Merge branch 'ps/guess-repo-name-at-root'

"git clone $URL", when cloning from a site whose sole purpose is to
host a single repository (hence, no path after <scheme>://<site>/),
tried to use the site name as the new repository name, but did not
remove username or password when <site> part was of the form
<user>@<pass>:<host>.  The code is taught to redact these.

* ps/guess-repo-name-at-root:
  clone: abort if no dir name could be guessed
  clone: do not use port number as dir name
  clone: do not include authentication data in guessed dir

1 files changed, 52 insertions, 10 deletions

diff --git a/builtin/clone.c b/builtin/clone.c
index bf451995a3..5169746b64 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -146,30 +146,68 @@ 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.
+	 * Strip trailing port number if we've got only a
+	 * hostname (that is, there is no dir separator but a
+	 * colon). This check is required such that we do not
+	 * strip URI's like '/foo/bar:2222.git', which should
+	 * result in a dir '2222' being guessed due to backwards
+	 * compatibility.
+	 */
+	if (memchr(start, '/', end - start) == NULL
+	    && memchr(start, ':', end - start) != NULL) {
+		ptr = end;
+		while (start < ptr && isdigit(ptr[-1]) && ptr[-1] != ':')
+			ptr--;
+		if (start < ptr && ptr[-1] == ':')
+			end = ptr - 1;
+	}
+
+	/*
+	 * 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}.
@@ -177,6 +215,10 @@ static char *guess_dir_name(const char *repo, int is_bundle, int is_bare)
 	len = end - start;
 	strip_suffix_mem(start, &len, is_bundle ? ".bundle" : ".git");
 
+	if (!len || (len == 1 && *start == '/'))
+	    die("No directory name could be guessed.\n"
+		"Please specify a directory on the command line");
+
 	if (is_bare)
 		dir = xstrfmt("%.*s.git", (int)len, start);
 	else