git/revision.c

#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"
#include "patch-ids.h"
#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;

static const char *term_bad;
static const char *term_good;

implement_shared_commit_slab(revision_sources, char *);

static inline int want_ancestry(const struct rev_info *revs);

void show_object_with_name(FILE *out, struct object *obj, const char *name)
{
	const char *p;

	fprintf(out, "%s ", oid_to_hex(&obj->oid));
	for (p = name; *p && *p != '\n'; p++)
		fputc(*p, out);
	fputc('\n', out);
}

static void mark_blob_uninteresting(struct blob *blob)
{
	if (!blob)
		return;
	if (blob->object.flags & UNINTERESTING)
		return;
	blob->object.flags |= UNINTERESTING;
}

static void mark_tree_contents_uninteresting(struct repository *r,
					     struct tree *tree)
{
	struct tree_desc desc;
	struct name_entry entry;

	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:
			mark_tree_uninteresting(r, lookup_tree(r, &entry.oid));
			break;
		case OBJ_BLOB:
			mark_blob_uninteresting(lookup_blob(r, &entry.oid));
			break;
		default:
			/* Subproject commit - not in this repository */
			break;
		}
	}

	/*
	 * We don't care about the tree any more
	 * after it has been marked uninteresting.
	 */
	free_tree_buffer(tree);
}

void mark_tree_uninteresting(struct repository *r, struct tree *tree)
{
	struct object *obj;

	if (!tree)
		return;

	obj = &tree->object;
	if (obj->flags & UNINTERESTING)
		return;
	obj->flags |= UNINTERESTING;
	mark_tree_contents_uninteresting(r, tree);
}

struct path_and_oids_entry {
	struct hashmap_entry ent;
	char *path;
	struct oidset trees;
};

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;

	e1 = container_of(eptr, const struct path_and_oids_entry, ent);
	e2 = container_of(entry_or_key, const struct path_and_oids_entry, ent);

	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;

	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 { 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 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;
		size_t namelen = strlen(name);
		int len = interpret_branch_name(name, namelen, &buf, &options);

		if (0 < len && len < namelen && buf.len)
			strbuf_addstr(&buf, name + len);
		add_reflog_for_walk(revs->reflog_info,
				    (struct commit *)obj,
				    buf.buf[0] ? buf.buf: name);
		strbuf_release(&buf);
		return; /* do not add the commit itself */
	}
	add_object_array_with_path(obj, name, &revs->pending, mode, path);
}

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)
{
	struct object_id oid;
	struct object *obj;
	if (get_oid("HEAD", &oid))
		return;
	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 struct object_id *oid,
				    unsigned int flags)
{
	struct object *object;
	struct commit *commit;

	/*
	 * If the repository has commit graphs, we try to opportunistically
	 * look up the object ID in those graphs. Like this, we can avoid
	 * parsing commit data from disk.
	 */
	commit = lookup_commit_in_graph(revs->repo, oid);
	if (commit)
		object = &commit->object;
	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_oid(struct rev_info *revs, const char *name,
		      const struct object_id *oid, unsigned int 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_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;

	/*
	 * Tag object? Look what it points to..
	 */
	while (object->type == OBJ_TAG) {
		struct tag *tag = (struct tag *) object;
		if (revs->tag_objects && !(flags & UNINTERESTING))
			add_pending_object(revs, object, tag->tag);
		object = parse_object(revs->repo, get_tagged_oid(tag));