1 files changed, 268 insertions, 91 deletions

diff --git a/setup.c b/setup.c
index 8f64fbdfb..860507e1f 100644
--- a/setup.c
+++ b/setup.c
@@ -1,4 +1,6 @@
 #include "cache.h"
+#include "repository.h"
+#include "config.h"
 #include "dir.h"
 #include "string-list.h"
 
@@ -134,21 +136,30 @@ int path_inside_repo(const char *prefix, const char *path)
 
 int check_filename(const char *prefix, const char *arg)
 {
-	const char *name;
+	char *to_free = NULL;
 	struct stat st;
 
-	if (starts_with(arg, ":/")) {
-		if (arg[2] == '\0') /* ":/" is root dir, always exists */
+	if (skip_prefix(arg, ":/", &arg)) {
+		if (!*arg) /* ":/" is root dir, always exists */
 			return 1;
-		name = arg + 2;
-	} else if (prefix)
-		name = prefix_filename(prefix, strlen(prefix), arg);
-	else
-		name = arg;
-	if (!lstat(name, &st))
+		prefix = NULL;
+	} else if (skip_prefix(arg, ":!", &arg) ||
+		   skip_prefix(arg, ":^", &arg)) {
+		if (!*arg) /* excluding everything is silly, but allowed */
+			return 1;
+	}
+
+	if (prefix)
+		arg = to_free = prefix_filename(prefix, arg);
+
+	if (!lstat(arg, &st)) {
+		free(to_free);
 		return 1; /* file exists */
-	if (errno == ENOENT || errno == ENOTDIR)
+	}
+	if (is_missing_file_error(errno)) {
+		free(to_free);
 		return 0; /* file does not exist */
+	}
 	die_errno("failed to stat '%s'", arg);
 }
 
@@ -177,6 +188,24 @@ static void NORETURN die_verify_filename(const char *prefix,
 }
 
 /*
+ * Check for arguments that don't resolve as actual files,
+ * but which look sufficiently like pathspecs that we'll consider
+ * them such for the purposes of rev/pathspec DWIM parsing.
+ */
+static int looks_like_pathspec(const char *arg)
+{
+	/* anything with a wildcard character */
+	if (!no_wildcard(arg))
+		return 1;
+
+	/* long-form pathspec magic */
+	if (starts_with(arg, ":("))
+		return 1;
+
+	return 0;
+}
+
+/*
  * Verify a filename that we got as an argument for a pathspec
  * entry. Note that a filename that begins with "-" never verifies
  * as true, because even if such a filename were to exist, we want
@@ -202,7 +231,7 @@ void verify_filename(const char *prefix,
 {
 	if (*arg == '-')
 		die("bad flag '%s' used after filename", arg);
-	if (check_filename(prefix, arg) || !no_wildcard(arg))
+	if (looks_like_pathspec(arg) || check_filename(prefix, arg))
 		return;
 	die_verify_filename(prefix, arg, diagnose_misspelt_rev);
 }
@@ -370,6 +399,11 @@ void setup_work_tree(void)
 	if (getenv(GIT_WORK_TREE_ENVIRONMENT))
 		setenv(GIT_WORK_TREE_ENVIRONMENT, ".", 1);
 
+	/*
+	 * NEEDSWORK: this call can essentially be set_git_dir(get_git_dir())
+	 * which can cause some problems when trying to free the old value of
+	 * gitdir.
+	 */
 	set_git_dir(remove_leading_path(git_dir, work_tree));
 	initialized = 1;
 }
@@ -531,6 +565,7 @@ const char *read_gitfile_gently(const char *path, int *return_error_code)
 	ssize_t len;
 
 	if (stat(path, &st)) {
+		/* NEEDSWORK: discern between ENOENT vs other errors */
 		error_code = READ_GITFILE_ERR_STAT_FAILED;
 		goto cleanup_return;
 	}
@@ -697,11 +732,16 @@ static const char *setup_discovered_git_dir(const char *gitdir,
 
 	/* --work-tree is set without --git-dir; use discovered one */
 	if (getenv(GIT_WORK_TREE_ENVIRONMENT) || git_work_tree_cfg) {
+		char *to_free = NULL;
+		const char *ret;
+
 		if (offset != cwd->len && !is_absolute_path(gitdir))
-			gitdir = real_pathdup(gitdir, 1);
+			gitdir = to_free = real_pathdup(gitdir, 1);
 		if (chdir(cwd->buf))
 			die_errno("Could not come back to cwd");
-		return setup_explicit_git_dir(gitdir, cwd, nongit_ok);
+		ret = setup_explicit_git_dir(gitdir, cwd, nongit_ok);
+		free(to_free);
+		return ret;
 	}
 
 	/* #16.2, #17.2, #20.2, #21.2, #24, #25, #28, #29 (see t1510) */
@@ -721,8 +761,10 @@ static const char *setup_discovered_git_dir(const char *gitdir,
 	if (offset == cwd->len)
 		return NULL;
 
-	/* Make "offset" point to past the '/', and add a '/' at the end */
-	offset++;
+	/* Make "offset" point past the '/' (already the case for root dirs) */
+	if (offset != offset_1st_component(cwd->buf))
+		offset++;
+	/* Add a '/' at the end */
 	strbuf_addch(cwd, '/');
 	return cwd->buf + offset;
 }
@@ -740,7 +782,7 @@ static const char *setup_bare_git_dir(struct strbuf *cwd, int offset,
 
 	/* --work-tree is set without --git-dir; use discovered one */
 	if (getenv(GIT_WORK_TREE_ENVIRONMENT) || git_work_tree_cfg) {
-		const char *gitdir;
+		static const char *gitdir;
 
 		gitdir = offset == cwd->len ? "." : xmemdupz(cwd->buf, offset);
 		if (chdir(cwd->buf))
@@ -816,50 +858,51 @@ static int canonicalize_ceiling_entry(struct string_list_item *item,
 	}
 }
 
+enum discovery_result {
+	GIT_DIR_NONE = 0,
+	GIT_DIR_EXPLICIT,
+	GIT_DIR_DISCOVERED,
+	GIT_DIR_BARE,
+	/* these are errors */
+	GIT_DIR_HIT_CEILING = -1,
+	GIT_DIR_HIT_MOUNT_POINT = -2,
+	GIT_DIR_INVALID_GITFILE = -3
+};
+
 /*
  * We cannot decide in this function whether we are in the work tree or
  * not, since the config can only be read _after_ this function was called.
+ *
+ * Also, we avoid changing any global state (such as the current working
+ * directory) to allow early callers.
+ *
+ * The directory where the search should start needs to be passed in via the
+ * `dir` parameter; upon return, the `dir` buffer will contain the path of
+ * the directory where the search ended, and `gitdir` will contain the path of
+ * the discovered .git/ directory, if any. If `gitdir` is not absolute, it
+ * is relative to `dir` (i.e. *not* necessarily the cwd).
  */
-static const char *setup_git_directory_gently_1(int *nongit_ok)
+static enum discovery_result setup_git_directory_gently_1(struct strbuf *dir,
+							  struct strbuf *gitdir,
+							  int die_on_error)
 {
 	const char *env_ceiling_dirs = getenv(CEILING_DIRECTORIES_ENVIRONMENT);
 	struct string_list ceiling_dirs = STRING_LIST_INIT_DUP;
-	static struct strbuf cwd = STRBUF_INIT;
-	const char *gitdirenv, *ret;
-	char *gitfile;
-	int offset, offset_parent, ceil_offset = -1;
+	const char *gitdirenv;
+	int ceil_offset = -1, min_offset = has_dos_drive_prefix(dir->buf) ? 3 : 1;
 	dev_t current_device = 0;
 	int one_filesystem = 1;
 
 	/*
-	 * We may have read an incomplete configuration before
-	 * setting-up the git directory. If so, clear the cache so
-	 * that the next queries to the configuration reload complete
-	 * configuration (including the per-repo config file that we
-	 * ignored previously).
-	 */
-	git_config_clear();
-
-	/*
-	 * Let's assume that we are in a git repository.
-	 * If it turns out later that we are somewhere else, the value will be
-	 * updated accordingly.
-	 */
-	if (nongit_ok)
-		*nongit_ok = 0;
-
-	if (strbuf_getcwd(&cwd))
-		die_errno(_("Unable to read current working directory"));
-	offset = cwd.len;
-
-	/*
 	 * If GIT_DIR is set explicitly, we're not going
 	 * to do any discovery, but we still do repository
 	 * validation.
 	 */
 	gitdirenv = getenv(GIT_DIR_ENVIRONMENT);
-	if (gitdirenv)
-		return setup_explicit_git_dir(gitdirenv, &cwd, nongit_ok);
+	if (gitdirenv) {
+		strbuf_addstr(gitdir, gitdirenv);
+		return GIT_DIR_EXPLICIT;
+	}
 
 	if (env_ceiling_dirs) {
 		int empty_entry_found = 0;
@@ -867,15 +910,15 @@ static const char *setup_git_directory_gently_1(int *nongit_ok)
 		string_list_split(&ceiling_dirs, env_ceiling_dirs, PATH_SEP, -1);
 		filter_string_list(&ceiling_dirs, 0,
 				   canonicalize_ceiling_entry, &empty_entry_found);
-		ceil_offset = longest_ancestor_length(cwd.buf, &ceiling_dirs);
+		ceil_offset = longest_ancestor_length(dir->buf, &ceiling_dirs);
 		string_list_clear(&ceiling_dirs, 0);
 	}
 
-	if (ceil_offset < 0 && has_dos_drive_prefix(cwd.buf))
-		ceil_offset = 1;
+	if (ceil_offset < 0)
+		ceil_offset = min_offset - 2;
 
 	/*
-	 * Test in the following order (relative to the cwd):
+	 * Test in the following order (relative to the dir):
 	 * - .git (file containing "gitdir: <path>")
 	 * - .git/
 	 * - ./ (bare)
@@ -887,61 +930,171 @@ static const char *setup_git_directory_gently_1(int *nongit_ok)
 	 */
 	one_filesystem = !git_env_bool("GIT_DISCOVERY_ACROSS_FILESYSTEM", 0);
 	if (one_filesystem)
-		current_device = get_device_or_die(".", NULL, 0);
+		current_device = get_device_or_die(dir->buf, NULL, 0);
 	for (;;) {
-		gitfile = (char*)read_gitfile(DEFAULT_GIT_DIR_ENVIRONMENT);
-		if (gitfile)
-			gitdirenv = gitfile = xstrdup(gitfile);
-		else {
-			if (is_git_directory(DEFAULT_GIT_DIR_ENVIRONMENT))
-				gitdirenv = DEFAULT_GIT_DIR_ENVIRONMENT;
+		int offset = dir->len, error_code = 0;
+
+		if (offset > min_offset)
+			strbuf_addch(dir, '/');
+		strbuf_addstr(dir, DEFAULT_GIT_DIR_ENVIRONMENT);
+		gitdirenv = read_gitfile_gently(dir->buf, die_on_error ?
+						NULL : &error_code);
+		if (!gitdirenv) {
+			if (die_on_error ||
+			    error_code == READ_GITFILE_ERR_NOT_A_FILE) {
+				/* NEEDSWORK: fail if .git is not file nor dir */
+				if (is_git_directory(dir->buf))
+					gitdirenv = DEFAULT_GIT_DIR_ENVIRONMENT;
+			} else if (error_code != READ_GITFILE_ERR_STAT_FAILED)
+				return GIT_DIR_INVALID_GITFILE;
 		}
-
+		strbuf_setlen(dir, offset);
 		if (gitdirenv) {
-			ret = setup_discovered_git_dir(gitdirenv,
-						       &cwd, offset,
-						       nongit_ok);
-			free(gitfile);
-			return ret;
+			strbuf_addstr(gitdir, gitdirenv);
+			return GIT_DIR_DISCOVERED;
 		}
-		free(gitfile);
 
-		if (is_git_directory("."))
-			return setup_bare_git_dir(&cwd, offset, nongit_ok);
-
-		offset_parent = offset;
-		while (--offset_parent > ceil_offset && cwd.buf[offset_parent] != '/');
-		if (offset_parent <= ceil_offset)
-			return setup_nongit(cwd.buf, nongit_ok);
-		if (one_filesystem) {
-			dev_t parent_device = get_device_or_die("..", cwd.buf,
-								offset);
-			if (parent_device != current_device) {
-				if (nongit_ok) {
-					if (chdir(cwd.buf))
-						die_errno(_("Cannot come back to cwd"));
-					*nongit_ok = 1;
-					return NULL;
-				}
-				strbuf_setlen(&cwd, offset);
-				die(_("Not a git repository (or any parent up to mount point %s)\n"
-				"Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set)."),
-				    cwd.buf);
-			}
-		}
-		if (chdir("..")) {
-			strbuf_setlen(&cwd, offset);
-			die_errno(_("Cannot change to '%s/..'"), cwd.buf);
+		if (is_git_directory(dir->buf)) {
+			strbuf_addstr(gitdir, ".");
+			return GIT_DIR_BARE;
 		}
-		offset = offset_parent;
+
+		if (offset <= min_offset)
+			return GIT_DIR_HIT_CEILING;
+
+		while (--offset > ceil_offset && !is_dir_sep(dir->buf[offset]))
+			; /* continue */
+		if (offset <= ceil_offset)
+			return GIT_DIR_HIT_CEILING;
+
+		strbuf_setlen(dir, offset > min_offset ?  offset : min_offset);
+		if (one_filesystem &&
+		    current_device != get_device_or_die(dir->buf, NULL, offset))
+			return GIT_DIR_HIT_MOUNT_POINT;
 	}
 }
 
+int discover_git_directory(struct strbuf *commondir,
+			   struct strbuf *gitdir)
+{
+	struct strbuf dir = STRBUF_INIT, err = STRBUF_INIT;
+	size_t gitdir_offset = gitdir->len, cwd_len;
+	size_t commondir_offset = commondir->len;
+	struct repository_format candidate;
+
+	if (strbuf_getcwd(&dir))
+		return -1;
+
+	cwd_len = dir.len;
+	if (setup_git_directory_gently_1(&dir, gitdir, 0) <= 0) {
+		strbuf_release(&dir);
+		return -1;
+	}
+
+	/*
+	 * The returned gitdir is relative to dir, and if dir does not reflect
+	 * the current working directory, we simply make the gitdir absolute.
+	 */
+	if (dir.len < cwd_len && !is_absolute_path(gitdir->buf + gitdir_offset)) {
+		/* Avoid a trailing "/." */
+		if (!strcmp(".", gitdir->buf + gitdir_offset))
+			strbuf_setlen(gitdir, gitdir_offset);
+		else
+			strbuf_addch(&dir, '/');
+		strbuf_insert(gitdir, gitdir_offset, dir.buf, dir.len);
+	}
+
+	get_common_dir(commondir, gitdir->buf + gitdir_offset);
+
+	strbuf_reset(&dir);
+	strbuf_addf(&dir, "%s/config", commondir->buf + commondir_offset);
+	read_repository_format(&candidate, dir.buf);
+	strbuf_release(&dir);
+
+	if (verify_repository_format(&candidate, &err) < 0) {
+		warning("ignoring git dir '%s': %s",
+			gitdir->buf + gitdir_offset, err.buf);
+		strbuf_release(&err);
+		strbuf_setlen(commondir, commondir_offset);
+		strbuf_setlen(gitdir, gitdir_offset);
+		return -1;
+	}
+
+	return 0;
+}
+
 const char *setup_git_directory_gently(int *nongit_ok)
 {
-	const char *prefix;
+	static struct strbuf cwd = STRBUF_INIT;
+	struct strbuf dir = STRBUF_INIT, gitdir = STRBUF_INIT;
+	const char *prefix, *env_prefix;
+
+	/*
+	 * We may have read an incomplete configuration before
+	 * setting-up the git directory. If so, clear the cache so
+	 * that the next queries to the configuration reload complete
+	 * configuration (including the per-repo config file that we
+	 * ignored previously).
+	 */
+	git_config_clear();
+
+	/*
+	 * Let's assume that we are in a git repository.
+	 * If it turns out later that we are somewhere else, the value will be
+	 * updated accordingly.
+	 */
+	if (nongit_ok)
+		*nongit_ok = 0;
+
+	if (strbuf_getcwd(&cwd))
+		die_errno(_("Unable to read current working directory"));
+	strbuf_addbuf(&dir, &cwd);
+
+	switch (setup_git_directory_gently_1(&dir, &gitdir, 1)) {
+	case GIT_DIR_NONE:
+		prefix = NULL;
+		break;
+	case GIT_DIR_EXPLICIT:
+		prefix = setup_explicit_git_dir(gitdir.buf, &cwd, nongit_ok);
+		break;
+	case GIT_DIR_DISCOVERED:
+		if (dir.len < cwd.len && chdir(dir.buf))
+			die(_("Cannot change to '%s'"), dir.buf);
+		prefix = setup_discovered_git_dir(gitdir.buf, &cwd, dir.len,
+						  nongit_ok);
+		break;
+	case GIT_DIR_BARE:
+		if (dir.len < cwd.len && chdir(dir.buf))
+			die(_("Cannot change to '%s'"), dir.buf);
+		prefix = setup_bare_git_dir(&cwd, dir.len, nongit_ok);
+		break;
+	case GIT_DIR_HIT_CEILING:
+		prefix = setup_nongit(cwd.buf, nongit_ok);
+		break;
+	case GIT_DIR_HIT_MOUNT_POINT:
+		if (nongit_ok) {
+			*nongit_ok = 1;
+			strbuf_release(&cwd);
+			strbuf_release(&dir);
+			return NULL;
+		}
+		die(_("Not a git repository (or any parent up to mount point %s)\n"
+		      "Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set)."),
+		    dir.buf);
+	default:
+		die("BUG: unhandled setup_git_directory_1() result");
+	}
+
+	/*
+	 * NEEDSWORK: This was a hack in order to get ls-files and grep to have
+	 * properly formated output when recursing submodules.  Once ls-files
+	 * and grep have been changed to perform this recursing in-process this
+	 * needs to be removed.
+	 */
+	env_prefix = getenv(GIT_TOPLEVEL_PREFIX_ENVIRONMENT);
+	if (env_prefix)
+		prefix = env_prefix;
 
-	prefix = setup_git_directory_gently_1(nongit_ok);
 	if (prefix)
 		setenv(GIT_PREFIX_ENVIRONMENT, prefix, 1);
 	else
@@ -950,6 +1103,30 @@ const char *setup_git_directory_gently(int *nongit_ok)
 	startup_info->have_repository = !nongit_ok || !*nongit_ok;
 	startup_info->prefix = prefix;
 
+	/*
+	 * Not all paths through the setup code will call 'set_git_dir()' (which
+	 * directly sets up the environment) so in order to guarantee that the
+	 * environment is in a consistent state after setup, explicitly setup
+	 * the environment if we have a repository.
+	 *
+	 * NEEDSWORK: currently we allow bogus GIT_DIR values to be set in some
+	 * code paths so we also need to explicitly setup the environment if
+	 * the user has set GIT_DIR.  It may be beneficial to disallow bogus
+	 * GIT_DIR values at some point in the future.
+	 */
+	if (startup_info->have_repository || getenv(GIT_DIR_ENVIRONMENT)) {
+		if (!the_repository->gitdir) {
+			const char *gitdir = getenv(GIT_DIR_ENVIRONMENT);
+			if (!gitdir)
+				gitdir = DEFAULT_GIT_DIR_ENVIRONMENT;
+			repo_set_gitdir(the_repository, gitdir);
+			setup_git_env();
+		}
+	}
+
+	strbuf_release(&dir);
+	strbuf_release(&gitdir);
+
 	return prefix;
 }