From ac6b664fa5760c00ff6f284703fc2d883278ba51 Mon Sep 17 00:00:00 2001 From: Henrik Levkowetz Date: Mon, 2 Dec 2019 16:24:51 +0000 Subject: [PATCH] Added normalization of draft title extracted from submitted XML. - Legacy-Id: 17119 --- ietf/submit/forms.py | 2 ++ ietf/utils/text.py | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/ietf/submit/forms.py b/ietf/submit/forms.py index 9c97ed411..c1e54e017 100644 --- a/ietf/submit/forms.py +++ b/ietf/submit/forms.py @@ -48,6 +48,7 @@ from ietf.submit.parsers.ps_parser import PSParser 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 @@ class SubmissionBaseUploadForm(forms.Form): 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) diff --git a/ietf/utils/text.py b/ietf/utils/text.py index f65014cb3..c2190bdbe 100644 --- a/ietf/utils/text.py +++ b/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()