git/commit.c

#include "cache.h"
#include "tag.h"
#include "commit.h"
#include "commit-graph.h"
#include "repository.h"
#include "object-store.h"
#include "pkt-line.h"
#include "utf8.h"
#include "diff.h"
#include "revision.h"
#include "notes.h"
#include "alloc.h"
#include "gpg-interface.h"
#include "mergesort.h"
#include "commit-slab.h"
#include "prio-queue.h"
#include "sha1-lookup.h"
#include "wt-status.h"
#include "advice.h"
#include "refs.h"
#include "commit-reach.h"

static struct commit_extra_header *read_commit_extra_header_lines(const char *buf, size_t len, const char **);

int save_commit_buffer = 1;

const char *commit_type = "commit";

struct commit *lookup_commit_reference_gently(struct repository *r,
		const struct object_id *oid, int quiet)
{
	struct object *obj = deref_tag(r,
				       parse_object(r, oid),
				       NULL, 0);

	if (!obj)
		return NULL;
	return object_as_type(r, obj, OBJ_COMMIT, quiet);
}

struct commit *lookup_commit_reference(struct repository *r, const struct object_id *oid)
{
	return lookup_commit_reference_gently(r, oid, 0);
}

struct commit *lookup_commit_or_die(const struct object_id *oid, const char *ref_name)
{
	struct commit *c = lookup_commit_reference(the_repository, oid);
	if (!c)
		die(_("could not parse %s"), ref_name);
	if (!oideq(oid, &c->object.oid)) {
		warning(_("%s %s is not a commit!"),
			ref_name, oid_to_hex(oid));
	}
	return c;
}

struct commit *lookup_commit(struct repository *r, const struct object_id *oid)
{
	struct object *obj = lookup_object(r, oid);
	if (!obj)
		return create_object(r, oid, alloc_commit_node(r));
	return object_as_type(r, obj, OBJ_COMMIT, 0);
}

struct commit *lookup_commit_reference_by_name(const char *name)
{
	struct object_id oid;
	struct commit *commit;

	if (get_oid_committish(name, &oid))
		return NULL;
	commit = lookup_commit_reference(the_repository, &oid);
	if (parse_commit(commit))
		return NULL;
	return commit;
}

static timestamp_t parse_commit_date(const char *buf, const char *tail)
{
	const char *dateptr;

	if (buf + 6 >= tail)
		return 0;
	if (memcmp(buf, "author", 6))
		return 0;
	while (buf < tail && *buf++ != '\n')
		/* nada */;
	if (buf + 9 >= tail)
		return 0;
	if (memcmp(buf, "committer", 9))
		return 0;
	while (buf < tail && *buf++ != '>')
		/* nada */;
	if (buf >= tail)
		return 0;
	dateptr = buf;
	while (buf < tail && *buf++ != '\n')
		/* nada */;
	if (buf >= tail)
		return 0;
	/* dateptr < buf && buf[-1] == '\n', so parsing will stop at buf-1 */
	return parse_timestamp(dateptr, NULL, 10);
}

static const unsigned char *commit_graft_sha1_access(size_t index, void *table)
{
	struct commit_graft **commit_graft_table = table;
	return commit_graft_table[index]->oid.hash;
}

static int commit_graft_pos(struct repository *r, const unsigned char *sha1)
{
	return sha1_pos(sha1, r->parsed_objects->grafts,
			r->parsed_objects->grafts_nr,
			commit_graft_sha1_access);
}

int register_commit_graft(struct repository *r, struct commit_graft *graft,
			  int ignore_dups)
{
	int pos = commit_graft_pos(r, graft->oid.hash);

	if (0 <= pos) {
		if (ignore_dups)
			free(graft);
		else {
			free(r->parsed_objects->grafts[pos]);
			r->parsed_objects->grafts[pos] = graft;
		}
		return 1;
	}
	pos = -pos - 1;
	ALLOC_GROW(r->parsed_objects->grafts,
		   r->parsed_objects->grafts_nr + 1,
		   r->parsed_objects->grafts_alloc);
	r->parsed_objects->grafts_nr++;
	if (pos < r->parsed_objects->grafts_nr)
		memmove(r->parsed_objects->grafts + pos + 1,
			r->parsed_objects->grafts + pos,
			(r->parsed_objects->grafts_nr - pos - 1) *
			sizeof(*r->parsed_objects->grafts));
	r->parsed_objects->grafts[pos] = graft;
	return 0;
}

struct commit_graft *read_graft_line(struct strbuf *line)
{
	/* The format is just "Commit Parent1 Parent2 ...\n" */
	int i, phase;
	const char *tail = NULL;
	struct commit_graft *graft = NULL;
	struct object_id dummy_oid, *oid;

	strbuf_rtrim(line);
	if (!line->len || line->buf[0] == '#')
		return NULL;
	/*
	 * phase 0 verifies line, counts hashes in line and allocates graft
	 * phase 1 fills graft
	 */
	for (phase = 0; phase < 2; phase++) {
		oid = graft ? &graft->oid : &dummy_oid;
		if (parse_oid_hex(line->buf, oid, &tail))
			goto bad_graft_data;
		for (i = 0; *tail != '\0'; i++) {
			oid = graft ? &graft->parent[i] : &dummy_oid;
			if (!isspace(*tail++) || parse_oid_hex(tail, oid, &tail))
				goto bad_graft_data;
		}
		if (!graft) {
			graft = xmalloc(st_add(sizeof(*graft),
					       st_mult(sizeof(struct object_id), i)));
			graft->nr_parent = i;
		}
	}
	return graft;

bad_graft_data:
	error("bad graft data: %s", line->buf);
	assert(!graft);
	return NULL;
}

static int read_graft_file(struct repository *r, const char *graft_file)
{
	FILE *fp = fopen_or_warn(graft_file, "r");
	struct strbuf buf = STRBUF_INIT;
	if (!fp)
		return -1;
	if (advice_graft_file_deprecated)
		advise(_("Support for <GIT_DIR>/info/grafts is deprecated\n"
			 "and will be removed in a future Git version.\n"
			 "\n"
			 "Please use \"git replace --convert-graft-file\"\n"
			 "to convert the grafts into replace refs.\n"
			 "\n"
			 "Turn this message off by running\n"
			 "\"git config advice.graftFileDeprecated false\""));
	while (!strbuf_getwholeline(&buf, fp, '\n')) {
		/* The format is just "Commit Parent1 Parent2 ...\n" */
		struct commit_graft *graft = read_graft_line(&buf);
		if (!graft)
			continue;
		if (register_commit_graft(r, graft, 1))
			error("duplicate graft data: %s", buf.buf);
	}
	fclose(fp);
	strbuf_release(&buf);
	return 0;
}

void prepare_commit_graft(struct repository *r)
{
	char *graft_file;

	if (r->parsed_objects->commit_graft_prepared)
		return;
	if (!startup_info->have_repository)
		return;

	graft_file = get_graft_file(r);
	read_graft_file(r, graft_file);
	/* make sure shallows are read */
	is_repository_shallow(r);
	r->parsed_objects->commit_graft_prepared = 1;
}

struct commit_graft *lookup_commit_graft(struct repository *r, const struct object_id *oid)
{
	int pos;
	prepare_commit_graft(r);
	pos = commit_graft_pos(r, oid->hash);
	if (pos < 0)
		return NULL;
	return r->parsed_objects->grafts[pos];
}

int for_each_commit_graft(each_commit_graft_fn fn, void *cb_data)
{
	int i, ret;
	for (i = ret = 0; i < the_repository->parsed_objects->grafts_nr && !ret; i++)
		ret = fn(the_repository->parsed_objects->grafts[i], cb_data);
	return ret;
}

int unregister_shallow(const struct object_id *oid)
{
	int pos = commit_graft_pos(the_repository, oid->hash);
	if (pos < 0)
		return -1;
	if (pos + 1 < the_repository->parsed_objects->grafts_nr)
		MOVE_ARRAY(the_repository->parsed_objects->grafts + pos,
			   the_repository->parsed_objects->grafts + pos + 1,
			   the_repository->parsed_objects->grafts_nr - pos - 1);
	the_repository->parsed_objects->grafts_nr--;
	return 0;
}

struct commit_buffer {
	void *buffer;
	unsigned long size;
};
define_commit_slab(buffer_slab, struct commit_buffer);

struct buffer_slab *allocate_commit_buffer_slab(void)
{
	struct buffer_slab *bs = xmalloc(sizeof(*bs));
	init_buffer_slab(bs);
	return bs;
}

void free_commit_buffer_slab(struct buffer_slab *bs)
{
	clear_buffer_slab(bs);
	free(bs);
}

void set_commit_buffer(struct repository *r, struct commit *commit, void *buffer, unsigned long size)
{
	struct commit_buffer *v = buffer_slab_at(
		r->parsed_objects->buffer_slab, commit);
	v->buffer = buffer;
	v->size = size;
}

const void *get_cached_commit_buffer(struct repository *r, const struct commit *commit, unsigned long *sizep)
{
	struct commit_buffer *v = buffer_slab_peek(
		r->parsed_objects->buffer_slab, commit);
	if (!v) {
		if (sizep)
			*sizep = 0;
		return NULL;
	}
	if (sizep)
		*sizep = v->size;
	return v->buffer;
}

const void *repo_get_commit_buffer(struct repository *r,
				   const struct commit *commit,
				   unsigned long *sizep)
{
	const void *ret = get_cached_commit_buffer(r, commit, sizep);
	if (!ret) {
		enum object_type type;
		unsigned long size;
		ret = repo_read_object_file(r, &commit->object.oid, &type, &size);
		if (!ret)
			die("cannot read commit object %s",
			    oid_to_hex(&commit->object.oid));
		if (type != OBJ_COMMIT)
			die("expected commit for %s, got %s",
			    oid_to_hex(&commit->object.oid), type_name(type));
		if (sizep)
			*sizep = size;
	}
	return ret;
}

void repo_unuse_commit_buffer(struct repository *r,
			      const struct commit *commit,
			      const void *buffer)
{
	struct commit_buffer *v = buffer_slab_peek(
		r->parsed_objects->buffer_slab, commit);
	if (!(v && v->buffer == buffer))
		free((void *)buffer);
}

void free_commit_buffer(struct parsed_object_pool *pool, struct commit *commit)
{
	struct commit_buffer *v = buffer_slab_peek(
		pool->buffer_slab, commit);
	if (v) {
		FREE_AND_NULL(v->buffer);
		v->size = 0;
	}
}

static inline void set_commit_tree(struct commit *c, struct tree *t)
{
	c->maybe_tree = t;
}

struct tree *repo_get_commit_tree(struct repository *r,
				  const struct commit *commit)
{
	if (commit->maybe_tree || !commit->object.parsed)
		return commit->maybe_tree;

	if (commit->graph_pos != COMMIT_NOT_FROM_GRAPH)
		return get_commit_tree_in_graph(r, commit);

	return NULL;
}

struct object_id *get_commit_tree_oid(const struct commit *commit)
{
	struct tree *tree = get_commit_tree(commit);
	return tree ? &tree->object.oid : NULL;
}

void release_commit_memory(struct parsed_object_pool *pool, struct commit *c)
{
	set_commit_tree(c, NULL);
	free_commit_buffer(pool, c);
	c->index = 0;
	free_commit_list(c->parents);

	c->object.parsed = 0;
}

const void *detach_commit_buffer(struct commit *commit, unsigned long *sizep)
{
	struct commit_buffer *v = buffer_slab_peek(
		the_repository->parsed_objects->buffer_slab, commit);
	void *ret;

	if (!v) {
		if (sizep)
			*sizep = 0;
		return NULL;
	}
	ret = v->buffer;
	if (sizep)
		*sizep = v->size;

	v->buffer = NULL;
	v->size = 0;
	return ret;
}

int parse_commit_buffer(struct repository *r, struct commit *item, const void *buffer, unsigned long size, int check_graph)
{
	const char *tail = buffer;
	const char *bufptr = buffer;
	struct object_id parent;
	struct commit_list **pptr;
	struct commit_graft *graft;
	const int tree_entry_len = the_hash_algo->hexsz + 5;
	const int parent_entry_len = the_hash_algo->hexsz + 7;

	if (item->object.parsed)
		return 0;
	item->object.parsed = 1;
	tail += size;
	if (tail <= bufptr + tree_entry_len + 1 || memcmp(bufptr, "tree ", 5) ||
			bufptr[tree_entry_len] != '\n')
		return error("bogus commit object %s", oid_to_hex(&item->object.oid));
	if (get_oid_hex(bufptr + 5, &parent) < 0)
		return error("bad tree pointer in commit %s",
			     oid_to_hex(&item->object.oid));
	set_commit_tree(item, lookup_tree(r, &parent));
	bufptr += tree_entry_len + 1; /* "tree " + "hex sha1" + "\n" */
	pptr = &item->parents;

	graft = lookup_commit_graft(r, &item->object.oid);
	while (bufptr + parent_entry_len < tail && !memcmp(bufptr, "parent ", 7)) {
		struct commit *new_parent;

		if (tail <= bufptr + parent_entry_len + 1 ||
		    get_oid_hex(bufptr + 7, &parent) ||
		    bufptr[parent_entry_len] != '\n')
			return error("bad parents in commit %s", oid_to_hex(&item->object.oid));
		bufptr += parent_entry_len + 1;
		/*
		 * The clone is shallow if nr_parent < 0, and we must
		 * not traverse its real parents even when we unhide them.
		 */
		if (graft && (graft->nr_parent < 0 || grafts_replace_parents))
			continue;
		new_parent = lookup_commit(r, &parent);
		if (new_parent)
			pptr = &commit_list_insert(new_parent, pptr)->next;
	}
	if (graft) {
		int i;
		struct commit *new_parent;
		for (i = 0; i < graft->nr_parent; i++) {
			new_parent = lookup_commit(r,
						   &graft->parent[i]);
			if (!new_parent)
				continue;
			pptr = &commit_list_insert(new_parent, pptr)->next;
		}
	}
	item->date = parse_commit_date(bufptr, tail);

	if (check_graph)
		load_commit_graph_info(r, item);

	return 0;
}

int repo_parse_commit_internal(struct repository *r,
			       struct commit *item,
			       int quiet_on_missing,
			       int use_commit_graph)
{
	enum object_type type;
	void *buffer;
	unsigned long size;
	int ret;

	if (!item)
		return -1;
	if (item->object.parsed)
		return 0;
	if (use_commit_graph && parse_commit_in_graph(r, item))
		return 0;
	buffer = repo_read_object_file(r, &item->object.oid, &type, &size);
	if (!buffer)
		return quiet_on_missing ? -1 :
			error("Could not read %s",
			     oid_to_hex(&item->object.oid));
	if (type != OBJ_COMMIT) {
		free(buffer);
		return error("Object %s not a commit",
			     oid_to_hex(&item->object.oid));
	}

	ret = parse_commit_buffer(r, item, buffer, size, 0);
	if (save_commit_buffer && !ret) {
		set_commit_buffer(r, item, buffer, size);
		return 0;
	}
	free(buffer);
	return ret;
}

int repo_parse_commit_gently(struct repository *r,
			     struct commit *item, int quiet_on_missing)
{
	return repo_parse_commit_internal(r, item, quiet_on_missing, 1);
}

void parse_commit_or_die(struct commit *item)
{
	if (parse_commit(item))
		die("unable to parse commit %s",
		    item ? oid_to_hex(&item->object.oid) : "(null)");
}

int find_commit_subject(const char *commit_buffer, const char **subject)
{
	const char *eol;
	const char *p = commit_buffer;

	while (*p && (*p != '\n' || p[1] != '\n'))
		p++;
	if (*p) {
		p = skip_blank_lines(p + 2);
		eol = strchrnul(p, '\n');
	} else
		eol = p;

	*subject = p;

	return eol - p;
}

struct commit_list *commit_list_insert(struct commit *item, struct commit_list **list_p)
{
	struct commit_list *new_list = xmalloc(sizeof(struct commit_list));
	new_list->item = item;
	new_list->next = *list_p;
	*list_p = new_list;
	return new_list;
}

unsigned commit_list_count(const struct commit_list *l)
{
	unsigned c = 0;
	for (; l; l = l->next )
		c++;
	return c;
}

struct commit_list *copy_commit_list(struct commit_list *list)
{
	struct commit_list *head = NULL;
	struct commit_list **pp = &head;
	while (list) {
		pp = commit_list_append(list->item, pp);
		list = list->next;
	}
	return head;
}

void free_commit_list(struct commit_list *list)
{
	while (list)
		pop_commit(&list);
}

struct commit_list * commit_list_insert_by_date(struct commit *item, struct commit_list **list)
{
	struct commit_list **pp = list;
	struct commit_list *p;
	while ((p = *pp) != NULL) {
		if (p->item->date < item->date) {
			break;
		}
		pp = &p->next;
	}
	return commit_list_insert(item, pp);
}

static int commit_list_compare_by_date(const void *a, const void *b)
{
	timestamp_t a_date = ((const struct commit_list *)a)->item->date;
	timestamp_t b_date = ((const struct commit_list *)b)->item->date;
	if (a_date < b_date)
		return 1;
	if (a_date > b_date)
		return -1;
	return 0;
}

static void *commit_list_get_next(const void *a)
{
	return ((const struct commit_list *)a)->next;
}

static void commit_list_set_next(void *a, void *next)
{
	((struct commit_list *)a)->next = next;
}

void commit_list_sort_by_date(struct commit_list **list)
{
	*list = llist_mergesort(*list, commit_list_get_next, commit_list_set_next,
				commit_list_compare_by_date);
}

struct commit *pop_most_recent_commit(struct commit_list **list,
				      unsigned int mark)
{
	struct commit *ret = pop_commit(list);
	struct commit_list *parents = ret->parents;

	while (parents) {
		struct commit *commit = parents->item;
		if (!parse_commit(commit) && !(commit->object.flags & mark)) {
			commit->object.flags |= mark;
			commit_list_insert_by_date(commit, list);
		}
		parents = parents->next;
	}
	return ret;
}

static void clear_commit_marks_1(struct commit_list **plist,
				 struct commit *commit, unsigned int mark)
{
	while (commit) {
		struct commit_list *parents;

		if (!(mark & commit->object.flags))
			return;

		commit->object.flags &= ~mark;

		parents = commit->parents;
		if (!parents)
			return;

		while ((parents = parents->next))
			commit_list_insert(parents->item, plist);

		commit = commit->parents->item;
	}
}

void clear_commit_marks_many(int nr, struct commit **commit, unsigned int mark)
{
	struct commit_list *list = NULL;

	while (nr--) {
		clear_commit_marks_1(&list, *commit, mark);
		commit++;
	}
	while (list)
		clear_commit_marks_1(&list, pop_commit(&list), mark);
}

void clear_commit_marks(struct commit *commit, unsigned int mark)
{
	clear_commit_marks_many(1, &commit, mark);
}

struct commit *pop_commit(struct commit_list **stack)
{
	struct commit_list *top = *stack;
	struct commit *item = top ? top->item : NULL;

	if (top) {
		*stack = top->next;
		free(top);
	}
	return item;
}

/*
 * Topological sort support
 */

/* count number of children that have not been emitted */
define_commit_slab(indegree_slab, int);

define_commit_slab(author_date_slab, timestamp_t);

void record_author_date(struct author_date_slab *author_date,
			struct commit *commit)
{
	const char *buffer = get_commit_buffer(commit, NULL);
	struct ident_split ident;
	const char *ident_line;
	size_t ident_len;
	char *date_end;
	timestamp_t date;

	ident_line = find_commit_header(buffer, "author", &ident_len);
	if (!ident_line)
		goto fail_exit; /* no author line */
	if (split_ident_line(&ident, ident_line, ident_len) ||
	    !ident.date_begin || !ident.date_end)
		goto fail_exit; /* malformed "author" line */

	date = parse_timestamp(ident.date_begin, &date_end, 10);
	if (date_end != ident.date_end)
		goto fail_exit; /* malformed date */
	*(author_date_slab_at(author_date, commit)) = date;

fail_exit:
	unuse_commit_buffer(commit, buffer);
}

int compare_commits_by_author_date(const void *a_, const void *b_,
				   void *cb_data)
{
	const struct commit *a = a_, *b = b_;
	struct author_date_slab *author_date = cb_data;
	timestamp_t a_date = *(author_date_slab_at(author_date, a));
	timestamp_t b_date = *(author_date_slab_at(author_date, b));

	/* newer commits with larger date first */
	if (a_date < b_date)
		return 1;
	else if (a_date > b_date)
		return -1;
	return 0;
}

int compare_commits_by_gen_then_commit_date(const void *a_, const void *b_, void *unused)
{
	const struct commit *a = a_, *b = b_;

	/* newer commits first */
	if (a->generation < b->generation)
		return 1;
	else if (a->generation > b->generation)
		return -1;

	/* use date as a heuristic when generations are equal */
	if (a->date < b->date)
		return 1;
	else if (a->date > b->date)
		return -1;
	return 0;
}

int compare_commits_by_commit_date(const void *a_, const void *b_, void *unused)
{
	const struct commit *a = a_, *b = b_;
	/* newer commits with larger date first */
	if (a->date < b->date)
		return 1;
	else if (a->date > b->date)
		return -1;
	return 0;
}

/*
 * Performs an in-place topological sort on the list supplied.
 */
void sort_in_topological_order(struct commit_list **list, enum rev_sort_order sort_order)
{
	struct commit_list *next, *orig = *list;
	struct commit_list **pptr;
	struct indegree_slab indegree;
	struct prio_queue queue;
	struct commit *commit;
	struct author_date_slab author_date;

	if (!orig)
		return;
	*list = NULL;

	init_indegree_slab(&indegree);
	memset(&queue, '\0', sizeof(queue));

	switch (sort_order) {
	default: /* REV_SORT_IN_GRAPH_ORDER */
		queue.compare = NULL;
		break;
	case REV_SORT_BY_COMMIT_DATE:
		queue.compare = compare_commits_by_commit_date;
		break;
	case REV_SORT_BY_AUTHOR_DATE:
		init_author_date_slab(&author_date);
		queue.compare = compare_commits_by_author_date;
		queue.cb_data = &author_date;
		break;
	}

	/* Mark them and clear the indegree */
	for (next = orig; next; next = next->next) {
		struct commit *commit = next->item;
		*(indegree_slab_at(&indegree, commit)) = 1;
		/* also record the author dates, if needed */
		if (sort_order == REV_SORT_BY_AUTHOR_DATE)
			record_author_date(&author_date, commit);
	}

	/* update the indegree */
	for (next = orig; next; next = next->next) {
		struct commit_list *parents = next->item->parents;
		while (parents) {
			struct commit *parent = parents->item;
			int *pi = indegree_slab_at(&indegree, parent);

			if (*pi)
				(*pi)++;
			parents = parents->next;
		}
	}

	/*
	 * find the tips
	 *
	 * tips are nodes not reachable from any other node in the list
	 *
	 * the tips serve as a starting set for the work queue.
	 */
	for (next = orig; next; next = next->next) {
		struct commit *commit = next->item;

		if (*(indegree_slab_at(&indegree, commit)) == 1)
			prio_queue_put(&queue, commit);
	}

	/*
	 * This is unfortunate; the initial tips need to be shown
	 * in the order given from the revision traversal machinery.
	 */
	if (sort_order == REV_SORT_IN_GRAPH_ORDER)
		prio_queue_reverse(&queue);

	/* We no longer need the commit list */
	free_commit_list(orig);

	pptr = list;
	*list = NULL;