Merge branch 'en/keep-cwd'

Many git commands that deal with working tree files try to remove a
directory that becomes empty (i.e. "git switch" from a branch that
has the directory to another branch that does not would attempt
remove all files in the directory and the directory itself).  This
drops users into an unfamiliar situation if the command was run in
a subdirectory that becomes subject to removal due to the command.
The commands have been taught to keep an empty directory if it is
the directory they were started in to avoid surprising users.

* en/keep-cwd:
  t2501: simplify the tests since we can now assume desired behavior
  dir: new flag to remove_dir_recurse() to spare the original_cwd
  dir: avoid incidentally removing the original_cwd in remove_path()
  stash: do not attempt to remove startup_info->original_cwd
  rebase: do not attempt to remove startup_info->original_cwd
  clean: do not attempt to remove startup_info->original_cwd
  symlinks: do not include startup_info->original_cwd in dir removal
  unpack-trees: add special cwd handling
  unpack-trees: refuse to remove startup_info->original_cwd
  setup: introduce startup_info->original_cwd
  t2501: add various tests for removing the current working directory

Author: gitster

builtin/clean.c

@@ -36,6 +36,8 @@ static const char *msg_skip_git_dir = N_("Skipping repository %s\n");
 static const char *msg_would_skip_git_dir = N_("Would skip repository %s\n");
 static const char *msg_warn_remove_failed = N_("failed to remove %s");
 static const char *msg_warn_lstat_failed = N_("could not lstat %s\n");
+static const char *msg_skip_cwd = N_("Refusing to remove current working directory\n");
+static const char *msg_would_skip_cwd = N_("Would refuse to remove current working directory\n");
 
 enum color_clean {
 	CLEAN_COLOR_RESET = 0,
@@ -153,6 +155,8 @@ static int remove_dirs(struct strbuf *path, const char *prefix, int force_flag,
 {
 	DIR *dir;
 	struct strbuf quoted = STRBUF_INIT;
+	struct strbuf realpath = STRBUF_INIT;
+	struct strbuf real_ocwd = STRBUF_INIT;
 	struct dirent *e;
 	int res = 0, ret = 0, gone = 1, original_len = path->len, len;
 	struct string_list dels = STRING_LIST_INIT_DUP;
@@ -231,16 +235,36 @@ static int remove_dirs(struct strbuf *path, const char *prefix, int force_flag,
 	strbuf_setlen(path, original_len);
 
 	if (*dir_gone) {
-		res = dry_run ? 0 : rmdir(path->buf);
-		if (!res)
-			*dir_gone = 1;
-		else {
-			int saved_errno = errno;
-			quote_path(path->buf, prefix, &quoted, 0);
-			errno = saved_errno;
-			warning_errno(_(msg_warn_remove_failed), quoted.buf);
+		/*
+		 * Normalize path components in path->buf, e.g. change '\' to
+		 * '/' on Windows.
+		 */
+		strbuf_realpath(&realpath, path->buf, 1);
+
+		/*
+		 * path and realpath are absolute; for comparison, we would
+		 * like to transform startup_info->original_cwd to an absolute
+		 * path too.
+		 */
+		 if (startup_info->original_cwd)
+			 strbuf_realpath(&real_ocwd,
+					 startup_info->original_cwd, 1);
+
+		if (!strbuf_cmp(&realpath, &real_ocwd)) {
+			printf("%s", dry_run ? _(msg_would_skip_cwd) : _(msg_skip_cwd));
 			*dir_gone = 0;
-			ret = 1;
+		} else {
+			res = dry_run ? 0 : rmdir(path->buf);
+			if (!res)
+				*dir_gone = 1;
+			else {
+				int saved_errno = errno;
+				quote_path(path->buf, prefix, &quoted, 0);
+				errno = saved_errno;
+				warning_errno(_(msg_warn_remove_failed), quoted.buf);
+				*dir_gone = 0;
+				ret = 1;
+			}
 		}
 	}
 
@@ -250,6 +274,8 @@ static int remove_dirs(struct strbuf *path, const char *prefix, int force_flag,
 			printf(dry_run ?  _(msg_would_remove) : _(msg_remove), dels.items[i].string);
 	}
 out:
+	strbuf_release(&realpath);
+	strbuf_release(&real_ocwd);
 	strbuf_release(&quoted);
 	string_list_clear(&dels, 0);
 	return ret;

builtin/rm.c

@@ -399,12 +399,13 @@ int cmd_rm(int argc, const char **argv, const char *prefix)
 	if (!index_only) {
 		int removed = 0, gitmodules_modified = 0;
 		struct strbuf buf = STRBUF_INIT;
+		int flag = force ? REMOVE_DIR_PURGE_ORIGINAL_CWD : 0;
 		for (i = 0; i < list.nr; i++) {
 			const char *path = list.entry[i].name;
 			if (list.entry[i].is_submodule) {
 				strbuf_reset(&buf);
 				strbuf_addstr(&buf, path);
-				if (remove_dir_recursively(&buf, 0))
+				if (remove_dir_recursively(&buf, flag))
 					die(_("could not remove '%s'"), path);
 
 				removed = 1;

builtin/stash.c

@@ -1538,8 +1538,10 @@ static int do_push_stash(const struct pathspec *ps, const char *stash_msg, int q
 			struct child_process cp = CHILD_PROCESS_INIT;
 
 			cp.git_cmd = 1;
+			if (startup_info->original_cwd)
+				cp.dir = startup_info->original_cwd;
 			strvec_pushl(&cp.args, "clean", "--force",
-				     "--quiet", "-d", NULL);
+				     "--quiet", "-d", ":/", NULL);
 			if (include_untracked == INCLUDE_ALL_FILES)
 				strvec_push(&cp.args, "-x");
 			if (run_command(&cp)) {

cache.h

@@ -1846,8 +1846,10 @@ void overlay_tree_on_index(struct index_state *istate,
 struct startup_info {
 	int have_repository;
 	const char *prefix;
+	const char *original_cwd;
 };
 extern struct startup_info *startup_info;
+extern const char *tmp_original_cwd;
 
 /* merge.c */
 struct commit_list;

common-main.c

@@ -26,6 +26,7 @@ static void restore_sigpipe_to_default(void)
 int main(int argc, const char **argv)
 {
 	int result;
+	struct strbuf tmp = STRBUF_INIT;
 
 	trace2_initialize_clock();
 
@@ -49,6 +50,9 @@ int main(int argc, const char **argv)
 	trace2_cmd_start(argv);
 	trace2_collect_process_info(TRACE2_PROCESS_INFO_STARTUP);
 
+	if (!strbuf_getcwd(&tmp))
+		tmp_original_cwd = strbuf_detach(&tmp, NULL);
+
 	result = cmd_main(argc, argv);
 
 	/*

dir.c

@@ -3160,6 +3160,7 @@ static int remove_dir_recurse(struct strbuf *path, int flag, int *kept_up)
 	int ret = 0, original_len = path->len, len, kept_down = 0;
 	int only_empty = (flag & REMOVE_DIR_EMPTY_ONLY);
 	int keep_toplevel = (flag & REMOVE_DIR_KEEP_TOPLEVEL);
+	int purge_original_cwd = (flag & REMOVE_DIR_PURGE_ORIGINAL_CWD);
 	struct object_id submodule_head;
 
 	if ((flag & REMOVE_DIR_KEEP_NESTED_GIT) &&
@@ -3215,9 +3216,14 @@ static int remove_dir_recurse(struct strbuf *path, int flag, int *kept_up)
 	closedir(dir);
 
 	strbuf_setlen(path, original_len);
-	if (!ret && !keep_toplevel && !kept_down)
-		ret = (!rmdir(path->buf) || errno == ENOENT) ? 0 : -1;
-	else if (kept_up)
+	if (!ret && !keep_toplevel && !kept_down) {
+		if (!purge_original_cwd &&
+		    startup_info->original_cwd &&
+		    !strcmp(startup_info->original_cwd, path->buf))
+			ret = -1; /* Do not remove current working directory */
+		else
+			ret = (!rmdir(path->buf) || errno == ENOENT) ? 0 : -1;
+	} else if (kept_up)
 		/*
 		 * report the uplevel that it is not an error that we
 		 * did not rmdir() our directory.
@@ -3283,6 +3289,9 @@ int remove_path(const char *name)
 		slash = dirs + (slash - name);
 		do {
 			*slash = '\0';
+			if (startup_info->original_cwd &&
+			    !strcmp(startup_info->original_cwd, dirs))
+				break;
 		} while (rmdir(dirs) == 0 && (slash = strrchr(dirs, '/')));
 		free(dirs);
 	}

dir.h

@@ -495,6 +495,9 @@ int get_sparse_checkout_patterns(struct pattern_list *pl);
 /* Remove the contents of path, but leave path itself. */
 #define REMOVE_DIR_KEEP_TOPLEVEL 04
 
+/* Remove the_original_cwd too */
+#define REMOVE_DIR_PURGE_ORIGINAL_CWD 0x08
+
 /*
  * Remove path and its contents, recursively. flags is a combination
  * of the above REMOVE_DIR_* constants. Return 0 on success.
@@ -504,7 +507,11 @@ int get_sparse_checkout_patterns(struct pattern_list *pl);
  */
 int remove_dir_recursively(struct strbuf *path, int flag);
 
-/* tries to remove the path with empty directories along it, ignores ENOENT */
+/*
+ * Tries to remove the path, along with leading empty directories so long as
+ * those empty directories are not startup_info->original_cwd.  Ignores
+ * ENOENT.
+ */
 int remove_path(const char *path);
 
 int fspathcmp(const char *a, const char *b);

sequencer.c

@@ -4223,6 +4223,8 @@ static int run_git_checkout(struct repository *r, struct replay_opts *opts,
 
 	cmd.git_cmd = 1;
 
+	if (startup_info->original_cwd)
+		cmd.dir = startup_info->original_cwd;
 	strvec_push(&cmd.args, "checkout");
 	strvec_push(&cmd.args, commit);
 	strvec_pushf(&cmd.env_array, GIT_REFLOG_ACTION "=%s", action);

setup.c

@@ -12,6 +12,7 @@ static int work_tree_config_is_bogus;
 
 static struct startup_info the_startup_info;
 struct startup_info *startup_info = &the_startup_info;
+const char *tmp_original_cwd;
 
 /*
  * The input parameter must contain an absolute path, and it must already be
@@ -432,6 +433,69 @@ void setup_work_tree(void)
 	initialized = 1;
 }
 
+static void setup_original_cwd(void)
+{
+	struct strbuf tmp = STRBUF_INIT;
+	const char *worktree = NULL;
+	int offset = -1;
+
+	if (!tmp_original_cwd)
+		return;
+
+	/*
+	 * startup_info->original_cwd points to the current working
+	 * directory we inherited from our parent process, which is a
+	 * directory we want to avoid removing.
+	 *
+	 * For convience, we would like to have the path relative to the
+	 * worktree instead of an absolute path.
+	 *
+	 * Yes, startup_info->original_cwd is usually the same as 'prefix',
+	 * but differs in two ways:
+	 *   - prefix has a trailing '/'
+	 *   - if the user passes '-C' to git, that modifies the prefix but
+	 *     not startup_info->original_cwd.
+	 */
+
+	/* Normalize the directory */
+	strbuf_realpath(&tmp, tmp_original_cwd, 1);
+	free((char*)tmp_original_cwd);
+	tmp_original_cwd = NULL;
+	startup_info->original_cwd = strbuf_detach(&tmp, NULL);
+
+	/*
+	 * Get our worktree; we only protect the current working directory
+	 * if it's in the worktree.
+	 */
+	worktree = get_git_work_tree();
+	if (!worktree)
+		goto no_prevention_needed;
+
+	offset = dir_inside_of(startup_info->original_cwd, worktree);
+	if (offset >= 0) {
+		/*
+		 * If startup_info->original_cwd == worktree, that is already
+		 * protected and we don't need original_cwd as a secondary
+		 * protection measure.
+		 */
+		if (!*(startup_info->original_cwd + offset))
+			goto no_prevention_needed;
+
+		/*
+		 * original_cwd was inside worktree; precompose it just as
+		 * we do prefix so that built up paths will match
+		 */
+		startup_info->original_cwd = \
+			precompose_string_if_needed(startup_info->original_cwd
+						    + offset);
+		return;
+	}
+
+no_prevention_needed:
+	free((char*)startup_info->original_cwd);
+	startup_info->original_cwd = NULL;
+}
+
 static int read_worktree_config(const char *var, const char *value, void *vdata)
 {
 	struct repository_format *data = vdata;
@@ -1330,6 +1394,7 @@ const char *setup_git_directory_gently(int *nongit_ok)
 		setenv(GIT_PREFIX_ENVIRONMENT, "", 1);
 	}
 
+	setup_original_cwd();
 
 	strbuf_release(&dir);
 	strbuf_release(&gitdir);

symlinks.c

@@ -279,7 +279,9 @@ static void do_remove_scheduled_dirs(int new_len)
 {
 	while (removal.len > new_len) {
 		removal.buf[removal.len] = '\0';
-		if (rmdir(removal.buf))
+		if ((startup_info->original_cwd &&
+		     !strcmp(removal.buf, startup_info->original_cwd)) ||
+		    rmdir(removal.buf))
 			break;
 		do {
 			removal.len--;
@@ -293,6 +295,10 @@ void schedule_dir_for_removal(const char *name, int len)
 {
 	int match_len, last_slash, i, previous_slash;
 
+	if (startup_info->original_cwd &&
+	    !strcmp(name, startup_info->original_cwd))
+		return;	/* Do not remove the current working directory */
+
 	match_len = last_slash = i =
 		longest_path_match(name, len, removal.buf, removal.len,
 				   &previous_slash);