[PATCH v3 3/6] clone: do not include authentication data in guessed dir

From: Patrick Steinhardt <ps@pks.im>
Date: Aug 4, 2015, 11:29 UTC
Message-ID: <1438687797-14254-4-git-send-email-ps@pks.im>
In-Reply-To: <1438687797-14254-1-git-send-email-ps@pks.im>

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'.

Fix this by first skipping authentication data.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
 builtin/clone.c | 46 +++++++++++++++++++++++++++++++++++-----------
 1 file changed, 35 insertions(+), 11 deletions(-)

diff --git a/builtin/clone.c b/builtin/clone.c
index a72ff7e..794a933 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -146,35 +146,59 @@ 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.
+	 */
+	ptr = start;
+	while (ptr < end && !is_dir_sep(*ptr) && *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. This is skipped if the
+	 * current path does not contain any path separators.
 	 */
-	start = end;
-	while (repo < start && !is_dir_sep(start[-1]) && start[-1] != ':')
-		start--;
+	if (memchr(start, '/', end - start) != NULL
+	    || memchr(start, ':', end - start) != NULL) {
+		start = end;
+		while (!is_dir_sep(start[-1]) && start[-1] != ':')
+			start--;
+	}
+	len = end - start;
 
 	/*
 	 * Strip .{bundle,git}.
 	 */
-	strip_suffix(start, is_bundle ? ".bundle" : ".git" , &len);
+	strip_suffix_mem(start, &len, is_bundle ? ".bundle" : ".git");
 
 	if (is_bare)
 		dir = xstrfmt("%.*s.git", (int)len, start);

-- 
2.5.0