git/builtin/clone.c

/*
 * Builtin "git clone"
 *
 * Copyright (c) 2007 Kristian Høgsberg <krh@redhat.com>,
 *		 2008 Daniel Barkalow <barkalow@iabervon.org>
 * Based on git-commit.sh by Junio C Hamano and Linus Torvalds
 *
 * Clone a repository into a different directory that does not yet exist.
 */

#define USE_THE_INDEX_COMPATIBILITY_MACROS
#include "builtin.h"
#include "config.h"
#include "lockfile.h"
#include "parse-options.h"
#include "fetch-pack.h"
#include "refs.h"
#include "refspec.h"
#include "object-store.h"
#include "tree.h"
#include "tree-walk.h"
#include "unpack-trees.h"
#include "transport.h"
#include "strbuf.h"
#include "dir.h"
#include "dir-iterator.h"
#include "iterator.h"
#include "sigchain.h"
#include "branch.h"
#include "remote.h"
#include "run-command.h"
#include "connected.h"
#include "packfile.h"
#include "list-objects-filter-options.h"

/*
 * Overall FIXMEs:
 *  - respect DB_ENVIRONMENT for .git/objects.
 *
 * Implementation notes:
 *  - dropping use-separate-remote and no-separate-remote compatibility
 *
 */
static const char * const builtin_clone_usage[] = {
	N_("git clone [<options>] [--] <repo> [<dir>]"),
	NULL
};

static int option_no_checkout, option_bare, option_mirror, option_single_branch = -1;
static int option_local = -1, option_no_hardlinks, option_shared;
static int option_no_tags;
static int option_shallow_submodules;
static int deepen;
static char *option_template, *option_depth, *option_since;
static char *option_origin = NULL;
static char *option_branch = NULL;
static struct string_list option_not = STRING_LIST_INIT_NODUP;
static const char *real_git_dir;
static char *option_upload_pack = "git-upload-pack";
static int option_verbosity;
static int option_progress = -1;
static int option_sparse_checkout;
static enum transport_family family;
static struct string_list option_config = STRING_LIST_INIT_NODUP;
static struct string_list option_required_reference = STRING_LIST_INIT_NODUP;
static struct string_list option_optional_reference = STRING_LIST_INIT_NODUP;
static int option_dissociate;
static int max_jobs = -1;
static struct string_list option_recurse_submodules = STRING_LIST_INIT_NODUP;
static struct list_objects_filter_options filter_options;
static struct string_list server_options = STRING_LIST_INIT_NODUP;
static int option_remote_submodules;

static int recurse_submodules_cb(const struct option *opt,
				 const char *arg, int unset)
{
	if (unset)
		string_list_clear((struct string_list *)opt->value, 0);
	else if (arg)
		string_list_append((struct string_list *)opt->value, arg);
	else
		string_list_append((struct string_list *)opt->value,
				   (const char *)opt->defval);

	return 0;
}

static struct option builtin_clone_options[] = {
	OPT__VERBOSITY(&option_verbosity),
	OPT_BOOL(0, "progress", &option_progress,
		 N_("force progress reporting")),
	OPT_BOOL('n', "no-checkout", &option_no_checkout,
		 N_("don't create a checkout")),
	OPT_BOOL(0, "bare", &option_bare, N_("create a bare repository")),
	OPT_HIDDEN_BOOL(0, "naked", &option_bare,
			N_("create a bare repository")),
	OPT_BOOL(0, "mirror", &option_mirror,
		 N_("create a mirror repository (implies bare)")),
	OPT_BOOL('l', "local", &option_local,
		N_("to clone from a local repository")),
	OPT_BOOL(0, "no-hardlinks", &option_no_hardlinks,
		    N_("don't use local hardlinks, always copy")),
	OPT_BOOL('s', "shared", &option_shared,
		    N_("setup as shared repository")),
	{ OPTION_CALLBACK, 0, "recurse-submodules", &option_recurse_submodules,
	  N_("pathspec"), N_("initialize submodules in the clone"),
	  PARSE_OPT_OPTARG, recurse_submodules_cb, (intptr_t)"." },
	OPT_ALIAS(0, "recursive", "recurse-submodules"),
	OPT_INTEGER('j', "jobs", &max_jobs,
		    N_("number of submodules cloned in parallel")),
	OPT_STRING(0, "template", &option_template, N_("template-directory"),
		   N_("directory from which templates will be used")),
	OPT_STRING_LIST(0, "reference", &option_required_reference, N_("repo"),
			N_("reference repository")),
	OPT_STRING_LIST(0, "reference-if-able", &option_optional_reference,
			N_("repo"), N_("reference repository")),
	OPT_BOOL(0, "dissociate", &option_dissociate,
		 N_("use --reference only while cloning")),
	OPT_STRING('o', "origin", &option_origin, N_("name"),
		   N_("use <name> instead of 'origin' to track upstream")),
	OPT_STRING('b', "branch", &option_branch, N_("branch"),
		   N_("checkout <branch> instead of the remote's HEAD")),
	OPT_STRING('u', "upload-pack", &option_upload_pack, N_("path"),
		   N_("path to git-upload-pack on the remote")),
	OPT_STRING(0, "depth", &option_depth, N_("depth"),
		    N_("create a shallow clone of that depth")),
	OPT_STRING(0, "shallow-since", &option_since, N_("time"),
		    N_("create a shallow clone since a specific time")),
	OPT_STRING_LIST(0, "shallow-exclude", &option_not, N_("revision"),
			N_("deepen history of shallow clone, excluding rev")),
	OPT_BOOL(0, "single-branch", &option_single_branch,
		    N_("clone only one branch, HEAD or --branch")),
	OPT_BOOL(0, "no-tags", &option_no_tags,
		 N_("don't clone any tags, and make later fetches not to follow them")),
	OPT_BOOL(0, "shallow-submodules", &option_shallow_submodules,
		    N_("any cloned submodules will be shallow")),
	OPT_STRING(0, "separate-git-dir", &real_git_dir, N_("gitdir"),
		   N_("separate git dir from working tree")),
	OPT_STRING_LIST('c', "config", &option_config, N_("key=value"),
			N_("set config inside the new repository")),
	OPT_STRING_LIST(0, "server-option", &server_options,
			N_("server-specific"), N_("option to transmit")),
	OPT_SET_INT('4', "ipv4", &family, N_("use IPv4 addresses only"),
			TRANSPORT_FAMILY_IPV4),
	OPT_SET_INT('6', "ipv6", &family, N_("use IPv6 addresses only"),
			TRANSPORT_FAMILY_IPV6),
	OPT_PARSE_LIST_OBJECTS_FILTER(&filter_options),
	OPT_BOOL(0, "remote-submodules", &option_remote_submodules,
		    N_("any cloned submodules will use their remote-tracking branch")),
	OPT_BOOL(0, "sparse", &option_sparse_checkout,
		    N_("initialize sparse-checkout file to include only files at root")),
	OPT_END()
};

static const char *get_repo_path_1(struct strbuf *path, int *is_bundle)
{
	static char *suffix[] = { "/.git", "", ".git/.git", ".git" };
	static char *bundle_suffix[] = { ".bundle", "" };
	size_t baselen = path->len;
	struct stat st;
	int i;

	for (i = 0; i < ARRAY_SIZE(suffix); i++) {
		strbuf_setlen(path, baselen);
		strbuf_addstr(path, suffix[i]);
		if (stat(path->buf, &st))
			continue;
		if (S_ISDIR(st.st_mode) && is_git_directory(path->buf)) {
			*is_bundle = 0;
			return path->buf;
		} else if (S_ISREG(st.st_mode) && st.st_size > 8) {
			/* Is it a "gitfile"? */
			char signature[8];
			const char *dst;
			int len, fd = open(path->buf, O_RDONLY);
			if (fd < 0)
				continue;
			len = read_in_full(fd, signature, 8);
			close(fd);
			if (len != 8 || strncmp(signature, "gitdir: ", 8))
				continue;
			dst = read_gitfile(path->buf);
			if (dst) {
				*is_bundle = 0;
				return dst;
			}
		}
	}

	for (i = 0; i < ARRAY_SIZE(bundle_suffix); i++) {
		strbuf_setlen(path, baselen);
		strbuf_addstr(path, bundle_suffix[i]);
		if (!stat(path->buf, &st) && S_ISREG(st.st_mode)) {
			*is_bundle = 1;
			return path->buf;
		}
	}

	return NULL;
}

static char *get_repo_path(const char *repo, int *is_bundle)
{
	struct strbuf path = STRBUF_INIT;
	const char *raw;
	char *canon;

	strbuf_addstr(&path, repo);
	raw = get_repo_path_1(&path, is_bundle);
	canon = raw ? absolute_pathdup(raw) : NULL;
	strbuf_release(&path);
	return canon;
}

static char *guess_dir_name(const char *repo, int is_bundle, int is_bare)
{
	const char *end = repo + strlen(repo), *start, *ptr;
	size_t len;
	char *dir;

	/*
	 * Skip scheme.
	 */
	start = strstr(repo, "://");
	if (start == NULL)
		start = repo;
	else
		start += 3;

	/*
	 * Skip authentication data. The stripping does happen
	 * greedily, such that we strip up to the last '@' inside
	 * the host part.
	 */
	for (ptr = start; ptr < end && !is_dir_sep(*ptr); ptr++) {
		if (*ptr == '@')
			start = ptr + 1;
	}

	/*
	 * Strip trailing spaces, slashes and /.git
	 */
	while (start < end && (is_dir_sep(end[-1]) || isspace(end[-1])))
		end--;
	if (end - start > 5 && is_dir_sep(end[-5]) &&
	    !strncmp(end - 4, ".git", 4)) {
		end -= 5;
		while (start < end && is_dir_sep(end[-1]))
			end--;
	}

	/*
	 * Strip trailing port number if we've got only a
	 * hostname (that is, there is no dir separator but a
	 * colon). This check is required such that we do not
	 * strip URI's like '/foo/bar:2222.git', which should
	 * result in a dir '2222' being guessed due to backwards
	 * compatibility.
	 */
	if (memchr(start, '/', end - start) == NULL
	    && memchr(start, ':', end - start) != NULL) {
		ptr = end;
		while (start < ptr && isdigit(ptr[-1]) && ptr[-1] != ':')
			ptr--;
		if (start < ptr && ptr[-1] == ':')
			end = ptr - 1;
	}

	/*
	 * Find last component. To remain backwards compatible we
	 * also regard colons as path separators, such that
	 * cloning a repository 'foo:bar.git' would result in a
	 * directory 'bar' being guessed.
	 */
	ptr = end;
	while (start < ptr && !is_dir_sep(ptr[-1]) && ptr[-1] != ':')
		ptr--;
	start = ptr;

	/*
	 * Strip .{bundle,git}.
	 */
	len = end - start;
	strip_suffix_mem(start, &len, is_bundle ? ".bundle" : ".git");

	if (!len || (len == 1 && *start == '/'))
		die(_("No directory name could be guessed.\n"
		      "Please specify a directory on the command line"));

	if (is_bare)
		dir = xstrfmt("%.*s.git", (int)len, start);
	else
		dir = xstrndup(start, len);
	/*
	 * Replace sequences of 'control' characters and whitespace
	 * with one ascii space, remove leading and trailing spaces.
	 */
	if (*dir) {
		char *out = dir;
		int prev_space = 1 /* strip leading whitespace */;
		for (end = dir; *end; ++end) {
			char ch = *end;
			if ((unsigned char)ch < '\x20')
				ch = '\x20';
			if (isspace(ch)) {
				if (prev_space)
					continue;
				prev_space = 1;
			} else
				prev_space = 0;
			*out++ = ch;
		}
		*out = '\0';
		if (out > dir && prev_space)
			out[-1] = '\0';
	}
	return dir;
}

static void strip_trailing_slashes(char *dir)
{
	char *end = dir + strlen(dir);

	while (dir < end - 1 && is_dir_sep(end[-1]))
		end--;
	*end = '\0';
}

static int add_one_reference(struct string_list_item *item, void *cb_data)
{
	struct strbuf err = STRBUF_INIT;
	int *required = cb_data;
	char *ref_git = compute_alternate_path(item->string, &err);

	if (!ref_git) {
		if (*required)
			die("%s", err.buf);
		else
			fprintf(stderr,
				_("info: Could not add alternate for '%s': %s\n"),
				item->string, err.buf);
	} else {
		struct strbuf sb = STRBUF_INIT;
		strbuf_addf(&sb, "%s/objects", ref_git);
		add_to_alternates_file(sb.buf);
		strbuf_release(&sb);
	}

	strbuf_release(&err);
	free(ref_git);
	return 0;
}

static void setup_reference(void)
{
	int required = 1;
	for_each_string_list(&option_required_reference,
			     add_one_reference, &required);
	required = 0;
	for_each_string_list(&option_optional_reference,
			     add_one_reference, &required);
}

static void copy_alternates(struct strbuf *src, const char *src_repo)
{
	/*
	 * Read from the source objects/info/alternates file
	 * and copy the entries to corresponding file in the
	 * destination repository with add_to_alternates_file().
	 * Both src and dst have "$path/objects/info/alternates".
	 *
	 * Instead of copying bit-for-bit from the original,
	 * we need to append to existing one so that the already
	 * created entry via "clone -s" is not lost, and also
	 * to turn entries with paths relative to the original
	 * absolute, so that they can be used in the new repository.
	 */
	FILE *in = xfopen(src->buf, "r");
	struct strbuf line = STRBUF_INIT;

	while (strbuf_getline(&line, in) != EOF) {
		char *abs_path;
		if (!line.len || line.buf[0] == '#')
			continue;
		if (is_absolute_path(line.buf)) {
			add_to_alternates_file(line.buf);
			continue;
		}
		abs_path = mkpathdup("%s/objects/%s", src_repo, line.buf);
		if (!normalize_path_copy(abs_path, abs_path))
			add_to_alternates_file(abs_path);
		else
			warning("skipping invalid relative alternate: %s/%s",
				src_repo, line.buf);
		free(abs_path);
	}
	strbuf_release(&line);
	fclose(in);
}

static void mkdir_if_missing(const char *pathname, mode_t mode)
{
	struct stat st;

	if (!mkdir(pathname, mode))
		return;

	if (errno != EEXIST)
		die_errno(_("failed to create directory '%s'"), pathname);
	else if (stat(pathname, &st))
		die_errno(_("failed to stat '%s'"), pathname);
	else if (!S_ISDIR(st.st_mode))
		die(_("%s exists and is not a directory"), pathname);
}

static void copy_or_link_directory(struct strbuf *src, struct strbuf *dest,
				   const char *src_repo)
{
	int src_len, dest_len;
	struct dir_iterator *iter;
	int iter_status;
	unsigned int flags;
	struct strbuf realpath = STRBUF_INIT;

	mkdir_if_missing(dest->buf, 0777);

	flags = DIR_ITERATOR_PEDANTIC | DIR_ITERATOR_FOLLOW_SYMLINKS;
	iter = dir_iterator_begin(src->buf, flags);

	if (!iter)
		die_errno(_("failed to start iterator over '%s'"), src->buf);

	strbuf_addch(src, '/');
	src_len = src->len;
	strbuf_addch(dest, '/');
	dest_len = dest->len;

	while ((iter_status = dir_iterator_advance(iter)) == ITER_OK) {
		strbuf_setlen(src, src_len);
		strbuf_addstr(src, iter->relative_path);
		strbuf_setlen(dest, dest_len);
		strbuf_addstr(dest, iter->relative_path);

		if (S_ISDIR(iter->st.st_mode)) {
			mkdir_if_missing(dest->buf, 0777);
			continue;
		}

		/* Files that cannot be copied bit-for-bit... */
		if (!fspathcmp(iter->relative_path, "info/alternates")) {
			copy_alternates(src, src_repo);
			continue;
		}

		if (unlink(dest->buf) && errno != ENOENT)
			die_errno(_("failed to unlink '%s'"), dest->buf);
		if (!option_no_hardlinks) {
			strbuf_realpath(&realpath, src->buf, 1);
			if (!link(realpath.buf, dest->buf))
				continue;
			if (option_local > 0)
				die_errno(_("failed to create link '%s'"), dest->buf);
			option_no_hardlinks = 1;
		}
		if (copy_file_with_time(dest->buf, src->buf, 0666))
			die_errno(_("failed to copy file to '%s'"), dest->buf);
	}

	if (iter_status != ITER_DONE) {
		strbuf_setlen(src, src_len);
		die(_("failed to iterate over '%s'"), src->buf);
	}

	strbuf_release(&realpath);
}

static void clone_local(const char *src_repo, const char *dest_repo)
{
	if (option_shared) {
		struct strbuf alt = STRBUF_INIT;
		get_common_dir(&alt, src_repo);
		strbuf_addstr(&alt, "/objects");
		add_to_alternates_file(alt.buf);
		strbuf_release(&alt);
	} else {
		struct strbuf src = STRBUF_INIT;
		struct strbuf dest = STRBUF_INIT;
		get_common_dir(&src, src_repo);
		get_common_dir(&dest, dest_repo);
		strbuf_addstr(&src, "/objects");
		strbuf_addstr(&dest, "/objects");
		copy_or_link_directory(&src, &dest, src_repo);
		strbuf_release(&src);
		strbuf_release(&dest);
	}

	if (0 <= option_verbosity)
		fprintf(stderr, _("done.\n"));
}

static const char *junk_work_tree;
static int junk_work_tree_flags;
static const char *junk_git_dir;
static int junk_git_dir_flags;
static enum {
	JUNK_LEAVE_NONE,
	JUNK_LEAVE_REPO,
	JUNK_LEAVE_ALL
} junk_mode = JUNK_LEAVE_NONE;

static const char junk_leave_repo_msg[] =
N_("Clone succeeded, but checkout failed.\n"
   "You can inspect what was checked out with 'git status'\n"
   "and retry with 'git restore --source=HEAD :/'\n");

static void remove_junk(void)
{
	struct strbuf sb = STRBUF_INIT;

	switch (junk_mode) {
	case JUNK_LEAVE_REPO:
		warning("%s", _(junk_leave_repo_msg));
		/* fall-through */
	case JUNK_LEAVE_ALL:
		return;
	default:
		/* proceed to removal */
		break;
	}

	if (junk_git_dir) {
		strbuf_addstr(&sb, junk_git_dir);
		remove_dir_recursively(&sb, junk_git_dir_flags);
		strbuf_reset(&sb);
	}
	if (junk_work_tree) {
		strbuf_addstr(&sb, junk_work_tree);
		remove_dir_recursively(&sb, junk_work_tree_flags);
	}
	strbuf_release(&sb);
}

static void remove_junk_on_signal(int signo)
{
	remove_junk();
	sigchain_pop(signo);
	raise(signo);
}

static struct ref *find_remote_branch(const struct ref *refs, const char *branch)
{
	struct ref *ref;
	struct strbuf head = STRBUF_INIT;
	strbuf_addstr(&head, "refs/heads/");
	strbuf_addstr(&head, branch);
	ref = find_ref_by_name(refs, head.buf);
	strbuf_release(&head);

	if (ref)
		return ref;

	strbuf_addstr(&head, "refs/tags/");
	strbuf_addstr(&head, branch);
	ref = find_ref_by_name(refs, head.buf);
	strbuf_release(&head);

	return ref;
}

static struct ref *wanted_peer_refs(const struct ref *refs,
		struct refspec *refspec)
{
	struct ref *head = copy_ref(find_ref_by_name(refs, "HEAD"));
	struct ref *local_refs = head;
	struct ref **tail = head ? &head->next : &local_refs;

	if (option_single_branch) {
		struct ref *remote_head = NULL;

		if (!