, "--abbrev")) { revs->abbrev = DEFAULT_ABBREV; - } else if (!prefixcmp(arg, "--abbrev=")) { - revs->abbrev = strtoul(arg + 9, NULL, 10); + } else if (skip_prefix(arg, "--abbrev=", &optarg)) { + revs->abbrev = strtoul(optarg, NULL, 10); if (revs->abbrev < MINIMUM_ABBREV) revs->abbrev = MINIMUM_ABBREV; - else if (revs->abbrev > 40) - revs->abbrev = 40; + else if (revs->abbrev > hexsz) + revs->abbrev = hexsz; } else if (!strcmp(arg, "--abbrev-commit")) { revs->abbrev_commit = 1; revs->abbrev_commit_given = 1; @@ -1574,13 +2452,15 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg } else if (!strcmp(arg, "--full-diff")) { revs->diff = 1; revs->full_diff = 1; + } else if (!strcmp(arg, "--show-pulls")) { + revs->show_pulls = 1; } else if (!strcmp(arg, "--full-history")) { revs->simplify_history = 0; } else if (!strcmp(arg, "--relative-date")) { - revs->date_mode = DATE_RELATIVE; + revs->date_mode.type = DATE_RELATIVE; revs->date_mode_explicit = 1; } else if ((argcount = parse_long_opt("date", argv, &optarg))) { - revs->date_mode = parse_date_format(optarg); + parse_date_format(optarg, &revs->date_mode); revs->date_mode_explicit = 1; return argcount; } else if (!strcmp(arg, "--log-size")) { @@ -1601,21 +2481,21 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg } else if ((argcount = parse_long_opt("grep", argv, &optarg))) { add_message_grep(revs, optarg); return argcount; - } else if (!strcmp(arg, "--grep-debug")) { - revs->grep_filter.debug = 1; } else if (!strcmp(arg, "--basic-regexp")) { - grep_set_pattern_type_option(GREP_PATTERN_TYPE_BRE, &revs->grep_filter); + revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_BRE; } else if (!strcmp(arg, "--extended-regexp") || !strcmp(arg, "-E")) { - grep_set_pattern_type_option(GREP_PATTERN_TYPE_ERE, &revs->grep_filter); + revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_ERE; } else if (!strcmp(arg, "--regexp-ignore-case") || !strcmp(arg, "-i")) { - revs->grep_filter.regflags |= REG_ICASE; - DIFF_OPT_SET(&revs->diffopt, PICKAXE_IGNORE_CASE); + revs->grep_filter.ignore_case = 1; + revs->diffopt.pickaxe_opts |= DIFF_PICKAXE_IGNORE_CASE; } else if (!strcmp(arg, "--fixed-strings") || !strcmp(arg, "-F")) { - grep_set_pattern_type_option(GREP_PATTERN_TYPE_FIXED, &revs->grep_filter); - } else if (!strcmp(arg, "--perl-regexp")) { - grep_set_pattern_type_option(GREP_PATTERN_TYPE_PCRE, &revs->grep_filter); + revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_FIXED; + } else if (!strcmp(arg, "--perl-regexp") || !strcmp(arg, "-P")) { + revs->grep_filter.pattern_type_option = GREP_PATTERN_TYPE_PCRE; } else if (!strcmp(arg, "--all-match")) { revs->grep_filter.all_match = 1; + } else if (!strcmp(arg, "--invert-grep")) { + revs->invert_grep = 1; } else if ((argcount = parse_long_opt("encoding", argv, &optarg))) { if (strcmp(optarg, "none")) git_log_output_encoding = xstrdup(optarg); @@ -1629,12 +2509,19 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg revs->limited = 1; } else if (!strcmp(arg, "--ignore-missing")) { revs->ignore_missing = 1; + } else if (opt && opt->allow_exclude_promisor_objects && + !strcmp(arg, "--exclude-promisor-objects")) { + if (fetch_if_missing) + BUG("exclude_promisor_objects can only be used when fetch_if_missing is 0"); + revs->exclude_promisor_objects = 1; } else { - int opts = diff_opt_parse(&revs->diffopt, argv, argc); + int opts = diff_opt_parse(&revs->diffopt, argv, argc, revs->prefix); if (!opts) unkv[(*unkc)++] = arg; return opts; } + if (revs->graph && revs->track_linear) + die("--show-linear-break and --graph are incompatible"); return 1; } @@ -1644,7 +2531,7 @@ void parse_revision_opt(struct rev_info *revs, struct parse_opt_ctx_t *ctx, const char * const usagestr[]) { int n = handle_revision_opt(revs, ctx->argc, ctx->argv, - &ctx->cpidx, ctx->out); + &ctx->cpidx, ctx->out, NULL); if (n <= 0) { error("unknown option `%s'", ctx->argv[0]); usage_with_options(usagestr, options); @@ -1653,24 +2540,49 @@ void parse_revision_opt(struct rev_info *revs, struct parse_opt_ctx_t *ctx, ctx->argc -= n; } -static int for_each_bad_bisect_ref(const char *submodule, each_ref_fn fn, void *cb_data) +static int for_each_bisect_ref(struct ref_store *refs, each_ref_fn fn, + void *cb_data, const char *term) +{ + struct strbuf bisect_refs = STRBUF_INIT; + int status; + strbuf_addf(&bisect_refs, "refs/bisect/%s", term); + status = refs_for_each_fullref_in(refs, bisect_refs.buf, fn, cb_data, 0); + strbuf_release(&bisect_refs); + return status; +} + +static int for_each_bad_bisect_ref(struct ref_store *refs, each_ref_fn fn, void *cb_data) { - return for_each_ref_in_submodule(submodule, "refs/bisect/bad", fn, cb_data); + return for_each_bisect_ref(refs, fn, cb_data, term_bad); } -static int for_each_good_bisect_ref(const char *submodule, each_ref_fn fn, void *cb_data) +static int for_each_good_bisect_ref(struct ref_store *refs, each_ref_fn fn, void *cb_data) { - return for_each_ref_in_submodule(submodule, "refs/bisect/good", fn, cb_data); + return for_each_bisect_ref(refs, fn, cb_data, term_good); } static int handle_revision_pseudo_opt(const char *submodule, - struct rev_info *revs, - int argc, const char **argv, int *flags) + struct rev_info *revs, + const char **argv, int *flags) { const char *arg = argv[0]; const char *optarg; + struct ref_store *refs; int argcount; + if (submodule) { + /* + * We need some something like get_submodule_worktrees() + * before we can go through all worktrees of a submodule, + * .e.g with adding all HEADs from --all, which is not + * supported right now, so stick to single worktree. + */ + if (!revs->single_worktree) + BUG("--single-worktree cannot be used together with submodule"); + refs = get_submodule_ref_store(submodule); + } else + refs = get_main_ref_store(revs->repo); + /* * NOTE! * @@ -1682,54 +2594,79 @@ static int handle_revision_pseudo_opt(const char *submodule, * register it in the list at the top of handle_revision_opt. */ if (!strcmp(arg, "--all")) { - handle_refs(submodule, revs, *flags, for_each_ref_submodule); - handle_refs(submodule, revs, *flags, head_ref_submodule); + handle_refs(refs, revs, *flags, refs_for_each_ref); + handle_refs(refs, revs, *flags, refs_head_ref); + if (!revs->single_worktree) { + struct all_refs_cb cb; + + init_all_refs_cb(&cb, revs, *flags); + other_head_refs(handle_one_ref, &cb); + } + clear_ref_exclusion(&revs->ref_excludes); } else if (!strcmp(arg, "--branches")) { - handle_refs(submodule, revs, *flags, for_each_branch_ref_submodule); + handle_refs(refs, revs, *flags, refs_for_each_branch_ref); + clear_ref_exclusion(&revs->ref_excludes); } else if (!strcmp(arg, "--bisect")) { - handle_refs(submodule, revs, *flags, for_each_bad_bisect_ref); - handle_refs(submodule, revs, *flags ^ UNINTERESTING, for_each_good_bisect_ref); + read_bisect_terms(&term_bad, &term_good); + handle_refs(refs, revs, *flags, for_each_bad_bisect_ref); + handle_refs(refs, revs, *flags ^ (UNINTERESTING | BOTTOM), + for_each_good_bisect_ref); revs->bisect = 1; } else if (!strcmp(arg, "--tags")) { - handle_refs(submodule, revs, *flags, for_each_tag_ref_submodule); + handle_refs(refs, revs, *flags, refs_for_each_tag_ref); + clear_ref_exclusion(&revs->ref_excludes); } else if (!strcmp(arg, "--remotes")) { - handle_refs(submodule, revs, *flags, for_each_remote_ref_submodule); + handle_refs(refs, revs, *flags, refs_for_each_remote_ref); + clear_ref_exclusion(&revs->ref_excludes); } else if ((argcount = parse_long_opt("glob", argv, &optarg))) { struct all_refs_cb cb; init_all_refs_cb(&cb, revs, *flags); for_each_glob_ref(handle_one_ref, optarg, &cb); + clear_ref_exclusion(&revs->ref_excludes); + return argcount; + } else if ((argcount = parse_long_opt("exclude", argv, &optarg))) { + add_ref_exclusion(&revs->ref_excludes, optarg); return argcount; - } else if (!prefixcmp(arg, "--branches=")) { + } else if (skip_prefix(arg, "--branches=", &optarg)) { struct all_refs_cb cb; init_all_refs_cb(&cb, revs, *flags); - for_each_glob_ref_in(handle_one_ref, arg + 11, "refs/heads/", &cb); - } else if (!prefixcmp(arg, "--tags=")) { + for_each_glob_ref_in(handle_one_ref, optarg, "refs/heads/", &cb); + clear_ref_exclusion(&revs->ref_excludes); + } else if (skip_prefix(arg, "--tags=", &optarg)) { struct all_refs_cb cb; init_all_refs_cb(&cb, revs, *flags); - for_each_glob_ref_in(handle_one_ref, arg + 7, "refs/tags/", &cb); - } else if (!prefixcmp(arg, "--remotes=")) { + for_each_glob_ref_in(handle_one_ref, optarg, "refs/tags/", &cb); + clear_ref_exclusion(&revs->ref_excludes); + } else if (skip_prefix(arg, "--remotes=", &optarg)) { struct all_refs_cb cb; init_all_refs_cb(&cb, revs, *flags); - for_each_glob_ref_in(handle_one_ref, arg + 10, "refs/remotes/", &cb); + for_each_glob_ref_in(handle_one_ref, optarg, "refs/remotes/", &cb); + clear_ref_exclusion(&revs->ref_excludes); } else if (!strcmp(arg, "--reflog")) { - handle_reflog(revs, *flags); + add_reflogs_to_pending(revs, *flags); + } else if (!strcmp(arg, "--indexed-objects")) { + add_index_objects_to_pending(revs, *flags); + } else if (!strcmp(arg, "--alternate-refs")) { + add_alternate_refs_to_pending(revs, *flags); } else if (!strcmp(arg, "--not")) { - *flags ^= UNINTERESTING; + *flags ^= UNINTERESTING | BOTTOM; } else if (!strcmp(arg, "--no-walk")) { revs->no_walk = REVISION_WALK_NO_WALK_SORTED; - } else if (!prefixcmp(arg, "--no-walk=")) { + } else if (skip_prefix(arg, "--no-walk=", &optarg)) { /* * Detached form ("--no-walk X" as opposed to "--no-walk=X") * not allowed, since the argument is optional. */ - if (!strcmp(arg + 10, "sorted")) + if (!strcmp(optarg, "sorted")) revs->no_walk = REVISION_WALK_NO_WALK_SORTED; - else if (!strcmp(arg + 10, "unsorted")) + else if (!strcmp(optarg, "unsorted")) revs->no_walk = REVISION_WALK_NO_WALK_UNSORTED; else return error("invalid argument to --no-walk"); } else if (!strcmp(arg, "--do-walk")) { revs->no_walk = 0; + } else if (!strcmp(arg, "--single-worktree")) { + revs->single_worktree = 1; } else { return 0; } @@ -1737,6 +2674,20 @@ static int handle_revision_pseudo_opt(const char *submodule, return 1; } +static void NORETURN diagnose_missing_default(const char *def) +{ + int flags; + const char *refname; + + refname = resolve_ref_unsafe(def, 0, NULL, &flags); + if (!refname || !(flags & REF_ISSYMREF) || (flags & REF_ISBROKEN)) + die(_("your current branch appears to be broken")); + + skip_prefix(refname, "refs/heads/", &refname); + die(_("your current branch '%s' does not have any commits yet"), + refname); +} + /* * Parse revision information, filling in the "rev_info" structure, * and removing the used arguments from the argument list. @@ -1746,11 +2697,11 @@ static int handle_revision_pseudo_opt(const char *submodule, */ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct setup_revision_opt *opt) { - int i, flags, left, seen_dashdash, read_from_stdin, got_rev_arg = 0, revarg_opt; - struct cmdline_pathspec prune_data; + int i, flags, left, seen_dashdash, revarg_opt; + struct strvec prune_data = STRVEC_INIT; const char *submodule = NULL; + int seen_end_of_options = 0; - memset(&prune_data, 0, sizeof(prune_data)); if (opt) submodule = opt->submodule; @@ -1766,7 +2717,7 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s argv[i] = NULL; argc = i; if (argv[i + 1]) - append_prune_data(&prune_data, argv + i + 1); + strvec_pushv(&prune_data, argv + i + 1); seen_dashdash = 1; break; } @@ -1777,14 +2728,13 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s revarg_opt = opt ? opt->revarg_opt : 0; if (seen_dashdash) revarg_opt |= REVARG_CANNOT_BE_FILENAME; - read_from_stdin = 0; for (left = i = 1; i < argc; i++) { const char *arg = argv[i]; - if (*arg == '-') { + if (!seen_end_of_options && *arg == '-') { int opts; opts = handle_revision_pseudo_opt(submodule, - revs, argc - i, argv + i, + revs, argv + i, &flags); if (opts > 0) { i += opts - 1; @@ -1796,13 +2746,19 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s argv[left++] = arg; continue; } - if (read_from_stdin++) + if (revs->read_from_stdin++) die("--stdin given twice?"); read_revisions_from_stdin(revs, &prune_data); continue; } - opts = handle_revision_opt(revs, argc - i, argv + i, &left, argv); + if (!strcmp(arg, "--end-of-options")) { + seen_end_of_options = 1; + continue; + } + + opts = handle_revision_opt(revs, argc - i, argv + i, + &left, argv, opt); if (opts > 0) { i += opts - 1; continue; @@ -1827,11 +2783,9 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s for (j = i; j < argc; j++) verify_filename(revs->prefix, argv[j], j == i); - append_prune_data(&prune_data, argv + i); + strvec_pushv(&prune_data, argv + i); break; } - else - got_rev_arg = 1; } if (prune_data.nr) { @@ -1849,11 +2803,10 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s * call init_pathspec() to set revs->prune_data here. * } */ - ALLOC_GROW(prune_data.path, prune_data.nr+1, prune_data.alloc); - prune_data.path[prune_data.nr++] = NULL; - init_pathspec(&revs->prune_data, - get_pathspec(revs->prefix, prune_data.path)); + parse_pathspec(&revs->prune_data, 0, 0, + revs->prefix, prune_data.v); } + strvec_clear(&prune_data); if (revs->def == NULL) revs->def = opt ? opt->def : NULL; @@ -1861,13 +2814,13 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s opt->tweak(revs, opt); if (revs->show_merge) prepare_show_merge(revs); - if (revs->def && !revs->pending.nr && !got_rev_arg) { - unsigned char sha1[20]; + if (revs->def && !revs->pending.nr && !revs->rev_input_given) { + struct object_id oid; struct object *object; struct object_context oc; - if (get_sha1_with_context(revs->def, 0, sha1, &oc)) - die("bad default revision '%s'", revs->def); - object = get_reference(revs, revs->def, sha1, 0); + if (get_oid_with_context(revs->repo, revs->def, 0, &oid, &oc)) + diagnose_missing_default(revs->def); + object = get_reference(revs, revs->def, &oid, 0); add_pending_object_with_mode(revs, object, revs->def, oc.mode); } @@ -1876,33 +2829,49 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s revs->diff = 1; /* Pickaxe, diff-filter and rename following need diffs */ - if (revs->diffopt.pickaxe || + if ((revs->diffopt.pickaxe_opts & DIFF_PICKAXE_KINDS_MASK) || revs->diffopt.filter || - DIFF_OPT_TST(&revs->diffopt, FOLLOW_RENAMES)) + revs->diffopt.flags.follow_renames) revs->diff = 1; - if (revs->topo_order) + if (revs->diffopt.objfind) + revs->simplify_history = 0; + + if (revs->line_level_traverse) { + if (want_ancestry(revs)) + revs->limited = 1; + revs->topo_order = 1; + } + + if (revs->topo_order && !generation_numbers_enabled(the_repository)) revs->limited = 1; if (revs->prune_data.nr) { - diff_tree_setup_paths(revs->prune_data.raw, &revs->pruning); + copy_pathspec(&revs->pruning.pathspec, &revs->prune_data); /* Can't prune commits with rename following: the paths change.. */ - if (!DIFF_OPT_TST(&revs->diffopt, FOLLOW_RENAMES)) + if (!revs->diffopt.flags.follow_renames) revs->prune = 1; if (!revs->full_diff) - diff_tree_setup_paths(revs->prune_data.raw, &revs->diffopt); + copy_pathspec(&revs->diffopt.pathspec, + &revs->prune_data); } - if (revs->combine_merges) - revs->ignore_merges = 0; + + diff_merges_setup_revs(revs); + revs->diffopt.abbrev = revs->abbrev; + diff_setup_done(&revs->diffopt); grep_commit_pattern_type(GREP_PATTERN_TYPE_UNSPECIFIED, &revs->grep_filter); + if (!is_encoding_utf8(get_log_output_encoding())) + revs->grep_filter.ignore_locale = 1; compile_grep_patterns(&revs->grep_filter); if (revs->reverse && revs->reflog_info) die("cannot combine --reverse with --walk-reflogs"); + if (revs->reflog_info && revs->limited) + die("cannot combine --walk-reflogs with history-limiting options"); if (revs->rewrite_parents && revs->children.name) die("cannot combine --parents and --children"); @@ -1914,9 +2883,18 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s if (revs->reflog_info && revs->graph) die("cannot combine --walk-reflogs with --graph"); + if (revs->no_walk && revs->graph) + die("cannot combine --no-walk with --graph"); if (!revs->reflog_info && revs->grep_filter.use_reflog_filter) die("cannot use --grep-reflog without --walk-reflogs"); + if (revs->line_level_traverse && + (revs->diffopt.output_format & ~(DIFF_FORMAT_PATCH | DIFF_FORMAT_NO_OUTPUT))) + die(_("-L does not yet support diff formats besides -p and -s")); + + if (revs->expand_tabs_in_log < 0) + revs->expand_tabs_in_log = revs->expand_tabs_in_log_default; + return left; } @@ -1928,28 +2906,32 @@ static void add_child(struct rev_info *revs, struct commit *parent, struct commi l->next = add_decoration(&revs->children, &parent->object, l); } -static int remove_duplicate_parents(struct commit *commit) +static int remove_duplicate_parents(struct rev_info *revs, struct commit *commit) { + struct treesame_state *ts = lookup_decoration(&revs->treesame, &commit->object); struct commit_list **pp, *p; int surviving_parents; /* Examine existing parents while marking ones we have seen... */ pp = &commit->parents; + surviving_parents = 0; while ((p = *pp) != NULL) { struct commit *parent = p->item; if (parent->object.flags & TMP_MARK) { *pp = p->next; + if (ts) + compact_treesame(revs, commit, surviving_parents); continue; } parent->object.flags |= TMP_MARK; + surviving_parents++; pp = &p->next; } - /* count them while clearing the temporary mark */ - surviving_parents = 0; + /* clear the temporary mark */ for (p = commit->parents; p; p = p->next) { p->item->object.flags &= ~TMP_MARK; - surviving_parents++; } + /* no update_treesame() - removing duplicates can't affect TREESAME */ return surviving_parents; } @@ -1963,15 +2945,163 @@ static struct merge_simplify_state *locate_simplify_state(struct rev_info *revs, st = lookup_decoration(&revs->merge_simplification, &commit->object); if (!st) { - st = xcalloc(1, sizeof(*st)); + CALLOC_ARRAY(st, 1); add_decoration(&revs->merge_simplification, &commit->object, st); } return st; } +static int mark_redundant_parents(struct commit *commit) +{ + struct commit_list *h = reduce_heads(commit->parents); + int i = 0, marked = 0; + struct commit_list *po, *pn; + + /* Want these for sanity-checking only */ + int orig_cnt = commit_list_count(commit->parents); + int cnt = commit_list_count(h); + + /* + * Not ready to remove items yet, just mark them for now, based + * on the output of reduce_heads(). reduce_heads outputs the reduced + * set in its original order, so this isn't too hard. + */ + po = commit->parents; + pn = h; + while (po) { + if (pn && po->item == pn->item) { + pn = pn->next; + i++; + } else { + po->item->object.flags |= TMP_MARK; + marked++; + } + po=po->next; + } + + if (i != cnt || cnt+marked != orig_cnt) + die("mark_redundant_parents %d %d %d %d", orig_cnt, cnt, i, marked); + + free_commit_list(h); + + return marked; +} + +static int mark_treesame_root_parents(struct commit *commit) +{ + struct commit_list *p; + int marked = 0; + + for (p = commit->parents; p; p = p->next) { + struct commit *parent = p->item; + if (!parent->parents && (parent->object.flags & TREESAME)) { + parent->object.flags |= TMP_MARK; + marked++; + } + } + + return marked; +} + +/* + * Awkward naming - this means one parent we are TREESAME to. + * cf mark_treesame_root_parents: root parents that are TREESAME (to an + * empty tree). Better name suggestions? + */ +static int leave_one_treesame_to_parent(struct rev_info *revs, struct commit *commit) +{ + struct treesame_state *ts = lookup_decoration(&revs->treesame, &commit->object); + struct commit *unmarked = NULL, *marked = NULL; + struct commit_list *p; + unsigned n; + + for (p = commit->parents, n = 0; p; p = p->next, n++) { + if (ts->treesame[n]) { + if (p->item->object.flags & TMP_MARK) { + if (!marked) + marked = p->item; + } else { + if (!unmarked) { + unmarked = p->item; + break; + } + } + } + } + + /* + * If we are TREESAME to a marked-for-deletion parent, but not to any + * unmarked parents, unmark the first TREESAME parent. This is the + * parent that the default simplify_history==1 scan would have followed, + * and it doesn't make sense to omit that path when asking for a + * simplified full history. Retaining it improves the chances of + * understanding odd missed merges that took an old version of a file. + * + * Example: + * + * I--------*X A modified the file, but mainline merge X used + * \ / "-s ours", so took the version from I. X is + * `-*A--' TREESAME to I and !TREESAME to A. + * + * Default log from X would produce "I". Without this check, + * --full-history --simplify-merges would produce "I-A-X", showing + * the merge commit X and that it changed A, but not making clear that + * it had just taken the I version. With this check, the topology above + * is retained. + * + * Note that it is possible that the simplification chooses a different + * TREESAME parent from the default, in which case this test doesn't + * activate, and we _do_ drop the default parent. Example: + * + * I------X A modified the file, but it was reverted in B, + * \ / meaning mainline merge X is TREESAME to both + * *A-*B parents. + * + * Default log would produce "I" by following the first parent; + * --full-history --simplify-merges will produce "I-A-B". But this is a + * reasonable result - it presents a logical full history leading from + * I to X, and X is not an important merge. + */ + if (!unmarked && marked) { + marked->object.flags &= ~TMP_MARK; + return 1; + } + + return 0; +} + +static int remove_marked_parents(struct rev_info *revs, struct commit *commit) +{ + struct commit_list **pp, *p; + int nth_parent, removed = 0; + + pp = &commit->parents; + nth_parent = 0; + while ((p = *pp) != NULL) { + struct commit *parent = p->item; + if (parent->object.flags & TMP_MARK) { + parent->object.flags &= ~TMP_MARK; + *pp = p->next; + free(p); + removed++; + compact_treesame(revs, commit, nth_parent); + continue; + } + pp = &p->next; + nth_parent++; + } + + /* Removing parents can only increase TREESAMEness */ + if (removed && !(commit->object.flags & TREESAME)) + update_treesame(revs, commit); + + return nth_parent; +} + static struct commit_list **simplify_one(struct rev_info *revs, struct commit *commit, struct commit_list **tail) { struct commit_list *p; + struct commit *parent; struct merge_simplify_state *st, *pst; int cnt; @@ -2013,7 +3143,9 @@ static struct commit_list **simplify_one(struct rev_info *revs, struct commit *c } /* - * Rewrite our list of parents. + * Rewrite our list of parents. Note that this cannot + * affect our TREESAME flags in any way - a commit is + * always TREESAME to its simplification. */ for (p = commit->parents; p; p = p->next) { pst = locate_simplify_state(revs, p->item); @@ -2021,46 +3153,58 @@ static struct commit_list **simplify_one(struct rev_info *revs, struct commit *c if (revs->first_parent_only) break; } - if (!revs->first_parent_only) - cnt = remove_duplicate_parents(commit); - else + + if (revs->first_parent_only) cnt = 1; + else + cnt = remove_duplicate_parents(revs, commit); /* * It is possible that we are a merge and one side branch * does not have any commit that touches the given paths; - * in such a case, the immediate parents will be rewritten - * to different commits. + * in such a case, the immediate parent from that branch + * will be rewritten to be the merge base. * * o----X X: the commit we are looking at; * / / o: a commit that touches the paths; * ---o----' * - * Further reduce the parents by removing redundant parents. + * Further, a merge of an independent branch that doesn't + * touch the path will reduce to a treesame root parent: + * + * ----o----X X: the commit we are looking at; + * / o: a commit that touches the paths; + * r r: a root commit not touching the paths + * + * Detect and simplify both cases. */ if (1 < cnt) { - struct commit_list *h = reduce_heads(commit->parents); - cnt = commit_list_count(h); - free_commit_list(commit->parents); - commit->parents = h; + int marked = mark_redundant_parents(commit); + marked += mark_treesame_root_parents(commit); + if (marked) + marked -= leave_one_treesame_to_parent(revs, commit); + if (marked) + cnt = remove_marked_parents(revs, commit); } /* * A commit simplifies to itself if it is a root, if it is * UNINTERESTING, if it touches the given paths, or if it is a - * merge and its parents simplifies to more than one commits + * merge and its parents don't simplify to one relevant commit * (the first two cases are already handled at the beginning of * this function). * - * Otherwise, it simplifies to what its sole parent simplifies to. + * Otherwise, it simplifies to what its sole relevant parent + * simplifies to. */ if (!cnt || (commit->object.flags & UNINTERESTING) || !(commit->object.flags & TREESAME) || - (1 < cnt)) + (parent = one_relevant_parent(revs, commit->parents)) == NULL || + (revs->show_pulls && (commit->object.flags & PULL_MERGE))) st->simplified = commit; else { - pst = locate_simplify_state(revs, commit->parents->item); + pst = locate_simplify_state(revs, parent); st->simplified = pst->simplified; } return tail; @@ -2091,10 +3235,7 @@ static void simplify_merges(struct rev_info *revs) yet_to_do = NULL; tail = &yet_to_do; while (list) { - commit = list->item; - next = list->next; - free(list); - list = next; + commit = pop_commit(&list); tail = simplify_one(revs, commit, tail); } } @@ -2106,10 +3247,7 @@ static void simplify_merges(struct rev_info *revs) while (list) { struct merge_simplify_state *st; - commit = list->item; - next = list->next; - free(list); - list = next; + commit = pop_commit(&list); st = locate_simplify_state(revs, commit); if (st->simplified == commit) tail = &commit_list_insert(commit, tail)->next; @@ -2130,81 +3268,403 @@ static void set_children(struct rev_info *revs) void reset_revision_walk(void) { - clear_object_flags(SEEN | ADDED | SHOWN); + clear_object_flags(SEEN | ADDED | SHOWN | TOPO_WALK_EXPLORED | TOPO_WALK_INDEGREE); +} + +static int mark_uninteresting(const struct object_id *oid, + struct packed_git *pack, + uint32_t pos, + void *cb) +{ + struct rev_info *revs = cb; + struct object *o = lookup_unknown_object(revs->repo, oid); + o->flags |= UNINTERESTING | SEEN; + return 0; +} + +define_commit_slab(indegree_slab, int); +define_commit_slab(author_date_slab, timestamp_t); + +struct topo_walk_info { + timestamp_t min_generation; + struct prio_queue explore_queue; + struct prio_queue indegree_queue; + struct prio_queue topo_queue; + struct indegree_slab indegree; + struct author_date_slab author_date; +}; + +static int topo_walk_atexit_registered; +static unsigned int count_explore_walked; +static unsigned int count_indegree_walked; +static unsigned int count_topo_walked; + +static void trace2_topo_walk_statistics_atexit(void) +{ + struct json_writer jw = JSON_WRITER_INIT; + + jw_object_begin(&jw, 0); + jw_object_intmax(&jw, "count_explore_walked", count_explore_walked); + jw_object_intmax(&jw, "count_indegree_walked", count_indegree_walked); + jw_object_intmax(&jw, "count_topo_walked", count_topo_walked); + jw_end(&jw); + + trace2_data_json("topo_walk", the_repository, "statistics", &jw); + + jw_release(&jw); +} + +static inline void test_flag_and_insert(struct prio_queue *q, struct commit *c, int flag) +{ + if (c->object.flags & flag) + return; + + c->object.flags |= flag; + prio_queue_put(q, c); +} + +static void explore_walk_step(struct rev_info *revs) +{ + struct topo_walk_info *info = revs->topo_walk_info; + struct commit_list *p; + struct commit *c = prio_queue_get(&info->explore_queue); + + if (!c) + return; + + if (repo_parse_commit_gently(revs->repo, c, 1) < 0) + return; + + count_explore_walked++; + + if (revs->sort_order == REV_SORT_BY_AUTHOR_DATE) + record_author_date(&info->author_date, c); + + if (revs->max_age != -1 && (c->date < revs->max_age)) + c->object.flags |= UNINTERESTING; + + if (process_parents(revs, c, NULL, NULL) < 0) + return; + + if (c->object.flags & UNINTERESTING) + mark_parents_uninteresting(c); + + for (p = c->parents; p; p = p->next) + test_flag_and_insert(&info->explore_queue, p->item, TOPO_WALK_EXPLORED); +} + +static void explore_to_depth(struct rev_info *revs, + timestamp_t gen_cutoff) +{ + struct topo_walk_info *info = revs->topo_walk_info; + struct commit *c; + while ((c = prio_queue_peek(&info->explore_queue)) && + commit_graph_generation(c) >= gen_cutoff) + explore_walk_step(revs); +} + +static void indegree_walk_step(struct rev_info *revs) +{ + struct commit_list *p; + struct topo_walk_info *info = revs->topo_walk_info; + struct commit *c = prio_queue_get(&info->indegree_queue); + + if (!c) + return; + + if (repo_parse_commit_gently(revs->repo, c, 1) < 0) + return; + + count_indegree_walked++; + + explore_to_depth(revs, commit_graph_generation(c)); + + for (p = c->parents; p; p = p->next) { + struct commit *parent = p->item; + int *pi = indegree_slab_at(&info->indegree, parent); + + if (repo_parse_commit_gently(revs->repo, parent, 1) < 0) + return; + + if (*pi) + (*pi)++; + else + *pi = 2; + + test_flag_and_insert(&info->indegree_queue, parent, TOPO_WALK_INDEGREE); + + if (revs->first_parent_only) + return; + } +} + +static void compute_indegrees_to_depth(struct rev_info *revs, + timestamp_t gen_cutoff) +{ + struct topo_walk_info *info = revs->topo_walk_info; + struct commit *c; + while ((c = prio_queue_peek(&info->indegree_queue)) && + commit_graph_generation(c) >= gen_cutoff) + indegree_walk_step(revs); +} + +static void reset_topo_walk(struct rev_info *revs) +{ + struct topo_walk_info *info = revs->topo_walk_info; + + clear_prio_queue(&info->explore_queue); + clear_prio_queue(&info->indegree_queue); + clear_prio_queue(&info->topo_queue); + clear_indegree_slab(&info->indegree); + clear_author_date_slab(&info->author_date); + + FREE_AND_NULL(revs->topo_walk_info); +} + +static void init_topo_walk(struct rev_info *revs) +{ + struct topo_walk_info *info; + struct commit_list *list; + if (revs->topo_walk_info) + reset_topo_walk(revs); + + revs->topo_walk_info = xmalloc(sizeof(struct topo_walk_info)); + info = revs->topo_walk_info; + memset(info, 0, sizeof(struct topo_walk_info)); + + init_indegree_slab(&info->indegree); + memset(&info->explore_queue, 0, sizeof(info->explore_queue)); + memset(&info->indegree_queue, 0, sizeof(info->indegree_queue)); + memset(&info->topo_queue, 0, sizeof(info->topo_queue)); + + switch (revs->sort_order) { + default: /* REV_SORT_IN_GRAPH_ORDER */ + info->topo_queue.compare = NULL; + break; + case REV_SORT_BY_COMMIT_DATE: + info->topo_queue.compare = compare_commits_by_commit_date; + break; + case REV_SORT_BY_AUTHOR_DATE: + init_author_date_slab(&info->author_date); + info->topo_queue.compare = compare_commits_by_author_date; + info->topo_queue.cb_data = &info->author_date; + break; + } + + info->explore_queue.compare = compare_commits_by_gen_then_commit_date; + info->indegree_queue.compare = compare_commits_by_gen_then_commit_date; + + info->min_generation = GENERATION_NUMBER_INFINITY; + for (list = revs->commits; list; list = list->next) { + struct commit *c = list->item; + timestamp_t generation; + + if (repo_parse_commit_gently(revs->repo, c, 1)) + continue; + + test_flag_and_insert(&info->explore_queue, c, TOPO_WALK_EXPLORED); + test_flag_and_insert(&info->indegree_queue, c, TOPO_WALK_INDEGREE); + + generation = commit_graph_generation(c); + if (generation < info->min_generation) + info->min_generation = generation; + + *(indegree_slab_at(&info->indegree, c)) = 1; + + if (revs->sort_order == REV_SORT_BY_AUTHOR_DATE) + record_author_date(&info->author_date, c); + } + compute_indegrees_to_depth(revs, info->min_generation); + + for (list = revs->commits; list; list = list->next) { + struct commit *c = list->item; + + if (*(indegree_slab_at(&info->indegree, c)) == 1) + prio_queue_put(&info->topo_queue, c); + } + + /* + * This is unfortunate; the initial tips need to be shown + * in the order given from the revision traversal machinery. + */ + if (revs->sort_order == REV_SORT_IN_GRAPH_ORDER) + prio_queue_reverse(&info->topo_queue); + + if (trace2_is_enabled() && !topo_walk_atexit_registered) { + atexit(trace2_topo_walk_statistics_atexit); + topo_walk_atexit_registered = 1; + } +} + +static struct commit *next_topo_commit(struct rev_info *revs) +{ + struct commit *c; + struct topo_walk_info *info = revs->topo_walk_info; + + /* pop next off of topo_queue */ + c = prio_queue_get(&info->topo_queue); + + if (c) + *(indegree_slab_at(&info->indegree, c)) = 0; + + return c; +} + +static void expand_topo_walk(struct rev_info *revs, struct commit *commit) +{ + struct commit_list *p; + struct topo_walk_info *info = revs->topo_walk_info; + if (process_parents(revs, commit, NULL, NULL) < 0) { + if (!revs->ignore_missing_links) + die("Failed to traverse parents of commit %s", + oid_to_hex(&commit->object.oid)); + } + + count_topo_walked++; + + for (p = commit->parents; p; p = p->next) { + struct commit *parent = p->item; + int *pi; + timestamp_t generation; + + if (parent->object.flags & UNINTERESTING) + continue; + + if (repo_parse_commit_gently(revs->repo, parent, 1) < 0) + continue; + + generation = commit_graph_generation(parent); + if (generation < info->min_generation) { + info->min_generation = generation; + compute_indegrees_to_depth(revs, info->min_generation); + } + + pi = indegree_slab_at(&info->indegree, parent); + + (*pi)--; + if (*pi == 1) + prio_queue_put(&info->topo_queue, parent); + + if (revs->first_parent_only) + return; + } } int prepare_revision_walk(struct rev_info *revs) { - int nr = revs->pending.nr; - struct object_array_entry *e, *list; + int i; + struct object_array old_pending; struct commit_list **next = &revs->commits; - e = list = revs->pending.objects; + memcpy(&old_pending, &revs->pending, sizeof(old_pending)); revs->pending.nr = 0; revs->pending.alloc = 0; revs->pending.objects = NULL; - while (--nr >= 0) { - struct commit *commit = handle_commit(revs, e->item, e->name); + for (i = 0; i < old_pending.nr; i++) { + struct object_array_entry *e = old_pending.objects + i; + struct commit *commit = handle_commit(revs, e); if (commit) { if (!(commit->object.flags & SEEN)) { commit->object.flags |= SEEN; next = commit_list_append(commit, next); } } - e++; } - if (!revs->leak_pending) - free(list); + object_array_clear(&old_pending); + + /* Signal whether we need per-parent treesame decoration */ + if (revs->simplify_merges || + (revs->limited && limiting_can_increase_treesame(revs))) + revs->treesame.name = "treesame"; + + if (revs->exclude_promisor_objects) { + for_each_packed_object(mark_uninteresting, revs, + FOR_EACH_OBJECT_PROMISOR_ONLY); + } + if (!revs->reflog_info) + prepare_to_use_bloom_filter(revs); if (revs->no_walk != REVISION_WALK_NO_WALK_UNSORTED) commit_list_sort_by_date(&revs->commits); if (revs->no_walk) return 0; - if (revs->limited) + if (revs->limited) { if (limit_list(revs) < 0) return -1; - if (revs->topo_order) - sort_in_topological_order(&revs->commits, revs->lifo); + if (revs->topo_order) + sort_in_topological_order(&revs->commits, revs->sort_order); + } else if (revs->topo_order) + init_topo_walk(revs); + if (revs->line_level_traverse && want_ancestry(revs)) + /* + * At the moment we can only do line-level log with parent + * rewriting by performing this expensive pre-filtering step. + * If parent rewriting is not requested, then we rather + * perform the line-level log filtering during the regular + * history traversal. + */ + line_log_filter(revs); if (revs->simplify_merges) simplify_merges(revs); if (revs->children.name) set_children(revs); + return 0; } -enum rewrite_result { - rewrite_one_ok, - rewrite_one_noparents, - rewrite_one_error -}; - -static enum rewrite_result rewrite_one(struct rev_info *revs, struct commit **pp) +static enum rewrite_result rewrite_one_1(struct rev_info *revs, + struct commit **pp, + struct prio_queue *queue) { - struct commit_list *cache = NULL; - for (;;) { struct commit *p = *pp; if (!revs->limited) - if (add_parents_to_list(revs, p, &revs->commits, &cache) < 0) + if (process_parents(revs, p, NULL, queue) < 0) return rewrite_one_error; - if (p->parents && p->parents->next) - return rewrite_one_ok; if (p->object.flags & UNINTERESTING) return rewrite_one_ok; if (!(p->object.flags & TREESAME)) return rewrite_one_ok; if (!p->parents) return rewrite_one_noparents; - *pp = p->parents->item; + if ((p = one_relevant_parent(revs, p->parents)) == NULL) + return rewrite_one_ok; + *pp = p; } } -static int rewrite_parents(struct rev_info *revs, struct commit *commit) +static void merge_queue_into_list(struct prio_queue *q, struct commit_list **list) +{ + while (q->nr) { + struct commit *item = prio_queue_peek(q); + struct commit_list *p = *list; + + if (p && p->item->date >= item->date) + list = &p->next; + else { + p = commit_list_insert(item, list); + list = &p->next; /* skip newly added item */ + prio_queue_get(q); /* pop item */ + } + } +} + +static enum rewrite_result rewrite_one(struct rev_info *revs, struct commit **pp) +{ + struct prio_queue queue = { compare_commits_by_commit_date }; + enum rewrite_result ret = rewrite_one_1(revs, pp, &queue); + merge_queue_into_list(&queue, &revs->commits); + clear_prio_queue(&queue); + return ret; +} + +int rewrite_parents(struct rev_info *revs, struct commit *commit, + rewrite_parent_fn_t rewrite_parent) { struct commit_list **pp = &commit->parents; while (*pp) { struct commit_list *parent = *pp; - switch (rewrite_one(revs, &parent->item)) { + switch (rewrite_parent(revs, &parent->item)) { case rewrite_one_ok: break; case rewrite_one_noparents: @@ -2215,14 +3675,62 @@ static int rewrite_parents(struct rev_info *revs, struct commit *commit) } pp = &parent->next; } - remove_duplicate_parents(commit); + remove_duplicate_parents(revs, commit); + return 0; +} + +static int commit_rewrite_person(struct strbuf *buf, const char *what, struct string_list *mailmap) +{ + char *person, *endp; + size_t len, namelen, maillen; + const char *name; + const char *mail; + struct ident_split ident; + + person = strstr(buf->buf, what); + if (!person) + return 0; + + person += strlen(what); + endp = strchr(person, '\n'); + if (!endp) + return 0; + + len = endp - person; + + if (split_ident_line(&ident, person, len)) + return 0; + + mail = ident.mail_begin; + maillen = ident.mail_end - ident.mail_begin; + name = ident.name_begin; + namelen = ident.name_end - ident.name_begin; + + if (map_user(mailmap, &mail, &maillen, &name, &namelen)) { + struct strbuf namemail = STRBUF_INIT; + + strbuf_addf(&namemail, "%.*s <%.*s>", + (int)namelen, name, (int)maillen, mail); + + strbuf_splice(buf, ident.name_begin - buf->buf, + ident.mail_end - ident.name_begin + 1, + namemail.buf, namemail.len); + + strbuf_release(&namemail); + + return 1; + } + return 0; } static int commit_match(struct commit *commit, struct rev_info *opt) { int retval; + const char *encoding; + const char *message; struct strbuf buf = STRBUF_INIT; + if (!opt->grep_filter.pattern_list && !opt->grep_filter.header_list) return 1; @@ -2233,50 +3741,104 @@ static int commit_match(struct commit *commit, struct rev_info *opt) strbuf_addch(&buf, '\n'); } + /* + * We grep in the user's output encoding, under the assumption that it + * is the encoding they are most likely to write their grep pattern + * for. In addition, it means we will match the "notes" encoding below, + * so we will not end up with a buffer that has two different encodings + * in it. + */ + encoding = get_log_output_encoding(); + message = logmsg_reencode(commit, NULL, encoding); + /* Copy the commit to temporary if we are using "fake" headers */ if (buf.len) - strbuf_addstr(&buf, commit->buffer); + strbuf_addstr(&buf, message); + + if (opt->grep_filter.header_list && opt->mailmap) { + if (!buf.len) + strbuf_addstr(&buf, message); + + commit_rewrite_person(&buf, "\nauthor ", opt->mailmap); + commit_rewrite_person(&buf, "\ncommitter ", opt->mailmap); + } /* Append "fake" message parts as needed */ if (opt->show_notes) { if (!buf.len) - strbuf_addstr(&buf, commit->buffer); - format_display_notes(commit->object.sha1, &buf, - get_log_output_encoding(), 1); + strbuf_addstr(&buf, message); + format_display_notes(&commit->object.oid, &buf, encoding, 1); } - /* Find either in the commit object, or in the temporary */ + /* + * Find either in the original commit message, or in the temporary. + * Note that we cast away the constness of "message" here. It is + * const because it may come from the cached commit buffer. That's OK, + * because we know that it is modifiable heap memory, and that while + * grep_buffer may modify it for speed, it will restore any + * changes before returning. + */ if (buf.len) retval = grep_buffer(&opt->grep_filter, buf.buf, buf.len); else retval = grep_buffer(&opt->grep_filter, - commit->buffer, strlen(commit->buffer)); + (char *)message, strlen(message)); strbuf_release(&buf); - return retval; + unuse_commit_buffer(commit, message); + return opt->invert_grep ? !retval : retval; } -static inline int want_ancestry(struct rev_info *revs) +static inline int want_ancestry(const struct rev_info *revs) { return (revs->rewrite_parents || revs->children.name); } +/* + * Return a timestamp to be used for --since/--until comparisons for this + * commit, based on the revision options. + */ +static timestamp_t comparison_date(const struct rev_info *revs, + struct commit *commit) +{ + return revs->reflog_info ? + get_reflog_timestamp(revs->reflog_info) : + commit->date; +} + enum commit_action get_commit_action(struct rev_info *revs, struct commit *commit) { if (commit->object.flags & SHOWN) return commit_ignore; - if (revs->unpacked && has_sha1_pack(commit->object.sha1)) + if (revs->unpacked && has_object_pack(&commit->object.oid)) return commit_ignore; - if (revs->show_all) - return commit_show; + if (revs->no_kept_objects) { + if (has_object_kept_pack(&commit->object.oid, + revs->keep_pack_cache_flags)) + return commit_ignore; + } if (commit->object.flags & UNINTERESTING) return commit_ignore; - if (revs->min_age != -1 && (commit->date > revs->min_age)) - return commit_ignore; + if (revs->line_level_traverse && !want_ancestry(revs)) { + /* + * In case of line-level log with parent rewriting + * prepare_revision_walk() already took care of all line-level + * log filtering, and there is nothing left to do here. + * + * If parent rewriting was not requested, then this is the + * place to perform the line-level log filtering. Notably, + * this check, though expensive, must come before the other, + * cheaper filtering conditions, because the tracked line + * ranges must be adjusted even when the commit will end up + * being ignored based on other conditions. + */ + if (!line_log_process_ranges_arbitrary_commit(revs, commit)) + return commit_ignore; + } + if (revs->min_age != -1 && + comparison_date(revs, commit) > revs->min_age) + return commit_ignore; if (revs->min_parents || (revs->max_parents >= 0)) { - int n = 0; - struct commit_list *p; - for (p = commit->parents; p; p = p->next) - n++; + int n = commit_list_count(commit->parents); if ((n < revs->min_parents) || ((revs->max_parents >= 0) && (n > revs->max_parents))) return commit_ignore; @@ -2286,46 +3848,145 @@ enum commit_action get_commit_action(struct rev_info *revs, struct commit *commi if (revs->prune && revs->dense) { /* Commit without changes? */ if (commit->object.flags & TREESAME) { + int n; + struct commit_list *p; /* drop merges unless we want parenthood */ if (!want_ancestry(revs)) return commit_ignore; - /* non-merge - always ignore it */ - if (!commit->parents || !commit->parents->next) - return commit_ignore; + + if (revs->show_pulls && (commit->object.flags & PULL_MERGE)) + return commit_show; + + /* + * If we want ancestry, then need to keep any merges + * between relevant commits to tie together topology. + * For consistency with TREESAME and simplification + * use "relevant" here rather than just INTERESTING, + * to treat bottom commit(s) as part of the topology. + */ + for (n = 0, p = commit->parents; p; p = p->next) + if (relevant_commit(p->item)) + if (++n >= 2) + return commit_show; + return commit_ignore; } } return commit_show; } +define_commit_slab(saved_parents, struct commit_list *); + +#define EMPTY_PARENT_LIST ((struct commit_list *)-1) + +/* + * You may only call save_parents() once per commit (this is checked + * for non-root commits). + */ +static void save_parents(struct rev_info *revs, struct commit *commit) +{ + struct commit_list **pp; + + if (!revs->saved_parents_slab) { + revs->saved_parents_slab = xmalloc(sizeof(struct saved_parents)); + init_saved_parents(revs->saved_parents_slab); + } + + pp = saved_parents_at(revs->saved_parents_slab, commit); + + /* + * When walking with reflogs, we may visit the same commit + * several times: once for each appearance in the reflog. + * + * In this case, save_parents() will be called multiple times. + * We want to keep only the first set of parents. We need to + * store a sentinel value for an empty (i.e., NULL) parent + * list to distinguish it from a not-yet-saved list, however. + */ + if (*pp) + return; + if (commit->parents) + *pp = copy_commit_list(commit->parents); + else + *pp = EMPTY_PARENT_LIST; +} + +static void free_saved_parents(struct rev_info *revs) +{ + if (revs->saved_parents_slab) + clear_saved_parents(revs->saved_parents_slab); +} + +struct commit_list *get_saved_parents(struct rev_info *revs, const struct commit *commit) +{ + struct commit_list *parents; + + if (!revs->saved_parents_slab) + return commit->parents; + + parents = *saved_parents_at(revs->saved_parents_slab, commit); + if (parents == EMPTY_PARENT_LIST) + return NULL; + return parents; +} + enum commit_action simplify_commit(struct rev_info *revs, struct commit *commit) { enum commit_action action = get_commit_action(revs, commit); if (action == commit_show && - !revs->show_all && revs->prune && revs->dense && want_ancestry(revs)) { - if (rewrite_parents(revs, commit) < 0) + /* + * --full-diff on simplified parents is no good: it + * will show spurious changes from the commits that + * were elided. So we save the parents on the side + * when --full-diff is in effect. + */ + if (revs->full_diff) + save_parents(revs, commit); + if (rewrite_parents(revs, commit, rewrite_one) < 0) return commit_error; } return action; } +static void track_linear(struct rev_info *revs, struct commit *commit) +{ + if (revs->track_first_time) { + revs->linear = 1; + revs->track_first_time = 0; + } else { + struct commit_list *p; + for (p = revs->previous_parents; p; p = p->next) + if (p->item == NULL || /* first commit */ + oideq(&p->item->object.oid, &commit->object.oid)) + break; + revs->linear = p != NULL; + } + if (revs->reverse) { + if (revs->linear) + commit->object.flags |= TRACK_LINEAR; + } + free_commit_list(revs->previous_parents); + revs->previous_parents = copy_commit_list(commit->parents); +} + static struct commit *get_revision_1(struct rev_info *revs) { - if (!revs->commits) - return NULL; + while (1) { + struct commit *commit; - do { - struct commit_list *entry = revs->commits; - struct commit *commit = entry->item; + if (revs->reflog_info) + commit = next_reflog_entry(revs->reflog_info); + else if (revs->topo_walk_info) + commit = next_topo_commit(revs); + else + commit = pop_commit(&revs->commits); - revs->commits = entry->next; - free(entry); + if (!commit) + return NULL; - if (revs->reflog_info) { - fake_reflog_parent(revs->reflog_info, commit); + if (revs->reflog_info) commit->object.flags &= ~(ADDED | SEEN | SHOWN); - } /* * If we haven't done the list limiting, we need to look at @@ -2334,11 +3995,18 @@ static struct commit *get_revision_1(struct rev_info *revs) */ if (!revs->limited) { if (revs->max_age != -1 && - (commit->date < revs->max_age)) + comparison_date(revs, commit) < revs->max_age) continue; - if (add_parents_to_list(revs, commit, &revs->commits, NULL) < 0) - die("Failed to traverse parents of commit %s", - sha1_to_hex(commit->object.sha1)); + + if (revs->reflog_info) + try_to_simplify_commit(revs, commit); + else if (revs->topo_walk_info) + expand_topo_walk(revs, commit); + else if (process_parents(revs, commit, &revs->commits, NULL) < 0) { + if (!revs->ignore_missing_links) + die("Failed to traverse parents of commit %s", + oid_to_hex(&commit->object.oid)); + } } switch (simplify_commit(revs, commit)) { @@ -2346,33 +4014,32 @@ static struct commit *get_revision_1(struct rev_info *revs) continue; case commit_error: die("Failed to simplify parents of commit %s", - sha1_to_hex(commit->object.sha1)); + oid_to_hex(&commit->object.oid)); default: + if (revs->track_linear) + track_linear(revs, commit); return commit; } - } while (revs->commits); - return NULL; + } } -static void gc_boundary(struct object_array *array) +/* + * Return true for entries that have not yet been shown. (This is an + * object_array_each_func_t.) + */ +static int entry_unshown(struct object_array_entry *entry, void *cb_data_unused) { - unsigned nr = array->nr; - unsigned alloc = array->alloc; - struct object_array_entry *objects = array->objects; + return !(entry->item->flags & SHOWN); +} - if (alloc <= nr) { - unsigned i, j; - for (i = j = 0; i < nr; i++) { - if (objects[i].item->flags & SHOWN) - continue; - if (i != j) - objects[j] = objects[i]; - j++; - } - for (i = j; i < nr; i++) - objects[i].item = NULL; - array->nr = j; - } +/* + * If array is on the verge of a realloc, garbage-collect any entries + * that have already been shown to try to free up some space. + */ +static void gc_boundary(struct object_array *array) +{ + if (array->nr == array->alloc) + object_array_filter(array, entry_unshown, NULL); } static void create_boundary_commit_list(struct rev_info *revs) @@ -2413,7 +4080,7 @@ static void create_boundary_commit_list(struct rev_info *revs) * If revs->topo_order is set, sort the boundary commits * in topological order */ - sort_in_topological_order(&revs->commits, revs->lifo); + sort_in_topological_order(&revs->commits, revs->sort_order); } static struct commit *get_revision_internal(struct rev_info *revs) @@ -2447,7 +4114,7 @@ static struct commit *get_revision_internal(struct rev_info *revs) if (revs->max_count) { c = get_revision_1(revs); if (c) { - while (0 < revs->skip_count) { + while (revs->skip_count > 0) { revs->skip_count--; c = get_revision_1(revs); if (!c) @@ -2462,9 +4129,8 @@ static struct commit *get_revision_internal(struct rev_info *revs) if (c) c->object.flags |= SHOWN; - if (!revs->boundary) { + if (!revs->boundary) return c; - } if (!c) { /* @@ -2510,24 +4176,34 @@ struct commit *get_revision(struct rev_info *revs) if (revs->reverse) { reversed = NULL; - while ((c = get_revision_internal(revs))) { + while ((c = get_revision_internal(revs))) commit_list_insert(c, &reversed); - } revs->commits = reversed; revs->reverse = 0; revs->reverse_output_stage = 1; } - if (revs->reverse_output_stage) - return pop_commit(&revs->commits); + if (revs->reverse_output_stage) { + c = pop_commit(&revs->commits); + if (revs->track_linear) + revs->linear = !!(c && c->object.flags & TRACK_LINEAR); + return c; + } c = get_revision_internal(revs); if (c && revs->graph) graph_update(revs->graph, c); + if (!c) { + free_saved_parents(revs); + if (revs->previous_parents) { + free_commit_list(revs->previous_parents); + revs->previous_parents = NULL; + } + } return c; } -char *get_revision_mark(const struct rev_info *revs, const struct commit *commit) +const char *get_revision_mark(const struct rev_info *revs, const struct commit *commit) { if (commit->object.flags & BOUNDARY) return "-"; @@ -2549,7 +4225,7 @@ char *get_revision_mark(const struct rev_info *revs, const struct commit *commit void put_revision_mark(const struct rev_info *revs, const struct commit *commit) { - char *mark = get_revision_mark(revs, commit); + const char *mark = get_revision_mark(revs, commit); if (!strlen(mark)) return; fputs(mark, stdout); |