git/commit.c

#include "git-compat-util.h"
#include "tag.h"
#include "commit.h"
#include "commit-graph.h"
#include "environment.h"
#include "gettext.h"
#include "hex.h"
#include "repository.h"
#include "object-name.h"
#include "object-store-ll.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 "hash-lookup.h"
#include "wt-status.h"
#include "advice.h"
#include "refs.h"
#include "commit-reach.h"
#include "run-command.h"
#include "setup.h"
#include "shallow.h"
#include "tree.h"
#include "hook.h"

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

int save_commit_buffer = 1;
int no_graft_file_deprecated_advice;

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(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_object(struct repository *r,
				    const struct object_id *oid)
{
	struct object *obj = parse_object(r, oid);
	return obj ? object_as_type(obj, OBJ_COMMIT, 0) : NULL;

}

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(obj, OBJ_COMMIT, 0);
}

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

	if (repo_get_oid_committish(the_repository, name, &oid))
		return NULL;
	commit = lookup_commit_reference(the_repository, &oid);
	if (repo_parse_commit(the_repository, commit))
		return NULL;
	return commit;
}

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

	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;

	/*
	 * Jump to end-of-line so that we can walk backwards to find the
	 * end-of-email ">". This is more forgiving of malformed cases
	 * because unexpected characters tend to be in the name and email
	 * fields.
	 */
	eol = memchr(buf, '\n', tail - buf);
	if (!eol)
		return 0;
	dateptr = eol;
	while (dateptr > buf && dateptr[-1] != '>')
		dateptr--;
	if (dateptr == buf)
		return 0;

	/*
	 * Trim leading whitespace, but make sure we have at least one
	 * non-whitespace character, as parse_timestamp() will otherwise walk
	 * right past the newline we found in "eol" when skipping whitespace
	 * itself.
	 *
	 * In theory it would be sufficient to allow any character not matched
	 * by isspace(), but there's a catch: our isspace() does not
	 * necessarily match the behavior of parse_timestamp(), as the latter
	 * is implemented by system routines which match more exotic control
	 * codes, or even locale-dependent sequences.
	 *
	 * Since we expect the timestamp to be a number, we can check for that.
	 * Anything else (e.g., a non-numeric token like "foo") would just
	 * cause parse_timestamp() to return 0 anyway.
	 */
	while (dateptr < eol && isspace(*dateptr))
		dateptr++;
	if (!isdigit(*dateptr) && *dateptr != '-')
		return 0;

	/*
	 * We know there is at least one digit (or dash), so we'll begin
	 * parsing there and stop at worst case at eol.
	 *
	 * Note that we may feed parse_timestamp() extra characters here if the
	 * commit is malformed, and it will parse as far as it can. For
	 * example, "123foo456" would return "123". That might be questionable
	 * (versus returning "0"), but it would help in a hypothetical case
	 * like "123456+0100", where the whitespace from the timezone is
	 * missing. Since such syntactic errors may be baked into history and
	 * hard to correct now, let's err on trying to make our best guess
	 * here, rather than insist on perfect syntax.
	 */
	return parse_timestamp(dateptr, NULL, 10);
}

static const struct object_id *commit_graft_oid_access(size_t index, const void *table)
{
	const struct commit_graft * const *commit_graft_table = table;
	return &commit_graft_table[index]->oid;
}

int commit_graft_pos(struct repository *r, const struct object_id *oid)
{
	return oid_pos(oid, r->parsed_objects->grafts,
		       r->parsed_objects->grafts_nr,
		       commit_graft_oid_access);
}

static void unparse_commit(struct repository *r, const struct object_id *oid)
{
	struct commit *c = lookup_commit(r, oid);

	if (!c->object.parsed)
		return;
	free_commit_list(c->parents);
	c->parents = NULL;
	c->object.parsed = 0;
}

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

	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;
	unparse_commit(r, &graft->oid);
	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 (!no_graft_file_deprecated_advice &&
	    advice_enabled(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);
	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;
}

void reset_commit_grafts(struct repository *r)
{
	int i;

	for (i = 0; i < r->parsed_objects->grafts_nr; i++) {
		unparse_commit(r, &r->parsed_objects->grafts[i]->oid);
		free(r->parsed_objects->grafts[i]);
	}
	r->parsed_objects->grafts_nr = 0;
	r->parsed_objects->commit_graft_prepared = 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_position(commit) != 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 = repo_get_commit_tree(the_repository, 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;
	}