Moved optional text wrapping before html escaping in markup_unicode(), used by get_unicode_document_content(). Fixes a problem with lines being wrapped when they should not be.

 - Legacy-Id: 12480

Author: levkowetz

ietf/doc/templatetags/ietf_filters.py

@@ -1,6 +1,5 @@
 # Copyright The IETF Trust 2007, All Rights Reserved
 
-import textwrap
 import re
 import datetime
 import os
@@ -11,6 +10,7 @@
 
 from ietf.doc.models import ConsensusDocEvent
 from ietf.doc.utils import get_document_content
+from ietf.utils.text import fill
 from django import template
 from django.conf import settings
 from django.utils.html import escape, fix_ampersands
@@ -164,23 +164,7 @@ def bracketpos(pos,posslug):
     else:
         return "[   ]"
 
-@register.filter(name='fill')
-def fill(text, width):
-    """Wraps each paragraph in text (a string) so every line
-    is at most width characters long, and returns a single string
-    containing the wrapped paragraph.
-    """
-    width = int(width)
-    paras = text.replace("\r\n","\n").replace("\r","\n").split("\n\n")
-    wrapped = []
-    for para in paras:
-        if para:
-            lines = para.split("\n")
-            maxlen = max([len(line) for line in lines])
-            if maxlen > width:
-                para = textwrap.fill(para, width, replace_whitespace=False)
-            wrapped.append(para)
-    return "\n\n".join(wrapped)
+register.filter('fill', fill)
 
 @register.filter(name='rfcspace')
 def rfcspace(string):

ietf/doc/utils.py

@@ -297,7 +297,7 @@ def add_events_message_info(events):
         e.in_reply_to = e.addedmessageevent.in_reply_to
 
 
-def get_unicode_document_content(key, filename, split=True, markup=True, codec='utf-8', errors='ignore'):
+def get_unicode_document_content(key, filename, split=True, markup=True, codec='utf-8', errors='ignore', width=None):
     try:
         with open(filename, 'rb') as f:
             raw_content = f.read().decode(codec,errors)
@@ -306,7 +306,7 @@ def get_unicode_document_content(key, filename, split=True, markup=True, codec='
         return error
 
     if markup:
-        return markup_txt.markup_unicode(raw_content, split)
+        return markup_txt.markup_unicode(raw_content, split, width)
     else:
         return raw_content
 

ietf/doc/views_doc.py

@@ -582,7 +582,7 @@ def document_main(request, name, rev=None):
     if doc.type_id == "review":
         basename = "{}.txt".format(doc.name, doc.rev)
         pathname = os.path.join(doc.get_file_path(), basename)
-        content = get_unicode_document_content(basename, pathname, split=False)
+        content = get_unicode_document_content(basename, pathname, split=False, width=80)
 
         review_req = ReviewRequest.objects.filter(review=doc.name).first()
 

ietf/templates/doc/document_review.html

@@ -113,6 +113,6 @@
   <h2>{{ doc.type.name }}<br><small>{{ doc.name }}</small></h2>
 
   {% if doc.rev and content != None %}
-    {{ content|fill:"80"|safe|linebreaksbr|keep_spacing|sanitize_html|safe }}
+    {{ content|safe|keep_spacing|sanitize_html|safe }}
   {% endif %}
 {% endblock %}

ietf/utils/markup_txt.py

@@ -34,7 +34,9 @@
 import string
 import re
 
-def markup(content, split=True):
+from ietf.utils.text import fill
+
+def markup(content, split=True, width=None):
     # normalize line endings to LF only
     content = content.replace("\r\n", "\n")
     content = content.replace("\r", "\n")
@@ -53,6 +55,10 @@ def markup(content, split=True):
     # remove runs of blank lines
     content = re.sub("\n\n\n+", "\n\n", content)
 
+    # maybe fill.  This must be done before the escaping below.
+    if width:
+        content = fill(content, width)
+
     # expand tabs + escape 
     content = escape(content.expandtabs())
 
@@ -72,7 +78,7 @@ def markup(content, split=True):
     else:
         return "<pre>" + content + "</pre>\n"
 
-def markup_unicode(content, split=True):
+def markup_unicode(content, split=True, width=None):
     # normalize line endings to LF only
     content = content.replace("\r\n", "\n")
     content = content.replace("\r", "\n")
@@ -82,6 +88,10 @@ def markup_unicode(content, split=True):
     # remove runs of blank lines
     content = re.sub("\n\n\n+", "\n\n", content)
 
+    # maybe fill.  This must be done before the escaping below.
+    if width:
+        content = fill(content, width)
+
     # expand tabs + escape 
     content = escape(content.expandtabs())
 

ietf/utils/text.py

@@ -2,6 +2,7 @@
 
 import re
 import unicodedata
+import textwrap
 
 from django.utils.functional import allow_lazy
 from django.utils import six
@@ -30,3 +31,21 @@ def strip_suffix(text, suffix):
         return text[:-len(suffix)]
     else:
         return text    
+
+def fill(text, width):
+    """Wraps each paragraph in text (a string) so every line
+    is at most width characters long, and returns a single string
+    containing the wrapped paragraph.
+    """
+    width = int(width)
+    paras = text.replace("\r\n","\n").replace("\r","\n").split("\n\n")
+    wrapped = []
+    for para in paras:
+        if para:
+            lines = para.split("\n")
+            maxlen = max([len(line) for line in lines])
+            if maxlen > width:
+                para = textwrap.fill(para, width, replace_whitespace=False)
+            wrapped.append(para)
+    return "\n\n".join(wrapped)
+