add IPv6 address parsing (#83)

* add IPv6 address parsing

* add tests with urls from https://www.ietf.org/rfc/rfc2732.txt

Author: JulianKahnert

tests/test_url.py

@@ -52,6 +52,13 @@
     u'http://127.0.10.150',
     u'http://localhost',
     u'http://localhost:8000',
+    u'http://[FEDC:BA98:7654:3210:FEDC:BA98:7654:3210]:80/index.html',
+    u'http://[1080:0:0:0:8:800:200C:417A]/index.html',
+    u'http://[3ffe:2a00:100:7031::1]',
+    u'http://[1080::8:800:200C:417A]/foo',
+    u'http://[::192.9.5.5]/ipng',
+    u'http://[::FFFF:129.144.52.38]:80/index.html',
+    u'http://[2010:836B:4179::836B:4179]',
 ])
 def test_returns_true_on_valid_url(address):
     assert url(address)
@@ -118,6 +125,9 @@ def test_returns_true_on_valid_public_url(address, public):
     'http://.www.foo.bar./',
     'http://127.12.0.260',
     'http://example.com/">user@example.com',
+    'http://[2010:836B:4179::836B:4179',
+    'http://2010:836B:4179::836B:4179',
+    'http://2010:836B:4179::836B:4179:80/index.html',
 ])
 def test_returns_failed_validation_on_invalid_url(address):
     assert isinstance(url(address), ValidationFailure)

validators/url.py

@@ -34,6 +34,40 @@
     u"" + ip_middle_octet + u"{2}"
     u"" + ip_last_octet + u")"
     u"|"
+    # IPv6 RegEx from https://stackoverflow.com/a/17871737
+    u"\[("
+    # 1:2:3:4:5:6:7:8
+    u"([0-9a-fA-F]{1,4}:){7,7}[0-9a-fA-F]{1,4}|"
+    # 1::                              1:2:3:4:5:6:7::
+    u"([0-9a-fA-F]{1,4}:){1,7}:|"
+    # 1::8             1:2:3:4:5:6::8  1:2:3:4:5:6::8
+    u"([0-9a-fA-F]{1,4}:){1,6}:[0-9a-fA-F]{1,4}|"
+    # 1::7:8           1:2:3:4:5::7:8  1:2:3:4:5::8
+    u"([0-9a-fA-F]{1,4}:){1,5}(:[0-9a-fA-F]{1,4}){1,2}|"
+    # 1::6:7:8         1:2:3:4::6:7:8  1:2:3:4::8
+    u"([0-9a-fA-F]{1,4}:){1,4}(:[0-9a-fA-F]{1,4}){1,3}|"
+    # 1::5:6:7:8       1:2:3::5:6:7:8  1:2:3::8
+    u"([0-9a-fA-F]{1,4}:){1,3}(:[0-9a-fA-F]{1,4}){1,4}|"
+    # 1::4:5:6:7:8     1:2::4:5:6:7:8  1:2::8
+    u"([0-9a-fA-F]{1,4}:){1,2}(:[0-9a-fA-F]{1,4}){1,5}|"
+    # 1::3:4:5:6:7:8   1::3:4:5:6:7:8  1::8
+    u"[0-9a-fA-F]{1,4}:((:[0-9a-fA-F]{1,4}){1,6})|"
+    # ::2:3:4:5:6:7:8  ::2:3:4:5:6:7:8 ::8       ::
+    u":((:[0-9a-fA-F]{1,4}){1,7}|:)|"
+    # fe80::7:8%eth0   fe80::7:8%1
+    # (link-local IPv6 addresses with zone index)
+    u"fe80:(:[0-9a-fA-F]{0,4}){0,4}%[0-9a-zA-Z]{1,}|"
+    u"::(ffff(:0{1,4}){0,1}:){0,1}"
+    u"((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}"
+    # ::255.255.255.255   ::ffff:255.255.255.255  ::ffff:0:255.255.255.255
+    # (IPv4-mapped IPv6 addresses and IPv4-translated addresses)
+    u"(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])|"
+    u"([0-9a-fA-F]{1,4}:){1,4}:"
+    u"((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}"
+    # 2001:db8:3:4::192.0.2.33  64:ff9b::192.0.2.33
+    # (IPv4-Embedded IPv6 Address)
+    u"(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])"
+    u")\]|"
     # host name
     u"(?:(?:[a-z\u00a1-\uffff0-9]-?)*[a-z\u00a1-\uffff0-9]+)"
     # domain name