[PATCH v2 5/6] clone: fix hostname parsing when guessing dir

[Patrick Steinhardt <ps@pks.im>]

We fail to guess a sensible directory name for a newly cloned
repository when the path component of the URL is empty. E.g.
cloning a repository 'ssh://user:password@example.com/' we create
a directory 'password@example.com' for the clone.

Fix this by using parse_connect_url to split host and path
components and explicitly checking whether we need to fall back
to the hostname for guessing a directory name.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
 builtin/clone.c | 73 +++++++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 53 insertions(+), 20 deletions(-)

diff --git a/builtin/clone.c b/builtin/clone.c
index a72ff7e..4547729 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -9,6 +9,7 @@
  */
 
 #include "builtin.h"
+#include "connect.h"
 #include "lockfile.h"
 #include "parse-options.h"
 #include "fetch-pack.h"
@@ -147,34 +148,62 @@ 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;
+	char *host, *path;
 	size_t len;
 	char *dir;
 
+	parse_connect_url(repo, &host, &path);
 	/*
-	 * Strip trailing spaces, slashes and /.git
+	 * If the path component of the URL is empty (e.g. it is
+	 * empty or only contains a '/') we fall back to the host
+	 * name.
 	 */
-	while (repo < end && (is_dir_sep(end[-1]) || isspace(end[-1])))
-		end--;
-	if (end - repo > 5 && is_dir_sep(end[-5]) &&
-	    !strncmp(end - 4, ".git", 4)) {
-		end -= 5;
-		while (repo < end && is_dir_sep(end[-1]))
+	if (!path || !*path || !strcmp(path, "/")) {
+		if (*host == '\0')
+			die("No directory name could be guessed.\n"
+				"Please specify a directory on the command line");
+		/*
+		 * Strip authentication information if it exists.
+		 */
+		start = strchr(host, '@');
+		if (start)
+			start++;
+		else
+			start = host;
+		/*
+		 * Strip port if it exitsts.
+		 */
+		end = strchr(start, ':');
+		if (!end)
+			end = start + strlen(start);
+		len = end - start;
+	} else {
+		/*
+		 * Strip trailing spaces, slashes and /.git
+		 */
+		while (repo < end && (is_dir_sep(end[-1]) || isspace(end[-1])))
 			end--;
-	}
+		if (end - repo > 5 && is_dir_sep(end[-5]) &&
+			!strncmp(end - 4, ".git", 4)) {
+			end -= 5;
+			while (repo < 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.
-	 */
-	start = end;
-	while (repo < start && !is_dir_sep(start[-1]) && start[-1] != ':')
-		start--;
+		/*
+		 * 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.
+		 */
+		start = end;
+		while (repo < start && !is_dir_sep(start[-1]) && start[-1] != ':')
+			start--;
 
-	/*
-	 * Strip .{bundle,git}.
-	 */
-	strip_suffix(start, is_bundle ? ".bundle" : ".git" , &len);
+		/*
+		 * Strip .{bundle,git}.
+		 */
+		strip_suffix(start, is_bundle ? ".bundle" : ".git" , &len);
+	}
 
 	if (is_bare)
 		dir = xstrfmt("%.*s.git", (int)len, start);
@@ -203,6 +232,10 @@ static char *guess_dir_name(const char *repo, int is_bundle, int is_bare)
 		if (out > dir && prev_space)
 			out[-1] = '\0';
 	}
+
+	free(host);
+	free(path);
+
 	return dir;
 }
 
-- 
2.5.0