connect.c: refactor url parsing

Make the function is_local() in transport.c public, rename it into
url_is_local_not_ssh() and use it in both transport.c and connect.c

Use a protocol "local" for URLs for the local file system.

One note about using file:// under Windows:

The (absolute) path on Unix like system typically starts with "/".
When the host is empty, it can be omitted, so that a shell scriptlet
url=file://$pwd
will give a URL like "file:///home/user/repo".

Windows does not have the same concept of a root directory located in "/".
When parsing the URL allow "file://C:/user/repo"
(even if RFC1738 indicates that "file:///C:/user/repo" should be used).

Signed-off-by: Torsten Bögershausen <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: tboegi

connect.c

@@ -232,14 +232,24 @@ int server_supports(const char *feature)
 
 enum protocol {
 	PROTO_LOCAL = 1,
+	PROTO_FILE,
 	PROTO_SSH,
 	PROTO_GIT
 };
 
+int url_is_local_not_ssh(const char *url)
+{
+	const char *colon = strchr(url, ':');
+	const char *slash = strchr(url, '/');
+	return !colon || (slash && slash < colon) ||
+		has_dos_drive_prefix(url);
+}
+
 static const char *prot_name(enum protocol protocol)
 {
 	switch (protocol) {
 		case PROTO_LOCAL:
+		case PROTO_FILE:
 			return "file";
 		case PROTO_SSH:
 			return "ssh";
@@ -261,7 +271,7 @@ static enum protocol get_protocol(const char *name)
 	if (!strcmp(name, "ssh+git"))
 		return PROTO_SSH;
 	if (!strcmp(name, "file"))
-		return PROTO_LOCAL;
+		return PROTO_FILE;
 	die("I don't handle protocol '%s'", name);
 }
 
@@ -564,9 +574,8 @@ static enum protocol parse_connect_url(const char *url_orig, char **ret_host,
 	char *url;
 	char *host, *path;
 	char *end;
-	int separator;
+	int separator = '/';
 	enum protocol protocol = PROTO_LOCAL;
-	int free_path = 0;
 
 	if (is_url(url_orig))
 		url = url_decode(url_orig);
@@ -578,10 +587,12 @@ static enum protocol parse_connect_url(const char *url_orig, char **ret_host,
 		*host = '\0';
 		protocol = get_protocol(url);
 		host += 3;
-		separator = '/';
 	} else {
 		host = url;
-		separator = ':';
+		if (!url_is_local_not_ssh(url)) {
+			protocol = PROTO_SSH;
+			separator = ':';
+		}
 	}
 
 	/*
@@ -597,17 +608,12 @@ static enum protocol parse_connect_url(const char *url_orig, char **ret_host,
 	} else
 		end = host;
 
-	path = strchr(end, separator);
-	if (path && !has_dos_drive_prefix(end)) {
-		if (separator == ':') {
-			if (host != url || path < strchrnul(host, '/')) {
-				protocol = PROTO_SSH;
-				*path++ = '\0';
-			} else /* '/' in the host part, assume local path */
-				path = end;
-		}
-	} else
+	if (protocol == PROTO_LOCAL)
 		path = end;
+	else if (protocol == PROTO_FILE && has_dos_drive_prefix(end))
+		path = end; /* "file://$(pwd)" may be "file://C:/projects/repo" */
+	else
+		path = strchr(end, separator);
 
 	if (!path || !*path)
 		die("No path specified. See 'man git-pull' for valid url syntax");
@@ -616,23 +622,20 @@ static enum protocol parse_connect_url(const char *url_orig, char **ret_host,
 	 * null-terminate hostname and point path to ~ for URL's like this:
 	 *    ssh://host.xz/~user/repo
 	 */
-	if (protocol != PROTO_LOCAL) {
-		char *ptr = path;
+
+	end = path; /* Need to \0 terminate host here */
+	if (separator == ':')
+		path++; /* path starts after ':' */
+	if (protocol == PROTO_GIT || protocol == PROTO_SSH) {
 		if (path[1] == '~')
 			path++;
-		else {
-			path = xstrdup(ptr);
-			free_path = 1;
-		}
-
-		*ptr = '\0';
 	}
 
+	path = xstrdup(path);
+	*end = '\0';
+
 	*ret_host = xstrdup(host);
-	if (free_path)
-		*ret_path = path;
-	else
-		*ret_path = xstrdup(path);
+	*ret_path = path;
 	free(url);
 	return protocol;
 }

connect.h

@@ -9,5 +9,6 @@ extern int git_connection_is_socket(struct child_process *conn);
 extern int server_supports(const char *feature);
 extern int parse_feature_request(const char *features, const char *feature);
 extern const char *server_feature_value(const char *feature, int *len_ret);
+extern int url_is_local_not_ssh(const char *url);
 
 #endif

t/t5500-fetch-pack.sh

@@ -612,4 +612,11 @@ do
 	done
 done
 
+test_expect_success MINGW 'fetch-pack --diag-url file://c:/repo' '
+	check_prot_path file://c:/repo file c:/repo
+'
+test_expect_success MINGW 'fetch-pack --diag-url c:repo' '
+	check_prot_path c:repo file c:repo
+'
+
 test_done

t/t5601-clone.sh

@@ -362,6 +362,14 @@ do
 		test_clone_url [::1]:$repo ::1 $repo
 	'
 done
+#home directory
+test_expect_success "clone host:/~repo" '
+	test_clone_url host:/~repo host "~repo"
+'
+
+test_expect_success "clone [::1]:/~repo" '
+	test_clone_url [::1]:/~repo ::1 "~repo"
+'
 
 # Corner cases
 for url in foo/bar:baz [foo]bar/baz:qux [foo/bar]:baz

transport.c

@@ -885,14 +885,6 @@ void transport_take_over(struct transport *transport,
 	transport->cannot_reuse = 1;
 }
 
-static int is_local(const char *url)
-{
-	const char *colon = strchr(url, ':');
-	const char *slash = strchr(url, '/');
-	return !colon || (slash && slash < colon) ||
-		has_dos_drive_prefix(url);
-}
-
 static int is_file(const char *url)
 {
 	struct stat buf;
@@ -941,7 +933,7 @@ struct transport *transport_get(struct remote *remote, const char *url)
 		ret->fetch = fetch_objs_via_rsync;
 		ret->push = rsync_transport_push;
 		ret->smart_options = NULL;
-	} else if (is_local(url) && is_file(url) && is_bundle(url, 1)) {
+	} else if (url_is_local_not_ssh(url) && is_file(url) && is_bundle(url, 1)) {
 		struct bundle_transport_data *data = xcalloc(1, sizeof(*data));
 		ret->data = data;
 		ret->get_refs_list = get_refs_from_bundle;
@@ -1297,7 +1289,7 @@ char *transport_anonymize_url(const char *url)
 	size_t anon_len, prefix_len = 0;
 
 	anon_part = strchr(url, '@');
-	if (is_local(url) || !anon_part)
+	if (url_is_local_not_ssh(url) || !anon_part)
 		goto literal_copy;
 
 	anon_len = strlen(++anon_part);