Issue 520 - Generate PAD files for download portals when updating download links

sitescripts/extensions/pad/validation.py

+# This file is part of the Adblock Plus web scripts,
+# Copyright (C) 2006-2014 Eyeo GmbH
+#
+# Adblock Plus is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 3 as
+# published by the Free Software Foundation.
+#
+# Adblock Plus is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with Adblock Plus.  If not, see <http://www.gnu.org/licenses/>.
+
 import itertools
 import warnings
 import re
 import urllib2
 from xml.dom import minidom
 
 FIELDS = [
   (['XML_DIZ_INFO', 'MASTER_PAD_VERSION_INFO', 'MASTER_PAD_VERSION'], r'^4\.0\Z'),
   (['XML_DIZ_INFO', 'MASTER_PAD_VERSION_INFO', 'MASTER_PAD_EDITOR'], r'^[^<\x09]{0,100}\Z'),
   (['XML_DIZ_INFO', 'MASTER_PAD_VERSION_INFO', 'MASTER_PAD_INFO'], r'^[^<\x09]{0,1000}\Z'),
@@ skipping 104 matching lines @@
   (['XML_DIZ_INFO', 'ASP', 'ASP_Member_Number'], None),
 ]
 
 def validate_fields(fields, nodes, filename):
   expected_nodes = set()
 
   for node_name, fields in itertools.groupby(fields, lambda (path, regex): path[0]):
     expected_nodes.add(node_name)
 
     regex = None
-    leaf = False
     nested_fields = []
     for path, regex_ in fields:
       if path == [node_name]:
         regex = regex_
-        leaf = True
       else:
         nested_fields.append((path[1:], regex_))
 
     found = False
     for node in nodes:
       if node.nodeName == node_name:
         if found:
           warnings.warn('invalid PAD file (duplicate node)\n'
                         'filename: %s\n'
                         'node:     %s' % (filename, node_name))
 
         if regex:
           value = ''.join(child.toxml() for child in node.childNodes)
           if not re.match(regex, value):
             warnings.warn('invalid PAD file (invalid value)\n'
                           'filename: %s\n'
                           'node:     %s\n'
                           'value:    %s\n'
                           'regex:    %s' % (filename, node_name, value, regex))
 
         if nested_fields:
-                validate_fields(nested_fields, node.childNodes, filename)
+          validate_fields(nested_fields, node.childNodes, filename)
 
         found = True
 
     if not found:
       if regex and not re.match(regex, ''):
         warnings.warn('invalid PAD file (missing node)\n'
                       'filename: %s\n'
                       'node:     %s' % (filename, node_name))
 
       validate_fields(nested_fields, [], filename)
@@ skipping 19 matching lines @@
   for field in doc.getElementsByTagName('Field'):
     path, regex  = [
       ''.join(node.nodeValue for node in field.getElementsByTagName(name)[0].childNodes)
       for name in ('Path', 'RegEx')
     ]
     print '  (%r, %s),' % (str(path).split('/'), "r'%s'" % regex if regex else 'None')
   print ']'
 
 if __name__ == '__main__':
   print_fields()