Update url regex

The url regex also leads to catastrophic backtracking for the
file in #15, which causes a massive slowdown.

clevercsv/detect_type.py

@@ -85,7 +85,7 @@
     "number_1": "^(?=[+-\.\d])[+-]?(?:0|[1-9]\d*)?(((?P<dot>((?<=\d)\.|\.(?=\d)))?(?(dot)(?P<yes_dot>\d*(\d*[eE][+-]?\d+)?)|(?P<no_dot>((?<=\d)[eE][+-]?\d+)?)))|((?P<comma>,)?(?(comma)(?P<yes_comma>\d+(\d+[eE][+-]?\d+)?)|(?P<no_comma>((?<=\d)[eE][+-]?\d+)?))))$",
     "number_2": "[+-]?(?:[1-9]|[1-9]\d{0,2})(?:\,\d{3})+\.\d*",
     "number_3": "[+-]?(?:[1-9]|[1-9]\d{0,2})(?:\.\d{3})+\,\d*",
-    "url": "((https?|ftp):\/\/(?!\-))?(((([\p{L}\p{N}]*\-?[\p{L}\p{N}]+)+\.)+([a-z]{2,}|local)(\.[a-z]{2,3})?)|localhost|(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}(\:\d{1,5})?))(\/[\p{L}\p{N}_\/()~?=&%\-\#\.:]*)?(\.[a-z]+)?",
+    "url": "((https?|ftp):\/\/(?!\-))?(((?:[\p{L}\p{N}-]+\.)+([a-z]{2,}|local)(\.[a-z]{2,3})?)|localhost|(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}(\:\d{1,5})?))(\/[\p{L}\p{N}_\/()~?=&%\-\#\.:]*)?(\.[a-z]+)?",
     "email": r"(^[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+$)",
     "ipv4": "(?:\d{1,3}\.){3}\d{1,3}",
     "unicode_alphanum": "(\p{N}?\p{L}+[\p{N}\p{L}\ "

tests/test_unit/test_detect_type.py

@@ -287,8 +287,6 @@ def test_url(self):
             "http://?",
             "http://??",
             "http://??/",
-            "http://a.b--c.de/",
-            "http://a.b-.co",
             "http://foo.bar/foo(bar)baz quux",
             "http://foo.bar?q=Spaces should be encoded",
             "http://www.foo.bar./",