feat: limit line width for PlaintextDraft

ietf/submit/utils.py

@@ -770,70 +770,6 @@ def save_files(form):
         log.log("saved file %s" % name)
     return file_name
 
-def get_draft_meta(form, saved_files):
-    authors = []
-    file_name = saved_files
-
-    if form.cleaned_data['xml']:
-        # Some meta-information, such as the page-count, can only
-        # be retrieved from the generated text file.  Provide a
-        # parsed draft object to get at that kind of information.
-        file_name['txt'] = os.path.join(settings.IDSUBMIT_STAGING_PATH, '%s-%s.txt' % (form.filename, form.revision))
-        file_size = os.stat(file_name['txt']).st_size
-        with io.open(file_name['txt']) as txt_file:
-            form.parsed_draft = PlaintextDraft(txt_file.read(), txt_file.name)
-    else:
-        file_size = form.cleaned_data['txt'].size
-
-    if form.authors:
-        authors = form.authors
-    else:
-        # If we don't have an xml file, try to extract the
-        # relevant information from the text file
-        for author in form.parsed_draft.get_author_list():
-            full_name, first_name, middle_initial, last_name, name_suffix, email, country, company = author
-
-            name = full_name.replace("\n", "").replace("\r", "").replace("<", "").replace(">", "").strip()
-
-            if email:
-                try:
-                    validate_email(email)
-                except ValidationError:
-                    email = ""
-
-            def turn_into_unicode(s):
-                if s is None:
-                    return ""
-
-                if isinstance(s, str):
-                    return s
-                else:
-                    try:
-                        return s.decode("utf-8")
-                    except UnicodeDecodeError:
-                        try:
-                            return s.decode("latin-1")
-                        except UnicodeDecodeError:
-                            return ""
-
-            name = turn_into_unicode(name)
-            email = turn_into_unicode(email)
-            company = turn_into_unicode(company)
-
-            authors.append({
-                "name": name,
-                "email": email,
-                "affiliation": company,
-                "country": country
-            })
-
-    if form.abstract:
-        abstract = form.abstract
-    else:
-        abstract = form.parsed_draft.get_abstract()
-
-    return authors, abstract, file_name, file_size
-
 
 def get_submission(form):
     # See if there is a Submission in state waiting-for-draft

ietf/utils/draft.py

@@ -194,18 +194,20 @@ def get_wordcount(self):
 
 class PlaintextDraft(Draft):
 
-    def __init__(self, text, source, name_from_source=False):
+    def __init__(self, text, source, name_from_source=False, max_line_width=100):
         """Initialize a Draft instance
 
         :param text: plaintext draft contents
         :param source: name of file containing the contents
         :param name_from_source: if True, fall back to source to determine draft name not found from text
+        :param max_line_width: (default 100) ignore contents of lines beyond this width
         """
         super().__init__()
         assert isinstance(text, str)
         self.source = str(source)
         self.rawtext = text
         self.name_from_source = name_from_source
+        self.max_line_width = max_line_width
 
         text = re.sub(".\x08", "", text)    # Get rid of inkribbon backspace-emphasis
         text = text.replace("\r\n", "\n")   # Convert DOS to unix
@@ -320,7 +322,7 @@ def begpage(pages, page, newpage, line=None):
             return pages, page, newpage
         for line in self.rawlines:
             linecount += 1
-            line = line.rstrip()
+            line = line.rstrip()[:self.max_line_width]  # source of lines used elsewhere in the class!
             if re.search(r"\[?page [0-9ivx]+\]?[ \t\f]*$", line, re.I):
                 pages, page, newpage = endpage(pages, page, newpage, line)
                 continue