Added normalization of draft title extracted from submitted XML.

 - Legacy-Id: 17119

Author: levkowetz

ietf/submit/forms.py

@@ -48,6 +48,7 @@
 from ietf.submit.parsers.xml_parser import XMLParser
 from ietf.utils import log
 from ietf.utils.draft import Draft
+from ietf.utils.text import normalize_text
 
 class SubmissionBaseUploadForm(forms.Form):
     xml = forms.FileField(label='.xml format', required=True)
@@ -204,6 +205,7 @@ def format_messages(where, e, log):
                 self.title = self.xmlroot.findtext('front/title').strip()
                 if type(self.title) is six.text_type:
                     self.title = unidecode(self.title)
+                self.title = normalize_text(self.title)
                 self.abstract = (self.xmlroot.findtext('front/abstract') or '').strip()
                 if type(self.abstract) is six.text_type:
                     self.abstract = unidecode(self.abstract)

ietf/utils/text.py

@@ -195,4 +195,4 @@ def unwrap(s):
     return s.replace('\n', ' ')
 
 def normalize_text(s):
-    return s.replace(r'\s+', ' ').strip()
+    return re.sub(r'[\s\u2028\u2029\n\r]+', ' ', s).strip()