clone: do not include authentication data in guessed dir

If the URI contains authentication data and the URI's path
component is empty, we fail to guess a sensible directory name.
E.g. cloning a repository 'ssh://user:password@example.com/' we
guess a directory name 'password@example.com' where we would want
the hostname only, e.g. 'example.com'.

The naive way of just adding '@' as a path separator would break
cloning repositories like 'foo/bar@baz.git' (which would
currently become 'bar@baz' but would then become 'baz' only).
Instead fix this by first dropping the scheme and then greedily
scanning for an '@' sign until we find the first path separator.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 31 insertions, 10 deletions

diff --git a/builtin/clone.c b/builtin/clone.c
index ed484cb6f4..6aa286fd7b 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -146,30 +146,51 @@ static char *get_repo_path(const char *repo, int *is_bundle)
 
 static char *guess_dir_name(const char *repo, int is_bundle, int is_bare)
 {
-	const char *end = repo + strlen(repo), *start;
+	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 (repo < end && (is_dir_sep(end[-1]) || isspace(end[-1])))
+	while (start < end && (is_dir_sep(end[-1]) || isspace(end[-1])))
 		end--;
-	if (end - repo > 5 && is_dir_sep(end[-5]) &&
+	if (end - start > 5 && is_dir_sep(end[-5]) &&
 	    !strncmp(end - 4, ".git", 4)) {
 		end -= 5;
-		while (repo < end && is_dir_sep(end[-1]))
+		while (start < end && is_dir_sep(end[-1]))
 			end--;
 	}
 
 	/*
-	 * Find last component, but be prepared that repo could have
-	 * the form  "remote.example.com:foo.git", i.e. no slash
-	 * in the directory part.
+	 * 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.
 	 */
-	start = end;
-	while (repo < start && !is_dir_sep(start[-1]) && start[-1] != ':')
-		start--;
+	ptr = end;
+	while (start < ptr && !is_dir_sep(ptr[-1]) && ptr[-1] != ':')
+		ptr--;
+	start = ptr;
 
 	/*
 	 * Strip .{bundle,git}.