Added stripping of leading and trailing whitespace from submission data (including email addresses) gleaned from submitted xml. Changed email line parsing to use email.utils.parseaddr() instead of a regex which only would handle unwuoted names (and possibly not utf-8 names) correctly.

 - Legacy-Id: 13423

Author: levkowetz

ietf/submit/forms.py

@@ -181,13 +181,13 @@ def clean(self):
                 author_info = self.xmlroot.findall('front/author')
                 for author in author_info:
                     author_dict = dict(
-                        company = author.findtext('organization'),
-                        last_name = author.attrib.get('surname'),
-                        full_name = author.attrib.get('fullname'),
-                        email = author.findtext('address/email'),
+                        company = author.findtext('organization').strip(),
+                        last_name = author.attrib.get('surname').strip(),
+                        full_name = author.attrib.get('fullname').strip(),
+                        email = author.findtext('address/email').strip(),
                     )
                     self.author_list.append(author_dict)
-                    line = "%(full_name)s <%(email)s>" % author_dict
+                    line = email.utils.formataddr((author_dict['full_name'], author_dict['email']))
                     self.authors.append(line)
             except forms.ValidationError:
                 raise

ietf/submit/models.py

@@ -1,5 +1,5 @@
-import re
 import datetime
+import email
 
 from django.db import models
 import jsonfield
@@ -15,12 +15,12 @@
 
 
 def parse_email_line(line):
-    """Split line on the form 'Some Name <email@example.com>'"""
-    m = re.match("([^<]+) <([^>]+)>$", line)
-    if m:
-        return dict(name=m.group(1), email=m.group(2))
-    else:
-        return dict(name=line, email="")
+    """
+    Split email address into name and email like
+    email.utils.parseaddr() but return a dictionary
+    """
+    name, addr = email.utils.parseaddr(line) if '@' in line else (line, '')
+    return dict(name=name, email=addr)
 
 class Submission(models.Model):
     state = models.ForeignKey(DraftSubmissionStateName)