fetch: Strip usernames from url's before storing them

When pulling from a remote, the full URL including username
is by default added to the commit message. Since it adds
very little value but could be used by malicious people to
glean valid usernames (with matching hostnames), we're far
better off just stripping the username before storing the
remote URL locally.

Note that this patch has no lasting visible effect when
"git pull" does not create a merge commit. It simply
alters what gets written to .git/FETCH_HEAD, which is used
by "git merge" to automagically create its messages.

Signed-off-by: Andreas Ericsson <ae@op5.se>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 54 insertions, 2 deletions

diff --git a/builtin-fetch.c b/builtin-fetch.c
index 3c998ea740..0bb290bf2f 100644
--- a/builtin-fetch.c
+++ b/builtin-fetch.c
@@ -289,7 +289,7 @@ static int update_local_ref(struct ref *ref,
 	}
 }
 
-static int store_updated_refs(const char *url, const char *remote_name,
+static int store_updated_refs(const char *raw_url, const char *remote_name,
 		struct ref *ref_map)
 {
 	FILE *fp;
@@ -298,11 +298,13 @@ static int store_updated_refs(const char *url, const char *remote_name,
 	char note[1024];
 	const char *what, *kind;
 	struct ref *rm;
-	char *filename = git_path("FETCH_HEAD");
+	char *url, *filename = git_path("FETCH_HEAD");
 
 	fp = fopen(filename, "a");
 	if (!fp)
 		return error("cannot open %s: %s\n", filename, strerror(errno));
+
+	url = transport_anonymize_url(raw_url);
 	for (rm = ref_map; rm; rm = rm->next) {
 		struct ref *ref = NULL;
 
@@ -376,6 +378,7 @@ static int store_updated_refs(const char *url, const char *remote_name,
 				fprintf(stderr, " %s\n", note);
 		}
 	}
+	free(url);
 	fclose(fp);
 	if (rc & 2)
 		error("some local refs could not be updated; try running\n"
diff --git a/transport.c b/transport.c
index 3dfb03c06e..8ad317bf32 100644
--- a/transport.c
+++ b/transport.c
@@ -1083,3 +1083,51 @@ int transport_disconnect(struct transport *transport)
 	free(transport);
 	return ret;
 }
+
+/*
+ * Strip username (and password) from an url and return
+ * it in a newly allocated string.
+ */
+char *transport_anonymize_url(const char *url)
+{
+	char *anon_url, *scheme_prefix, *anon_part;
+	size_t anon_len, prefix_len = 0;
+
+	anon_part = strchr(url, '@');
+	if (is_local(url) || !anon_part)
+		goto literal_copy;
+
+	anon_len = strlen(++anon_part);
+	scheme_prefix = strstr(url, "://");
+	if (!scheme_prefix) {
+		if (!strchr(anon_part, ':'))
+			/* cannot be "me@there:/path/name" */
+			goto literal_copy;
+	} else {
+		const char *cp;
+		/* make sure scheme is reasonable */
+		for (cp = url; cp < scheme_prefix; cp++) {
+			switch (*cp) {
+				/* RFC 1738 2.1 */
+			case '+': case '.': case '-':
+				break; /* ok */
+			default:
+				if (isalnum(*cp))
+					break;
+				/* it isn't */
+				goto literal_copy;
+			}
+		}
+		/* @ past the first slash does not count */
+		cp = strchr(scheme_prefix + 3, '/');
+		if (cp && cp < anon_part)
+			goto literal_copy;
+		prefix_len = scheme_prefix - url + 3;
+	}
+	anon_url = xcalloc(1, 1 + prefix_len + anon_len);
+	memcpy(anon_url, url, prefix_len);
+	memcpy(anon_url + prefix_len, anon_part, anon_len);
+	return anon_url;
+literal_copy:
+	return xstrdup(url);
+}
diff --git a/transport.h b/transport.h
index b1c2252766..27bfc528ac 100644
--- a/transport.h
+++ b/transport.h
@@ -74,5 +74,6 @@ const struct ref *transport_get_remote_refs(struct transport *transport);
 int transport_fetch_refs(struct transport *transport, const struct ref *refs);
 void transport_unlock_pack(struct transport *transport);
 int transport_disconnect(struct transport *transport);
+char *transport_anonymize_url(const char *url);
 
 #endif