fixed leading double slash issue

scrapy#44

.gitignore

@@ -13,4 +13,6 @@ dist/
 *venv*/
 
 # test
-.tox/
+.tox/
+
+.idea/

src/protego.py

@@ -174,6 +174,8 @@ def _quote_path(self, path):
     def _quote_pattern(self, pattern):
         if pattern.startswith("https://") or pattern.startswith("http://"):
             pattern = "/" + pattern
+        if pattern.startswith("//"):
+            pattern = "//" + pattern
 
         # Corner case for query only (e.g. '/abc?') and param only (e.g. '/abc;') URLs.
         # Save the last character otherwise, urlparse will kill it.

tests/test_protego.py

@@ -1122,6 +1122,16 @@ def test_bytestrings(self):
 
         self.assertEqual("Protego.parse expects str, got bytes", str(context.exception))
 
+    def test_leading_double_slash_in_pattern(self):
+        content = "User-Agent: *\nDisallow: //folder/*\n"
+        rp = Protego.parse(content)
+        self.assertTrue(rp.can_fetch("http://example.com/", "FooBot"))
+        self.assertTrue(rp.can_fetch("http://example.com/folder", "FooBot"))
+        self.assertTrue(rp.can_fetch("http://example.com/folder/", "FooBot"))
+        self.assertTrue(rp.can_fetch("http://example.com/folder/page", "FooBot"))
+        self.assertTrue(rp.can_fetch("http://example.com//folder", "FooBot"))
+        self.assertFalse(rp.can_fetch("http://example.com//folder/page", "FooBot"))
+
     def test_visit_time(self):
         """Some website specified allow time for crawling in UTC"""
         content = "User-Agent: *\nVisit-time: 0200 0630\nUser-Agent: NoTime"