Issue 2234 - Add a WSGI controller to collect email addresses for the Adblock Browser iOS launch

sitescripts/utils.py

 # coding: utf-8
 
 # This file is part of the Adblock Plus web scripts,
 # Copyright (C) 2006-2015 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,
@@ skipping 95 matching lines @@
   config = get_config()
   if config.has_option('DEFAULT', 'mailerDebug') and config.get('DEFAULT', 'mailerDebug') == 'yes':
     (handle, path) = mkstemp(prefix='mail_', suffix='.eml', dir='.')
     os.close(handle)
     f = codecs.open(path, 'wb', encoding='utf-8')
     print >>f, mail
     f.close()
   else:
     subprocess.Popen([config.get('DEFAULT', 'mailer'), '-t'], stdin=subprocess.PIPE).communicate(mail.encode('utf-8'))
 
+def encode_email_address(email):
+  '''
+  Validates and encodes an email address.
+
+  The validation implemented here is very rudamentery and not meant
+  to be complete, as full email validation can get extremly complicated
+  and is rarely needed. This function is primarily making sure that the
+  email address contains no whitespaces and only valid ASCII characters.
+  '''
+  match = re.search(r'^([^@\s]+)@([^@\s]+)$', email)
+  if not match:
+    raise ValueError
+
+  try:
+    return email.encode('ascii')
+  except UnicodeEncodeError:
+    return '%s@%s' % (match.group(1).encode('ascii'),
+                      match.group(2).encode('idna'))

[Wladimir Palant, 2015/04/23 16:04:40]

This seems to have two issues:

1. match.group(1).encode('ascii') can fail and will produce another
UnicodeEncodeError - yet the caller is only expecting ValueError.

2. I'm unsure whether match.group(2).encode('idna') will work - it requires
unicode, not str. What do we have here?

[Sebastian Noack, 2015/04/23 16:29:41]

issubclass(UnicodeEncodeError, ValueError) => True
Sure, a function supposed to encode text, is supposed to be called with a
unicode object, as we do here.

+
 _template_cache = {}
 
 def get_template(template, autoescape=True):
   """Parses and returns a Jinja2 template"""
   key = (template, autoescape)
   if not key in _template_cache:
     if autoescape:
       env = get_template_environment()
     else:
       env = get_unescaped_template_environment()
@@ skipping 28 matching lines @@
     Returns a custom Jinja2 template environment with additional filters.
   """
   from sitescripts.templateFilters import filters
   import jinja2
   if not loader:
     loader = jinja2.FileSystemLoader(siteScriptsPath)
   env = jinja2.Environment(loader=loader, autoescape=True)
   env.filters.update(filters)
   env.filters.update(additional_filters)
   return env