From 9e5ef7ed0f512e953951075010d86d9a5cd3e88a Mon Sep 17 00:00:00 2001
From: Pierre-Yves Chibon <pingou@pingoured.fr>
Date: Dec 22 2016 14:07:17 +0000
Subject: Move the regex to validate an URL to the pagure module so it can easily be re-used


---

diff --git a/pagure/__init__.py b/pagure/__init__.py
index 488f1ce..493a4c1 100644
--- a/pagure/__init__.py
+++ b/pagure/__init__.py
@@ -19,6 +19,7 @@ __api_version__ = '0.10'
 import datetime
 import logging
 import os
+import re
 import subprocess
 import urlparse
 from logging.handlers import SMTPHandler
@@ -608,6 +609,52 @@ def get_remote_repo_path(remote_git, branch_from, loop=False):
     return repopath
 
 
+ip_middle_octet = u"(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5]))"
+ip_last_octet = u"(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))"
+
+"""
+regex based on https://github.com/kvesteri/validators/blob/master/validators/url.py
+"""
+urlregex = re.compile(
+    u"^"
+    # protocol identifier
+    u"(?:(?:https?|ftp)://)"
+    # user:pass authentication
+    u"(?:\S+(?::\S*)?@)?"
+    u"(?:"
+    u"(?P<private_ip>"
+    # IP address exclusion
+    # private & local networks
+    u"(?:(?:10|127)" + ip_middle_octet + u"{2}" + ip_last_octet + u")|"
+    u"(?:(?:169\.254|192\.168)" + ip_middle_octet + ip_last_octet + u")|"
+    u"(?:172\.(?:1[6-9]|2\d|3[0-1])" + ip_middle_octet + ip_last_octet + u"))"
+    u"|"
+    # IP address dotted notation octets
+    # excludes loopback network 0.0.0.0
+    # excludes reserved space >= 224.0.0.0
+    # excludes network & broadcast addresses
+    # (first & last IP address of each class)
+    u"(?P<public_ip>"
+    u"(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])"
+    u"" + ip_middle_octet + u"{2}"
+    u"" + ip_last_octet + u")"
+    u"|"
+    # host name
+    u"(?:(?:[a-z\u00a1-\uffff0-9]-?)*[a-z\u00a1-\uffff0-9]+)"
+    # domain name
+    u"(?:\.(?:[a-z\u00a1-\uffff0-9]-?)*[a-z\u00a1-\uffff0-9]+)*"
+    # TLD identifier
+    u"(?:\.(?:[a-z\u00a1-\uffff]{2,}))"
+    u")"
+    # port number
+    u"(?::\d{2,5})?"
+    # resource path
+    u"(?:/\S*)?"
+    u"$",
+    re.UNICODE | re.IGNORECASE
+)
+urlpattern = re.compile(urlregex)
+
 # Import the application
 import pagure.ui.app
 import pagure.ui.admin
diff --git a/pagure/ui/issues.py b/pagure/ui/issues.py
index 9f9fb23..0aad641 100644
--- a/pagure/ui/issues.py
+++ b/pagure/ui/issues.py
@@ -26,7 +26,6 @@ from binaryornot.helpers import is_binary_string
 
 import kitchen.text.converters as ktc
 import mimetypes
-import re
 
 import pagure.doc_utils
 import pagure.exceptions
@@ -34,54 +33,7 @@ import pagure.lib
 import pagure.lib.encoding_utils
 import pagure.forms
 from pagure import (APP, SESSION, LOG, __get_file_in_tree,
-                    login_required, authenticated)
-
-
-ip_middle_octet = u"(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5]))"
-ip_last_octet = u"(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))"
-
-"""
-regex based on https://github.com/kvesteri/validators/blob/master/validators/url.py
-"""
-urlregex = re.compile(
-    u"^"
-    # protocol identifier
-    u"(?:(?:https?|ftp)://)"
-    # user:pass authentication
-    u"(?:\S+(?::\S*)?@)?"
-    u"(?:"
-    u"(?P<private_ip>"
-    # IP address exclusion
-    # private & local networks
-    u"(?:(?:10|127)" + ip_middle_octet + u"{2}" + ip_last_octet + u")|"
-    u"(?:(?:169\.254|192\.168)" + ip_middle_octet + ip_last_octet + u")|"
-    u"(?:172\.(?:1[6-9]|2\d|3[0-1])" + ip_middle_octet + ip_last_octet + u"))"
-    u"|"
-    # IP address dotted notation octets
-    # excludes loopback network 0.0.0.0
-    # excludes reserved space >= 224.0.0.0
-    # excludes network & broadcast addresses
-    # (first & last IP address of each class)
-    u"(?P<public_ip>"
-    u"(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])"
-    u"" + ip_middle_octet + u"{2}"
-    u"" + ip_last_octet + u")"
-    u"|"
-    # host name
-    u"(?:(?:[a-z\u00a1-\uffff0-9]-?)*[a-z\u00a1-\uffff0-9]+)"
-    # domain name
-    u"(?:\.(?:[a-z\u00a1-\uffff0-9]-?)*[a-z\u00a1-\uffff0-9]+)*"
-    # TLD identifier
-    u"(?:\.(?:[a-z\u00a1-\uffff]{2,}))"
-    u")"
-    # port number
-    u"(?::\d{2,5})?"
-    # resource path
-    u"(?:/\S*)?"
-    u"$",
-    re.UNICODE | re.IGNORECASE
-)
-urlpattern = re.compile(urlregex)
+                    login_required, authenticated, urlpattern)
 
 
 # URLs